Search

Internet of Things (IoT) has brought changes in many fields by joining physical space with the cyber space. The IoT devices are becoming increasingly complex. With the rapid deployment of cameras, tasks in IoT like visual information are more important, but IoT devices have limited computing resources, including power, computing ability, storage, etc. Some tasks that might be perfectly normal to perform on a computer would be rather challenging on an IoT device. Therefore, how to maintain acceptable performance while minimizing resources is becoming a more consequential part in IoT. In the paper, we aim to solve the problem of object detection and tracking in IoT while minimizing resources. The traditional algorithms need to use convolutional neural network (CNN) to identify different objects in each frame, and then determine the tracking target from identified objects, which typically requires a lot of computing resources. By incorporating spatial attention, and multi-domain network, we proposed a novel algorithm named as Spatial Attention Powered Multi-Domain Network (SA-MDNet). By adding spatial attention mechanism to the original MDNet model, and using multi class cross entropy loss, we are able to distinguish the background and the target in different video sequences effectively and efficiently. This novel algorithm achieves similar performance on the OTB 50/100/2013 datasets compared to several state-of-art models, while uses only a fraction of the memory compared to MDNet.

Digital electronics course is one of the very fundamental courses for the students of undergraduate programme of electrical and electronic engineering (EEE) and the other undergraduate engineering disciplines. Therefore, "digital electronics" shall be taught effectively, so that students can apply the knowledge learned to solve their real-life engineering problems. A teacher needs to adopt new teaching methodologies to attract current generation of students, and thus, to prepare them with practical knowledge and skills. Skills in the cognitive domain of Bloom's taxonomy revolve around knowledge, comprehension and critical thinking of a particular topic. This makes teaching and learning more effective and efficient. In this paper, the teaching method of 'digital electronics' course for the undergraduate EEE students in the cognitive domain has been described with an example. Class performance evaluation in two different cohorts shows that the students' results improve after using this approach.Keywords: Bloom's taxonomy, cognitive domain, digital electronics course, teaching methods.

IoT has started capturing the market all over the world. Nearly all household appliances are available and consumer can buy them. Lack of security leaves the customer potentially exposed to various risk factors. Risk might be ranging daily routine data theft to great financial risk, even in some cases there is life threating risk for specific or group of persons. On analyzing various devices, through that come to know that many are not devices enforced strong passwords are not devices applied, or brute-force attacks is not protected, physical replacement of faulty sensors or wiretapping the traffic. As per approximation, every two among ten applications of mobile which are being used for managing and handling IOT devices are vulnerable and are not using SSL for communication data encryption. IoT involve billions of sensors spreading all around the world. Many of them are not physically protected. Attacker could access those sensors/devices and manipulate them or replace them. Captured data through sensors is also not safe if transmitted without encrypting them. Further many devices don’t have such power to perform heavy encryption. In this research Proposed a PUF (Physically unclonable function) and light weight encryption technique-based solution. Physically unclonable function create a class for new embedded and its security purpose. PUF mainly concentrate on shift the security challenges and issues. It has a very simple architecture and can solve problem of energy-constrained IoT devices. Through this research work introduced PUF functionality with hardware sensors. Since PUF function cannot be cloned therefore sensors are safe and any modification or replacement can be easily detected. Further data received from sensors will be encrypted using light weigh encryption technique. In future this proposed methodology explore a how to store safely vast amount of data generated through billions of sensors.

Functional Encryption (FE) expands traditional public-key encryption in two different ways: it supports fine-grained access control and allows learning a function of the encrypted data. In this paper, we review all FE classes, describing their functionalities and main characteristics. In particular, we mention several schemes for each class, providing their security assumptions and comparing their properties. To our knowledge, this is the first survey that encompasses the entire FE family., To appear in Advances in Mathematics of Communications, https://www.aimsciences.org/article/doi/10.3934/amc.2021049

Zero-Shot Learning (ZSL) aims to recognize unseen classes that never appear during training. Recently, generative adversarial networks (GANs) have been introduced to convert ZSL into a supervised learning problem by synthesizing unseen visual features. However, since unseen classes are never experienced for the generator during training, the synthesized unseen visual features often become heavily biased towards seen classes, or sometimes there is even no meaningful class that can be assigned to them. This is known as the \textit{bias problem}. In this paper, we propose a novel method, namely Adaptive Bias-Aware GAN (ABA-GAN), to alleviate generating biased visual features. For this purpose, we build a semantic adversarial network to regularize the feature generator. Specifically, an adaptive adversarial loss is proposed to constrain the feature distributions, which avoids the generation of meaningless visual features. Meanwhile, a domain divider is presented to explicitly distinguish synthesized visual features between seen and unseen domains, such that the bias towards seen classes can be alleviated. Moreover, we propose a novel metric named bias score (BS) to explicitly quantify the degree of the strong bias. Extensive experiments on four widely used benchmark datasets demonstrate that our proposed method outperforms the state-of-the-art approaches under both ZSL and GZSL protocols.

Deep learning methods have achieved significant progress in the presence of correctly annotated datasets in instance segmentation. However, object classes in large-scale datasets are sometimes ambiguous, which easily causes confusion. Besides, limited experience and knowledge of annotators can lead to mislabeled object semantic classes. To solve this issue, a novel method is proposed in this paper, which considers different roles of noisy class labels in different sub-tasks. Our method is based on two basic observations: firstly, the foreground-background annotation of a sample is correct even though its class label is noisy. Secondly, symmetric loss benefits the model robustness to noisy labels but harms the learning of hard samples, while cross entropy loss is the opposite. Based on the two basic observations, in the foreground-background sub-task, cross entropy loss is used to fully exploit correct gradient guidance. In the foreground-instance sub-task, symmetric loss is used to prevent incorrect gradient guidance provided by noisy class labels. Furthermore, we apply contrastive self-supervised loss to update features of all foreground, to compensate for insufficient guidance provided by partially correct labels especially in the highly noisy setting. Extensive experiments conducted with three popular datasets (i.e., Pascal VOC, Cityscapes and COCO) have demonstrated the effectiveness of our method in a wide range of noisy class label scenarios.

This article explains problems of individualization of education and extracurricular activities’ programs’ development. Main problems that need to be solved at various stages of the organization of extracurricular activities, from its methodological study to organizational and technical planning are analyzed. An overview of the directions of extracurricular activities, the forms in which it can be organized as well as the specifics of its implementation at various levels of education is offered. In order to reduce the labor intensity of time costs taking into account the time allocated for its implementation as well as the ability to generate plans taking into account individual preferences an intelligent information system was developed. Multi-criteria mathematical models from the class of optimization methods for solving the posed problem of decision support, functional and software-architectural developed model of a web service and examples of its work on the stages of planning general activities in the optimization formulation are presented. The proposed approach can be widely used in educational institutions of various levels interested in reducing the cost of organizing extracurricular work, automatic checking for compliance with requirements, as well as generating a work plan taking into account the opinions of various categories of experts.

This article is concerned with the problem of the $H_{∞}$ output feedback control for a class of event-triggered networked systems subject to multiple cyber attacks. Two dynamic event-triggered generators are equipped at sensor and observer sides, respectively, to lower the frequency of unnecessary data transmission. The sensor-to-observer (STO) channel and observer-to-controller (OTC) channel are subject to deception attacks and Denial-of-Service (DoS) attacks, respectively. The aim of the addressed problem is to design an output feedback controller, with the consideration of the effects of dynamic event-triggered schemes (DETSs) and multiple cyber attacks. Sufficient condition is derived, which can guarantee that the resulted closed-loop system is asymptotically mean-square stable (AMSS) with a prescribed $H_{∞}$ performance. Moreover, we provide the desired output feedback controller design method. Finally, the effectiveness of the proposed method is demonstrated by an example.

In recent years, we have witnessed the proliferation of mobile devices such as smart phones, tablets, smart watches, etc., the majority of which are based on the Android operating system. However, because these Android-based mobile devices are becoming increasingly popular, they are now the primary target of mobile malware, which could cause both privacy leakage and property loss. To address the rapidly deteriorating security issues caused by mobile malware, various research efforts have been made to develop novel and effective detection mechanisms to identify and battle them. Nevertheless, in order to avoid being caught by these malware detection mechanisms, malware authors are inclined to launch adversarial example attacks by tampering with mobile applications. In this paper, several types of adversarial example attacks are investigated and a feasible approach is proposed to fight against them. First, we look at adversarial example attacks on the Android system and prior solutions that have been proposed to address these attacks. Then, we specifically focus on the data poisoning attack and evasion attack models, which may mutate various application features, such as API calls, permissions and the class label, to produce adversarial examples. Then, we propose and design a malware detection approach which is resistant to the adversarial examples. To observe and investigate how the malware detection system is impacted by the adversarial example attacks, we conduct experiments on some real Android application datasets which are composed of both malware and benign applications. Experimental results clearly indicate that the performance of Android malware detection is severely degraded when facing the adversarial example attacks.

Entity resolution (ER) identifies data instances referring to the same real-world entity and has received enormous research attention. In this paper, we examine the task of ER from a broader perspective, with its input extended from textual records, which are conventionally studied in the literature, to other modalities such as check-in sequences, GPS trajectories and surveillance video frames to generate new applications. Our goal in this paper is to design an effective model to uniformly support all these ER applications with different input formats. Technically, we fully exploit the semantic contexts of embedding vectors for the pair of input instances. In particular, we propose an integrated multi-context attention framework that takes into account self-attention, pair-attention and global-attention from three types of context. The idea can be further extended to incorporate attribute attention in order to support structured datasets. We conduct extensive experiments on a diverse class of entity resolutions tasks, including tasks on unstructured, structured and dirty textual records, check-in sequences, GPS trajectories and surveillance video frames. The experimental results verified the effectiveness and generality of our model. When compared with strong baselines in these applications, our model can achieve superior or comparative performance.

As a class of context-aware systems, context-aware service recommendation aims to bind high-quality services to users while taking into account their context requirements, including invocation time, location, social profiles, connectivity, and so on. However, current CASR approaches are not scalable with the huge amount of service data (QoS and context information, users reviews and feedbacks). In addition, they lack a rich representation of contextual information as they adopt a simple matrix view. Moreover, current CASR approaches adopt the traditional user-service relation and they do not allow for multi-relational interactions between users and services in different contexts. To offer a scalable and context-sensitive service recommendation with great analysis and learning capabilities, we provide a rich and multi-relational representation of the CASR knowledge, based on the concept of knowledge graph. The constructed context-aware service knowledge graph (C-SKG) is, then, transformed into a low-dimentional vector space to facilitate its processing. For this purpose, we adopt Dilated Recurrent Neural Networks to propose a context-aware knowledge graph embedding, based on the principles of first-order and subgraph-aware proximity. Finally, a recommendation algorithm is defined to deliver the top-rated services according to the target user's context. Experiments have proved the accuracy and scalability of our CASR approach.

International audience; This paper uses the recent glottal flow model for iterative adaptive inverse filtering to analyze recordings from dysfunctional speakers, namely those with larynx-related impairment such as laryngectomy. The analytical model allows extraction of the voice source spectrum, described by a compact set of parameters. This single model is used to visualize and better understand speech production characteristics across impaired and nonimpaired voices. The analysis reveals some discriminative aspects of the source model which map to a physiological class description of those impairments. Furthermore, being based on analysis of source parameters only, it is complementary to any existing techniques of vocal-tract or phonetic analysis. The results indicate the potential for future automated speech reconstruction systems that adapt to the method of reconstruction required, as well as being useful for mainstream speech systems, such as ASR, in which front-end analysis can direct back-end models to suit characteristics of impaired speech.

The ON-OFF controlled very-high-frequency Class E dc-dc converter has been extensively investigated for achieving high power density and fast dynamic response. However, the basic ON-OFF control cannot limit the output current at overload or short-circuit condition. This letter proposes an ON-OFF control with current limitation function by adding an output current closed-loop for reducing the output voltage reference when overload or short-circuit occurs. The design considerations for the output current regulator are given. A prototype of 30-MHz, 10-W Class E dc-dc converter is fabricated and tested in the lab, and the experimental results are provided to verify the effectiveness of the proposed control scheme.

Design is an inseparable part of most scientific and engineering tasks, including real and simulation-based experimental design processes and parameter/hyperparameter tuning/optimization. Several model-based experimental design techniques have been developed for design in domains with partial available knowledge about the underlying process. This article focuses on a powerful class of model-based experimental design called the mean objective cost of uncertainty (MOCU). The MOCU-based techniques are objective-based, meaning that they take the main objective of the process into account during the experimental design process. However, the lack of scalability of MOCU-based techniques prevents their application to most practical problems, including large discrete or combinatorial spaces. To achieve a scalable objective-based experimental design, this article proposes a graph-based MOCU-based Bayesian optimization framework. The correlations among samples in the large design space are accounted for using a graph-based Gaussian process, and an efficient closed-form sequential selection is achieved through the well-known expected improvement policy. The proposed framework's performance is assessed through the structural intervention in gene regulatory networks, aiming to make the network away from the states associated with cancer.

Recent works reveal that network embedding techniques enable many machine learning models to handle diverse downstream tasks on graph-structured data. However, as previous methods usually focus on learning embedding for a single network, they cannot learn representations transferable on multiple networks. Hence, it is important to design a network embedding algorithm that supports downstream model transferring on different networks, known as domain adaptation. In this paper, we propose a Domain Adaptive Network Embedding framework, which applies Graph Convolutional Network to learn transferable embedding. In DANE, nodes from multiple networks are encoded to vectors via a shared and aligned embedding space. The distribution of embedding on different networks are further aligned by Adversarial Learning Regularization. To achieve better performance in scenarios where labels are provided, DANE adopts a cross-entropy error term of the GCN framework and class centroid aligning method. Moreover, DANE's advantages in learning transferable network embedding can be guaranteed theoretically. Extensive experiments reflect that the proposed framework outperforms other well-recognized network embedding baselines in cross-network domain adaptation tasks, and the semi-supervised components improve the performance significantly.

Class imbalance is a prevalent phenomenon in various real-world applications and it presents significant challenges to model learning, including deep learning. In this work, we embed ensemble learning into the deep convolutional neural networks (CNNs) to tackle the class-imbalanced learning problem. An ensemble of auxiliary classifiers branching out from various hidden layers of a CNN is trained together with the CNN in an end-to-end manner. To that end, we designed a new loss function that can rectify the bias toward the majority classes by forcing the CNN's hidden layers and its associated auxiliary classifiers to focus on the samples that have been misclassified by previous layers, thus enabling subsequent layers to develop diverse behavior and fix the errors of previous layers in a batch-wise manner. A unique feature of the new method is that the ensemble of auxiliary classifiers can work together with the main CNN to form a more powerful combined classifier, or can be removed after finished training the CNN and thus only acting the role of assisting class imbalance learning of the CNN to enhance the neural network's capability in dealing with class-imbalanced data. Comprehensive experiments are conducted on four benchmark data sets of increasing complexity (CIFAR-10, CIFAR-100, iNaturalist, and CelebA) and the results demonstrate significant performance improvements over the state-of-the-art deep imbalance learning methods.

Stochastic optimization methods have become a class of popular optimization tools in machine learning. Especially, stochastic gradient descent (SGD) has been widely used for machine learning problems such as training neural networks due to low per-iteration computational complexity. In fact, the Newton or quasi-newton methods leveraging second-order information are able to achieve a better solution than the first-order methods. Thus, stochastic quasi-Newton (SQN) methods have been developed to achieve the better solution efficiently than the stochastic first-order methods by utilizing approximate second-order information. However, the existing SQN methods still do not reach the best known stochastic first-order oracle (SFO) complexity. To fill this gap, we propose a novel faster stochastic quasi-Newton method (SpiderSQN) based on the variance reduced technique of SIPDER. We prove that our SpiderSQN method reaches the best known SFO complexity of $\mathcal{O}(n+n^{1/2}\epsilon^{-2})$ in the finite-sum setting to obtain an $\epsilon$-first-order stationary point. To further improve its practical performance, we incorporate SpiderSQN with different momentum schemes. Moreover, the proposed algorithms are generalized to the online setting, and the corresponding SFO complexity of $\mathcal{O}(\epsilon^{-3})$ is developed, which also matches the existing best result. Extensive experiments on benchmark datasets demonstrate that our new algorithms outperform state-of-the-art approaches for nonconvex optimization., Comment: 11 pages, accepted for publication by TNNLS. arXiv admin note: text overlap with arXiv:1902.02715 by other authors

Few-shot learning aims at heuristically resolving new tasks with limited labeled data; most of the existing approaches are affected by knowledge learned from similar experiences. However, inter-class barriers and new samples insufficiency limit the transfer of knowledge. In this paper, we propose a novel mixture distribution graph network, in which the inter-class relation is explicitly modeled and propagated via graph generation. Owing to the weighted distribution features based on Gaussian Mixture Model, we take class diversity into consideration, thereby utilizing information precisely and efficiently. Equipped with Minimal Gated Units, the “memory" of similar tasks can be preserved and reused through episode training, which fills a gap in temporal characteristics and softens the impact of data insufficiency. Extensive trials are carried out based on the MiniImageNet and CIFAR-FS datasets. Results turn out that our method exceeds most state-of-the-art approaches, which shows the validity and universality of our method in few-shot learning.

This paper designs formation–containment control algorithms for a class of second-order nonlinear multi-agent systems governed by Euler–Lagrange dynamics with communication delays. The formation–containment problem consists of leader agents’ formation control and follower agents’ containment control. Firstly, to make the leaders form a desired formation and move collectively with a constant velocity, a coordinated formation control algorithm is designed and the variable-gain technique is used to eliminate the effect of communication delays on the leaders’ formation control. Secondly, considering that only the leaders have access to the desired moving velocity, we propose distributed velocity estimators for followers in which the communication delays also exist in the followers’ information interaction. By using the estimated velocity information, coordinated containment control laws are designed for the followers to drive them asymptotically converge to the convex hull spanned by all leaders. Furthermore, to increase the system robustness against uncertainties and external disturbances, the adaptive updating laws are designed for all agents. Finally, simulations are given to demonstrate these obtained results.

We present a technique to automatically generate search heuristics for dynamic symbolic execution. A key challenge in dynamic symbolic execution is how to effectively explore the program's execution paths to achieve high code coverage in a limited time budget. Dynamic symbolic execution employs a search heuristic to address this challenge, which favors exploring particular types of paths that are most likely to maximize the final coverage. However, manually designing a good search heuristic is nontrivial and typically ends up with suboptimal and unstable outcomes. The goal of this paper is to overcome this shortcoming of dynamic symbolic execution by automatically learning search heuristics. We define a class of search heuristics, namely a parametric search heuristic, and present an algorithm that efficiently finds an optimal heuristic for each subject program. Experimental results with industrial-strength symbolic execution tools (e.g., KLEE) show that our technique can successfully generate search heuristics that significantly outperform existing manually-crafted heuristics in terms of branch coverage and bug-finding.

This article studies the pinning synchronization problem with edge-based decentralized adaptive schemes under link attacks. The link attacks considered here are a class of malicious attacks to break links between neighboring nodes in complex networks. In such an insecure network environment, two kinds of edge-based decentralized adaptive update strategies (synchronous and asynchronous) on coupling strengths and gains are designed to realize the security synchronization of complex networks. Moreover, by virtue of the edge pinning technique, the corresponding secure synchronization problem is considered under the case where only a small fraction of coupling strengths and gains is updated. These designed adaptive strategies do not require any global information, and therefore, the obtained results in this article are developed in a fully decentralized framework. Finally, a numerical example is provided to verify the availability of the achieved theoretical outcomes.

In this article, the output consensus problem is investigated for a class of switched nonlinear multiagent systems, where denial-of-service attacks and faults are considered in communication channels and agents’ actuators, respectively. The cyber attacks can damage the communication channels, which will cause the consensus performance degradation or even failure to achieve consensus. Compared with the existing results on consensus of multiagent systems under cyber attacks, the agents’ dynamics in this article are described by higher order heterogeneous switched nonlinear systems. The cyber attacks, actuator faults, asynchronous switchings, and the high complexity of the system make the existing consensus algorithms ineffective. A novel control scheme for the output consensus of the multiagent system subject to cyber attacks is proposed. By the graph theory, switched system theory and Lyapunov function method, sufficient conditions are presented to check whether the consensus objective can be achieved. Finally, the effectiveness of the proposed scheme is illustrated by two numerical simulations.

The Department of Clinical Laboratory Sciences at Virginia Commonwealth University incorporated the use of a game-based learning platform into a junior level Immunology course. The primary goal of this addition was to increase student engagement during review sessions. In previous years, each Immunology class was started with a review of material from an earlier lecture. The review consisted of short answer and multiple choice questions as a means to highlight important concepts and allow additional opportunities for students to ask questions. During these review periods it was observed that class participation ranged from 3-20%. Additionally, those who did participated were the same students in each class period. The incorporation of the game-based learning pAlatform into review sessions involved asking review questions in multiple choice format with 30 seconds of time for students to answer after each question was asked. This new format resulted in class participation increasing to 95-100%. Review of student answers also allowed the instructor to determine which areas the students needed additional assistance with before exams. Student feedback indicated that they enjoyed the ability to be anonymous when answering questions while still getting immediate feedback. This new review format will be utilized in additional courses, specifically Immunohematology. Furthermore, this game-based platform will be used to review material with senior students in their advanced senior level courses.

Objectives: This study aimed to discover the extent to which medical students can evaluate medical websites, evaluation criteria used, factors affecting their abilities and whether a teaching intervention could rectify problems. Medical students and practitioners are required to evaluate medical information available on the Internet. Most current medical students are familiar with the Internet, but their ability to evaluate material may require improvement. Methods: A class of undergraduate medical students evaluated an unreliable medical website, received a teaching intervention on website evaluation criteria and re-evaluated the same site. This mixed-methods study was conducted at Sultan Qaboos University, Muscat, Oman, from September to December 2018. Results: A total of 149 (response rate: 82.3%) students participated. Students spent, on average, 4.69 hours per day on the Internet. No significant correlations were found between demographic indicators and Internet time. On a 10-point Likert scale, students’ scores ranged from 5–6, with no significant differences between the pre- and post-intervention evaluations, except for increased polarisation away from the mean. Qualitative comments indicated an awareness of relevant criteria but an overall inability to critically apply them. Conclusion: The results indicate that one cannot make a blanket statement about medical students’ ability to evaluate medical websites despite their familiarity with technology. Moreover, website evaluation should be viewed primarily from the information perspective and that critical thinking ability may play a major role. Due to these overriding factors, short interventions are unlikely to have an impact, and other educational strategies should be developed. These are necessary to ensure that medical students can function independently as life-long learners and medical professionals. Keywords: Internet; Medical Students; Oman.

A fuzzy adaptive switching event-triggered control strategy is obtained for a class of uncertain nonlinear switched systems with predefined accuracy. Since the switching may occur between two adjacent sampling instants and may lead to trigger a new event, it raises the mismatched switching and brings severe challenges to avoid the Zeno behavior of the subsystem controllers. The formidable problems are successfully addressed by a new switching event-triggering mechanism without restrictive assumptions. With the proposed fuzzy adaptive switching control approach, the adverse effects of mismatched switching between the subsystem and the controller are addressed, and no subsystem controllers exhibit the Zeno behavior. Furthermore, by using a projection operator-based adaptation strategy and constructing a class of continuous functions, the convergence accuracy of the switched system appears explicitly in design parameters. It allows designers to make decisions in advance based on the requirement of convergence accuracy. Finally, theoretical results are verified by two illustrative examples.

The control of underactuated Euler–Lagrange systems with uncertain and switched parameters is an important problem whose solution has many applications. The problem is challenging as standard adaptive control techniques do not extend to this class of systems due to structural constraints that lead to parameterization difficulties. This note proposes an adaptive switched control framework that handles the uncertainty and switched dynamics without imposing structural constraints. A case study inspired by autonomous vessel operations is used to show the effectiveness of the proposed approach.

Few-shot learning (FSL) for human-object interaction (HOI) aims at recognizing various relationships between human actions and surrounding objects only from a few samples. It is a challenging vision task, in which the diversity and interactivity of human actions result in great difficulty to learn an adaptive classifier to catch ambiguous interclass information. Therefore, traditional FSL methods usually perform unsatisfactorily in complex HOI scenes. To this end, we propose dynamic graph-in-graph networks (DGIG-Net), a novel graph prototypes framework to learn a dynamic metric space by embedding a visual subgraph to a task-oriented cross-modal graph for few-shot HOI. Specifically, we first build a knowledge reconstruction graph to learn latent representations for HOI categories by reconstructing the relationship among visual features, which generates visual representations under the category distribution of every task. Then, a dynamic relation graph integrates both reconstructible visual nodes and dynamic task-oriented semantic information to explore a graph metric space for HOI class prototypes, which applies the discriminative information from the similarities among actions or objects. We validate DGIG-Net on multiple benchmark datasets, on which it largely outperforms existing FSL approaches and achieves state-of-the-art results.

Recently, a multitude of methods for image-to-image translation have demonstrated impressive results on problems, such as multidomain or multiattribute transfer. The vast majority of such works leverages the strengths of adversarial learning and deep convolutional autoencoders to achieve realistic results by well-capturing the target data distribution. Nevertheless, the most prominent representatives of this class of methods do not facilitate semantic structure in the latent space and usually rely on binary domain labels for test-time transfer. This leads to rigid models, unable to capture the variance of each domain label. In this light, we propose a novel adversarial learning method that: 1) facilitates the emergence of latent structure by semantically disentangling sources of variation and 2) encourages learning generalizable, continuous, and transferable latent codes that enable flexible attribute mixing. This is achieved by introducing a novel loss function that encourages representations to result in uniformly distributed class posteriors for disentangled attributes. In tandem with an algorithm for inducing generalizable properties, the resulting representations can be utilized for a variety of tasks such as intensity-preserving multiattribute image translation and synthesis, without requiring labeled test data. We demonstrate the merits of the proposed method by a set of qualitative and quantitative experiments on popular databases such as MultiPIE, RaFD, and BU-3DFE, where our method outperforms other state-of-the-art methods in tasks such as intensity-preserving multiattribute transfer and synthesis.

Zero-shot learning (ZSL) is a pretty intriguing topic in the computer vision community since it handles novel instances and unseen categories. In a typical ZSL setting, there is a main visual space and an auxiliary semantic space. Most existing ZSL methods handle the problem by learning either a visual-to-semantic mapping or a semantic-to-visual mapping. In other words, they investigate a unilateral connection from one end to the other. However, the connection between the visual space and the semantic space are bilateral in reality, that is, the visual space depicts the semantic space; the semantic space, on the other hand, describes the visual space. In this article, therefore, we investigate the bilateral connections in ZSL and present a novel model, called Boomerang-GAN, by taking advantage of conditional generative adversarial networks (GANs). Specifically, we generate unseen visual samples from their category semantic embeddings by a conditional GAN. Different from the existing generative ZSL methods that only consider generating visual features from class descriptions, our method also considers that the generated visual features can be translated back to their corresponding semantic embeddings by introducing a multimodal cycle-consistent loss. Extensive experiments of both ZSL and generalized ZSL on five widely used datasets verify that our method is able to outperform previous state-of-the-art approaches in both recognition and segmentation tasks.

Intelligent systems, like driver assistance systems, remain within vehicles and help drivers by providing essential information about traffic, blockage of roads, and possible routes for safe driving. The objective of scene text spotting in a driver assistance system is to localize and recognize scene texts, signs of milestones, traffic panels, and road marks in natural scene images. However, text edges get fainted due to adverse weather conditions, like fog, rain, smog, or poor contrast. This makes the task of spotting more challenging. In this paper, we propose an end-to-end trainable deep neural network, known as Met-MLTS, that can address the issue of spotting multi-oriented text instances in scene images captured in adverse meteorological conditions. It localizes words, predicts script class, and performs word spotting for every rotated bounding box. It is a fast multilingual scene text spotter that utilizes hierarchical spatial context, channel-wise inter-dependencies, and semantic edge supervision to localize and recognize words and predict script class in scene images using smartphones. We explore inter-class interference to reduce the misclassification problem. A light-weight recognition module for multilingual character segmentation, word-level recognition, and script identification is incorporated. We demonstrate the efficacy of our spotting network on resource-constraint devices.

In the fall of 1978 I was consultant to a video project called "The Unemployment Tapes," designed to explore through talks with local people the human costs, the causes, and the possible cures of unemployment in an old industrial area of Connecticut. At the time, I was also reading and thinking about class, language, and the theories of Basil Bernstein. I began to notice in the taped interviews a close correspondence to Bernstein's cen­tral distinction between "restricted" and "elaborated" codes: almost all the peo­ple interviewed on the streets spoke in the restricted code that Bernstein attrib­utes to the working class, while managers and officials used the elaborated code of what Bernstein calls the "middle class." . . . The power relations of a society permeate speech and shape it, while speech reproduces or challenges the pow­er relations of the society. The way we talk is not just an artifact of class, any more than class is an artifact of the ways we talk. Speech takes place in society, but society also takes place "in" speech. The point is well illustrated, I believe, by what happened in those two interviews. A Bernsteinian explanation of their con­trasts badly misrepresents the social forces at work in them, assigning to static "class," differences in speech that ex­press dynamic and changeable power relations. . . . Movements toward worker self-management, co-ops, progressive credit unions, consumer movements, union organizing, populist movements of many kinds, are all fertile soil in which elaborated codes (put to better use than by the mayor, I hope) may grow along with the habit of democracy.

We present an approach to analyse learning outcomes in a broad class of misspecified environments, spanning both single-agent and social learning. We introduce a novel “prediction accuracy” order over subjective models and observe that this makes it possible to partially restore standard martingale convergence arguments that apply under correctly specified learning. Based on this, we derive general conditions to determine when beliefs in a given environment converge to some long-run belief either locally or globally (i.e. from some or all initial beliefs). We show that these conditions can be applied, first, to unify and generalize various convergence results in previously studied settings. Second, they enable us to analyse environments where learning is “slow”, such as costly information acquisition and sequential social learning. In such environments, we illustrate that even if agents learn the truth when they are correctly specified, vanishingly small amounts of misspecification can generate extreme failures of learning.

While the interactional conditions and timing of applause in audience response to public speeches has received attention in conversation analysis research, little research has been done on applause in educational contexts. The nature of applause, however, can vary depending on the context. This paper examines classroom-specific applause and focuses on where in classroom interaction the applause can occur, who initiates the applause, and what the applause accomplishes in the interaction. The data come from 14 audio and video-recorded Japanese primary school EFL class sessions. The analysis reveals that the applause in the data was a typically teacher-initiated action and it regularly occurred in sequence closing position as a positive assessment to the students’ success in carrying out the teachers’ oriented-to expectations.

This paper examines how orientation to cultural identities in an Irish language class in the United States is used to negotiate issues of authenticity and linguistic and cultural authority. The data were recorded in a beginning level Irish language class in Southern California, in which the teacher and all but one student were American. The Irish identity of the remaining student was highly salient to the other students and to the teacher, conferring authenticity and linguistic authority on him. The teacher's evaluations of the students ascribe authenticity and linguistic authority to the Irish student based on perceptions about his identity, in spite of his rejection of such authority. Thus, even when participants do not claim identity based Statuses, they may be imposed by others in a way that is consequential for interaction. Keywords: Identity; Authenticity; Irish; Linguistic authority.

This study deals with Formulaic Speech (FS) usage in the context of the partial L2 immersion class. It tries to define and classify FS according to its functions. The fact that learners resort to FS shows that second language production is not only based on the construction of sentences from scratch but also on the integration of formulaic sequences in discourse. But what is the use of FS? What are the possible functions it performs? We attempt to show that FS makes up for a lack of structural knowledge and might therefore be used as a learning strategy in the acquisition of structure. Then we consider the psycholinguistic function of FS and try to demonstrate that it might be a pre-planning strategy and a way for the learner to economize effort on processing and thus focus on his or her learning of the language. Finally, the paper analyzes the communicative function of FS and its role in the relation between speaker and hearer, and suggests that it might play a part in the development of pragmatic competence. Keywords: Formulaic Speech, Second language acquisition, Second language production, Partial immersion, Communicative competence.

In this work, we propose a novel framework to address the formation control problem for a class of multirobot systems with two types of constraints, namely the performance constraints and the feasibility constraints. For the performance constraints, we consider the constraint requirements on the distance tracking errors between the real and the desired trajectories for each robot, so that to ensure precise tracking of the robot without deviating too much from its desired trajectory, as well as the constraints on the interrobot distance, so that to ensure the safe operation of the team. For the feasibility constraints, we consider the constraints on the heading angle, so that the controllers designed in the brief are feasible. Universal barrier functions are adopted in the controller design and analysis, which is a generic framework that can address systems with different types of constraints in a unified controller architecture. Through rigorous analysis, exponential convergence rate can be guaranteed on the distance tracking errors, while all constraints are satisfied during the operation. A simulation example and an experiment using three AmigoBot mobile robots further demonstrate the efficacy of the proposed control framework.

API misuses are well-known causes of software crashes and security vulnerabilities. However, their detection and repair is challenging given that the correct usages of (third-party) APIs might be obscure to the developers of client programs. This paper presents the first empirical study to assess the ability of existing automated bug repair tools to repair API misuses, which is a class of bugs previously unexplored. Our study examines and compares 14 Java test-suite-based repair tools (11 proposed before 2018, and three afterwards) on a manually curated benchmark (APIREPBENCH) consisting of 101 API misuses. We develop an extensible execution framework (APIARTY) to automatically execute multiple repair tools. Our results show that the repair tools are able to generate patches for 28% of the API misuses considered. While the 11 less recent tools are generally fast (the median execution time of the repair attempts is 3.87 minutes and the mean execution time is 30.79 minutes), the three most recent are less efficient (i.e., 98% slower) than their predecessors. The tools generate patches for API misuses that mostly belong to the categories of missing null check, missing value, missing exception, and missing call. Most of the patches generated by all tools are plausible (65%), but only few of these patches are semantically correct to human patches (25%). Our findings suggest that the design of future repair tools should support the localisation of complex bugs, including different categories of API misuses, handling of timeout issues, and ability to configure large software projects. Both APIREPBENCH and APIARTY have been made publicly available for other researchers to evaluate the capabilities of repair tools on detecting and fixing API misuses.

Karunanayaka and Tang (2017) introduced a class of compromise designs for estimating main effects under the baseline parameterization. Their approach is to add some runs to the basic one-factor-at-a-time design, and its implementation requires computer search except for the case of adding one run where a theoretical result is available. The reliance on computer search only allowed them to find the limited results from adding up to four runs to the basic one-factor-at-a-time design. In this paper, we provide a systematic construction of compromise designs, without computer search and without restriction on the run size and the number of factors. Closed-form expressions of the bias and efficiency criteria are obtained for the new designs. Both theoretical and empirical studies show that our designs outperform those of Karunanayaka and Tang (2017) saving small-sized problems.

The wireless sensor networks (WSNs) are special network which has purpose of gathering information in certain area. Multipath routing is the paramount path of addressing QoS and energy balancing concerns in low power and lossy networks (LLNs) especially in IoT technology. Most of the extant efforts bring the limited number of disjoint paths into play, and intersect the traffic among them pursuant to a compound metric or centralized optimization problem. This paper proposes a multi-class multipath routing protocol for LLNs (called M2RPL), that construct a braided multipath routing graph based on the standard RPL (IPv6 Routing Protocol for Low-Power and Lossy Networks) protocol, and an energy balanced optimal rate assignment mechanism (EBORA) that solves a local multi class optimization problem for minimum cost traffic rate assignment. Moreover the algorithm tries to maximize network lifetime by equalizing the energy dissipation rates of equi-level nodes. The simulation results expose the efficiency of the proposed framework, leading to an average 15% increase in lifetime, and improved QoS performance in terms of delay and reliability, compared to some well-known algorithms.

Exploring the characterization laws of image data and improving the efficiency of image data characterization knowledge is essential to promote the development of the Internet of Things technology. Considering that images in the real world usually contain multiple objects, and the objects are closely dependent. For these reasons, it brings great challenges to the robust representation learning of multi-label images. In general, researchers model the relationship between objects based on a class activation map and use graph convolution to mine the dependencies between objects. However, graph structure data often contain noise, which means that the edges between nodes are sometimes not so reliable, and the relative importance of neighbors is also different. Based on this, our goal is to reduce noisy connections and false connections between objects, eliminate multi-label image representation bias, and learn robust representations. Therefore, we propose a Robust Representation Learning method for multi-label images driven by Graph Attention Network (RRL-GAT). Specifically, to reduce the accidental false connection of objects in the image, we propose the Class Attention Graph convolution module (C-GAT) to mine the strong association structure between categories. Besides, for the dynamic correlation between objects in the image, we propose an Adaptive Graph Attention Convolution module (A-GAT) to capture the subtle dynamic dependencies in the image. The results on two authoritative datasets show that our method is significantly better than all current state-of-the-art methods. Besides, the visualization results show that RRL-GAT can capture the semantic relationship of a specific input image and has sufficient recognizability.

This paper presents and analyzes a case study of a five-week study abroad course called Inequality in Brazil: An exploration of race, class, gender, sexuality, and geography. The course was constructed to teach social inequality in the context of Brazil by using place-based and experiential learning within the framework of critical pedagogy (Freire, 1989). By examining inequality through the lens of culture and geography, students were empowered to become student-teachers in their explorations of race, class, gender, and sexuality as they linked theory to practice and lived experience. This paper provides an example of how study abroad can be used to teach about issues of inequality by partnering with community members to build learning environments where students and community members can all benefit.

Internet of Things (IoT) and 5G network are fundamental building blocks for Industrial Internet of Things (IIoT). IoT has enabled real-time monitoring and actuation in industrial floors and machinery,aimed at improving the efficiency and safety of industrial activities and processes. On the other hand,5G networks will provide ultra-reliable and low-latency communication for the wireless integration of autonomous industrial machinery,mobile vehicles,and robots,and management systems,aimed at the real-time control and management of industrial machinery towards smart factories. In IIoT,machine learning (ML) will also play a fundamental role in handling complex tasks at industrial machinery and 5G networks management,configuration,and control. However,ML suffers from the cold-start problem and needs a large amount of highly accurate data samples for model training,which is costly and difficult to obtain in IIoT applications. In this paper,we shed light on the design of transfer learning (TL)-based systems for IIoT. We discuss how TL can overcome the demand for high-quality large data samples required to training ML models in IIoT. We also highlight the work principles and daunting challenges faced during the TL systems for IIoT. Furthermore,we categorize the TL systems for IIoT into TL for IIoT machinery level and for IIoT networking level and provide an in-depth discussion of the design building blocks and challenges of TL systems in each proposed class. Finally,we point out some future research directions for the design of novel TL-based systems for envisioned 5G-enabled IIoT applications.

With increasing usage of face recognition algorithms, it is well established that external artifacts and makeup accessories can be applied to different facial features such as eyes, nose, mouth, and cheek, to obfuscate one’s identity or to impersonate someone else’s identity. Recognizing faces in the presence of these artifacts comprises the problem of disguised face recognition, which is one of the most arduous covariates of face recognition. The challenge becomes exacerbated when disguised faces are captured in real-time environment, with low resolution images. To address the challenge of disguised face recognition, this paper first proposes a novel multi-objective encoder-decoder network, termed as DED-Net. DED-Net attempts to learn the class variations in the feature space generated by both disguised as well non-disguised images, using a combination of Mahalanobis and Cosine distance metrics, along with Mutual Information based supervision. The DED-Net is then extended to learn from the local and global features of both disguised and non-disguised face images for efficient face recognition, and the complete framework is termed as Disguise Resilient (D-Res) framework. The efficacy of the proposed framework has been demonstrated on two real-world benchmark datasets: Disguised Faces in the Wild (DFW) 2018 and DFW2019 competition datasets. In addition, this research also emphasizes on the importance of recognizing disguised faces in low resolution settings and proposes three experimental protocols to simulate the real-world surveillance scenario. To this effect, benchmark results have been shown on seven protocols for three low resolution settings (32×32, 24×24, and 16×16) of the two DFW benchmark datasets. The results demonstrate superior performance of the D-Res framework, in comparison with benchmark algorithms. For example, an improvement of around 3% is observed on the Overall protocol of the DFW2019 dataset, where the D-Res framework achieves 96.3%. Experiments have also been performed on benchmark face verification datasets (LFW, YTF, and IJB-B), where the D-Res framework achieves improved verification accuracy.

This article investigates a class of finite-time cooperative tracking problems of heterogeneous mixed-order multiagent systems (MASs) with higher-order dynamics. Different from the previous works of heterogeneous MASs, the agents in this study are considered to have different first-, second-, or even higher-order nonlinear dynamics. It means that, according to different tasks and situations, the following agents can have nonidentical orders or different numbers of states to be synchronized, which is more general for the practical cooperative applications. The leader is a higher-order nonautonomous system and contains full state information to be synchronized for all agents with mixed-order dynamics. Accordingly, the spanning tree is defined based on the specific state rather than on the agent to guarantee that each following agent can receive adequate state information. Distributed control protocols are designed for all agents to achieve the ultimate state synchronization to the leader in finite time. The Lyapunov approach is used for the stability analysis and a practical example of mixed-order mechanical MASs verifies the effectiveness and performance of the proposed distributed control protocols.