{"title":"Stock Prediction Based On Event Graph","authors":"Chunfu Xie","doi":"10.1109/dsins54396.2021.9670610","DOIUrl":"https://doi.org/10.1109/dsins54396.2021.9670610","url":null,"abstract":"Stock market forecasting has always been a classic but challenging problem. We propose a method of stock price prediction based on the financial event graph. First, based on the deep learning method, events are extracted from the news to build the event graph. Second, the event graph is expressed by the TransD translation model and expressed as dense vectors. Last, taking the encoding vector of the event graph as input, we select the logistic regression model as the stock prediction model and get the output of the stock fluctuations of the next day. The accuracy and F1 score obtained by this method exceed the baseline model, which proves the effectiveness of the algorithm proposed by us.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121146344","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 the application framework of blockchain technology in digital creative industry","authors":"Xuetao Jin, Yijun Liu, Tianchang Zhang","doi":"10.1109/dsins54396.2021.9670574","DOIUrl":"https://doi.org/10.1109/dsins54396.2021.9670574","url":null,"abstract":"Blockchain which changes productivity and production relations, affects many industries. Using ASMI analysis method, this paper explores the business problems in the digital creative industry and the application of blockchain in solving the corresponding problems. The study found that before the advent of the blockchain, there were three main types of pain points in the digital creative industry: the lack of proof of existence function, the lack of coordination mechanisms among stakeholders, and the inability of the Internet to realize value transferring fully. Blockchain ensures that the information on the chain is immutable and traceable and can realize the confirmation of virtual assets and copyright and the circulation, distribution, and measurement of value. In the future, the expansion from the end of the industrial chain to the upstream and midstream, the formation of various applications with the consortium chain as the underlying protocol, cross-chain interoperability, and the application of non-fungible tokens will become the trend of the integration of blockchain and digital creative industry.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125785731","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":"Semantic Model-based Dynamic Adaptation Method for Heterogeneous Peripherals of Instrument","authors":"Junhua Chen, Ran Liu, Jiatong Zhang","doi":"10.1109/dsins54396.2021.9670623","DOIUrl":"https://doi.org/10.1109/dsins54396.2021.9670623","url":null,"abstract":"Different hardware interface circuits and corresponding external device drivers and functional modules are needed to be designed and developed to meet specific product configuration requirements in the traditional instrument development model. However, due to the high coupling degree of instrument software development system architecture and inefficient management and reuse of design resources, the development of instrument devices with different peripherals (sensors, actuators, etc.) based on the same type of instrument microcontroller chip(IMC) still needs a lot of development work, which has been unable to meet the needs of the rapid development of multi-protocol, multi-service, multi-perception and multi-series instrument equipment. This paper presents a dynamic adaptation method of instrument heterogeneous peripherals based on semantic model, which can support the rapid development of product families based on the same core chip but with different peripherals. By using the instrument-specific development kit, the semantic model is customized and instantiated according to the requirement information of heterogeneous peripheral devices. Then the model instance is parsed to obtain the resource adaptation software code of the heterogeneous peripheral. In particular, this method designs the statically compiled adaptation mode and the dynamically running adaptation mode respectively for resource-constrained and resource-rich instrument forms, which can support the rapid development of a family of products with the same core chip but different peripherals as well as the dynamic replacement of peripherals during the use of instrument and equipment. The method we proposed can reduce the product cost and shorten the development cycle of instrument products compared with the traditional development mode.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114982531","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":"Projections of Temperature and Precipitation in CMIP6 in Populated Cities in North America","authors":"Lai Yuan","doi":"10.1109/dsins54396.2021.9670629","DOIUrl":"https://doi.org/10.1109/dsins54396.2021.9670629","url":null,"abstract":"Climate change in the future will be intensified unless significant actions are taken to reduce or capture anthropogenic emissions. This paper uses the recently released CMIP6 simulation data to characterize specific changes in temperature and precipitation expected to take place in 28 populated cities in North America. This practice is based on examination of temperature and precipitation in four periods defined as historical, present day, near-future, and far-future. I first evaluate city-level estimations from CMIP6 with a reanalysis data from ERA5-Land for the present day. I then characterize spatial and seasonal changes in annual and monthly temperature and precipitation in the near and far-future for the 28 cities under SSP-585. Annual mean and maximum temperatures increase in all cities, while the annual minimum temperature shows the same trend but with some exceptions. The comparison across the four periods suggests an acceleration of warming in the second half of the century. Annual precipitation, however, shows an intensification in increasing maximums and decreasing minimums in many cities examined in this study, indicating higher risk of both droughts and extreme precipitation. I discuss the implications of the projected changes in terms of occurrence of extreme events, human health, and the loss and distributional effect in future economic development of the cities. Overall, significantly higher adverse impacts are expected, and the income gap between southern and northern cities will likely be widened. These findings provide city-level implications of climate change in North America for decision-makers.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130711863","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 Study of Counterfactual Inference Based on Instrumental Variables and Machine Learning","authors":"Youren Zhang, Wenxian Xie, Zhengxun He, Yifan Ren, Ziyan Jiang","doi":"10.1109/DSInS54396.2021.9670568","DOIUrl":"https://doi.org/10.1109/DSInS54396.2021.9670568","url":null,"abstract":"Causal inference is based on the inference of cause to effect and is part of causal analysis. It is an important method in data analysis and data science, and its application is very widespread in many fields. Counterfactual inference is a very important part of causal inference, which is the activity of thinking in which facts that have occurred in the past are negated and re-represented in order to construct a hypothesis of possibility and this paper specifically investigates two ideas for solving the counterfactual inference problem, the first approach is to use instrumental variables and the second approach is to use machine learning. In addition, based on the previous work which introduced Balancing Neural Network (BNN), this paper illustrates two ideas of modifying the architecture of BNN using shortcut connection. The assessment of performance of these two ideas will be done in future works.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126411312","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}
Yi Gao, Li Ma, Chongqing Shi, Yanliang Yang, Lin Li
{"title":"Analysis of the application status and prospect of smart bracelets in the elderly","authors":"Yi Gao, Li Ma, Chongqing Shi, Yanliang Yang, Lin Li","doi":"10.1109/dsins54396.2021.9670594","DOIUrl":"https://doi.org/10.1109/dsins54396.2021.9670594","url":null,"abstract":"With the rapid development of the aging population, artificial intelligence and big data in China, changes have occurred to the health needs, health care systems and services for the elderly, which shift from nursing equipment to medical facilities. In this paper, 472 elderly people in Wuhan, China, are taken as the research objects. The questionnaire survey is selected as a way to understand the use status and demand of the elderly for smart health bracelets. Moreover, how to combine the development of clinical nursing in the new era on the existing basis, so as to realize the informatization, intelligence and convenience of the smart health bracelet for the elderly, is discussed. It is hoped to provide a theoretical reference for the development of such smart health bracelets.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126432412","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":"Causal Analysis of Customer Churn Using Deep Learning","authors":"David Hason Rudd, Huan Huo, Guandong Xu","doi":"10.1109/DSInS54396.2021.9670561","DOIUrl":"https://doi.org/10.1109/DSInS54396.2021.9670561","url":null,"abstract":"Customer churn describes terminating a relationship with a business or reducing customer engagement over a specific period. Two main business marketing strategies play vital roles to increase market share dollar- value: gaining new and preserving existing customers. Customer acquisition cost can be five to six times that for customer retention, hence investing in customers with churn risk is smart. Causal analysis of the churn model can predict whether a customer will churn in the foreseeable future and assist enterprises to identify effects and possible causes for churn and subsequently use that knowledge to apply tailored incentives. This paper proposes a framework using a deep feedforward neural network for classification accompanied by a sequential pattern mining method on high-dimensional sparse data. We also propose a causal Bayesian network to predict cause probabilities that lead to customer churn. Evaluation metrics on test data confirm the XGBoost and our deep learning model outperformed previous techniques. Experimental analysis confirms that some independent causal variables representing the level of super guarantee contribution, account growth, and customer tenure were identified as confounding factors for customer churn with a high degree of belief. This paper provides a real-world customer churn analysis from current status inference to future directions in local superannuation funds.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132327634","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":"The Research of Computer Technology on the Efficiency of Visual inspection and Information Reading in Off-road Vehicles","authors":"Yulie Wang, Boku Li","doi":"10.1109/dsins54396.2021.9670597","DOIUrl":"https://doi.org/10.1109/dsins54396.2021.9670597","url":null,"abstract":"Objective method conclusion Explore the impact of off-road vehicle driving environment and instrument interface design factors on driver reading efficiency and visual inspection. The experimental principle of computer simulation of visual information is studied, and the eye movement data of drivers reading the instrument are recorded by ASL eye movement instrument; SPSS data analysis tool was used to analyze the experimental data indexes measured in the eye movement experiment.(1) Under the condition of simulated vibration, the lateral vibration of the instrument panel has a great impact on the driver’s reading;(2) The influence of vibration frequency on instrument reading efficiency is linear in the range of 0-20hz, and the influence of vibration frequency greater than 20Hz on reading efficiency decreases gradually;(3) The influence of vibration amplitude on instrument reading efficiency is nonlinear. When the amplitude is above 80pt, the influence on instrument reading efficiency gradually decreases.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134381958","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}
Qin Zhang, Jinlong Pan, Hu Chen, Yixiong Feng, Zhaoxi Hong
{"title":"Research on Change Path Optimization for Complex Mechanical Products Considering upgrade Risk","authors":"Qin Zhang, Jinlong Pan, Hu Chen, Yixiong Feng, Zhaoxi Hong","doi":"10.1109/dsins54396.2021.9670577","DOIUrl":"https://doi.org/10.1109/dsins54396.2021.9670577","url":null,"abstract":"Affected by uncertain factors such as customer demand, product design process will face with varying degrees of upgrade risk. In order to response to change requirements and reduce the impact of component changes, change path optimization for complex products considering upgrade risk is proposed. The goal of this work is to optimize change paths with multi-objective programming. The optimization model is constructed with the goal of minimizing the change complexity, the minimizing change propagation intensity and minimizing the change time. The improved whale algorithm is proposed to solve the model. A set of non-dominated solutions is obtained which can guide decision makers to choose the appropriate scheme. Finally, a product change path optimization for an elevator is given to verify the effectiveness of the proposed method.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121127503","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}
He Zhao, Qiming Wang, Zhaozhu Jia, Yiming Chen, Jianxin Zhang
{"title":"Bayesian based Facial Expression Recognition Transformer Model in Uncertainty","authors":"He Zhao, Qiming Wang, Zhaozhu Jia, Yiming Chen, Jianxin Zhang","doi":"10.1109/dsins54396.2021.9670628","DOIUrl":"https://doi.org/10.1109/dsins54396.2021.9670628","url":null,"abstract":"Facial expression recognition (FER) has always been a major researching area. Accurate and robust FER system remains challenging due to the environment influence of human face, such as posture transformation, light illumination and occlusion. Besides, facial expression itself is extremely complex with emotion overlapping which determines that the expression dataset is inevitable with mislabeled or uncertain data. In this paper, we propose a new Transformer based architecture for the FER task combined with Bayesian theory. We also modify the feature extractor module and training strategy (namely Adapted-SCN) against the uncertainty from training data. Our novel architecture improves the performance by up to 90.86% accuracy on FERPlus and 74.69% accuracy on FER2013, respectively.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117016756","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}