Wei Wang

Despite the demonstrated empirical efficacy of prompt tuning to adapt a pretrained language model for a new task, the theoretical underpinnings of the difference between" tuning parameters before the input" against" the tuning of model weights" are limited. We thus take one of the first steps to understand the role of soft-prompt tuning for transformer-based architectures. By considering a general purpose architecture, we analyze prompt tuning from the lens of both: universal approximation and limitations with finite-depth fixed-weight pretrained transformers for continuous-valued functions. Our universality result guarantees the existence of a strong transformer with a prompt to approximate any sequence-to-sequence function in the set of Lipschitz functions. The limitations of prompt tuning for limited-depth transformers are first proved by constructing a set of datasets, that cannot be memorized by a prompt of any length for a given single encoder layer. We also provide a lower bound on the required number of tunable prompt parameters and compare the result with the number of parameters required for a low-rank update (based on LoRA) for a single-layer setting. We finally extend our analysis to multi-layer settings by providing sufficient conditions under which the transformer can at best learn datasets from invertible functions only. Our theoretical claims are also corroborated by empirical results.

BACKGROUNDMany studies have explored the relationship between depression and metabolic syndrome (MetS), especially in older people. China has entered an aging society. However, there are still few studies on the elderly in Chinese communities.AIMTo investigate the incidence and risk factors of depression in MetS patients in mainland China and to construct a predictive model.METHODSData from four waves of the China Health and Retirement Longitudinal Study were selected, and middle-aged and elderly patients with MetS (n= 2533) were included based on the first wave. According to the center for epidemiological survey-depression scale (CESD), participants with MetS were divided into depression (n= 938) and non-depression groups (n= 1595), and factors related to depression were screened out. Subsequently, the 2-, 4-, and 7-year follow-up data were analyzed, and a prediction model for …

The defense of Use-After-Free (UAF) exploits generally could be guaranteed via static or dynamic analysis, however, both of which are restricted to intrinsic deficiency. The static analysis has limitations in loop handling, optimization of memory representation and constructing a satisfactory test input to cover all execution paths. While the lack of maintenance of pointer information in dynamic analysis may lead to defects that cannot accurately identify the relationship between pointers and memory. In order to successfully exploit a UAF vulnerability, attackers need to reference freed memory. However, main existing schemes barely defend all types of UAF exploits because of the incomplete check of pointers. To solve this problem, we propose UAF-GUARD to defend against the UAF exploits via fine-grained memory permission management. Specially, we design two key data structures to enable the fine-grained …

ChatGPT, an artificial intelligence (AI)-powered chatbot developed by OpenAI, is creating a buzz across all occupational sectors. Its name comes from its basis in the Generative Pretrained Transformer (GPT) language model. ChatGPT’s most promising feature is its ability to offer human-like responses to text input using deep learning techniques at a level far superior to any other AI model. Its rapid integration in various industries signals the public’s burgeoning reliance on AI technology. Thus, it is essential to critically evaluate ChatGPT’s potential impacts on academic clinical and translational medicine research.

Anchor link prediction exacerbates the risk of privacy leakage via the de-anonymization of social network data. Embedding-based methods for anchor link prediction are limited by the excessive similarity of the associated nodes in a latent feature space and the variation between latent feature spaces caused by the semantics of different networks. In this article, we propose a novel method which reduces the impact of semantic discrepancies between different networks in the latent feature space. The proposed method consists of two phases. First, graph embedding focuses on the network structural roles of nodes and increases the distinction between the associated nodes in the embedding space. Second, a federated adversarial learning framework which performs graph embedding on each social network and an adversarial learning model on the server according to the observable anchor links is used to associate …

Recently, an exciting experimental conclusion in Li et al. (Knowl Inf Syst 62(2):611–637, ) about measures of uncertainty for knowledge bases has attracted great research interest for many scholars. However, these efforts lack solid theoretical interpretations for the experimental conclusion. The main limitation of their research is that the final experimental conclusions are only derived from experiments on three datasets, which makes it still unknown whether the conclusion is universal. In our work, we first review the mathematical theories, definitions, and tools for measuring the uncertainty of knowledge bases. Then, we provide a series of rigorous theoretical proofs to reveal the reasons for the superiority of using the knowledge amount of knowledge structure to measure the uncertainty of the knowledge bases. Combining with experiment results, we verify that knowledge amount has much better performance for …

This paper investigates the attitude tracking control problem of rigid spacecraft with inertia parameter identification. Based on the relative attitude and angular velocity error dynamics, a basic adaptive backstepping based attitude tracking control scheme is firstly designed such that asymptotic attitude tracking can be achieved. However, the parameter identification error cannot decay to zero if the persistent excitation (PE) condition is not satisfied. To solve this issue, a filtering‐based concurrent learning adaptive backstepping control scheme is then proposed, by incorporating torque filtering technique with concurrent learning technique. A more mild rank condition, which consists of some collectable historical data, is provided to guarantee the convergence of parameter identification error. In addition, a valid data collection algorithm is given. It should be mentioned that a distinctive feature of the proposed filtering …

We present a deep-learning-based platform, MIND-S, for protein post-translational modification (PTM) predictions. MIND-S employs a multi-head attention and graph neural network and assembles a 15-fold ensemble model in a multi-label strategy to enable simultaneous prediction of multiple PTMs with high performance and computation efficiency. MIND-S also features an interpretation module, which provides the relevance of each amino acid for making the predictions and is validated with known motifs. The interpretation module also captures PTM patterns without any supervision. Furthermore, MIND-S enables examination of mutation effects on PTMs. We document a workflow, its applications to 26 types of PTMs of two datasets consisting of ∼50,000 proteins, and an example of MIND-S identifying a PTM-interrupting SNP with validation from biological data. We also include use case analyses of targeted …

As influencers play considerable roles in social media marketing, companies increase the budget for influencer marketing. Hiring effective influencers is crucial in social influencer marketing, but it is challenging to find the right influencers among hundreds of millions of social media users. In this paper, we propose InfluencerRank that ranks influencers by their effectiveness based on their posting behaviors and social relations over time. To represent the posting behaviors and social relations, the graph convolutional neural networks are applied to model influencers with heterogeneous networks during different historical periods. By learning the network structure with the embedded node features, InfluencerRank can derive informative representations for influencers at each period. An attentive recurrent neural network finally distinguishes highly effective influencers from other influencers by capturing the knowledge of the dynamics of influencer representations over time. Extensive experiments have been conducted on an Instagram dataset that consists of 18,397 influencers with their 2,952,075 posts published within 12 months. The experimental results demonstrate that InfluencerRank outperforms existing baseline methods. An in-depth analysis further reveals that all of our proposed features and model components are beneficial to discover effective influencers.

Manufacturing data analytics tasks are traditionally undertaken with Mechanism Models (MMs), which are domain-specific mathematical equations modeling the underlying physical or chemical processes of the tasks. Recently, Deep Learning (DL) has been increasingly applied to manufacturing. MMs and DL have their individual pros and cons, motivating the development of Mechanism-guided Deep Learning Models (MDLMs) that combine the two. Existing MDLMs are often tailored to specific tasks or types of MMs, and can fail to effectively 1) utilize interconnections of multiple input examples, 2) adaptively self-correct prediction errors with error bounding, and 3) ensemble multiple MMs. In this work, we propose a generic, task-agnostic MDLM framework that can embed one or more MMs in deep networks, and address the 3 aforementioned issues. We present 2 diverse use cases where we experimentally …

An adjustable bed includes a bed frame supporting a plurality of platforms having at least a head platform and a back platform, a back lifting assembly, a foot lifting assembly, a base frame pivotally and detachably connected to the bed frame, a bed frame tilting actuator pivotally connected to the bed frame and the base frame for operably adjusting the bed frame from the horizontal position to the sloping position relative to the base frame, or vice versa. The adjustable bed also includes a head platform tilting actuator pivotally connected to the head platform and the back platform for operably adjusting the head platform in a tilting position or a flat position relative to the back platform.

There are a large number of solutions for big data processing in the Internet of Things (IoT) environments, among which the IoT cloud infrastructure is one of the most mature solutions. Typically, modern IoT cloud infrastructures have different kinds of configuration options. The diversity of configurations leads to frequent software configuration errors. Generally, troubleshooting configuration errors relies on finding the mapping relationship between configuration options in the documents (e.g., official manuals) and their read sites in the source code. Most current works still manually extract configuration read sites. Automated methods are not always interchangeable and they incur considerable time overheads and low extraction rates.In this paper, we propose CRSExtractor, an automatic technique for extracting configuration read sites based on intra-procedural analysis. Using our technique, configuration option read …

Automated driving systems (ADSs) conceive an efficient and safe way of driving. The safety of ADSs depends on a precise object detector that needs to be upgraded continuously facing various environments. Massive annotations are required to utilize collected images of surroundings through vehicles and accommodate new environments. Auto labelling is one approach to alleviate such dilemma. To this end, we propose a novel Weakly Supervised Object Localization (WSOL) method which can localize objects precisely without detection annotations. This paper proposed Soft Guidance Module (SGM), Channel Erasing Module (CEM) and incorporate them into a multi-flow framework allowing the two mutually beneficial. Finally, experiments and visualizations are performed to evaluate our method on Stanford Cars, ILSVRC 2016 and CUB-200-2011 datasets.

Diabetic retinopathy (DR) is a complication of diabetic patients and a significant cause of blindness globally among the working population (Antonetti et al., 2021). There are 451 million suffering from DR in the world, and this is projected to increase to 639 million in 2045 (Cho et al., 2018). In diabetics, blood is provided to all retina layers through micro blood vessels that are sensitive to unrestricted blood sugar levels. DR may cause no symptoms or only mild vision problems at first, but it can cause blindness eventually. When substantial glucose or fructose is collected in the blood, blood vessels begin to collapse due to insufficient oxygen supply to the cells. Occlusion in these blood vessels can cause serious eye damage. As a result, metabolic rate decreases, and abnormal blood vessels accumulate in DR (Dai et al., 2021). Microaneurysms (MAs) are the early signs of DR, which

PurposeTo describe an artificial intelligence platform that detects thyroid eye disease (TED).DesignDevelopment of a deep learning model.Methods1944 photographs from a clinical database were used to train a deep learning model. 344 additional images (‘test set’) were used to calculate performance metrics. Receiver operating characteristic, precision–recall curves and heatmaps were generated. From the test set, 50 images were randomly selected (‘survey set’) and used to compare model performance with ophthalmologist performance. 222 images obtained from a separate clinical database were used to assess model recall and to quantitate model performance with respect to disease stage and grade.ResultsThe model achieved test set accuracy of 89.2%, specificity 86.9%, recall 93.4%, precision 79.7% and an F1 score of 86.0%. Heatmaps demonstrated that the model identified pixels corresponding to …

Structure prediction tasks such as event extraction require an in-depth understanding of the output structure and sub-task dependencies, thus they still heavily rely on task-specific training data to obtain reasonable performance. Due to the high cost of human annotation, low-resource event extraction, which requires minimal human cost, is urgently needed in real-world information extraction applications. We propose to synthesize data instances given limited seed demonstrations to boost low-resource event extraction performance. We propose STAR, a structure-to-text data generation method that first generates complicated event structures (Y) and then generates input passages (X), all with Large Language Models. We design fine-grained step-by-step instructions and the error cases and quality issues identified through self-reflection can be self-refined. Our experiments indicate that data generated by STAR can significantly improve the low-resource event extraction performance and they are even more effective than human-curated data points in some cases.

There are four equally important major building blocks of life: nucleic acids (DNA and RNA), proteins, carbohydrates (glycans), and lipids. The first two are also known as the first and second alphabets of biology, following the principle of the ‘‘central dogma” of transcription (DNA to RNA) and translation (RNA to protein). However, the latter two crucial components, glycans and lipids, are missing from biology’s central dogma. Regarding the communication between glycans and lipids, there may be a yet-to-bediscovered law: Does a paracentral dogma exist? This commentary focuses on glycans, the third alphabet of life, and their role in the sociomateriality of the cell, which provides a novel dimension of medical science—glycomedicine. This is an allied new discipline that employs glycomics approaches with the aim of better targeting disease diagnostics, as well as drug discovery, prescription choice, and dosing …

As a primary goal of predictive analytics, uplift modeling is used to estimate what impact a specific action or treatment will have on an outcome. In convention, the treatment is evaluated as a success once the buyer has purchased following the treatment, regardless of the kinds of treatments and the corresponding cost. Obviously, it cannot be classified as a binary classification problem. Therefore, we extend the ordinary uplift model to support multi-treatments tasks. In order to reconcile this aspect of interpretability with tree-based models, we use random forest (RF) as our base model. We present Gross Merchandise Value (GMV)-based RF for uplift modeling (GRFlift): an uplift model, where typical commercial evaluation GMV is designed as novel tree splitting criteria to directly quantify the uplift achievement. A targeted regularization term is also designed to adjust the splitting distribution differences. The splitting …

This paper considers the one-way trading problem with fixed costs where the trader can only trade in one direction throughout, either sell or buy, and he only knows limited information on price fluctuations beforehand. We construct a robust optimization model based on Savage's regret criterion, in order to find the online trading policy that minimizes the worst-case regret. However, it is very difficult to obtain analytical results if the trading horizon is relatively long, due to the discontinuity in the trader's objective function caused by the fixed cost. Thus we propose to solve the alternative problem with prepaid trading opportunities, which is not only a satisfactory approximation of the original one, but also a realistic problem with many practical applications, such as in the stock or future market. The optimal online trading policy of the new problem can be easily found based on the existing results of the one-way trading …

A47C31/00—Details or accessories for chairs, beds, or the like, not provided for in other groups of this subclass, eg upholstery fasteners, mattress protectors, stretching devices for mattress nets

Hypergraph networks are closer to real life because they can reflect higher-order interactions, so researchers have begun using them to build models for real-world networks. The mean-field approach is the current tool for studying the percolation problem on hypergraph networks. However, we found that when there is a loop in the hypergraph network, the calculated results using this approach deviate from the real results. Therefore, in this paper, we rephrase the percolation on the hypergraph network as a message passing process, thus obtaining a message passing approach. Our proposed approach has been tested in several hypergraph networks with loops, and the experimental results are more accurate than those under the mean-field approach. This is helpful to analyze and understand the robustness of hypergraph networks with loops. In addition, we also specifically analyzed how four different types of loops affect the accuracy of the experiment. Our proposed message passing approach also provides another way to study percolation on hypergraph networks.

Wireless body area networks (WBANs) have been deployed in numerous applications, where the most common communication technology is Bluetooth. Bluetooth uses the numeric comparison protocol (NCP) to negotiate session keys based on the elliptic curve cryptography (ECC) and Out-of-Band (OoB) channels. However, the scalar multiplication of ECC is a heavy computing operation for devices in WBANs. To address this issue, we propose the lightweight and secure NCP (LSNCP) which requires less scalar multiplication than the NCP in Bluetooth. New logic expressions and rules are proposed to verify the security of LSNCP in GNY logic. The proof shows that LSNCP is secure. We conduct a provable security analysis by integrating the commitment scheme and short hash function. The result shows that LSNCP is secure in the modified Bellare–Rogaway model. Finally, we conduct theoretical analysis and …

In recent years, the research of multilayer interdependent networks has become a hotspot in complex networks. However, most of the study is limited to describing pairwise interactions. The systems in the real world are usually networks with higher-order interactions consisting of three or more units, such as epidemic transmission and cooperative communication networks. To better reflect the complex networks in the real world, this paper introduces the higher-order structures in the network, that is, simplicial complexes. In this paper, we construct a theoretical model of a two-layer partial dependence network with simplicial complexes in which failures between nodes occur through the synergistic effects of pairwise and higher-order interactions. In this model, removing a node will cause all other nodes in the same simplex to be removed, and due to the dependency between the two networks, the failure of the node …

Ketodeoxynononic acid (Kdn) is a rather uncommon class of sialic acid in mammals. However, associations have been found between elevated concentrations of free or conjugated Kdn in relation to human cancer progression. Hitherto, there has been a lack of conclusive evidence that Kdn occurs on (specific) human glycoproteins (conjugated Kdn). Here, we report for the first time that Kdn is expressed on prostate-specific antigen (PSA) N-linked glycans derived from human seminal plasma and urine. Interestingly, Kdn was found only in an α2,3-linkage configuration on an antennary galactose, indicating a highly specific biosynthesis. This unusual glycosylation feature was also identified in a urinary PSA cohort in relation to prostate cancer (PCa), although no differences were found between PCa and non-PCa patients. Further research is needed to investigate the occurrence, biosynthesis, biological role, and …

The hydroxyl (OH), hydroperoxy (HO, and organic peroxy (RO radicals play important roles in atmospheric chemistry. In the presence of nitrogen oxides (NO, reactions between OH and volatile organic compounds (VOCs) can initiate a radical propagation cycle that leads to the production of ozone and secondary organic aerosols. Previous measurements of these radicals under low-NO conditions in forested environments characterized by emissions of biogenic VOCs, including isoprene and monoterpenes, have shown discrepancies with modeled concentrations. During the summer of 2016, OH, HO, and RO radical concentrations were measured as part of the Program for Research on Oxidants: Photochemistry, Emissions, and Transport – Atmospheric Measurements of Oxidants in Summer (PROPHET-AMOS) campaign in a midlatitude deciduous broadleaf forest. Measurements of OH and HO were made by laser-induced fluorescence–fluorescence assay by gas expansion (LIF-FAGE) techniques, and total peroxy radical (XO mixing ratios were measured by the Ethane CHemical AMPlifier (ECHAMP) instrument. Supporting measurements of photolysis frequencies, VOCs, NO, O, and meteorological data were used to constrain a zero-dimensional box model utilizing either the Regional Atmospheric Chemical Mechanism (RACM2) or the Master Chemical Mechanism (MCM). Model simulations tested the influence of HO regeneration reactions within the isoprene oxidation scheme from the Leuven Isoprene Mechanism (LIM1). On average, the LIM1 models overestimated daytime maximum measurements by approximately 40 % for OH, 65 % for HO …

Certain aspects of the present disclosure provide techniques for vectorization of transactions including: receiving electronic transaction information of one or more transactions of a user; for each transaction of the one or more transactions: segmenting the electronic transaction information of the transaction into one or more transaction words; generating a second transaction description related to the transaction; and identifying a category of the transaction; generating, based on the corresponding identified categories of the one or more transactions, a set of transaction history data of the user; providing the set of transaction history data of the user as an input to a machine learned model trained to output a set of word embedding vectors; determining, based on an output of the machine learned model comprising a set of word embedding vectors, a set of similar merchants; and providing the set of similar merchants for …

Transferring facial pose and expression features from one face to another is a challenging problem and an interesting topic in pattern recognition, but is one of great importance with many applications. However, existing models usually learn to transfer pose and expression features with classification labels, which cannot hold all the differences in shape and size between conditional faces and source faces. To solve this problem, we propose a generative adversarial network model based on classification features for facial pose and facial expression transfer. We constructed a two-stage classifier to capture the high-dimensional classification features for each face first. Then, the proposed generation model attempts to transfer pose and expression features with classification features. In addition, we successfully combined two cost functions with different convergence speeds to learn pose and expression features. Compared to state-of-the-art models, the proposed model achieved leading scores for facial pose and expression transfer on two datasets.

In this paper, a push-sum based distributed delayed dual averaging algorithm (PS-DDDA) is proposed to solve the distributed constrained optimization problem over the time-varying unbalanced directed graph (digraph). It considers the scenario in which each agent has delays while calculating the gradients and communicating. Both delays are assumed to be time-varying but bounded, which are more common in practice. Furthermore, we demonstrate that the cost function at the local state average converges to the optimal value and the local state average converges to the consensus with a rate of O (1/T) by utilizing the diminishing step size, where T is the total number of iterations. Moreover, to solve the distributed online constrained optimization problem, we propose the online version of PS-DDDA, and prove that its regret bound increases sublinearly with a rate of O (T). Finally, the effectiveness of the proposed …

Spectral–spatial features are important for ground target identification and classification with high spatial resolution remotely sensed (HSRRS) Imagery. In this article, two novel features, named the Gaussian-weighting spectral (GWS) feature and the area shape index (ASI) feature, are proposed to complement the deficiency of the basic image feature for land cover classification with HSRRS imagery. The proposed GWS feature is an adaptive region-based feature that aims to improve the spectral homogeneity of a local area surrounding a pixel. Additionally, it is well known that the spectral feature is inadequate for classifying HSRRS imagery. Therefore, one spatial feature called the ASI feature is proposed here to describe the relationship between the area and shape for an adaptive region around each pixel. The proposed GWS and ASI features coupled with the basic red–green–blue (RGB) feature are fed into a …

Few-shot question answering (QA) aims at precisely discovering answers to a set of questions from context passages while only a few training samples are available. Although existing studies have made some progress and can usually achieve proper results, they suffer from understanding deep semantics for reasoning out the questions. In this paper, we develop Gotta, a Generative prOmpT-based da Ta Augmentation framework to mitigate the challenge above. Inspired by the human reasoning process, we propose to integrate the cloze task to enhance few-shot QA learning. Following the recent success of prompt-tuning, we present the cloze task in the same format as the main QA task, allowing the model to learn both tasks seamlessly together to fully take advantage of the power of prompt-tuning. Extensive experiments on widely used benchmarks demonstrate that Gotta consistently outperforms competitive …

This article addresses the distributed consensus filtering problem of heterogeneous multienergy networks, where subnetworks exhibit different dynamics and are coupled by output constraints. The global consensus is reached by propagating constraints between subnetworks in the form of interval vectors. Guaranteed intervals satisfying given constraints are returned, which are then used to correct the local states through the probability density function truncation. Given the dependence and wrapping effects during constraint propagation, a hybrid Newton forward–backward propagation (FBP) contractor is proposed for avoiding overly pessimistic estimates. It extends the FBP contractor by replacing the natural inclusion function with centered forms. In addition, an event-triggered mechanism is designed to enhance the efficiency of constraint propagation, which allows the threshold values to be adaptively adjusted …

Gathering events, e.g., going to gyms and meetings, are ubiquitous and crucial in the spreading phenomena, which induce higher-order interactions, and thus can be described as higher-order networks. Previous studies on the coevolution of epidemic-infodemic dynamics ignored the higher-order interactions in the social system, which affects our understanding of the reality spreading. We propose a mathematical framework for the coevolution of epidemic and infodemic on higher-order networks described by simplicial complex, and introduce the Microscopic Markov Chain Approach (MMCA) and mean-field approach to establish the dynamic process. We study the coevolution mathematical model on both artificial simplicial complex and real-world higher-order networks and find that the higher-order interactions show a ’double-edged sword’ role in shaping epidemic size, which is dependent on the breakout of …

A47C31/00—Details or accessories for chairs, beds, or the like, not provided for in other groups of this subclass, eg upholstery fasteners, mattress protectors, stretching devices for mattress nets

In an open Internet-of-Things (IoT) environment, cloud-device collaborative development brings more functional services to users. However, privacy disclosure risks concerning service provision and users’ accessing behavior also increase. Traditional privacy protection approaches involve a centralized system with a third-party administrative server, which has the risk of single-point failures and overlooks the issue of privacy information leakage concerning users’ behaviors. Blockchain is a decentralized and traceable technology that provides a reliable solution for secure access by users. This paper proposes a novel blockchain-based secure access framework (BSAF) for cloud-device service collaborations with privacy protection. Specifically, a key matrix encryption mechanism is used to protect the privacy of users’ behaviors, and a fully homomorphic encryption mechanism is designed to protect the privacy of …

An adjustable bed includes a frame structure; a plurality of platforms disposed on the frame structure; and an adjustable assembly coupled with the frame structure and the plurality of platforms for operably adjusting one or more of the plurality of platforms in desired positions; and an aromatherapy system attached onto the one or more platforms for producing desired fragrance in a surrounding space of the adjustable bed so as to promote health and well-being of a user. Each aromatherapy device is configured to produce a fragrance when said aromatherapy device is turned on, and one or more working modes. The fragrance is identical to or different from that produced by other aromatherapy device of the one or more aromatherapy devices.

Certain aspects of the present disclosure provide techniques for generating a human readable summary explanation to a user for an outcome generated by a complex machine learning model. In one embodiment, a risk assessment service can receive a request from a user in which a risk model of the risk assessment service performs a specific task (eg, determining the level of risk associated with the user). Once the risk model determines the risk associated with the user, in order to comply with regulations from a compliance system, the risk model can provide a user with an explanation as to the outcome for transparency purposes.

Since its appearance in May 2022, monkeypox has spread to> 100 countries and afflicted tens of thousands of people. Individuals infected with monkeypox present a fever, an extensive characteristic rash, and usually swollen lymph nodes (Chatterjee e t al., 2022). The number of confirmed cases worldwide continues to grow at a rapid rate, but the treatment to this highly infectious viral disease is still very limited. Identification of new targeted-therapies will be crucial to control of this emerging public health threat.The monkeypox virus is an enveloped double-stranded DNA virus that belongs to the Orthopoxvirus genus of the Poxviridae family (Isidro et al., 2022). It has a very large genome (~ 200 kb) and codes around 200 proteins (Kugelman et al., 2014). Poxviruses express a dual specific phosphatase (H1) that de-phosphorylates signal transducer and activator of transcription 1 (STAT1) and blocks interferon signal …

The present disclosure discloses a method for predicting oxygen load in iron and steel enterprises based on production plan, which relates to influencing factor extraction, neural network modeling and similar sequence matching technologies. The method uses the actual industrial operation data to first extract the relevant data such as the production plan and production performance of converter steel-making, analyze the influencing factors, and extract the main influencing variables of oxygen consumption. Then, the neural network prediction model of oxygen consumption of a single converter is established, the mean square error is taken as the evaluation index, and the predicting result of time granularity of a converter in the blowing stage is given. Finally, in combination with the information of smelting time and smelting duration of each device in the converter production plan, the prediction value of oxygen load in …

With the emergence of multisource data and the development of cloud computing platforms, accurate prediction of event-scale dust source regions based on machine learning (ML) methods should be considered, especially accounting for the temporal variability in sample and predictor variables. Arid Central Asia (ACA) is recognized as one of the world’s primary potential sand and dust storm (SDS) sources. In this study, based on the Google Earth Engine (GEE) platform, four ML methods were used for SDS source prediction in ACA. Fourteen meteorological and terrestrial factors were selected as influencing factors controlling SDS source susceptibility and applied in the modeling process. Generally, the results revealed that the random forest (RF) algorithm performed best, followed by the gradient boosting tree (GBT), maximum entropy (MaxEnt) model and support vector machine (SVM). The Gini impurity index …

Lice are six-legged, wingless, insect parasites of mammals and birds, and include two main functional groups: blood-sucking lice and chewing lice. However, it is still not clear whether the Chinese red panda Ailurus styani is infested with the parasitic louse. In the present study, we describe a new genus and a species of chewing louse, Pancola ailurus (Phthiraptera: Trichodectidae) based on morphological and molecular datasets. The morphological features showed that Pancola is closer to Paratrichodectes. The genetic divergence of cox1 and 12S rRNA among the Pancola ailurus n. sp. and other Trichodectidae lice was 29.7 – 34.6% and 38.9 – 43.6%, respectively. Phylogenetic analyses based on the available mitochondrial gene sequences showed that P. ailurus n. sp. is more closely related to Trichodectes canis and Geomydoecus aurei than to Felicola subrostratus and together nested within the family …

In this paper, the fault-tolerant control (FTC) problem for a class of nonlinear systems with uncertain parameters and unknown actuator failures is studied. The considered failure number of times is not limited to be finite, and the input-to-state stable assumption is no longer needed. An adaptive FTC scheme is proposed based on event-triggered strategy. A set of event-triggering conditions are designed for not only the controller but also the parameter estimators, with which the parameter estimator-to-controller and controller-to-actuator channels are both event-triggered simultaneously. It is proved that, with our proposed scheme, all the closed-loop signals are globally uniformly bounded, and the system output converges into a compact set which can be made small by appropriately adjusting the design parameters. Also, the Zeno behavior is proved to be excluded. Besides, a modified FTC scheme is designed for the …

While vulnerability databases are important sources of information for software security, it is known that information in these databases is inconsistent. How to rectify these incorrect data is a challenging issue. In this paper, we employ developer logs and patches to automatically identify vulnerable source code versions that each CVE really affects. Our tool organizes all versions of a piece of software into a version tree, and identifies the first vulnerable version, and the last vulnerable versions in the version tree trunk and branches. For evaluation, we took Linux Kernel as the case study and quantified the error rate of the vulnerable versions reported by the NVD. The total number of vulnerable Linux Kernel versions reported by the NVD was 43,727 (as of September 2020), of which the total number of false positives reached 2,497 and the total number of false negatives reached 9,330, accounting for 5.7% and 21.34 …

Adequately choosing the physicochemical characteristics of adsorbent is crucial in improving its adsorption performance. This work investigated the effect of particle size of magnetic resins on adsorption behaviors of tetracycline (TC) and their antifouling performance. Smaller particle size resin Q150 (10–30 μm) shows notably faster TC adsorption kinetics when compared resins with hundreds of microns (Q100 and Q1). Simulated by Weber-Morris equation, the film diffusion time of Q150 was only 20 min, 2–25 times faster than that of other resins. At this adsorption time, Q150 can reach more than 80% of the maximum adsorption, and the ring-like fluorescence images indicate that the molecules are accumulated on the external surface. Q150 also shows better reusability and antifouling performance over Q100 and Q1. After 20 adsorption–desorption cycles, the adsorption capacity of Q150 at 20 min only decreases 9 …

In this article, an adaptive fuzzy fixed-time fault-tolerant tracking control problem for high-order nonlinear systems (HONSs) with sensor and actuator faults is considered. The fuzzy logic systems are introduced to approximate the unknown nonlinear functions of the HONS. In addition, based on backstepping technology and fixed-time theory, an adaptive fuzzy fixed-time fault-tolerant controller is developed to ensure that all the signals of the closed-loop HONS are bounded. Eventually, a numerical example can be shown to prove the rationality of the developed method

G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

When public health emergencies occur, a large amount of low-credibility information is widely disseminated by social bots, and public sentiment is easily manipulated by social bots, which may pose a potential threat to the public opinion ecology of social media. Therefore, exploring how social bots affect the mechanism of information diffusion in social networks is a key strategy for network governance. This study combines machine learning methods and causal regression methods to explore how social bots influence information diffusion in social networks with theoretical support. Specifically, combining stakeholder perspective and emotional contagion theory, we proposed several questions and hypotheses to investigate the influence of social bots. Then, the study obtained 144,314 pieces of public opinion data related to COVID-19 in J city from March 1, 2022, to April 18, 2022, on Weibo, and selected 185,782 …

An elastic base structure and a piece of upholstered furniture therewith. The elastic base structure includes a base frame comprising a pair of first support rods and a pair of second support rods connected to the pair of first support rod to form a square or rectangular structure; a plurality of serpentine springs; and a plurality of double-branched hook clips. Each serpentine spring has two oppose ends disconnectably connected to two double-branched hook clips that are in turn disconnectably connected to the pair of first support rods, respectively, such that the plurality of serpentine springs are parallel to each other.

An adjustable bed includes a head frame assembly, a first slidable assembly having a slidable assembly base and slidable assembly sides slidable within lower C steel brackets; head lift arm bracket assemblies pivotally connected to the slidable assembly sides; and a head lift platform mounted on the head lift arm bracket assemblies, an upper seat platform mounted on the first slidable assembly, and a lower seat platform movably attached onto the higher C steel bracket; a second slidable assembly with a spacing bracket having a guiding slot mounted on the slidable assembly base and the fixing bracket being mounted on the lower seat platform, and the connecting bolt mounted on the fixing bracket and received in the guiding slot; and a head lift motor secured to the head frame assembly for operably driving the head lift arm bracket assemblies in head lift forward or backward direction.

A smart bed body structure includes: a bed body, a control unit, a speech recognition unit and an audio device. The control unit is electrically connected with the speech recognition unit; the speech recognition unit is electrically connected with the audio device. The bed body includes: a load-bearing mechanism, at least one turnover mechanism and a base. The control unit and the audio device are arranged on the bottom face of the load-bearing mechanism. The load-bearing mechanism is arranged on the top face of the base, the turnover mechanisms being arranged between the load-bearing mechanism and the base, the load-bearing mechanism can be upwards turned over relative to the base by means of the turnover mechanisms. The control unit is electrically connected with the turnover mechanisms.

The majority of image-to-image translation models tend to struggle in varying domain settings. For one varying domain, samples vary significantly in shape and size and have no domain labels. This paper proposes an unsupervised class-to-class translation model based on conditional contrastive learning to tackle the domain variations problem. The initial hypothesis is that the latent modalities of two varying domains are categorizable by style differences of different samples and turn the image-to-image translation problem into class-to-class translation. Firstly, unsupervised semantic clustering is performed for each domain to divide them into multiple classes and then leverage the classification features of different classes to perform class-to-class translation. Two conditional contrastive learning loss functions for each domain are proposed to perform unsupervised semantic clustering and decompose it into multiple …

Knowledge resources, e.g. knowledge graphs, which formally represent essential semantics and information for logic inference and reasoning, can compensate for the unawareness nature of many natural language processing techniques based on deep neural networks. This paper provides a focused review of the emerging but intriguing topic that fuses quality external knowledge resources in improving the performance of natural language processing tasks. Existing methods and techniques are summarised in three main categories: (1) static word embeddings, (2) sentence-level deep learning models, and (3) contextualised language representation models, depending on when, how and where external knowledge is fused into the underlying learning models. We focus on the solutions to mitigate two issues: knowledge inclusion and inconsistency between language and knowledge. Details on the design of each …

The integrity of industrial data is of great significance to the related technology research in the industrial field. Aiming at the problem of high missing rate of time series data in industrial system, a multi-feature generation network-based imputation algorithm is proposed in this paper, which combines variational autoencoder with generative adversarial network and transforms industrial data sequence into Gaussian mixture distribution. In order to realize data imputation by using the generation idea, a reconstruction loss function is combined to the objective function in the model, and the generated sequence not only satisfies the target distribution, but also matches the target sequence. Considering the multi-scale characteristics of industrial data, a multi-feature generation method for imputation is designed, which decomposes the data into multi-scale series and imputes the subsequences under multiple time scales …

3D point clouds are a crucial type of data collected by LiDAR sensors and widely used in transportation applications due to its concise descriptions and accurate localization. Deep neural networks (DNNs) have achieved remarkable success in processing large amount of disordered and sparse 3D point clouds, especially in various computer vision tasks, such as pedestrian detection and vehicle recognition. Among all the learning paradigms, Self-Supervised Learning (SSL), an unsupervised training paradigm that mines effective information from the data itself, is considered as an essential solution to solve the time-consuming and labor-intensive data labelling problems via smart pre-training task design. This paper provides a comprehensive survey of recent advances on SSL for point clouds. We first present an innovative taxonomy, categorizing the existing SSL methods into four broad categories based on the …

Industrial time series data usually have a high noise. In this paper, an echo state network (ESN) model with input noise is proposed to address the problem of predicting time series with noise. In the ESN, the introduction of the input noise makes it difficult to accurately estimate the non-linear states of the dynamical reservoir, therefore, in this study, the states are approximated by linearizing it through an extended Kalman filter (EKF). For the learning of the model parameters, the expectation maximization algorithm (EM) is used to iteratively update all the uncertain parameters to construct the prediction intervals, where the state estimation is performed using a forward back algorithm. To verify the effectiveness of the proposed method, two benchmark data sets and three real gas data sets from steel enterprises are used in this paper. Experimental results show that the prediction accuracy of the proposed method is better …

While classical laboratory and animal data have long established cannabinoid genotoxicity, it is only recently, with the application of modern analytical techniques, that the scale of epidemiological disease that may be attributable to cannabinoid exposure has been revealed. The importance and urgency of this work is heightened by the increased cannabis use that is accompanying the relaxation of legislation around cannabis use in many places, the widespread global movement toward cannabis legalization, and the general increase in the cannabinoid potency of available strains. Building on an original pathfinding epidemiological study of congenital anomalies in Hawaii, the United States [1] and confirmed by similar findings from Colorado in the United States, Canada, and Australia [2],[3],[4], contemporary studies in the United States and Europe have found that 46/62 and 90/95 congenital anomalies [5],[6 …

The pathogen diversity means that multiple strains coexist, and widely exist in the biology systems. The new mutation of SARS-CoV-2 leading to worldwide pathogen diversity is a typical example. What are the main factors of inducing the pathogen diversity? Previous studies indicated the pathogen mutation is the most important reason for inducing the pathogen diversity. The traffic network and gene network are crucial in shaping the dynamics of pathogen contagion, while their roles for the pathogen diversity still lacking a theoretical study. To this end, we propose a reaction–diffusion process of pathogens with mutations on meta-population networks, which includes population movement and strain mutation. We extend the Microscopic Markov Chain Approach (MMCA) to describe the model. Traffic networks make pathogen diversity more likely to occur in cities with lower infection densities. The likelihood of …

Epidemic spreading dynamic is usually used to describe the virus spread in the biology system and information diffusion in the social system. Previous studies indicated that multiple epidemics rarely evolve dependently, but constantly interact and coevolve. In this paper, a novel mathematical model is proposed to study the link cooperation effect of two epidemics cooperatively spreading on complex networks. The link cooperation effect means that the first epidemic is transmitted through this link, and the second epidemic will have a higher transmission probability when it is transmitted through the same link. We develop an edge-based compartmental method and can well predict the numerical simulations. We find the link cooperation effect promote the epidemic outbreak size. The phase transition is closely relates to the strength of the link cooperation effect and network topology. For the cooperate epidemics on ER …

During HIV-1 assembly, two copies of viral genomic RNAs (gRNAs) are selectively packaged into new viral particles. This process is mediated by specific interactions between HIV-1 Gag and the packaging signals at the 5′ leader (5′L) of viral gRNA. 5′L is able to adopt different conformations, which promotes either gRNA dimerization and packaging or Gag translation. Dimerization and packaging are coupled. Whether the selective packaging of the gRNA dimer is due to favorable interactions between Gag and 5′L in the packaging conformation is not known. Here, using RNAs mimicking the two 5′L conformers, we show that the 5′L conformation dramatically affects Gag–RNA interactions. Compared to the RNA in the translation conformation (5′LT), the RNA in the packaging conformation (5′LP) can bind more Gag molecules. Gag associates with 5′LP faster than it binds to 5′LT, whereas Gag …

Nodes usually cooperate to form groups and survive or fail in real-world systems. Researchers typically consider the interdependence between node groups in studying the interdependent network. This paper studies the robustness of interdependent hypergraph networks under different attack strategies. According to the characteristics of the network model, we propose a series of target attack strategies and compare the destructive effect of these strategies on the network. Second, we analyze the impact of the random edge removal strategy on the robustness of hypergraph networks under different edge removal ratios. Finally, we propose four target-node edge removal strategies and compare their destructive effects on the network at the same edge removal ratios. Simulation results show that target attack and edge removal strategies can appreciably reduce the robustness of interdependent hypergraph networks …

Commonsense knowledge is a crucial resource to help the machine understand the human world. However, the conventional methods of extracting commonsense knowledge with isA relation (or isA commonsense knowledge) from text corpora generally do not work well since commonsense knowledge is typically omitted in communication. In this paper, we mainly focus on the inference of isA commonsense knowledge (the definition of isA here to express a hypernym-hyponym relationship and we concentrate on whether the description of (s, isA, o) is correct based on this relationship, e.g., (mammal, isA, animal), (Hello Kitty, isA, cat)) with a special kind of knowledge graph: lexical taxonomy. Lexical and semantic features of terms are both extracted from three relationships including exclusive, compatible, andinclusive relationships then a simple but effective classification model is further utilized to predict whether …

Data series indexes are necessary for managing and analyzing the increasing amounts of data series collections that are nowadays available. These indexes support both exact and approximate similarity search, with approximate search providing high-quality results within milliseconds, which makes it very attractive for certain modern applications. Reducing the pre-processing (i.e., index building) time and improving the accuracy of search results are two major challenges. DSTree and the iSAX index family are state-of-the-art solutions for this problem. However, DSTree suffers from long index building times, while iSAX suffers from low search accuracy. In this paper, we identify two problems of the iSAX index family that adversely affect the overall performance. First, we observe the presence of a proximity-compactness trade-off related to the index structure design (i.e., the node fanout degree), significantly limiting …

An optimal energy scheduling strategy for integrated energy systems (IESs) can effectively improve the energy utilization efficiency and reduce carbon emissions. Due to the large-scale state space of IES caused by uncertain factors, it would be beneficial for the model training process to formulate a reasonable state-space representation. Thus, a condition knowledge representation and feedback learning framework based on contrastive reinforcement learning is designed in this study. Considering that different state conditions would bring inconsistent daily economic costs, a dynamic optimization model based on deterministic deep policy gradient is established, so that the condition samples can be partitioned according to the preoptimized daily costs. In order to represent the overall conditions on a daily basis and constrain the uncertain states in the IES environment, the state-space representation is constructed by …

Are Federated Learning (FL) systems free from backdoor poisoning with the arsenal of various defense strategies deployed? This is an intriguing problem with significant practical implications regarding the utility of FL services. Despite the recent flourish of poisoning-resilient FL methods, our study shows that carefully tuning the collusion between malicious participants can minimize the trigger-induced bias of the poisoned local model from the poison-free one, which plays the key role in delivering stealthy backdoor attacks and circumventing a wide spectrum of state-of-the-art defense methods in FL. In our work, we instantiate the attack strategy by proposing a distributed backdoor attack method, namely Cerberus Poisoning (CerP). It jointly tunes the backdoor trigger and controls the poisoned model changes on each malicious participant to achieve a stealthy yet successful backdoor attack against a wide spectrum of defensive mechanisms of federated learning techniques. Our extensive study on 3 large-scale benchmark datasets and 13 mainstream defensive mechanisms confirms that Cerberus Poisoning raises a significantly severe threat to the integrity and security of federated learning practices, regardless of the flourish of robust Federated Learning methods.

The domestic pig louse Haematopinus suis (Linnaeus, 1758) (Phthiraptera: Anoplura) is a common ectoparasite of domestic pigs, which can act as a vector of various infectious disease agents. Despite its significance, the molecular genetics, biology and systematics of H. suis from China have not been studied in detail. In the present study, the entire mitochondrial (mt) genome of H. suis isolate from China was sequenced and compared with that of H. suis isolate from Australia. We identified 37 mt genes located on nine circular mt minichromosomes, 2.9 kb-4.2 kb in size, each containing 2-8 genes and one large non-coding region (NCR) (1,957 bp-2,226 bp). The number of minichromosomes, gene content, and gene order in H. suis isolates from China and Australia are identical. Total sequence identity across coding regions was 96.3% between H. suis isolates from China and Australia. For the 13 protein-coding …

Anchor link prediction across social networks is highly important for multiple social network analysis. Traditional methods rely heavily on user-generated information or the quality of network topology information and are not suitable for real-life multiple social networks. Deep learning methods based on graph embedding are limited by the latent similarity of the associated nodes in a single network and the overlap between different networks used for projections of multiple network feature spaces. In this paper, we propose a novel method which eliminates overlapping restriction. The proposed method consists of two phases. First, graph embedding with reconciliation of similarity and distinction is used to obtain an effective embedding vector space. Second, cross-network features for supervised learning are constructed via cross-network feature mining based on collisions between the features of nodes belonging to …

A method may include obtaining a cluster. The cluster may include a subset of reference entities. The method may further include calculating distances between features of a target entity and features of the subset of reference entities, selecting, based on the distances, peer entities from the subset, and generating an estimated value of a metric. The generating may include applying, to the features of the target entity, a machine learning model trained using training data including values of the features for the peer entities labeled with a value of the metric. The method may further include presenting the estimated value of the metric.

Open Source Software (OSS) is forming the spines of technology infrastructures, attracting millions of talents to contribute. Notably, it is challenging and critical to consider both the developers’ interests and the semantic features of the project code to recommend appropriate development tasks to OSS developers. In this paper, we formulate the novel problem of code recommendation, whose purpose is to predict the future contribution behaviors of developers given their interaction history, the semantic features of source code, and the hierarchical file structures of projects. We introduce CODER, a novel graph-based CODE Recommendation framework for open source software developers, which accounts for the complex interactions among multiple parties within the system. CODER jointly models microscopic user-code interactions and macroscopic user-project interactions via a heterogeneous graph and further …

Formation control of multi-agent systems has a wide range of applications, but it has not been paid much attention in Takagi–Sugeno (T-S) fuzzy systems. In this paper, an event-triggered sampling strategy is designed for the formation control of T-S fuzzy systems, which allows the fuzzy controller and the fuzzy model not to share the same membership functions. The control strategy reduces the transmission frequency of sampling states by setting event conditions for information transmission. By means of Lyapunov stability theory, a set of formation conditions based on LMI is established. Less conservative and more efficient conditions are also obtained based on the properties of membership functions. Numerical examples show the validity of the proposed formation conditions, and the conservatism of the two criteria is compared.

Few-shot learning aims to recognize novel concepts with only a few examples. To this end, previous studies resort to acquiring a strong inductive bias via meta-learning on a group of similar tasks, which however needs a large labeled base dataset to sample training tasks. In this paper, we show that such inductive bias can be learned from a flat collection of unlabeled images, and instantiated as transferable representations among seen and unseen classes. Specifically, we propose a novel unsupervised Part Discovery Network (PDN) to learn transferable representations from unlabeled images, which automatically selects the most discriminative part from an input image and then maximizes its similarities to the global view of the input and other neighbors with similar semantics. To better leverage the learned representations for few-shot learning, we further propose Part-Aligned Similarity (PAS), the key of which is …

The lumbar support mechanism and an adjustable bed having the same. The lumbar support mechanism includes a lumbar support member; first, second, third and fourth support legs; a linkage member; and first and second lumbar support brackets operably attachable to a back platform of the adjustable bed. The first and second support legs are pivotally connected between the lumbar support member and the linkage member; and the third and fourth support legs are pivotally connected between the first and second support legs, and the first and second lumbar support brackets, respectively, such that the lumbar support member is operably movable between a retracted position and an expanded (ejected) position when the linkage member moves between first and second positions. The lumbar support is provided when the lumbar support member is in the ejected position.

Forced periodic operation is a technique that periodically changes the manipulating variable of a chemical reaction system in order to exploit nonlinear dynamics to improve reactant conversion rate. However, the analysis and design of a periodically operated chemical process is a significant challenge. To resolve this problem, recently, nonlinear frequency response (NFR) based methods have been proposed. However, because of the need to derive the NFR from a first principle model, existing NFR methods can only perform qualitative analysis to simple processes and are often difficult to be applied in engineering practice. This article proposes a novel data driven approach to the analysis and optimal design of forced periodic operation of chemical reactions. From the data generated numerically using the first principle model or experimentally from experimental tests, the approach produces a data-driven NFR …

It has become a tendency to use a combination of autoencoders and graph neural networks for attribute graph clustering to solve the community detection problem. However, the existing methods do not consider the influence differences between node neighborhood information and high-order neighborhood information, and the fusion of structural and attribute features is insufficient. In order to make better use of structural information and attribute information, we propose a model named community detection fusing graph attention network (CDFG). Specifically, we firstly use an autoencoder to learn attribute features. Then the graph attention network not only calculates the influence weight of the neighborhood node on the target node but also adds the high-order neighborhood information to learn the structural features. After that, the two features are initially fused by the balance parameter. The feature fusion module extracts the hidden layer representation of the graph attention layer to calculate the self-correlation matrix, which is multiplied by the node representation obtained by the preliminary fusion to achieve secondary fusion. Finally, the self-supervision mechanism makes it face the community detection task. Experiments are conducted on six real datasets. Using four evaluation metrics, the CDFG model performs better on most datasets, especially for the networks with longer average paths and diameters and smaller clustering coefficients.

With cycling moving from being a pastime to a mainstream form of mobility and transport, bike-sharing systems (BSSs) are increasingly being deployed in many cities. Analysis of BSS usage data can provide insights into factors that shape the patterns of trips, uncovering latent city dynamics.

Human gait refers to a daily motion that represents not only mobility but can also be used to identify the walker by either human observers or computers. Recent studies reveal that gait even conveys information about the walker’s emotion. Individuals in different emotion states may show different gait patterns. The mapping between various emotions and gait patterns provides a new source for automated emotion recognition. Compared to traditional emotion detection biometrics, such as facial expression, speech, and physiological parameters, gait is remotely observable, more difficult to imitate, and requires less cooperation from the subject. These advantages make gait a promising source for emotion detection. This article reviews current research on gait-based emotion detection, particularly on how gait parameters can be affected by different emotion states and how the emotion states can be recognized through …

Dear Editor, The single cell RNA sequencing (scRNA-seq) technology provides new insights into understanding of single-cell transcriptomic atlas and intercellular communication. 1 scRNA-seq is used to characterize the considerable heterogeneity and complexity of cell type, to uncover the cell fate and context, critical molecular features and progression trajectories, as well as to explore potential pathogenesis and individualized therapeutic targets. 2–4 One of major challenges is to identify of biology-specific biomarkers as the cell identity for cell phenotypes and functional subtypes, although bioinformatic and fstatistical methods for scRNA-seq are developed and improved rapidly. 5 More and more cell type/subtypes are identified in response to various stimulus, external challenge and even pathological conditions. The correctness and specificity of cell-specific transcriptomic profiles based on scRNA-seq are highly …

In the era of big data, with an increasing number of e-commerce and social media users worldwide, the demand for automated sentiment analysis systems is growing rapidly. With respect to industrial interests, aspect-based sentiment analysis (ABSA), which focuses on the sentiment at the aspect level, has become a popular research topic. ABSA includes two subtasks aspect-term sentiment analysis (ATSA) and aspect-category sentiment analysis (ACSA). This paper proposes a multi-task learning framework based on the pre-trained BERT model as a shared representation layer to jointly learn ATSA and ACSA tasks. To fully exploit the contextual information surrounding the aspects, we add a multi-head self-attention layer with a skip connection on top of the shared BERT model. Experimental results on SemEval datasets show that our multi-task learning model improves the performance of the ATSA task and …

We propose to identify compromised mobile devices from a network administrator’s point of view. Intuitively, inadvertent users (and thus their devices) who download apps through untrustworthy markets are often lured to install malicious apps through in-app advertisements or phishing. We thus hypothesize that devices sharing similar apps would have a similar likelihood of being compromised, resulting in an association between a compromised device and its apps. We propose to leverage such associations to identify unknown compromised devices using the guilt-by-association principle. Admittedly, such associations could be relatively weak as it is hard, if not impossible, for an app to automatically download and install other apps without explicit user initiation. We describe how we can magnify such associations by carefully choosing parameters when applying graph-based inferences. We empirically evaluate …

Internet of Things (IoT) data from different trust domains is usually shared to assist in providing more services, where privacy sensitive information of shared data will be leaked or accessed without authorization. The traditional centralized access control method is difficult to adapt to the current dynamic and distributed large-scale IoT environment, and there is a risk of the single point of failure. To address these challenges, we propose a fine-grained access control framework for shared data based on cross-blockchain technology and Interplanetary File System (IPFS). In this framework, we firstly introduce a cross-blockchain module to realize cross-domain data sharing and solve the problem of data isolation between different data domains in IoT. Then IPFS is used to store the shared data, avoiding the risk of centralized storage. Combining symmetric encryption algorithm with ciphertext policy attribute based …

Usage‐based insurance (UBI) provides reasonable vehicle insurance premiums based on vehicle usage and driving behavior. In general, there are three major issues in realizing intelligent UBI systems. First, UBI evaluation mechanisms are not auditable to drivers. Insurers may thus deliberately adjust the UBI premiums. Second, the process of collecting driving data by insurers may lead to serious privacy breaches. Third, forging safer driving data for reducing insurance premiums may cause economic losses for insurers. To address these challenges, in this study, we propose CCUBI, a cross‐chain‐based premium competition scheme with privacy preservation for intelligent UBI systems. We introduce tamper‐resistant blockchain and smart contracts to construct credible insurance mechanisms. The cross‐chain technology connects these blockchains in the entire network to form an open premium competition …

BackgroundImmunoglobulin G (IgG) N-glycans have been shown to be associated with the risk of type 2 diabetes (T2D) and its risk factors. However, whether these associations reflect causal effects remain unclear. Furthermore, the associations of IgG N-glycans and inflammation are not fully understood.MethodsWe examined the causal associations of IgG N-glycans with inflammation (C-reactive protein (CRP) and fibrinogen) and T2D using two-sample Mendelian randomization (MR) analysis in East Asian and European populations. Genetic variants from IgG N-glycan quantitative trait loci (QTL) data were used as instrumental variables. Two-sample MR was conducted for IgG N-glycans with inflammation (75,391 and 18,348 participants of CRP and fibrinogen in the East Asian population, 204,402 participants of CRP in the European population) and T2D risk (77,418 cases and 356,122 controls of East Asian …

Complex networks operate in all areas of human life. As a key and popular research direction in the complexity discipline, the study of complex networks has a significant impact and contribution to multidisciplinary fields. In this paper, we study the problem of enhancing network controllability by adding edges from a given candidate set with minimum cost based on the structural controllability theory of complex networks. Specifically, we first formulate such a problem as a bi-objective network optimization model and then transform it into a network flow problem. An algorithm named Controllability Enhancement based Minimum-cost Max-flow (CEMM) is proposed, which can achieve: 1) A certain number of edges selected in the candidate set are added to a network such that the number of driver nodes is minimized; 2) The minimum cost of newly added edges is guaranteed. The feasibility of CEMM is verified by …

Stirring-sampling method is a widely adopted method to measure sediment concentrations in collection tanks of runoff plots, but with high systematic measurement errors. This research aimed to advance an approach for building correction equations to remove measurement errors in designed sediment concentration range. Experimental data of sediment measurement from the stirring-sampling method, with four representative soils, under the designed sediment concentrations (1, 2, 5, 8, 10, 20, 50, 80, 100, 200, 500, 800, and 1000 kg/m3) were used to demonstrate the correction methodological process. Two correction methods (step-wise correction and universal correction) were suggested for the trial in this study based on the distribution of measurement errors. In the step-wise correction, the correction equations were made with a series of linear functions without intercept for the low concentration group (0-20 kg/m3), a series of linear functions with intercept for the high (20-200 kg/m3) and extremely high (200-1000 kg/m3) concentration groups, consecutively. The correction equations were a series of power functions in the universal correction. For the step-wise correction, most of the relative errors of correction sediment concentrations were smaller than 15% and 10% under high and extremely high concentration groups, but the corrected accuracy was not good in the sediment concentration of 1, 2, 5 kg/m3 with the corrected relative errors of 0.20%-206.07%. For the universal correction, the corrected relative errors (0.19%-31.81%) of the four soils were low under the condition of extremely high sediment concentrations, but other corrected …

Recent studies find existing self-supervised speech encoders contain primarily acoustic rather than semantic information. As a result, pipelined supervised automatic speech recognition (ASR) to large language model (LLM) systems achieve state-of-the-art results on semantic spoken language tasks by utilizing rich semantic representations from the LLM. These systems come at the cost of labeled audio transcriptions, which is expensive and time-consuming to obtain. We propose a task-agnostic unsupervised way of incorporating semantic information from LLMs into self-supervised speech encoders without labeled audio transcriptions. By introducing semantics, we improve existing speech encoder spoken language understanding performance by over 10\% on intent classification, with modest gains in named entity resolution and slot filling, and spoken question answering FF1 score by over 2\%. Our unsupervised approach achieves similar performance as supervised methods trained on over 100 hours of labeled audio transcripts, demonstrating the feasibility of unsupervised semantic augmentations to existing speech encoders.

This paper investigates a distributed optimization problem based on the framework of a multi-agent system over a directed communication network, where the global cost function is the sum of the local cost functions of agents. The communication network is abstracted as a weight-unbalanced directed graph. First, a surplus-based accelerated algorithm with a fixed stepsize (SAAFS) is proposed by integrating the gradient tracking strategy into the surplus-based consensus protocol to address the problem considered. The matrix norm argument and matrix perturbation theory are employed to prove the linear convergence of SAAFS under the assumption that each local cost function is strongly convex with the Lipschitz continuous gradient. Second, the limitation of the stepsize, which is common to all agents, is relaxed in the cases of different stepsizes for each agent, such that the surplus-based accelerated algorithm …

This paper investigates the adaptive consensus tracking control problem for a class of high-order multi-agent systems in a strict feedback form under a directed topology condition. In contrast to the existing consensus tracking results, in this paper, unknown system parameters, unmeasurable states, communication delays and switching topologies of the multiagent systems are considered simultaneously. Given the fact that only the system output is available in the controller design, a group of state estimation filters is designed for each agent to observe its own and its neighbors’ unmeasurable states. By incorporating adaptive backstepping technique with a novel Lyapunov-Krasovskii function, a distributed consensus tracking control scheme is then proposed under switching topology condition. It is shown that with the proposed control scheme, the boundedness of all the closed-loop signals can be guaranteed and …

BackgroundCardiovascular disease (CVD) is a serious disease that endangers human health and is one of the main causes of death. Therefore, using the patient’s electronic medical record (EMR) to predict CVD automatically has important application value in intelligent assisted diagnosis and treatment, and is a hot issue in intelligent medical research. However, existing methods based on natural language processing can only predict CVD according to the whole or part of the context information of EMR.ResultsGiven the deficiencies of the existing research on CVD prediction based on EMRs, this paper proposes a risk factor attention-based model (RFAB) to predict CVD by utilizing CVD risk factors and general EMRs text, which adopts the attention mechanism of a deep neural network to fuse the character sequence and CVD risk factors contained in EMRs text. The experimental results show that the proposed …

With the rapid development of decentralized financial (DeFi), the total value locked (TVL) in DeFi continues to increase. A big number of adversaries exploit logic vulnerabilities to attack DeFi applications for profit, such as flash loan attacks and price manipulation attacks. However, the current vulnerability detection tools for smart contracts cannot be directly used to detect the logic vulnerabilities generated by the combination of different protocols. How to characterize and detect DeFi attacks that exploited logic vulnerabilities is a big challenge. In this work, we propose a deep-learning-based attack detection system on DeFi, called DeFiScanner, in which we design a novel neural network that includes a global model, a local model, and a fusion model to characterize DeFi attacks. First, the unstructured emitted events are automatically and efficiently normalized. Second, the transaction-related features of normalized …

A foldable bed includes a plurality of boards comprising an upper board, a middle board, and a lower board; a support assembly for supporting the plurality of boards, wherein the support assembly includes a first support structure for supporting the upper board and the middle board, and a second support structure for supporting the lower board; and a pair of connection mechanisms for connecting the first support structure and the second support structure such that the first support structure and the second support structure are pivotally foldable relative to one another at the pair of connection mechanisms.

Data sparsity and cold start are very challenging and popular problems in the field of recommendation. This paper establishes a personalized model of knowledge graph fine-grained attention mechanism for recommendation(KGFARS). At the user side, the attention mechanism is introduced to capture the weight assigned by use to item, and the information of items is aggregated to learn user’s embedding. A fine-grained attention mechanism algorithm is proposed on the item side, which essentially consists of a two-stage preference: 1) the preference of user and relationship which between a given item and a neighborhood; 2) the preference of user and corresponding neighborhood under the relationship. In addition, a multi-channel information aggregation function is designed for the fusion process of item and neighborhoods, which allows similar entities to transmit more information and improve the generalization …

The present invention belongs to the field of information technology, involving the techniques of fuzzy modeling, reinforcement learning, parallel computing, etc. It is a method combining granular computing and reinforcement learning for construction of long-term prediction interval and determination of its structure. Adopting real industrial data, the present invention constructs multi-layer structure for assigning information granularity in unequal length and establishes corresponding optimization model at first. Then considering the importance of the structure on prediction accuracy, Monte-Carlo method is deployed to learn the structural parameters. Based on the optimal multi-layer granular computing structure along with implementing par allel computing strategy, the long-term prediction intervals of gaseous generation and consumption are finally obtained. The proposed method exhibits superiority on accuracy and …

Use of unmanned aerial vehicles (UAVs) for urban services has been an exciting topic in today's urban planning and management research. Most UAVs use unlicensed spectrum for remote control and communications. Their communication distance is limited within a few hundred meters; and the control channel is prone to interference. In comparison, urban cellular networks can cover a wide urban area with a low chance of interference, making them a viable alternative for UAVs on services that require real-time and reliable connections. In this article we provide a performance evaluation of this concept. We first address some key challenges in designing and implementing a UAV platform connected to cellular networks. The cellular networks include 4G and 5G. Then we use the platform to test the actual performance of 4G and 5G in urban areas with a focus on their signal strength and packet delay. A comparative …

Federated learning (FL) is a promising distributed machine learning architecture that allows participants to cooperatively train a global model without sharing local data. However, both the trust of a central FL server and well-designed attacks against FL have significantly restricted the development of FL. In this work, we propose TBFL, a trusted blockchain-based federated learning system. It replaces the traditional central server with the functionalities provided by a decentralized blockchain. To prevent malicious participants from attacking the global model, TBFL employs a novel model verification and a scoring mechanism to keep detecting malicious participants. In addition, TBFL leverages a scalable incentive mechanism to enhance its reliability and fairness. We demonstrate the efficacy and attack-resilience of the proposed TBFL through experimental evaluation. The results validate the great performance and …

Blockchain-based traceability systems are a promising approach because they are decentralized, transparent, and tamper proof; however, if all traceability data are uploaded to a blockchain platform, it may affect the efficiency or even lead to data explosion. Additionally, it is difficult to guarantee the reliability of the original data source of massive Internet of Things (IoT) devices. Furthermore, when different enterprise nodes adopt different data storage structures, the costs that are associated with data sharing will increase. In this paper, we have proposed a trustworthy product traceability system that is based on hyperledger fabric and Electronic Product Code Information Service (EPCIS), which is not only capable of making products traceable, but it can also authenticate and authorize the IoT devices that are used for data collection. First, we adopted the on-chain and off-chain collaborative management mechanism in order to alleviate data explosion on the chain. Second, we proposed a scheme to authenticate and authorize devices based on blockchain. Third, we complied with EPCIS and Core Business Vocabulary (CBV) standards and provided the EPCIS location discovery service in order to improve the interactivity. Finally, we implemented and tested the proposed traceability system and compared it with the existing research. The proposed solution provides product information traceability, data tamper proofing, data confidentiality, and data source reliability.

Intelligent Computing for Big Data Edited by Intelligent Computing for Big Data Wei Wang and Ka Lok Man Printed Edition of the Special Issue Published in Applied Sciences www. mdpi. com/journal/applsci Page 2 Intelligent Computing for Big Data Page 3 Page 4 Intelligent Computing for Big Data Editors Wei Wang Ka Lok Man MDPI• Basel• Beijing• Wuhan• Barcelona• Belgrade• Manchester• Tokyo• Cluj• Tianjin Page 5 Editors Wei Wang Xi’an Jiaotong-Liverpool University China Ka Lok Man Xi’an Jiaotong-Liverpool University China Editorial Office MDPI St. Alban-Anlage 66 4052 Basel, Switzerland This is a reprint of articles from the Special Issue published online in the open access journal Applied Sciences (ISSN 2076-3417)(available at: https://www. mdpi. com/journal/applsci/special issues/Intelligent Computing Big Data). For citation purposes, cite each article independently as indicated on the article page …

In this brief, we investigate the consensus tracking control problem for first-order nonlinear multi-agent systems with unknown system parameters, external disturbances and directed communication graph. The system dynamics of each agent is not required to satisfy Lipschitz condition. Besides, the desired trajectory is not of linearly parameterized form with basis functions known by all the agents. In this setting, how to design a fully distributed adaptive control scheme to guarantee consensus tracking is a difficult issue since non-symmetric Laplacian matrix brings difficulties of designing fully distributed parameter update laws. To solve this issue, the design idea of transforming the original first-order multi-agent systems into augmented second-order multi-agent systems is firstly presented. Based on adaptive backstepping technique, a novel fully distributed consensus tracking control scheme is then proposed. Finally …

A log is a text message that is generated in various services, frameworks, and programs. The majority of log data mining tasks rely on log parsing as the first step, which transforms raw logs into formatted log templates. Existing log parsing approaches often fail to effectively handle the trade-off between parsing quality and performance. In view of this, in this paper, we present Multi-Layer Parser (ML-Parser), an online log parser that runs in a streaming manner. Specifically, we present a multi-layer structure in log parsing to strike a balance between efficiency and effectiveness. Coarse-grained tokenization and a fast similarity measure are applied for efficiency while fine-grained tokenization and an accurate similarity measure are used for effectiveness. In experiments, we compare ML-Parser with two existing online log parsing approaches, Drain and Spell, on ten real-world datasets, five labeled and five unlabeled …

Machine Learning-as-a-Service systems (MLaaS) have been largely developed for cybersecurity-critical applications, such as detecting network intrusions and fake news campaigns. Despite effectiveness, their robustness against adversarial attacks is one of the key trust concerns for MLaaS deployment. We are thus motivated to assess the adversarial robustness of the Machine Learning models residing at the core of these securitycritical applications with categorical inputs. Previous research efforts on accessing model robustness against manipulation of categorical inputs are specific to use cases and heavily depend on domain knowledge, or require white-box access to the target ML model. Such limitations prevent the robustness assessment from being as a domain-agnostic service provided to various real-world applications. We propose a provably optimal yet computationally highly efficient adversarial …