2021 International Conference on Networking Systems of AI (INSAI)最新文献

{"title":"Development of AI Hair Follicle Detecting System and Related Biomedical Products","authors":"Xin Zhang, Ruonan Zheng, Jinwen Lin, Yanru Zeng, Yuming Zheng","doi":"10.1109/INSAI54028.2021.00019","DOIUrl":"https://doi.org/10.1109/INSAI54028.2021.00019","url":null,"abstract":"In order to solve the problems of hair loss, alopecia areata, prematurely greying, dandruff and other problems caused by health problems of hair follicles among young and middle-aged people, an AI hair follicle detecting system is developed through the detection of scalp and hair texture, and biomedical products related to hair follicles health are developed and improved. Through the algorithm design and simulation experiment of the detecting points, hardware architecture analysis and design, FPGA internal logic design, experimental analysis and the establishment of cloud server design schemes, a hair follicle detecting data platform and a portable detector that can be used in computers, mobile phones and other electronic terminals are developed, which enriches the hair follicle detection picture information, digitizes the pictures, compares and analyzes the digital 3D code of the image detected by the detector with the database, more accurately judges the user's hair follicle problem, and gives professional guidance. By cooperating with tracking services and recommendations of related treatment products, it establishes permanent hair follicle health files for users, regularly pushes professional knowledge for scalp care, and recommends targeted products and services for problematic scalp treatment. Combined with self-developed biomedical products made from pure plants, targeted treatment for hair follicles is carried out. The data detecting platform has been established; twenty or thirty portable devices with high accuracy in judging hair follicle problems have been produced and put in communities, shopping malls, head therapy salons, and pharmaceutical companies, offering good user experience. At present, more than a dozen enterprises and medical institutions have had the intention of further cooperation. The developed biomedical products have been well received after users experience in barbershops and head therapy salons, with a high purchase rate. The development of AI hair follicle detecting system and related biomedical products can specifically solve the problems of hair loss, alopecia areata, prematurely greying, and dandruff caused by the health problems of hair follicles among young and middle-aged people. The initial market feedback is good, and there is an urgent need to further expand and promote the platform and a space to enrich related products.","PeriodicalId":232335,"journal":{"name":"2021 International Conference on Networking Systems of AI (INSAI)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133927064","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":"Online Data Assimilation for Remote Space Manipulator Attitude Estimation with Time-varying Communication Delay","authors":"Runqiu Wu, Zhecaorui Wang, Yulong Yang, Zhaosheng Jian, Yan Qian, Shuo Wang","doi":"10.1109/INSAI54028.2021.00066","DOIUrl":"https://doi.org/10.1109/INSAI54028.2021.00066","url":null,"abstract":"The remote space manipulator system plays an important role in assisting astronauts on carrying out the space operation. It is necessary to estimate the attitude of space manipulator accurately and timely for real-time space-ground cooperation between the astronauts in the orbit and the mission center on the earth. However, the signals received by the mission center experience communication delay as well as measurement noise due to the complex cosmic environment. In this paper, we propose an online data assimilation framework to estimate the attitude of remote space manipulator system, taking account for both the observation uncertainty and the communication delays. In specific, we implement the framework using Kalman filtering. The simulation results show that the proposed framework delivers accurate real-time attitude estimation in facing with large measurement noise and communication delays.","PeriodicalId":232335,"journal":{"name":"2021 International Conference on Networking Systems of AI (INSAI)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122897462","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":"Deep Convolutional Neural Networks for Accurate Diagnosis of Nasopharyngeal Carcinoma in pCLE Images","authors":"Lin-bin Wu, Rong Cao, Lei Zhang, Huiliang Shang, Haitao Wu","doi":"10.1109/INSAI54028.2021.00032","DOIUrl":"https://doi.org/10.1109/INSAI54028.2021.00032","url":null,"abstract":"Objectives/Hypothesis: Probe-based confocal laser endomicroscopy(pCLE) can be used for the real-time cell-level optical biopsy of nasopharyngeal lesions in vivo. The development and validation of deep-learning-based automatic diagnosis of pCLE images are essential to the rapid screening and detection of nasopharyngeal carcinoma. Methods: From May 1, 2017, to November 30, 2017, the pCLE images were consecutively collected as samples in data sets from 31 patients with highly suspected NPC. The pCLE images were divided into training, cross-validation, and test sets to train, validate and test the proposed model. The proposed model's accuracy, sensitivity, and specificity are using pathological diagnosis as the gold standard. Analysis of the data is from May 15, 2019, to May 31, 2020. Results: The data set contains 3623 pCLE images in total. Eighty percent of the images were selected randomly as the training set, then another 10% as the validation set, and the last 10% as the test set. We proposed a deep learning model based on ResNet50. On the test data set, the model achieved an overall detection accuracy of 94.7%. The proposed model has higher accuracy, over 20.8%, compared to the best traditional supervised machine learning. Conclusions: Our algorithm automatically detected the nasopharyngeal carcinoma through screening images, which conduces to the otolaryngologists in their diagnosis. This deep-learning-based framework will be of great importance in the rapid screening and detecting of NPC.","PeriodicalId":232335,"journal":{"name":"2021 International Conference on Networking Systems of AI (INSAI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128011506","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":"A Kind of BEAM-PSO Algorithm Solving TSP","authors":"Q. Song","doi":"10.1109/INSAI54028.2021.00060","DOIUrl":"https://doi.org/10.1109/INSAI54028.2021.00060","url":null,"abstract":"In order to solve the TSP problem with large scale and high complexity, the Beam-PSO hybrid optimization algorithm was constructed based on the framework of the standard particle swarm optimization algorithm. Beam Search optimization technology was used to further enhance the deep development capability of standard PSO algorithm, in order to enhance the optimization performance of standard PSO algorithm. TSP standard data set and Matlab simulation test were adopted to compare with other algorithms. The algorithm’s optimal solution was closer to the known optimal solution, and the average value of multiple optimization results was smaller, proving that this algorithm had strong search performance and could effectively deal with discrete optimization problems.","PeriodicalId":232335,"journal":{"name":"2021 International Conference on Networking Systems of AI (INSAI)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128433554","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":"Based on Evaluation of English Teaching Ability by Particle Swarm Optimization Algorithm under the Background of Smart Classroom Teaching Model","authors":"Liufang Yi","doi":"10.1109/INSAI54028.2021.00020","DOIUrl":"https://doi.org/10.1109/INSAI54028.2021.00020","url":null,"abstract":"Smart classroom is the inevitable result of the deep integration of modern information technology and education. The use of particle swarm optimization algorithm can realize the process tracking of teaching and learning in and out of class, create an intelligent learning environment, and facilitate students to break through the limitations of time and space. Based the goal of improving English teaching ability, combined with the connotation and characteristics of smart classroom. Through evaluation of English teaching ability by Particle Swarm Optimization Algorithm this paper establishes smart classroom teaching model. Smart classroom teaching model for the coordinated development of teachers from the perspective of smart classroom teaching model exploration and application, in order to explore whether the teaching model can improve students' learning efficiency, reduce teachers' repetitive work and improve teaching effect. The conclusion of this paper can be employed to reference to promote the construction of English smart classroom teaching ability in vocational and technical institutes colleges, improve the quality of English teaching and promote the reform of English Teaching in vocational and technical institutes colleges.","PeriodicalId":232335,"journal":{"name":"2021 International Conference on Networking Systems of AI (INSAI)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124954220","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":"Artificial Intelligence Empowered Visual Communication Graphic Design","authors":"Muzi Qu, Yaxuan Liu, Yuan Feng","doi":"10.1109/INSAI54028.2021.00021","DOIUrl":"https://doi.org/10.1109/INSAI54028.2021.00021","url":null,"abstract":"The application of artificial intelligence technology in the field of art has been going on for several years, as an important art design category, visual communication graphic design needs to adapt to advanced technology. This research is conducted by art professionals based on the needs of today's art design and combined with the technological advantages of artificial intelligence. The purpose is to construct artificial intelligence application technology with practical significance. Apply artificial intelligence technology in the \"graphic design\" of visual communication. Trial design becomes more efficient and optimized in this research, we apply artificial intelligence technology as an intelligent design auxiliary tool to provide technical support for human designers, so that the graphic design is greatly reduced in difficulty and the presentation effect is improved. the assistive technology of artificial intelligence make the process of graphic design more efficient, copy and generate in a convenient way, making artistic design faster and more intelligent. Intelligent design not only has important theoretical significance, but also has very important engineering value.","PeriodicalId":232335,"journal":{"name":"2021 International Conference on Networking Systems of AI (INSAI)","volume":"255 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122203180","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":"Research on Sports Data Acquisition and Transmission Technology Based on VR","authors":"Shihong Yao, Wei Long, Lingxi Hu, Linhua Jiang","doi":"10.1109/INSAI54028.2021.00059","DOIUrl":"https://doi.org/10.1109/INSAI54028.2021.00059","url":null,"abstract":"Motion data acquisition and transmission technology is widely used in VR field. In recent years, with the development of related technologies, its application in the VR field has become increasingly perfect. In this regard, this paper will give a detailed overview of the relevant sports data collection methods and transmission technology, including the technology and principle of riding speed, human heart rate and turning angle, as well as the wired transmission technology and wireless transmission technology suitable for VR field, such as Bluetooth and WIFE data transmission technologies. In addition, this paper summarizes the methods and technologies in the existing literature, and compares the performance of these technologies. Finally, the shortcomings and future research trends of motion data acquisition and transmission technology for VR are summarized.","PeriodicalId":232335,"journal":{"name":"2021 International Conference on Networking Systems of AI (INSAI)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123242450","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":"A Review of Artificial Intelligence in Preoperative Clinical Staging of Liver Cancer","authors":"Haopeng Kuang, Zhongwei Yang, Xukun Zhang, Shunli Wang, Lihua Zhang","doi":"10.1109/INSAI54028.2021.00024","DOIUrl":"https://doi.org/10.1109/INSAI54028.2021.00024","url":null,"abstract":"Accurate staging of liver cancer is significant for preoperative planning, diagnosis, treatment, and prognosis. With the development of artificial intelligence technology, data-driven methods represented by machine learning are also applied in the staging task of liver cancer. In this process, more and more biochemical clinical test indicators have been added to the clinical staging system, increasing accuracy and limiting clinical application due to excessive complexity. In this paper, the existing artificial intelligence-related studies on liver cancer preoperative staging tasks were extensively collected. However, it was found that there were still some uniform limitations in these methods. Based on this, we propose designing an intelligent interactive framework for preoperative clinical staging that integrates identification, segmentation, and classification tasks. The framework aims to better apply ai-based approaches to clinical practice. In addition, to implement the framework proposed in this paper, we also propose establishing an extensive, multicenter, standardized open data set through interdisciplinary collaboration between clinical medicine and computer science.","PeriodicalId":232335,"journal":{"name":"2021 International Conference on Networking Systems of AI (INSAI)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114204139","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":"Research on Badminton Motion Recognition Based on Hidden Markov Model","authors":"Jiexin Liu, Xiaochun Wu","doi":"10.1109/INSAI54028.2021.00014","DOIUrl":"https://doi.org/10.1109/INSAI54028.2021.00014","url":null,"abstract":"In order to improve problems such as uncoordinated movements of exercisers and sports injuries, a badminton motion recognition method based on hidden Markov model is proposed, which uses non-visual sensing motion recognition based on multiple sensors to find out the problems existing in the technical movement during the movement and obtain the best motion effect. Firstly, four wearable inertial sensors were placed in several important parts of the experimental object, and each sensor collected signals of triaxial acceleration and angular velocity signals in three-dimensional space. Secondly, the HMM model is established through data acquisition, preprocessing, window segmentation, feature extraction and selection, classification and recognition. Finally, through three comparative experiments, the recognition rate was raised from 91.99% and 91.60% to 98.1%, effectively improving the recognition rate of badminton movements. The results of this study can provide scientific solutions to the technical movement problems existing in exercitation and promote the health management of the whole life cycle.","PeriodicalId":232335,"journal":{"name":"2021 International Conference on Networking Systems of AI (INSAI)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128548543","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":"Personalized Recommendation System of Innovation and Entrepreneurship Course Based on Collaborative Filtering","authors":"Dongliang Wang, Yaming Zheng, Zhixin Liu, Wenfeng Zheng, Jiawei Tian, Xinxin Fan","doi":"10.1109/INSAI54028.2021.00016","DOIUrl":"https://doi.org/10.1109/INSAI54028.2021.00016","url":null,"abstract":"This article will use the process and structure of personalized recommendation to design a recommendation system suitable for innovation and entrepreneurship course platform. It also conducts a comparative analysis of the existing innovation and entrepreneurship platforms to clarify the characteristics and attributes of the innovation and entrepreneurship platforms. Through comparative research on the use process, application scenarios, advantages and disadvantages of traditional personalized recommendation algorithms. On the basis of making full use of the characteristics of the innovation and entrepreneurship platform, a collaborative filtering algorithm was selected to complete the recommendation system design.","PeriodicalId":232335,"journal":{"name":"2021 International Conference on Networking Systems of AI (INSAI)","volume":"338 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133314425","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}