Pub Date : 2016-08-01DOI: 10.1109/FSKD.2016.7603512
Yan Liu, Yongwei Li, Yihong Zhao, Xiao-Mou. Chen
The increasing scale of multi-core processors are likely to be randomly heterogeneous by design or because of diversity and flaws. The latter type of heterogeneity introduced by some unforeseen variable factors such as the manufacturing process variation is especially challenging because of its unpredictability. In this environment, thread scheduler and global power manager must handle such randomly heterogeneous. Furthermore, these algorithms must supply high efficiency, scalability and low overhead because future multi-core processors may have a number of cores on a single die. This paper presents a variation-aware scheduling algorithm for application scheduling and power management. Thread switching and sampling among different cores in the multi-core processor introduce obvious overhead than previous many-core scheduling algorithms. Proposed scheme records the information of swapped thread of preferential core and uses tabu search-based randomly heterogeneous scheduling algorithm(TSR) to avoid the occurrence of repeated sampling and reduce the migration frequency and sampling frequency of a thread. The experimental results show that TSR algorithm has decreased 45.7% of thread migration and 42.2% of the sampling time as compared with local search algorithm. This paper regards the transcendental Hungarian offline scheduling algorithm as the baseline. ED2 of TSR only decrease by 8.58% as compared with that of Hungarian offline scheduling algorithm, but compared with the random search scheduling algorithm, ED2 of TSR decreased by 39.4%.
{"title":"A scheduling algorithm in the randomly heterogeneous multi-core processor","authors":"Yan Liu, Yongwei Li, Yihong Zhao, Xiao-Mou. Chen","doi":"10.1109/FSKD.2016.7603512","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603512","url":null,"abstract":"The increasing scale of multi-core processors are likely to be randomly heterogeneous by design or because of diversity and flaws. The latter type of heterogeneity introduced by some unforeseen variable factors such as the manufacturing process variation is especially challenging because of its unpredictability. In this environment, thread scheduler and global power manager must handle such randomly heterogeneous. Furthermore, these algorithms must supply high efficiency, scalability and low overhead because future multi-core processors may have a number of cores on a single die. This paper presents a variation-aware scheduling algorithm for application scheduling and power management. Thread switching and sampling among different cores in the multi-core processor introduce obvious overhead than previous many-core scheduling algorithms. Proposed scheme records the information of swapped thread of preferential core and uses tabu search-based randomly heterogeneous scheduling algorithm(TSR) to avoid the occurrence of repeated sampling and reduce the migration frequency and sampling frequency of a thread. The experimental results show that TSR algorithm has decreased 45.7% of thread migration and 42.2% of the sampling time as compared with local search algorithm. This paper regards the transcendental Hungarian offline scheduling algorithm as the baseline. ED2 of TSR only decrease by 8.58% as compared with that of Hungarian offline scheduling algorithm, but compared with the random search scheduling algorithm, ED2 of TSR decreased by 39.4%.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122685963","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}
Pub Date : 2016-08-01DOI: 10.1109/FSKD.2016.7603375
Lei Li, Linyuan Wang, Xiaoqi Xi, Bin Yan, Yanmin Sun
Dual Energy Computed Tomography (DECT) has recently gained significantly research interest because of its ability of object separation, contrast enhancement, artifact reduction and material composition assessment. Aiming for the nonlinear projection decomposition problem in DECT image reconstruction, a hybrid projection decomposition algorithm is proposed with combination of iterative method and isotransmission fitting method. Firstly, the nonlinear projection aquation for a given polychromatic projection value is transformed to linear equation plus a nonlinear pertubative item for single variable to speed up the iteration speed and avoid non-convergence. Secondly, a linear approximation fitting model of iso-transmission line is built for high and low energy projection with iso-transmission point pairs solved above. Then the high and low energy projection joint nonlinear solving problem is transformed into solving high and low energy projection iso-transmission line intersection problem, so as to realize the fast decomposition of dual energy projection. Finally, local searching near the intersection of projection matching is used to compensate the error of linear approximation fitting to get more accurate decomposition result. The accuracy and efficiency of the proposed method are demonstrated by numerical simulation.
{"title":"A hybrid projection decomposition algorithm for dual-energy computed tomography","authors":"Lei Li, Linyuan Wang, Xiaoqi Xi, Bin Yan, Yanmin Sun","doi":"10.1109/FSKD.2016.7603375","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603375","url":null,"abstract":"Dual Energy Computed Tomography (DECT) has recently gained significantly research interest because of its ability of object separation, contrast enhancement, artifact reduction and material composition assessment. Aiming for the nonlinear projection decomposition problem in DECT image reconstruction, a hybrid projection decomposition algorithm is proposed with combination of iterative method and isotransmission fitting method. Firstly, the nonlinear projection aquation for a given polychromatic projection value is transformed to linear equation plus a nonlinear pertubative item for single variable to speed up the iteration speed and avoid non-convergence. Secondly, a linear approximation fitting model of iso-transmission line is built for high and low energy projection with iso-transmission point pairs solved above. Then the high and low energy projection joint nonlinear solving problem is transformed into solving high and low energy projection iso-transmission line intersection problem, so as to realize the fast decomposition of dual energy projection. Finally, local searching near the intersection of projection matching is used to compensate the error of linear approximation fitting to get more accurate decomposition result. The accuracy and efficiency of the proposed method are demonstrated by numerical simulation.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122746603","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}
Pub Date : 2016-08-01DOI: 10.1109/FSKD.2016.7603219
Baoxian Jia, Yong Wang, Jinhai Yuan, Jun-qing Li
The classical harmony search (HS) algorithm has been improved. The algorithm effectively prevents it from becoming trapped by a local optimal solution. It allows to be used to deale the shortest-path issue. To solve the shortest route problem, we improved the classical harmony algorithm and seek the optimal solution in the global scope. Second, by the application of the dynamic priority value encoding scheme, we constructed the path based on the priority value of correspondent nodes of variables in the harmonic vector. Through the iterative update of the harmony memory banks, we finally obtained the shortest route. Finally the simulation experiments show us that the proposed algorithm is better than PSO algorithm and HS algorithm on the performance.
{"title":"Solving the shortest-path problem in logistics distribution for vehicle-routing optimization","authors":"Baoxian Jia, Yong Wang, Jinhai Yuan, Jun-qing Li","doi":"10.1109/FSKD.2016.7603219","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603219","url":null,"abstract":"The classical harmony search (HS) algorithm has been improved. The algorithm effectively prevents it from becoming trapped by a local optimal solution. It allows to be used to deale the shortest-path issue. To solve the shortest route problem, we improved the classical harmony algorithm and seek the optimal solution in the global scope. Second, by the application of the dynamic priority value encoding scheme, we constructed the path based on the priority value of correspondent nodes of variables in the harmonic vector. Through the iterative update of the harmony memory banks, we finally obtained the shortest route. Finally the simulation experiments show us that the proposed algorithm is better than PSO algorithm and HS algorithm on the performance.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125144716","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}
Pub Date : 2016-08-01DOI: 10.1109/FSKD.2016.7603486
Hanwu Wang, Liang An, Beibei Yang, Tao Yu
The IEEE 802.16m based broadband wireless access is a promising technology to provide high speed and wide coverage communications for wireless users. However, how to achieve the desired utilization of the radio frequency bandwidth resource in such networks is an open issue as it covers the radio channel capacity exploitation, channel transmission bandwidth utilization optimization and resource utilization scheme performance analysis. In this regarding, we first propose a novel scheme to exploit the maximal channel transmission rate with respect to the time-varying state of each communication channel. Then we construct an efficient channel utilization scheme to fully utilize the channel transmission bandwidth according to the user's performance requirements. Next we also present an analytical scheme to analyze the performance of the channel usage scheme regarding various performance metrics. Experiment results validate the superiority of the proposed utilization scheme.
{"title":"An optimal bandwidth resource utilization scheme in IEEE 802.16m communication networks","authors":"Hanwu Wang, Liang An, Beibei Yang, Tao Yu","doi":"10.1109/FSKD.2016.7603486","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603486","url":null,"abstract":"The IEEE 802.16m based broadband wireless access is a promising technology to provide high speed and wide coverage communications for wireless users. However, how to achieve the desired utilization of the radio frequency bandwidth resource in such networks is an open issue as it covers the radio channel capacity exploitation, channel transmission bandwidth utilization optimization and resource utilization scheme performance analysis. In this regarding, we first propose a novel scheme to exploit the maximal channel transmission rate with respect to the time-varying state of each communication channel. Then we construct an efficient channel utilization scheme to fully utilize the channel transmission bandwidth according to the user's performance requirements. Next we also present an analytical scheme to analyze the performance of the channel usage scheme regarding various performance metrics. Experiment results validate the superiority of the proposed utilization scheme.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125302244","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}
Pub Date : 2016-08-01DOI: 10.1109/FSKD.2016.7603479
H. Wang
Separating the high resolution remote sensing images is a difficult problem in the relative research field of image processing and remote sensing. A novel model of separating the high resolution remote sensing images is proposed based on sparse representation, different dictionary which has an efficient indication of different content of remote sensing image is obtained based on dictionary learning algorithm according to the characteristics of the high spatial resolution remote sensing images, separating by SSF algorithm. After experimental, it is showed that the algorithm can separate features of remote sensing images better, and it is more robust.
{"title":"The separation of high resolution remote sensing images based on dictionary learning","authors":"H. Wang","doi":"10.1109/FSKD.2016.7603479","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603479","url":null,"abstract":"Separating the high resolution remote sensing images is a difficult problem in the relative research field of image processing and remote sensing. A novel model of separating the high resolution remote sensing images is proposed based on sparse representation, different dictionary which has an efficient indication of different content of remote sensing image is obtained based on dictionary learning algorithm according to the characteristics of the high spatial resolution remote sensing images, separating by SSF algorithm. After experimental, it is showed that the algorithm can separate features of remote sensing images better, and it is more robust.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125394881","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}
Pub Date : 2016-08-01DOI: 10.1109/FSKD.2016.7603174
Shengyu Pei, Lang Tong
As the K-means algorithm is dependent on the initial clustering center, and the particle swarm optimization (PSO) converges prematurely and is easily trapped in local minima, a Gaussian kernel particle swarm optimization clustering algorithm is proposed in this paper. The algorithm adopts the theory of good point set to initialize population, which makes the initial clustering center more rational. Particle swarm iteration formula was optimized by using Gaussian kernel method, which makes particle swarm algorithm converge rapidly to the global optimal. By testing 23 UCI data sets, the experimental results show that the clustering effect of the proposed algorithm is better than that of the K-means and the traditional particle swarm optimization clustering algorithm.
{"title":"Gaussian kernel particle swarm optimization clustering algorithm","authors":"Shengyu Pei, Lang Tong","doi":"10.1109/FSKD.2016.7603174","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603174","url":null,"abstract":"As the K-means algorithm is dependent on the initial clustering center, and the particle swarm optimization (PSO) converges prematurely and is easily trapped in local minima, a Gaussian kernel particle swarm optimization clustering algorithm is proposed in this paper. The algorithm adopts the theory of good point set to initialize population, which makes the initial clustering center more rational. Particle swarm iteration formula was optimized by using Gaussian kernel method, which makes particle swarm algorithm converge rapidly to the global optimal. By testing 23 UCI data sets, the experimental results show that the clustering effect of the proposed algorithm is better than that of the K-means and the traditional particle swarm optimization clustering algorithm.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"125 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126274833","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}
Pub Date : 2016-08-01DOI: 10.1109/FSKD.2016.7603404
Umutoni Nadine, Huiying Cao, Jiangzhou Deng
Collaborative filtering (CF) is commonly used and successful techniques in recommendation systems (RS) but it has showed some problems like sparsity and cold start. Different techniques are employed to overcome the collaborative problems but there is no one single algorithm which can satisfy the personalized needs of each user. This paper presents a new hybrid recommendation approach to improve the effectiveness through the competition process among a series of algorithms. Experiment has been conducted on MovieLens to verify our proposed approach. The results indicate that our approach enabled more efficient and stable recommendation than single method.
{"title":"Competitive recommendation algorithm for E-commerce","authors":"Umutoni Nadine, Huiying Cao, Jiangzhou Deng","doi":"10.1109/FSKD.2016.7603404","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603404","url":null,"abstract":"Collaborative filtering (CF) is commonly used and successful techniques in recommendation systems (RS) but it has showed some problems like sparsity and cold start. Different techniques are employed to overcome the collaborative problems but there is no one single algorithm which can satisfy the personalized needs of each user. This paper presents a new hybrid recommendation approach to improve the effectiveness through the competition process among a series of algorithms. Experiment has been conducted on MovieLens to verify our proposed approach. The results indicate that our approach enabled more efficient and stable recommendation than single method.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125737518","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}
This paper is concerned with finding the k shortest routes or paths in a network where each node has some specific time windows only within which is the node accessible. Because of such time windows at nodes, classical methods for the k shortest paths problem (k-SPP) is not applicable to the k shortest paths problem in a time-window network (k-SPPTW). Taking inspiration from the natural ripple-spreading phenomenon, we propose a novel ripple-spreading algorithm (RSA) for the k-SPPTW. By conducting a purpose-designed ripple relay race in a time-window network, the reported RSA can resolve not only one-to-one k-SPPTW, but also one-to-all k-SPPTW, where all the k shortest paths from a given source node to every other node in the network need to be found. The computational complexity of RSA is just 0(k×NATU×NL), where NL is the number of links in the network, and NATU is the average simulated time units for a ripple to travel through a link. Experimental results demonstrate the effectiveness and efficiency of the proposed RSA for the k-SPPTW.
{"title":"A ripple-spreading algorithm to calculate the k shortest paths in a network with time-windows","authors":"Xiao-Bing Hu, Ming-Kong Zhang, Jian-Qin Liao, Hailin Zhang","doi":"10.1109/FSKD.2016.7603203","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603203","url":null,"abstract":"This paper is concerned with finding the k shortest routes or paths in a network where each node has some specific time windows only within which is the node accessible. Because of such time windows at nodes, classical methods for the k shortest paths problem (k-SPP) is not applicable to the k shortest paths problem in a time-window network (k-SPPTW). Taking inspiration from the natural ripple-spreading phenomenon, we propose a novel ripple-spreading algorithm (RSA) for the k-SPPTW. By conducting a purpose-designed ripple relay race in a time-window network, the reported RSA can resolve not only one-to-one k-SPPTW, but also one-to-all k-SPPTW, where all the k shortest paths from a given source node to every other node in the network need to be found. The computational complexity of RSA is just 0(k×NATU×NL), where NL is the number of links in the network, and NATU is the average simulated time units for a ripple to travel through a link. Experimental results demonstrate the effectiveness and efficiency of the proposed RSA for the k-SPPTW.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125901411","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}
Pub Date : 2016-08-01DOI: 10.1109/FSKD.2016.7603487
Chunting Yan, Shujuan Wang
On-demand data broadcast has been broadly utilized In wireless communication networks. With the rapid increase of on-demand data dissemination services in burgeoning applications, clients are not satisfied with one data item per request but turn to multiple data item per request, while most of the existing scheduling algorithms focus on single-item request environment. In this work, we lucubrate the performance of the original scheduling algorithms that are proposed for single-item request based on network coding in multi-item request circumstances. The simulations come out that more hot data requested and larger cache size have positive effects on the performance of average access time and deadline miss ratio.
{"title":"Evaluations of network coding-based scheduling approach for wireless data disseminations with time constraints","authors":"Chunting Yan, Shujuan Wang","doi":"10.1109/FSKD.2016.7603487","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603487","url":null,"abstract":"On-demand data broadcast has been broadly utilized In wireless communication networks. With the rapid increase of on-demand data dissemination services in burgeoning applications, clients are not satisfied with one data item per request but turn to multiple data item per request, while most of the existing scheduling algorithms focus on single-item request environment. In this work, we lucubrate the performance of the original scheduling algorithms that are proposed for single-item request based on network coding in multi-item request circumstances. The simulations come out that more hot data requested and larger cache size have positive effects on the performance of average access time and deadline miss ratio.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"293 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126019313","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}
Pub Date : 2016-08-01DOI: 10.1109/FSKD.2016.7603442
Humaid Alshamsi, H. Meng, Maozhen Li
Facial expression has made significant progress in recent years with many commercial systems are available for real-world applications. It gains strong interest to implement a facial expression system on a portable device such as tablet and smart phone device using the camera already integrated in the devices. It is very common to see face recognition phone unlocking app in new smart phones which are proven to be hassle free way to unlock a phone. Implementation a facial expression system in a smart phone would provide fun applications that can be used to measure the mood of the user in their daily life or as a tool for their daily monitoring of the motion in phycology studies. However, traditional facial expression algorithms are normally computing extensive and can only be implemented offline at a computer. In this paper, a novel automatic system has been proposed to recognize emotions from face images on a smart phone in real-time. In our system, the camera of the smart phone is used to capture the face image, BRIEF features are extracted and k-nearest neighbor algorithm is implemented for the classification. The experimental results demonstrate that the proposed facial expression recognition on mobile phone is successful and it gives up to 89.5% recognition accuracy.
{"title":"Real time facial expression recognition app development on mobile phones","authors":"Humaid Alshamsi, H. Meng, Maozhen Li","doi":"10.1109/FSKD.2016.7603442","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603442","url":null,"abstract":"Facial expression has made significant progress in recent years with many commercial systems are available for real-world applications. It gains strong interest to implement a facial expression system on a portable device such as tablet and smart phone device using the camera already integrated in the devices. It is very common to see face recognition phone unlocking app in new smart phones which are proven to be hassle free way to unlock a phone. Implementation a facial expression system in a smart phone would provide fun applications that can be used to measure the mood of the user in their daily life or as a tool for their daily monitoring of the motion in phycology studies. However, traditional facial expression algorithms are normally computing extensive and can only be implemented offline at a computer. In this paper, a novel automatic system has been proposed to recognize emotions from face images on a smart phone in real-time. In our system, the camera of the smart phone is used to capture the face image, BRIEF features are extracted and k-nearest neighbor algorithm is implemented for the classification. The experimental results demonstrate that the proposed facial expression recognition on mobile phone is successful and it gives up to 89.5% recognition accuracy.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129723652","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：