Search

Due to the increasing size of s (s), their design and optimization phases (i.e., ) grow increasingly complex. At design time, a large design space needs to be explored to find an implementation that fulfills all specifications and then optimizes metrics like energy, area, delay, reliability, etc. At run time, a large configuration space needs to be searched to find the best set of parameters (e.g., voltage/frequency) to further optimize the system. Both spaces are infeasible for exhaustive search typically leading to heuristic optimization algorithms that find some trade-off between design quality and computational overhead. ML can build powerful models that have successfully been employed in related domains. In this survey, we categorize how () may be used and is used for design-time and run-time optimization and exploration strategies of s. A meta-study of published techniques unveils areas in that are well-explored and underexplored with, as well as trends in the employed algorithms. We present a comprehensive categorization and summary of the state of the art on for. Finally, we summarize remaining challenges and promising open research directions.

Due to the highly infectious nature of the novel coronavirus (COVID‐19) disease, excessive number of patients waits in the line for chest X‐ray examination, which overloads the clinicians and radiologists and negatively affects the patient's treatment, prognosis and control of the pandemic. Now that the clinical facilities such as the intensive care units and the mechanical ventilators are very limited in the face of this highly contagious disease, it becomes quite important to classify the patients according to their severity levels. This paper presents a novel implementation of convolutional neural network (CNN) approach for COVID‐19 disease severity classification (assessment). An automated CNN model is designed and proposed to divide COVID‐19 patients into four severity classes as mild, moderate, severe, and critical with an average accuracy of 95.52% using chest X‐ray images as input. Experimental results on a sufficiently large number of chest X‐ray images demonstrate the effectiveness of CNN model produced with the proposed framework. To the best of the author's knowledge, this is the first COVID‐19 disease severity assessment study with four stages (mild vs. moderate vs. severe vs. critical) using a sufficiently large number of X‐ray images dataset and CNN whose almost all hyper‐parameters are automatically tuned by the grid search optimiser.

Nagahara M., Krishnamachari B., Ogura M., et al. Control, intervention, and behavioral economics over human social networks against COVID-19. Advanced Robotics, 35(11), 733-739, May 19, 2021 © 2021 Informa UK Limited, trading as Taylor & Francis Group and The Robotics Society of Japan. https://doi.org/10.1080/01691864.2021.1928553., In this short paper, we propose a new direction of cross-cutting research for prediction and control of spreading COVID-19 viruses over a human social network. Such a network consists of human agents whose behaviors are highly uncertain and biased. To predict and control such an uncertain network, we need to employ various researches such as control theory, signal processing, machine learning, and behavioral economics. In this article, we introduce our recent research results and propose future research topics to overcome the COVID-19 pandemic.

In this paper, linear regression (LR), multi-linear regression (MLR) and polynomial regression (PR) techniques are applied to propose a model Li-MuLi-Poly. The model predicts COVID-19 deaths happening in the United States of America. The experiment was carried out on machine learning model, minimum mean square error model, and maximum likelihood ratio model. The best-fitting model was selected according to the measures of mean square error, adjusted mean square error, mean square error, root mean square error (RMSE) and maximum likelihood ratio, and the statistical t-test was used to verify the results. Data sets are analyzed, cleaned up and debated before being applied to the proposed regression model. The correlation of the selected independent parameters was determined by the heat map and the Carl Pearson correlation matrix. It was found that the accuracy of the LR model best-fits the dataset when all the independent parameters are used in modeling, however, RMSE and mean absolute error (MAE) are high as compared to PR models. The PR models of a high degree are required to best-fit the dataset when not much independent parameter is considered in modeling. However, the PR models of low degree best-fits the dataset when independent parameters from all dimensions are considered in modeling.

Electrical energy is a vital part of modern life, and expectations for grid resilience to allow a continuous and reliable energy supply has tremendously increased even during adverse events (e.g. Ukraine cyberattack, Hurricane Maria). The global pandemic COVID‐19 has raised the electric energy reliability risk due to potential workforce disruptions, supply chain interruptions, and increased possible cybersecurity threats. Additionally, the pandemic introduces a significant degree of uncertainty to the grid operation in the presence of other challenges including aging power grids, high proliferation of distributed generation, market mechanism, and active distribution network. This situation increases the need for measures for the resiliency of power grids to mitigate the impact of the pandemic as well as simultaneous extreme events including cyberattacks and adverse weather events. Solutions to manage such an adverse scenario will be multi‐fold: (a) emergency planning and organisational support, (b) following safety protocol, (c) utilising enhanced automation and sensing for situational awareness, and (d) integration of advanced technologies and data points for ML‐driven enhanced decision support. Enhanced digitalisation and automation resulted in better network visibility at various levels, including generation, transmission, and distribution. These data or information can be employed to take advantage of advanced machine learning techniques for automation and increased power grid resilience. In this paper, the resilience of power grids in the face of pandemics is explored and various machine learning tools that can be helpful to augment human operators are discused by: (a) reviewing the impact of COVID‐19 on power grid operations and actions taken by operators/organisations to minimise the impact of COVID‐19, and (b) presenting recently developed tools and concepts of machine learning and artificial intelligence that can be applied to increase the resiliency of power systems in normal and extreme scenarios such as the COVID‐19 pandemic.

Since the end of 2019, computed tomography (CT) images have been used as an important substitute for the time‐consuming Reverse Transcriptase polymerase chain reaction (RT‐PCR) test; a new coronavirus 2019 (COVID‐19) disease has been detected and has quickly spread through many countries across the world. Medical imaging such as computed tomography provides great potential due to growing skepticism toward the sensitivity of RT‐PCR as a screening tool. For this purpose, automated image segmentation is highly desired for a clinical decision aid and disease monitoring. However, there is limited publicly accessible COVID‐19 image knowledge, leading to the overfitting of conventional approaches. To address this issue, the present paper focuses on data augmentation techniques to create synthetic data. Further, a framework has been proposed using WoT and traditional U‐Net with EfficientNet B0 to segment the COVID Radiopedia and Medseg datasets automatically. The framework achieves an F‐score of 0.96, which is best among state‐of‐the‐art methods. The performance of the proposed framework also computed using Sensitivity, Specificity, and Dice‐coefficient, achieves 84.5%, 93.9%, and 65.0%, respectively. Finally, the proposed work is validated using three quality of service (QoS) parameters such as server latency, response time, and network latency which improves the performance by 8%, 7%, and 10%, respectively.

Pervasive technologies such as Artificial Intelligence, Virtual Reality and the Internet of Things, despite their great potential for improved workability and well-being of older workers, entail wide ethical concerns. Aligned with these considerations we emphasize the need to present from the viewpoint of ethics the risks of personalized ICT solutions that aim to remedy health and support the well-being of the ageing population at workplaces. The ethical boundaries of digital technologies are opaque. The main motivation is to cope with the uncertainties of workplaces’ digitization and develop an ethics framework, termed SmartFrameWorK, for personalized health support through ICT tools at workplace environments. SmartFrameWorK is built upon a five-dimensional approach of ethics norms: autonomy, privacy, transparency, trustworthiness and accountability to incite trust in digital workplace technologies. A typology underpins these principles and guides the ethical decision-making process with regard to older worker particular needs, context, data type-related risks and digital tools’ use throughout their lifecycle. Risk analysis of pervasive technology use and multimodal data collection, highlighted the imperative for ethically aware practices for older workers' activity and behaviour monitoring. The SmartFrameWorK methodology has been applied in a case study to provide evidence that personalized digital services could elicit trust in users through a well-defined framework. Ethics compliance is a dynamic process from participants’ engagement to data management. Defining ethical determinants is pivotal towards building trust and reinforcing better workability and well-being in older workers.

The advent of internet of things has opened the opportunities for people with disabilities, increased their inclusion and productivity in their living society. Most of the invented smart sensing devices including the wearable ones for users with speech impairments are expensive and not affordable for patients in the low income countries such as Egypt. Morse Glasses is a cost efficient wearable device based on IoT technology and a modified Morse code that tracks the patient’s eyes blinks and translates it into a generated speech. A sequence of Morse encoded alphabets/sentences along with the frequently used ones is displayed and heard on any android supported device that is installed Morse Glasses mobile application. With cost less than 30$, patients with motor neuron diseases such as Amyotrophic Lateral Sclerosis (ALS) can communicate easily with the others, express their needs and simply live their life normally.

Recently, cryptographic literature has seen new block cipher designs such as PRESENT, GIFT or SKINNY that aim to be more lightweight than the current standard, i.e., AES. Even though AES family of block ciphers were designed two decades ago, they still remain as the de facto encryption standard, with AES-128 being the most widely deployed variant. In this work, we revisit the combined one-in-all implementation of the AES family, namely both encryption and decryption of each AES-128/192/256 as a single ASIC circuit. A preliminary version appeared in Africacrypt 2019 by Balli and Banik, where the authors design a byte-serial circuit with such functionality. We improve on their work by reducing the size of the compact circuit to 2268 GE through 1-bit-serial implementation, which achieves 38% reduction in area. We also report stand-alone bit-serial versions of the circuit, targeting only a subset of modes and versions, e.g., AES-192 and AES-256. Our results imply that, in terms of area, AES-192 and AES-256 can easily compete with the larger members of recently designed SKINNY family, e.g., SKINNY-128-256, SKINNY-128-384. Thus, our implementations can be used interchangeably inside authenticated encryption candidates such as SKINNY-AEAD/-HASH, ForkAE or Romulus in place of SKINNY.

This article focuses on building a prototyping for immersive captioning following a user-centric approach. This methodology is characterised by following a bottom-up approach, where usability and user needs are at the heart of the development. Recent research on user requirements for captioning in immersive environments has shown that there is both a need for improvement and a wealth of research opportunities. The final aim is to identify how to display captions for an optimal viewing experience. This work began four years ago with some partial findings. We build from the lessons learnt, focussing on the user-centric design requirements cornerstone: prototyping. Our prototype framework integrates methods used in existing solutions aiming at instant contrast-and-compare functionalities. The first part of the article presents the state of the art for user requirements identifying the reasons behind the development of the prototyping framework. The second part of the article describes the two-stage framework development. The initial framework concept answered to the challenges resulting from the previous research. As soon as the first framework was developed, it became obvious that a second improved solution was required, almost as a showcase on how ideas can quickly be implemented for user testing, and for users to elicit requirements and creative solutions. The article finishes with a list of functionalities, resulting in new caption modes, and the opportunity of becoming a comprehensive immersive captions testbed, where tools such as eye-tracking, or physiological testing devices could be testing captions across any device with a web browser.

Background It is now common to search for health information online. A 2013 Pew Research Center survey found that 77% of online health seekers began their query at a search engine. The widespread use of online health information seeking also applies to women’s reproductive health. Despite online interest in birth control, not much is known about related interests and concerns reflected in the search terms in the United States. Objective In this study, we identify the top search terms on Google related to birth control in Louisiana and Mississippi and compare those results to the broader United States, examining how Google searches on birth control have evolved over time and identifying regional variation within states. Methods We accessed search data on birth control from 2014-2018 from 2 Google application programming interfaces (APIs), Google Trends and Google Health Trends. We selected Google as it is the most commonly used search engine. We focused our analysis on data from 2017 and compared with 2018 data as appropriate. To assess trends, we analyzed data from 2014 through 2018. To compare the relative search frequencies of the top queries across Louisiana, Mississippi, and the United States, we used the Google Health Trends API. Relative search volume by designated marketing area (DMA) gave us the rankings of search volume for each birth control method in each DMA as compared to one another. Results Results showed that when people searched for “birth control” in Louisiana and the broader United States, they were searching for information on a diverse spectrum of methods. This differs from Mississippi, where the data indicated people were mainly searching for information related to birth control pills. Across all locations, searches for birth control pills were significantly higher than any other queries related to birth control in the United States, Louisiana, and Mississippi, and this trend remained constant from 2014 to 2018. Regional level analysis showed variations in search traffic for birth control across each state. Conclusions The internet is a growing source of health information for many users, including information on birth control. Understanding popular Google search queries on birth control can inform in-person discussions initiated by family planning practitioners and broader birth control messaging campaigns. International Registered Report Identifier (IRRID) RR2-10.2196/16543

Satellite imagery is changing the way we understand and predict economic activity in the world. Advancements in satellite hardware and low-cost rocket launches have enabled near-real-time, high-resolution images covering the entire Earth. It is too labour-intensive, time-consuming and expensive for human annotators to analyse petabytes of satellite imagery manually. Current computer vision research exploring this problem still lack accuracy and prediction speed, both significantly important metrics for latency-sensitive automatized industrial applications. Here we address both of these challenges by proposing a set of improvements to the object recognition model design, training and complexity regularisation, applicable to a range of neural networks. Furthermore, we propose a fully convolutional neural network (FCN) architecture optimised for accurate and accelerated object recognition in multispectral satellite imagery. We show that our FCN exceeds human-level performance with state-of-the-art 97.67% accuracy over multiple sensors, it is able to generalize across dispersed scenery and outperforms other proposed methods to date. Its computationally light architecture delivers a fivefold improvement in training time and a rapid prediction, essential to real-time applications. To illustrate practical model effectiveness, we analyse it in algorithmic trading environment. Additionally, we publish a proprietary annotated satellite imagery dataset for further development in this research field. Our findings can be readily implemented for other real-time applications too.

Background In the era of big data, networks are becoming a popular factor in the field of data analysis. Networks are part of the main structure of BeGraph software, which is a 3D visualization application dedicated to the analysis of complex networks. Objective The main objective of this research was to visually analyze tendencies of mental health diseases in a region of Spain, using the BeGraph software, in order to make the most appropriate health-related decisions in each case. Methods For the study, a database was used with 13,531 records of patients with mental health disorders in three acute medical units from different health care complexes in a region of Spain. For the analysis, BeGraph software was applied. It is a web-based 3D visualization tool that allows the exploration and analysis of data through complex networks. Results The results obtained with the BeGraph software allowed us to determine the main disease in each of the health care complexes evaluated. We noted 6.50% (463/7118) of admissions involving unspecified paranoid schizophrenia at the University Clinic of Valladolid, 9.62% (397/4128) of admissions involving chronic paranoid schizophrenia with acute exacerbation at the Zamora Hospital, and 8.84% (202/2285) of admissions involving dysthymic disorder at the Rio Hortega Hospital in Valladolid. Conclusions The data analysis allowed us to focus on the main diseases detected in the health care complexes evaluated in order to analyze the behavior of disorders and help in diagnosis and treatment.

With the rapid development of emerging technologies, research on technology adoption is valuable for improving the reception efficiency of new technologies. This paper uses bibliometric analysis methods and visualization software to explore the research stages, the hot issues, the limitations of the research and the future fronts. A total of 11,706 documents were collected as the original data using the retrieval formulas. Sorted by the numbers of citations, the top 10% of the documents are extracted as the top-cited documents. First, combining software and bibliometric analysis, we obtain the annual development trends and identify the productive countries/regions, the influential institutions and the high-yielding authors. In addition, we overview the representative authors and their works in the development of technology adoption. Then, we conduct keyword analysis and burstiness analysis to identify the academic hotspots, research fronts and limitations in this field. The results show that increasingly more researches have shifted from theories to applications. Technology adoption has multiple applications in the fields of online shopping, mobile learning, mobile banking, e-learning and health care delivery. Finally, we draw conclusions on the bibliometric findings and forecast the future research trends of technology adoption. In the future, more researches will focus on the impacts of age, gender, culture, and the environment on technology adoption.

In this paper, a long-term workload management problem for multi-server edge computing with server collaboration is studied. In the considered model, mobile users computation-intensive tasks are generated dynamically over the time and offloaded to associated edge servers according to pre-determined subscription agreements. Upon receiving the subscribed workload, each edge server can then decide to whether participate in server collaboration for enabling workload re-allocation (i.e., workload exchange) with other heterogeneously configured edge servers. Unlike most of the existing work, this paper takes into account both competitions and collaborations among strategic edge servers in sharing their computing capacities. To achieve the equilibrium for each edge server in minimizing its expected cost (including energy consumption, delay, transmission, configuration and pricing costs), a joint optimization is formulated for determining i) its amount of workload to undertake, ii) compensation price charged from peers, and iii) computing speed to adopt. To efficiently solve this problem, we propose a novel cooperative queueing game approach, which integrates a convex optimization, a core cost sharing scheme and a mapping rule. Theoretical analyses and extensive simulations are conducted to evaluate the performance of the proposed solution, and demonstrate its superiority over counterparts.

This paper aims to predict a set of apps a user will open on her mobile device in the next time slot. Such an information is essential for many smartphone operations, e.g., app pre-loading and content pre-caching, to improve user experience. However, it is hard to build an explicit model that accurately captures the complex environment context and predicts a set of apps at one time. This paper presents a deep reinforcement learning framework, named as DeepAPP, which learns a model-free predictive neural network from historical app usage data. Meanwhile, an online updating strategy is designed to adapt the predictive network to the time-varying app usage behavior. To transform DeepAPP into a practical deep reinforcement learning system, several challenges are addressed by developing a context representation method for complex contextual environment, a general agent for overcoming data sparsity and a lightweight personalized agent for minimizing the prediction time. Extensive experiments on a large-scale anonymized app usage dataset reveal that DeepAPP provides high accuracy (precision 70.6% and recall of 62.4%) and reduces the prediction time of the state-of-the-art by 6.58 times. A field experiment of 29 participants demonstrates DeepAPP can effectively reduce launch time of apps.

This paper is the second part of a two-part survey series on large-scale global optimization. The first part covered two major algorithmic approaches to large-scale optimization, namely decomposition methods and hybridization methods such as memetic algorithms and local search. In this part we focus on sampling and variation operators, approximation and surrogate modeling, initialization methods, and parallelization. We also cover a range of problem areas in relation to large-scale global optimization, such as multi-objective optimization, constraint handling, overlapping components, the component imbalance issue, and benchmarks, and applications. The paper also includes a discussion on pitfalls and challenges of current research and identifies several potential areas of future research.

On-board embedded software developed for spaceflight systems (space software) must adhere to stringent software quality assurance procedures. For example, verification and validation activities are typically performed and assessed by third party organizations. To further minimize the risk of human mistakes, space agencies, such as the European Space Agency (ESA), are looking for automated solutions for the assessment of software testing activities, which play a crucial role in this context. Over the years, mutation analysis has shown to be a promising solution for the automated assessment of test suites; it consists of measuring the quality of a test suite in terms of the percentage of injected faults leading to a test failure. A number of optimization techniques, addressing scalability and accuracy problems, have been proposed to facilitate the industrial adoption of mutation analysis. However, to date, two major problems prevent space agencies from enforcing mutation analysis in space software development. In this paper, we enhance mutation analysis optimization techniques to enable their applicability to embedded software and propose a pipeline that successfully integrates them to address scalability and accuracy issues in this context, as described above. Further, we report on the largest study involving embedded software systems in the mutation analysis literature. Our research is part of a research project funded by ESA ESTEC involving private companies (GomSpace Luxembourg and LuxSpace) in the space sector. These industry partners provided the case studies reported in this paper; they include an on-board software system managing a microsatellite currently on-orbit, a set of libraries used in deployed cubesats, and a mathematical library certified by ESA., Accepted for publication on IEEE TRANSACTIONS ON SOFTWARE ENGINEERING

To achieve higher throughputs in cellular networks, 3GPP proposes to use unlicensed frequency bands and develops technologies - the latest one is NR-U - allowing a cellular base station to transmit in unlicensed bands, which are already occupied by Wi-Fi networks. To enable fair channel sharing between two technologies, the base station uses a sort of CSMA/CA with binary exponential backoff similar to Wi-Fi. However, the base station can start data transmission only at strictly periodic time moments. Many papers propose sending a reservation signal between the end of the backoff procedure and such a moment to prevent nearby devices from accessing the channel. However, this approach significantly reduces Wi-Fi performance. The paper proposes a novel method CR-LBT of transmitting a reservation signal that greatly decreases channel resource waste caused by collisions and improves channel resource sharing fairness. With developed analytical models and simulations, it is shown that CR-LBT may simultaneously increase the throughput of both NR-U and Wi-Fi networks. The effect is more noticeable for the Wi-Fi network, the throughput of which may rise three times compared with the traditional method of sending the reservation signal. Finally, the influence of various factors on CR-LBT performance is studied.

We present Arianna+, a framework to design networks of ontologies for representing knowledge enabling smart homes to perform human activity recognition online. In the network, nodes are ontologies allowing for various data contextualisation, while edges are general-purpose computational procedures elaborating data. Arianna+ provides a flexible interface between the inputs and outputs of procedures and statements, which are atomic representations of ontological knowledge. Arianna+ schedules procedures on the basis of events by employing logic-based reasoning, i.e., by checking the classification of certain statements in the ontologies. Each procedure involves input and output statements that are differently contextualised in the ontologies based on specific prior knowledge. Arianna+ allows to design networks that encode data within multiple contexts and, as a reference scenario, we present a modular network based on a spatial context shared among all activities and a temporal context specialised for each activity to be recognised. In the paper, we argue that a network of small ontologies is more intelligible and has a reduced computational load than a single ontology encoding the same knowledge. Arianna+ integrates in the same architecture heterogeneous data processing techniques, which may be better suited to different contexts. Thus, we do not propose a new algorithmic approach to activity recognition, instead, we focus on the architectural aspects for accommodating logic-based and data-driven activity models in a context-oriented way. Also, we discuss how to leverage data contextualisation and reasoning for activity recognition, and to support an iterative development process driven by domain experts., The paper has been accepted for publication in the IEEE Transactions on Cybernetics journal on April 2021 and with DOI 10.1109/TCYB.2021.3073539. It is an extension of arXiv:1707.03988v1 and it is related to the arXiv:1809.08208v1 article. It contains 20 pages, 6 figures, 4 tables and 2 Appendices

This paper focuses on designing high-data-rate wireless communications for drone networks in the mmWave and THz frequency bands. MmWave/THz-band communications has been envisioned as a key technology to achieve ultra broadband wireless links through beamforming in 5G and beyond networks. However, a main challenge with these frequency bands is that the narrow-beam directional wireless links can be easily disconnected because of the beam misalignment in mobile environments. To address this challenge, in this paper we design a new beam control scheme called LeBeam, with the objective of maximizing the expected capacity of the mmWave/THz-band links by determining the optimal beamwidth dynamically under drone mobility uncertainties. In LeBeam, an ESN is adopted to capture the mobility uncertainties of the drones dynamically and predict the optimal beamwidth based on the first- and second-order moments of the drone mobility. The ESN has been trained based on real drone flight traces. The performance of LeBeam is evaluated over UBSim, a newly developed trace-driven Universal Broadband Simulator for integrated aerial and ground wireless networking.

Numerous machine learning (ML), and more recently, deep learning (DL) based approaches, have been proposed to tackle scalability issues in electronic design automation, including those in integrated circuit (IC) test. This paper examines state-of-the-art DL for IC test and highlights two critical unaddressed challenges. The first challenge involves identifying fit-for-purpose statistical metrics to train and evaluate ML model performance and usefulness in IC test. Our work shows that current metrics do not reflect how well ML models have learned to generalize and perform in the domain-specific context. From this insight, we propose and evaluate alternative metrics that better capture a model’s likely usefulness in the IC test problem. The second challenge is to choose an appropriate input abstraction so as to enable an ML model to learn robust and reliable features. We investigate how well DL for IC test techniques generalize by exploring their robustness to perturbations that alter a netlist’s structure but do not alter its functionality. This paper provides insights into challenges via empirical evaluation of the state-ofthe- art and offers guidance for future work.

Offloading computation based on mobile edge computing paradigms can augment the computational capabilities of resource-scarce mobile devices. However, the capacity limitations of edge servers constrain the performance improvement achieved through computation offloading. In this paper, we consider a three-tier computation offloading schema with multiple users, edge servers and cloud servers. Computation can be offloaded from mobile devices to edge servers or can be further offloaded to remote cloud servers if necessary. Since a number of mobile devices connected to edge servers will share a common wireless communication network, which may contain both uplink and downlink channels, the assignment of bandwidth assignment the channels also constrains the performance improvement of computation offloading. In this paper, the problems of how to determine the offloading strategy and of how to assign the bandwidth are jointly studied and formulated as a programming problem to minimize the average application response time. We analyze the joint problem and further transform it into a piecewise convex programming problem. We propose an efficient algorithm that can find the optimal solution. Extensive experiments demonstrate that our algorithm significantly outperforms previous algorithms. The experimental results also show that the performance of our algorithm is highly robust.

In modern manufacturing, vision-based defect recognition is an essential technology to guarantee product quality, and it plays an important role in industrial intelligence. With the developments of industrial big data, defect images can be captured by ubiquitous sensors. And, how to realize accuracy recognition has become a research hotspot. In the past several years, many vision-based defect recognition methods have been proposed, and some newly-emerged techniques, such as deep learning, have become increasingly popular and have addressed many challenging problems effectively. Hence, a comprehensive review is urgently needed, and it can promote the development and bring some insights in this area. This paper surveys the recent advances in vision-based defect recognition and presents a systematical review from a feature perspective. This review divides the recent methods into designed-feature based methods and learned-feature based methods, and summarizes the advantages, disadvantages and application scenarios. Furthermore, this paper also summarizes the performance metrics for vision-based defect recognition methods. And some challenges and development trends are also discussed.

An increasing number of cloud services are operated globally, where the service data are frequently replicated across geographically distributed datacenters to improve service quality and reliability. Such replication generates many one-to-many bulk data transfers over inter-datacenter networks from one datacenter to many receiver datacenters. To provide end-users with guaranteed services, these data transfers are usually required to be completed within designated deadlines. Despite the exponential growth in data demand, there has been little work on guaranteeing deadlines for one-to-many transfers, which is the subject of this paper. This paper proposes a centralized admission control coupled with a scheduling algorithm, named deAdline-Guaranteed transfEr (AGE), to guarantee the deadline of admitted data transfers and utilize the network capacity efficiently. The key idea is to flexibly select the source datacenter for receiver datacenters and allow the remaining receivers to obtain a replica from either the original source or the other receivers that have already received a copy. By jointly allocating the source for receivers and the bandwidth and routing paths for every data transfer, AGE maximizes the number of deadline-satisfied transfers. Our simulations show that compared to the state-of-the-art, AGE guarantees the deadline for up to 70% more transfers, achieves at least 2× higher network throughput, and reduces the completion time up to 80%.

In recent years, plenty of metrics have been proposed to identify networks that are free of gradient explosion and vanishing. However, due to the diversity of network components and complex serial-parallel hybrid connections in modern DNNs, the evaluation of existing metrics usually requires strong assumptions, complex statistical analysis, or has limited application fields, which constraints their spread in the community. In this paper, inspired by the Gradient Norm Equality and dynamical isometry, we first propose a novel metric called Block Dynamical Isometry, which measures the change of gradient norm in individual block. Because our Block Dynamical Isometry is norm-based, its evaluation needs weaker assumptions compared with the original dynamical isometry. To mitigate the challenging derivation, we propose a highly modularized statistical framework based on free probability. Our framework includes several key theorems to handle complex serial-parallel hybrid connections and a library to cover the diversity of network components. Besides, several sufficient prerequisites are provided. Powered by our metric and framework, we analyze extensive initialization, normalization, and network structures. We find that Gradient Norm Equality is a universal philosophy behind them. Then, we improve some existing methods based on our analysis, including an activation function selection strategy for initialization techniques, a new configuration for weight normalization, and a depth-aware way to derive coefficients in SeLU. Moreover, we propose a novel normalization technique named second moment normalization, which is theoretically 30% faster than batch normalization without accuracy loss. Last but not least, our conclusions and methods are evidenced by extensive experiments on multiple models over CIFAR10 and ImageNet., Comment: Under review as a regular paper in TPAMI

Deep learning has emerged as a powerful machine learning technique to employ in multimodal sentiment analysis tasks. In the recent years, many deep learning models and various algorithms have been proposed in the field of multimodal sentiment analysis which urges the need to have survey papers that summarize the recent research trends and directions. This survey paper tackles a comprehensive overview of the latest updates in this field. We present a sophisticated categorization of thirty-five state-of-the-art models, which have recently been proposed in video sentiment analysis field, into eight categories based on the architecture used in each model. The effectiveness and efficiency of these models have been evaluated on the most two widely used datasets in the field, CMU-MOSI and CMU-MOSEI. After carrying out an intensive analysis of the results, we eventually conclude that the most powerful architecture in multimodal sentiment analysis task is the Multi-Modal Multi-Utterance based architecture, which exploits both the information from all modalities and the contextual information from the neighbouring utterances in a video in order to classify the target utterance. This architecture mainly consists of two modules whose order may vary from one model to another. The first module is the Context Extraction Module that is used to model the contextual relationship among the neighbouring utterances in the video and highlight which of the relevant contextual utterances are more important to predict the sentiment of the target one. In most recent models, this module is usually a bidirectional recurrent neural network based module. The second module is an Attention-Based Module that is responsible for fusing the three modalities (text, audio and video) and prioritizing only the important ones. Furthermore, this paper provides a brief summary of the most popular approaches that have been used to extract features from multimodal videos in addition to a comparative analysis between the most popular benchmark datasets in the field. We expect that these findings can help newcomers to have a panoramic view of the entire field and get quick experience from the provided helpful insights. This will guide them easily to the development of more effective models.

This paper discusses the key technologies for the fusion of Radio Frequency Identification (RFID) technology and wireless sensor networks through a fusion approach; meanwhile, it addresses the problem of energy imbalance infusion networks. This paper introduces the network energy consumption calculation methods under direct transmission and minimum energy multi-hop routing protocols, and designs an improved network structure model to improve the communication scale. The RFID reading and writing system based on Zig Bee technology is developed, and focuses on the hardware interface circuit design of the fusion system, the development of compatible communication protocols, the anti-collision algorithm, and the transmission performance of the system under two outdoor environments. The design of the environmental collection terminal uses relevant sensors to collect the transport environment data in the carriage. And Wireless Sensor Network (WSN) combined with General Packet Radio Service (GPRS) technology realizes the function of the main aggregation node of wireless sensors. The method achieves data aggregation and data transmission, and the development of the application platform of the monitoring system uses software technology. Based on the browser/server (B/S) architecture, the development of the monitoring system is finally realized. Finally, the cold chain transportation simulation experiment was conducted to test the system, and the results showed that the hardware of the cold chain coordination monitoring system can work normally and the software design of the monitoring system can meet the basic requirements of the system for the third-party logistics enterprises. The efficiency of our results is improved by about 10% compared to other studies, and their accuracy is improved to a higher degree, which makes our model more practical.

Recently, smart data has attracted great attention in the smart city community since it can provide valuable information to support intelligent services such as planning, monitoring, and decision making. However, it imposes a big challenge to explore smart data from big data gathered from smart city with various advanced fusion and analysis approaches. This paper proposes an incremental tensor-based fuzzy c-means approach (IT-FCM) for obtaining smart data from continuously generated big data. Specifically, a weighted version of the tensor-based fuzzy c-means approach (T-FCM) is firstly proposed to cluster the dataset that combines the previous cluster centroids and the new generated data. Aiming to improve the clustering efficiency, the old data objects are represented by the centroids to avoid repeat clustering. Furthermore, this paper presents an edge-cloud-aided clustering scheme to fuse big data from different sources and perspectives and further to implement co-clustering on the fused datasets for exploring smart data. Finally, the proposed IT-FCM approach is evaluated by comparing with T-FCM regarding clustering accuracy and efficiency on two different datasets in the experiments. The results state that IT-FCM outperforms T-FCM in clustering streaming big data in terms of accuracy and efficiency for obtaining smart data.

Big data has been continuously generated from the rapidly developing of cloud/fog/edge computing, Internet of Things (IoT) and 5G technology. This big data not only brings great benefits and opportunities to human beings but also brings many risks and challenges. One major challenge is how to represent and treat higher-order and heterogeneous data from multi-sources. Tensors are emerging as powerful tools for representation and modeling of this data. Tensor decomposition can be used to extract potentially useful information from this data. Thus, it has attracted much attention from the big data community. The main target of this paper is to propose a novel data fusion framework to solve several main challenges of CPSS data applications, including CPSS big data representation, fusion, efficient computing, storage, robustness, and security issues. In this paper, we use many graphics to visualize complex tensor decomposition and transformation processes. The visualization may help the readers better understand tensor and tensor decomposition. It also provides a general guideline and a good starting point for those who are interested in tensor and tensor decomposition. Specifically, we first introduce the most extensively used matrix and tensor decomposition methods. Second, the current popular data fusion methods are reviewed and summarized. Third, we propose a novel tensor-network-conversion-based data fusion approach which can simultaneously analyze multiple matrices and multiple tensors. To better understand this approach, we give a brief review of tensor network. Fourth, based on the proposed approach, a novel CPSS big data fusion framework is proposed in this paper. Meanwhile, we verify it by a concise case study. Finally, some challenges and open problems of the proposed framework are discussed. The discussion also includes some exciting future research directions in the big data fusion field.

Recent years have witnessed an enormous growth in the number of wireless IoT devices and thereby Internet of Things (IoT) is classified as one of the novel cutting edge technologies that has redesigned the traditional industry into a smart industry, given its applicability for a wide range of applications in providing data-driven decision-making. Meanwhile, the data with missing values is still emerging as one of the longstanding challenges in an IoT architecture due to the common-mode failures, potentially leading to both bias and loss of precision. In spite of the fact that numerous techniques have been developed for imputing missing values, the major issue in terms of imputation precision or computational complexity for large missing subsequences is still a matter under debate. To address this issue, this paper proposes a newly developed algorithm called MP-BMDI that ensures high imputation performance for supporting big data analyses in IoT-based applications, where the absence of large missing subsequences is fully required to offer unbiased results. In our approach, we initially seek a finite number of subsequences that are mostly similar to the subsequence before the missing values, then adjust the height of these following subsequences to optimal locations. Once the most proper subsequence for replacing is chosen among them based on the pattern score function PSF(r) introduced in this paper, the missing gap is completely filled by the corresponding subsequence. Numerical results are here presented to validate the merits of the proposed algorithm compared to the alternative benchmark approaches by leveraging sensor data collected from real-time environmental monitoring and deliver significant insights on the effectiveness of the proposed algorithm from various perspectives.

Single carrier multiple access division (SC-FDMA) technology is one of the good uplink modulation techniques in a wireless communication system. Promises high transmission speed, low bit error rate and high spectral efficiency with low peak to average power ratio (PAPR) compared to OFDMA. This paper is proposed analytical model and link level simulation using MATLAB® to enhance the ratio of peak average power (PAPR) performance for distributed SC-FDMA sub-carrier assignment of. The methodology using the first full-featured digital MIMO software allows for in-depth verification and improvement of MIMO technologies applied to satellite broadcasting networks. Moreover, the demonstrator allows to complete and confirm our theory and simulation-based. The aim of this paper is to enhancement PAPR by analyzing the mobile satellite digital that employed distributed sub-carrier assignment for MIMO-SC-FDMA. The model is verified and validated by link level simulation.

An in-depth analysis of the artificial intelligence online triage of hospitals in sustainable smart city is conducted, and a model of factors influencing patients’ choice of medical institutions is constructed based on the theory of planned behavior and Anderson’s health service utilization model. Based on the questionnaire and the model, a structural equation model is constructed to explore and analyze patients’ intention to seek medical treatment at the primary level and that at large hospitals respectively, revealing the mechanism of different influencing factors on patients’ intention to seek medical treatment at the primary level and that at large hospitals, and providing a reference for guiding patients to seek medical treatment at the primary level and choosing medical institutions nationally. (1) This paper reveals the influencing mechanism of patients’ medical treatment behavior, proposes a patient-centered medical institution selection method, and explores the strategic choices affecting patients’ primary care, which provides an important reference for establishing a scientific and reasonable hierarchical diagnosis and treatment model. (2) Meanwhile, how to provide precise medical services to patients by acquiring and fusing multi-source and multi-modal mass data will become one of the principles guarantees of a harmonious society in the future. (3) Compared with other studies, the accuracy and efficiency of the research results of the online hierarchical diagnosis and treatment model in this paper are greatly improved. The current results are also fully applicable to practical applications. In the future, we will conduct in-depth research on the general testability of the model. analysis.

Three-dimensional Morphable Models (3DMMs) are powerful statistical tools for representing the 3D shapes and textures of an object class. Here we present the most complete 3DMM of the human head to date that includes face, cranium, ears, eyes, teeth and tongue. To achieve this, we propose two methods for combining existing 3DMMs of different overlapping head parts: i. use a regressor to complete missing parts of one model using the other, ii. use the Gaussian Process framework to blend covariance matrices from multiple models. Thus we build a new combined face-and-head shape model that blends the variability and facial detail of an existing face model (the LSFM) with the full head modelling capability of an existing head model (the LYHM). Then we construct and fuse a highly-detailed ear model to extend the variation of the ear shape. Eye and eye region models are incorporated into the head model, along with basic models of the teeth, tongue and inner mouth cavity. The new model achieves state-of-the-art performance. We use our model to reconstruct full head representations from single, unconstrained images allowing us to parameterize craniofacial shape and texture, along with the ear shape, eye gaze and eye color., 18 pages, 18 figures, submitted to Transactions on Pattern Analysis and Machine Intelligence (TPAMI) on the 9th of October as an extension paper of the original oral CVPR paper : arXiv:1903.03785

Testing is the process of evaluating a system by manual or automated means. While Regression Test Selection (RTS) discards test cases and Test Suite Minimization (TSM) shows diminution in fault detection rate, Test Case Prioritization (TCP) does not discard test cases. Test Case Prioritization techniques can be coverage or historical information based or model based. It can also be cost-time aware or requirement-risk aware. GUI/Web applications need special prioritization mechanism. In this paper, 90 scholarly articles ranging from 2001 to 2018 have been reviewed. We have explored IEEE, Wiley, ACM Library, Springer, Taylor & Francis and Elsevier database. We have also described each prioritization method with their findings and subject programs. This paper includes a chronological catalogue listing of the reviewed papers. We have framed three research questions which sum up the frequently used prioritization metrics, regularly used subject programs and the distribution of different prioritization techniques. To the best of our knowledge, this is the first review with a detail report of the last 18 years of TCP techniques. We hope this article will be beneficial for both beginners and seasoned professionals.

With the rapid development of information and network technology, hospital information systems (HIS) has also become a hot research area. However, data could be subjected to the threat of security attacks, leakage, tampering, and forgery during medical data transmissions, data storage, and sharing based on public networks and cloud environments. The immutability, decentralization and anonymity of the blockchain provided new ways for solving the aforementioned problems. This paper proposes a complete medical information system model based on blockchain technology, to realize the goal of safe storage and sharing of medical data. A data collection system based on Internet of Things (IoT) was also developed that can simultaneously collect data from different types of non-invasive medical instruments to realize real-time collection of patient health record during surgery (SHR). This system designed an anonymous medical data sharing scheme based on cloud servers and proxy re-encryption algorithm to improve the security of private medical data sharing. The system was implemented based on the permissioned blockchain architecture Hyperledger Fabric, and a dual-channel Fabric deployment architecture and medical chaincode were designed for data management and access control. We also carried out computing overhead test, performance test and safety evaluation on the system, and the test results meet the requirements of actual medical production environment. The research work of this paper provides means for remote diagnosis and treatment, data mining and other practical applications based on the medical data on the blockchain.

Serverless computing has seen a myriad of work exploring its potential. Some systems tackle Function-as-a-Service (FaaS) properties on automatic elasticity and scale to run highly-parallel computing jobs. However, they focus on specific platforms and convey that their ideas can be extrapolated to any FaaS runtime. An important question arises: do all FaaS platforms fit parallel computations? In this paper, we argue that not all of them provide the necessary means to host highly-parallel applications. To validate our hypothesis, we create a comparative framework and categorize the architectures of four cloud FaaS offerings, emphasizing parallel performance. We attest and extend this description with an empirical experiment that consists in plotting in deep detail the evolution of a parallel computing job on each service. The analysis of our results evinces that FaaS is not inherently good for parallel computations and architectural differences across platforms are decisive to categorize their performance. A key insight is the importance of virtualization technologies and the scheduling approach of FaaS platforms. Parallelism improves with lighter virtualization and proactive scheduling due to finer resource allocation and faster elasticity. This causes some platforms like AWS and IBM to perform well for highly-parallel computations, while others such as Azure present difficulties to achieve the required parallelism degree. Consequently, the information in this paper becomes of special interest to help users choose the most adequate infrastructure for their parallel applications., Comment: 19 pages, 15 figures, submitted to FGCS, revised

Aiming at the security issues during the multi-types data storage and data transmission in autonomous Internet of Things (IoT) systems, this paper proposes an AI algorithm for data enhanced encryption used in the ends and the intermediate nodes of IoTs. The algorithm in this paper first constructs a three-dimensional Arnold transformation matrix for data unit value encryption in the end of IoTs, and designs a quantum logic intelligent mapping that effectively diffuses the encrypted data units to reduce the linear correlation of the image data and to improve the security performance of IoT edge data. Furthermore, the algorithm designs an AI access strategy for scrambling sequence nodes and builds a random-access route for the elements of the scrambling sequence which can reduce the calculation cost and improve the operating efficiency of IoT system in the ends and intermediate nodes. Finally, the data shared matrix is used to share the encrypted data to achieve the (k, n) threshold strategy. Experimental results prove that the algorithm has high plaintext and key sensitivity and can effectively resist brute force attacks, statistical analysis and differential attacks. The algorithm in this paper provides an AI solution for data security encryption in the ends and the intermediate nodes of autonomous IoT systems.

Nowadays smartphones become an indispensable tool in many people's everyday life that makes themselves attractive targets for attackers. Among various malware targeting at smartphones, SMS-based malware is one of the most notorious ones. Though a number of Android dynamic analysis frameworks have been proposed to analyze SMS-based malware, most of these frameworks or some Android tools, such as Google Android Emulator, do not support an app or malware to send SMS messages to a real smartphone; hence, security researchers cannot use them directly to analyze the behavior of SMS-based malware. In our previous work, SMS Helper, we designed an application layer tool to allow an app or malware in an Android emulator to send and receive SMS messages to or from a real smartphone. Based on SMS Helper, this paper proposes an Android dynamic analysis framework, called SMS Observer, to assist security researchers to analyze SMS-based malware. SMS Observer integrates SMS Helper into it as a client agent, meanwhile, and it maintains the integrity of system logs. This paper also figures out a way to detect whether an app is executed in an emulator and describes how to use SMS Observer to prevent such evasion. Experimental results using real-world malware samples show SMS Observer is much more effective in detecting SMS-related behavior of SMS-based malware than existing frameworks, such as Google Android Emulator, Andrubis, CopperDroid, and DroidBox. SMS Observer can analyze sophisticated SMS-based malware samples and provide a comprehensive view of malicious behavior.

Since project monitoring aims to make decisions, which have future impacts on a project’s success, accurate forecasting of project characteristics is of greater importance. This paper proposes the detection of problems in scheduling projects by introducing the forecasting of successors and renewable resource features. For this purpose, this paper presents the novel applications of forecasting models ”long short term memory” (LSTM) and ”gated recurrent unit” (GRU) in this study. Subsequently, forecasting results of successors and renewable resource characteristics of projects are determined by covering historical records’ observed values from real-life engineering projects’ datasets. Results show that LSTM and GRU models’ proposed applications can reduce errors from one up to seven steps-ahead forecastings. Moreover, forecasting the increased number of successors may require more renewable resources to effectively complete the jobs in projects. Generally, the proposed models are reliable and robust to application in forecasting the project scheduling task.

Most of the papers published so far on fractional discrete systems are related to theoretical results on their chaotic behaviors or to applications based on the mathematical modeling of the chaotic phenomena. No paper has been published to date regarding the hardware implementation of hyperchaotic fractional maps. This manuscript makes a contribution to the topic by presenting the first example of hardware implementation of hyperchaotic fractional maps. In particular, by exploiting the Grunwald–Letnikov difference operator, the paper introduces a new version of the fractional Grassi–Miller map. The system dynamics are analyzed via bifurcation diagrams and Lyapunov exponents, showing that the conceived map is hyperchaotic when the fractional order μ belongs to the interval [ 0 . 966 , 1 ] . Finally, a hardware implementation of the fractional map is illustrated, with the aim to concretely highlight the presence of hyperchaos in physical systems described by fractional difference equations. Arduino, an open-source platform, has been used to illustrate the simplicity as well as the feasibility of the implementation.

This paper presents an automated, domain-independent, metamorphic testing platform called MTKeras. In this paper, we report on an investigation demonstrating the effectiveness and usability of MTKeras through five case studies in the four domains of image classification, sentiment analysis, search engines and database management systems. We also report on the effectiveness of combining metamorphic relation (input) patterns in individual metamorphic relations, enhancing the failure-finding abilities of the individual relations. The results of our experiments support combining patterns, and the use of MTKeras. The research reported in this paper shows the applicability of metamorphic relation patterns, and introduces a practical tool for the research community.

Context: Higher Order Mutants (HOMs) present some advantages concerning the First-Order Mutants (FOMs). HOMs can better simulate real and subtle faults, reduce the number of generated mutants and test cases, and so on. Objective: In order to characterize the Higher Order Mutation Testing (HOMT) field, this paper presents results of a mapping study, by synthesizing characteristics of the HOMT approaches, HOM generation strategies, evaluation aspects, trends and research opportunities. Method: We followed a research plan to locate, assess, extract and group the outcomes from relevant studies. We found 69 primary studies, which were classified based on dimensions related to aspects of the conducted evaluation, purpose and use of HOMs. Results: Java is the preferred language. Most approaches use Second-Order Mutants (SOMs). We found 50 different techniques used to generate/select HOMs. We observed that from 39 primary studies which apply a strategy, ≈49% use search-based techniques. Conclusions: HOMT has been arising interest in the last years. The results herein presented provide researchers the start-of-the-art on HOMT, allowing them to understand existing approaches, and how the HOMs have been used and evaluated. Furthermore, this paper points out open issues and not addressed topics, which require more investigation, discussing trends and research opportunities in the field.

This paper argues that training GANs on local and non-local dependencies in speech data offers insights into how deep neural networks discretize continuous data and how symbolic-like rule-based morphophonological processes emerge in a deep convolutional architecture. Acquisition of speech has recently been modeled as a dependency between latent space and data generated by GANs in Begu\v{s} (2020b; arXiv:2006.03965), who models learning of a simple local allophonic distribution. We extend this approach to test learning of local and non-local phonological processes that include approximations of morphological processes. We further parallel outputs of the model to results of a behavioral experiment where human subjects are trained on the data used for training the GAN network. Four main conclusions emerge: (i) the networks provide useful information for computational models of speech acquisition even if trained on a comparatively small dataset of an artificial grammar learning experiment; (ii) local processes are easier to learn than non-local processes, which matches both behavioral data in human subjects and typology in the world's languages. This paper also proposes (iii) how we can actively observe the network's progress in learning and explore the effect of training steps on learning representations by keeping latent space constant across different training steps. Finally, this paper shows that (iv) the network learns to encode the presence of a prefix with a single latent variable; by interpolating this variable, we can actively observe the operation of a non-local phonological process. The proposed technique for retrieving learning representations has general implications for our understanding of how GANs discretize continuous speech data and suggests that rule-like generalizations in the training data are represented as an interaction between variables in the network's latent space., Comment: In press at Computer Speech & Language

RFID is an established technology and its implementation has been increasing steadily in different industries in the last decades. An important and relatively recent RFID breakthrough has been that of moving the level of tagging from pallet- or case-level, to item-level. This development has opened up a new set of use cases and benefits, especially in retail. One of these new use cases is the estimation of items’ location by positioning and tracking the tags attached to them. This problem is often seen as a classification problem, especially when tags that are read at the retail store must be located either in the sales floor or in the backroom area. The typical approach to ease this classification consists of physically shielding the interested areas via hardware installations, although this solution is expensive and lacks flexibility. In this paper, we present a different solution, namely a software-based shielding approach, to address the classification problem. Our solution makes use of item-level RFID tags and is based on the well-known logistic regression. Whenever a reading session is performed by means of a handheld reader, the classification model estimates in real-time (i.e. within a few seconds) which tagged items are in the same area of the reader and which are not, with no need of any shielding hardware installation. According to the validation preliminary tests presented in this paper, in which we simulated a fashion retail store, the proposed approach has an overall average accuracy of 95.5%.

International audience; This paper presents a novel method for image manipulation iden- tification of natural images in JPEG format. The image forgery detection technique is based on a signal-dependent noise model that is relevant to de- scribe a natural image acquired by a digital camera. This parametric model is characterized by two fingerprints which are used to falsification identification. The problem is cast in the framework of the hypothesis testing theory. For practical use, the Generalized Likelihood Ratio Tests (GLRT) are presented and their performance is theoretically established. There are different types of image forgery which have been considered in this paper for example re- sampling, Gaussian filtering and median filtering. Experiments with real and simulated images highlight the relevance of the proposed approach.

Facial emotion recognition (FER) methods have been proposed mainly using 2D images. These methods suffer from many problems caused by the difficult conditions of unconstrained environments such as light conditions and view variations. In this paper, we aim to recognize the emotional facial expressions independently of their identity using the 3D data and 2D depth images. Since the 3D FER is a very fine-grained recognition task, mapping the 3D images into 2D depth images may lack some geometric characteristics of the expressive face and decay the FER performance. Convolutional Neural Networks (CNN), however, have been successfully applied to the 2D depth images and improved handcrafted-based methods in computer vision and pattern recognition applications. For this reason, we combine in this paper two types of features; handcrafted and deep learning features and prove their complementarity for 3D FER. Favorably, covariance descriptors have proven a very good ability to combine features from different types into a compact representation. Therefore, we propose to use the covariance matrices of features (handcrafted and deep ones), instead of the features independently. Since covariance matrices belong to one of the manifold space types, formed by SPD (Symmetric Positive Definite) matrices, we mainly focus on the generalization of the RBF kernel to the manifold space for 3D FER using a supervised SVM classification. The achieved performance of the proposed method on the Bosphorus and BU-3DFE datasets outperforms similar state-of-the-arts.

This paper proposes a new tent-multi dynamic piecewise coupled mapping lattice (TMDPCML). Through the comprehensive analysis of the performance test results, TMDPCML system increases the correlation dynamics of spatiotemporal behavior and improves the efficiency of energy diffusion between lattices. Moreover, TMDPCML system has larger parameter space, better chaos and outstanding cryptographic characteristics. Therefore, this paper proposes a privacy image encryption algorithm combined with TMDPCML system. The application of TMDPCML system in private images encryption further proves that TMDPCML system has good chaotic behavior and meets the requirements of cryptography.

In medical fields it is very difficult and time-consuming to label samples. Only a small number of labeled samples or unlabeled samples are often encountered in medical fields. How to deal with this problem in medical diagnosis? Domain adaptation is an effective machine learning method to solve the scarce or no labeled samples problem. In this paper, an improved adversarial domain adaptation network is presented to solve this problem in tumor image diagnosis. We construct the tumor image diagnosis adversarial domain adaptation network framework. The framework consists of three parts: a feature extractor, a domain discriminator and a label predictor. The loss function of framework is designed in the paper. We design a feature extractor to acquire the domain invariant feature between the source domain and target domain. The feature extractor is an improved neural network consisting of several convolutional layers and sampling layers. The feature extractor pre-processes the input samples and gets the initial feature of the input space. The domain discriminator predicts the domain label and works adversarial with the feature extractor. The adversarial learning between the feature extractor and the domain discriminator acts as a regularization in the framework. The adversarial game can minimize the distance between the two domains and make sure the feature extractor learns the domain invariant feature. A label predictor is designed to classify the tumor image of the target domain based on the domain-invariant feature. The experiments on tumor image dataset are presented to validate the performance of proposed method. The experimental results show that the proposed method is superior to the other domain adaptation methods.

Automatic marking of English compositions is a rapidly developing field in recent years. It has gradually replaced teachers’ manual reading and become an important tool to relieve the teaching burden. The existing literature shows that the error of verb consistency and the error of verb tense are the two types of grammatical errors with the highest error rate in English composition. Hence, the detection results of verb errors can reflect the practicability and effectiveness of an automatic reading system. This paper proposes an English verb’s grammar error detection algorithm based on the cyclic neural network. Since LSTM can effectively retain the valid information in the context during training, this paper decided to use LSTM to model the labeled training corpus. At the same time, how to convert the text information in English compositions into numerical values for subsequent calculation is also an important step in automatic reading. Most mainstream tools use the word bag model, i.e., each word is encoded according to the order of each word in the dictionary. Although this encoding method is simple and easy to use, it not only causes the vector to lose the sequence information of the text but also is prone to dimensional disaster. Therefore, word embedding model is adopted in this paper to encode the text, and the text information is sequentially mapped to a low-dimensional vector space. In this way, the position information of the text is not lost, and the dimensional disaster is avoided. The proposed work collects some corpus samples and compares the proposed algorithm with Jouku and Bingguo. The verification results show the superiority of the proposed algorithm in verb error detection.