Yihan Ma, Jieteng Jiang, Shuo Dong, Chunmei Li, Xiyu Yan
{"title":"Book Recommendation Model Based on Wide and Deep Model","authors":"Yihan Ma, Jieteng Jiang, Shuo Dong, Chunmei Li, Xiyu Yan","doi":"10.1109/AIID51893.2021.9456524","DOIUrl":"https://doi.org/10.1109/AIID51893.2021.9456524","url":null,"abstract":"[Purpose] Personalized recommendation is one of the hottest research areas in recent years Recommendation systems developed by Google, Amazon, Alibaba and other companies have brought them huge benefits, which are recommendations based on big data analysis. However,For data sets with large data sparseness, traditional recommendation algorithms for historical records cannot obtain satisfactory recommendation results, and traditional recommendation algorithms often cannot discover the potential interests of users. In this paper, we managed to extend the personalized recommendation system to the University Library Lending system [Methodology]Firstly, to meet the challenge of data sparsity, we collected the information of readers and books in the borrowing records of Qinghai University Library in recent 20 years. Secondly, through the analysis and research of the Wide and Deep model, the recommendation model is obtained by joint training of LR (Logistic Regression) and DNN (Deep Neural Network) networks. Moreover, we improved the double-label of the Wide and Deep model into multiple labels and got the final model after extensive training. [Findings]The experimental results show that the accuracy of our book recommendation model is significantly better than traditional recommendation algorithms and hybrid recommendation algorithms. [Originality]Firstly we set up a large Qinghai University book data set for training and testing and verification.Secondly, completed the model migration and improvement of W & D. Through a large number of experiments for comparative research, it is concluded that the improved W & D model is suitable for book recommendation systems.The value of the AUC index of the traditional collaborative filtering model is the lowest. The AUC value of the weighted bipartite graph model is greater than the collaborative filtering model. The AUC value of the hybrid model is basically the same as that of the weighted bipartite graph model. The Wide & Deep model has the highest AUC value. Reached 0.75. Therefore, the Wide & Deep model is suitable for a book personalized recommendation system with sparse characteristics of big data.","PeriodicalId":412698,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124266134","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":"Pallet Detection Based on Halcon for Warehouse Robots","authors":"F. Jia, Zhaosheng Tao, Fusong Wang","doi":"10.1109/AIID51893.2021.9456540","DOIUrl":"https://doi.org/10.1109/AIID51893.2021.9456540","url":null,"abstract":"Pallet detection is the key step of cargo handling for warehouse robots. In order to improve the recognition rate of pallet detection due to the influence of complex background, a pallet detection method based on point cloud is proposed. In this method, time-of-flight (ToF) camera is used to collect the point cloud. ResNet50 neural network model which is provided by Halcon software is used for deep learning, and deep learning is used to extract the region of interest of pallet contour. The extracted region of interest is processed to obtain the regions of the pallet pockets, and the minimum rectangles surrounding each of the pocket regions are solved to obtain the position coordinates of the pocket centers. The experimental results show that the precision of pallet detection can reach 94.5%. This method has high recognition rate in complex background, and has reference value for the design of pallet detection system of warehouse robots.","PeriodicalId":412698,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121065948","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 Data Integrity of Information Management System Based on QKD Error-Correction","authors":"Guoshan Liu, Fu Liu","doi":"10.1109/AIID51893.2021.9456544","DOIUrl":"https://doi.org/10.1109/AIID51893.2021.9456544","url":null,"abstract":"The development of information technology has promoted the continuous progress of the information age. In all areas of society, information resources play a special role. The paper adopts the information management system and the QKD_SoC architecture to design the overall functional architecture. According to the processes and functions that the QKD software system needs to manage, each of functional module is divided, and the relationship between the internal modules of the SoC and the internal and external interfaces are designed. The startup process of the SoC system and the running process of the system are designed. A distributed heterogeneous environment for data storage is constructed, storage node positioning design is optimized, the association rule features of data in a distributed heterogeneous environment are extracted, and the fuzzy mean clustering method is used to classify external data and extract action features. The piecewise linear data fusion is realized in the high-dimensional phase space, the performance of the data balanced storage channel is improved, and the distributed storage and resource sharing of the data at the transmission link layer are realized. Experiments show that compared with traditional data storage methods, the research method in this paper has greatly improved the utilization of data space and data integrity, and has made a contribution to ensuring the integrity of data storage and transmission.","PeriodicalId":412698,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID)","volume":"267 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121326534","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 Incoherent Frequency Discrimination Algorithm of FM Telemetry Signal Based on GPU","authors":"Kuanfei Sun, Wenge Yang, Yiwen Jiao, Dong Li, Tianyi Chai, Chao Li","doi":"10.1109/AIID51893.2021.9456571","DOIUrl":"https://doi.org/10.1109/AIID51893.2021.9456571","url":null,"abstract":"To improve the flexibility of FM telemetry system and the universality of the hardware platform, an incoherent demodulation method of FM telemetry signal based on GPU is designed. Based on CUDA parallel operation architecture, the efficient orthogonal down-conversion module, parallel filter module, and incoherent frequency discrimination module are developed. The experimental results show that the demodulation method based on GPU is correct, efficient and reliable, and can realize the real-time demodulation of FM telemetry signal.","PeriodicalId":412698,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125939643","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":"Predicting the influence of Covid-19 on GDP with ensembled machine learning models","authors":"Yafei Wu, Youshuai Yang, Yudong Wu, Boshuai Ye","doi":"10.1109/AIID51893.2021.9456539","DOIUrl":"https://doi.org/10.1109/AIID51893.2021.9456539","url":null,"abstract":"Since it first broke out in 2019, the Covid-19 pandemic has made a huge impact on everyone's daily lives. As vaccination progresses smoothly in many countries and the pandemic gradually gets under control, it is important that we understand its impact on the global economy to fully recover from the damage Covid-19 has caused. In this paper, we analyzed over 50000 records of pandemic data for over 200 countries to identify the important factors affecting the GDP per capita of the countries. We also proposed a method ensembling three machine learning models predict a country's GDP based on pandemic data.","PeriodicalId":412698,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126025252","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 Neural Network Prediction and Decision-Making Methods in Environmental Economy Application Research in the System","authors":"Yanan Chen","doi":"10.1109/AIID51893.2021.9456480","DOIUrl":"https://doi.org/10.1109/AIID51893.2021.9456480","url":null,"abstract":"In today's life, people pay more and more attention to the development of environment and economy, so environmental protection issues are involved in daily work and life. The forecasting and decision-making method is to analyze various possible solutions and propose the best alternatives. This article introduces the theory of forecasting algorithms and their application scope and advantages; looking forward to the future, more new technologies will be used to optimize the model; finally, it is verified through examples that this strategy can bring the greatest benefits to the enterprise, so that it can adapt to the changing market environment and the economic system makes the right choice to improve the efficiency and other aspects of the desired effect.","PeriodicalId":412698,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127001222","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":"Adaptive Weighted Cost Multipath Routing on PISA","authors":"Zixi Cui, Yuxiang Hu, Saifeng Hou","doi":"10.1109/AIID51893.2021.9456453","DOIUrl":"https://doi.org/10.1109/AIID51893.2021.9456453","url":null,"abstract":"In this paper, we propose MP-Turbo, a dynamic weighted-cost multipath routing based on protocol independent switch architecture. In this algorithm, a non-equivalent hash threshold method is designed for the match-action pipeline. By dividing the continuous hash result space according to the weight proportion and mapping it to the corresponding ports, the redundancy of hash entries is avoided. The improved application combines the weighted routing logic of ordinary packet and the weight updating logic of probe packet, and performs the function of load balancing with state in a single node at line speed. The experimental results show that the end-to-end transmission delay of the system is reduced by more than 19% when the optimized weighted routing algorithm is applied to the existing load balancing application framework.","PeriodicalId":412698,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122837287","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":"Point Cloud Grid Reduction Method Based on Feature Parameters","authors":"Xiaohong Zhou, Hengxin Yang, Hao Yang","doi":"10.1109/AIID51893.2021.9456517","DOIUrl":"https://doi.org/10.1109/AIID51893.2021.9456517","url":null,"abstract":"A large amount of the 3D point cloud data obtained by 3D laser scanning technology are redundant, which is not conducive to computer storage and calculation and reduces the reconstruction efficiency. Considering the low accuracy of several point cloud reduction method and the lack of details, proposing a point cloud grid reduction method based on feature parameters. Firstly, the point cloud topological relationship is established by calculating the point cloud normal vector and curvature according to the KD-tree, and the product of multiple parameters which are used as the feature parameters; then, the voxel grid algorithm is used to divide the point cloud data and distinguish them according to the average curvature in each grid feature area and non-feature area; finally, different methods are used to simplify the point cloud in different areas. Through the comparative analysis of experiments, this paper shows that the method can improve the reconstruction efficiency, effectively avoid holes, and better retain the detailed features of the point cloud.","PeriodicalId":412698,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114140053","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}
Zhang Yipeng, Gao Xiang, Paul- Mengvi Gatpandan, Maryli F. Rosas, Daniel Jr. Dasig
{"title":"Public opinion hot topic discovery based on improved bacterial foraging algorithm","authors":"Zhang Yipeng, Gao Xiang, Paul- Mengvi Gatpandan, Maryli F. Rosas, Daniel Jr. Dasig","doi":"10.1109/AIID51893.2021.9456485","DOIUrl":"https://doi.org/10.1109/AIID51893.2021.9456485","url":null,"abstract":"In order to find the hot topic from public opinion and solve the problem that the topic mining accuracy is not high enough, the topic is disturbed by unrelated links and the topic cannot be focused on a point, the swarm intelligence algorithm is applied to topic mining, and an improved bacterial foraging algorithm is proposed. The algorithm improves the chemotaxis, copy and migration operations in the original algorithm, which makes up for the shortcomings of the original algorithm, and greatly improves the accuracy and convergence. The correlation value of web page is taken as the measurement of web page heat, and the heat evaluation model is established. The improved bacterial foraging algorithm is used to cluster the web pages. The results of experiments and other algorithms show that the algorithm has better clustering effect.","PeriodicalId":412698,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128251228","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":"Experimental study on the aerodynamic performance of the bionic rotor blades with non-smooth surface","authors":"Y. Xiong, De-Shun Kong","doi":"10.1109/AIID51893.2021.9456516","DOIUrl":"https://doi.org/10.1109/AIID51893.2021.9456516","url":null,"abstract":"The microstructure on shark skin is known to have a drag-reducing effect. But this design has rarely been used to reduce the air resistance of the blades. Based on bionic non-smooth theory and the microstructural features of shark skin, this paper investigates the aerodynamic performance of a rotor used in an unmanned-aerial vehicle (UAV) by arranging bionic non-smooth structural arrays on its upper surface. In this paper, four bionic rotor models were designed with different shapes and orientations, and the three bionic rotor models were selected by numerical simulation and compared with the original rotor for actual experimental tests. In the test, it was found that the bionic rotor blade with transverse grooves improved lift by 5.9% and reduced torque by 1.8% compared to the original blade. This work provides an effective way to improve the aerodynamic performance of rotor blades and increase the endurance of UAVs.","PeriodicalId":412698,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128631657","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}