{"title":"Eye Detection with Faster R-CNN","authors":"Jiali Cui, Fuqiang Chen, Duo Shi, Liqiang Liu","doi":"10.5220/0008096201110116","DOIUrl":"https://doi.org/10.5220/0008096201110116","url":null,"abstract":"The accuracy of eye detection is crucial to a variety of biometric identification technologies, such as iris recognition. The challenge of eye detection comes from improving accuracy of detection in the case of occlusion or reflection of glasses. In this paper, an eye detection method based on Faster Region-based Convolutional Neural Network (Faster R-CNN) is proposed. The method includes three import parts: convolutional layers, region proposal network (RPN) and detection network. By training monocular and binocular models on the training dataset, the recall of monocular and binocular models on test dataset can reach 96% and 95% respectively, which proves that the proposed method based on Faster R-CNN has high accuracy of detection in the task.","PeriodicalId":415288,"journal":{"name":"Proceedings of the International Conference on Advances in Computer Technology, Information Science and Communications","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133185384","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":"Analysis of the CRAX Vulnerability Automatic Utilization Process","authors":"Zhao Chao, Pan Zulie, Huang Zhao, Huang Hui","doi":"10.5220/0008097100320037","DOIUrl":"https://doi.org/10.5220/0008097100320037","url":null,"abstract":"In recent years, the number of software vulnerabilities has been on the rise, and the harm of software vulnerabilities has become more and more serious. However, there are so many software vulnerabilities that simple manual analysis cannot meet the requirements. In view of the above problems, this paper introduces CRAX. CRAX is a new framework based on symbolic execution. And it is to act as a backend of static/dynamic program analyzers, bug finders, fuzzers, and crash report database. It can automatically, efficiently and quickly analyze software vulnerabilities and generate stable and efficient test cases. The paper analyzes CRAX's automatic analysis process of vulnerability program and the generation process of test cases in detail, and in chapter 3 and chapter 4, it emphatically introduces the constraint construction and reconstruction process in the process of CRAX's automatic analysis.","PeriodicalId":415288,"journal":{"name":"Proceedings of the International Conference on Advances in Computer Technology, Information Science and Communications","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134073380","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 Method for Health Detection in Eureka Based on Load Forecasting","authors":"Chao Deng, Xinming Tan, Lang Li","doi":"10.5220/0008098902270232","DOIUrl":"https://doi.org/10.5220/0008098902270232","url":null,"abstract":"Health detection relies on the heartbeat mechanism in Eureka. The heartbeat mechanism analyzes the status of service by periodically detecting the running status of the service node. But it doesn't care whether the service runs successfully, therefore reducing the success rate of service calls. In order to solve the problem, this paper proposes a new method for load forecasting based on time series. The value of load forecasting is used to measure the health of the service node quantitatively, and the number of available instances is effectively reduced during load balancing and the load balancing efficiency was improved.","PeriodicalId":415288,"journal":{"name":"Proceedings of the International Conference on Advances in Computer Technology, Information Science and Communications","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134639045","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":"An Improved Token Bucket Algorithm for Service Gateway Traffic Limiting","authors":"Lang Li, Xinming Tan, Chao Deng","doi":"10.5220/0008098802220226","DOIUrl":"https://doi.org/10.5220/0008098802220226","url":null,"abstract":"In the Spring Cloud micro-service system, the gateway Zuul, as the entrance to all internal services, must carry out the traffic limiting operation to guarantee the stability of the service in the case of high concurrency. The traditional token bucket traffic shaping algorithm cannot guarantee the stability of core services. In order to solve this problem, this paper designed an overload protection strategy based on URI configuration file in combination with gateway Zuul, which can filter the request before acquiring the tokens. It improved the token bucket algorithm, realized the traffic limiting function and guaranteed the stability and immediacy of the core service process.","PeriodicalId":415288,"journal":{"name":"Proceedings of the International Conference on Advances in Computer Technology, Information Science and Communications","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123788816","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":"Translation of Network Popular Words","authors":"Luo Shihan","doi":"10.5220/0008097500380043","DOIUrl":"https://doi.org/10.5220/0008097500380043","url":null,"abstract":"In today’s SNS, numerous network popular words have been creating. Due to most network popular words are only used in a short period of time, it is hardly to find a dictionary that includes network popular words. So, it is unpractical to translate network popular words by traditional machine translation method. Now, the research of extracting network popular words has obtained some outcomes to a certain extent. However, the existing research of paraphrasing network popular words, which uses distributed representation method to analyse network popular words, does not make much progress. The purpose of this paper is to improve the translation of network popular words by adding sentiment analysis into distributed representation method. By analysing network popular words in eight sentiment polarity (joy, sadness, trust, disgust, fear, anger, surprise, anticipation), the accuracy of translation of network popular words is obviously improved.","PeriodicalId":415288,"journal":{"name":"Proceedings of the International Conference on Advances in Computer Technology, Information Science and Communications","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128992056","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}
Jingwen Yu, Jiechen Li, Zhanwei Xuan, Lei Wang, Xiang Feng
{"title":"Security Using Dynamic Secret Based on Packet Loss Rate for Wireless Sensor Networks","authors":"Jingwen Yu, Jiechen Li, Zhanwei Xuan, Lei Wang, Xiang Feng","doi":"10.5220/0008097001780183","DOIUrl":"https://doi.org/10.5220/0008097001780183","url":null,"abstract":"The transmission security of wireless sensor networks plays a vital role in the application of the wireless sensor network. In order to protect these networks, many security protocols are proposed at this stage to protect the security of routing and data transmission. While much of the previous transport mechanism depends on the link layer encryption whose algorithms are not applied to end-to-end transmission. Thus there is scope for further research on the security of source node to sink transmission, and a new method that sink updates the key of the current group by calculating the packet loss rate and considering the local retransmission of the link layer is proposed. Our method provides a supplemental mechanism for existing transport protocols that even if an attacker eavesdrops the current key, the security is automatically replenished, thereby enhancing the security of the transmission. Theoretical analysis and simulation experiments show that the proposed method can guarantee the end-to-end transmission security, and it also consumes less energy than the application of dynamic key update directly to end-to-end transmission.","PeriodicalId":415288,"journal":{"name":"Proceedings of the International Conference on Advances in Computer Technology, Information Science and Communications","volume":"159 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123830349","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":"Sensing as a Service- A Service-Oriented Collaborative Sensing Framework for Detecting Composite Events in Industrial Cyber-Physical System","authors":"Tao Wang, Xiao Hong, Lianglun Cheng","doi":"10.5220/0008099402640271","DOIUrl":"https://doi.org/10.5220/0008099402640271","url":null,"abstract":"The widespread deployment of sensors in Industrial Cyber-Physical System (ICPS) enables real-time monitoring kinds of composite events occurring in the industrial process. However, due to the high degree of heterogeneity of the sensing nodes in ICPSs, it is very hard to effectively composing the platform-specific functionalities provided by heterogeneous sensor nodes for detecting various composite events. In this article, by exploiting REST framework and expanding the basic architecture of S2aaS, we propose a service-oriented and lightweight collaborative sensing framework for detecting multiple composite events in ICPSs. Further, the specific implementation details about the process of RESTful service registry of sensing node, sensing service discovery and service composition is presented. We develop an application prototype to test the feasibility and scalability of the system, and the experiment results show that RESTful-based sensing service collaboration outperforms SOAP-based one with more lightweight communication and less power consumption as expected. Based on our proposed collaborative sensing framework with Restful sensing services, it is very convenient to provide a sensor web services for various requirements of composite event detection.","PeriodicalId":415288,"journal":{"name":"Proceedings of the International Conference on Advances in Computer Technology, Information Science and Communications","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125184321","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":"Queue-Sensing-Based CSAT: A Downlink Transmission Scheme for LTE-M in Unlicensed Spectrum","authors":"Gong Zelin, Ying Wang, T. Luo","doi":"10.5220/0008098500920097","DOIUrl":"https://doi.org/10.5220/0008098500920097","url":null,"abstract":"A shortage of licensed spectrum is a major hindrance to the capacity of Long Term Evolution for Metro (LTE-M) to carry urban rail transit services at present. Inspired by LTE-Unlicensed (LTE-U) offloading some of data traffic transmitted in licensed spectrum by accessing the unlicensed 5GHz frequency band, we propose a queue-sensing-based Carrier Sensing Adaptive Transmission (CSAT) scheme for LTE-M in unlicensed spectrum based on LTE-U. The scheme calculates the minimum amount of data that should be transmitted during current transmission duration by queue length at the beginning of each LTE-U cycle, according to which, LTE-U adjusts its duty cycle to meet the requirement of LTE-M service. This paper focuses on the downlink transmission scheme for LTE-M in unlicensed spectrum, and verifies its performance by simulation, which tells that Queue-sensing-based CSAT will not only provide a reliable transmission for LTE-M services, but also maximize the fairness of channel occupancy in unlicensed","PeriodicalId":415288,"journal":{"name":"Proceedings of the International Conference on Advances in Computer Technology, Information Science and Communications","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125232962","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":"Deep Learning for Channel Decoding Under Correlated Noise","authors":"Xiangxiang Zhang, T. Luo","doi":"10.5220/0008098301350141","DOIUrl":"https://doi.org/10.5220/0008098301350141","url":null,"abstract":"","PeriodicalId":415288,"journal":{"name":"Proceedings of the International Conference on Advances in Computer Technology, Information Science and Communications","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125046912","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":"Classification of DHCP Spoofing and Effectiveness of DHCP Snooping","authors":"Shigeo Akashi, Yao Tong","doi":"10.5220/0008099002330238","DOIUrl":"https://doi.org/10.5220/0008099002330238","url":null,"abstract":"It is well known that DHCP snooping is a famous countermeasure against DHCP spoofing. Actually, to what extent DHCP snooping can protect the authenticated DHCP clients from being given malicious DHCP transactions through the network where the authenticated DHCP clients and the malicious DHCP servers share with each other? The answer to this question is that DHCP snooping can protect DHCP spoofing to a certain extent, though DHCP snooping cannot protect DHCP spoofing completely. In the former half of this paper, it is shown that DHCP spoofing can be classified into two cases, namely DHCP spoofing from inside and DHCP spoofing from outside, and in the latter half of this paper, it is shown that DHCP snooping can protect the former attack from being implemented but cannot protect the latter attack from being implemented. More exactly speaking, it is shown that DHCP snooping cannot prevent DHCP spoofing from outside from being implemented, while applying the longest matching prefix rule to leading a malicious network segment which is constructed on the basis of the leaked DHCP transactions beforehand.","PeriodicalId":415288,"journal":{"name":"Proceedings of the International Conference on Advances in Computer Technology, Information Science and Communications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123056989","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}