Pub Date : 2021-01-05DOI: 10.1109/iccrd51685.2021.9386708
{"title":"ICCRD 2021 Copyright Page","authors":"","doi":"10.1109/iccrd51685.2021.9386708","DOIUrl":"https://doi.org/10.1109/iccrd51685.2021.9386708","url":null,"abstract":"","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115445104","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386354
Chenglong Cao, Xiaoling Zhu
During the epidemic outbreak of COVID-19, all universities, middle schools and primary schools in China adopted the form of online teaching. It brings convenience, but it also raises some security and privacy issues. The challenge to solve the issues is how to achieve effective access control and how to ensure the authenticity of online data. Because blockchain has the characteristics of openness, unforgeability and decentralization, we present a trusted data management scheme for e-learning system based on blockchain. In the scheme, large amounts of resource data are stored in a distributed storage system; the evidences of uploaded data are stored in blockchain network established by high credible institutions. Once the data in the distributed storage are tampered, it will be discovered by looking up blockchain transactions. In order to make up for the lack of privacy protection in blockchain, we adopt attribute encryption. For different resources, different ciphertext policies are given. Only the users whose attributes satisfy the policy can decrypt the data. Further, a fine-grained access control scheme for e-learning is designed. In addition, the scheme can prevent collusion attacks; even if multiple users collude, they will not get more resources.
{"title":"Trusted Data Management for E-learning System Based on Blockchain","authors":"Chenglong Cao, Xiaoling Zhu","doi":"10.1109/ICCRD51685.2021.9386354","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386354","url":null,"abstract":"During the epidemic outbreak of COVID-19, all universities, middle schools and primary schools in China adopted the form of online teaching. It brings convenience, but it also raises some security and privacy issues. The challenge to solve the issues is how to achieve effective access control and how to ensure the authenticity of online data. Because blockchain has the characteristics of openness, unforgeability and decentralization, we present a trusted data management scheme for e-learning system based on blockchain. In the scheme, large amounts of resource data are stored in a distributed storage system; the evidences of uploaded data are stored in blockchain network established by high credible institutions. Once the data in the distributed storage are tampered, it will be discovered by looking up blockchain transactions. In order to make up for the lack of privacy protection in blockchain, we adopt attribute encryption. For different resources, different ciphertext policies are given. Only the users whose attributes satisfy the policy can decrypt the data. Further, a fine-grained access control scheme for e-learning is designed. In addition, the scheme can prevent collusion attacks; even if multiple users collude, they will not get more resources.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125020032","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386407
Shaolong Zhu, Du Chen, Meiyi Yang, Xuening Shang
Traditional network encryption mechanisms have many drawbacks, such as low encryption efficiency. In order to solve these problems, the paper proposes a new dynamic multi-path and multi-protocol encryption communication mechanism, which improves the universality of encryption algorithms and encryption efficiency while ensuring the security and privacy of user information. At the same time, the trade-off between information security and resource consumption is considered. The whole system is implemented by SDN, and the data plane adopts P4 technology. It is verified that the proposed method has a shorter encryption and decryption time than AES and RSA, and reduces the resource overhead of the system, and has stronger practicability.
{"title":"Dynamic Multi-path and Multi-protocol Encrypted Communication Mechanism","authors":"Shaolong Zhu, Du Chen, Meiyi Yang, Xuening Shang","doi":"10.1109/ICCRD51685.2021.9386407","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386407","url":null,"abstract":"Traditional network encryption mechanisms have many drawbacks, such as low encryption efficiency. In order to solve these problems, the paper proposes a new dynamic multi-path and multi-protocol encryption communication mechanism, which improves the universality of encryption algorithms and encryption efficiency while ensuring the security and privacy of user information. At the same time, the trade-off between information security and resource consumption is considered. The whole system is implemented by SDN, and the data plane adopts P4 technology. It is verified that the proposed method has a shorter encryption and decryption time than AES and RSA, and reduces the resource overhead of the system, and has stronger practicability.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132487256","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386709
Yunyi Liu, Ruining Yang
Depression is one of the most prevalent psychiatric disorders and an important public health problem. Its etiology is multifaceted, and the specific pathophysiological mechanisms are still unclear. At present, the main treatment methods for depression are medication, psychotherapy and physical therapy, and clinical applications usually combine two or three methods. Psychotherapy is currently mainly oriented towards the traditional face-to-face communication with psychologists, and is rarely combined with the current rapid development of technology. In this paper, we aim to design an intelligent robot that incorporates deep learning methods to help doctors treat patients more efficiently. The problem is that the current models of robots are trained by uploading data to a server, and then having the server train the robot. There are disadvantages of this approach. First, patient videos and conversations are private information. So uploading those private information to the server can lead to patient information leakage, which is bad. Second, the data recorded in daily life, including audio and video, are very large files that are slow to transfer and tend to cause package loss and other problems in the process. Training a multi-robot model in combination with federal learning would be a good solution to these two problems. The article combines federal learning with basic deep learning methods to design a depression treatment robot(DTbot) that can treat patients with more privacy and efficiency while handling their personal information.
{"title":"Federated Learning Application on Depression Treatment Robots(DTbot)","authors":"Yunyi Liu, Ruining Yang","doi":"10.1109/ICCRD51685.2021.9386709","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386709","url":null,"abstract":"Depression is one of the most prevalent psychiatric disorders and an important public health problem. Its etiology is multifaceted, and the specific pathophysiological mechanisms are still unclear. At present, the main treatment methods for depression are medication, psychotherapy and physical therapy, and clinical applications usually combine two or three methods. Psychotherapy is currently mainly oriented towards the traditional face-to-face communication with psychologists, and is rarely combined with the current rapid development of technology. In this paper, we aim to design an intelligent robot that incorporates deep learning methods to help doctors treat patients more efficiently. The problem is that the current models of robots are trained by uploading data to a server, and then having the server train the robot. There are disadvantages of this approach. First, patient videos and conversations are private information. So uploading those private information to the server can lead to patient information leakage, which is bad. Second, the data recorded in daily life, including audio and video, are very large files that are slow to transfer and tend to cause package loss and other problems in the process. Training a multi-robot model in combination with federal learning would be a good solution to these two problems. The article combines federal learning with basic deep learning methods to design a depression treatment robot(DTbot) that can treat patients with more privacy and efficiency while handling their personal information.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128399621","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386710
Zhen Meng, Xuezhi Wang, Li Ma, Yuanchun Zhou
With the development of scientific big data technology, problem-oriented analysis becomes normal case. iAnalysis V1.0, an interactive analysis cloud service system, gives a unified cloud resource management service for scientific data analysis. It can not only be used directly by end-user scientists through the service portal, but also be called by other existing data systems in the form of docker container. In this paper, there are presented the key technical methods of iAnalysis V1.0, including the interactive analysis service solution based on container technology, the interactive analysis components and storage & high-performance computing services for interactive analysis. There are also introduced the specific application services of iAnalysis V1.0 such as lightweight deployment service, management and monitoring services, external application programming interface services and so on. Some applications of iAnalysis V1.0 are also presented. The basic deployment images of iAnalysis V1.0 can be download from https://hub.docker.com/repository/docker/bioinf/ianalysis.
{"title":"iAnalysis V1.0: An Interactive Analysis Service System","authors":"Zhen Meng, Xuezhi Wang, Li Ma, Yuanchun Zhou","doi":"10.1109/ICCRD51685.2021.9386710","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386710","url":null,"abstract":"With the development of scientific big data technology, problem-oriented analysis becomes normal case. iAnalysis V1.0, an interactive analysis cloud service system, gives a unified cloud resource management service for scientific data analysis. It can not only be used directly by end-user scientists through the service portal, but also be called by other existing data systems in the form of docker container. In this paper, there are presented the key technical methods of iAnalysis V1.0, including the interactive analysis service solution based on container technology, the interactive analysis components and storage & high-performance computing services for interactive analysis. There are also introduced the specific application services of iAnalysis V1.0 such as lightweight deployment service, management and monitoring services, external application programming interface services and so on. Some applications of iAnalysis V1.0 are also presented. The basic deployment images of iAnalysis V1.0 can be download from https://hub.docker.com/repository/docker/bioinf/ianalysis.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127523453","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386461
Lv Hexin, Xinli Yang, Guoyong Dai
With people focus much more on their health, the need of Chinese medicine is increasing heavily. There are thousands of kinds of Chinese medicine prescriptions. Different pharmacists are familiar with different prescriptions and a single pharmacist is not likely to deal with all the prescriptions well. Therefore, there is a need to find the most proper pharmacist for each prescription so that the quality and efficiency for pharmacists dealing with prescriptions can be improved.To solve the problem, we propose a novel approach by leveraging learning to rank algorithm. The model built by our approach can be used to automatically recommend which pharmacist is the most proper for an unknown labeled prescription.With experiments on a Chinese medicine dataset, we demonstrate that our approach can better achieve pharmacist assignment. In particular, when compared with the baseline, our approach can achieve an improvement of over 300% in terms of MAP.With the learning to rank approach, we can achieve automated pharmacist assignment for different kinds of Chinese medicine prescriptions and improve the quality and efficiency for pharmacists dealing with prescriptions.
{"title":"A Learning to Rank Approach for Pharmacist Assignment","authors":"Lv Hexin, Xinli Yang, Guoyong Dai","doi":"10.1109/ICCRD51685.2021.9386461","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386461","url":null,"abstract":"With people focus much more on their health, the need of Chinese medicine is increasing heavily. There are thousands of kinds of Chinese medicine prescriptions. Different pharmacists are familiar with different prescriptions and a single pharmacist is not likely to deal with all the prescriptions well. Therefore, there is a need to find the most proper pharmacist for each prescription so that the quality and efficiency for pharmacists dealing with prescriptions can be improved.To solve the problem, we propose a novel approach by leveraging learning to rank algorithm. The model built by our approach can be used to automatically recommend which pharmacist is the most proper for an unknown labeled prescription.With experiments on a Chinese medicine dataset, we demonstrate that our approach can better achieve pharmacist assignment. In particular, when compared with the baseline, our approach can achieve an improvement of over 300% in terms of MAP.With the learning to rank approach, we can achieve automated pharmacist assignment for different kinds of Chinese medicine prescriptions and improve the quality and efficiency for pharmacists dealing with prescriptions.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130857523","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 : 2021-01-05DOI: 10.1109/iccrd51685.2021.9386512
{"title":"ICCRD 2021 Cover Page","authors":"","doi":"10.1109/iccrd51685.2021.9386512","DOIUrl":"https://doi.org/10.1109/iccrd51685.2021.9386512","url":null,"abstract":"","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116021833","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386515
Zhuang Miao, Yang Li, Jiabao Wang, Jixiao Wang, Rui Zhang
Recent years have witnessed wide application of infrared and visible image fusion. However, most existing deep fusion methods focused primarily on improving the accuracy without taking much consideration of efficiency. In this paper, our goal is to build a better, faster and stronger image fusion method, which can reduce the computation complexity significantly while keep the fusion quality unchanged. To this end, we systematically analyzed the image fusion accuracy for different depth of image features and designed a lightweight backbone network with spatial frequency for infrared and visible image fusion. Unlikely previous methods based on traditional convolutional neural networks, our method can greatly preserve the detail information during image fusion. We analyze the spatial frequency strategy of our prototype and show that it can maintain more edges and textures information during fusion. Furthermore, our method has fewer parameters and lower computation in comparison of state-of-the-art fusion methods. Experiments conducted on benchmarks demonstrate that our method can achieve compelling fusion results over 97.0% decline of parameter size, running 5 times faster than state-of-the-art fusion methods.
{"title":"Better and Faster Deep Image Fusion with Spatial Frequency","authors":"Zhuang Miao, Yang Li, Jiabao Wang, Jixiao Wang, Rui Zhang","doi":"10.1109/ICCRD51685.2021.9386515","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386515","url":null,"abstract":"Recent years have witnessed wide application of infrared and visible image fusion. However, most existing deep fusion methods focused primarily on improving the accuracy without taking much consideration of efficiency. In this paper, our goal is to build a better, faster and stronger image fusion method, which can reduce the computation complexity significantly while keep the fusion quality unchanged. To this end, we systematically analyzed the image fusion accuracy for different depth of image features and designed a lightweight backbone network with spatial frequency for infrared and visible image fusion. Unlikely previous methods based on traditional convolutional neural networks, our method can greatly preserve the detail information during image fusion. We analyze the spatial frequency strategy of our prototype and show that it can maintain more edges and textures information during fusion. Furthermore, our method has fewer parameters and lower computation in comparison of state-of-the-art fusion methods. Experiments conducted on benchmarks demonstrate that our method can achieve compelling fusion results over 97.0% decline of parameter size, running 5 times faster than state-of-the-art fusion methods.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132581998","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386712
Soha Bahanshal, Byung Kim
Predicting hospital readmissions among diabetic patients has been of substantial interest to many researchers and health decision makers to provide quality and cost effective health care. In this paper, we optimize an efficient classifier for hospital readmission prediction within 30 days of discharge, the hybrid fuzzy weighted k-nearest neighbor (HFWkNN) method. The optimization is performed through the hyperparameter γ, ε and εmin introduced in the membership function of HFWkNN. These hyperparameters are important since they directly control the behavior of the training phase and significantly affect the performance of the method. A relationship is established between the performance of the proposed HFWkNN and the hyperparameters using two powerful optimization algorithms; grid search and random search. Experimental results show improved performance using the optimized hyperparameters in the resulting hospital readmission prediction model. To show that HFWkNN model can be generalized, the results are compared with those of several kNN-based algorithms using two additional classification datasets in addition to the hospital readmission dataset. They are IRIS dataset and breast cancer dataset. These are common benchmark sets with real-world data. The model so far achieved higher classification accuracy than FkNN model. The best hyperparameter values for HFWkNN with grid search are γ=0.2249, ε=1.112 and εmin=0.01. Also, HFWkNN shows a performance of 80.00%, meaning that it has generalized well on the different data sets.
{"title":"An Optimized Hybrid Fuzzy Weighted k-Nearest Neighbor to Predict Hospital Readmission for Diabetic Patients","authors":"Soha Bahanshal, Byung Kim","doi":"10.1109/ICCRD51685.2021.9386712","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386712","url":null,"abstract":"Predicting hospital readmissions among diabetic patients has been of substantial interest to many researchers and health decision makers to provide quality and cost effective health care. In this paper, we optimize an efficient classifier for hospital readmission prediction within 30 days of discharge, the hybrid fuzzy weighted k-nearest neighbor (HFWkNN) method. The optimization is performed through the hyperparameter γ, ε and εmin introduced in the membership function of HFWkNN. These hyperparameters are important since they directly control the behavior of the training phase and significantly affect the performance of the method. A relationship is established between the performance of the proposed HFWkNN and the hyperparameters using two powerful optimization algorithms; grid search and random search. Experimental results show improved performance using the optimized hyperparameters in the resulting hospital readmission prediction model. To show that HFWkNN model can be generalized, the results are compared with those of several kNN-based algorithms using two additional classification datasets in addition to the hospital readmission dataset. They are IRIS dataset and breast cancer dataset. These are common benchmark sets with real-world data. The model so far achieved higher classification accuracy than FkNN model. The best hyperparameter values for HFWkNN with grid search are γ=0.2249, ε=1.112 and εmin=0.01. Also, HFWkNN shows a performance of 80.00%, meaning that it has generalized well on the different data sets.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"30 9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128663201","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：