Pub Date : 2016-10-01DOI: 10.1109/COMPCOMM.2016.7924773
Da Zhang, Songyang Lao, Kang Lai, Liang Bai
In recent years, a wide range of computer vision applications have relied upon superpixel. In an effort to generate superpixel segmentation for RGB-D images, we present a new efficient framework which combines color and spatial features and makes use of depth information as far as possible. It is performed by defining a measurement for the point cloud computed from depth map and distance between vertex normal. We use the distance of voxels to distinguish objects on depth map and use normal map to separate planes in the object. In this way, our method is able to generate superpixels both edge compact and plane fitting. Then we compare our proposed method with six state-of-the-art superpixel algorithms by considering their ability to adhere to image boundaries. The comparisons demonstrate that the performance of our method based on linear iterative clustering (SLIC) algorithm is superior to the most recent superpixel methods.
{"title":"A superpixel method using 3-D geometry and normal priori information for RGB-D data","authors":"Da Zhang, Songyang Lao, Kang Lai, Liang Bai","doi":"10.1109/COMPCOMM.2016.7924773","DOIUrl":"https://doi.org/10.1109/COMPCOMM.2016.7924773","url":null,"abstract":"In recent years, a wide range of computer vision applications have relied upon superpixel. In an effort to generate superpixel segmentation for RGB-D images, we present a new efficient framework which combines color and spatial features and makes use of depth information as far as possible. It is performed by defining a measurement for the point cloud computed from depth map and distance between vertex normal. We use the distance of voxels to distinguish objects on depth map and use normal map to separate planes in the object. In this way, our method is able to generate superpixels both edge compact and plane fitting. Then we compare our proposed method with six state-of-the-art superpixel algorithms by considering their ability to adhere to image boundaries. The comparisons demonstrate that the performance of our method based on linear iterative clustering (SLIC) algorithm is superior to the most recent superpixel methods.","PeriodicalId":210833,"journal":{"name":"2016 2nd IEEE International Conference on Computer and Communications (ICCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114768115","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 : 2016-10-01DOI: 10.1109/COMPCOMM.2016.7925042
Jun Guo, Shuying Yang
The process of voice generation belongs to nonlinear system, and the voice signal is chaotic. The traditional Volterra model is generally 2 order truncation, a low order filter is used to estimate the speech signal, and prediction effect is not accurate. So, this paper proposes a feature extraction scheme based on the wavelet packet decomposition and Volterra adaptive model. Firstly, the speech signal will be decomposed by wavelet packet. Secondly, reconstruct the phase space for all sub-band signals. Thirdly, using second order Volterra series expansion and the linear adaptive FIR filter to estimate parameter vector H(n) and output signal U(n) for Volterra model, and weight vectors of Volterra filter are obtained for speaker recognition. Speaker recognition experiment is completed based on hidden Markov model. The experimental results show the extracted features have been obviously improved, especially in the noise environment.
{"title":"Speaker recognition based on wavelet packet decomposition and Volterra adaptive model","authors":"Jun Guo, Shuying Yang","doi":"10.1109/COMPCOMM.2016.7925042","DOIUrl":"https://doi.org/10.1109/COMPCOMM.2016.7925042","url":null,"abstract":"The process of voice generation belongs to nonlinear system, and the voice signal is chaotic. The traditional Volterra model is generally 2 order truncation, a low order filter is used to estimate the speech signal, and prediction effect is not accurate. So, this paper proposes a feature extraction scheme based on the wavelet packet decomposition and Volterra adaptive model. Firstly, the speech signal will be decomposed by wavelet packet. Secondly, reconstruct the phase space for all sub-band signals. Thirdly, using second order Volterra series expansion and the linear adaptive FIR filter to estimate parameter vector H(n) and output signal U(n) for Volterra model, and weight vectors of Volterra filter are obtained for speaker recognition. Speaker recognition experiment is completed based on hidden Markov model. The experimental results show the extracted features have been obviously improved, especially in the noise environment.","PeriodicalId":210833,"journal":{"name":"2016 2nd IEEE International Conference on Computer and Communications (ICCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114981398","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 : 2016-10-01DOI: 10.1109/COMPCOMM.2016.7924680
Yaping Zhong, Weihong Hu
It is a lack of in-depth study on the comprehensive information services and assessment in the national physical fitness and the National Fitness Program. A WebGIS-based interactive platform was designed to collect and analyze national physical fitness-related indicators such as data from the National Fitness Program and the geographical and humanistic environments. Seven functional modules were designed for the platform. The core functional module of the platform is the analysis and evaluation subsystem. Five evaluation models were provided. Based on the canonical correlation analysis method, the internal relations were explored among the national physical fitness, the National Fitness Program, and the geographical and humanistic environment factors. This study provides a new approach for the analysis and evaluation of the national physical fitness monitoring data, as well as a reference for the future development of the National Fitness Program.
{"title":"The research on WebGIS-based information integration and data analysis platform for China's Physical Fitness and the National Fitness Program","authors":"Yaping Zhong, Weihong Hu","doi":"10.1109/COMPCOMM.2016.7924680","DOIUrl":"https://doi.org/10.1109/COMPCOMM.2016.7924680","url":null,"abstract":"It is a lack of in-depth study on the comprehensive information services and assessment in the national physical fitness and the National Fitness Program. A WebGIS-based interactive platform was designed to collect and analyze national physical fitness-related indicators such as data from the National Fitness Program and the geographical and humanistic environments. Seven functional modules were designed for the platform. The core functional module of the platform is the analysis and evaluation subsystem. Five evaluation models were provided. Based on the canonical correlation analysis method, the internal relations were explored among the national physical fitness, the National Fitness Program, and the geographical and humanistic environment factors. This study provides a new approach for the analysis and evaluation of the national physical fitness monitoring data, as well as a reference for the future development of the National Fitness Program.","PeriodicalId":210833,"journal":{"name":"2016 2nd IEEE International Conference on Computer and Communications (ICCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123432694","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 : 2016-10-01DOI: 10.1109/COMPCOMM.2016.7924845
Le Wei, Wei Wang, Z. Sheng, Wenqing Liu
According to the demand of credibility for the application software in the dynamic environment, the component technology is introduced into the development of the trusted service software to improve the software quality and development efficiency. Firstly, the basic idea to ensure the component credibility is described. Then an adaptive trusted component model is given and described in this paper. And subsequently an adaptive supporting framework is proposed. The framework can ensure the reliable performance of the component, can adjust the structure and behavior of the component depending on the change of runtime context adaptively, and can meet the needs of the upper application. Finally, the adaptive adjustment process of components is given based on the proposed model and framework.
{"title":"Trusted component model and supporting framework based on adaptive mechanism","authors":"Le Wei, Wei Wang, Z. Sheng, Wenqing Liu","doi":"10.1109/COMPCOMM.2016.7924845","DOIUrl":"https://doi.org/10.1109/COMPCOMM.2016.7924845","url":null,"abstract":"According to the demand of credibility for the application software in the dynamic environment, the component technology is introduced into the development of the trusted service software to improve the software quality and development efficiency. Firstly, the basic idea to ensure the component credibility is described. Then an adaptive trusted component model is given and described in this paper. And subsequently an adaptive supporting framework is proposed. The framework can ensure the reliable performance of the component, can adjust the structure and behavior of the component depending on the change of runtime context adaptively, and can meet the needs of the upper application. Finally, the adaptive adjustment process of components is given based on the proposed model and framework.","PeriodicalId":210833,"journal":{"name":"2016 2nd IEEE International Conference on Computer and Communications (ICCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123500194","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 : 2016-10-01DOI: 10.1109/COMPCOMM.2016.7924918
Ning Pan, Zhiqiang Zhu, Liangsheng He, Lei Sun, Hang Su
Role Based Access Control (RBAC) has become the de facto access control model in recent years. In order to deploy RBAC, organizations have to define a set of roles from the existing user-permission assignment relationships, the process of which is called role mining. There have been many role mining algorithms proposed to devise a complete and correct set of roles which may not be very important because the user-permission assignment relationships are dynamic. This paper defines the δ-Approx Important Role Mining Problem (d-IRMP) which is proved to be NP-complete and proposes a heuristic bottom-up role mining algorithm that reduces the total number of roles with important assignments preserved at first. Furthermore, experiments were carried out with publicly available datasets to evaluate the approach and the results compared with other algorithms demonstrate the effectiveness of the proposed algorithm.
{"title":"Mining approximate roles under important assignment","authors":"Ning Pan, Zhiqiang Zhu, Liangsheng He, Lei Sun, Hang Su","doi":"10.1109/COMPCOMM.2016.7924918","DOIUrl":"https://doi.org/10.1109/COMPCOMM.2016.7924918","url":null,"abstract":"Role Based Access Control (RBAC) has become the de facto access control model in recent years. In order to deploy RBAC, organizations have to define a set of roles from the existing user-permission assignment relationships, the process of which is called role mining. There have been many role mining algorithms proposed to devise a complete and correct set of roles which may not be very important because the user-permission assignment relationships are dynamic. This paper defines the δ-Approx Important Role Mining Problem (d-IRMP) which is proved to be NP-complete and proposes a heuristic bottom-up role mining algorithm that reduces the total number of roles with important assignments preserved at first. Furthermore, experiments were carried out with publicly available datasets to evaluate the approach and the results compared with other algorithms demonstrate the effectiveness of the proposed algorithm.","PeriodicalId":210833,"journal":{"name":"2016 2nd IEEE International Conference on Computer and Communications (ICCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121963534","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}
Advanced Audio Coding (AAC) is adopted by the Digital Audio Broadcasting plus (DAB+) system, which is the upgraded version of DAB. The increasing demand of the portable DAB+ receivers requires low-cost, low-power DAB+ baseband chip. This brings the demand of hardware-architecture AAC decoders. This paper reports a hardware implementation of the Temporal Noise Shaping (TNS) decoder, which is an important tool in AAC to eliminate the pre-echo phenomenon. The proposed TNS decoder shares the process unit with other AAC blocks to save silicon area, and uses gated clock to reduce power consumption. The design consumes only 516 logic elements and 64*18 bits ROM. It has been integrated in a DAB+ baseband chip and works well for several DAB+ receivers.
{"title":"Hardware implementation of the Temporal Noise Shaping decoder for DAB+ baseband chip","authors":"Hongsheng Zhang, Guoyu Wang, Mingying Lu, Renyi Zhu","doi":"10.1109/COMPCOMM.2016.7925085","DOIUrl":"https://doi.org/10.1109/COMPCOMM.2016.7925085","url":null,"abstract":"Advanced Audio Coding (AAC) is adopted by the Digital Audio Broadcasting plus (DAB+) system, which is the upgraded version of DAB. The increasing demand of the portable DAB+ receivers requires low-cost, low-power DAB+ baseband chip. This brings the demand of hardware-architecture AAC decoders. This paper reports a hardware implementation of the Temporal Noise Shaping (TNS) decoder, which is an important tool in AAC to eliminate the pre-echo phenomenon. The proposed TNS decoder shares the process unit with other AAC blocks to save silicon area, and uses gated clock to reduce power consumption. The design consumes only 516 logic elements and 64*18 bits ROM. It has been integrated in a DAB+ baseband chip and works well for several DAB+ receivers.","PeriodicalId":210833,"journal":{"name":"2016 2nd IEEE International Conference on Computer and Communications (ICCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122081714","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 : 2016-10-01DOI: 10.1109/COMPCOMM.2016.7924724
Borui Zhang, Guangyuan Liu, Guoqiang Xie
In this paper, a novel facial expression recognition method using local binary pattern (LBP) and local phase quantization (LPQ) based on Gabor face image is proposed. To capture the salient visual properties, the Gabor filter is firstly adopted to extract features of the face image among five scales and eight orientations. Then the Gabor image is encoded by the LBP operator and LPQ operator, respectively. Two-stage principal component analysis and linear discriminant analysis (PCA-LDA) approach are used to reduce the dimension of the fused feature combined by the Gabor LBP feature and Gabor LPQ feature. In the experiment, the classification is done by the multi-class SVM classifiers based on the Japanese female facial expression (JAFFE) database. The result shows that the proposed method outperforms many other approaches in this paper in terms of accuracy.
{"title":"Facial expression recognition using LBP and LPQ based on Gabor wavelet transform","authors":"Borui Zhang, Guangyuan Liu, Guoqiang Xie","doi":"10.1109/COMPCOMM.2016.7924724","DOIUrl":"https://doi.org/10.1109/COMPCOMM.2016.7924724","url":null,"abstract":"In this paper, a novel facial expression recognition method using local binary pattern (LBP) and local phase quantization (LPQ) based on Gabor face image is proposed. To capture the salient visual properties, the Gabor filter is firstly adopted to extract features of the face image among five scales and eight orientations. Then the Gabor image is encoded by the LBP operator and LPQ operator, respectively. Two-stage principal component analysis and linear discriminant analysis (PCA-LDA) approach are used to reduce the dimension of the fused feature combined by the Gabor LBP feature and Gabor LPQ feature. In the experiment, the classification is done by the multi-class SVM classifiers based on the Japanese female facial expression (JAFFE) database. The result shows that the proposed method outperforms many other approaches in this paper in terms of accuracy.","PeriodicalId":210833,"journal":{"name":"2016 2nd IEEE International Conference on Computer and Communications (ICCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116806327","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 : 2016-10-01DOI: 10.1109/COMPCOMM.2016.7924865
Qing-bin Luo, Guowu Yang, Kun She, Xiaoyu Li, Yu-qi Wang
In this paper, a novel scheme for quantum homomorphic signature based on coherent states is proposed, which is an effective approach to identity authentication for multiple streams to enhance the security of quantum networks. The state used for signature are arbitrarily close in trace distance to states of O(log2n), if the length of the nodes' messages is n-bit. The scheme analysis shows that the scheme is a quantum group homomorphic signature scheme and the signature is unforgeable.
{"title":"Quantum homomorphic signature using coherent states","authors":"Qing-bin Luo, Guowu Yang, Kun She, Xiaoyu Li, Yu-qi Wang","doi":"10.1109/COMPCOMM.2016.7924865","DOIUrl":"https://doi.org/10.1109/COMPCOMM.2016.7924865","url":null,"abstract":"In this paper, a novel scheme for quantum homomorphic signature based on coherent states is proposed, which is an effective approach to identity authentication for multiple streams to enhance the security of quantum networks. The state used for signature are arbitrarily close in trace distance to states of O(log2n), if the length of the nodes' messages is n-bit. The scheme analysis shows that the scheme is a quantum group homomorphic signature scheme and the signature is unforgeable.","PeriodicalId":210833,"journal":{"name":"2016 2nd IEEE International Conference on Computer and Communications (ICCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123964434","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 : 2016-10-01DOI: 10.1109/COMPCOMM.2016.7924936
Xiaohan Zhang, Z. Jin
With its high market share, the Android platform has become a growing target for mobile malware, which posed great threat to customers' safety. Meanwhile, malwares employed various techniques, take code obfuscation for example, to evade detection. The commercial mobile anti-malware products, however, are vulnerable to common code transformation techniques. This paper proposes an enhanced malware detection approach which combines advantage of static analysis and performance of ensemble learning to improve Android malware detection accuracy. The model extracts semantics-based features which can resist common obfuscation techniques, and also uses feature collection from code and app characteristics through static analysis. Real-world malware samples are used to evaluate the model and the results of experiments have proved that this approach improved the efficiency with AUC of 2.06% higher than previous approach.
{"title":"A new semantics-based android malware detection","authors":"Xiaohan Zhang, Z. Jin","doi":"10.1109/COMPCOMM.2016.7924936","DOIUrl":"https://doi.org/10.1109/COMPCOMM.2016.7924936","url":null,"abstract":"With its high market share, the Android platform has become a growing target for mobile malware, which posed great threat to customers' safety. Meanwhile, malwares employed various techniques, take code obfuscation for example, to evade detection. The commercial mobile anti-malware products, however, are vulnerable to common code transformation techniques. This paper proposes an enhanced malware detection approach which combines advantage of static analysis and performance of ensemble learning to improve Android malware detection accuracy. The model extracts semantics-based features which can resist common obfuscation techniques, and also uses feature collection from code and app characteristics through static analysis. Real-world malware samples are used to evaluate the model and the results of experiments have proved that this approach improved the efficiency with AUC of 2.06% higher than previous approach.","PeriodicalId":210833,"journal":{"name":"2016 2nd IEEE International Conference on Computer and Communications (ICCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125925821","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 : 2016-10-01DOI: 10.1109/COMPCOMM.2016.7924731
Honglei Wei, Danni Peng, Xufei Zhu, Dongdong Wu
For capturing sea cucumber in the sea, an object tracking method based on Mean-Shift algorithm was proposed. Firstly, defogging algorithm was used to get restored image, and the feature of color histogram was extracted from the restored image. Then the local image was cropped at the same position and local area in the second frame. Mean-Shift algorithm was used to search the feature of color histogram in cropped area. Finally, tracking was realized by searching the searching process converged in the next frames one by one. Compared with the color histogram Mean-Shift algorithm (CHMS) algorithm, the proposed algorithm have better tracking performance and robustness.
{"title":"A target tracking algorithm for vision based sea cucumber capture","authors":"Honglei Wei, Danni Peng, Xufei Zhu, Dongdong Wu","doi":"10.1109/COMPCOMM.2016.7924731","DOIUrl":"https://doi.org/10.1109/COMPCOMM.2016.7924731","url":null,"abstract":"For capturing sea cucumber in the sea, an object tracking method based on Mean-Shift algorithm was proposed. Firstly, defogging algorithm was used to get restored image, and the feature of color histogram was extracted from the restored image. Then the local image was cropped at the same position and local area in the second frame. Mean-Shift algorithm was used to search the feature of color histogram in cropped area. Finally, tracking was realized by searching the searching process converged in the next frames one by one. Compared with the color histogram Mean-Shift algorithm (CHMS) algorithm, the proposed algorithm have better tracking performance and robustness.","PeriodicalId":210833,"journal":{"name":"2016 2nd IEEE International Conference on Computer and Communications (ICCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129428747","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：