Ateeq ur Rehman, Aimin Jiang, Aziz Ur Rehman, Anand Paul
{"title":"Weighted Based Trustworthiness Ranking in Social Internet of Things by using Soft Set Theory","authors":"Ateeq ur Rehman, Aimin Jiang, Aziz Ur Rehman, Anand Paul","doi":"10.1109/ICCC47050.2019.9064242","DOIUrl":"https://doi.org/10.1109/ICCC47050.2019.9064242","url":null,"abstract":"Internet of Things (IoT) is an evolving research area for the last two decades. The integration of the IoT and social networking concept results in developing an interdisciplinary research area called the Social Internet of Things (SIoT). The SIoT is dominant over the traditional IoT because of its structure, implementation, and operational manageability. In the SIoT, devices interact with each other independently to establish a social relationship for collective goals. To establish trustworthy relationships among the devices significantly improves the interaction in the SIoT and mitigates the phenomenon of risk. The problem is to choose a trustworthy node who is most suitable according to the choice parameters of the node. The best-selected node by one node is not necessarily the most suitable node for other nodes, as the trustworthiness of the node is independent for everyone. We employ some theoretical characterization of the soft-set theory to deal with this kind of decision-making problem. In this paper, we developed a weighted based trustworthiness ranking model by using soft set theory to evaluate the trustworthiness in the SIoT. The purpose of the proposed research is to reduce the risk of fraudulent transactions by identifying the most trusted nodes.","PeriodicalId":6739,"journal":{"name":"2019 IEEE 5th International Conference on Computer and Communications (ICCC)","volume":"16 1","pages":"1644-1648"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81129429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shiyu Gao, Jianguo Yu, Weizhi Zhu, Kun Bi, Lanlan Zhou
{"title":"Clustering Structure Based Time Switching Power Control optimization for Energy Harvesting Ad-Hoc Networks","authors":"Shiyu Gao, Jianguo Yu, Weizhi Zhu, Kun Bi, Lanlan Zhou","doi":"10.1109/ICCC47050.2019.9064252","DOIUrl":"https://doi.org/10.1109/ICCC47050.2019.9064252","url":null,"abstract":"Energy harvesting technology provides neoteric possibilities for prolonging the service life of mobile nodes in Ad-Hoc networks. In this paper, we focus on using energy harvesting technology in clustering structure based Ad-Hoc networks to decrease the system total power consumption as well as prolong the lifetime of the cluster. Distinct from the way in which a base station transmits energy to multiple mobile nodes in a general wireless network, we propose a scheme that the process of energy harvesting occurs at the cluster head which is able to receive information and harvest energy from dedicated subcarriers sent by the cluster members so as to alleviate burdens on its battery. We split the communication slot into two parts, energy transmission and information transmission, and formulate an optimization problem to obtain its optimal time switching ratio which will determine the power of each subcarrier and affect the energy consumption performance of the networks. Simulation results show that our proposed scheme can substantially reduce system power consumption and prolong the cluster’s lifetime under different channel conditions, numerical analysis also proves that it is feasible to expand the capacity of cluster with less cost.","PeriodicalId":6739,"journal":{"name":"2019 IEEE 5th International Conference on Computer and Communications (ICCC)","volume":"105 1","pages":"1080-1085"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89529642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Effectiveness of Visual Features on Diverse Reading Orders for Information Extraction","authors":"S. Bhat, D. Adiga, M. Shah, Viveka Vyeth","doi":"10.1109/ICCC47050.2019.9064294","DOIUrl":"https://doi.org/10.1109/ICCC47050.2019.9064294","url":null,"abstract":"Information extraction from unstructured documents, meant only for human readers, has to be dealt with differently than from the structured documents. Unstructured documents include visual clues that draw human attention and convey the majority of information to readers. There have been several recent advancements in information extraction in such documents using the conventional natural language processing methodologies. However, there has been little to no work towards using the non-sequential relationships that are found only in unstructured documents for the task of information extraction. In this study, we propose novel methodologies to capture the non-sequential relationships present in the unstructured documents for the task of Named Entity Recognition (NER) using Conditional Random Field (CRF). We experiment with two different datasets having different types of logical reading order and we compare three sets of features. The NER model, that uses the proposed novel features, achieves mean F1-Scores of 68.15% on Retail Receipt and 85.54% on Air Ticket documents.","PeriodicalId":6739,"journal":{"name":"2019 IEEE 5th International Conference on Computer and Communications (ICCC)","volume":"46 1","pages":"1759-1764"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89653430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Acoustic Signal-based Leak Size Estimation for Electric Valves Using Deep Belief Network","authors":"A. Ayodeji, Yong-kuo Liu, Wen Zhou, Xin-qiu Zhou","doi":"10.1109/ICCC47050.2019.9064354","DOIUrl":"https://doi.org/10.1109/ICCC47050.2019.9064354","url":null,"abstract":"To achieve the balance of plant, industrial valves are extensively used for critical safety and control functions. Conventionally, the threshold and the visual observation method are used for valve health monitoring. However, these methods are slow. This study presents a systematic application of deep belief network (DBN) for fault size estimation in the DN50 electric gate valve. First, real acoustic signals representing the malfunctions are acquired. Secondly, the influence of the transmission path and background noise from other equipment are decoupled, using wavelet packet decomposition and reconstruction. Finally, three different DBN models are developed for valve internal leakage assessment, using the original signals, time-domain parameters and the decomposed wavelet packets. Evaluation results show that the model trained with the time-domain signals achieve the optimal result. The model also shows the capability to automatically extract the deep features from the signal, escaping the dependence on the conventional signal processing method and reducing the signal processing time. The application of DBN for size estimation also solves the slow convergence problems in the conventional multi-layer, backpropagation neural networks.","PeriodicalId":6739,"journal":{"name":"2019 IEEE 5th International Conference on Computer and Communications (ICCC)","volume":"4 3 1","pages":"948-954"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89690413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A New Deep Learning Architecture for Person Detection","authors":"Liang Zhao, Y. Wan","doi":"10.1109/ICCC47050.2019.9064172","DOIUrl":"https://doi.org/10.1109/ICCC47050.2019.9064172","url":null,"abstract":"Person detection is a branch of object detection. It refers to positioning people in the image, finding the location and range of the person, and has a wide range of applications in fields such as video surveillance and target tracking. Yolo3 is currently one of the best deep learning structure for object detection. In this paper we further improve the Yolo3 network by combining the excellent characteristics of the end-to-end network for person detection. We propose a new person detection network model called PDnet. Among the main contributions, we further optimize the Yolo3 feature extraction network structure, change the three output ports of Yolo3 to one, and improve the anchor boxe clustering algorithm, so that our network model can extract the person features better, speed up the convergence of the category loss in the original loss function. The experimental results show that compared to vannila Yolo3, our proposed PDnet has better robustness and higher accuracy in person detection.","PeriodicalId":6739,"journal":{"name":"2019 IEEE 5th International Conference on Computer and Communications (ICCC)","volume":"43 1","pages":"2118-2122"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89760590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jun Li, Zhichao Xing, Sha Wei, Yuwen Qian, Weibin Zhang
{"title":"Dynamic Vehicle Data Gathering via Deep Reinforcement Learning Approach","authors":"Jun Li, Zhichao Xing, Sha Wei, Yuwen Qian, Weibin Zhang","doi":"10.1109/ICCC47050.2019.9064339","DOIUrl":"https://doi.org/10.1109/ICCC47050.2019.9064339","url":null,"abstract":"With the rapid development of vehicular ad hoc networks (VANETs), there have been numerous efforts to big data and analysis of vehicle information for roadside intelligence. However, continuous data gathering is energy consuming and eventually causes data backlog due to the capacity-limited backhaul links, while sparse gathering frequency may miss the timely detection of critical traffic information. Therefore, this paper focus on the dynamic data gathering problem in vehicular networks. In the scenario with environment changes dynamically, we first model the problem as a Markov decision process (MDP), and then propose different deep reinforcement learning(DRL) based maximization frequency matching algorithms, to determine the optimal gathering frequency at each time. The simulation results compare the performance differences of the algorithms, and show the trend of frequency matching in different storage spaces.","PeriodicalId":6739,"journal":{"name":"2019 IEEE 5th International Conference on Computer and Communications (ICCC)","volume":"293 1","pages":"1916-1920"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89223842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Secure Transmission with a Cooperative UAV-enabled Jammer","authors":"Yang Chen, Zhong-pei Zhang, Binrui Li","doi":"10.1109/ICCC47050.2019.9064333","DOIUrl":"https://doi.org/10.1109/ICCC47050.2019.9064333","url":null,"abstract":"In this paper, we investigate the secrecy performance of cooperative wireless communication networks, where a source (Alice) intends to transmit information to a legitimate user (Bob) with an unmanned aerial vehicle (UAV) enabled friendly jammer in the presence of a passive eavesdropper (Eve). In order to maximize the secrecy rate of the system under a certain secrecy outage probability, we design a scheme utilizing artificial-noise (AN) beamforming and cooperative jamming to determine the optimal power allocation factor with only location and statistical channel state information of the Eve. Numerical results validate that the proposed scheme can significantly improve the secrecy rate and secure energy efficiency (EE) performance.","PeriodicalId":6739,"journal":{"name":"2019 IEEE 5th International Conference on Computer and Communications (ICCC)","volume":"79 1","pages":"1131-1136"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89428998","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Revisiting Link Quality Metrics for Wireless Sensor Networks","authors":"Wei Liu, Yu Xia, Jinwei Xu, Shunren Hu, Rong Luo","doi":"10.1109/ICCC47050.2019.9064098","DOIUrl":"https://doi.org/10.1109/ICCC47050.2019.9064098","url":null,"abstract":"Packet Reception Ratio (PRR), Received Signal Strength Indicator (RSSI) and Link Quality Indicator (LQI) are common metrics for link quality estimation. However, utilization and statistical methods of these metrics are different, so it fails to describe their link quality estimation capabilities systematically and deeply. Some works even came to contradicting conclusions. In this paper, these three metrics are comprehensively evaluated through collecting and analyzing large amounts of experimental data. It is shown that average PRR could be used to distinguish good links from bad links. Standard deviation of PRR could be used to identify moderate links. So, good links, moderate links and bad links are able to be distinguished more effectively and accurately by combining average value and standard deviation of PRR. Both average RSSI and LQI could be used to identify good links. However, they could not distinguish moderate and bad links. Standard deviation of RSSI doesn’t have link quality estimation capability, and so does the standard deviation of LQI within fixed time windows. Unlike them, standard deviation of LQI with fixed number of received packets could be used to identify good links, but still not moderate and bad links.","PeriodicalId":6739,"journal":{"name":"2019 IEEE 5th International Conference on Computer and Communications (ICCC)","volume":"9 1","pages":"597-603"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86568818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Linxi Wang, Xiaoxi Hu, Xun Han, Yin Kuang, Xinquan Yang
{"title":"A Multi-target Tracking Algorithm Based on AGMM-PHD","authors":"Linxi Wang, Xiaoxi Hu, Xun Han, Yin Kuang, Xinquan Yang","doi":"10.1109/ICCC47050.2019.9064290","DOIUrl":"https://doi.org/10.1109/ICCC47050.2019.9064290","url":null,"abstract":"Aiming at the problem that traditional tracking algorithms can not effectively track maneuvering multi-target in clutter environment, a new maneuvering multi-target tracking algorithm is proposed in this paper. By combining the Adaptive Grid method with the PHD filtering algorithm, the adaptive adjustment of the model set is realized, so that the tracking algorithm can adapt to the state change of the maneuvering targets. The simulation results show that, compared with the traditional fixed structure multi-model tracking algorithm, the algorithm proposed in this paper has better tracking performance and higher cost-effectiveness ratio. It has broad application prospects in multi-target tracking.","PeriodicalId":6739,"journal":{"name":"2019 IEEE 5th International Conference on Computer and Communications (ICCC)","volume":"228 1","pages":"322-326"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86689209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Language Constructs and Semantics for Runtime-independent Parallelism Expression on Heterogeneous Systems","authors":"Shusen Wu, Xiaoshe Dong, Yufei Wang, Weiduo Chen","doi":"10.1109/ICCC47050.2019.9064451","DOIUrl":"https://doi.org/10.1109/ICCC47050.2019.9064451","url":null,"abstract":"The emergence of heterogeneous processors such as GPUs provide massively parallel computing power but also exacerbate the difficulties of parallel programming. Although low-level programming methods such as CUDA and OpenCL can yield good performance, the programming productivity is poor and applications lack portability. In this paper, we present a core language Ruler, which extends C with high-level parallel constructs. These constructs enable programmers to express parallelism in programs without concerning runtime details, thus ease user programming. We present the operational semantics of the language and show how these constructs reserve parallel patterns and parallelism degree of high-level applications. Those information could inform the compiler to generate efficient code and maintain the performance on different platforms. We have implemented a compiler and runtime system for Ruler on the top of OpenCL. Multiple benchmarks are rebuilt with Ruler and evaluated on both a NVIDIA GPU and an Intel MIC platform to demonstrate the effectiveness of our techniques. The size of Ruler code is only 13%-64% to that of the OpenCL code. The rebuilt benchmarks execute smoothly on both platforms after compilation, yielding a competitive performance to that of handcrafted benchmark OpenCL code on both platforms.","PeriodicalId":6739,"journal":{"name":"2019 IEEE 5th International Conference on Computer and Communications (ICCC)","volume":"127 1","pages":"1269-1275"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89097391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}