- Wenbing Zhao;Shunkun Yang;Xiong Luo;
In this paper, we present the design and implementation of an avatar-based interactive system that facilitates rehabilitation for people who have received total knee replacement surgeries. The system empowers patients to carry out exercises prescribed by a clinician at the home settings more effectively. Our system helps improve accountability for both patients and clinicians. The primary sensing modality is the Microsoft Kinect sensor, which is a depth camera that comes with a Software Development Kit(SDK). The SDK provides access to 3-dimensional skeleton joint positions to software developers, which significantly reduces the challenges in developing accurate motion tracking systems, especially for use at home. However, the Kinect sensor is not wellequipped to track foot orientation and its subtle movements. To overcome this issue, we augment the system with a commercial off-the-shelf Inertial Measurement Unit(IMU). The two sensing modalities are integrated where the Kinect serves as the primary sensing modality and the IMU is used for exercises where Kinect fails to produce accurate measurement. In this pilot study, we experiment with four rehabilitation exercises, namely, quad set,side-lying hip abduction, straight raise leg, and ankle pump. The Kinect is used to assess the first three exercises,and the IMU is used to assess the ankle pump exercise.
2021年06期 v.26 791-799页 [查看摘要][在线阅读][下载 8873K] [下载次数：42 ] |[网刊下载次数：0 ] |[引用频次：2 ] |[阅读次数：0 ] - Keji Han;Yun Li;Bin Xia;
Deep Neural Networks(DNNs) are demonstrated to be vulnerable to adversarial examples, which are elaborately crafted to fool learning models. Since the accuracy and robustness of DNNs are at odds for the adversarial training method, the adversarial example detection algorithms check whether the specific example is adversarial, which is promising to solve the issue of the adversarial example. However, among the existing methods,model-aware detection methods do not generalize well, while the detection accuracies of the generative-based methods are lower compared to the model-aware methods. In this paper, we propose a cascade model-aware generative adversarial example detection method, namely CMAG. CMAG consists of two first-order reconstructors and a second-order reconstructor, which can illustrate what the model sees to the human by reconstructing the logit and feature maps of the last convolution layer. Experimental results demonstrate that our method is effective and is more interpretable compared to some state-of-the-art methods.
2021年06期 v.26 800-812页 [查看摘要][在线阅读][下载 6001K] [下载次数：29 ] |[网刊下载次数：0 ] |[引用频次：2 ] |[阅读次数：0 ] - Jiangru Yuan;Xingjie Zeng;Haiyun Wu;Weishan Zhang;Jiehan Zhou;Bingyang Chen;
Interwell connectivity, an important element in reservoir characterization, especially for water flooding,is used to make decisions for better oil production. The existing methods in literature directly use related data of wells to infer interwell connectivity, but they ignore the influence between different wells. The connection of one well to more than two wells(as is often true in the oil field well pattern) will impact the accuracy of the connectivity analysis. To address this challenge, this paper proposes the Particle Swarm Optimization-based CatBoost for Interwell Connectivity(PSOC4IC) based on relative features to analyze interwell connectivity with the combination of joint mutual information maximization-based denoising sparse autoencoder for inter-feature construction and extraction and PSO-based CatBoost(PSO-CatBoost) for connectivity prediction with high-dimensional noise data.The experimental results show that the PSOC4IC improves analysis accuracy.
2021年06期 v.26 813-820页 [查看摘要][在线阅读][下载 5645K] [下载次数：50 ] |[网刊下载次数：0 ] |[引用频次：1 ] |[阅读次数：0 ] - Weiping Wang;Zhaorong Wang;Zhanfan Zhou;Haixia Deng;Weiliang Zhao;Chunyang Wang;Yongzhen Guo;
Industrial Control Systems(ICSs) are the lifeline of a country. Therefore, the anomaly detection of ICS traffic is an important endeavor. This paper proposes a model based on a deep residual Convolution Neural Network(CNN) to prevent gradient explosion or gradient disappearance and guarantee accuracy. The developed methodology addresses two limitations: most traditional machine learning methods can only detect known network attacks and deep learning algorithms require a long time to train. The utilization of transfer learning under the modification of the existing residual CNN structure guarantees the detection of unknown attacks. One-dimensional ICS flow data are converted into two-dimensional grayscale images to take full advantage of the features of CNN. Results show that the proposed method achieves a high score and solves the time problem associated with deep learning model training.The model can give reliable predictions for unknown or differently distributed abnormal data through short-term training. Thus, the proposed model ensures the safety of ICSs and verifies the feasibility of transfer learning for ICS anomaly detection.
2021年06期 v.26 821-832页 [查看摘要][在线阅读][下载 4686K] [下载次数：63 ] |[网刊下载次数：0 ] |[引用频次：39 ] |[阅读次数：0 ] - Quanwei Huang;Yuezhi Zhou;Linmi Tao;Weikang Yu;Yaoxue Zhang;Li Huo;Zuoxiang He;
The accurate segmentation of medical images is crucial to medical care and research; however, many efficient supervised image segmentation methods require sufficient pixel level labels. Such requirement is difficult to meet in practice and even impossible in some cases, e.g., rare Pathoma images. Inspired by traditional unsupervised methods, we propose a novel Chan–Vese model based on the Markov chain for unsupervised medical image segmentation. It combines local information brought by superpixels with the global difference between the target tissue and the background. Based on the Chan–Vese model, we utilize weight maps generated by the Markov chain to model and solve the segmentation problem iteratively using the min-cut algorithm at the superpixel level.Our method exploits abundant boundary and local region information in segmentation and thus can handle images with intensity inhomogeneity and object sparsity. In our method, users gain the power of fine-tuning parameters to achieve satisfactory results for each segmentation. By contrast, the result from deep learning based methods is rigid.The performance of our method is assessed by using four Computerized Tomography(CT) datasets. Experimental results show that the proposed method outperforms traditional unsupervised segmentation techniques.
2021年06期 v.26 833-844页 [查看摘要][在线阅读][下载 752K] [下载次数：67 ] |[网刊下载次数：0 ] |[引用频次：6 ] |[阅读次数：0 ] - Shiyuan Xu;Xue Chen;Yunhua He;
Purchases of electric vehicles have been increasing in recent years. These vehicles differ from traditional fossil-fuel-based vehicles especially in the time consumed to keep them running. Electric-Vehicle-charging Service Providers(EVSPs) must arrange reasonable charging times for users in advance. Most EVSP services are based on third-party platforms, but reliance on third-party platforms creates a lack of security, leaving users vulnerable to attacks and user-privacy leakages. In this paper, we propose an anonymous blockchain-based system for charging-connected electric vehicles that eliminates third-party platforms through blockchain technology and the establishment of a multi-party security system between electric vehicles and EVSPs. In our proposed system, digital certificates are obtained by completing distributed Public Key Infrastructure(distributed-PKI) identity registration,with the user registration kept separate from the verification process, which eliminates dependence on the EVSP for information security. In the verification process, we adopt smart contracts to solve problems associated with centralized verification and opaque services. Furthermore, we utilize zero-knowledge proof and ring-signature superposition to realize completely anonymous verification, which ensures undeniability and unforgeability with no detriment to anonymity. The evaluation results show that the user anonymity, information authenticity, and system security of our system fulfill the necessary requirements.
2021年06期 v.26 845-856页 [查看摘要][在线阅读][下载 1499K] [下载次数：43 ] |[网刊下载次数：0 ] |[引用频次：10 ] |[阅读次数：0 ] - Kaihang Yu;Zhonggui Ma;Runyu Ni;Tao Zhang;
Wireless edge caching has been proposed to reduce data traffic congestion in backhaul links, and it is being envisioned as one of the key components of next-generation wireless networks. This paper focuses on the influences of different caching strategies in Device-to-Device(D2D) networks. We model the D2D User Equipments(DUEs) as the Gauss determinantal point process considering the repulsion between DUEs, as well as the caching replacement process as a many-to-many matching game. By analyzing existing caching placement strategies, a new caching strategy is proposed, which represents the preference list of DUEs as the ratio of content popularity to cached probability. There are two distinct features in the proposed caching strategy.(1) It can cache other contents besides high popularity contents.(2) It can improve the cache hit ratio and reduce the latency compared with three caching placement strategies: Least Recently Used(LRU), Equal Probability Random Cache(EPRC), and the Most Popular Content Cache(MPC). Meanwhile, we analyze the effect of caching on the system performance in terms of different content popularity factors and cache capacity. Simulation results show that our proposed caching strategy is superior to the three other comparison strategies and can significantly improve the cache hit ratio and reduce the latency.
2021年06期 v.26 857-868页 [查看摘要][在线阅读][下载 6660K] [下载次数：69 ] |[网刊下载次数：0 ] |[引用频次：23 ] |[阅读次数：0 ] - Wei Zhang;Zhuo Li;Xin Chen;
With the rapid development of mobile devices, the use of Mobile Crowd Sensing(MCS) mode has become popular to complete more intelligent and complex sensing tasks. However, large-scale data collection may reduce the quality of sensed data. Thus, quality control is a key problem in MCS. With the emergence of the federated learning framework, the number of complex intelligent calculations that can be completed on mobile devices has increased.In this study, we formulate a quality-aware user recruitment problem as an optimization problem. We predict the quality of sensed data from different users by analyzing the correlation between data and context information through federated learning. Furthermore, the lightweight neural network model located on mobile terminals is used. Based on the prediction of sensed quality, we develop a user recruitment algorithm that runs on the cloud platform through terminal-cloud collaboration. The performance of the proposed method is evaluated through simulations. Results show that compared with existing algorithms, i.e., Random Adaptive Greedy algorithm for User Recruitment(RAGUR)and Context-Aware Tasks Allocation(CATA), the proposed method improves the quality of sensed data by 23.5% and 38.8%, respectively.
2021年06期 v.26 869-877页 [查看摘要][在线阅读][下载 1608K] [下载次数：32 ] |[网刊下载次数：0 ] |[引用频次：12 ] |[阅读次数：0 ] - Weishan Zhang;Zhaoxiang Hou;Xiao Wang;Zhidong Xu;Xin Liu;Fei-Yue Wang;
Abnormal or drastic changes in the natural environment may lead to unexpected events, such as tsunamis and earthquakes, which are becoming a major threat to national economy. Currently, no effective assessment approach can deduce a situation and determine the optimal response strategy when a natural disaster occurs.In this study, we propose a social evolution modeling approach and construct a deduction model for self-playing,self-learning, and self-upgrading on the basis of the idea of parallel data and reinforcement learning. The proposed approach can evaluate the impact of an event, deduce the situation, and provide optimal strategies for decisionmaking. Taking the breakage of a submarine cable caused by earthquake as an example, we find that the proposed modeling approach can obtain a higher reward compared with other existing methods.
2021年06期 v.26 878-885页 [查看摘要][在线阅读][下载 1064K] [下载次数：47 ] |[网刊下载次数：0 ] |[引用频次：2 ] |[阅读次数：0 ] - Ao Xiong;Derong Liu;Hongkang Tian;Zhengyuan Liu;Peng Yu;Michel Kadoch;
The internet is an abundant source of news every day. Thus, efficient algorithms to extract keywords from the text are important to obtain information quickly. However, the precision and recall of mature keyword extraction algorithms need improvement. TextRank, which is derived from the PageRank algorithm, uses word graphs to spread the weight of words. The keyword weight propagation in Text Rank focuses only on word frequency. To improve the performance of the algorithm, we propose Semantic Clustering TextRank(SCTR), a semantic clustering news keyword extraction algorithm based on TextRank. Firstly, the word vectors generated by the Bidirectional Encoder Representation from Transformers(BERT) model are used to perform k-means clustering to represent semantic clustering. Then, the clustering results are used to construct a TextRank weight transfer probability matrix. Finally,iterative calculation of word graphs and extraction of keywords are performed. The test target of this experiment is a Chinese news library. The results of the experiment conducted on this text set show that the SCTR algorithm has greater precision, recall, and F1 value than the traditional TextRank and Term Frequency-Inverse Document Frequency(TF-IDF) algorithms.
2021年06期 v.26 886-893页 [查看摘要][在线阅读][下载 1624K] [下载次数：84 ] |[网刊下载次数：0 ] |[引用频次：27 ] |[阅读次数：0 ] - Hongsong Chen;Yongpeng Zhang;Yongrui Cao;Jing Xie;
Deep learning frameworks promote the development of artificial intelligence and demonstrate considerable potential in numerous applications. However, the security issues of deep learning frameworks are among the main risks preventing the wide application of it. Attacks on deep learning frameworks by malicious internal or external attackers would exert substantial effects on society and life. We start with a description of the framework of deep learning algorithms and a detailed analysis of attacks and vulnerabilities in them. We propose a highly comprehensive classification approach for security issues and defensive approaches in deep learning frameworks and connect different attacks to corresponding defensive approaches. Moreover, we analyze a case of the physical-world use of deep learning security issues. In addition, we discuss future directions and open issues in deep learning frameworks.We hope that our research will inspire future developments and draw attention from academic and industrial domains to the security of deep learning frameworks.
2021年06期 v.26 894-904页 [查看摘要][在线阅读][下载 2371K] [下载次数：41 ] |[网刊下载次数：0 ] |[引用频次：12 ] |[阅读次数：0 ] - Ziarmal Nazar Mohammad;Fadi Farha;Adnan O.M Abuassba;Shunkun Yang;Fang Zhou;
With the rapid development of cyberspace and smart home technology, human life is changing to a new virtual dimension with several promises for improving its quality. Moreover, the heterogeneous, dynamic, and internet-connected nature of smart homes brings many privacy and security difficulties. Unauthorized access to the smart home system is one of the most harmful actions and can cause several trust problems and relationship conflicts between family members and invoke home privacy issues. Access control is one of the best solutions for handling this threat, and it has been used to protect smart homes and other Internet of Things domains for many years. This survey reviews existing access control schemes for smart homes, which concern the essential authorization requirements and challenges that need to be considered while designing an authorization framework for smart homes. Furthermore, we note the most critical challenges that other access control solutions neglect for smart homes.
2021年06期 v.26 906-917页 [查看摘要][在线阅读][下载 6420K] [下载次数：84 ] |[网刊下载次数：0 ] |[引用频次：9 ] |[阅读次数：0 ] - Dawei Wei;Huansheng Ning;Feifei Shi;Yueliang Wan;Jiabo Xu;Shunkun Yang;Li Zhu;
The pervasiveness of the smart Internet of Things(IoTs) enables many electric sensors and devices to be connected and generates a large amount of dataflow. Compared with traditional big data, the streaming dataflow is faced with representative challenges, such as high speed, strong variability, rough continuity, and demanding timeliness, which pose severe tests of its efficient management. In this paper, we provide an overall review of IoT dataflow management. We first analyze the key challenges faced with IoT dataflow and initially overview the related techniques in dataflow management, spanning dataflow sensing, mining, control, security, privacy protection,etc. Then, we illustrate and compare representative tools or platforms for IoT dataflow management. In addition,promising application scenarios, such as smart cities, smart transportation, and smart manufacturing, are elaborated,which will provide significant guidance for further research. The management of IoT dataflow is also an important area, which merits in-depth discussions and further study.
2021年06期 v.26 918-930页 [查看摘要][在线阅读][下载 9504K] [下载次数：77 ] |[网刊下载次数：0 ] |[引用频次：10 ] |[阅读次数：0 ] <正>~~
2021年06期 v.26 931-935页 [查看摘要][在线阅读][下载 60K] [下载次数：25 ] |[网刊下载次数：0 ] |[引用频次：0 ] |[阅读次数：0 ]