Search

With the increasing prominence of smart mobile devices, an innovative distributed computing paradigm, namely Mobile Crowdsourcing (MCS), has emerged. By directly recruiting skilled workers, MCS exploits the power of the crowd to complete location-dependent tasks. Currently, based on online social networks, a new and complementary worker recruitment mode, i.e., socially aware MCS, has been proposed to effectively enlarge worker pool and enhance task execution quality, by harnessing underlying social relationships. In this paper, we propose and develop a novel worker recruitment game in socially aware MCS, i.e., Acceptance-aware Worker Recruitment (AWR). To accommodate MCS task invitation diffusion over social networks, we design a Random Diffusion model, where workers randomly propagate task invitations to social neighbors, and receivers independently make a decision whether to accept or not. Based on the diffusion model, we formulate the AWR game as a combinatorial optimization problem, which strives to search a subset of seed workers to maximize overall task acceptance under a pre-given incentive budget. We prove its NP hardness, and devise a meta-heuristic-based evolutionary approach named MA-RAWR to balance exploration and exploitation during the search process. Comprehensive experiments using two real-world data sets clearly validate the effectiveness and efficiency of our proposed approach.

Mobile crowd sensing (MCS) is a popular sensing paradigm that leverages the power of massive mobile workers to perform various location-based sensing tasks. To assign workers with suitable tasks, recent research works investigated mobility prediction methods based on probabilistic and statistical models to estimate the worker's moving behavior, based on which the allocation algorithm is designed to match workers with tasks such that workers do not need to deviate from their daily routes and tasks can be completed as many as possible. In this paper, we propose a new multi-task allocation method based on mobility prediction, which differs from the existing works by (1) making use of workers' historical trajectories more comprehensively by using the fuzzy logic system to obtain more accurate mobility prediction and (2) designing a global heuristic searching algorithm to optimize the overall task completion rate based on the mobility prediction result, which jointly considers workers' and tasks' spatiotemporal features. We evaluate the proposed prediction method and task allocation algorithm using two real-world datasets. The experimental results validate the effectiveness of the proposed methods compared against baselines.

The focal role of flow in promoting desirable outcomes in companies, such as increased employees' well-being and performance, led scholars to study flow in the context of work. However, current measurement approaches which assess flow via self-report scales after task execution are limited due to obtrusiveness and a lack of real-time support. Hence, new measurement approaches must be created to overcome these limitations. In this paper, we use cardiac features (heart rate variability; HRV) and a Random Forest classifier to distinguish high and low flow. Our results from a large-scale lab experiment with 158 participants and a field study with nine participants reveal, that with HRV features alone, flow-classifiers can be built with an accuracy of 68.5% (lab) and 70.6% (field). Our research contributes to the challenge of developing a less obtrusive, real-time measurement method of flow based on physiological features and to investigate flow from a physiological perspective. Our findings may serve as foundation for future work aiming to build physio-adaptive systems which can improve employee's performance. For instance, these systems could ensure that no notifications are forwarded to employees while the system is 'sensing' flow.

Textual emotion detection is an attractive task while previous studies mainly focused on polarity or single-emotion classification. However, human expressions are complex, and multiple emotions often occur simultaneously with non-negligible emotion correlations. In this paper, a Multi-label Emotion Detection Architecture (MEDA) is proposed to detect all associated emotions expressed in a given piece of text. MEDA is mainly composed of two modules: Multi-Channel Emotion-Specified Feature Extractor (MC-ESFE) and Emotion Correlation Learner (ECorL). MEDA captures underlying emotion-specified features through MC-ESFE module in advance. MC-ESFE is composed of multiple channel-wise ESFE networks. Each channel is devoted to the feature extraction of a specified emotion from sentence-level to context-level through a hierarchical structure. Based on obtained features, emotion correlation learning is implemented through an emotion sequence predictor in ECorL. During model training, we define a new loss function, which is called multi-label focal loss. With this loss function, the model can focus more on misclassified positive-negative emotion pairs and improve the overall performance by balancing the prediction of positive and negative emotions. The evaluation of proposed MEDA architecture is carried out on emotional corpus: RenCECps and NLPCC2018 datasets. The experimental results indicate that the proposed method can achieve better performance than state-of-the-art methods in this task.

Exploring large virtual environments, such as cities, is a central task in several domains, such as gaming and urban planning. VR systems can greatly help this task by providing an immersive experience; however, a common issue with viewing and navigating a city in the traditional sense is that users can either obtain a local or a global view, but not both at the same time, requiring them to continuously switch between perspectives, losing context and distracting them from their analysis. In this paper, our goal is to allow users to navigate to points of interest without changing perspectives. To accomplish this, we design an intuitive navigation interface that takes advantage of the strong sense of spatial presence provided by VR. We supplement this interface with a perspective that warps the environment, called UrbanRama, based on a cylindrical projection, providing a mix of local and global views. The design of this interface was performed as an iterative process in collaboration with architects and urban planners. We conducted a qualitative and a quantitative pilot user study to evaluate UrbanRama and the results indicate the effectiveness of our system in reducing perspective changes, while ensuring that the warping doesn't affect distance and orientation perception., Comment: Video: https://www.youtube.com/watch?v=M8BFZnxq-Qg

In this work, we study an important task in location-based services, namely Personalized Route Recommendation (PRR). Given a road network, the PRR task aims to generate user-specific route suggestions for replying to users' route queries. A classic approach is to adapting search algorithms to construct pathfinding-like solutions. These methods typically focus on reducing search space with suitable heuristic strategies. For these search algorithms, heuristic strategies are often handcrafted, which are not flexible to work in complicated task settings. In this paper, we propose to improve search algorithms with neural networks for solving the PRR task based on the widely used A* algorithm. Our model consists of two components. First, we employ attention-based Recurrent Neural Networks (RNN) to model the cost from the source to the candidate location by incorporating useful context information. Second, we propose to use an estimation network for predicting the cost from a candidate location to the destination. The two components are integrated in a principled way for deriving a more accurate cost of a candidate location for the A* algorithm. Extensive experiment results on three real-world datasets have shown the effectiveness and robustness of the proposed model.

Multiple cooperative task allocation (MCTA) is a crucial problem in mobile crowdsensing, where each task requires more than one user to cooperatively complete. As more and more users join sensing tasks in groups, it is indispensable to develop a group-oriented crowdsensing mechanism supporting MCTA. However, existing studies generally focus on a group that can provide sufficient users to accomplish a task. Once these groups no longer exist, the corresponding task will be discarded or be performed with compromised quality. In this paper, we propose a novel three-phase approach named Group-oriented Cooperative Crowdsensing (GoCC) to tackle the MCTA problem in social mobile crowdsensing. This approach exploits real-life relationships in the social network to form compatible groups, which improves the task coverage via group-oriented cooperation while achieving good task cooperation quality. Specifically, phase 1 selects a subset of users on the social network as initial leaders and directly pushes sensing tasks to them. Phase 2 utilizes the leaders to search for their socially connected users to model groups. Phase 3 presents the process of group-oriented task allocation for solving the MCTA problem. Experiments on the real-world dataset validate that our approach significantly outperforms the representative approaches.

Few-shot learning is an emerging yet challenging problem in which the goal is to achieve generalization from only few examples. Meta-learning tackles few-shot learning via the learning of prior knowledge shared across tasks and using it to learn new tasks. One of the most representative meta-learning algorithms is the model-agnostic meta-learning (MAML), which formulates prior knowledge as a common initialization, a shared starting point from where a learner can quickly adapt to unseen tasks. However, forcibly sharing an initialization can lead to conflicts among tasks and the compromised (undesired by tasks) location on optimization landscape, thereby hindering task adaptation. Furthermore, the degree of conflict is observed to vary not only among the tasks but also among the layers of a neural network. Thus, we propose task-and-layer-wise attenuation on the compromised initialization to reduce its adverse influence on task adaptation. As attenuation dynamically controls (or selectively forgets) the influence of the compromised prior knowledge for a given task and each layer, we name our method Learn to Forget (L2F). Experimental results demonstrate that the proposed method greatly improves the performance of the state-of-the-art MAML-based frameworks across diverse domains: few-shot classification, cross-domain few-shot classification, regression, reinforcement learning, and visual tracking.

The task of point of interest (POI) recommendation aims to recommend unvisited places to users based on their check-in history. A major challenge in POI recommendation is data sparsity, because a user typically visits only a very small number of POIs among all available POIs. In this paper, we propose AUC-MF to address the POI recommendation problem by maximizing Area Under the ROC curve (AUC). AUC has been widely used for measuring classification performance with imbalanced data distributions. To optimize AUC, we transform the recommendation task to a classification problem, where the visited locations are positive examples and the unvisited are negative ones. We define a new lambda for AUC to utilize the LambdaMF model, which combines the lambda-based method and matrix factorization model in collaborative filtering. Many studies have shown that geographic information plays an important role in POI recommendation. In this study, we focus on two levels geographic information: local similarity and global similarity. We further show that AUC-MF can be easily extended to incorporate geographical contextual information for POI recommendation.

Mind wandering is often defined as the phenomenon of one's attention drifting away from the current activity toward inner thoughts and feelings. In the laboratory, mind wandering is most frequently assessed with thought reports that are collected while people perform some ongoing activity. It is not clear, however, inasmuch the resulting mind-wandering reports are reflective of person-consistent mind-wandering tendencies and/or situation-driven fluctuations in mind-wandering behavior. To shed light on this question, we tested how consistent mind-wandering reports are across different measurement occasions and tasks to investigate to which extent they indicate individual differences in mind wandering. Results from a latent state-trait analysis showed that mind-wandering reports are occasion-consistent to some extent and also somewhat task-specific. Theoretical implications of these findings are that mind wandering in the laboratory is less affected by situational factors than often assumed, but that individual differences in mind wandering partly depend on the currently ongoing task. Future research should investigate the origins of task-specificity effects on mind wandering and researchers should further incorporate the idea of task-specificity in future theory building. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

One opportunity for organizations to participate in open source software (OSS) development is through organizations OSS (orgsOSS), a term we use to describe a group of organizations that commit resources to collectively develop OSS. This archetype of OSS development is distinct from other types that include organizations, yet is understudied. As organizations increasingly contribute to and rely on OSS as part of their strategy, understanding how they can collaborate to build software holds importance for the future of software development. This study collects a unique dataset of development tasks from a large orgsOSS project spanning over two years and seven releases. Building on existing OSS research, we explore norms with respect to collaboration, i.e., how developers assign, discuss, and complete tasks, in an orgsOSS project. Interestingly, our analysis reveals that developers in orgsOSS do not always adhere to ideals of widespread sharing and participation espoused by traditional OSS, however some developer and task characteristics helped foster these ideals. Based on these and other findings, we develop a set of propositions and associated collaboration mechanisms that are important to future orgsOSS and other similarly structured software development projects.

Few-shot learning under the N-way K-shot setting (i.e., K annotated samples for each of N classes) has been widely studied in relation extraction (e.g., FewRel) and image classification (e.g., Mini-ImageNet). Named entity recognition (NER) is typically framed as a sequence labeling problem where the entity classes are inherently entangled together because the entity number and classes in a sentence are not known in advance, leaving the N-way K-shot NER problem so far unexplored. In this paper, we first formally define a more suitable N-way K-shot setting for NER. Then we propose FewNER, a novel meta-learning approach for few-shot NER. FewNER separates the entire network into a task-independent part and a task-specific part. During training in FewNER, the task-independent part is meta-learned across multiple tasks and a task-specific part is learned for each single task in a low-dimensional space. At test time, FewNER keeps the task-independent part fixed and adapts to a new task via gradient descent by updating only the task-specific part, resulting in it being less prone to overfitting and more computationally efficient. The results demonstrate that FewNER achieves state-of-the-art performance against nine baseline methods by significant margins on three adaptation experiments.

Crowdsourced software testing (short for crowdtesting) is a special type of crowdsourcing. It requires that crowdworkers master appropriate skill-sets and commit significant effort for completing a task. Abundant uncertainty may arise during a crowdtesting process due to imperfect information between the task requester and crowdworkers. For example, a worker frequently chooses tasks in an ad hoc manner in crowdtesting context, and an inappropriate task selection may lead to the worker's failing to detect any bugs, and significant testing effort unpaid and wasted. Recent studies have explored methods for supporting task requesters to make informed decisions on task pricing, worker recommendation, and so on. Unfortunately, very few study offers decision making support from the crowdworkers' perspectives. We motivate this study through a pilot study, revealing the large portion (74\%) of unpaid crowdworkers' effort due to the inappropriate task choice. Drawn from our previous work on context-aware crowdworker recommendations, we advocate a more effective alternative to manual task selection would be to provide contextualized and personalized task recommendation considering the diverse distribution of worker preference and expertise, with objectives to increase their winning chances and to potentially reduce the frequency of unpaid crowd work. This paper proposes a context-aware personalized task recommendation approach PTRec, consisting of a testing context model and a learning-based task recommendation model to aid dynamic worker decision in selecting crowdtesting tasks. The testing context model is constructed in two perspectives, i.e., process context and resource context, to capture the in-process progress-oriented information and crowdworkers' characteristics respectively. Built on top of this context model, the learning-based task recommendation model extracts 60 features automatically, and employs random forest learner to generate dynamic and personalized task recommendation which matches workers' expertise and interest. The evaluation is conducted on 636 crowdtesting tasks involving 2,404 crowdworkers from one of the largest crowdtesting platforms, and results show the potential in recommending proper tasks to workers so as to improve bug detection efficiency and increase their monetary earnings.

In this article, fault diagnosis is of great significance for system health maintenance. For real applications, diagnosis accuracy suffers from unbalanced data patterns, where normal data are usually abundant than anomaly ones, leading to tremendous diagnosis obstacles. Therefore, it is challenging to use only normal data for fault diagnosis under this imbalanced condition. In addition, a single fault diagnosis model can only conduct one fault diagnosis task in most of cases. Accordingly, a one-class generative adversarial detection (OCGAD) framework based on semisupervised learning is proposed to learn one-class latent knowledge for dealing with multiple semisupervised fault diagnosis tasks, i.e., fault detection using only normal knowledge learning, novelty detection from unknown conditional data, and fault classification with unlabeled data. A bi-directional generative adversarial network (Bi-GAN) is first trained with only normal data. A one-class support vector machine is then established using features exacted by Bi-GAN from signals acquired from an attitude sensor for multifunctional fault detection. The presented OCGAD model is validated using an industrial robot with experiments of three fault detection tasks. The results demonstrate that the present model has good performance for dealing with multiple semisupervised diagnosis problems. info:eu-repo/semantics/publishedVersion

Workers participating in a crowdsourcing platform can have a wide range of abilities and interests. An important problem in crowdsourcing is the task recommendation problem, in which tasks that best match a particular worker's preferences and reliabilities are recommended to that worker. A task recommendation scheme that assigns tasks more likely to be accepted by a worker who is more likely to complete it reliably results in better performance for the task requester. Without prior information about a worker, his preferences and reliabilities need to be learned over time. In this paper, we propose a multi-armed bandit (MAB) framework to learn a worker's preferences and his reliabilities for different categories of tasks. However, unlike the classical MAB problem, the reward from the worker's completion of a task is unobservable. We therefore include the use of gold tasks (i.e., tasks whose solutions are known \emph{a priori} and which do not produce any rewards) in our task recommendation procedure. Our model could be viewed as a new variant of MAB, in which the random rewards can only be observed at those time steps where gold tasks are used, and the accuracy of estimating the expected reward of recommending a task to a worker depends on the number of gold tasks used. We show that the optimal regret is $O(\sqrt{n})$, where $n$ is the number of tasks recommended to the worker. We develop three task recommendation strategies to determine the number of gold tasks for different task categories, and show that they are order optimal. Simulations verify the efficiency of our approaches. Agency for Science, Technology and Research (A*STAR) Ministry of Education (MOE) Accepted version This work was supported in part by the Singapore Ministry of Education Academic Research Fund Tier 2 grant MOE2018-T2-2-019 and by A*STAR under its RIE2020 Advanced Manufacturing and Engineering (AME) Industry Alignment Fund – Pre Positioning (IAF-PP) (Grant No. A19D6a0053).

Predictive Maintenance technologies are particularly appealing for Industrial Equipment producers, as they pave the way to the selling of high added-value services and customized maintenance plans. However, standard Predictive Maintenance approaches assume the availability of sensor measurements, and the costs associated with adding sensors or remotely accessing sensor readings may discourage the development of such technologies. In this context, Alarm Forecasting can be very useful as it represents a low-cost alternative or helpful support to sensor-based Predictive Maintenance. In this work, we propose a new formulation for the Alarm Forecasting problem, framed as a multi-label classification task.

The predictive business process monitoring is a family of online approaches to predict the unfolding of running traces basedon the knowledge learned from historical event logs. In this paper, we address the task of predicting the next trace activity from the completed events in a running trace. This is an important business capability as counting on accurate predictions of the future activities may allow companies to guarantee the higher utilization by acting proactively in anticipation. We propose a novel predictive process approach that couples multi-view learning and deep learning, in order to gain predictive accuracy by accounting for the variety ofinformation possibly recorded in event logs. Experiments with various benchmark event logs prove the effectiveness of the proposed approach compared to several recent state-of-the-art methods.

In human-robot shared manufacturing contexts, product parts or tools hand-over between the robot and the human is an important collaborative task. Facilitating the robot to figure out and predict human hand-over intentions correctly to improve the task efficiency in human-robot collaboration is therefore a necessary issue to be addressed. In this study, a teaching-learning-prediction (TLP) framework is proposed for the robot to learn from its human partner's multimodal demonstrations and predict human hand-over intentions. In this approach, the robot can be programmed by the human through demonstrations utilizing natural language and wearable sensors according to task requirements and the human's working preferences. Then the robot learns from human hand-over demonstrations online via extreme learning machine (ELM) algorithms to update its cognition capacity, allowing the robot to use its learned policy to predict human intentions actively and assist its human companion in hand-over tasks. Experimental results and evaluations suggest that the human may program the robot easily by the proposed approach when the task changes, as the robot can effectively predict hand-over intentions with competitive accuracy to complete the hand-over tasks.

As multiple software components with different safety-criticality levels are integrated on a shared computing platform, a real-time embedded system becomes a mixed-criticality (MC) system, which should provide timing guarantees at all different levels of assurance to software components with different criticality levels. In the real-time systems community, the concept of an MC system is regarded as a promising, emerging solution to solve an inherent challenge of real-time systems: pessimistic reservation of computing resources, which yields a low resource-utilization for the sake of guaranteeing timing requirements. Since a timing guarantee should be provided before a real-time system starts to operate, its feasibility has been extensively studied for single-criticality systems; however, the same cannot be said for MC systems. In this article, we develop necessary feasibility tests for MC real-time embedded systems, which is the first study that yields non-trivial results for MC necessary feasibility on both uniprocessor and multiprocessor platforms. To this end, we investigate characteristics of MC necessary feasibility conditions, and identify new challenges posed by the characteristics. By addressing those challenges, we develop two collective necessary feasibility tests and their simplified versions, which are able to exploit a tradeoff between capability in finding infeasible task sets and time-complexity. The simulation results demonstrate that the proposed tests find a number of additional infeasible task sets for both uniprocessor and multiprocessor platforms, which have been proven neither feasible nor infeasible by any existing studies.

Recent years have seen a rapidly growing number of online reviews of products. As a result, it is often not possible for customers to go through each review before making purchase decisions. One way to address this problem is to build a system for automatically addressing the helpfulness of reviews and present only those reviews that are determined to be helpful by the system to an end user. The vast majority of existing approaches to the task of review helpfulness prediction are based on hand-crafted features, thus making system performance heavily dependent on the quality of these features. In light of this weakness, we propose a new model of review helpfulness prediction using a combination of Convolutional Neural Network (CNN) and TransE wherein hand-crafted features can also be incorporated to improve the output. Specifically, CNN enables us to learn the semantic information from a review and TransE is used to capture the relationship between different entities mentioned in the review. Experiments on the Amazon product review datasets demonstrate that our approach significantly outperforms the state of the art.

The classical planning problem aims to find a sequence of permitted actions leading a system to a designed state, i.e., to achieve the system's task. However, in many realistic cases we also have requirements on how to complete the task, indicating that some behaviors and situations are more preferred than others. In this paper, we present the probabilistic preference-based planning problem (P4) for Markov decision processes, where the preferences are defined based on an enriched probabilistic LTL-style logic. We first recall Solver P4 Solver, an SMT-based planner computing the preferred plan by reducing the problem to a quadratic programming one previously developed to solve P4. To improve computational efficiency and scalability, we then introduce a new encoding of the probabilistic preference-based planning problem as a multi-objective model checking one, and propose the corresponding planner SolverMOP4 Solver MO. We illustrate the efficacy of both planners on some selected case studies to show that the model checking-based algorithm is considerably more efficient than the quadratic-programming-based one.

Many software engineering tools build and evaluate their models based on historical data to support development and process decisions. These models help us answer numerous interesting questions, but have their own caveats. In a real-life setting, the objective function of human decision-makers for a given task might be influenced by a whole host of factors that stem from their cognitive biases, subverting the ideal objective function required for an optimally functioning system. Relying on this data as ground truth may give rise to systems that end up automating software engineering decisions by mimicking past sub-optimal behaviour. We illustrate this phenomenon and suggest mitigation strategies to raise awareness.

A Relational-Sequential dataset (or RS-dataset for short) contains records comprised of a patient's values in demographic attributes and their sequence of diagnosis codes. The task of clustering an RS-dataset is helpful for analyses ranging from pattern mining to classification. However, existing methods are not appropriate to perform this task. Thus, we initiate a study of how an RS-dataset can be clustered effectively and efficiently. We formalize the task of clustering an RS-dataset as an optimization problem. At the heart of the problem is a distance measure we design to quantify the pairwise similarity between records of an RS-dataset. Our measure uses a tree structure that encodes hierarchical relationships between records, based on their demographics, as well as an edit-distance-like measure that captures both the sequentiality and the semantic similarity of diagnosis codes. We also develop an algorithm which first identifies k representative records (centers), for a given k, and then constructs k clusters, each containing one center and the records that are closer to the center compared to other centers. Experiments using two Electronic Health Record datasets demonstrate that our algorithm constructs compact and well-separated clusters, which preserve meaningful relationships between demographics and sequences of diagnosis codes, while being efficient and scalable.

Just-in-time (JIT) bug prediction is an effective quality assurance activity that identifies whether a code commit will introduce bugs into the mobile app, aiming to provide prompt feedback to practitioners for priority review. Since collecting sufficient labeled bug data is not always feasible for some mobile apps, one possible approach is to leverage cross-app models. In this work, we propose a new cross-triplet deep feature embedding method, called CDFE, for cross-app JIT bug prediction task. The CDFE method incorporates a state-of-the-art cross-triplet loss function into a deep neural network to learn high-level feature representation for the cross-app data. This loss function adapts to the cross-app feature learning task and aims to learn a new feature space to shorten the distance of commit instances with the same label and enlarge the distance of commit instances with different labels. In addition, this loss function assigns higher weights to losses caused by cross-app instance pairs than that by intra-app instance pairs, aiming to narrow the discrepancy of cross-app bug data. We evaluate our CDFE method on a benchmark bug dataset from 19 mobile apps with two effort-aware indicators. The experimental results on 342 cross-app pairs show that our proposed CDFE method performs better than 14 baseline methods.

Task allocation is a key issue in Mobile Crowd Sensing (MCS), which affects the sensing efficiency and quality. Previous studies focus on the allocation of tasks that have already been published to the platform, but there are some very urgent tasks that need to be executed once they were detected. Existing studies for either delay-tolerant or time-sensitive tasks have a certain time delay from task publishing to execution, so it is impossible to achieve task detection then execution seamlessly. Thus, we first define the Instant Sensing and then Instant Actuation (ISIA) problem in MCS and propose a new model to solve it. We aim to allocate POIs where ISIA tasks are most likely to be detected to workers with similar sensing types so that these tasks can be executed once they are detected. This paper presents a two-phase task allocation framework called ISIATasker. In the sensing locations clustering and sensor selection phase, we cluster independent sensing locations into several POIs and then select the optimal cooperative sensor set for each POI to assist workers in completing sensing. In the POIs allocation phase, we propose a method called PA-DDQN based on deep reinforcement learning to plan an optimal path for each worker, thus maximize the overall sensing type matching degree and POI coverage to enable instant sensing and then instant actuation. Finally, extensive experiments are conducted based on real-world datasets to demonstrate that the matching degree and POI coverage of ISIATasker outperforms other baselines.

In this work, we formulate the problem of estimating and selecting task-relevant temporal signal segments from a single EEG trial in the form of a Markov decision process and propose a novel reinforcement-learning mechanism that can be combined with the existing deep-learning based BCI methods. To be specific, we devise an actor-critic network such that an agent can determine which timepoints need to be used (informative) or discarded (uninformative) in composing the intention-related features in a given trial, and thus enhancing the intention identification performance. To validate the effectiveness of our proposed method, we conducted experiments with a publicly available big MI dataset and applied our novel mechanism to various recent deep-learning architectures designed for MI classification. Based on the exhaustive experiments, we observed that our proposed method helped achieve statistically significant improvements in performance., 8 pages, 6 figures, 2 tables, and under review

Part-level representations are important for robust person re-identification (ReID), but in practice feature quality suffers due to the body part misalignment problem. In this paper, we present a robust, compact, and easy-to-use method called the Multi-task Part-aware Network (MPN), which is designed to extract semantically aligned part-level features from pedestrian images. MPN solves the body part misalignment problem via multi-task learning (MTL) in the training stage. More specifically, it builds one main task (MT) and one auxiliary task (AT) for each body part on the top of the same backbone model. The ATs are equipped with a coarse prior of the body part locations for training images. ATs then transfer the concept of the body parts to the MTs via optimizing the MT parameters to identify part-relevant channels from the backbone model. Concept transfer is accomplished by means of two novel alignment strategies: namely, parameter space alignment via hard parameter sharing and feature space alignment in a class-wise manner. With the aid of the learned high-quality parameters, MTs can independently extract semantically aligned part-level features from relevant channels in the testing stage. MPN has three key advantages: 1) it does not need to conduct body part detection in the inference stage; 2) its model is very compact and efficient for both training and testing; 3) in the training stage, it requires only coarse priors of body part locations, which are easy to obtain. Systematic experiments on four large-scale ReID databases demonstrate that MPN consistently outperforms state-of-the-art approaches by significant margins. Code is available at https://github.com/WangKan0128/MPN., Accepted Version to IEEE Transactions on Pattern Analysis and Machine Intelligence

Efficient task and resource allocation techniques are critical to managing the relationships between the components of cloud, fog, and mist-assisted internet of things networks. Fulfilling this function necessarily implicates concerns between two affected groups, users, who prioritize cost-effectiveness and latency, and service providers, who prioritize efficient and cost-effective resource management. While there is no single solution that is capable of simultaneously wholly optimizing the experiences of both groups, solutions that ensure mutual satisfaction can be achieved. To accomplish this, we developed an algorithm that first derives two objective functions, user and service provider satisfaction, from data concerning service provisioning, user preferences, and resources utilization. The algorithm then combines these functions into a mutual objective function that maximizes satisfaction of both individuals. Next, available computing nodes are ordered in a list, prioritizing by compromising factors, and the most appropriate node(s) for task completion are selected. The proposed algorithm was tested extensively through simulations and compared with existing techniques. Ultimately, the proposed algorithm outperformed alternatives across every metric, illustrating its utility as a means of achieving mutual satisfaction and improving quality of service.

Unintended motion has been one of the major causes of intra-operative injuries in tele-operated surgeries. Due to the large workspace discrepancy between master and slave manipulators, the tip of the slave may deviate from the intended master command without prior notice, when the slave is moved beyond its joint limits. Conventional solutions like the constrained optimization based Virtual Fixture (VF) method suffered from non-intuitive tip motion management and unnatural haptics in high-dimensional systems. To this end, we propose a Task Space Virtual Fixture (TSVF) architecture to systematically address those issues by forbidden-region VF design. It decomposes the high-dimensional task space into low-dimensional task sub-spaces according to its inherent topology. In each sub-space, we design a human-centric TSVF geometry and controller to manage the tip behavior by exploiting the nonlinear kinematics mapping. This architecture builds a real-time TSVF system with natural and predictable haptics. To showcase this concept, we designed and implemented the proposed TSVF system for the state-of-the-art surgical system, da Vinci Research Kit (dVRK). Simulations, experiments, and human-factor user study verified its effectiveness and intuitiveness. In the user study, our proposed TSVF system demonstrated the most easy-to-understand tip behavior and showed a significant positive effect over haptics likeability.

In mobile crowd sensing, the mobile terminal integrates a variety of widely distributed sensing devices and communication ports. Sensing devices and communication ports can collect and share all kinds of perception data. However, inherent contradictions exist among perceived ability, communication port, and moving rule while collecting real-time and accurate sensing information. This article mainly focused on recruited and selected mobile nodes and assigned sensing tasks to improve the quality of sensing information. The optimization of the implementation stage of the sensing task is beyond the scope of this study. This article proposes a utility-based sensing task decomposition and subcontract algorithm, which is a method of sensing data acquisition that establishes direct collaboration between mobile nodes. A mobility model based on Markov chain is established to forecast the spatial distribution of sensing nodes. A utility function is designed to estimate the sensing task execution capacity of sensing nodes based on spatial distribution and tempo-spatial coverage of the collected data. The sensing tasks are then decomposed and subcontracted to neighboring nodes according to the utilities of the neighboring nodes to the decomposed sensing tasks. This method improves the quality of sensing data in terms of sensing data coverage and finished ratio of sensing task.

Meta-learning automatically infers an inductive bias by observing data from a number of related tasks. The inductive bias is encoded by hyperparameters that determine aspects of the model class or training algorithm, such as initialization or learning rate. Meta-learning assumes that the learning tasks belong to a task environment, and that tasks are drawn from the same task environment both during meta-training and meta-testing. This, however, may not hold true in practice. In this paper, we introduce the problem of transfer meta-learning, in which tasks are drawn from a target task environment during meta-testing that may differ from the source task environment observed during meta-training. Novel information-theoretic upper bounds are obtained on the transfer meta-generalization gap, which measures the difference between the meta-training loss, available at the meta-learner, and the average loss on meta-test data from a new, randomly selected, task in the target task environment. The first bound, on the average transfer meta-generalization gap, captures the meta-environment shift between source and target task environments via the KL divergence between source and target data distributions. The second, PAC-Bayesian bound, and the third, single-draw bound, account for this shift via the log-likelihood ratio between source and target task distributions. Furthermore, two transfer meta-learning solutions are introduced. For the first, termed Empirical Meta-Risk Minimization (EMRM), we derive bounds on the average optimality gap. The second, referred to as Information Meta-Risk Minimization (IMRM), is obtained by minimizing the PAC-Bayesian bound. IMRM is shown via experiments to potentially outperform EMRM.

Abstract. Task performance of digit span has been widely used in the research on human short-term memory. The present study was conducted to show that the dynamic change of underlying mental effort can be further estimated by measuring the strength of theta oscillations at a forehead site on the scalp. Fourteen healthy adults ( Mage = 26.1 years) performed a passive listening (PL) task and an auditory digit span (DS) task, and electroencephalography (EEG) data were recorded simultaneously during the two tasks. Considering that the digit span paradigm has often been conducted in a non-laboratory location, the EEG data were collected with a wireless single-channel headset system. The headset system was validated in this study by replicating the EEG (an enhancement of frontal theta power) as well as event-related potential (N200 and P300) responses to the deviant tone stimuli in the PL task. The outcomes of the DS task showed that the memory span of the participants was at least eight items. Moreover, frontal theta power in response to a list of six to eight digits increased significantly. This pattern of results supports a hypothesis that additional mental effort is required for short-term retention of verbal items when the number of stimulus items exceeds the newly proposed limit of short-term memory capacity. Some strengths and limitations of the current EEG headset system are also discussed.

Person-dependent facial expression recognition has received considerable research attention in recent years. Unfortunately, different identities can adversely influence recognition accuracy, and the recognition task becomes challenging. Other adverse factors, including limited training data and improper measures of facial expressions, can further contribute to the above dilemma. To solve these problems, a novel identity-aware method is proposed in this study. Furthermore, this study also represents the first attempt to fulfill the challenging person-dependent facial expression recognition task based on deep metric learning and facial image synthesis techniques. Technically, a StarGAN is incorporated to synthesize facial images depicting different but complete basic emotions for each identity to augment the training data. Then, a deep-convolutional-neural-network-based network is employed to automatically extract latent features from both real facial images and all synthesized facial images. Next, a Mahalanobis metric network trained based on extracted latent features outputs a learned metric that measures facial expression differences between images, and the recognition task can thus be realized. Extensive experiments based on several well-known publicly available datasets are carried out in this study for performance evaluations. Person-dependent datasets, including CK+, Oulu (all 6 subdatasets), MMI, ISAFE, ISED, etc., are all incorporated. After comparing the new method with several popular or state-of-the-art facial expression recognition methods, its superiority in person-dependent facial expression recognition can be proposed from a statistical point of view.

In this paper, the problem of minimizing energy and time consumption for task computation and transmission in mobile edge computing-enabled balloon networks is investigated. In the considered network, high-altitude balloons (HABs), acting as flying wireless base stations, can use their powerful computational abilities to process the computational tasks offloaded from their associated users. Since the data size of each user’s computational task varies over time, the HABs must dynamically adjust their resource allocation schemes to meet the users’ needs. This problem is posed as an optimization problem whose goal is to minimize the energy and time consumption for task computation and transmission by adjusting the user association, service sequence, and task allocation schemes. To solve this problem, a support vector machine (SVM)-based federated learning (FL) algorithm is proposed to determine the user association proactively. The proposed SVM-based FL method enables HABs to cooperatively build an SVM model that can determine all user associations without any transmissions of either user historical associations or computational tasks to other HABs. Given the predictions of the optimal user association, the service sequence and task allocation of each user can be optimized so as to minimize the weighted sum of the energy and time consumption. Simulations with real city cellular traffic data show that the proposed algorithm can reduce the weighted sum of the energy and time consumption of all users by up to 15.4% compared to a conventional centralized method.

In this article, we present an online scalable tele-impedance framework, which enables the individual and collaborative control of multiple different robotic platforms. The framework provides an intuitive low-cost interface with visual feedback and a SpaceMouse, through which the operator can define the desired task-level trajectories and impedance profiles. With a simple mouse click, the user can switch between the robots and the collaborative operation mode. The control, subsequently, manages the distribution of the required parameters into the involved robots. Thanks to the introduced virtual hand concept, where each robot is defined as a finger, new robots can be easily added or removed via their kinodynamic parameters. The proposed framework was evaluated with three different experiments: a simulated auscultation on a mock-up patient, a cooperative task where a robot drives the patient on a wheelchair and a different robot performs the auscultation, and a collaborative task where two robots relocate a container. The results demonstrate the capabilities of the framework in terms of adaptability to different robotic platforms, the number of robots involved, and the task requirements. Additionally, quantitative and subjective analysis of 12 subjects showed how the developed interface, even in the presence of inaccurate visual feedback, allowed a smooth and accurate execution of the tasks.

The study of human behaviors in cognitive sciences provides clues to understand and describe people’s personal and interpersonal functioning. In particular, the temporal analysis of behavioral dynamics can be a powerful tool to reveal events, correlations and causalities but also to discover abnormal behaviors. However, the annotation of these dynamics can be expensive in terms of temporal and human resources. To tackle this challenge, this paper proposes a methodology to semi-automatically annotate behavioral data. Behavioral dynamics can be expressed as sequences of simple dynamical processes: transitions between such processes are generally known as change-points. This paper describes the necessary steps to detect and classify change-points in behavioral data by using a dataset collected in a real use-case scenario. This dataset includes motor observations from children with typical development and with neuro-developmental disorders. Abnormal movements which are present in such disorders are useful to validate the system in conditions that are challenging even for experienced annotators. Results show that the system: can be effective in the semi-automated annotation task; can be efficient in presence of abnormal behaviors; may achieve good performance when trained with limited manually annotated data.

The ability to collaborate with previously unseen human teammates is crucial for artificial agents to be effective in human-agent teams (HATs). Due to individual differences and complex team dynamics, it is hard to develop a single agent policy to match all potential teammates. In this article, we study both human-human and HAT in a dyadic cooperative task, Team Space Fortress. Results show that the team performance is influenced by both players’ individual skill level and their ability to collaborate with different teammates by adopting complementary policies. Based on human-human team results, we propose an adaptive agent that identifies different human policies and assigns a complementary partner policy to optimize team performance. The adaptation method relies on a novel similarity metric to infer human policy and then selects the most complementary policy from a pretrained library of exemplar policies. We conducted human-agent experiments to evaluate the adaptive agent and examine mutual adaptation in HAT. Results show that both human adaptation and agent adaptation contribute to team performance.

Vision-language navigation (VLN) is the task of navigating an embodied agent to carry out natural language instructions inside real 3D environments. In this paper, we study how to address three critical challenges for this task: the cross-modal grounding, the ill-posed feedback, and the generalization problems. First, we propose a novel Reinforced Cross-Modal Matching (RCM) approach that enforces cross-modal grounding both locally and globally via reinforcement learning (RL). Particularly, a matching critic is used to provide an intrinsic reward to encourage global matching between instructions and trajectories, and a reasoning navigator is employed to perform cross-modal grounding in the local visual scene. Evaluation on a VLN benchmark dataset shows that our RCM model significantly outperforms baseline methods by 10 percent on Success Rate weighted by Path Length (SPL) and achieves the state-of-the-art performance. To improve the generalizability of the learned policy, we further introduce a Self-Supervised Imitation Learning (SIL) method to explore and adapt to unseen environments by imitating its own past, good decisions. We demonstrate that SIL can approximate a better and more efficient policy, which tremendously minimizes the success rate performance gap between seen and unseen environments (from 30.7 to 11.7 percent).

Mind wandering (MW) is a highly prevalent phenomenon despite its negative consequences on behavior. Current views about its origin share the idea that MW occurs due to changes in the executive functions system. Here, we argue that not all instances of MW are necessarily related to changes in that system. Combining results from MW and sleep research, we propose that MW could also be related to the depletion of resources in primary task-related networks. To test this hypothesis, participants performed four sessions of the texture discrimination task (TDT) on a day. The TDT is a perceptual learning task in which performance is negatively related to the local build-up of sleep pressure. During the TDT, MW was recorded in both a subjective (i.e., with thought probes) and an objective (i.e., phasic pupillary response) manner. Results showed that accuracy on the TDT was mirrored in the objective measure of MW. For the subjective measure, the pattern was similar to that of task performance but could not be interpreted as reliable. These results demonstrate that not all MW is necessarily related to changes in the executive system and support the hypothesis that MW could be related to the depletion of local, task-related resources. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

It is important to encourage older adults to remain active when interacting with assistive robots. This study proposes a schematic model for integrating levels of automation (LOAs) and transparency (LoTs) in assistive robots to match the preferences and expectations of older adults. Metrics to evaluate LOA and LoT design combinations are defined. We develop two distinctive test cases to examine interaction design considerations for robots working for this population in everyday tasks: a person-following task with a mobile robot and a table-setting task with a robot manipulator. Evaluations in user studies with older adults reveal that LOA and LoT combinations influence interaction elements. Low LOA and high LoT encouraged activity engagement while receiving adequate information regarding the robot's behavior. The variety of objective and subjective metrics is essential to provide a holistic framework for evaluating the interaction.

In mobile crowdsensing, it is a challenge to assign tasks to appropriate smartphones. Existing task allocation mechanisms mainly aim at optimizing the global system performance, while ignoring the personal preferences of individual crowdsensing tasks and smartphone users. Nevertheless, in an open crowdsensing system, a task assignment is prone to be unstable if smartphone users or tasks have incentives to deviate from the global assignment, and seek for alternative choices to improve their own utilities. Besides that, during task competition, the rational smartphone users might choose to adjust their payments after the first few failures, which however, brings new challenges in achieving the stability. To address these issues, this paper constructs a distributed many-to-many matching model to capture the interaction between crowdsensing tasks and smartphone users, taking into account the budget constraints of tasks. Then, we design a stable matching algorithm to allocate the tasks to the users, and determine their payments. We prove that the proposed algorithm achieves several desirable properties including individual rationality, stability, and convergency. It is also proved that the proposed scheme achieves at least half of the optimal system efficiency when each smartphone provides homogeneous service quality. Finally, simulation results confirm the effectiveness of the proposed scheme.

The minimum travel distance of task participants is one of the significant optimization objectives of privacy-preserving task assignment in mobile crowdsensing (MCS). However, when the travel distance is minimized, most of the previous schemes only focus on the task participant privacy and disregard the task requester privacy. Moreover, existing solutions usually only support the constraint of a single type, such as equality constraints or range constraints. In this paper, we propose a bilateral privacy-preserving Task Assignment mechanism for MCS (iTAM), which protects not only the task participants privacy but also the task requesters privacy and can minimize the travel distance. Furthermore, iTAM provides both equality and range constraints of task assignment by utilizing the Paillier cryptosystem. To accommodate the multiple relations between the task participants and the task, we propose the single/multiple task participants selection problems for a task requiring task participants to compete and cooperate. Experimental evaluations over synthetic and real-world data illustrate that iTAM is feasible and effective. Compared with the state-of-the-art, iTAM positively solves the optimal problem of travel distance. The complexities of iTAM are $\mathcal {O}(n)$ O ( n ) and $\mathcal {O}(n\log n)$ O ( n log n ) for a single and multiple task participants selection problems, respectively.

This article considers human-autonomy teams (HATs) in which two human team members interact and collaborate with an autonomous teammate to achieve a common task while dealing with unexpected technological failures that were imposed either in automation or autonomy. A Wizard of Oz methodology is used to simulate the autonomous teammate. One of the critical aspects of HAT performance is the trust that develops over time as team members interact with each other in a dynamic task environment. For this reason, it is important to examine the dynamic nature of teammate trust through real-time measures of team interactions. This article examines team interaction and trust to understand better how they change under automation and autonomy failures. Thus, we address two research questions: 1) How does trust in HATs evolve over time?; and 2) How is the relationship between team interaction and trust impacted by the failures? We hypothesize that trust in HATs will decrease as autonomy failures increase. We also hypothesize that team interaction would be related to the development of trust and recovery from the failures. The results implicate three general trends: 1) team interaction dynamics are linked to the development of trust in HATs; 2) trust in the autonomous teammate is only associated with recovery from autonomy failures; 3) team interaction dynamics are related to both automation and autonomy failure recovery.

As a key research issue in mobile crowdsensing (MCS), recent studies on task recommendation have begun to focus on recommending tasks to participants according to the learned participant preferences. The common drawbacks of these studies are that, on the one hand, the factors affecting participant preferences are predefined, which is not practical as the influential factors are quite complex and a full map of participant profiles needs to be preexisted. On the other hand, they do not consider how to update the recommendation dynamically. To overcome these drawbacks, a profile-free and real-time task recommendation method is proposed in this work. First, we apply the recommendation systems to MCS to realize profile-free task recommendations. Second, a participant-task-location tensor is constructed, based on which an improved tensor factorization method is presented to provide task recommendations for participants at a given location. Finally, we design a real-time update algorithm based on the idea of one update at a time to update task recommendation lists for participants in real time. Based on real-world trace data sets, extensive evaluations show that the proposed method has obvious advantages over other baselines in terms of accuracy and time cost.

High Recall Information Retrieval (HIRE) aims at identifying all (or nearly all) relevant documents given a query. HIRE, for example, is used in the systematic literature review task, where the goal is to identify all relevant scientific articles. The documents selected by HIRE as relevant define the user effort to identify the target information. On this way, one of HIRE goals is only to return relevant documents avoiding overburning the user with non-relevant information. Traditionally, supervised machine learning algorithms are used as HIRE' core to produce a ranking of relevant documents (e.g. SVM). However, such algorithms depend on an initial training set (seed) to start the process of learning. In this work, we propose a new approach to produce the initial seed for HIRE focus on reducing the user effort. Our approach combines an active learning approach with a raking strategy to select only the informative examples. The experimentation shows that our approach is able to reduce until 18% the labeling effort with competitive recall.

The grade groups (GGs) of Gleason scores (Gs) is the most critical indicator in the clinical diagnosis and treatment system of prostate cancer. End-to-end method for stratifying the patient-level pathological appearance of prostate cancer (PCa) in magnetic resonance (MRI) are of high demand for clinical decision. Existing methods typically employ a statistical method for integrating slice-level results to a patient-level result, which ignores the asymmetric use of ground truth (GT) and overall optimization. Therefore, more domain knowledge (e.g., diagnostic logic of radiologists) needs to be incorporated into the design of the framework. The patient-level GT is necessary to be logically assigned to each slice of a MRI to achieve joint optimization between slice-level analysis and patient-level decision-making. In this paper, we propose a framework (PCa-GGNet-v2) that learns from radiologists to capture signs in a separate two-dimensional (2-D) space of MRI and further associate them for the overall decision, where all steps are optimized jointly in an end-to-end trainable way. In the training phase, patient-level prediction is transferred from weak supervision to supervision with GT. An association route records the attentional slice for reweighting loss of MRI slices and interpretability. We evaluate our method in an in-house multi-center dataset ( N = 570) and PROSTATEx ( N = 204), which yields five-classification accuracy over 80% and AUC of 0.804 at patient-level respectively. Our method reveals the state-of-the-art performance for patient-level multi-classification task to personalized medicine.

Deep reinforcement learning (DRL) excels at playing a wide variety of simulated games and allows for a generic learning process that does not consider a specific knowledge of the task. However, due to the fact that a large prohibitively number of interactions with the environment are required and that the initial policy behavior is almost random, such an algorithm cannot be trained directly in a real-world environment while satisfying given safety constraints. In this article, a control framework based on DRL that shifts toward training directly in the transient real-world environment is proposed. This research is working on the assumption that some demonstration knowledge that operates under previous controllers and an abstract of the agent environment dynamics are available. By encoding this prior knowledge into a sophisticated learning architecture, a warm-starting DRL algorithm with a safe exploration guarantee can be anticipated. Taking the boost control problem for a variable geometry turbocharger equipped diesel engine as an example, the proposed algorithm improves the initial performance by 74.6% and the learning efficiency by an order of magnitude in contrast to its vanilla counterpart. Compared with other existing DRL-based powertrain control methods, the proposed algorithm can realize the “model-free” concept in the strict sense, making it attractive for future DRL-based powertrain control algorithms to build on.