In this paper, we present an open cloud DRM service provider to protect the digital content's copyright. The proposed architecture enables the service providers to use an on-the fly DRM technique with digital signature and symmetric-key encryption. Unlike other similar works, our system does not keep the encrypted digital content but lets the content creators do so in their own cloud storage. Moreover, the key used for symmetric encryption are managed in an extremely secure way by means of the key fission engine and the key fusion engine. The ideas behind the two engines are taken from the works in secure network coding and secret sharing. Although the use of secret sharing and secure network coding for the storage of digital content is proposed in some other works, this paper is the first one employing those ideas only for key management while letting the content be stored in the owner's cloud storage. In addition, we implement an Android SDK for e-Book readers to be compatible with our proposed open cloud DRM service provider. The experimental results demonstrate that our proposal is feasible for the real e-Book market, especially for individual businesses.
{"title":"Multiple Secret Key Sharing Based on the Network Coding Technique for an Open Cloud DRM Service Provider","authors":"Wiroon Sriborrirux, Panuwat Promsiri, Apirath Limmanee","doi":"10.1109/CSE.2014.191","DOIUrl":"https://doi.org/10.1109/CSE.2014.191","url":null,"abstract":"In this paper, we present an open cloud DRM service provider to protect the digital content's copyright. The proposed architecture enables the service providers to use an on-the fly DRM technique with digital signature and symmetric-key encryption. Unlike other similar works, our system does not keep the encrypted digital content but lets the content creators do so in their own cloud storage. Moreover, the key used for symmetric encryption are managed in an extremely secure way by means of the key fission engine and the key fusion engine. The ideas behind the two engines are taken from the works in secure network coding and secret sharing. Although the use of secret sharing and secure network coding for the storage of digital content is proposed in some other works, this paper is the first one employing those ideas only for key management while letting the content be stored in the owner's cloud storage. In addition, we implement an Android SDK for e-Book readers to be compatible with our proposed open cloud DRM service provider. The experimental results demonstrate that our proposal is feasible for the real e-Book market, especially for individual businesses.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116232705","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}
A hash chain is a popular tool for improving the efficiency of several cryptographic applications. In spite of the computation efficiency of one-way function, the performance issue is a challenging research topic for chains with long length in resource-constrained environments. We propose a recursive algorithm of hash chain traversal for arbitrary length n with [log2n] storage cells and the computational costs of our solution are less than 12 n log2 n hash function evaluations.
散列链是一种流行的工具，用于提高几种加密应用程序的效率。尽管单向函数的计算效率很高，但对于资源受限环境下的长链，性能问题是一个具有挑战性的研究课题。我们提出了一个任意长度n的递归哈希链遍历算法，存储单元为[log2n]，我们的解决方案的计算成本小于12 n log2n哈希函数计算。
{"title":"A Recursive Algorithm for General Hash Chain Traversal","authors":"Yi-Wen Peng, Wei-Mei Chen","doi":"10.1109/CSE.2014.228","DOIUrl":"https://doi.org/10.1109/CSE.2014.228","url":null,"abstract":"A hash chain is a popular tool for improving the efficiency of several cryptographic applications. In spite of the computation efficiency of one-way function, the performance issue is a challenging research topic for chains with long length in resource-constrained environments. We propose a recursive algorithm of hash chain traversal for arbitrary length n with [log2n] storage cells and the computational costs of our solution are less than 12 n log2 n hash function evaluations.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115259209","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}
As a promising direction of future Internet, Content-Centric Network (CCN) has attracted world-wide attention. In-network caching is an important feature of CCN network, which has significant impacts on the performance of content transmission. Existing researches on in-network caching either have no regard for the collaboration or need giant additional overhead for global optimization. This paper proposes a hierarchical division-based cache storage strategy, called HD, which allows the contents can be cached in different nodes by grouping contents into different hierarchies. HD aims to reduce propagation delay and server load by light-weight collaboration mechanisms that allows the popular contents could be cached along the path with certain a probability. The performance of HD scheme was evaluated by comparing with the well-known schemes through simulation. The experimental results indicate that HD strategy can save up to 30.77% hop reduction ratio, 44.93% average cache hit ratio and 11.88% server hit ratio while the parameter α of Zipf distribution is increasing.
{"title":"HD: A Cache Storage Strategy Based on Hierarchical Division in Content-centric Networking","authors":"Zongming Feng, Jun Yu Li, Haibo Wu, Jiang Zhi","doi":"10.1109/CSE.2014.123","DOIUrl":"https://doi.org/10.1109/CSE.2014.123","url":null,"abstract":"As a promising direction of future Internet, Content-Centric Network (CCN) has attracted world-wide attention. In-network caching is an important feature of CCN network, which has significant impacts on the performance of content transmission. Existing researches on in-network caching either have no regard for the collaboration or need giant additional overhead for global optimization. This paper proposes a hierarchical division-based cache storage strategy, called HD, which allows the contents can be cached in different nodes by grouping contents into different hierarchies. HD aims to reduce propagation delay and server load by light-weight collaboration mechanisms that allows the popular contents could be cached along the path with certain a probability. The performance of HD scheme was evaluated by comparing with the well-known schemes through simulation. The experimental results indicate that HD strategy can save up to 30.77% hop reduction ratio, 44.93% average cache hit ratio and 11.88% server hit ratio while the parameter α of Zipf distribution is increasing.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123382294","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}
In recent years, developments in Internet of things and ubiquitous computing have created new opportunities to promote sensors participation in environmental, military and personalized monitoring. Up to now, sensor networks have been proposed for various applications, which are however characterized by a lack of interoperability. In this context, the paper gives a survey on semantic sensor web, and proposes a general method for modeling geospatial sensor knowledge by adding semantic annotations and rule reasoning to the Sensor ML (Sensor Model Language) described sensor information within OGC (Open Geospatial Consortium) SWE (Sensor Web Enablement) framework. We describe the air quality monitoring instance which gives a solution for automatically reporting the health implications and cautionary statements to the nearby people. This work constitutes an essential step towards the geospatial knowledge modeling of interoperable and intelligent sensor networks.
近年来，物联网和普适计算的发展为促进传感器参与环境、军事和个性化监测创造了新的机会。到目前为止，传感器网络已经被提出用于各种应用，但其特点是缺乏互操作性。在此背景下，本文对语义传感器web进行了综述，并提出了一种通用的建模地理空间传感器知识的方法，即在OGC (Open geospatial Consortium) SWE (sensor web Enablement)框架中对传感器信息进行描述的sensor ML (sensor Model Language，传感器模型语言)中添加语义注释和规则推理。我们描述了一个空气质量监测实例，该实例给出了一个解决方案，可以自动向附近的人报告健康影响和警告声明。这项工作是迈向可互操作和智能传感器网络的地理空间知识建模的重要一步。
{"title":"Modeling Geospatial Sensor Knowledge under a Semantic Sensor Web Environment","authors":"Xiaoliang Meng, Yuwei Wang, Yunhao Wu","doi":"10.1109/CSE.2014.215","DOIUrl":"https://doi.org/10.1109/CSE.2014.215","url":null,"abstract":"In recent years, developments in Internet of things and ubiquitous computing have created new opportunities to promote sensors participation in environmental, military and personalized monitoring. Up to now, sensor networks have been proposed for various applications, which are however characterized by a lack of interoperability. In this context, the paper gives a survey on semantic sensor web, and proposes a general method for modeling geospatial sensor knowledge by adding semantic annotations and rule reasoning to the Sensor ML (Sensor Model Language) described sensor information within OGC (Open Geospatial Consortium) SWE (Sensor Web Enablement) framework. We describe the air quality monitoring instance which gives a solution for automatically reporting the health implications and cautionary statements to the nearby people. This work constitutes an essential step towards the geospatial knowledge modeling of interoperable and intelligent sensor networks.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124839492","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}
In road networks, k-Range Nearest Neighbor (kRNN) queries locate the k-nearest neighbors for every point on the road segments that are within a given query region, based on the network distance. This is an important task, because the user's location information may not be accurate, furthermore, users may be unwilling to reveal their exact location for privacy reasons. Therefore, in this specific situation, evaluating the query result at each point and communicating with the server will create a significant communication burden for the client. We propose an efficient approach that computes a safe segment region for each inside road segment, such that the client is not required to evaluate the query answer returned by the LBS (location-based server) within the safe region. In addition, our safe region-based query processing algorithm is designed for a directed road network, where each road network has a particular orientation. In contrast, previous kRNN research produced algorithms that operated only in undirected road networks.
{"title":"A Safe-Region Approach to k-RNN Queries in Directed Road Network","authors":"Kamil Zeberga, Hyung-Ju Cho, Tae-Sun Chung","doi":"10.1109/CSE.2014.167","DOIUrl":"https://doi.org/10.1109/CSE.2014.167","url":null,"abstract":"In road networks, k-Range Nearest Neighbor (kRNN) queries locate the k-nearest neighbors for every point on the road segments that are within a given query region, based on the network distance. This is an important task, because the user's location information may not be accurate, furthermore, users may be unwilling to reveal their exact location for privacy reasons. Therefore, in this specific situation, evaluating the query result at each point and communicating with the server will create a significant communication burden for the client. We propose an efficient approach that computes a safe segment region for each inside road segment, such that the client is not required to evaluate the query answer returned by the LBS (location-based server) within the safe region. In addition, our safe region-based query processing algorithm is designed for a directed road network, where each road network has a particular orientation. In contrast, previous kRNN research produced algorithms that operated only in undirected road networks.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123620726","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}
To solve the problem of data forwarding between various types of interfaces, we design a multi-interface routing system based on FPGA for the heterogeneous network communication system. In order to deal with the problem of port address non-uniform, we propose a virtual IP address allocation method, and based on the method, we design a routing algorithm. The simulation results show that the algorithm have routing function between different ports. In addition, we test a case on FPGA, and our experimental results show that we achieve data forwarding between RS232, USB, and Ethernet port. It's proved that we realize a multi-interface routing mechanism which can work in a heterogeneous network communication system.
{"title":"A Multiple Interfaces Routing System Embedded on FPGA","authors":"Zhihua Chen, Deshi Li","doi":"10.1109/CSE.2014.241","DOIUrl":"https://doi.org/10.1109/CSE.2014.241","url":null,"abstract":"To solve the problem of data forwarding between various types of interfaces, we design a multi-interface routing system based on FPGA for the heterogeneous network communication system. In order to deal with the problem of port address non-uniform, we propose a virtual IP address allocation method, and based on the method, we design a routing algorithm. The simulation results show that the algorithm have routing function between different ports. In addition, we test a case on FPGA, and our experimental results show that we achieve data forwarding between RS232, USB, and Ethernet port. It's proved that we realize a multi-interface routing mechanism which can work in a heterogeneous network communication system.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"264 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122540133","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}
The college students are outstanding contemporary youth, and the universities are source of various social trend of thought. It is a big challenge for the college educational workers to cultivate the college students of healthy, upward characters. However, the traditional teaching methods cannot meet the requirements and get an expected result. To solve these problems, a cultural transmission platform under wireless networks is developed in this paper. This platform combined the political and ideological education and wireless smart terminals, which can reduce the burden of college students and teachers. The system used Tomcat to be the website server, used web service to be the middle layer of communication between android and MySQL database and used B/S+C/S model to be the frame of communication and operation. The platform consisted of the mobile terminal which has the function of the news display, interactive, voting, a login/registration and the local server which do the data saving, information disposing and information exchanging. This system reduced the burden of the college students and teachers, which also broadened their horizons and improved the ability of the college's cultural transmission.
{"title":"Solutions for the Key Technologies of Cultural Transmission Platform under Wireless Networks","authors":"Chao Guo, Yinbo Liu, Xingang Liu","doi":"10.1109/CSE.2014.192","DOIUrl":"https://doi.org/10.1109/CSE.2014.192","url":null,"abstract":"The college students are outstanding contemporary youth, and the universities are source of various social trend of thought. It is a big challenge for the college educational workers to cultivate the college students of healthy, upward characters. However, the traditional teaching methods cannot meet the requirements and get an expected result. To solve these problems, a cultural transmission platform under wireless networks is developed in this paper. This platform combined the political and ideological education and wireless smart terminals, which can reduce the burden of college students and teachers. The system used Tomcat to be the website server, used web service to be the middle layer of communication between android and MySQL database and used B/S+C/S model to be the frame of communication and operation. The platform consisted of the mobile terminal which has the function of the news display, interactive, voting, a login/registration and the local server which do the data saving, information disposing and information exchanging. This system reduced the burden of the college students and teachers, which also broadened their horizons and improved the ability of the college's cultural transmission.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129798969","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}
We introduce a novel method, named S-CRP (Segmentation based on distance dependent Chinese Restaurant Process), to segment broadcast sports videos into semantic shots. S-CRP employs distance dependent Chinese Restaurant Process (DCRP) using two segmentation criteria, namely appearance and time distances. It takes advantage of the customer (frame) assignments in DCRP and is able to reduce the negative effect of noisy frames without the use of domain knowledge and more sophisticated classifiers. In addition, we find that the conventional performance evaluation metrics are unable to reflect the quality of the segmentation properly. We introduced a new performance metric, namely Levenshtein distance Ratio, which gives a more accurate measure of how well the segmentation result can match the original video structure.
我们提出了一种新的方法，S-CRP (Segmentation based distance dependent Chinese Restaurant Process)，将广播体育视频分割成语义片段。S-CRP采用距离相关中式餐厅过程(DCRP)，采用外观距离和时间距离两个分割标准。它利用了DCRP中的客户(帧)分配，并且能够在不使用领域知识和更复杂的分类器的情况下减少噪声帧的负面影响。此外，我们发现传统的性能评价指标不能很好地反映分割的质量。我们引入了一个新的性能指标，即Levenshtein距离比，它可以更准确地衡量分割结果与原始视频结构的匹配程度。
{"title":"A New Segmentation Method for Broadcast Sports Video","authors":"Hao Sun, Jim X. Chen, H. Wechsler, Yongquan Jiang","doi":"10.1109/CSE.2014.328","DOIUrl":"https://doi.org/10.1109/CSE.2014.328","url":null,"abstract":"We introduce a novel method, named S-CRP (Segmentation based on distance dependent Chinese Restaurant Process), to segment broadcast sports videos into semantic shots. S-CRP employs distance dependent Chinese Restaurant Process (DCRP) using two segmentation criteria, namely appearance and time distances. It takes advantage of the customer (frame) assignments in DCRP and is able to reduce the negative effect of noisy frames without the use of domain knowledge and more sophisticated classifiers. In addition, we find that the conventional performance evaluation metrics are unable to reflect the quality of the segmentation properly. We introduced a new performance metric, namely Levenshtein distance Ratio, which gives a more accurate measure of how well the segmentation result can match the original video structure.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129860549","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}
Guangyu Dong, Kai Lin, Keqiu Li, Huayong Luo, Xiangwen Zhang
Indoor positioning based on Wi-Fi signal attracts a lot of attention in the location field. However, accuracy of positioning is often affected due to the instability of indoor Wi-Fi signal. In order to overcome this problem and reduce the errors, we present a new indoor WiFi-based positioning algorithm called FMA-RRSS which is the abbreviation of Fingerprint Matching Algorithm Based on Relative Received Strength Signal. In this paper, we propose a new position-determined model to produce location information from WiFi signal. Combined with the traditional solution of fingerprint database in indoor positioning, we use relative RSS value representing location information to estimate a clients actual position. We set up a positioning system and implement the FMA-RRSS in the actual WiFi environment. The experimental results show the improvement of positioning accuracy, fingerprint training complexity and response time of matching algorithm compared with other traditional indoor positioning algorithm like RADAR and Free Loc.
{"title":"FMA-RRSS: Fingerprint Matching Algorithm Based on Relative Received Signal Strength in Indoor Wi-Fi Positioning","authors":"Guangyu Dong, Kai Lin, Keqiu Li, Huayong Luo, Xiangwen Zhang","doi":"10.1109/CSE.2014.212","DOIUrl":"https://doi.org/10.1109/CSE.2014.212","url":null,"abstract":"Indoor positioning based on Wi-Fi signal attracts a lot of attention in the location field. However, accuracy of positioning is often affected due to the instability of indoor Wi-Fi signal. In order to overcome this problem and reduce the errors, we present a new indoor WiFi-based positioning algorithm called FMA-RRSS which is the abbreviation of Fingerprint Matching Algorithm Based on Relative Received Strength Signal. In this paper, we propose a new position-determined model to produce location information from WiFi signal. Combined with the traditional solution of fingerprint database in indoor positioning, we use relative RSS value representing location information to estimate a clients actual position. We set up a positioning system and implement the FMA-RRSS in the actual WiFi environment. The experimental results show the improvement of positioning accuracy, fingerprint training complexity and response time of matching algorithm compared with other traditional indoor positioning algorithm like RADAR and Free Loc.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129950886","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}
Yang Qifan, Tang Hao, Zhao Xuebing, Li Yin, Zhang Sanfeng
User experience of smart mobile devices can be improved in numerous scenarios with the assist of in-air gesture recognition. Most existing methods proposed by industry and academia are based on special sensors. On the contrary, a special sensor-independent in-air gesture recognition method named Dolphin is proposed in this paper which can be applied to off-the-shelf smart devices directly. The only sensors Dolphin needs are the loudspeaker and microphone embedded in the device. Dolphin emits a continuous 21 KHz tone by the loudspeaker and receive the gesture-reflecting ultrasonic wave by the microphone. The gesture performed is encoded into the reflected ultrasonic in the form of Doppler shift. By combining manual recognition and machine leaning methods, Dolphin extracts features from Doppler shift and recognizes a rich set of pre-defined gestures with high accuracy in real time. Parameter selection strategy and gesture recognition under several scenarios are discussed and evaluated in detail. Dolphin can be adapted to multiple devices and users by training using machine learning methods.
{"title":"Dolphin: Ultrasonic-Based Gesture Recognition on Smartphone Platform","authors":"Yang Qifan, Tang Hao, Zhao Xuebing, Li Yin, Zhang Sanfeng","doi":"10.1109/CSE.2014.273","DOIUrl":"https://doi.org/10.1109/CSE.2014.273","url":null,"abstract":"User experience of smart mobile devices can be improved in numerous scenarios with the assist of in-air gesture recognition. Most existing methods proposed by industry and academia are based on special sensors. On the contrary, a special sensor-independent in-air gesture recognition method named Dolphin is proposed in this paper which can be applied to off-the-shelf smart devices directly. The only sensors Dolphin needs are the loudspeaker and microphone embedded in the device. Dolphin emits a continuous 21 KHz tone by the loudspeaker and receive the gesture-reflecting ultrasonic wave by the microphone. The gesture performed is encoded into the reflected ultrasonic in the form of Doppler shift. By combining manual recognition and machine leaning methods, Dolphin extracts features from Doppler shift and recognizes a rich set of pre-defined gestures with high accuracy in real time. Parameter selection strategy and gesture recognition under several scenarios are discussed and evaluated in detail. Dolphin can be adapted to multiple devices and users by training using machine learning methods.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129566089","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：