Traditional manual detection method of crop pests is a quite tedious work with low efficiency, which brings great inconvenience to the control and removal of crop pests at early stage. In recently years, computer vision becomes a critical and promising technique for pest detection. However, limited to the shape and size of the pest and other issues, the perforance of these methods are not so effective and accurate. In order to improve the detection accuracy, we propose a discriminative method for pest detection on leaves based on low-rank representation and sparsity. By utilizing the lowrank characteristics of natural images, the sparsity of the noise image and the prior knowledge of color information of the crop pest images, our method decomposes the original image into low-rank image and sparse noise image, which contains all pests on the leaf. After that, the crop pests with leaf can be separate from the background and counted effectively. The experimental results show that our method can detect pests on leaf conveniently. This is of great significance for future pest judgment and management.
{"title":"A Discriminative Pest Detection Method Based on Low-Rank Representation","authors":"Yang Wang, Yong Zhang, Yunhui Shi, Baocai Yin","doi":"10.1109/ICDH.2018.00024","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00024","url":null,"abstract":"Traditional manual detection method of crop pests is a quite tedious work with low efficiency, which brings great inconvenience to the control and removal of crop pests at early stage. In recently years, computer vision becomes a critical and promising technique for pest detection. However, limited to the shape and size of the pest and other issues, the perforance of these methods are not so effective and accurate. In order to improve the detection accuracy, we propose a discriminative method for pest detection on leaves based on low-rank representation and sparsity. By utilizing the lowrank characteristics of natural images, the sparsity of the noise image and the prior knowledge of color information of the crop pest images, our method decomposes the original image into low-rank image and sparse noise image, which contains all pests on the leaf. After that, the crop pests with leaf can be separate from the background and counted effectively. The experimental results show that our method can detect pests on leaf conveniently. This is of great significance for future pest judgment and management.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"9 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":"115569676","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}
Yan Xiong, Qiang Chen, S. Deng, Sheng Liang, Kai Wang, Jun Zhang, Jie Wang
Generalized sidelobe canceller (GSC) is wildly used in speech enhancement due to its efficient implementation. However, the conventional GSC has some drawbacks when applied to speech enhancement system. First, it is focused on improving the signal-to-noise ratio (SNR) without considering the characteristics of speech so that is not optimal for speech enhancement applications. Second, the adaptive branch in the GSC does not always estimate the noise in the fixed branch output accurately, especially when the SNR is high, the noise is spatially incoherent, or the spatial incoherent noises and spatial coherent interferences coexist. In this paper, we propose a model-based post filter for the sub-band GSC which is a typical form of the microphone array beamformer. An improved noise estimation method is developed to estimate the noise in the fixed branch output of each sub-band GSC from its adaptive branch output. Then the fixed branch output is filtered by an optimal filter which is constructed according to a GMM model trained by clean speeches and an online-estimated noise model. Experimental results show that the proposed method achieves significant improvement over the conventional sub-band GSC and outperforms several speech enhancement methods in different noisy environments.
{"title":"Model-Based Post Filter for Microphone Array Speech Enhancement","authors":"Yan Xiong, Qiang Chen, S. Deng, Sheng Liang, Kai Wang, Jun Zhang, Jie Wang","doi":"10.1109/ICDH.2018.00023","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00023","url":null,"abstract":"Generalized sidelobe canceller (GSC) is wildly used in speech enhancement due to its efficient implementation. However, the conventional GSC has some drawbacks when applied to speech enhancement system. First, it is focused on improving the signal-to-noise ratio (SNR) without considering the characteristics of speech so that is not optimal for speech enhancement applications. Second, the adaptive branch in the GSC does not always estimate the noise in the fixed branch output accurately, especially when the SNR is high, the noise is spatially incoherent, or the spatial incoherent noises and spatial coherent interferences coexist. In this paper, we propose a model-based post filter for the sub-band GSC which is a typical form of the microphone array beamformer. An improved noise estimation method is developed to estimate the noise in the fixed branch output of each sub-band GSC from its adaptive branch output. Then the fixed branch output is filtered by an optimal filter which is constructed according to a GMM model trained by clean speeches and an online-estimated noise model. Experimental results show that the proposed method achieves significant improvement over the conventional sub-band GSC and outperforms several speech enhancement methods in different noisy environments.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"248 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":"122461830","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}
Banks frequently face massive credit risks, which might lead to opportunities lost or financial losses. Regarding to this, more and more data mining methods are used in bank credit scoring nowadays. However, different data mining methods for classification can produce different results. The aim of this paper is to fuse the different data mining results together to get one better solution by using the information fusion technique. In this study, information fusion technique is used to build the credit scoring models based on data mining methods such as SVM and Logistic regression model. Two real credit scoring data sets of UCI databases are used to demonstrate the effectiveness and feasibility of the method. The results show that the information fusion model has certain validity, reliability and a higher accuracy than those of the two methods obtained separately.
{"title":"Credit Scoring Using Information Fusion Technique","authors":"Di Wang, Zuoquan Zhang","doi":"10.1109/ICDH.2018.00036","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00036","url":null,"abstract":"Banks frequently face massive credit risks, which might lead to opportunities lost or financial losses. Regarding to this, more and more data mining methods are used in bank credit scoring nowadays. However, different data mining methods for classification can produce different results. The aim of this paper is to fuse the different data mining results together to get one better solution by using the information fusion technique. In this study, information fusion technique is used to build the credit scoring models based on data mining methods such as SVM and Logistic regression model. Two real credit scoring data sets of UCI databases are used to demonstrate the effectiveness and feasibility of the method. The results show that the information fusion model has certain validity, reliability and a higher accuracy than those of the two methods obtained separately.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"36 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":"129140349","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":"[Copyright notice]","authors":"","doi":"10.1109/icdh.2018.00003","DOIUrl":"https://doi.org/10.1109/icdh.2018.00003","url":null,"abstract":"","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"37 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":"124516864","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 order to solve the problem of ambiguous acquisition of BOC signals caused by its property of multiple peaks, an unambiguous acquisition algorithm is proposed in this paper. The concept of sub quadratic correlation function and sub QBOC code are first defined in this letter by analyzing the autocorrelation and quadratic correlation of BOC(n, n). Then a new correlation function without multiple peaks can be obtained by a simple combination of sub quadratic correlation, which can be used to unambiguous acquisition for BOC(n, n). The theoretical analysis and simulation prove that the proposed algorithm not only can accomplish unambiguous acquisition but also have more effective de-ambiguity, higher capture sensitivity and higher peak to average power ratio compared to the classical BPSK-like, SPCP and ASPeCT algorithms.
{"title":"A Novel Unambiguous Acquisition Algorithm for BOC(n, n) Signals","authors":"Xiyan Sun, Xiaoqian Chen, Qiang Fu, Suqing Yan, Weimin Zhen","doi":"10.1109/icdh.2018.00054","DOIUrl":"https://doi.org/10.1109/icdh.2018.00054","url":null,"abstract":"In order to solve the problem of ambiguous acquisition of BOC signals caused by its property of multiple peaks, an unambiguous acquisition algorithm is proposed in this paper. The concept of sub quadratic correlation function and sub QBOC code are first defined in this letter by analyzing the autocorrelation and quadratic correlation of BOC(n, n). Then a new correlation function without multiple peaks can be obtained by a simple combination of sub quadratic correlation, which can be used to unambiguous acquisition for BOC(n, n). The theoretical analysis and simulation prove that the proposed algorithm not only can accomplish unambiguous acquisition but also have more effective de-ambiguity, higher capture sensitivity and higher peak to average power ratio compared to the classical BPSK-like, SPCP and ASPeCT algorithms.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"32 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":"125021998","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The block chain has achieved great success in bit coin, and its decentralization idea caught highly attention of financial institutions, capital markets and academia. Decentralization is the most fundamental feature of the block chain, but decentralization sacrifices efficiency, while mining leads to high bit coin transaction costs; in some industries, such as the commercial retail, high efficiency and low cost are required. The consensus algorithm is the core technology to achieve non-centralization. This article proposes a DPoS consensus mechanism election algorithm. This algorithm improves the ring-based coordinator election algorithm. First, the algorithm is used to elect the agents, and then the final winner, reach a new consensus, meet the requirements of the block chain performance in the commercial retail sector, reduce transaction costs, and construct a fair, freely competitive, non-monopoly, secure and non-centralized block chain platform.
{"title":"A New Election Algorithm for DPos Consensus Mechanism in Blockchain","authors":"Yinghui Luo, Yiqun Chen, Qiang Chen, Q. Liang","doi":"10.1109/ICDH.2018.00029","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00029","url":null,"abstract":"The block chain has achieved great success in bit coin, and its decentralization idea caught highly attention of financial institutions, capital markets and academia. Decentralization is the most fundamental feature of the block chain, but decentralization sacrifices efficiency, while mining leads to high bit coin transaction costs; in some industries, such as the commercial retail, high efficiency and low cost are required. The consensus algorithm is the core technology to achieve non-centralization. This article proposes a DPoS consensus mechanism election algorithm. This algorithm improves the ring-based coordinator election algorithm. First, the algorithm is used to elect the agents, and then the final winner, reach a new consensus, meet the requirements of the block chain performance in the commercial retail sector, reduce transaction costs, and construct a fair, freely competitive, non-monopoly, secure and non-centralized block chain platform.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"10 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":"122762825","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 Chinese financial market, more and more investors paid attention to the stock market. How to analysis stock scientifically is a crutial issue that investors should consider. In order to do stock selection, the financial indicators of listed companies are particularly important. However, in real world the number of high-quality stocks is much smaller than ordinary stocks, that is, the dataset is unbalanced. And company's financial data is often high dimensional and contain many irrelevant features. In this paper, firstly we propose a hybrid BASMOTE algorithm based on the borderline-SMOTE algorithm and ADASYN algorithm. Introduce the ADASYN algorithm's adaptive thought to the borderline-SMOTE algorithm, so as to obtain more effective and reasonable new minority examples. Secondly, a hybrid feature selection method, HPMG, is proposed, which introduces the wrapper thought and ensemble thought into traditional feature selection methods. We use multi-dimensional financial indicators of A-Shares data of Chinese market, the validity of the BASMOTE algorithm and the HPMG are compared respectively with existing over-sampling methods and feature selection methods. It proves that the BASMOTE algorithm and HPMG are better than the existing over-sampling methods and feature selection methods.
{"title":"Modified Machine Learning Model and Stock Classification Research Based on Unbalanced Data","authors":"Marui Du, Zuoquan Zhang, Yuqing Zhang","doi":"10.1109/ICDH.2018.00043","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00043","url":null,"abstract":"With the development of Chinese financial market, more and more investors paid attention to the stock market. How to analysis stock scientifically is a crutial issue that investors should consider. In order to do stock selection, the financial indicators of listed companies are particularly important. However, in real world the number of high-quality stocks is much smaller than ordinary stocks, that is, the dataset is unbalanced. And company's financial data is often high dimensional and contain many irrelevant features. In this paper, firstly we propose a hybrid BASMOTE algorithm based on the borderline-SMOTE algorithm and ADASYN algorithm. Introduce the ADASYN algorithm's adaptive thought to the borderline-SMOTE algorithm, so as to obtain more effective and reasonable new minority examples. Secondly, a hybrid feature selection method, HPMG, is proposed, which introduces the wrapper thought and ensemble thought into traditional feature selection methods. We use multi-dimensional financial indicators of A-Shares data of Chinese market, the validity of the BASMOTE algorithm and the HPMG are compared respectively with existing over-sampling methods and feature selection methods. It proves that the BASMOTE algorithm and HPMG are better than the existing over-sampling methods and feature selection methods.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"139 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":"122894511","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}
There emerges an increasing need to improve the accuracy of computer recognition of fundus medical images. Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and deep convolutional neural networks (CNNs). However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. In this study, an improved DensenNet method based on Transfer Learning techniques is proposed for fundus medical images. Two experiments for fundus medical image data have been conducted respectively. The first one is to train the DenseNet models from scratch; the second one is fine-tuning operations by transfer learning, in which the DenseNet models pre-trained from natural image dataset to fundus medical images are improved. Experimental Results prove that the proposed method can improve the accuracy of fundus medical image classification, which is valuable for medical diagnosis.
{"title":"An Improved DenseNet Method Based on Transfer Learning for Fundus Medical Images","authors":"Xiaowei Xu, Jiancheng Lin, Ye Tao, Xiaodong Wang","doi":"10.1109/ICDH.2018.00033","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00033","url":null,"abstract":"There emerges an increasing need to improve the accuracy of computer recognition of fundus medical images. Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and deep convolutional neural networks (CNNs). However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. In this study, an improved DensenNet method based on Transfer Learning techniques is proposed for fundus medical images. Two experiments for fundus medical image data have been conducted respectively. The first one is to train the DenseNet models from scratch; the second one is fine-tuning operations by transfer learning, in which the DenseNet models pre-trained from natural image dataset to fundus medical images are improved. Experimental Results prove that the proposed method can improve the accuracy of fundus medical image classification, which is valuable for medical diagnosis.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"27 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":"125068078","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 i]","authors":"","doi":"10.1109/icdh.2018.00001","DOIUrl":"https://doi.org/10.1109/icdh.2018.00001","url":null,"abstract":"","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":"126623839","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}
High-quality Drosophila embryo images can provide reliable data sources for the research of gene expression and gene interaction. Based on the Drosophila embryo images, a FEMine system is constructed to assist geneticists in quickly mining information for analysis. The extraction of interested Drosophila embryo is an important pretreatment in the FEMine systems. In this paper, taking contour extraction task as image generation task, we proposed a conditional generative adversarial network to generate contour maps of the same size as input images. Based on the Drosophila embryo manual dataset DEDS(Drosophila embryo Dataset)1, for each of the ground-truth, we turn the regions of the interested Drosophila embryo into contours of that. The experiments on DEDS demonstrate that our framework can efficiently extract the contours of the interested Drosophila embryos.
{"title":"Contour Extraction of Drosophila Embryos Based on Conditional Generative Adversarial Nets","authors":"Hui Huang, Zhoutao Wang, Y. Gong, Qingzhen Xu","doi":"10.1109/ICDH.2018.00022","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00022","url":null,"abstract":"High-quality Drosophila embryo images can provide reliable data sources for the research of gene expression and gene interaction. Based on the Drosophila embryo images, a FEMine system is constructed to assist geneticists in quickly mining information for analysis. The extraction of interested Drosophila embryo is an important pretreatment in the FEMine systems. In this paper, taking contour extraction task as image generation task, we proposed a conditional generative adversarial network to generate contour maps of the same size as input images. Based on the Drosophila embryo manual dataset DEDS(Drosophila embryo Dataset)1, for each of the ground-truth, we turn the regions of the interested Drosophila embryo into contours of that. The experiments on DEDS demonstrate that our framework can efficiently extract the contours of the interested Drosophila embryos.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"32 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":"126342899","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：