Search

Researchers from academia and the corporate-sector rely on scholarly digital libraries to access articles. Attackers take advantage of innocent users who consider the articles' files safe and thus open PDF-files with little concern. In addition, researchers consider scholarly libraries a reliable, trusted, and untainted corpus of papers. For these reasons, scholarly digital libraries are an attractive-target and inadvertently support the proliferation of cyber-attacks launched via malicious PDF-files. In this study, we present related vulnerabilities and malware distribution approaches that exploit the vulnerabilities of scholarly digital libraries. We evaluated over two-million scholarly papers in the CiteSeerX library and found the library to be contaminated with a surprisingly large number (0.3-2%) of malicious PDF documents (over 55% were crawled from the IPs of US-universities). We developed a two layered detection framework aimed at enhancing the detection of malicious PDF documents, Sec-Lib, which offers a security solution for large digital libraries. Sec-Lib includes a deterministic layer for detecting known malware, and a machine learning based layer for detecting unknown malware. Our evaluation showed that scholarly digital libraries can detect 96.9% of malware with Sec-Lib, while minimizing the number of PDF-files requiring labeling, and thus reducing the manual inspection efforts of security-experts by 98%.

© 2013 IEEE. With the rapid growth of scientific publications, it is hard for researchers to acquire appropriate papers that meet their expectations. Recommendation system for scientific articles is an essential technology to overcome this problem. In this paper, we propose a novel low-rank and sparse matrix factorization-based paper recommendation (LSMFPRec) method for authors. The proposed method seamlessly combines low-rank and sparse matrix factorization method with fine-grained paper and author affinity matrixes that are extracted from heterogeneous scientific network. Thus, it can effectively alleviate the sparsity and cold start problems that exist in traditional matrix factorization based collaborative filtering methods. Moreover, LSMFPRec can significantly reduce the error propagated from intermediate outputs. In addition, the proposed method essentially captures the low-rank and sparse characteristics that exist in scientific rating activities; therefore, it can generate more reasonable predicted ratings for influential and uninfluential papers. The effectiveness of the proposed LSMFPRec is demonstrated by the recommendation evaluation conducted on the AAN and CiteULike data sets.

Over the decades, the immense growth has been reported in research publications due to continuous developments in science. To date, various approaches have been proposed that find similarity between research papers by applying different similarity measures collectively or individually based on the content of research papers. However, the contemporary schemes are not conceptualized enough to find related research papers in a coherent manner. This paper is aimed at finding related research papers by proposing a comprehensive and conceptualized model via building ontology named COReS: Content-based Ontology for Research Paper Similarity. The ontology is built by finding the explicit relationships (i.e., super-type sub-type, disjointedness, and overlapping) between state-of-the-art similarity techniques. This paper presents the applications of the COReS model in the form of a case study followed by an experiment. The case study uses InText citation-based and vector space-based similarity measures and relationships between these measures as defined in COReS. The experiment focuses on the computation of comprehensive similarity and other content-based similarity measures and rankings of research papers according to these measures. The obtained Spearman correlation coefficient results between ranks of research papers for different similarity measures and user study-based measure, justify the application of COReS for the computation of document similarity. The COReS is in the process of evaluation for ontological errors. In the future, COReS will be enriched to provide more knowledge to improve the process of comprehensive research paper similarity computation.

Most existing studies and public datasets for handwritten Chinese text recognition are based on the regular documents with clean and blank background, lacking research reports for handwritten text recognition on challenging areas such as educational documents and financial bills. In this paper, we focus on examination paper text recognition and construct a challenging dataset named examination paper text (SCUT-EPT) dataset, which contains 50 000 text line images (40 000 for training and 10 000 for testing) selected from the examination papers of 2 986 volunteers. The proposed SCUT-EPT dataset presents numerous novel challenges, including character erasure, text line supplement, character/phrase switching, noised background, nonuniform word size, and unbalanced text length. In our experiments, the current advanced text recognition methods, such as convolutional recurrent neural network (CRNN) exhibits poor performance on the proposed SCUT-EPT dataset, proving the challenge and significance of the dataset. Nevertheless, through visualizing and error analysis, we observe that humans can avoid vast majority of the error predictions, which reveal the limitations and drawbacks of the current methods for handwritten Chinese text recognition (HCTR). Finally, three popular sequence transcription methods, connectionist temporal classification (CTC), attention mechanism, and cascaded attention-CTC are investigated for HCTR problem. It is interesting to observe that although the attention mechanism has been proved to be very effective in English scene text recognition, its performance is far inferior to the CTC method in the case of HCTR with large-scale character set.

Recently, it has been shown that channel feedback helps to enhance the physical layer security (PLS) of communication systems. The current use of feedback focuses on generating secret keys protecting the transmitted messages, and this feedback scheme is proved to be optimal for some physically degraded channel models. In this paper, we revisit the model of the state-dependent wiretap channel with the noncausal state at the transmitter, which plays an important role in the PLS of the wireless communication systems. We propose a new feedback scheme for this model and show that the proposed new scheme performs better than the already existing secret key-based feedback scheme. The results of this paper are further explained via a Gaussian example.

Voice-over IP (VoIP) technology is a kind of digital transmission technology based on IP network. It is one of the important methods to use voice service in VoIP as steganographic carrier to ensure secure transmission. However, the traditional steganographic code has some problems, such as low embedding efficiency and weak concealment, which cannot meet the requirements of VoIP streaming media information hiding for the security of secret information. Therefore, a steganographic algorithm combining F5 and simplified wet paper code (SWPC) algorithm is proposed. The main idea is to embed secret messages in each row of the carrier matrix using the F5 algorithm, and then the SWPC algorithm is used to embed the columns according to the wet and dry characteristics of the wet paper code without affecting the results before row embedding. We use the VoIP streams encoded by the ITU-T G.729a codec as a carrier to verify the proposed scheme. The experimental results demonstrate that the proposed scheme can achieve relatively better IP speech data steganographic transparency and that it can outperform F5-WPC and SWPC approaches.

Lifetime estimation of power semiconductor devices have been widely investigated to improve the reliability and reduce the cost of maintenance of power converters. However in most reported work, the aging effect is not considered in the lifetime evaluation process due to the omission or limitation of thermal cycle counting method. Additionally, the electrical/thermal simulation and lifetime estimation are usually implemented in different simulators/platforms, for the same reason. Thus, to tackle these problems, a concise but comprehensive MOSFET model that enables electro-thermal modeling, aging and lifetime estimation on LTspice® circuit simulator is proposed in this paper. The idea comes from the fact that, MOSFET on-state resistance Rds,on is not only temperature dependent, but also widely accepted as the device failure precursor. In other words, as it carries critical information about instantaneous temperature and aging progress. Hence, co-simulation can be achieved by constructing electrical, thermal, and aging and lifetime sub-modules exclusively first, and using Rds,on, to build linkages among them. Averaged modeling technique is adopted due to the ease of establishing links among these three sub-modules, and fast simulation speed as compared to a switched converter model. Behavioral models are employed to realize the thermal cycles counting, stress accumulation and degradation evaluation. This paper demonstrates that it is possible to use a single simulation software to monitor performances of devices and circuits, and their lifetime estimation simultaneously. High-stress thermal cycling and long-term random mission profiles are applied to verify the correctness of the model and to mimic a 10-year load respectively. An accelerated aging trend can be observed in the long-term mission profile simulation, which is in agreement with the theory. Facilitated by the employment of averaged circuits, the proposed method is a good simulation/analytical tool to implement a long-term mission profile that requires reliability assessment.

This paper tackles the problem of detecting incongruities between headlines and body text, where a news headline is irrelevant or even in opposition to the information in its body. Our model, called the graph-based hierarchical dual encoder (GHDE), utilizes a graph neural network to efficiently learn the content similarity between news headlines and long body paragraphs. This paper also releases a million-item-scale dataset of incongruity labels that can be used for training. The experimental results show that the proposed graph-based neural network model outperforms previous state-of-the-art models by a substantial margin (5.3%) on the area under the receiver operating characteristic (AUROC) curve. Real-world experiments on recent news articles confirm that the trained model successfully detects headline incongruities. We discuss the implications of these findings for combating infodemics and news fatigue.

In the process of power transmission and distribution, non-technical losses are usually caused by users’ abnormal power consumption behavior. It will not only affect the dispatch and operation of the distribution network, bring hidden dangers to the security of the power grid, but also damage the operating costs of power companies and disrupt the operation of the power market. Aiming at users’ abnormal electricity consumption behavior, this paper proposes a model based on particle swarm optimization and long-short term memory with the attention mechanism (PSO-Attention-LSTM). Firstly, according to the actual electricity theft behavior, six typical electricity theft modes are summarized, and 4 composite modes are obtained by combining them, so as to comprehensively test the detection performance of the model for various electricity theft behaviors. Secondly, a detection model based on PSO-Attention-LSTM is proposed, and the model is built using the TensorFlow framework. The model uses the attention mechanism to give different weights to the hidden state of LSTM, which reduces the loss of historical information, strengthens important information and suppresses useless information. Use PSO to solve the difficult problem of model parameter selection, and optimize the hyperparameters to improve the model performance. Finally, the data set of the University of Massachusetts was used for simulation and compared with convolutional neural network-long short term memory (CNN-LSTM), attention mechanism-based long short term memory (Attention-LSTM), LSTM, gated recurrent unit (GRU), support vector regression (SVR), random forest (RF) and linear regression (LR) to verify the effectiveness and accuracy of the method used in this article. In this paper, Matlab software is used to analyze and visualize the detection result data.

To prevent privacy leakage, cloud services need to take corresponding methods, so participants often face the dilemma of service utility and privacy protection. In this paper, we propose a dynamic adaptive access control model based on trust permission and privacy protection to solve the problem of privacy disclosure and utility in the cloud service. Firstly, we add the concept of obligation and purpose into access control and establish the privacy information tree and privacy policy tree. Secondly, we establish a new trust evaluation and give the corresponding weight algorithm. Thirdly, we quantify the privacy information with the normal space and correlation coefficient method. Further, we propose a tradeoff relationship model between trust permission and privacy protection, each participant can select the corresponding parameters according to the actual requirement and personal preference. Experimental analysis and comparison results verify the feasibility, effectiveness, and superiority of our method. Finally, we summarize the work of this paper and point out the future development direction.

An intrusion detection system (IDS) is an important protection instrument for detecting complex network attacks. Various machine learning (ML) or deep learning (DL) algorithms have been proposed for implementing anomaly-based IDS (AIDS). Our review of the AIDS literature identifies some issues in related work, including the randomness of the selected algorithms, parameters, and testing criteria, the application of old datasets, or shallow analyses and validation of the results. This paper comprehensively reviews previous studies on AIDS by using a set of criteria with different datasets and types of attacks to set benchmarking outcomes that can reveal the suitable AIDS algorithms, parameters, and testing criteria. Specifically, this paper applies 10 popular supervised and unsupervised ML algorithms for identifying effective and efficient ML-AIDS of networks and computers. These supervised ML algorithms include the artificial neural network (ANN), decision tree (DT), k-nearest neighbor (k-NN), naive Bayes (NB), random forest (RF), support vector machine (SVM), and convolutional neural network (CNN) algorithms, whereas the unsupervised ML algorithms include the expectation-maximization (EM), k-means, and self-organizing maps (SOM) algorithms. Several models of these algorithms are introduced, and the turning and training parameters of each algorithm are examined to achieve an optimal classifier evaluation. Unlike previous studies, this study evaluates the performance of AIDS by measuring the true positive and negative rates, accuracy, precision, recall, and F-Score of 31 ML-AIDS models. The training and testing time for ML-AIDS models are also considered in measuring their performance efficiency given that time complexity is an important factor in AIDSs. The ML-AIDS models are tested by using a recent and highly unbalanced multiclass CICIDS2017 dataset that involves real-world network attacks. In general, the k-NN-AIDS, DT-AIDS, and NB-AIDS models obtain the best results and show a greater capability in detecting web attacks compared with other models that demonstrate irregular and inferior results.

Handwritten mathematical expressions are an essential part of many domains, including education, engineering, and science. The pervasive availability of computationally powerful touch-screen devices, similar to the recent emergence of deep neural networks as high-quality sequence recognition models, result in the widespread adoption of online recognition of handwritten mathematical expressions. Also, a deeper study and improvement of such technologies is necessary to address the current challenges posed by the extensive usage of distance learning, and remote work due to the world pandemic. This paper delineates the state-of-the-art recognition methods along with the user's experience in pen-centric applications for operating with handwritten mathematical expressions. Recognition methods have been categorized into classes, with a description of their merits and limitations. Particular attention is paid to end-to-end approaches based on encoder-decoder architecture and multi-modal input. Evaluation protocols and open benchmark datasets are considered as well as the comparison of the recognition performance, based on open competition results. The use of handwritten math recognition is illustrated by examples of applications for various fields and platforms. A distinctive part of the survey is that we also considered how UI design relies on the use of different recognition approaches, which is aimed at helping potential researchers improve the performance of the introduced approaches toward the best responses in practical applications. Finally, this paper presents the prospective survey of future research directions in handwritten mathematical expression recognition and their applications.

Industry 4.0 is a revolution in manufacturing by introducing disruptive technologies such as Internet of Things (IoT) and cloud-computing into the heart of the factory. The resulting increased automation and the improved production synergy between stocks, supply chains and customer demands, come along with the threats and attacks from the Internet. Despite extensive literature on the cybersecurity topic, many actors in manufacturing factories are just realizing the impact of cybersecurity in the preservation of their business. This paper introduces step-by-step the concepts and practical aspects of an Industry 4.0 manufacturing factory that are related to cybersecurity. Based on a subdivision of a typical factory into several generic perimeters, we present the vulnerabilities and threats regarding the network and devices usually found in each perimeter. Therefore, it is more efficient to present the recent proposals of the literature regarding cybersecurity guidelines and solutions in Industry 4.0. Instead of spreading a lot of references regarding every aspect of cybersecurity, we focused on a limited number of papers among the recent references. However, for each paper, we provide the details about the purpose of the proposal, the methodology adopted, the technical solution developed and its evaluation by the authors. These solutions range from classical cybersecurity countermeasures to innovative ones, such as those based on honeypots and digital twins. In order to deliver a review also useful to non scientists, we present our guidelines along with those of some organizations involved in cybersecurity harmonization and standardization in the world.

The Internet of Things is based on a communication network to automatically receive various information from the natural world. It uses intelligent objects with perception, communication and computers to automatically receive various information from nature. All independently managed physical objects are connected to each other to achieve integrated perception, reliable transmission and intelligent processing, and to establish intelligent information between people and objects, and objects and object service systems. This article mainly introduces the impact of industrial agglomeration on the regional economy in a simulated intelligent environment based on machine learning. This paper proposes a method to detect industrial agglomeration index to analyze industrial agglomeration. Through the establishment of the industrial agglomeration index system, the level of integration of the manufacturing industry in our city was objectively analyzed, and the impact of the integration of manufacturing industry on our city was tested empirically. Finally, the relationship between industrial integration and regional economic development was tested. The experimental results in this paper show that industrial integration in a smart environment based on simulation learning has a significant positive impact on regional economic development. Among them, the level of cooperation between the manufacturing service industry and the manufacturing industry increased by 1%, and the level of regional economic development increased by 0.025%.

Technology forecasting not only helps business managers to make the right decisions but also helps researchers to grasp the direction of technology development. Technology forecasting, which facilitates the identification of the development technologies with high potential, can be an effective tool to support the management and plan for the future research activities. For this purpose, this paper firstly constructs Multi-modal input based on deep learning (MIDL) text classification model to extract relevant SCI papers from Web of Science database from 1996 to 2019 for topic classification, and then apply the Ensemble Empirical Mode Decomposition (EEMD) and Long Short-Term Memory (LSTM) neural networks to build an EEMD-LSTM technology forecasting model to predict the future development of each research field. Besides, we verify the validity of the method by taking robotics as an example in this paper. The results show that the accuracy, recall and F1 of MIDL text classification model are 0.826, 0.822 and 0.824 respectively. As compared with the optimal results of other classification models, the accuracy, recall and F1 are improved by 4.1%, 3.5%, and 3.8% respectively. The mean MAPE of the EEMD-LSTM model is 7%, which is 11% lower than ARIMA, 8% lower than LSTM, and 10% lower than 2-layer-LSTM.

As is the case in many big data mining scenarios with a large scale of samples, the heavy computation cost hinders the application of machine learning, which has to iteratively compute by passing over the whole dataset without considering the roles of different samples in training computation. However, we argue that most of the samples dominating computation resources contribute little to the gradient-based model update, particularly when the model is close to convergence. We define this observation as the Sample Contribution Pattern (SCP) in machine learning. This paper proposes two approaches to exploit SCP by detecting gradient characteristics and triggering the reuse of outdated gradients. In particular, this paper reports research results in (1) the definition and description of SCP to reveal an intrinsic gradient contribution pattern of different samples; (2) a novel SCP-based optimizing algorithm (SCPOA) that outperforms alternative tested algorithms in terms of computation overhead; (3) a variant of SCPOA that incorporates discarding-recovering mechanisms to carefully tradeoff between model accuracy and computation cost; (4) the implementation and evaluation of two algorithms based on popular distributed big data mining platforms running typical sample-sets; (5) intuitive convergence proof of the algorithms. Our experimental results illustrate that the proposed approaches can significantly reduce the computation cost with competitive accuracy.

In recent years, a variety of supervised manifold learning techniques have been proposed to outperform their unsupervised alternative versions in terms of classification accuracy and data structure capturing. Some dissimilarity measures have been used in these techniques to guide the dimensionality reduction process. Their good performance was empirically demonstrated; however, the relevant analysis is still missing. This paper contributes to a theoretical analysis on a) how dissimilarity measures affect maintaining manifold neighbourhood structure and b) how supervised manifold learning techniques could contribute to the reduction of classification error. This paper also provides a cross-comparison between supervised and unsupervised manifold learning approaches in terms of structure capturing using Kendall’s Tau coefficients and co-ranking matrices. Four different metrics (including three dissimilarity measures and Euclidean distance) have been considered along with manifold learning methods such as Isomap, ${t}$ -Stochastic Neighbour Embedding ( ${t}$ -SNE), and Laplacian Eigenmaps (LE), in two datasets: Breast Cancer and Swiss-Roll. This paper concludes that although the dissimilarity measures used in the manifold learning techniques can reduce classification error, they do not learn well or preserve the structure of the hidden manifold in the high dimensional space, but instead, they destroy the structure of the data. Based on the findings of this paper, it is advisable to use supervised manifold learning techniques as a pre-processing step in classification. In addition, it is not advisable to apply supervised manifold learning for visualization purposes since the two-dimensional representation using supervised manifold learning does not improve the preservation of data structure.

It is expected that peer to peer energy trading will constitute a significant share of research in upcoming generation power systems due to the rising demand of energy in smart microgrids. However, the on-demand use of energy is considered a big challenge to achieve the optimal cost for households. This paper proposes a blockchain-based predictive energy trading platform to provide real-time support, day-ahead controlling, and generation scheduling of distributed energy resources. The proposed blockchain-based platform consists of two modules; blockchain-based energy trading and smart contract enabled predictive analytics modules. The blockchain module allows peers with real-time energy consumption monitoring, easy energy trading control, reward model, and unchangeable energy trading transaction logs. The smart contract enabled predictive analytics module aims to build a prediction model based on historical energy consumption data to predict short-term energy consumption. This paper uses real energy consumption data acquired from the Jeju province energy department, the Republic of Korea. This study aims to achieve optimal power flow and energy crowdsourcing, supporting energy trading among the consumer and prosumer. Energy trading is based on day-ahead, real-time control, and scheduling of distributed energy resources to meet the smart grid’s load demand. Moreover, we use data mining techniques to perform time-series analysis to extract and analyze underlying patterns from the historical energy consumption data. The time-series analysis supports energy management to devise better future decisions to plan and manage energy resources effectively. To evaluate the proposed predictive model’s performance, we have used several statistical measures, such as mean square error and root mean square error on various machine learning models, namely recurrent neural networks and alike. Moreover, we also evaluate the blockchain platform’s effectiveness through hyperledger calliper in terms of latency, throughput, and resource utilization. Based on the experimental results, the proposed model is effectively used for energy crowdsourcing between the prosumer and consumer to attain service quality.

The epidemic increase in online reviews’ growth made the sentiment classification a fascinating domain in academic and industrial research. The reviews assist several domains, which is complicated to gather annotated training data. Several sentiment classification methodologies are devised for performing the sentiment analysis, but retrieval of information is not accurately performed, less effective, and less convergence speed. In this paper, we propose a sentiment paper proposes a sentiment classification model, namely Spider Monkey Crow Optimization algorithm (SMCA), for training the deep recurrent neural network (DeepRNN). In this method, the telecom review is employed to remove stop words and stemming to eliminate inappropriate data to minimize user’s seeking time. Meanwhile, the feature extraction is performed using SentiWordNet to derive the sentiments from the reviews. The extracted SentiWordNet features and other features, like elongated words, punctuation, hashtag, and numerical values, are employed in the DeepRNN for classifying sentiments. To retrieve the required review, the Fuzzy K-Nearest neighbor (Fuzzy-KNN) is employed to retrieve the review based on a distance measure. With rigorous assessments and experimentation, it is observed that the proposed SMCA-based DeepRNN performs better in terms of accuracy of 97.7%, precision of 95.5%, recall of 94.6%, and F1-score 96.7%, respectively.

This paper presents a complete procedure on prototyping using the FPGA of the STEMlab board and is intended to serve as a guide for developers, students and researchers interested in speeding up their projects and experiments. Due to the reconfigurability of its internal circuitry, being as simple as a code modification (using hardware description language), FPGA technology allows testing of several controller topologies and/or parameters without the need of any physical change at hardware. This feature allows a much faster development cycle of either commercial products or academic experiments. Besides the reconfigurability of the FPGA, the STEMlab board also offers the advantage of several peripheral already available, which includes, among others, high speed analog-to-digital and digital-to-analog converters, Ethernet communication and a dual-core ARM processor capable of running a Linux operating system. In this paper, a didactic method of use of this board is presented, from getting started to a complete academic and industrial application: detection of early damage on an induction motor using frequency response analysis.

Accident causal scenario can describe the process logic of the accident clearly and concretely from the perspective of the control mechanism. Only by improving the quality of the causal scenario can the effective control measures be taken. Combining the technical characteristics of the fully automatic operation (FAO) system, the paper proposes an automated accident causal scenario identification method for FAO system based on the System-Theoretic Process Analysis (STPA) method. Aiming at the problem that there are too many layers in the hierarchical control structure diagram of STPA method, which makes it impossible to effectively trace the cause and the problem that the basic control structure model only contains the control structural information and lacks the cause information, a new basic control structure model is defined to model multiple control processes in time sequence, and then the paper extends it from four aspects: control action, input variables, external disturbance, and synchronous timing to add more system cause information. For the lack of a unified standard description problem for the causal scenario, a four-stage causal scenario description method is defined, this paper has developed the first timing, non-first timing, synchronous timing, and external disturbance causal scenario search rules to ensure the automatic identification of the causal scenarios. Applying the automated safety analysis method to the case study of the operational scenarios of parking in a station of Beijing Yanfang Line, the automated identification of related causal scenarios is successfully completed through the Auto-STPA platform, and corresponding safety requirements are added. The feasibility of the method and the applicability to the analysis of operational scenarios are verified.

Hyperspectral and multispectral information processing systems and technologies have demonstrated its usefulness for the improvement of agricultural productivity and practices by providing useful information to farmers and crop managers on the factors affecting crop status and growth. These technologies are widely used in a range of agriculture applications such as crop management, crop yield forecasting, crop disease detection, and the monitoring of agriculture land usage, water, and soil conditions. Hyperspectral information sensing can acquire several hundred spectral bands that cover the electromagnetic spectrum of an observational scene in a single acquisition. The resulting hyperspectral data cube contains a large volume of spatial and spectral information. The hyperspectral sequence of images or video further increases the data generation velocity and volume which lead to the Big data challenges particularly in agricultural remote sensing applications. This paper is structured to first give a comprehensive review of representative studies to provide insights into significant research efforts in agriculture using Big data, machine learning and deep learning with the focus on frameworks or architectures, information processing and analytics with hyperspectral and multispectral data. The potential for utilizing Big data, machine learning and deep learning for hyperspectral and multispectral data in agriculture is very promising. The paper then further explores the potential of using ensemble machine learning and scalable parallel discriminant analysis which takes into consideration the spatial and spectral components for Big data in agriculture. To the best of our knowledge, no similar review study on agriculture with Big data, machine learning and deep learning for hyperspectral and multispectral information processing has been reported. Furthermore, the potential of ensemble machine learning and scalable parallel discriminant analysis has not been explored in agriculture information processing. Experiments and data analytics have been performed on hyperspectral data from agriculture for validation. The results have shown the good performance of our approach.

Dyslexia is a neurological disorder that is characterized by imprecise comprehension of words and generally poor reading performance. It affects a significant population of school-age children, with more occurrences in males, thus, putting them at risk of poor academic performance and low self-esteem for a lifetime. The long-term hope is to have a dyslexia diagnostic method that is informed by neural-biomarkers. In this regard, large numbers of machine learning methods and, more recently, deep learning methods have been implemented across various types of dataset with the above-chance classification accuracy. However, attainment of clinical acceptability of these state-of-the-art methods is bedeviled by certain challenges including lack of biologically-interpretable biomarkers, privacy of dataset and classifiers, hyper-parameter selection/optimization, and overfitting problem among others. This review paper critically analyzes recent machine learning methods for detecting dyslexia and its biomarkers and discusses challenges that require proper attentions from the users of deep learning methods in order to enable them to attain clinically relevance and acceptable level. The review is conducted within the premise of implementation and experimental outcomes for each of the 22 selected articles using the Preferred Reporting Items for Systematic review and Meta-Analyses (PRISMA) protocol, with a view to outlining some critical challenges for achieving high accuracy and reliability of the state-of-the-art machine learning methods. As an evidence-based protocol for reporting in systematic reviews and meta-analyses, PRISMA helps to ensure clarity and transparency of this paper by showing a four-phase flow diagram of the selection process for articles used in this review. It is therefore, envisaged that higher classification performance of clinical relevance can be achieved using deep learning models for dyslexia and its biomarkers by addressing identified potential challenges.

Several hypovigilance detection systems (HDx) were developed to avoid road-side accidents due to driver fatigue. They have suffered from several limitations. Notably many of these are focused on center-head position to define an area of interest (often referred to as PERCLOS (percentage eye closure)) without considering the face occlusion problem, light illumination, and suffer poor response time. These HDx systems mostly depend on image processing, vision-based, and multisensor-based features. To address these problems, the author utilized vision, sensors, environmental, and vehicular-based features that integrated together by fusion to predict multistage of HDx. Lately, few studies have utilized the combination of multimodal features and deep learning (DL) architectures. Those multimodal-based features (M-HDx) were feasible to predict stages of driver fatigue (multi-stage). However, there is a need to critically measure the performance of these M-HDx by carrying out a comparative analysis to recognize multi-stage of fatigue in terms of hardware-based benchmarks. Moreover, it is important to evaluate the M-HDx systems using different features-set with respect to traditional and advanced machine learning techniques. Therefore, the primary aim of this work is in algorithm and feature modeling, then compare the advantages and differences with other work. In this paper, a different study is conducted compare to state-of-the-art survey articles by statistically measuring the performance. After experiments on M-HDx systems, this paper concludes that there is still a research gap to real-time development of multistage M-HDx systems. In the end, the paper summarizes the directions, challenges, and applications in the development of HDx systems to assist other researchers for further research.

Big Data (BD), Machine Learning (ML) and Internet of Things (IoT) are expected to have a large impact on Smart Farming and involve the whole supply chain, particularly for rice production. The increasing amount and variety of data captured and obtained by these emerging technologies in IoT offer the rice smart farming strategy new abilities to predict changes and identify opportunities. The quality of data collected from sensors greatly influences the performance of the modelling processes using ML algorithms. These three elements (e.g., BD, ML and IoT) have been used tremendously to improve all areas of rice production processes in agriculture, which transform traditional rice farming practices into a new era of rice smart farming or rice precision agriculture. In this paper, we perform a survey of the latest research on intelligent data processing technology applied in agriculture, particularly in rice production. We describe the data captured and elaborate role of machine learning algorithms in paddy rice smart agriculture, by analyzing the applications of machine learning in various scenarios, smart irrigation for paddy rice, predicting paddy rice yield estimation, monitoring paddy rice growth, monitoring paddy rice disease, assessing quality of paddy rice and paddy rice sample classification. This paper also presents a framework that maps the activities defined in rice smart farming, data used in data modelling and machine learning algorithms used for each activity defined in the production and post-production phases of paddy rice. Based on the proposed mapping framework, our conclusion is that an efficient and effective integration of all these three technologies is very crucial that transform traditional rice cultivation practices into a new perspective of intelligence in rice precision agriculture. Finally, this paper also summarizes all the challenges and technological trends towards the exploitation of multiple sources in the era of big data in agriculture.

Diabetes is one of the most rapidly growing chronic diseases, which has affected millions of people around the globe. Its diagnosis, prediction, proper cure, and management are crucial. Data mining based forecasting techniques for data analysis of diabetes can help in the early detection and prediction of the disease and the related critical events such as hypo/hyperglycemia. Numerous techniques have been developed in this domain for diabetes detection, prediction, and classification. In this paper, we present a comprehensive review of the state-of-the-art in the area of diabetes diagnosis and prediction using data mining. The aim of this paper is twofold; firstly, we explore and investigate the data mining based diagnosis and prediction solutions in the field of glycemic control for diabetes. Secondly, in the light of this investigation, we provide a comprehensive classification and comparison of the techniques that have been frequently used for diagnosis and prediction of diabetes based on important key metrics. Moreover, we highlight the challenges and future research directions in this area that can be considered in order to develop optimized solutions for diabetes detection and prediction.

Recently, development in intelligent transportation systems (ITS) requires the input of various kinds of data in real-time and from multiple sources, which imposes additional research and application challenges. Ongoing studies on Data Fusion (DF) have produced significant improvement in ITS and manifested an enormous impact on its growth. This paper reviews the implementation of DF methods in ITS to facilitate traffic flow analysis (TFA) and solutions that entail the prediction of various traffic variables such as driving behavior, travel time, speed, density, incident, and traffic flow. It attempts to identify and discuss real-time and multi-sensor data sources that are used for various traffic domains, including road/highway management, traffic states estimation, and traffic controller optimization. Moreover, it attempts to associate abstractions of data level fusion, feature level fusion, and decision level fusion on DF methods to better understand the role of DF in TFA and ITS. Consequently, the main objective of this paper is to review DF methods used for real-time and multi-sensor (heterogeneous) TFA studies. The review outcomes are (i) a guideline of constructing DF methods which involve preprocessing, filtering, decision, and evaluation as core steps, (ii) a description of the recent DF algorithms or methods that adopt real-time and multi-sensor sources data and the impact of these data sources on the improvement of TFA, (iii) an examination of the testing and evaluation methodologies and the popular datasets and (iv) an identification of several research gaps, some current challenges, and new research trends.

Considering smartphone-based indoor localization and tracking, combination of Wi-Fi fingerprinting and pedestrian dead reckoning (PDR) becomes prevalent due to wide deployment of indoor Wi-Fi access points and easily access of inertial measurement units (IMUs) on smartphones. Since Wi-Fi fingerprinting depends on the similarities between online and offline received signal strengths, it suffers from the fluctuation of radio signal measurements. Meanwhile, the PDR relies on the IMUs, which undergo accumulated errors in long walking distance. In this paper, we aim to improve the indoor tracking accuracy, while filling up the gap between two popular Android and iOS platforms. In particular, we propose a hybrid tracking algorithm that integrates the PDR with Wi-Fi/iBeacon signal features. There are three key points in our paper. First, we process Wi-Fi/iBeacon signals to build conversion functions to convert signals to related proximity distances. Besides, in order to support mobile tracking, we introduce a placement methodology for iBeacon installation for a specific region of interest. Second, a mobile smartphone uses an improved PDR to localize itself, while incorporating Wi-Fi/iBeacon data for estimating a starting point and correcting its location along the walking path. Finally, we build an iOS app to implement the proposed scheme and display visual tracking results. Experiment results show that our proposed scheme is more robust and accurate compared to the conventional schemes.

Social engineering attacks have posed a serious security threat to cyberspace. However, there is much we have yet to know regarding what and how lead to the success of social engineering attacks. This paper proposes a conceptual model which provides an integrative and structural perspective to describe how social engineering attacks work. Three core entities (effect mechanism, human vulnerability and attack method) are identified to help the understanding of how social engineering attacks take effect. Then, beyond the familiar scope, we analyze and discuss the effect mechanisms involving 6 aspects (persuasion, social influence, cognition & attitude & behavior, trust and deception, language & thought & decision, emotion and decision-making) and the human vulnerabilities involving 6 aspects (cognition and knowledge, behavior and habit, emotions and feelings, human nature, personality traits, individual characters), respectively. Finally, 16 social engineering attack scenarios (including 13 attack methods) are presented to illustrate how these mechanisms, vulnerabilities and attack methods are used to explain the success of social engineering attacks. Besides, this paper offers lots of materials for security awareness training and future empirical research, and the model is also helpful to develop a domain ontology of social engineering in cybersecurity.

Near Field Communication (NFC) is a prominent short-range, contact-less communication technology, which is rapidly getting popular in modern smart devices. For communication between two active devices via NFC, applications generally choose the peer-to-peer operation mode. In this paper, we exploit the possibility of using the NFC read/write mode, designed primarily for unidirectional data transfer from an active NFC reader to a passive NFC tag, for bi-directional half-duplex communication between two active NFC devices. The advantages of using the NFC read/write mode include low protocol overhead and permitting different data formats. However, the challenges are avoiding the reader collision problem, maintaining a secure session, and completing all transactions in an acceptable time frame. In this paper, we address the above challenges and propose a methodology for efficient communication between active NFC devices using NFC read/write mode. To evaluate the scheme, we design a secure Multi-Factor Authentication (MFA) system that requires bi-directional communication for mutually authenticating two NFC devices. The proposed methodology is experimentally verified using NFC-enabled Android smartphones and a Kerberos server as the third-party authenticator.

In the era of paper-based contract, a lot of time, human labor and expenses are required to handle the process of contract drafting, contract signing, contract execution, and payment settlement. The emerging of electronic contract enhances the tedious signing process of paper-based contract and improves the efficiency of contract management. However, due to the centralized system architecture and the database-based storage schema, the stored contract data is at high risk of information leaking, data tampering and hacker attacks. In this study, we introduce Blockchain technology to the contract management, and develop a process-oriented contract management system (BEcontractor) for a Hangzhou-located power grid enterprise X, aiming to solve a series of security issues existing in the traditional electronic contract system. By deploying BEcontractor, procurement activities could be resumed online among X and its nation-widely commodity suppliers during COVID-19 epidemic. Up to September 2020, 6336 electronic contracts have been signed, with an accumulated amount of $\yen ~6.5$ billion. It is showed that the cost for accomplishing the contract signing process was significantly reduced, and the payment period was shortened from three months to around one month.

The standardization and digitalization of nine constitutions of traditional Chinese medicine (TCM) have promoted the development of TCM automation. The keys to constitution identification are tongue diagnosis and consultation diagnosis. In this paper, a tongue detection method based on the combination of the histogram of oriented gradients (HOG) and the support vector machine (SVM) is proposed. To separate the tongue body and tongue coating, a k-means segmentation method based on the Lab color space is proposed. Based on the clustering analysis of the difference between the color components of the tongue body and tongue coating in the Lab color space, the separation is realized. Thus, the relationship between the tongue image and constitution can be analyzed. The method for consultation diagnosis is divided into a questionnaire scale and a question answering system. The questionnaire includes 29 quantified items with corresponding weights and answer scores, so the final score of each type of constitution is calculated. The final constitution type is determined on the basis of the scores of both diagnoses. In addition, the key of question answering system is text similarity calculation. First, a sentence similarity calculation method combining the n-gram language model and word2vec is proposed. Then, a multifeature fusion sentence similarity calculation method combining the Word Mover’s Distance (WMD) and editing distance is proposed. Finally, the experimental results show the effectiveness of the proposed method, and a constitution identification application is developed based on the content of this paper.

Self-adaptive approaches are a promising to address the dynamic and uncertain nature of the environments where today’s complex systems operate. In particular, systems operating in military environments, during crises or under unexpected conditions need to address critical concerns related to resource sparsity and the unstable and uncertain nature of exchanged information. Despite a plethora of self-adaptive and autonomic approaches proposed in the last decade, very few have been designed for or evaluated in contested environments , where adversarial action in the communications domain leads to stale or incomplete information, or in resource-constrained environments, where resources are either limited or required by a large number of components. These conditions are where self-adaptability to aid human operators is needed the most. To better understand self-adaptation in contested and resource-constrained environments, we conducted a systematic literature review of publications over the last decade. We conduct our review through the lens of a military environment, where contention, both physical and from a resource, be it computational or communication based is at its peak. We followed the systematic literature review methodology and analysed 238 primary studies. We identified that the most frequent application domains are those where failures are frequent and costly, namely, cloud computing, web services and applications, and servers. Despite this, less than 3% of the papers considered constrained resources and stale or incomplete information and a significant focus was on developing centralised solutions instead of distributed ones throughout all papers. Very few papers (4.6%) considered environments where the information about the system components was not readily available. No papers evaluated the systems running in contested and resource-constrained environments. We present an analysis of the self-adaptive systems that consider incomplete or stale information and constrained resources, discuss their limitations and identify future areas of research. Critical research gaps include the lack of evaluation of self-adaptive approaches, including the lack of standards or formalisms to allow for the comparison of various approaches. In addition, there is a need to consider more self-* properties and non-functional requirements in order to make sure the designed system is resilient. This paper presents our review findings in detail, examines how self-adaptation happens in contested and resource-constrained environments, and discusses the identified research gaps.

Watermarking is an important technique for protecting sensitive e-multimedia data and intellectual property. Watermarking techniques are used for many applications such as ownership protection, which is a popular area of research as compared to others such as authentication and local temper localization. There are many image watermarking schemes that have been recently published based on the frequency domain as it can fulfill watermarking requirements such as high robustness and imperceptibility. Singular-value decomposition (SVD) is one of them and is used in many frequency transform-based image watermarking schemes due to its stability and mathematical simplicity. However, there are many schemes that lack robustness against malicious cyberattacks, whereby the watermarks are easy to detect and destroy. Consequently, the proposed watermarking schemes became more complicated and cannot resist various geometric and non-geometric attacks. Thus, there are many existing hybrid SVD-based image watermarking schemes found be insecure. As there is also a lack of in-depth reviews in this domain, the focus of this paper is the analysis of the state-of-the-art in hybrid SVD-based image watermarking. We perform efficiency comparisons to highlight various security problems, open issues, and research gaps. Based on our findings, we additionally provide some recommendations for the development of more robust schemes in the future. This paper provides essential information for researchers and practitioners alike to advance the field of image watermarking.

The ever-increasing number of mobile platforms constitutes a challenge for application developers, who must develop efficient mobile applications for multiple platforms. Recently, a specific interest is being taken in the Model Based User Interface Development (MBUID) by Software Engineering Community. In such paradigm, an application’s user interface is obtained by defining models and transformations of those models. This paper aim at adopting MBUID paradigm to address the problem of mobile application development. As such, we propose a new approach and its support system for the automatic generation of mobile user interfaces. The approach and the system are based on a set of standards and relevant technologies such as EMF, GMF, ATL, and Xpand. A case study is presented, in the paper, with the aim of verifying the usefulness of this approach.

This paper presents an overview of device identification techniques and the Manufacturer Usage Description (MUD) standard used for the Internet of things to reduce the IoT attack surface. The ongoing diversity and the sheer increase in the number of connected IoT devices have crumpled security efforts. There is a need to reconsider and redesign the underlying concept of developing security systems to resolve IoT security challenges. In this backdrop, device profiling and identification have emerged as an exciting technique that helps to reduce IoT device attack surface. One of the known approaches for device identification is to fingerprint a device. There are many ways to fingerprint the device, mostly using device network flows or device local attributes. The device identification ensures the authenticity of the device attached to the network, like user authentication. Since IoT devices mostly work using machine-to-machine (M2M) communication, this requires identifying each device properly. But there is no unified approach for device identification for the ever-growing world of IoT devices and applications. One of the major steps forward in this direction is the development of the Manufacturer Usage Description (MUD) standard that defines the role of a device within the network. It limits the device to execute the primary task only, which will help to reduce the attack surface. Since the inception of MUD, many security frameworks use this standard for IoT security. However, there is a need to scrutinize the security frameworks based on the MUD, to find out the claimed effectiveness of the standard in IoT security. This paper initially identifies and classifies the potential vulnerabilities in IoT devices. Then, the study provides an overview of the research that focuses on device identification techniques and analyzes their role in IoT security. Finally, the research presents an overview of MUD technology, its implementation scenarios, the limitation of the latest MUD standard, and its applications in the industry. The prime aim of this work is to examine the MUD benefits in IoT security along with the weaknesses and challenges while implementing this standard along with future directions.

Context: User stories have been widely accepted as artifacts to capture the user requirements in agile software development. They are short pieces of texts in a semi-structured format that express requirements. Natural language processing (NLP) techniques offer a potential advantage in user story applications. Objective: Conduct a systematic literature review to capture the current state-of-the-art of NLP research on user stories. Method: The search strategy is used to obtain relevant papers from SCOPUS, ScienceDirect, IEEE Xplore, ACM Digital Library, SpringerLink, and Google Scholar. Inclusion and exclusion criteria are applied to filter the search results. We also use the forward and backward snowballing techniques to obtain more comprehensive results. Results: The search results identified 718 papers published between January 2009 to December 2020. After applying the inclusion/exclusion criteria and the snowballing technique, we identified 38 primary studies that discuss NLP techniques in user stories. Most studies used NLP techniques to extract aspects of who, what, and why from user stories. The purpose of NLP studies in user stories is broad, ranging from discovering defects, generating software artifacts, identifying the key abstraction of user stories, and tracing links between model and user stories. Conclusion: NLP can help system analysts manage user stories. Implementing NLP in user stories has many opportunities and challenges. Considering the exploration of NLP techniques and rigorous evaluation methods is required to obtain quality research. As with NLP research in general, the ability to understand a sentence’s context continues to be a challenge.

Semantic segmentation is a task that covers most of the perception needs of intelligent vehicles in an unified way. Recent studies witnessed that attention mechanisms achieve impressive performance in computer vision task. Current attention mechanisms based segmentation methods differ with each other in position and form of the attention mechanism, and perform differently in practice. This paper firstly introduces the effectiveness of multi-scale context features and attention mechanisms in segmentation tasks. We find that multi-scale and channel attention can play a vital role in constructing effective context features. Based on this analysis, this paper proposes an efficient attention pyramid network (EAPNet) for semantic segmentation. Specifically, to efficient handle the problem of segmenting objects at multiple scales, we design efficient channel attention pyramid (ECAP) which employ atrous convolution with channel attention in cascade or in parallel to capture multi-scale context by using multiple atrous rates. Furthermore, we propose a residual attention fusion block (RAFB), whose purpose is to simultaneously focus on meaningful low-level feature maps and spatial location information. At the same time, we will explore different channel attention modules and spatial attention modules, and describe their impact on network performance. We empirically evaluate our EAPNet on two semantic segmentation datasets, including PASCAL VOC 2012 and Cityscapes datasets. Experimental results show that without MS COCO pre-training and any post-processing, EAPNet achieved 81.7% mIoU on the PASCAL VOC 2012 validation set. With deeplabv3+ as the benchmark, EAPNet improve the model performance of more than 1.50% mIoU.

Recognizing the current weather conditions from a single image is of great theoretical significance. It also has potential practical value for daily life and traffic scheduling. To achieve that, typical weather recognition methods focus on learning a general weather description, e.g., sunny, cloudy, foggy, rainy and snowy etc, for the overall weather condition. However, it is far away from being sufficient for many tasks especially traffic management and control. To solve this key problem, this paper proposes a Global-Similarity Local-Salience Network (abbreviated as GSLSNet) for traffic weather recognition. Specifically, a simple but effective Global-Similarity Module (GSM) is proposed to recognize the overall weather condition and a Local-Salience Module (LSM) is presented to restrict the network to focus on road weather details. Besides, this paper also provides a new traffic weather dataset, named TWData, which is the first fine categorized dataset especially for highway weather recognition. Experimental results compared with state-of-the-art methods on both public datasets and TWData demonstrate the superiority of the proposed GSLSNet.

A distributed denial of service (DDoS) attack represents a major threat to service providers. More specifically, a DDoS attack aims to disrupt and deny services to legitimate users by overwhelming the target with a massive number of malicious requests. A cyberattack of this kind is likely to result in tremendous economic losses for businesses and service providers due to increasing both operating and financial costs. In recent years, machine learning (ML) techniques have been widely used to prevent DDoS attacks. Indeed, many defense systems have been transformed into smart and intelligent systems through the use of ML techniques, which allow them to defeat DDoS attacks. This paper analyzes recent studies concerning DDoS detection methods that have adapted single and hybrid ML approaches in modern networking environments. Additionally, the paper discusses different DDoS defense systems based on ML techniques that make use of a virtualized environment, including cloud computing, software-defined network, and network functions virtualization environments. As the development of the Internet of Things (IoT) has been the subject of significant research attention in recent years, the paper also discusses ML approaches as security solutions against DDoS attacks in IoT environments. Furthermore, the paper recommends a number of directions for future research. This paper is intended to assist the research community with the design and development of effective defense systems capable of overcoming different types of DDoS attacks.

A detection model of Internet of Things encrypted traffic based on edge intelligence is proposed in the paper, which can reduce the communication times of distributed Internet of Things gateways in the process of edge intelligence as well as the encrypted traffic detection model establishment time, in order to solve the problems that it is difficult to carry out efficient classification and accurate identification of the encrypted traffic of Internet of Things. In this paper, four new classification and identification methods for encrypted traffic are put forward, namely time-sequence behavior analysis, dynamic behavior analysis, key behavior analysis and two-round filtering analysis. The experimental results show that when the sample size is 1600, the encrypted traffic detection model establishment time is less than 100 seconds, and the accuracy of all the four new traffic classification methods is more than 92% and the recall rates of them are more than 83%.

Recent advances in the cyber-physical smart grid (CPSG) have enabled a broad range of new devices based on the information and communication technology (ICT). However, these ICT-enabled devices are susceptible to a growing threat of cyber-physical attacks. This paper performs a thorough review of the state-of-the-art cyber-physical security of the smart grid. By focusing on the physical layer of the CPSG, this paper provides an abstracted and unified state-space model, in which cyber-physical attack and defense models can be effectively generalized. The existing cyber-physical attacks are categorized in terms of their target components. We then discuss several operational and informational defense approaches that present the current state-of-the-art in the field, including moving target defense, watermarking, and data-driven approaches. Finally, we discuss challenges and future opportunities associated with the smart grid cyber-physical security.

Graph embedding models are widely used in knowledge graph completion (KGC) task. However, most models are based on the assumption that knowledge is completely certain, and this is inconsistent with real-world situations. Although there are multiple studies on uncertain knowledge embedding tasks, they often use knowledge confidence to learn embedding and cannot make full use the structural and uncertain information of knowledge. This paper presents a new embedding model named Structural and Uncertain Knowledge Embedding (SUKE), which comprises two components: an evaluator and a confidence generator. For unknown triples, the evaluator learns the structural and uncertain information to evaluate its rationality and obtain a candidate set. The confidence generator then determines the confidence of the candidate set to achieve KGC. To verify the effectiveness of the proposed model, confidence prediction, triple evaluation, and fact classification tasks are performed on three data sets. Experimental results show that SUKE performs better than mainstream embedding methods. The model proposed in this paper can help advance the research on the embedding of uncertain knowledge graphs.

Wireless communication systems play a very crucial role in modern society for entertainment, business, commercial, health and safety applications. These systems keep evolving from one generation to next generation and currently we are seeing deployment of fifth generation (5G) wireless systems around the world. Academics and industries are already discussing beyond 5G wireless systems which will be sixth generation (6G) of the evolution. One of the main and key components of 6G systems will be the use of Artificial Intelligence (AI) and Machine Learning (ML) for such wireless networks. Every component and building block of a wireless system that we currently are familiar with from our knowledge of wireless technologies up to 5G, such as physical, network and application layers, will involve one or another AI/ML techniques. This overview paper, presents an up-to-date review of future wireless system concepts such as 6G and role of ML techniques in these future wireless systems. In particular, we present a conceptual model for 6G and show the use and role of ML techniques in each layer of the model. We review some classical and contemporary ML techniques such as supervised and un-supervised learning, Reinforcement Learning (RL), Deep Learning (DL) and Federated Learning (FL) in the context of wireless communication systems. We conclude the paper with some future applications and research challenges in the area of ML and AI for 6G networks.

Sentiment Analysis is an important research direction of natural language processing, and it is widely used in politics, news and other fields. Word embeddings play a significant role in sentiment analysis. The existing sentiment embeddings methods directly embed the sentiment lexicons into traditional word representation. This sentiment representation methods can only differentiate the sentiment information of different words, not the same word in different contexts, so it cannot provide accurate sentiment information for word in different contexts. This paper proposes sentiment concept to solve the problem. First, we found the optimal sentiment concept of words in Microsoft Concept Graph according to the context of words. Then we obtained the sentiment information of words under optimal sentiment concept from the multi-semantics sentiment intensity lexicon which we constructed in this paper to achieve accurate embedding of sentiment information and provide more accurate semantics and sentiment representation for words. Finally, we combined two refined word embeddings methods to achieve a more comprehensive word representation. Compared with traditional and sentiment embeddings methods on six representative datasets, the validity of the word embeddings method based on sentiment concept proposed in this paper is verified.

Nowadays, rehabilitation training for stroke survivors is mainly completed under the guidance of the physician. There are various treatment ways, however, most of them are affected by various factors such as experience of physician and training intensity. The treatment effect cannot be fed back in time, and objective evaluation data is lacking. In addition, the treatment method is complicated, costly, and highly dependent on physicians. Moreover, stroke survivors’ compliance is poor, which leads to various limitations. This paper combines the Internet-of-Things, machine learning, and intelligence system technologies to design a smartphone-based intelligence system to help stroke survivors to improve upper limb rehabilitation. With the built-in multi-modal sensors of the smart phone, training action data of users can be obtained, and then transfer to the server through the Internet. This research presents a DTW-KNN joint algorithm to recognize accuracy of rehabilitation actions and classify to multiple training completion levels. The experimental results show that the DTW-KNN algorithm can evaluate the rehabilitation actions, the accuracy rates of the classification in excellent, good, and normal are 85.7%, 66.7%, and 80% respectively. The intelligence system presented in this paper can help stroke survivors to proceed rehabilitation training independently and remotely, which reduces medical costs and psychological burden.

Real-time Ethernet has been applied to train control and management system (TCMS) of 250km/h Fuxing Electric Multiple Units (EMUs) and some urban rail vehicles. The openness of the Ethernet communication protocol poses a risk of intrusion attacks on the train communication network. It is, therefore, necessary that a safety protection technology is introduced to the train communication network based on real-time Ethernet. In this paper, a train communication network intrusion detection system based on anomaly detection and attack classification is proposed. Firstly, the paper built an anomaly detection model based on support vector machines (SVM). The particle swarm optimization-support vector machines (PSO-SVM), and genetic algorithm-support vector machines (GA-SVM) optimization algorithms are used to optimize the kernel function parameters of SVM. Secondly, the paper built two attack classification models based on random forest. They are iterative dichotomiser3 (ID3) and classification and regression tree (CART). And then, the built intrusion detection and attack classification model is tested by using the public data set knowledge discovery and data mining-99(KDD-99) and the data set of the simulation train real-time Ethernet test bench. PSO-SVM improves the intrusion detection accuracy from 90.3% to 95.75%, GA-SVM improves the detection accuracy from 90.3% to 95.85%. The training time of the PSO-SVM algorithm was higher than that of the GA-SVM algorithm, and much higher than that of the SVM, without optimization. Both ID3 and CART models are verified valid in the attack classification, while the ID3 algorithm obtained 100% accuracy on the training set, and only 32.89% accuracy on the test set, ID3 has a poor classification accuracy of the data outside of the training set. Also, the classification time is very long for ID3 compared with CART. So the comprehensive experimental results show that the intrusion detection system of train real-time Ethernet can use the GA-SVM model for detection of abnormal data. After passing the normal data, the CART model can be used to distinguish between the types of attacks to better complete subsequent responses and operations. Compared with the anomaly detection model based on SVM, the proposed model improves intrusion detection accuracy. And the proposed attack classification algorithm based on CART can improve the computing speed while ensuring the precision of classification.

Physical fitness monitoring is an important tool for disease prevention and early diagnosis and treatment. Efficient physical fitness monitoring can effectively reduce the risks of disease and relieve the medical burden. This paper analyzes the shortcomings of traditional clustering routing protocols, and proposes a new Internet of Things (IoT) clustering routing algorithm using Particle Swarm Optimization (PSO). The calculation method of the optimal number of clusters is granted, and the fitness function is redesigned. This function fully considers the remaining energy of sensor nodes, distance between clusters and node spacing, etc., and specifically introduces the process of applying PSO to select the optimal cluster head combination and the process of PSO cluster routing algorithm. Based on the traditional particle swarm algorithm, this paper proposes a monitoring algorithm based on two-way chaotic search by introducing chaotic search strategy and reverse learning strategy. This algorithm largely avoids the situation of particles falling into local optima. The experimental results show that the method gets closer to the optimal solution than the traditional particle swarm algorithm. A scheme for constructing Hbase secondary index using hidden column family is proposed, and Hbase table join optimization algorithm is proposed based on bloom filter and Hash join algorithm. On the overall load of Hbase, a pre-partitioned Hash algorithm and a load prediction algorithm based on exponential smoothing are proposed to improve the performance of Hbase to meet business needs. Experimental results show that the Hbase particle swarm optimization algorithm proposed in the article can effectively improve the functioning of Hbase from the perspective of data writing and query.

6G is anticipated to become more human-centered than 5G and should not only explore more spectrum at high-frequency bands but, more importantly, converge driving technological trends such as blockchain technologies and connected robotics. This paper focuses on the emerging field of robonomics, which studies the sociotechnical impact of blockchain technologies on social human-robot interaction and behavioral economics for the social integration of robots into human society. Advanced blockchain technologies such as oracles enable the on-chaining of blockchain-external off-chain information stemming from human users. In doing so, they leverage on human intelligence rather than machine learning only. In this paper, we investigate the widely studied trust game of behavioral economics in a blockchain context, paying close attention to the importance of developing efficient cooperation and coordination technologies. After identifying open research challenges of blockchain-enabled implementations of the trust game, we first develop a smart contract that replaces the experimenter in the middle between trustor and trustee and demonstrate experimentally that a social efficiency of up to 100% can be achieved by using deposits to enhance both trust and trustworthiness. We then present an on-chaining oracle architecture for a networked $N$ -player trust game that involves a third type of human agents called observers, who track the players’ investment and reciprocity. The presence of third-party reward and penalty decisions helps raise the average normalized reciprocity above 80%, even without requiring any deposit. Finally, we experimentally demonstrate that mixed logical-affective persuasive strategies for social robots improve the trustees’ trustworthiness and reciprocity significantly.

The popularity and usage of Cloud computing is increasing rapidly. Several companies are investing in this field either for their own use or to provide it as a service for others. One of the results of Cloud development is the emergence of various security problems for both industry and consumer. One of the ways to secure Cloud is by using Machine Learning (ML). ML techniques have been used in various ways to prevent or detect attacks and security gaps on the Cloud. In this paper, we provide a Systematic Literature Review (SLR) of ML and Cloud security methodologies and techniques. We analyzed 63 relevant studies and the results of the SLR are categorized into three main research areas: (i) the different types of Cloud security threats, (ii) ML techniques used, and (iii) the performance outcomes. We have defined 11 Cloud security areas. Moreover, distributed denial-of-service (DDoS) and data privacy are the most common Cloud security areas, with a 16% level of use and 14%respectively. On the other hand, we found 30 ML techniques used, some used hybrid and others as standalone. The most popular ML used is SVM in both hybrid and standalone models. Furthermore, 60% of the papers compared their models with other models to prove the efficiency of their proposed model. Moreover, 13 different evaluation metrics were enumerated. The most applied metric is true positive rate and least used is training time. Lastly, from 20 datasets found, KDD and KDD CUP'99 are the most used among relevant studies.