Classification is an important and difficult problem in Polarimetric SAR (POLSAR) image processing. Most existing classification methods combine multiple features (scattering parameters or statistical distribution) to improve the performance. However, based on the observation that various regions have different characteristics due to the different scattering mechanism, which implies that different features should be used for certain pixels rather than using the combination of various features for the whole image, so that simple combinations will result in numerous error classifications. In this paper, a novel POLSAR classification method based on multitask learning with multiple features is proposed. Firstly, different types of features are extracted, and then POLSAR classification problem is formulated as a multitask joint sparse representation learning problem. The strength of different features are employed by using of a joint sparse norm. Finally, experimental results on real POLSAR data show that our method outperforms several state-of-the-art algorithms.
{"title":"Polarimetric SAR Image Classification by Multitask Sparse Representation Learning","authors":"Bo Li, Ying Li, Minxia Chen","doi":"10.1109/ICDH.2018.00013","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00013","url":null,"abstract":"Classification is an important and difficult problem in Polarimetric SAR (POLSAR) image processing. Most existing classification methods combine multiple features (scattering parameters or statistical distribution) to improve the performance. However, based on the observation that various regions have different characteristics due to the different scattering mechanism, which implies that different features should be used for certain pixels rather than using the combination of various features for the whole image, so that simple combinations will result in numerous error classifications. In this paper, a novel POLSAR classification method based on multitask learning with multiple features is proposed. Firstly, different types of features are extracted, and then POLSAR classification problem is formulated as a multitask joint sparse representation learning problem. The strength of different features are employed by using of a joint sparse norm. Finally, experimental results on real POLSAR data show that our method outperforms several state-of-the-art algorithms.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130878683","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"[Title page iii]","authors":"","doi":"10.1109/icdh.2018.00002","DOIUrl":"https://doi.org/10.1109/icdh.2018.00002","url":null,"abstract":"","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128016496","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 the field of clothing recommendation, building a successful recommendation system means giving each user an optimal personalized recommending list. The top ranked clothing in the list are expected to meet a series of user's needs such as preference, taste, style, and consumption level. In online shopping, the most common way is to use user's explicit rating of items. However, user's implicit feedback such as browsing log, collection, and reviews may contains extra information to help model user's preference more accurately. In addition, the recommended clothing should also meet user's consumption level, which is an important factor easily overlooked in recommendation system. In this paper, we combine visual features of clothing images, user's implicit feedback and the price factor to construct a recommendation model based on Siamese network and Bayesian personalized ranking to recommend clothing satisfying user's preference and consumption level. Then on the basis of recommending clothing, we use Generative Adversarial Networks to generate new clothing images and use them to form a compatible collocation to provide fashion suggestions out of datasets.
{"title":"From Recommendation to Generation: A Novel Fashion Clothing Advising Framework","authors":"Zilin Yang, Zhuo Su, Yang Yang, Ge Lin","doi":"10.1109/ICDH.2018.00040","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00040","url":null,"abstract":"In the field of clothing recommendation, building a successful recommendation system means giving each user an optimal personalized recommending list. The top ranked clothing in the list are expected to meet a series of user's needs such as preference, taste, style, and consumption level. In online shopping, the most common way is to use user's explicit rating of items. However, user's implicit feedback such as browsing log, collection, and reviews may contains extra information to help model user's preference more accurately. In addition, the recommended clothing should also meet user's consumption level, which is an important factor easily overlooked in recommendation system. In this paper, we combine visual features of clothing images, user's implicit feedback and the price factor to construct a recommendation model based on Siamese network and Bayesian personalized ranking to recommend clothing satisfying user's preference and consumption level. Then on the basis of recommending clothing, we use Generative Adversarial Networks to generate new clothing images and use them to form a compatible collocation to provide fashion suggestions out of datasets.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133745813","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}
Nannan Li, Haohao Li, Jiangbei Hu, Shengfa Wang, Zhixun Su, Zhongxuan Luo
Feature space analysis is always the most central problem in all kinds of graphic applications, and the acquirement of different kinds of basis for feature space has never been stopped. In this paper, we propose a novel way to analyze the feature space by factorizing it into visually reasonable and physically meaningful basis and corresponding encoders (coefficients). Non-negative matrix factorization (NMF) has previously been shown to be powerful in information retrieval, computer vision and pattern recognition for its physically soundable and additive fashion. By transferring the factorization idea onto tasks of graphic applications, in this paper, we propose a framework for generating new feature basis and encoders for further analysis, which helps empower the downstream graphic applications, including analysis on one single model and joint analysis on a couple of models. Instead of factorizing the matrix composed of images or graphic elements/objects, we propose to apply sparseand-constrained NMF (SAC-NMF) to the feature space that is more general and extendable. And by designing various feature descriptors, we get the base functions for the feature space to enable the analysis of one single model and co-analysis of a list of models. Through the extensive experiments, our analytical framework has exhibited many attractive advantages such as being object-aware, robust, discriminative, extendable, etc.
{"title":"Encoding the Models with Object-Aware Feature Basis: A New Analytical Tool for Graphic Applications","authors":"Nannan Li, Haohao Li, Jiangbei Hu, Shengfa Wang, Zhixun Su, Zhongxuan Luo","doi":"10.1109/ICDH.2018.00060","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00060","url":null,"abstract":"Feature space analysis is always the most central problem in all kinds of graphic applications, and the acquirement of different kinds of basis for feature space has never been stopped. In this paper, we propose a novel way to analyze the feature space by factorizing it into visually reasonable and physically meaningful basis and corresponding encoders (coefficients). Non-negative matrix factorization (NMF) has previously been shown to be powerful in information retrieval, computer vision and pattern recognition for its physically soundable and additive fashion. By transferring the factorization idea onto tasks of graphic applications, in this paper, we propose a framework for generating new feature basis and encoders for further analysis, which helps empower the downstream graphic applications, including analysis on one single model and joint analysis on a couple of models. Instead of factorizing the matrix composed of images or graphic elements/objects, we propose to apply sparseand-constrained NMF (SAC-NMF) to the feature space that is more general and extendable. And by designing various feature descriptors, we get the base functions for the feature space to enable the analysis of one single model and co-analysis of a list of models. Through the extensive experiments, our analytical framework has exhibited many attractive advantages such as being object-aware, robust, discriminative, extendable, etc.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115177791","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}
With the development of image stitching and its wide application, image stitching has become an important and heated topic in image processing. An effective image stitching algorithm based on SURF feature matching and wavelet transform image fusion is proposed in this paper. Firstly, SURF feature points in the two adjacent images are extracted and matched. Then rapid and accurate image registration can be achieved by adopting the improved RNASCA algorithm to removing the mismatched feature point pairs. The multi-resolution decomposition of the overlapping region is processed by Wavelet Transform. Then the multi-scale image fusion is processed by fade-in and fade-out in order to eliminate the stitching seam better. Experiments show that the fusion results of the overlapping region are natural and there also is a certain robustness for translation, rotation, scale and luminance variant.
{"title":"Image Stitching Algorithm Based on SURF and Wavelet Transform","authors":"Jinxin Ruan, Liying Xie, Yuyan Ruan, Lindong Liu, Qiang Chen, Qian Zhang","doi":"10.1109/ICDH.2018.00009","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00009","url":null,"abstract":"With the development of image stitching and its wide application, image stitching has become an important and heated topic in image processing. An effective image stitching algorithm based on SURF feature matching and wavelet transform image fusion is proposed in this paper. Firstly, SURF feature points in the two adjacent images are extracted and matched. Then rapid and accurate image registration can be achieved by adopting the improved RNASCA algorithm to removing the mismatched feature point pairs. The multi-resolution decomposition of the overlapping region is processed by Wavelet Transform. Then the multi-scale image fusion is processed by fade-in and fade-out in order to eliminate the stitching seam better. Experiments show that the fusion results of the overlapping region are natural and there also is a certain robustness for translation, rotation, scale and luminance variant.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128594039","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}
When using a singular value decomposition (SVD) algorithm to estimate the pseudo code sequence of shortcode direct sequence spread spectrum (DSSS) signals directly under impulse noise, the pseudo code information extracted by the algorithm will be seriously interfered, and the estimation performance will deteriorate obviously. In this paper, proposed is a pseudo code sequence blind estimation algorithm based on fractional low order(FLO) joint M estimation. Under the condition of known pseudo code rate and pseudo code period, the received signal is segmented by the size of double PN period, and the fractional low order matrix of the received signal is constructed by using this algorithm in order to reduce the noise component, and then the matrix is decomposed by the SVD algorithm. By taking the summation and subtraction operation between the absolute value of the principal component and its complement sets to estimate the position of the out-of-step point of the pseudo code. Finally, the blind estimation of a pseudo code sequence is realized. Simulation results show that the proposed algorithm can greatly improve the performance of pseudo code sequence blind estimation in an impulse noise channel. When the signal-to-noise ratio (SNR) is about -5 db, the accuracy of the]pseudo code estimation can be kept above 90%.
{"title":"Blind Estimation of PN Sequence Based on FLO Joint M Estimation for Short-Code DSSS Signals","authors":"Xiyan Sun, Zhuo Fan, Yuanfa Ji, Suqing Yan, Shouhua Wang, Weimin Zhen","doi":"10.1109/ICDH.2018.00051","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00051","url":null,"abstract":"When using a singular value decomposition (SVD) algorithm to estimate the pseudo code sequence of shortcode direct sequence spread spectrum (DSSS) signals directly under impulse noise, the pseudo code information extracted by the algorithm will be seriously interfered, and the estimation performance will deteriorate obviously. In this paper, proposed is a pseudo code sequence blind estimation algorithm based on fractional low order(FLO) joint M estimation. Under the condition of known pseudo code rate and pseudo code period, the received signal is segmented by the size of double PN period, and the fractional low order matrix of the received signal is constructed by using this algorithm in order to reduce the noise component, and then the matrix is decomposed by the SVD algorithm. By taking the summation and subtraction operation between the absolute value of the principal component and its complement sets to estimate the position of the out-of-step point of the pseudo code. Finally, the blind estimation of a pseudo code sequence is realized. Simulation results show that the proposed algorithm can greatly improve the performance of pseudo code sequence blind estimation in an impulse noise channel. When the signal-to-noise ratio (SNR) is about -5 db, the accuracy of the]pseudo code estimation can be kept above 90%.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129163817","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}
Privacy preserve machine learning is a hot topic in multimedia domain. In this paper, we propose a secure multifractal feature extraction and representation method in the encrypted domain. We first use chaotic sequence to scramble the image in a block wise way, then according to the characteristic of chaotic sequence which preserves locally the randomness and maintain special periodicity we propose a multifractal feature extraction method in the encrypted domain. Experimental results showed that multifractal feature has a good distinguish ability in the encrypted domain.
{"title":"Encrypted Image Feature Extraction by Privacy-Preserving MFS","authors":"Guoming Chen, Qiang Chen, Xiongyong Zhu, Yiqun Chen","doi":"10.1109/ICDH.2018.00016","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00016","url":null,"abstract":"Privacy preserve machine learning is a hot topic in multimedia domain. In this paper, we propose a secure multifractal feature extraction and representation method in the encrypted domain. We first use chaotic sequence to scramble the image in a block wise way, then according to the characteristic of chaotic sequence which preserves locally the randomness and maintain special periodicity we propose a multifractal feature extraction method in the encrypted domain. Experimental results showed that multifractal feature has a good distinguish ability in the encrypted domain.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132683972","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}
Taking advantage of machine learning models, many researchers are exploring to dig out valuable information in large Traditional TCM(TCM) data. In view of the problems of existing TCM herb community detection methods, including poor flexibility, poor extensibility, poor performance of the herb network map, the difficulty in handling the network with small granularity, and the poor balance of detection results, this paper innovatively proposes a new herb community detection idea based on Graph Embedding. This idea mainly has three steps. The first step is constructing the TCM prescription network. The second step is mapping every herb node in the network to herb vector. The third step is using common vector clustering algorithm to get herb communities by dividing the network. In this paper, the second step is the core step. In order to reflect one-to-one and one-to-many relationship of herb nodes, this paper proposes two herb vector construction methods based on two Graph Embedding methods, respectively are matrix decomposition method and improved random walk method. In order to evaluate the experiment results, this paper proposes a comprehensive evaluation metrics which combining modularity, balance, and manual analysis and conducts experiments on relevant outpatient prescription record data. Experimental results show that the new herb community detection methods proposed in this paper has great performance in evaluation metrics than the traditional community detection algorithm, at the same time, the proposed vector construction method can also find potential new herb communities and help innovation of constructing prescription.
{"title":"Herb Community Detection from TCM Prescription Based on Graph Embedding","authors":"Gansen Zhao, Zijing Li, Xinming Wang, Weimin Ning, Xutian Zhuang, Jianfei Wang, Qiang Chen, Zefeng Mo, Bingchuan Chen, Huiyan Chen","doi":"10.1109/icdh.2018.00062","DOIUrl":"https://doi.org/10.1109/icdh.2018.00062","url":null,"abstract":"Taking advantage of machine learning models, many researchers are exploring to dig out valuable information in large Traditional TCM(TCM) data. In view of the problems of existing TCM herb community detection methods, including poor flexibility, poor extensibility, poor performance of the herb network map, the difficulty in handling the network with small granularity, and the poor balance of detection results, this paper innovatively proposes a new herb community detection idea based on Graph Embedding. This idea mainly has three steps. The first step is constructing the TCM prescription network. The second step is mapping every herb node in the network to herb vector. The third step is using common vector clustering algorithm to get herb communities by dividing the network. In this paper, the second step is the core step. In order to reflect one-to-one and one-to-many relationship of herb nodes, this paper proposes two herb vector construction methods based on two Graph Embedding methods, respectively are matrix decomposition method and improved random walk method. In order to evaluate the experiment results, this paper proposes a comprehensive evaluation metrics which combining modularity, balance, and manual analysis and conducts experiments on relevant outpatient prescription record data. Experimental results show that the new herb community detection methods proposed in this paper has great performance in evaluation metrics than the traditional community detection algorithm, at the same time, the proposed vector construction method can also find potential new herb communities and help innovation of constructing prescription.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"494 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134018511","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}
With the development of the Beidou satellite navigation system, the monitoring of ionospheric scintillation combined with GPS and Beidou system has become a trend. In this paper, the design and implementation of the upper computer software for ionospheric scintillation monitoring are introduced, and the related algorithms such as ionospheric amplitude scintillation monitoring, ionospheric phase scintillation monitoring and ionospheric TEC monitoring are discussed and analyzed. The ionospheric scintillation monitoring system developed in this paper can calculate the ionospheric amplitude scintillation index and ionospheric phase scintillation index of the L1/L2 frequency point of GPS satellite and the B1/B2 frequency signal of Beidou satellite in real time. It can also calculate the ionospheric parameters such as TEC, σ_TEC, ROT and ROTI of each satellite, and can store the observed data and make the judgement and analysis of ionospheric scintillation events. Finally, the functional test results of ionospheric scintillation monitoring system are given, and discussed and analyzed.
{"title":"Algorithm of Ionospheric Scintillation Monitoring","authors":"Xiyan Sun, Zheyang Zhang, Yuanfa Ji, Suqing Yan, Wentao Fu, Qidong Chen","doi":"10.1109/ICDH.2018.00053","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00053","url":null,"abstract":"With the development of the Beidou satellite navigation system, the monitoring of ionospheric scintillation combined with GPS and Beidou system has become a trend. In this paper, the design and implementation of the upper computer software for ionospheric scintillation monitoring are introduced, and the related algorithms such as ionospheric amplitude scintillation monitoring, ionospheric phase scintillation monitoring and ionospheric TEC monitoring are discussed and analyzed. The ionospheric scintillation monitoring system developed in this paper can calculate the ionospheric amplitude scintillation index and ionospheric phase scintillation index of the L1/L2 frequency point of GPS satellite and the B1/B2 frequency signal of Beidou satellite in real time. It can also calculate the ionospheric parameters such as TEC, σ_TEC, ROT and ROTI of each satellite, and can store the observed data and make the judgement and analysis of ionospheric scintillation events. Finally, the functional test results of ionospheric scintillation monitoring system are given, and discussed and analyzed.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126614662","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}
Ruyue Wang, Hanhui Li, Rushi Lan, S. Luo, Xiaonan Luo
In this paper, we propose to tackle the problem of Alzheimer's Disease (AD) classification by a novel Hierarchical Ensemble Learning (HEL) framework. Given an MRI image of a subject, our method will divide it into multiple slices, and generate the classification result in a coarse-to-fine way: First, for each slice, multiple pre-trained deep neural networks are adopted to extract features, and classiflers trained with each type of these features are used to generate the coarse predictions; Second, we employ ensemble learning on the coarse results to generate a refined result for each slice; At last, the given subject is classified based on the refined results aggregated from all slices. Using pre-trained networks for feature extraction can reduce the computational costs of training significantly, and the ensemble of multiple features and predicted results from slices can increase the classification accuracy effectively. Hence, our method can achieve the balance between efficiency and effectiveness. Experimental results show that the HEL framework can obtain notable performance gains with respect to various features and classifiers.
{"title":"Hierarchical Ensemble Learning for Alzheimer's Disease Classification","authors":"Ruyue Wang, Hanhui Li, Rushi Lan, S. Luo, Xiaonan Luo","doi":"10.1109/ICDH.2018.00047","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00047","url":null,"abstract":"In this paper, we propose to tackle the problem of Alzheimer's Disease (AD) classification by a novel Hierarchical Ensemble Learning (HEL) framework. Given an MRI image of a subject, our method will divide it into multiple slices, and generate the classification result in a coarse-to-fine way: First, for each slice, multiple pre-trained deep neural networks are adopted to extract features, and classiflers trained with each type of these features are used to generate the coarse predictions; Second, we employ ensemble learning on the coarse results to generate a refined result for each slice; At last, the given subject is classified based on the refined results aggregated from all slices. Using pre-trained networks for feature extraction can reduce the computational costs of training significantly, and the ensemble of multiple features and predicted results from slices can increase the classification accuracy effectively. Hence, our method can achieve the balance between efficiency and effectiveness. Experimental results show that the HEL framework can obtain notable performance gains with respect to various features and classifiers.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116833193","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：