Pub Date : 2015-05-25DOI: 10.1109/ICAIOT.2015.7111524
Yuming Hua, Junhai Guo, Hua Zhao
Deep Belief Network is an algorithm among deep learning. It is an effective method of solving the problems from neural network with deep layers, such as low velocity and the overfitting phenomenon in learning. In this paper, we will introduce how to process a Deep Belief Network by using Restricted Boltzmann Machines. What is more, we will combine the Deep Belief Network together with softmax classifier, and use it in the recognition of handwritten numbers.
{"title":"Deep Belief Networks and deep learning","authors":"Yuming Hua, Junhai Guo, Hua Zhao","doi":"10.1109/ICAIOT.2015.7111524","DOIUrl":"https://doi.org/10.1109/ICAIOT.2015.7111524","url":null,"abstract":"Deep Belief Network is an algorithm among deep learning. It is an effective method of solving the problems from neural network with deep layers, such as low velocity and the overfitting phenomenon in learning. In this paper, we will introduce how to process a Deep Belief Network by using Restricted Boltzmann Machines. What is more, we will combine the Deep Belief Network together with softmax classifier, and use it in the recognition of handwritten numbers.","PeriodicalId":310429,"journal":{"name":"Proceedings of 2015 International Conference on Intelligent Computing and Internet of Things","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117229953","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 : 2015-05-25DOI: 10.1109/ICAIOT.2015.7111535
Kert Pjatkin, M. Daneshmand, P. Rasti, G. Anbarjafari
In this work, a new iris recognition algorithm based on tonal distribution of iris images is introduced. During the process of identification probability distribution functions of colored irises are generated in HSI and YCbCr color spaces. The discrimination between classes is obtained by using Kullback-Leibler divergence. In order to obtain the final decision on recognition, the multi decision on various color channels has been combined by employing mean rule. The decisions of H, S, Y, Cb and Cr color channels have been combined. The proposed technique overcome the conventional principle component analysis technique and achieved a recognition rate of 100% using the UPOL database. The major advantage is the fact that it is computationally less complex than the Daugman's algorithm and it is suitable for using visible light camera as opposed to the one proposed by Daugman where NIR cameras are used for obtaining the irises.
本文提出了一种基于虹膜图像色调分布的虹膜识别算法。在识别过程中，在HSI和YCbCr颜色空间中生成彩色虹膜的概率分布函数。利用Kullback-Leibler散度得到了类间判别。为了得到最终的识别决策，采用均值规则对不同颜色通道的多决策进行组合。H, S, Y, Cb和Cr颜色通道的决定被合并。该方法克服了传统的主成分分析方法，利用UPOL数据库实现了100%的识别率。该方法的主要优点是计算复杂度低于道格曼算法，并且适合于使用可见光相机，而不是道格曼提出的使用近红外相机获取虹膜的方法。
{"title":"Probability distribution function based iris recognition boosted by the mean rule","authors":"Kert Pjatkin, M. Daneshmand, P. Rasti, G. Anbarjafari","doi":"10.1109/ICAIOT.2015.7111535","DOIUrl":"https://doi.org/10.1109/ICAIOT.2015.7111535","url":null,"abstract":"In this work, a new iris recognition algorithm based on tonal distribution of iris images is introduced. During the process of identification probability distribution functions of colored irises are generated in HSI and YCbCr color spaces. The discrimination between classes is obtained by using Kullback-Leibler divergence. In order to obtain the final decision on recognition, the multi decision on various color channels has been combined by employing mean rule. The decisions of H, S, Y, Cb and Cr color channels have been combined. The proposed technique overcome the conventional principle component analysis technique and achieved a recognition rate of 100% using the UPOL database. The major advantage is the fact that it is computationally less complex than the Daugman's algorithm and it is suitable for using visible light camera as opposed to the one proposed by Daugman where NIR cameras are used for obtaining the irises.","PeriodicalId":310429,"journal":{"name":"Proceedings of 2015 International Conference on Intelligent Computing and Internet of Things","volume":"204 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128781760","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 : 2015-05-25DOI: 10.1109/ICAIOT.2015.7111540
Hui‐Jie Sun
Image segmentation is one of the key technologies in image processing, image segmentation quality relates to subsequent processing directly such as image measurement and image recognition, etc. This paper presents a new intelligent optimization algorithm: (artificial fish swarm algorithm, artificial bacterial swarm algorithm and artificial bee colony swarm algorithm), a new method of image segmentation, namely the wavelet transform for segmented images, combined with gray-scale morphology and rough sets theory to solve the problem of image noise, uses a new intelligent optimization algorithm to improve the effect of segmentation, the segmentation performance better, faster, and has important theoretical significance and practical value.
{"title":"Image segmentation algorithm based on swarm intelligence technology","authors":"Hui‐Jie Sun","doi":"10.1109/ICAIOT.2015.7111540","DOIUrl":"https://doi.org/10.1109/ICAIOT.2015.7111540","url":null,"abstract":"Image segmentation is one of the key technologies in image processing, image segmentation quality relates to subsequent processing directly such as image measurement and image recognition, etc. This paper presents a new intelligent optimization algorithm: (artificial fish swarm algorithm, artificial bacterial swarm algorithm and artificial bee colony swarm algorithm), a new method of image segmentation, namely the wavelet transform for segmented images, combined with gray-scale morphology and rough sets theory to solve the problem of image noise, uses a new intelligent optimization algorithm to improve the effect of segmentation, the segmentation performance better, faster, and has important theoretical significance and practical value.","PeriodicalId":310429,"journal":{"name":"Proceedings of 2015 International Conference on Intelligent Computing and Internet of Things","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128709067","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 : 2015-05-25DOI: 10.1109/ICAIOT.2015.7111549
Chang Huiyou, Li-guo Hao, H. Yongjun
In this paper, an improved pork freshness detecting method based on digital image processing and BP neutral network was presented. The shape of the slaughtering fresh pork cell was oval and smooth and it will change obviously in the process of pork corruption. The edge of cell will rupture and merge together until being absolutely misshapen. Seven characteristic parameters about cell shape would be extracted to stand for the level of corruption. And designs then correspond to the pork freshness standard TVB-N and characteristic parameters finally trained by BP neural network. The experimental results showed that the characteristic parameter about cell shape could detect the freshness effectively.
{"title":"An intelligent method of detecting pork freshness based on digital image processing","authors":"Chang Huiyou, Li-guo Hao, H. Yongjun","doi":"10.1109/ICAIOT.2015.7111549","DOIUrl":"https://doi.org/10.1109/ICAIOT.2015.7111549","url":null,"abstract":"In this paper, an improved pork freshness detecting method based on digital image processing and BP neutral network was presented. The shape of the slaughtering fresh pork cell was oval and smooth and it will change obviously in the process of pork corruption. The edge of cell will rupture and merge together until being absolutely misshapen. Seven characteristic parameters about cell shape would be extracted to stand for the level of corruption. And designs then correspond to the pork freshness standard TVB-N and characteristic parameters finally trained by BP neural network. The experimental results showed that the characteristic parameter about cell shape could detect the freshness effectively.","PeriodicalId":310429,"journal":{"name":"Proceedings of 2015 International Conference on Intelligent Computing and Internet of Things","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122988728","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 : 2015-05-25DOI: 10.1109/ICAIOT.2015.7111548
Chen-xi Gou, Bai-gen Cai, Yang Miao
Multi-resolution modeling (MRM) could describe a real system as a set of models of different resolutions. By doing this, real system could be analyzed at different abstraction levels for different simulation objectives. MRM is a useful method for complex and large-scale simulation. Since there are different models of the same object created for different purpose, consistency of the models should be considered for abnormal situation during model simulation. To maintain consistency of multi-resolution models, outputs of different models with same inputs could be mapped into a certain fields for comparison. Ontology mapping method was adopted for information process. For inconsistency situation, consistency maintenance procedure was proposed to ensure consistency of models during simulation.
{"title":"Multi-resolution model consistency maintenance method based on ontology mapping","authors":"Chen-xi Gou, Bai-gen Cai, Yang Miao","doi":"10.1109/ICAIOT.2015.7111548","DOIUrl":"https://doi.org/10.1109/ICAIOT.2015.7111548","url":null,"abstract":"Multi-resolution modeling (MRM) could describe a real system as a set of models of different resolutions. By doing this, real system could be analyzed at different abstraction levels for different simulation objectives. MRM is a useful method for complex and large-scale simulation. Since there are different models of the same object created for different purpose, consistency of the models should be considered for abnormal situation during model simulation. To maintain consistency of multi-resolution models, outputs of different models with same inputs could be mapped into a certain fields for comparison. Ontology mapping method was adopted for information process. For inconsistency situation, consistency maintenance procedure was proposed to ensure consistency of models during simulation.","PeriodicalId":310429,"journal":{"name":"Proceedings of 2015 International Conference on Intelligent Computing and Internet of Things","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131504388","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 : 2015-05-25DOI: 10.1109/ICAIOT.2015.7111537
Chujian Bi, Qiushi Zhang, Rui Bao, Haoxiang Wang
In this paper, a novel unsupervised change detection algorithm based on game theory is proposed for synthetic aperture radar(SAR) images. With the introduction of Nash-game theory, we find the balance of segmentation accuracy and overall restoration performance. Restoration of images plays a denoising role due to the complex movement while obtaining a SAR image. The Segmentation procedure transfers the difference map into change map. To make the algorithm less time-consuming, we analyze the state-of-the-art methods for generating the change map and finally select the minus map as the preferred one. The experiment based on the proposed methodology proves the accuracy and robustness of our algorithm compared with several well-known change detection techniques on both noise-free and noisy satellite images. Further optimization methods are discussed in the end.
{"title":"SAR image restoration and change detection based on game theory","authors":"Chujian Bi, Qiushi Zhang, Rui Bao, Haoxiang Wang","doi":"10.1109/ICAIOT.2015.7111537","DOIUrl":"https://doi.org/10.1109/ICAIOT.2015.7111537","url":null,"abstract":"In this paper, a novel unsupervised change detection algorithm based on game theory is proposed for synthetic aperture radar(SAR) images. With the introduction of Nash-game theory, we find the balance of segmentation accuracy and overall restoration performance. Restoration of images plays a denoising role due to the complex movement while obtaining a SAR image. The Segmentation procedure transfers the difference map into change map. To make the algorithm less time-consuming, we analyze the state-of-the-art methods for generating the change map and finally select the minus map as the preferred one. The experiment based on the proposed methodology proves the accuracy and robustness of our algorithm compared with several well-known change detection techniques on both noise-free and noisy satellite images. Further optimization methods are discussed in the end.","PeriodicalId":310429,"journal":{"name":"Proceedings of 2015 International Conference on Intelligent Computing and Internet of Things","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133040815","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 : 2015-05-25DOI: 10.1109/ICAIOT.2015.7111553
Yi Wang, Yanjun Hu
The almost blank subframe (ABS) has been studied in 3GPP as a way to mitigate downlink interference experienced by cell range expansion (CRE) user equipments (UEs). However, the throughput of CRE UEs highly depends on the ratios of ABS which are statically configured in many situations. The coordinated multi-point (CoMP) is one of the key solutions standardized in LTE-A which can be implemented in CRE with ABS to exploit the abundant spatial resources. And distributed cell selection could help guarantee the UEs' performance under different range expansion biases. In this paper, a distributed CoMP method for CRE with ABS is proposed in heterogeneous networks. Simulation results show that our proposed algorithm provides considerable performance gains in the spectrum efficiency with different bias and users settings.
{"title":"Distributed CoMP transmission for cell range expansion with almost blank subframe in downlink heterogeneous networks","authors":"Yi Wang, Yanjun Hu","doi":"10.1109/ICAIOT.2015.7111553","DOIUrl":"https://doi.org/10.1109/ICAIOT.2015.7111553","url":null,"abstract":"The almost blank subframe (ABS) has been studied in 3GPP as a way to mitigate downlink interference experienced by cell range expansion (CRE) user equipments (UEs). However, the throughput of CRE UEs highly depends on the ratios of ABS which are statically configured in many situations. The coordinated multi-point (CoMP) is one of the key solutions standardized in LTE-A which can be implemented in CRE with ABS to exploit the abundant spatial resources. And distributed cell selection could help guarantee the UEs' performance under different range expansion biases. In this paper, a distributed CoMP method for CRE with ABS is proposed in heterogeneous networks. Simulation results show that our proposed algorithm provides considerable performance gains in the spectrum efficiency with different bias and users settings.","PeriodicalId":310429,"journal":{"name":"Proceedings of 2015 International Conference on Intelligent Computing and Internet of Things","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116859093","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 : 2015-05-25DOI: 10.1109/ICAIOT.2015.7111544
Yang Qin, Liujie Sun, Wenju Wang
We present a digital watermarking algorithm for 3D model which is based on encrypted holographic digital watermarking algorithm to protect the embedded watermark information (such as a specific identity of the copyright information, etc.) and to improve the security and robustness of the digital watermark information. Firstly, the watermark image is processed by the double random phase modulation to get the hologram watermark which makes a high security. Then in the embedding procedures, affine invariant preprocessing is used for 3D models. We calculate the distance of each vertex to center of gravity of the 3D model which is noted as r, and take it as the watermark embedding element to embed the watermark. The experimental results show that the algorithm had the good performance of the watermark robustness to attacks such as noise addition, model simplification, model cropping, and affine attacks. This algorithm can be widely used for digital copyright protection and other aspects of identity hidden.
{"title":"A robust watermarking scheme for 3D models based on encrypted holographic algorithm","authors":"Yang Qin, Liujie Sun, Wenju Wang","doi":"10.1109/ICAIOT.2015.7111544","DOIUrl":"https://doi.org/10.1109/ICAIOT.2015.7111544","url":null,"abstract":"We present a digital watermarking algorithm for 3D model which is based on encrypted holographic digital watermarking algorithm to protect the embedded watermark information (such as a specific identity of the copyright information, etc.) and to improve the security and robustness of the digital watermark information. Firstly, the watermark image is processed by the double random phase modulation to get the hologram watermark which makes a high security. Then in the embedding procedures, affine invariant preprocessing is used for 3D models. We calculate the distance of each vertex to center of gravity of the 3D model which is noted as r, and take it as the watermark embedding element to embed the watermark. The experimental results show that the algorithm had the good performance of the watermark robustness to attacks such as noise addition, model simplification, model cropping, and affine attacks. This algorithm can be widely used for digital copyright protection and other aspects of identity hidden.","PeriodicalId":310429,"journal":{"name":"Proceedings of 2015 International Conference on Intelligent Computing and Internet of Things","volume":"2012 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127401144","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 : 2015-05-25DOI: 10.1109/ICAIOT.2015.7111541
Jicang Lu, Hui Lin, Weizheng Zhang, Xiaowei Shi
For the problem of real-time monitoring and condition decision of high-voltage substation switches, a real-time monitoring algorithm is proposed for the substation folded switch based on geometric analysis of monitoring images. Firstly, capture images containing the folded switch using the properly installed camera, and transfer them to the data processing terminal. Then, search for straight line segments representing two arms of switch using the method of image contour description, and calculate the angles between the segments using the cosine theorem. At last, determine the condition of the switch that whether it is closed well. The experimental results show that the proposed method could accurately calculate the real-time angle of the switch, and then achieve unmanned and real-time monitoring for condition of the switch.
{"title":"A condition monitoring algorithm based on image geometric analysis for substation switch","authors":"Jicang Lu, Hui Lin, Weizheng Zhang, Xiaowei Shi","doi":"10.1109/ICAIOT.2015.7111541","DOIUrl":"https://doi.org/10.1109/ICAIOT.2015.7111541","url":null,"abstract":"For the problem of real-time monitoring and condition decision of high-voltage substation switches, a real-time monitoring algorithm is proposed for the substation folded switch based on geometric analysis of monitoring images. Firstly, capture images containing the folded switch using the properly installed camera, and transfer them to the data processing terminal. Then, search for straight line segments representing two arms of switch using the method of image contour description, and calculate the angles between the segments using the cosine theorem. At last, determine the condition of the switch that whether it is closed well. The experimental results show that the proposed method could accurately calculate the real-time angle of the switch, and then achieve unmanned and real-time monitoring for condition of the switch.","PeriodicalId":310429,"journal":{"name":"Proceedings of 2015 International Conference on Intelligent Computing and Internet of Things","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116145149","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 : 2015-05-25DOI: 10.1109/ICAIOT.2015.7111551
Chengmin Lv, Baohong Ma, Xin Du, Bo Li, Tao Liang
In this article, the chief research and analysis of the network performance measurement and its research trend in the world are introduced. The network measurement technologies are classified according to consultative layer and other method. Measurement technologies of network layer are emphasized. The advantages/disadvantages of the bandwidth measurement technologies and traffic measurement technologies are analyzed. The future research emphasis of the measurement technologies is summarized.
{"title":"Analysis and research of network measurement technologies","authors":"Chengmin Lv, Baohong Ma, Xin Du, Bo Li, Tao Liang","doi":"10.1109/ICAIOT.2015.7111551","DOIUrl":"https://doi.org/10.1109/ICAIOT.2015.7111551","url":null,"abstract":"In this article, the chief research and analysis of the network performance measurement and its research trend in the world are introduced. The network measurement technologies are classified according to consultative layer and other method. Measurement technologies of network layer are emphasized. The advantages/disadvantages of the bandwidth measurement technologies and traffic measurement technologies are analyzed. The future research emphasis of the measurement technologies is summarized.","PeriodicalId":310429,"journal":{"name":"Proceedings of 2015 International Conference on Intelligent Computing and Internet of Things","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124161250","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：