Search

Gypsum is regarded as an environmentally friendly binding material and is widely used to enhance the engineering properties of soft fine-grained soils. However, the time-dependent strength and deformation characteristics of fine-grained soils stabilised with gypsum have not yet been thoroughly investigated and rational evaluation of these characteristics will assist in the formulation of cost-effective and reliable design approaches. In this study, the time-dependent mechanical behaviours of gypsum-mixed fine-grained soil (GMFS) specimens were investigated under unconfined monotonic loading conditions, considering ageing periods of 3–90 days and five different loading rates (LR = 0.0005–1.0%/min). The results revealed that the unconfined compressive strength and stiffness of the GMFS specimens initially decreased with ageing and finally became stable after 14 days and 28 days of ageing for water/gypsum ratios of 1.30 and 1.60, respectively. Furthermore, the strength and stiffness of the GMFS specimens increased with an increase in LR.

Fuzzy rough set (FRS) theory is generally used to measure the uncertainty of data. However, this theory cannot work well when the class density of a data distribution differs greatly. In this work, a relative distance measure is first proposed to fit the mentioned data distribution. Based on the measure, a relative FRS model is introduced to remedy the mentioned imperfection of classical FRSs. Then, the positive region, negative region, and boundary region are defined to measure the uncertainty of data with the relative FRSs. Besides, a relative fuzzy dependency is defined to evaluate the importance of features to decision. With the proposed feature evaluation, we propose a feature selection algorithm and design a classifier based on the maximal positive region. The classification principle is that an unlabeled sample will be classified into the class corresponding to the maximal degree of the positive region. Experimental results show the relative fuzzy dependency is an effective and efficient measure for evaluating features, and the proposed feature selection algorithm presents better performance than some classical algorithms. Besides, it also shows the proposed classifier can achieve slightly better performance than the KNN classifier, which demonstrates that the maximal positive region-based classifier is effective and feasible.

Aspect level sentiment classification aims to classify the sentiment polarity of a given aspect term or aspect category in a sentence. For sentiment classification towards a given aspect term, since a sentence may contain more than one aspect term, there may exist some opinions which are not the modifiers of the given aspect term. It is necessary to capture relevant opinion for a certain aspect term. Previous works use the relative distance between an aspect term and all other words in a sentence, in order to capture the nearest opinion of the aspect term. This can be infeasible when the sentence has a complex syntactic structure. In this paper, we detect the dependency relation between an aspect term and its related sentiment words in the dependency parse tree. Then, we integrate this relationship into CNN and Bi-LSTM respectively. Experiments show that the related sentiment features for an aspect term is helpful for models to discriminate its sentiment polarity, and our proposed models achieve state-of-the-art results among neural network models.

Recognizing the emotional state of a person within the image in real-world scenarios is a key problem in affective computing and has various promising applications. Local regions in the image, including different objects in the background scene and parts within the foreground body, usually have different contributions to emotion perception of the target person. This, however, has not been well exploited in most existing methods. In this paper, we propose to make relational region-level analysis to account for the different contributions of different regions to emotion recognition. For the background scene, we propose a Body-Object Attention (BOA) module to estimate the contributions of background objects to emotion recognition given the target foreground body. Within the foreground body, we propose a Body Part Attention (BPA) module to recalibrate the channel-wise body feature responses to attend on body parts that are more important. Moreover, we propose to model the emotion label dependency in real-world images, considering both the semantic meanings of these labels and their co-occurrence patterns. We evaluate the proposed method on the EMOTIC and CAER-S datasets, and experimental results show the superiority of our method compared with the state-of-the-art algorithms.

Data-driven fault detection and isolation (FDI) depends on complete, comprehensive, and accurate fault information. Optimal test selection can substantially improve information achievement for FDI and reduce the detecting cost and the maintenance cost of the engineering systems. Considerable efforts have been worked to model the test selection problem (TSP), but few of them considered the impact of the measurement uncertainty and the fault occurrence. In this article, a conditional joint distribution (CJD)-based test selection method is proposed to construct an accurate TSP model. In addition, we propose a deep copula function which can describe the dependency among the tests. Afterward, an improved discrete binary particle swarm optimization (IBPSO) algorithm is proposed to deal with TSP. Then, application to an electrical circuit is used to illustrate the efficiency of the proposed method over two available methods: 1) joint distribution-based IBPSO and 2) Bernoulli distribution-based IBPSO.

The ability to accurately predict human encounters can inspire a variety of promising applications, ranging from epidemiology to data forwarding in opportunistic networks. This work aims at designing a low cost, highly accurate human encounter prediction model based on Wi-Fi datasets. By leveraging the temporal dependency of human mobility, we propose the distributed human encounter prediction (DHEP) model, which uses the Wi-Fi access history and inferred contact information of only the person of interest to estimate future encounters of that person. We implement the proposed DHEP model using a recurrent neural network and a feed-forward neural network. An embedding model that learns the low-dimensional representation of a person's location is proposed to reduce the number of training parameters. The experimental results on two large Wi-Fi datasets show the proposed RNN-based DHEP model outperforms existing models, and achieves 87% to 91% accuracy based on University at Buffalo (UB) traces. We also compare DH P with the centralized human encounter prediction (CHEP) model, which gathers the contact history of all people for predicting future encounters. Despite a slightly lower performance than CHEP, DHEP has a low overhead and can protect data privacy.

When viewing omnidirectional images (ODIs), viewers can access different viewports via head movement (HM), which sequentially forms head trajectories in spatial-temporal domain. Thus, head trajectories play a key role in modeling human attention on ODIs. In this paper, we establish a large-scale dataset collecting 21,600 head trajectories on 1,080 ODIs. By mining our dataset, we find two important factors influencing head trajectories, i.e., temporal dependency and subject-specific variance. Accordingly, we propose a novel approach integrating hierarchical Bayesian inference into long short-term memory (LSTM) network for head trajectory prediction on ODIs, which is called HiBayes-LSTM. In HiBayes-LSTM, we develop a mechanism of Future Intention Estimation (FIE), which captures the temporal correlations from previous, current and estimated future information, for predicting viewport transition. Additionally, a training scheme called Hierarchical Bayesian inference (HBI) is developed for modeling inter-subject uncertainty in HiBayes-LSTM. For HBI, we introduce a joint Gaussian distribution in a hierarchy, to approximate the posterior distribution over network weights. By sampling subject-specific weights from the approximated posterior distribution, our HiBayes-LSTM approach can yield diverse viewport transition among different subjects and obtain multiple head trajectories. Extensive experiments validate that our HiBayes-LSTM approach significantly outperforms 9 state-of-the-art approaches for trajectory prediction on ODIs, and then it is successfully applied to predict saliency on ODIs.

Collaborative Filtering (CF) filters the flow of data that can be recommended, by a Recommender System (RS), to a target user according to his taste and his preferences. The target user’s profile is built based on his similarity with other users. For this reason, CF technique is very sensitive to the similarity measure used to quantify the dependency strength between two users (or two items). In this paper we provide an in-depth review on similarity measures used for CF-based RS. For each measure, we outline its fundamental background and we test its performance through an experimental study. Experiments are carried out on three standard datasets (MovieLens100k, MovieLens1M and Jester) and reveal many important conclusions. In fact, results show that ITR and IPWR are the most suitable similarity measures for a user-based RS while AMI is the best choice for an item-based RS. Evaluation metrics show that under the user-based approach, ITR obtains an MAE equal to 0.786 and 0.731 on MovieLens100k and MovieLens1M, respectively. Whereas, IPWR reach an MAE equal to 3.256 on Jester. Also, AMI gets under the item-based approach an MAE equal to 0.745, 0.724 and 3.281 on MovieLens100k, MovieLens1M and Jester, respectively.

This work enables mobile user authentication via finger inputs on ubiquitous surfaces leveraging low-cost physical vibration. The system we proposed extends finger-input authentication beyond touch screens to any solid surface for IoT devices (e.g., smart access systems and IoT appliances). Unlike passcode or biometrics-based solutions, it integrates passcode, behavioral and physiological characteristics, and surface dependency together to provide a low-cost, tangible and enhanced security solution. The proposed system builds upon a touch sensing technique with vibration signals that can operate on surfaces constructed from a broad range of materials. New algorithms are developed to discriminate fine-grained finger inputs and supports three independent passcode secrets including PIN number, lock pattern, and simple gestures by extracting unique features in the frequency domain to capture both behavioral and physiological characteristics including contacting area, touching force, and etc. The system is implemented using a single pair of low-cost portable vibration motor and receiver that can be easily attached to any surface (e.g., a door panel, a stovetop or an appliance). Extensive experiments demonstrate that our system can authenticate users with high accuracy (e.g., over 97% within two trials), low false positive rate (e.g., less 2%) and is robust to various types of attacks.

The practice of backporting aims to bring the benefits of a bug or vulnerability fix from a higher to a lower release of a software package. When such a package adheres to semantic versioning, backports can be recognised as new releases in a lower major train. This is particularly useful in case a substantial number of software packages continues to depend on that lower major train. In this article, we study the backporting practices in four popular package distributions, namely Cargo, npm, Packagist and RubyGems. We observe that many dependent packages could benefit from backports provided by their dependencies. In particular, we find that a majority of security vulnerabilities affect more than one major train but are only fixed in the highest one, letting thousands of dependent packages exposed to the vulnerability. Despite that, we find that backporting updates is quite infrequent, and mostly practised by long-lived and more active packages for a variety of reasons.

Part-of-Speech (POS) tagging is a fundamental sequence labeling problem in Natural Language Processing. Recent deep learning sequential models combine the forward and backward word informatio for POS tagging. The information of contextual words to the current word play a vital role in capturing the non-continuous relationship. We have proposed Monotonic chunk-wise attention with CNN-GRU-Softmax (MCCGS), a deep learning architecture that adheres to these essential information. This architecture consists of Input Encoder (IE), encodes word and character-level, Contextual Encoder (CE), assigns the weightage to adjacent word and Disambiguator (D), which resolves intra-label dependencies as core components. Moreover, different morphological features have been integrated into the core components of MCCGS architecture as MCCGS-IE, MCCGS-CE and MCCGS-D. The MCCGS architecture is validated on the 21 languages from Universal Dependency (UD) treebank. The state-of-the-art models, Type constraints, Retrofitting, Distant Supervision from Disparate Sources and Position-aware Self Attention, MCCGS and its variants such as MCCGS-IE, MCCGS-CE and MCCGS-D are obtained mean accuracy 83.65 % , 81.29 % , 84.10 % , 90.18 % , 90.40 % , 91.40 % , 90.90 % , 92.30 % , respectively. The proposed model architecture provides state-of-the-art accuracy on the low resource languages as Marathi ( 93.58 % ), Tamil ( 87.50 % ), Telugu ( 96.69 % ) and Sanskrit ( 97.28 % ) from UD treebank and Hindi ( 95.64 % ) and Urdu ( 87.47 % ) from Hindi-Urdu multi-representational treebank.

Multiview fuzzy systems aim to deal with fuzzy modeling in multiview scenarios effectively and to obtain the interpretable model through multiview learning. However, current studies of multiview fuzzy systems still face several challenges, one of which is how to achieve efficient collaboration between multiple views when there are few labeled data. To address this challenge, this article explores a novel transductive multiview fuzzy modeling method. The dependency on labeled data is reduced by integrating transductive learning into the fuzzy model to simultaneously learn both the model and the labels using a novel learning criterion. Matrix factorization is incorporated to further improve the performance of the fuzzy model. In addition, collaborative learning between multiple views is used to enhance the robustness of the model. The experimental results indicate that the proposed method is highly competitive with other multiview learning methods.

Establishing an open-domain emotional conversation generation with content and emotional dependence is a key step towards intelligent interactions. However, the researchers only dedicated to adding the thematic content or emotional words and handing both factors are not yet properly solved. In this paper, we aim to address the issue of integrity in emotional content which indicates the response has a dependency relationship between theme and emotion. We propose a thematic-emotional conversation model, which consists of parallel channels and joint encoding, to maximize integrity in conversation generation. We first use the encoding of parallel channel to strengthen the decoding weight of the theme and emotion. The joint encoding of the dual attention mechanism and the thematic emotional trade-off strategy involved in the encoding to ensure that the theme complements the emotional content during the response generation. After that, the bidirectional training interactions between post and response are calculated to derive the new response inference vectors. Experiment results suggest that the proposed model is effective not only in content integrity but also in emotion.

Many engineering products have more than one failure mode and the evolution of each mode can be monitored by measuring a performance characteristic (PC). It is found that the underlying multi-dimensional degradation often occurs with inherent process stochasticity and heterogeneity across units, as well as dependency among PCs. To accommodate these features, in this paper, we propose a novel multivariate degradation model based on the inverse Gaussian process. The model incorporates random effects that are subject to a multivariate normal distribution to capture both the unit-wise variability and the PC-wise dependence. Built upon this structure, we obtain some mathematically tractable properties such as the joint and conditional distribution functions, which subsequently facilitate the future degradation prediction and lifetime estimation. An expectation-maximization algorithm is developed to infer the model parameters along with the validation tools for model checking. In addition, two simulation studies are performed to assess the performance of the inference method and to evaluate the effect of model misspecification. Finally, the application of the proposed methodology is demonstrated by two illustrative examples.

Classical fuzzy rough set often uses fuzzy rough dependency as an evaluation function of feature selection. However, this function only retains the maximum member- ship degree of a sample to one decision class, it can not describe the classification error. Therefore, in this work, a novel criterion function for feature selection is proposed to overcome this weakness. To characterize the classification error rate, we first introduce a class of irreflexive and symmetric fuzzy binary relations to redefine the concepts of fuzzy rough approximations. Then, we propose a novel concept of dependency: inner product dependency to describe the classification error, and construct a criterion function to evaluate the importance of candidate features. The proposed criterion function not only can maintain a maximum dependency function, but also guarantees the minimum classification error. The experimental analysis shows that the proposed criterion function is effective for data sets with a large overlap between different categories.

In this paper, we address Emotion Recognition in Conversation (ERC) where conversational data are presented in a multimodal setting. Psychological evidence shows that self and inter-speaker influence are two central factors to emotion dynamics in conversation. State-of-the-art models do not effectively synthesise these two factors. Therefore, we propose an Adapted Dynamic Memory Network (A-DMN) where self and inter-speaker influences are modelled individually and further synthesised oriented towards the current utterance. Specifically, we model the dependency of the constituent utterances in a dialogue video using a global RNN to capture inter-speaker influence. Likewise, each speaker is assigned an RNN to capture their self influence. Afterwards, an Episodic Memory Module is devised to extract contexts for self and inter-speaker influence and synthesise them to update the memory. This process repeats itself for multiple passes until a refined representation is obtained and used for final prediction. Additionally, we explore cross-modal fusion in the context of multimodal ERC, and propose a convolution-based method which proves effective in extracting local interactions and computationally efficient. Extensive experiments demonstrate that A-DMN outperforms the state-of-the-art models on benchmark datasets.

Weakly supervised temporal action detection aims at localizing temporal positions of action instances in untrimmed videos with only action class labels. In general, previous methods individually classify each frame based on the appearance information and the short-term motion information, and then integrate consecutive high-response action frames into entities which serve as detected action instances. However, the long-range temporal dependencies between action frames are not fully utilized, and the detection results are more likely to be trapped in the most discriminative action segments. To alleviate this issue, we propose a novel two-branch (i.e., the coarse detection branch and the refining detection branch) detection framework with learning the long-range temporal dependencies for obtaining more accurate detection results, where only action class labels are required. The coarse detection branch is used to localize the most discriminative segments of action instances based on a typical multi-instance learning paradigm under the supervision of action class labels, whereas the refining detection branch is expected to localize the less discriminative segments of action instances via learning the long-range temporal dependencies between frames based on the proposed Transformer-style architecture and learning strategies. This collaboration mechanism takes full advantage of complementary information from the provided action class labels and the natural temporal dependencies between action frames, forming a more comprehensive solution. Consequently, our method obtains more precise detection results. Expectedly, the proposed method outperforms recent weakly supervised temporal action detection methods on dataset THUMOS14 and ActivityNet measured by mAP@tIoU and AR@AN.

Web services often impose inter-parameter dependencies that restrict the way in which two or more input parameters can be combined to form valid calls to the service. Unfortunately, current specification languages for web services like the OpenAPI Specification (OAS) provide no support for the formal description of such dependencies, which makes it hardly possible to automatically discover and interact with services without human intervention. In this article, we present an approach for the specification and automated analysis of inter-parameter dependencies in web APIs. We first present a domain-specific language, called Inter-parameter Dependency Language (IDL), for the specification of dependencies among input parameters in web services. Then, we propose a mapping to translate an IDL document into a constraint satisfaction problem (CSP), enabling the automated analysis of IDL specifications using standard CSP-based reasoning operations. Specifically, we present a catalogue of nine analysis operations on IDL documents allowing to compute, for example, whether a given request satisfies all the dependencies of the service. Finally, we present a tool suite including an editor, a parser, an OAS extension, a constraint programming-aided library, and a test suite supporting IDL specifications and their analyses. Together, these contributions pave the way for a new range of specification-driven applications in areas such as code generation and testing. Junta de Andalucía US-1264651 Ministerio de Ciencia, Innovación y Universidades RTI2018-101204-B-C21 Ministerio de Educación y Formación Profesional FPU17/04077

Novel empirical path loss and root mean square delay spread (RDS) models for smart office scenarios are proposed. The effects of person density on the path loss and RDS are investigated based on the extensive measurements at 2.3-2.5GHz. Firstly, both of the measured path loss and RDS data are modeled as the dual log-distance functions. It is caused by the regular structure and furniture in the office environment. Secondly, in the proposed path loss model, the path loss exponents and the additional attenuation factor are modeled as quadratic functions of the person density. Meanwhile, the RDS is found to be uncorrelated with the person density. These phenomena reveal that the persons in the environments can be regarded as absorbers rather than scatters. rgb0.00,0.00,0.00Then, the accuracy of the proposed models is validated by the measured data and compared with two traditional models. Finally, the effect of the persons’ movements on the path loss and RDS are investigated, and the proposed models are extended to millimeter wave bands by ray tracing technology. The proposed models and results can provide necessary information for link budget and algorithm design for the Internet of Things smart office scenarios.

Understanding human language is one of the key themes of artificial intelligence. For language representation, the capacity of effectively modeling the linguistic knowledge from the detail-riddled and lengthy texts and getting rid of the noises is essential to improve its performance. Traditional attentive models attend to all words without explicit constraint, which results in inaccurate concentration on some dispensable words. In this work, we propose using syntax to guide the text modeling by incorporating explicit syntactic constraints into attention mechanisms for better linguistically motivated word representations. In detail, for self-attention network (SAN) sponsored Transformer-based encoder, we introduce syntactic dependency of interest (SDOI) design into the SAN to form an SDOI-SAN with syntax-guided self-attention. Syntax-guided network (SG-Net) is then composed of this extra SDOI-SAN and the SAN from the original Transformer encoder through a dual contextual architecture for better linguistics inspired representation. The proposed SG-Net is applied to typical Transformer encoders. Extensive experiments on popular benchmark tasks, including machine reading comprehension, natural language inference, and neural machine translation show the effectiveness of the proposed SG-Net design., The early version accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). Journal extension of arXiv:1908.05147 (AAAI 2020)

Digital active gate driving has been shown to effectively manage the switching performance for power devices with the adjustable driving waveforms. However, most of the studies are based on a dedicated test circuit rather than a practical inverter with the sinusoidal output current. In fact, it is the dependency on the load current that makes the design of the gate driving profiles a critical issue. To investigate the digital active gate driver in an inverter application, this paper has applied optimal patterns adapting to time-varying output load current. Prior to the search of optimal patterns, the proper design framework is discussed with three frameworks of different time resolutions. With the proper resolution determined for patterns, multiple optimizations are carried out for different current conditions. In this way, the search for optimal patterns can be completed in an efficient time. Next, a look-up table of optimal switching pattern in correspondence with each certain load current condition was built in advance. According to the output load current, the optimal pattern is selected based on the look-up table. Compared to the conventional constant driving waveform, the power loss has been reduced by 7% with a full optimal look-up table applied.

As one of the most complex social problems around the world, crime may bring the risk of dying or losing property to the public if not handled properly. Crime prediction which aims at predicting crime incidents before they happen is of great importance to fight against crime. Previous studies are concerned primarily with day-level crime prediction and have certain limitations on modeling complex spatial–temporal-categorical dependency contained in the criminal activities as well as utilizing external factors to facilitate the forecast. In this paper, we develop a novel Neural Attentive framework for Hour-level Crime prediction (NAHC) to cope with these challenges. Specifically, we first adopt the priori knowledge-based data enhancement strategy to alleviate the zero-inflated issue raised in hour-level settings. Then, multi-graph convolutional networks are applied to capture spatial dependency from different aspects. After that, we integrate gated recurrent units with a temporal attention mechanism to jointly address temporal dependency and capture time-sensitive external factors. A categorical attention mechanism is proposed for dealing with categorical dependency and finally a fully connected network is utilized to generate the final prediction results. Extensive experiments on two real-world crime datasets demonstrate the effectiveness of our framework over the state-of-the-art comparing methods.

Recently, emotion recognition in real sceneries such as in the wild has attracted extensive attention in affective computing, because existing spontaneous emotions in real sceneries are more challenging and difficult to identify than other emotions. Motivated by the diverse effects of different lengths of audio spectrograms on emotion identification, this paper proposes a multiscale deep convolutional long short-term memory (LSTM) framework for spontaneous speech emotion recognition. Initially, a deep convolutional neural network (CNN) model is used to learn deep segment-level features on the basis of the created image-like three channels of spectrograms. Then, a deep LSTM model is adopted on the basis of the learned segment-level CNN features to capture the temporal dependency among all divided segments in an utterance for utterance-level emotion recognition. Finally, different emotion recognition results, obtained by combining CNN with LSTM at multiple lengths of segment-level spectrograms, are integrated by using a score-level fusion strategy. Experimental results on two challenging spontaneous emotional datasets, i.e., the AFEW5.0 and BAUM-1s databases, demonstrate the promising performance of the proposed method, outperforming state-of-the-art methods.

This article presents a data-driven method for computing reachable sets where active learning (AL) is used to reduce the computational burden. Set-based methods used to estimate reachable sets typically do not scale well with the state-space dimension, or rely heavily on the existence of a model. If such a model is not available, it is simple to generate state trajectory data by numerically simulating black-box oracles of systems (whose dynamics are unknown) from sampled initial conditions. Using these data samples, the estimation of reachable sets can be posed as a classification problem, wherein AL can intelligently select samples that are most informative and least similar to previously labeled samples. By exploiting submodularity, the actively learned samples can be selected efficiently, with bounded suboptimality. Our proposed framework is illustrated by estimating the domains of attractions of model predictive controllers (MPCs) and reinforcement learners. We also consider a scenario where there are two oracles that differ with respect to evaluation costs and labeling accuracy. We propose a framework to reduce the dependency of the expensive oracle in labeling samples using disagreement-based AL (DBAL). The potential of the DBAL algorithm is demonstrated on a solver selection problem for real-time MPC.

The majority of finite mixture models suffer from not allowing asymmetric tail dependencies within components and not capturing non-elliptical clusters in clustering applications. Since vine copulas are very flexible in capturing these types of dependencies, we propose a novel vine copula mixture model for continuous data. We discuss the model selection and parameter estimation problems and further formulate a new model-based clustering algorithm. The use of vine copulas in clustering allows for a range of shapes and dependency structures for the clusters. Our simulation experiments illustrate a significant gain in clustering accuracy when notably asymmetric tail dependencies or/and non-Gaussian margins within the components exist. The analysis of real data sets accompanies the proposed method. We show that the model-based clustering algorithm with vine copula mixture models outperforms the other model-based clustering techniques, especially for the non-Gaussian multivariate data.

Aspect-based sentiment analysis (ABSA) is crucial for exploring user feedbacks and preferences on produces or services. Although numerous classical deep learning-based methods have been proposed in previous literature, several useful cues (e.g., contextual, lexical, and syntactic) are still not fully considered and utilized. In this study, a new approach for ABSA is proposed through the guidance of contextual, lexical, and syntactic cues. First, a novel sub-network is introduced to represent a target in a sentence in ABSA by considering the whole context. Second, lexicon embedding is applied to incorporate additional lexical cues. Third, a new attention module, namely, dependency attention, is proposed to elaborate syntactic dependency cues between words in attention inference. Experimental results on four benchmark data sets demonstrate the effectiveness of our proposed approach to aspect-based sentiment analysis.

With the widespread application of smart devices, spatial crowdsourcing (SC) has been extensively integrated into daily life. Task assignment is a crucial issue in SC and has attracted much attention. Most prior studies on task assignment ignore the importance of dependency among tasks, resulting in some ineffective matching pairs and wasting workers’ time. To this end, we formulate a new problem in SC, abbreviated as multi-stage complex task assignment (MSCTA), which aims to assign workers to multi-stage complex tasks to maximize the total profit. Compared with existing studies, MSCTA can obtain more effective assignments by considering the dependency constraints among tasks. We prove that the MSCTA problem is NP-hard and propose a greedy algorithm and a game algorithm. Specifically, both algorithms iteratively utilize a filtering module to obtain a set of executable tasks (ET) for assignment. The greedy algorithm can quickly assign the most profitable workers to the subtasks in each round of ET, and obtain a provable approximate result. The game algorithm is proved to be convergent and can win a Nash equilibrium when processing the subtasks in each round of ET. Extensive experimental results demonstrate the efficiency of our algorithm.

Chemical-induced disease (CID) relation extraction from biomedical articles plays an important role in disease treatment and drug development. Existing methods are insufficient for capturing complete document level semantic information due to ignoring semantic information of entities in different sentences. In this work, we proposed an effective document-level relation extraction model to automatically extract intra-/inter-sentential CID relations from articles. Firstly, our model employed BERT to generate contextual semantic representations of the title, abstract and shortest dependency paths (SDPs). Secondly, to enhance the semantic representation of the whole document, cross attention with self-attention (named cross2self-attention) between abstract, title and SDPs was proposed to learn the mutual semantic information. Thirdly, to distinguish the importance of the target entity in different sentences, the Gaussian probability distribution was utilized to compute the weights of the co-occurrence sentence and its adjacent entity sentences. More complete semantic information of the target entity is collected from all entities occurring in the document via our presented document-level R-BERT (DocR-BERT). Finally, the related representations were concatenated and fed into the softmax function to extract CIDs. We evaluated the model on the CDR corpus provided by BioCreative V. The proposed model without external resources is superior in performance as compared with other state-of-the-art models (our model achieves 53.5%, 70%, and 63.7% of the F1-score on inter-/intra-sentential and overall CDR dataset). The experimental results indicate that cross2self-attention, the Gaussian probability distribution and DocR-BERT can effectively improve the CID extraction performance. Furthermore, the mutual semantic information learned by the cross self-attention from abstract towards title can significantly influence the extraction performance of document-level biomedical relation extraction tasks.

Cascading failures are one of the main mechanisms causing widespread blackouts of power networks. Models simulating the behavior of cascading failures are widely used in the literature to understand fault propagation and investigate effective mitigation strategies. However, there is a lack of validated models that address the specific requirements of resilience analysis in power networks and that are computationally fast and converge reliably for very large contingency sizes that may occur under extreme events. This article presents a novel comprehensive ac cascading failure model particularly designed for resilience analysis in power networks. The model is capable to deal with large contingency sizes, it is computationally efficient in large networks and integrates seamlessly with established resilience metrics. It incorporates dynamic phenomena and protection mechanisms using static representations. The model is verified following the recommendations by the IEEE PES working group on cascading failures using internal validation, sensitivity analysis, and comparison to historical outage data. Furthermore, an analysis of the impact of different contingency sizes and the dependency of cascades on network loading level, are given to illustrate some applications of the model and to highlight its capabilities.

Non-intrusive load monitoring (NILM) is to estimate individual appliance’s power consumption from aggregated smart meter data, which is useful for optimized energy management and provisioning of customized services. While deep learning (DL) has achieved state-of-the-art NILM performance, it is still constrained by the dependency on large amounts of data and intensive computations on training. In this paper, we propose a pre-training approach to address the generalization of DL models for NILM. We develop a meta-learning based approach and an ensemble learning based approach, which pre-train a base model and then fine-tune it with few-short learning when applied to an unknown dataset. The models are validated with two real-world datasets and shown to achieve a superior transferability performance compared with traditional DL and transfer learning methods.

The short-term reversal anomaly has been believed to be compensation for liquidity provision. We put forth the hypotheses that i) liquidity provision for a stock increases with the stock's capital gains overhang and ii) short-term reversal is more pronounced for the stocks with a large capital loss overhang. Our empirical findings support our hypotheses and the results hold firmly, even after we control for risk as well as lottery preferences and past return effects. We also document that this reference dependency of short-term reversal is stronger among stocks with low institutional ownership and during the low liquidity period.

Aviation and aerospace system are typical Phased-Mission Systems (PMSs) featured with varying configuration, phased load condition and cross phase failure correlation. The coupling effect of Functional Dependency (FDEP) and Physical Dependency (PDEP) has a unique influence on the failure behavior of PMS. In this article, the coupling effect is analyzed, and the degradation of components is modeled with the positive drift wiener process, in which the drift coefficient is related to environmental conditions and operation stress. Finally, failure behavior and system reliability are simulated. An avionics controller is studied as a case, with the degradation time distribution model and simulation algorithm, the coupling effect and dynamical system reliability can be achieved. Results show that this modeling method can describe the coupling effects of FDEP and PDEP and their influence on the failure behavior and reliability of the PMS system.

A faulty situation occurred in Service Oriented Architecture (SOA) based systems can affect its functionality. It is challenging to guarantee the reliability of service utilization in a distributed, concurrent and dynamic composition of web services. This paper aims to present a fault detection approach of SOA using dependency analysis. Data and control dependencies are identified and a fault diagnosis approach based on these dependencies is proposed in this paper. The presented approach extends discrete state space techniques to simulate the concurrent and distributed behavior through Colored Petri Nets (CPNs) for the SOA-based systems in case of the faulty situation. Concrete translation from SOA based system to a CPN model is presented. Model-based technique is used and some heuristics are presented for dependency analysis and fault detection purpose. The experimental performance analysis shows the feasibility of our proposed approach.

Coronavirus Disease-19 (COVID-19) has lead global epidemics with high morbidity and mortality. However, there are currently no proven effective drugs targeting COVID-19. Identifying drug-virus associations can not only provide insights into the understanding of drug-virus interaction mechanism, but also guide and facilitate the screening of compound candidates for antiviral drug discovery. Since conventional experiment methods are time-consuming, laborious and expensive, computational methods to identify potential drug candidates for viruses (e.g., COVID-19) provide an alternative strategy. In this work, we propose a novel framework of Heterogeneous Graph Attention Networks for Drug-Virus Association predictions, named HGATDVA. First, we fully incorporate multiple sources of biomedical data, e.g., drug chemical information, virus genome sequences and viral protein sequences, to construct abundant features for drugs and viruses. Second, we construct two drug-virus heterogeneous graphs. For each graph, we design a self-enhanced graph attention network (SGAT) to explicitly model the dependency between a node and its local neighbors and derive the graph-specific representations for nodes. Third, we further develop a neural network architecture with tri-aggregator to aggregate the graph-specific representations to generate the final node representations. Extensive experiments were conducted on two datasets, i.e., DrugVirus and MDAD, and the results demonstrated that our model outperformed 7 state-of-the-art methods. Case study on SARS-CoV-2 validated the effectiveness of our model in identifying potential drugs for viruses.

The comparably low driving ranges of battery electric vehicles (BEV) cause time-consuming recharging stops if long distances have to be covered. Thus, navigation systems not only have to compute routes leading from the BEV's current position to the destination, but also to plan recharging stops. This type of routing problem is often modeled as a constrained shortest path problem. The constraint ensures that the BEV does not run out of energy. In this paper, a de facto deterministic reformulation of this problem type is suggested, which allows handling uncertainty-particularly the risks resulting from imperfect energy consumption predictions. For this purpose, a certain part of the battery capacity is used as an energy buffer. Different approaches to dynamically optimize the size of this energy buffer in dependency of the expected level of uncertainty are proposed and a corresponding modification of a typical routing algorithm is described. Furthermore, a simulation study is conducted showing that the described framework allows keeping the probability to run out of energy close to zero (for the test settings: < 0.5%) as long as a suitable approach for defining the size of the energy buffer is applied.

Quality prediction, as the basis of quality control, is dedicated to predicting quality indices of the manufacturing process. In recent years, data-driven deep learning methods have received a lot of attention due to their accuracy, robustness, and convenience for the prediction of quality indices. However, the existing studies mainly focus on the quality prediction of a single machine, while ignoring dependency relationships among multiple machines in multistage manufacturing process. To tackle the above issues, a novel path enhanced bidirectional graph attention network (PGAT) is proposed in this article. PGAT models the dependencies among machines into directed graphs and introduces graph attention network to encode the dependencies. Nonetheless, it is difficult for graph neural networks to encode long-distance dependencies. Hence, dependency path information is introduced into the features of machines. Moreover, in order to solve the label noise problem that often occurs in actual industrial dataset, a masked loss function is devised. With its help, batch training with noisy labels can be achieved, which improves the training efficiency. Furthermore, experiments are conducted on a public quality prediction dataset collected from an actual production line. PGAT achieves the state-of-the-art results on this dataset, which confirms the effectiveness of PGAT. Additionally, the experimental results demonstrate the critical role of modeling dependency relationships among machines.

Reliable traffic flow prediction is of great value in the field of transportation, which, for example, contributes to traffic control and public safety. The key of achieving better performance is to well capture the non-linear spatial-temporal dependency. The state-of-the-art works consider both aspects, but they ignore the effect of the global trend on local dynamics and fail to capture long-term dynamic dependencies. In this article, we propose a novel Global-Local Temporal Convolutional Network (GL-TCN) to break through these limitations. Specifically, a novel local temporal convolutional mechanism is proposed to capture the long-term local dynamics effectively. Meanwhile, the global and local flow patterns are integrated to handle the effect of the global flow trend on local dynamics. To the best of our knowledge, this is the first work to utilize the temporal convolutional network for traffic flow prediction. Experiments on two real-world datasets demonstrate the superior performance of our method over several state-of-the-art baselines.

Resting-state functional magnetic resonance imaging (rs-fMRI) has become a popular non-invasive way of diagnosing neurological disorders or their early stages by probing functional connectivity between different brain regions of interest (ROIs) across subjects. In the past decades, researchers have proposed many methods to estimate brain functional networks (BFNs) based on blood-oxygen-level-dependent (BOLD) signals captured by rs-fMRI. However, most of the existing methods estimate BFNs under the assumption that signals are independently sampled, which ignores the temporal dependency and sequential order of different time points (or volumes). To address this problem, in this paper, we first propose a novel BFN estimation model by introducing a latent variable to control the sequence of volumes for encoding the temporal dependency and sequential information of signals into the estimated BFNs. Then, we develop an efficient learning algorithm to solve the proposed model by the alternating optimization scheme. To verify the effectiveness of the proposed method, the estimated BFNs are used to identify subjects with mild cognitive impairment (MCIs) from normal controls (NCs). Experimental results show that our method outperforms the baseline methods in the sense of classification performance.

The buckling responses of the micro-components show size dependency. The general strain gradient theory is applied to explain the size effects. In this paper, we derive the theoretical relations among the classical couple stress theory, the modified couple stress theory and the general theory. The general theory includes all strain gradients and can respectively reduce to the classical couple stress theory and the modified couple stress theory when certain strain gradients are ignored. Subsequently, we further compare the difference of the ability of the general theory and the reduced theories to capture the size-dependent buckling response of the beam. The buckling load of the beam predicted by the general theory is larger than that predicted by the reduced theories. The general theory can predict the size dependency more accurately. In addition, the variation law of buckling load with the location of the upper elastic layer is also clarified. The location variation of the upper elastic layer leads to the change of buckling load, and thus affects the ability of the beam to resist the deformation.

Colonisation of decaying leaves fallen from mangrove trees by bacteria and fungi is thought to play an important role at the base of food webs in most tropical estuaries. Compound-specific isotope analysis of amino acids (CSIA-AA) has enabled the previously difficult methodological task of measuring plant, bacterial and fungal energy flows to food webs. Here, we assessed the biosynthetic origins of amino acids at the base of a mangrove food web using the CSIA-AA approach. Trophic positions of the 2 most common mangrove fauna—fiddler crabs and sesarmid crabs—estimated from nitrogen isotopes in phenylalanine and glutamic acid approached 2, suggesting that these species are herbivores rather than microbivores. Consistent with this finding, carbon isotope fingerprints in AAs did not support the importance of essential AAs derived from fungi and bacteria but rather suggested the importance of those originating from plants, especially microalgae. These results suggest that (1) microbial mineralization of decaying leaves supports the production of more easily assimilated microalgae and (2) bacteria and fungi, as intermediates, also routinely incorporate plant-derived AAs into their biomass.

We propose a point-cloud-centric depth completion method called attention bilateral convolutional network for depth completion (ABCD). The proposed method uses LiDAR data and camera data to improve the resolution of the sparse depth information. Color images, which have been seen as fundamental to depth completion tasks, are inevitably sensitive to light and weather conditions. We designed an attentive bilateral convolutional layer (ABCL) to build a robust depth completion network under diverse environmental conditions. An ABCL efficiently learns geometric characteristics by directly leveraging a 3D point cloud and enhances the representation capability of sparse depth information by highlighting the core while suppressing clutter. The ABCD, with an ABCL as a building block, stably fills the void in sparse depth images even under unfamiliar conditions with minimum dependency on unstable camera sensors. Therefore, the proposed method is expected to be a solution to depth completion problems caused by changes in the environment in which images are captured. Through comparative experiments with other methods using the KITTI [1] and VirtualKITTI2 [2] datasets, we demonstrated the outstanding performance of the proposed method in diverse driving environments.

Rain streaks showing in images or videos would severely degrade the performance of computer vision applications. Thus, it is of vital importance to remove rain streaks and facilitate our vision systems. While recent convolutinal neural network based methods have shown promising results in single image rain removal (SIRR), they fail to effectively capture long-range location dependencies or aggregate convolutional channel information simultaneously. However, as SIRR is a highly illposed problem, these spatial and channel information are very important clues to solve SIRR. First, spatial information could help our model to understand the image context by gathering long-range dependency location information hidden in the image. Second, aggregating channels could help our model to concentrate on channels more related to image background instead of rain streaks. In this paper, we propose a non-local channel aggregation network (NCANet) to address the SIRR problem. NCANet models 2D rainy images as sequences of vectors in three directions, namely vertical direction, transverse direction and channel direction. Recurrently aggregating information from all three directions enables our model to capture the long-range dependencies in both channels and spaitials locations. Extensive experiments on both heavy and light rain image data sets demonstrate the effectiveness of the proposed NCANet model.

This paper proposes a new optimization method and its platform for automatically adjusting the control parameters of a digital active gate driver using a PWM inverter. The proposed optimization method applies the searching parameters for only any duration in an ac current cycle and fixed parameters for the other duration. This enables us to find the optimal operating points of power devices so as to reduce the surge voltage and switching loss with the consideration of their dependency on the load current. Additionally, the proposed optimization method also can find the operating points while the inverter performs a continuous switching operation. For this reason, the proposed optimization method can be applied to a continuous running test of PWM inverters, for example, in a manufacturing process. The validity of the proposed method and platform was evaluated by using a 10-kW three-phase PWM inverter with digital gate drives. The experimental results confirmed that the proposed optimization method makes it possible to find the optimal operating points for reducing the surge voltage and/or the power loss.

The balanced, unbalanced and harmonic current sharing inaccuracy caused by the mismatched wire impedances of distributed generation (DG) units influences the normal operation of islanded microgrids. To deal with this issue, an iterative virtual impedance regulation (IVIR) strategy is proposed in this paper, both the resistive and reactive parts in the output impedances of DG units are regulated. The whole process is decomposed into several successive iterations. In each iteration, the fixed virtual impedance and adaptive virtual impedance regulation are combined to generate a virtual resistance increment and uniform virtual reactance increment according to the uniform output current magnitude and phase angle respectively. Based on these increments, the virtual impedance at fundamental-negative and harmonic frequencies also are modified. With the proposed strategy, all the balanced, unbalanced and harmonic current sharing is accurate with a relatively small virtual impedance. Only the local current information is required for the IVIR process, and the communication is merely used to exchange the VIR mode status flags at the beginning and the end of the IVIR process, the dependency on communication is minimized. The feasibility of the proposed strategy is verified with the simulation and experimental results.

Additive manufacturing offers a high degree of freedom enabling the realization of complex structures such as lattice structures. However, in the framework of selective laser melting, this promised design freedom encounters manufacturing limits that depend on the employed material. The present contribution deals with the manufacturability investigation of inclined filigree lattice struts additively manufactured with AlSi10Mg. The results show a clear parameter dependency of the realizable critical inclination angles, which are far below the commonly accepted 45° to 30° inclination limit. The findings suggest a deeper investigation of the relationship of the strut manufacturability and the process parameters to exceed the inclination limit.

The blooming Internet of Things (IoTs) devices have brought many new types of sensing applications and methods to the traditional cloud-enabled IoTs framework. Hence, the new network framework becomes bidirectional gradually, in which IoTs devices can also perform moderate computation tasks instead of being solely used as data harvesters. This new coming framework known as edge computing significantly improves the traditional cloud-enabled network latency and dependency by shifting part of computation back to “local”. However, new security risks emerge when the edge computing shifts data and models back to the IoTs devices. Acies, a differential privacy based privacy-preserving classification system for edge computing is proposed to secure the classification models offloaded to edge devices. Acies supports popular classifiers such as Nearest Neighborhood, Support Vector Machine and Sparse Representation Classifier with a variety of feature selection methods. According to our evaluation on different datasets, classification models with Acies can be private and maintain high utility. Acies achieves reliable privacy protection under reconstruction attacks with minimal impact on classification accuracy (2% ∽ 5%) only. Acies outperforms the naive input dataset perturbation methods by up to 30% higher classification accuracy when the privacy requirements of the applications is high (the privacy budget e is less than 2).

Relation extraction is a critical natural language processing task. Existing dependency-based models captured long-range syntactic relations, but they usually cannot fully exploit information from sentences. They often used hand-crafted rules to prune redundant edges from dependency trees, but suffer from the imbalance of including and removing contents. When incorporating sequence models, they usually ignored the semantic and syntactic interactions between words. In this paper, we propose to automatically learn relational dependency structures with a fine-grained gating strategy. We decompose the dependency tree into differently informative parts and apply different gating methods to each part. To further capture the word-level interactions, we propose to apply the co-attention mechanism to combine structure and sequence models. We apply a neural network to learn the affinity matrix and derive mutual attention weights between semantic and syntactic representations. We conduct experiments on two benchmark datasets and the results indicate the effectiveness of our method.

Multimodal human sentiment comprehension refers to recognizing human affection from multiple modalities. There exist two key issues for this problem. Firstly, it is difficult to explore time-dependent interactions between modalities and focus on the important time steps. Secondly, processing the long fused sequence of utterances is susceptible to the forgetting problem due to the long-term temporal dependency. In this paper, we introduce a hierarchical learning architecture to classify utterance-level sentiment. To address the first issue, we perform time-step level fusion to generate fused features for each time step, which explicitly models time-restricted interactions by incorporating information across modalities at the same time step. Furthermore, based on the assumption that acoustic features directly reflect emotional intensity, we pioneer emotion intensity attention to focus on the time steps where emotion changes or intense affections take place. To handle the second issue, we propose Residual Memory Network (RMN) to process the fused sequence. RMN utilizes some techniques such as directly passing the previous state into the next time step, which helps to retain the information from many time steps ago. We show that our method achieves state-of-the-art performance on multiple datasets. Results also suggest that RMN yields competitive performance on sequence modeling tasks.

In this review, the impact of the structure dimensionality and surface morphologies of WO3 for efficient detection of gases such as H2, NH3, H2S, CO, O3, VOCs etc. along with the influence of surface functionalization and doping has been discussed.