{"title":"ICANet: A Method of Short Video Emotion Recognition Driven by Multimodal Data","authors":"Bingdian Yang, Qian Zhang, Zhichao Liu","doi":"10.1109/INSAI56792.2022.00014","DOIUrl":"https://doi.org/10.1109/INSAI56792.2022.00014","url":null,"abstract":"With the fast development of artificial intelligence and short videos, emotion recognition has become one of the most important research topics in human-computer interaction. At present, most emotion recognition methods still stay in a single modality. However, in daily life, human beings will usually disguise their real emotions, which leads to the problem that the low accuracy of single modal emotion recognition. Moreover, it is not easy to distinguish similar emotions. Therefore, we propose a new approach denoted as ICANet to achieve multimodal short video emotion recognition by employing three different modalities of audio, video, and optical flow, making up for the lack of a single modality and then improving the accuracy of emotion recognition in short videos. ICANet has a better accuracy of 80.77% on the IEMOCAP benchmark. The cross-modal fusion method of short video emotion recognition established in this paper can effectively improve the accuracy of emotion recognition in human-computer interaction scenarios.","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131157549","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}
Weiqing Yao, Chengxuan Jiang, Xian Luo, Zhiwei Bao
{"title":"A FNV Based IPv6 Address Autoconfiguration Scheme for Power IoT Sensory Device","authors":"Weiqing Yao, Chengxuan Jiang, Xian Luo, Zhiwei Bao","doi":"10.1109/INSAI56792.2022.00048","DOIUrl":"https://doi.org/10.1109/INSAI56792.2022.00048","url":null,"abstract":"The construction of a new power system based on new energy has recently attracted a lot of attention, posing both a significant obstacle and an incredible potential for the advancement of the conventional power grid. Internet of Things (IoT) plays a crucial role in developing smart grid for its enormous benefit in supplying massive data and enabling connectivity for communication among various different types of power equipment. The sensing layer is of huge importance in the multi-layer structure of power IoT, offering data support for the estimation of power consumption, dynamic power allocation and a variety of other services. However, the design of IPv6 address autoconfiguration scheme in the sensing layer is challenging given the large number of sensory devices and the dynamic paradigm for interconnection. In this paper, a novel IPv6 address autoconfiguration scheme for power IoT sensory device is proposed to cope with the aforementioned problem. Utilizing Fowler-Noll-Vo (FNV) hash algorithm, this proposed approach can achieve a relatively low duplicated address rate in a densely concentrated distribution scenario. The feasibility and efficiency of the suggested configuration scheme are evaluated by the simulation results.","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115307034","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":"Commodity Price Analysis and Prediction Based on Ensemble Learning","authors":"Yang Gong, P. Zhang","doi":"10.1109/INSAI56792.2022.00045","DOIUrl":"https://doi.org/10.1109/INSAI56792.2022.00045","url":null,"abstract":"From the development of human social productive forces to a certain stage, commodities appear. Especially in modern society, people often need to buy things. When you buy something, there is a price issue. In order to help people grasp the price of a commodity, this paper proposes a commodity price analysis and prediction method based on ensemble learning. This method first obtains the historical data of the product; then simply analyzes the batch of data; then visualizes the data features; then adopts bagging regression in ensemble learning, using different weak classifiers (decision tree, support vector machine, K nearest neighbors), random forest, linear) for modeling comparison and analysis, the highest model accuracy rate can reach 0.9502; finally, five models are used to predict future prices. After testing, this method can be used in certain scenarios.","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116164509","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 Blockchain's Role in Promoting the Digital Economy Among the Belt and Road Countries","authors":"Jingxuan Li, Fei Gao, Bo Zhu, Ziyu Gu","doi":"10.1109/INSAI56792.2022.00031","DOIUrl":"https://doi.org/10.1109/INSAI56792.2022.00031","url":null,"abstract":"Digital economy has become the key in reshaping the global trade structure and changing the global competitive landscape. As a key technology for digital transformation and an important impetus for the development of digital economy, blockchain has been paid much more attention by global major economies. More and more countries regard blockchain as an important role in promoting their digital economy, especially among the Belt and Road countries. This paper analyzes the features of blockchain technology and its applications in empowering the digital economy. This paper also analyzes the development status of blockchain in key countries through three dimensions, including the national strategic layout, technical standards formulation and infrastructure construction, and application development and industry ecosystem. Furthermore, it analyzes the opportunities and challenges facing China's digital Belt and Road in Southeast Asia in blockchain-based digital economic cooperation and proposes suggestions for international cooperation of blockchain empowering digital economy.","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126729391","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":"Military Web Information Extraction Incorporating Resource Metadata Distribution","authors":"Hui Li, Jiahao Zhou, Wei Sun","doi":"10.1109/INSAI56792.2022.00019","DOIUrl":"https://doi.org/10.1109/INSAI56792.2022.00019","url":null,"abstract":"We analyze the relationship between the metadata distribution of military resources and the distribution of the web content in news, events, and resources in three major sections of military web stations, and thus we propose a method for extracting information from military web pages by integrating the metadata distribution and the basic features of military web pages to increase the difference between the content density and the noisy text density, to extract the content of military web pages. To verify the practical effectiveness of the proposed method in extracting information from military web pages, 69,379 web pages in the three major sections were randomly selected for the experiments in this work. The experimental results show that compared with the CETR, VIPS, SRV, and WNISK algorithms, the proposed method in this paper achieves better content extraction performance, with F-values of 98.21%, 97.11%, and 97.46% for the extraction of web page information in the three major sections respectively.","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130914124","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: Machine Learning in Visible Light Wireless Positioning System","authors":"Pan Zhu, Shibo Gong, Xuerui Zhao, Xinhuan Sun","doi":"10.1109/INSAI56792.2022.00032","DOIUrl":"https://doi.org/10.1109/INSAI56792.2022.00032","url":null,"abstract":"In the era of solid development of artificial intelligence, the combination of machine learning methods and wireless localization systems has led researchers to new research ideas to improve the performance of wireless localization in space and the plane. In this paper, we describe wireless localization systems and related traditional localization methods, in addition to classifying and analyzing a summary of machine learning methods in recent related localization problems. The performance of wireless localization systems is evaluated according to three traditional classifications of machine learning: supervised, unsupervised, and deep learning. We also provide insight into the algorithms used in machine learning and wireless localization system-related articles over the years. Finally, we provide an overview summary of wireless localization systems based on machine learning methods and give directions for the future development of wireless optical localization systems.","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"327 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113956110","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}
Cheng Qian, Bo Han, Yue Tang, Bohong Duan, Yinan Wu, Lei Wang
{"title":"Missile Attack Zone Fitting Based on K-SAE-SVM","authors":"Cheng Qian, Bo Han, Yue Tang, Bohong Duan, Yinan Wu, Lei Wang","doi":"10.1109/INSAI56792.2022.00047","DOIUrl":"https://doi.org/10.1109/INSAI56792.2022.00047","url":null,"abstract":"In short-range air combat, the UCAV has high maneuverability, and the situation on both sides is changing rapidly. Therefore, it is very important to solve the attack zone in real-time. It can be seen that the calculation of missile attack zone based on the optimal escape strategy of enemy aircraft is complex, and the solution time is about 200s, which completely cannot meet the needs of UCAV air combat. In terms of attack area fitting, the deep neural network has strong nonlinear fitting ability, and has very good real-time after training. It has been effectively applied in many fields, which will be an effective solution for nonlinear attack area fitting. In this paper, k-sparse autoencoder combined with SVM is proposed to build a fast solution network of missile attack zone. Simulation results show that the proposed method has good real-time performance after deep network training, which is verified to meet the decision needs in real time.","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128425198","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 GAN Based Data Augmentation Method for Road Pothole Detection","authors":"Lu Wang","doi":"10.1109/INSAI56792.2022.00010","DOIUrl":"https://doi.org/10.1109/INSAI56792.2022.00010","url":null,"abstract":"The detection accuracy of road potholes is not high due to the small number of positive samples. In order to expand the training dataset of the detection network and improve its detection accuracy, this paper proposes a road pothole data augmentation method combining generative adversarial network and image fusion technology. In this method, the clear forged pothole images with different morphometry are generated separately through SinGAN network, and the pothole image and road image are synthesized by Poisson image fusion. A mask image generation method for Poisson image fusion is also presented to further improve the edge smoothness of the fused part. The results of experiments have shown that the image samples generated by this method can significantly improve the accuracy of the road pothole detection network, and verified the effectiveness of this method.","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130812576","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":"Design-Based Research of Early Warning System for Drowning Based on Artificial Intelligence","authors":"Shaotong Cai, Yumei Gan, Mingjing Feng","doi":"10.1109/INSAI56792.2022.00049","DOIUrl":"https://doi.org/10.1109/INSAI56792.2022.00049","url":null,"abstract":"This paper mainly proposes and designs solutions to problems about early warning for drowning. The purpose is to carry out the planning of early warning for drowning by the use of artificial intelligence technology. By studying existing rescue systems for drowning and pertinent literature, combining the advantages of big data technology with the sore points of current early warning products for drowning, and employing strategies for system design to carry on practice, design and technology are integrated to realize the user information visualization, intelligent monitoring and other functions. Finally, A fast scanning system in swimming area is invented to locate drowning personnel and rescue them safely from the perspective of rescuers, by which the drowning monitoring can be achieved quickly and accurately. According to the particularity of drowning environment, the early warning system is also used as the information center to realize rescue plans with information technology, demanded form and efficient functions.","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129166707","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 Cluster-based Parallel Doppler Search Algorithm for Deep Space Exploration Applications","authors":"Yun Yu, Quan Guo","doi":"10.1109/INSAI56792.2022.00051","DOIUrl":"https://doi.org/10.1109/INSAI56792.2022.00051","url":null,"abstract":"The orbit predictions are subject to considerable errors due to the orbital maneuvers and systematic errors of the deep space probes. The detector signals are Doppler-shifted, so the correlated data cannot be integrated for a long time to achieve a higher signal-to-noise ratio. In addition, the computation of correlation increases with the increase of ground tracking stations, space detectors, and correlation channels. In this paper, we propose a cluster based Doppler search technique. First, a priory model is used to run fringe rotation and phase compensation relative to the center of the Earth. Second, a phase structure approach is applied to solve the Doppler frequency problem with high accuracy. Finally, a least square method is used to generate a polynomial model as the input to the correlation model. Due to the multi-channel signal and many grounds receiving stations, the data calculation can be enriched with Doppler search methods at the theoretical level and specific parallel algorithm design solutions at the application level. Through the analysis of the algorithms; the search speed can be improved by using cluster-distributed computing. The results of this study can help to improve the determination of deep space probe orbit capability by differential VLBI technology for application in deep space exploration in China.","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"30 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131775837","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}