Pub Date : 2021-10-13DOI: 10.1109/icisfall51598.2021.9627424
C. Ezeife, Mahreen Nasir, Ritu Chaturvedi, Angel Veliz Castro
To promote big data application access, usage and deployment, this paper presents a downloadable open source code implementation for an E-Commerce Recommendation system, HSPRec (Historical Sequential Pattern Recommendation System), in JAVA. The HSPRec system is composed of six different modules for generating purchase/click sequential databases, mining sequential patterns, computing click purchase similarities, generating purchase sequential rules, computing weights for frequent purchase patterns through Weighted Frequent Purchase Pattern Miner, and normalization of the user-item ratings to predict level of interest. The source code of each module and the main runner are discussed under four possible headings of running environment, input data files and format, minimum support format, output data files and format. The overall goal of the HSPRec system is to improve E-commerce Recommendation accuracy by incorporating more complex sequential patterns of user purchase and click stream behavior learned through frequent sequential purchase patterns. HSPRec provides more accurate recommendations than the tested comparative systems.
{"title":"The HSPRec E-Commerce System Open Source Code Implementation","authors":"C. Ezeife, Mahreen Nasir, Ritu Chaturvedi, Angel Veliz Castro","doi":"10.1109/icisfall51598.2021.9627424","DOIUrl":"https://doi.org/10.1109/icisfall51598.2021.9627424","url":null,"abstract":"To promote big data application access, usage and deployment, this paper presents a downloadable open source code implementation for an E-Commerce Recommendation system, HSPRec (Historical Sequential Pattern Recommendation System), in JAVA. The HSPRec system is composed of six different modules for generating purchase/click sequential databases, mining sequential patterns, computing click purchase similarities, generating purchase sequential rules, computing weights for frequent purchase patterns through Weighted Frequent Purchase Pattern Miner, and normalization of the user-item ratings to predict level of interest. The source code of each module and the main runner are discussed under four possible headings of running environment, input data files and format, minimum support format, output data files and format. The overall goal of the HSPRec system is to improve E-commerce Recommendation accuracy by incorporating more complex sequential patterns of user purchase and click stream behavior learned through frequent sequential purchase patterns. HSPRec provides more accurate recommendations than the tested comparative systems.","PeriodicalId":240142,"journal":{"name":"2021 IEEE/ACIS 20th International Fall Conference on Computer and Information Science (ICIS Fall)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116352794","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 : 2021-10-13DOI: 10.1109/icisfall51598.2021.9627447
Quanfeng Wang, Yuanxu Zhang, Chen Li, Jian Gao
Underwater pose estimation plays an important role in the process of underwater positioning and operation. In this paper, the point cloud data are collected by a depth camera, and the obtained point cloud data are clustered by RanSanc algorithm to accurately identify the 3D point cloud data of the target. By extracting the view feature histogram(VFH) of the target 3D point cloud data for subsequent pose estimation research, the time-consuming and labor-consuming caused by the large amount of overall point cloud data is avoided. Then, the VFH descriptors in different pose are trained and calibrated by the two-dimensional code truth measurement system, and the training set is saved by using the kd-tree neighbor search structure. Finally, the accuracy and feasibility of the proposed pose estimation algorithm are verified in a water tank experiments.
{"title":"Point Cloud-based 3D Underwater Pose Estimation Using RANSAC and VFH Descriptors","authors":"Quanfeng Wang, Yuanxu Zhang, Chen Li, Jian Gao","doi":"10.1109/icisfall51598.2021.9627447","DOIUrl":"https://doi.org/10.1109/icisfall51598.2021.9627447","url":null,"abstract":"Underwater pose estimation plays an important role in the process of underwater positioning and operation. In this paper, the point cloud data are collected by a depth camera, and the obtained point cloud data are clustered by RanSanc algorithm to accurately identify the 3D point cloud data of the target. By extracting the view feature histogram(VFH) of the target 3D point cloud data for subsequent pose estimation research, the time-consuming and labor-consuming caused by the large amount of overall point cloud data is avoided. Then, the VFH descriptors in different pose are trained and calibrated by the two-dimensional code truth measurement system, and the training set is saved by using the kd-tree neighbor search structure. Finally, the accuracy and feasibility of the proposed pose estimation algorithm are verified in a water tank experiments.","PeriodicalId":240142,"journal":{"name":"2021 IEEE/ACIS 20th International Fall Conference on Computer and Information Science (ICIS Fall)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133875756","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}
Welcome to ICIS 2021-Fall. The 21st International Fall Virtual Conference on Computer and Information Science (ICIS 2021-Fall) is sponsored by the Institute of Electrical and Electronics Engineers (IEEE) and the International Association for Computer and Information Science (ACIS) and in cooperation with Northwest Polytechnical University The purpose of ICIS is to bring together researchers and practitioners from academia, industry, and government to exchange their research ideas and results and to discuss the state of the art in the areas of the conference. In addition, the participants of the conference will have a chance to hear from invited speaker Peter Marwedel, TU Dortmund, Germany. I would like to thank the Conference Co-Chairs Jiangbin Zheng, School of Software, Northwestern Polytechnical University, China, Simon Xu, Algoma University, Canada; the Program Co-Chairs Kailong Zhang, School of Computer, Northwestern Polytechnical University, China, Qun Chen, School of Computer, Northwestern Polytechnical University, China; and the members of the Program Committee for their hard work. And most importantly, we would like to thank all the authors for sharing their ideas and experiences through their outstanding papers contributed to the conference. We hope that ICIS 2021-Fall will be successful and enjoyable to all participants.
{"title":"Message from General Chair","authors":"F. Quaglia","doi":"10.1109/pads.2008.3","DOIUrl":"https://doi.org/10.1109/pads.2008.3","url":null,"abstract":"Welcome to ICIS 2021-Fall. The 21st International Fall Virtual Conference on Computer and Information Science (ICIS 2021-Fall) is sponsored by the Institute of Electrical and Electronics Engineers (IEEE) and the International Association for Computer and Information Science (ACIS) and in cooperation with Northwest Polytechnical University The purpose of ICIS is to bring together researchers and practitioners from academia, industry, and government to exchange their research ideas and results and to discuss the state of the art in the areas of the conference. In addition, the participants of the conference will have a chance to hear from invited speaker Peter Marwedel, TU Dortmund, Germany. I would like to thank the Conference Co-Chairs Jiangbin Zheng, School of Software, Northwestern Polytechnical University, China, Simon Xu, Algoma University, Canada; the Program Co-Chairs Kailong Zhang, School of Computer, Northwestern Polytechnical University, China, Qun Chen, School of Computer, Northwestern Polytechnical University, China; and the members of the Program Committee for their hard work. And most importantly, we would like to thank all the authors for sharing their ideas and experiences through their outstanding papers contributed to the conference. We hope that ICIS 2021-Fall will be successful and enjoyable to all participants.","PeriodicalId":240142,"journal":{"name":"2021 IEEE/ACIS 20th International Fall Conference on Computer and Information Science (ICIS Fall)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132916109","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 : 2021-10-13DOI: 10.1109/icisfall51598.2021.9627366
Mucong Gao, Chunfang Li, Rui Yang, Minyong Shi, Jintian Yang
Point cloud is one of the data sources widely used in many fields, such as 3D scanning calculation and computer vision, and information extraction is a necessary link in point cloud processing, analysis, and application. The experimental data is the dense point cloud model scanned by a 3D scanner. According to the characteristics of the model data, this paper proposes a dense point cloud foot model extraction method based on Euclidean distance, that is, judge the adjacent points of the dense point cloud data based on Euclidean distance, identify the redundant parts outside the foot model, and then extract the foot model. The results show that this method can identify the redundant part well, and the extracted foot model is also effective.
{"title":"Point Cloud Foot Model Extraction Algorithm for 3D Foot Model Scanner","authors":"Mucong Gao, Chunfang Li, Rui Yang, Minyong Shi, Jintian Yang","doi":"10.1109/icisfall51598.2021.9627366","DOIUrl":"https://doi.org/10.1109/icisfall51598.2021.9627366","url":null,"abstract":"Point cloud is one of the data sources widely used in many fields, such as 3D scanning calculation and computer vision, and information extraction is a necessary link in point cloud processing, analysis, and application. The experimental data is the dense point cloud model scanned by a 3D scanner. According to the characteristics of the model data, this paper proposes a dense point cloud foot model extraction method based on Euclidean distance, that is, judge the adjacent points of the dense point cloud data based on Euclidean distance, identify the redundant parts outside the foot model, and then extract the foot model. The results show that this method can identify the redundant part well, and the extracted foot model is also effective.","PeriodicalId":240142,"journal":{"name":"2021 IEEE/ACIS 20th International Fall Conference on Computer and Information Science (ICIS Fall)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131896041","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 : 2021-10-13DOI: 10.1109/icisfall51598.2021.9627456
M. Wang, Wei Niu, Yangyang Zhao
The failure rate of capacitors is high in the circuit system, and in the system with high requirement for capacitance reliability, it is very important to predict the remaining useful life accurately. In this paper, a particle filter method based on genetic algorithm is proposed to predict the remaining useful life of capacitors. Using the capacitance data set published by NASA, an exponential degradation model is established, and the resampling procedure in traditional particle filter method is optimized by crossover, mutation and optimization in genetic algorithm to increase the particle diversity, and to propel particles move to the high likelihood region. Therefore, the particle depletion problem caused by the resampling step in the traditional particle filter is improved to some extent. The simulation results show that the particle filter method based on genetic algorithm can be used to achieve more accurate prediction of remaining life of electrolyte capacitor.
{"title":"Remaining Useful Life Prediction of Capacitor Based on Genetic Algorithm and Particle Filter","authors":"M. Wang, Wei Niu, Yangyang Zhao","doi":"10.1109/icisfall51598.2021.9627456","DOIUrl":"https://doi.org/10.1109/icisfall51598.2021.9627456","url":null,"abstract":"The failure rate of capacitors is high in the circuit system, and in the system with high requirement for capacitance reliability, it is very important to predict the remaining useful life accurately. In this paper, a particle filter method based on genetic algorithm is proposed to predict the remaining useful life of capacitors. Using the capacitance data set published by NASA, an exponential degradation model is established, and the resampling procedure in traditional particle filter method is optimized by crossover, mutation and optimization in genetic algorithm to increase the particle diversity, and to propel particles move to the high likelihood region. Therefore, the particle depletion problem caused by the resampling step in the traditional particle filter is improved to some extent. The simulation results show that the particle filter method based on genetic algorithm can be used to achieve more accurate prediction of remaining life of electrolyte capacitor.","PeriodicalId":240142,"journal":{"name":"2021 IEEE/ACIS 20th International Fall Conference on Computer and Information Science (ICIS Fall)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115938542","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 : 2021-10-13DOI: 10.1109/icisfall51598.2021.9627474
Guangting Li, Xin Zhang, Shikang Nie, Yibo Chen, Chenchen Lin, Yifeng He
In this paper, basing on the region character presented by the width of the road in SAR image, a new road extraction frame, combing the image dynamics with watershed transformation, is constructed. Firstly, the image dynamics calculation is researched, and a fast calculation of ridge dynamics, which is performed by uniting the one dimension dynamics of different directions, is proposed. Then, the ridge dynamics is used to extract the road seeds. Finally, the regions, which belong to the results of watershed transformation and contain the road seeds, are merged for road extraction. Both the bright lines and the dark lines in SAR images are extracted and constitute the comparatively integrated road net, which illustrates the effectiveness of the proposed method.
{"title":"Road Extraction in SAR Iimage Based on the Image Dynamics and Watershed Transformation","authors":"Guangting Li, Xin Zhang, Shikang Nie, Yibo Chen, Chenchen Lin, Yifeng He","doi":"10.1109/icisfall51598.2021.9627474","DOIUrl":"https://doi.org/10.1109/icisfall51598.2021.9627474","url":null,"abstract":"In this paper, basing on the region character presented by the width of the road in SAR image, a new road extraction frame, combing the image dynamics with watershed transformation, is constructed. Firstly, the image dynamics calculation is researched, and a fast calculation of ridge dynamics, which is performed by uniting the one dimension dynamics of different directions, is proposed. Then, the ridge dynamics is used to extract the road seeds. Finally, the regions, which belong to the results of watershed transformation and contain the road seeds, are merged for road extraction. Both the bright lines and the dark lines in SAR images are extracted and constitute the comparatively integrated road net, which illustrates the effectiveness of the proposed method.","PeriodicalId":240142,"journal":{"name":"2021 IEEE/ACIS 20th International Fall Conference on Computer and Information Science (ICIS Fall)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122098463","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 : 2021-10-13DOI: 10.1109/icisfall51598.2021.9627419
Wenqian Shang, Sunyu Zhu, Dong Xiao
With the constant maturity of deep learning technology, human-computer dialogue has become a research hotspot in natural language processing. People in academia and industry are very concerned about it. The extensive use of artificial intelligence and deep learning technology in the human-machine dialogue system and the deep neural network modeling for text semantics are of great significance in promoting human-computer dialogue technologies and the application of human-computer dialogue to serve humanity better. Based on the above background, this paper focuses on the research of the human-computer dialogue system based on the improved seq2seq model, using the pre-trained Bert improved model as the codec modeling, and addressing the lack of Q&A data sets, the imbalance of category distribution, and the robustness of the model. These problems can be solved by adding disturbance structure adversarial sample training.
{"title":"Research On Human-computer Dialogue Based On Improved Seq2seq Model","authors":"Wenqian Shang, Sunyu Zhu, Dong Xiao","doi":"10.1109/icisfall51598.2021.9627419","DOIUrl":"https://doi.org/10.1109/icisfall51598.2021.9627419","url":null,"abstract":"With the constant maturity of deep learning technology, human-computer dialogue has become a research hotspot in natural language processing. People in academia and industry are very concerned about it. The extensive use of artificial intelligence and deep learning technology in the human-machine dialogue system and the deep neural network modeling for text semantics are of great significance in promoting human-computer dialogue technologies and the application of human-computer dialogue to serve humanity better. Based on the above background, this paper focuses on the research of the human-computer dialogue system based on the improved seq2seq model, using the pre-trained Bert improved model as the codec modeling, and addressing the lack of Q&A data sets, the imbalance of category distribution, and the robustness of the model. These problems can be solved by adding disturbance structure adversarial sample training.","PeriodicalId":240142,"journal":{"name":"2021 IEEE/ACIS 20th International Fall Conference on Computer and Information Science (ICIS Fall)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128971010","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 : 2021-10-13DOI: 10.1109/icisfall51598.2021.9627360
Han Bingjie, Niu Wei, Wang Jichao
Remaining Useful Life (RUL) estimation is the most common task in the research field of prognostics and health management (PHM). Accurate RUL estimation can avoid accidents, maximize equipment utilization, and minimize maintenance costs. RUL estimation based on performance degradation data is a hot spot in current research. The data-driven method can find out the relationship between the sensor data and the system degradation level with run-to-failure data and do not require any domain knowledge. RUL estimation can be carried out even when it is difficult to obtain the mathematical model of system degradation process. Sensors are used to collect data and monitor performance index. The actual system will experience multiple working conditions from the initial state to the performance failure process, and different working conditions have different impact on system degradation. In order to solve the problem that the degradation trend of sensor data is not declining obviously and the prediction of residual life is not accurate, a similar residual remaining useful life prediction method based on operating conditions clustering analysis and information fusion is proposed. Similarity-based methods are suitable for RUL estimation when complex systems cannot use data learning to build a global model. The core idea of RUL estimation based on similarity method is that if the test samples have similar degradation performance as the reference samples, then they may have similar RUL. In this paper, considering the influence of system operating conditions and sensor sensitivity on aero-engine life prediction, a remaining life estimation method based on multi-information fusion residual similarity model is proposed. Firstly, different working conditions were analyzed by clustering, and the data of various sensors were normalized. Then, the data of multiple sensors with different sensitivity were fused into a health index related to system degradation by the information fusion method. The distance between the degradation curve of the test sample and the degradation trajectory of the similar model was taken as the scoring basis, and the closest degradation curves were selected according to the scoring level. Finally, the closest similar degradation curves were selected according to the scores, and the Remaining Useful Life was predicted based on the residual life of these curves. The validity of the proposed method is verified by the failure data test of aero turbofan engine. The experimental results show that the proposed method has high accuracy and versatility when a large number of historical data are available. By comparing the estimated life of different breakpoints, it is found that the Remaining Useful Life estimation becomes more accurate with the increase of the proportion of verified data. Compared with other related methods, this method has achieved better results in predicting accuracy.
{"title":"An Improved Similarity-based Prognostics Method for Remaining Useful Life Estimation of Aero-Engine","authors":"Han Bingjie, Niu Wei, Wang Jichao","doi":"10.1109/icisfall51598.2021.9627360","DOIUrl":"https://doi.org/10.1109/icisfall51598.2021.9627360","url":null,"abstract":"Remaining Useful Life (RUL) estimation is the most common task in the research field of prognostics and health management (PHM). Accurate RUL estimation can avoid accidents, maximize equipment utilization, and minimize maintenance costs. RUL estimation based on performance degradation data is a hot spot in current research. The data-driven method can find out the relationship between the sensor data and the system degradation level with run-to-failure data and do not require any domain knowledge. RUL estimation can be carried out even when it is difficult to obtain the mathematical model of system degradation process. Sensors are used to collect data and monitor performance index. The actual system will experience multiple working conditions from the initial state to the performance failure process, and different working conditions have different impact on system degradation. In order to solve the problem that the degradation trend of sensor data is not declining obviously and the prediction of residual life is not accurate, a similar residual remaining useful life prediction method based on operating conditions clustering analysis and information fusion is proposed. Similarity-based methods are suitable for RUL estimation when complex systems cannot use data learning to build a global model. The core idea of RUL estimation based on similarity method is that if the test samples have similar degradation performance as the reference samples, then they may have similar RUL. In this paper, considering the influence of system operating conditions and sensor sensitivity on aero-engine life prediction, a remaining life estimation method based on multi-information fusion residual similarity model is proposed. Firstly, different working conditions were analyzed by clustering, and the data of various sensors were normalized. Then, the data of multiple sensors with different sensitivity were fused into a health index related to system degradation by the information fusion method. The distance between the degradation curve of the test sample and the degradation trajectory of the similar model was taken as the scoring basis, and the closest degradation curves were selected according to the scoring level. Finally, the closest similar degradation curves were selected according to the scores, and the Remaining Useful Life was predicted based on the residual life of these curves. The validity of the proposed method is verified by the failure data test of aero turbofan engine. The experimental results show that the proposed method has high accuracy and versatility when a large number of historical data are available. By comparing the estimated life of different breakpoints, it is found that the Remaining Useful Life estimation becomes more accurate with the increase of the proportion of verified data. Compared with other related methods, this method has achieved better results in predicting accuracy.","PeriodicalId":240142,"journal":{"name":"2021 IEEE/ACIS 20th International Fall Conference on Computer and Information Science (ICIS Fall)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123845334","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 : 2021-10-13DOI: 10.1109/icisfall51598.2021.9627470
Huawen Ma, Jixin Ma, Han Wang, Pengsheng Li, W.-C. Du
Sentiment analysis technologies have a strong impact on financial markets. In recent years there has been increasing interest in analyzing the sentiment of investors. The objective of this paper is to evaluate the current state of the art and synthesize the published literature related to the financial sentiment analysis, especially in investor sentiment for prediction of stock price. Starting from this overview the paper provides answers to the questions about how and to what extent research on investor sentiment analysis and stock price trend forecasting in the financial markets has developed and which tools are used for these purposes remains largely unexplored. This paper represents the comprehensive literature-based study on the fields of the investors sentiment analytics and machine learning applied to analyzing the sentiment of investors and its influencing stock market and predicting stock price.
{"title":"A Comprehensive Review of Investor Sentiment Analysis in Stock Price Forecasting","authors":"Huawen Ma, Jixin Ma, Han Wang, Pengsheng Li, W.-C. Du","doi":"10.1109/icisfall51598.2021.9627470","DOIUrl":"https://doi.org/10.1109/icisfall51598.2021.9627470","url":null,"abstract":"Sentiment analysis technologies have a strong impact on financial markets. In recent years there has been increasing interest in analyzing the sentiment of investors. The objective of this paper is to evaluate the current state of the art and synthesize the published literature related to the financial sentiment analysis, especially in investor sentiment for prediction of stock price. Starting from this overview the paper provides answers to the questions about how and to what extent research on investor sentiment analysis and stock price trend forecasting in the financial markets has developed and which tools are used for these purposes remains largely unexplored. This paper represents the comprehensive literature-based study on the fields of the investors sentiment analytics and machine learning applied to analyzing the sentiment of investors and its influencing stock market and predicting stock price.","PeriodicalId":240142,"journal":{"name":"2021 IEEE/ACIS 20th International Fall Conference on Computer and Information Science (ICIS Fall)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132376021","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 : 2021-10-13DOI: 10.1109/icisfall51598.2021.9627398
Honghao Gao, Yuan Zhang
This paper presents a Reinforcement Learning (RL) based rate control scheme for low latency video communication with High Efficiency Video Coding (HEVC). To avoid buffer overflow and underflow with a small buffer size constraint, we propose a new bit allocation and Quantization Parameter (QP) decision method based on the buffer status to control the buffer occupancy. Different from the heuristics design, the proposed RL-based rate control algorithm uses a neural network to allocate the target bit number and determine the QP value. Experimental results show that the proposed scheme effectively reduces the bit rate fluctuation and can avoid buffer overflow and underflow, which ensures a higher control accuracy and more consistent video quality than other existing methods.
{"title":"Rate Control with Delay Constraint for H.265/HEVC","authors":"Honghao Gao, Yuan Zhang","doi":"10.1109/icisfall51598.2021.9627398","DOIUrl":"https://doi.org/10.1109/icisfall51598.2021.9627398","url":null,"abstract":"This paper presents a Reinforcement Learning (RL) based rate control scheme for low latency video communication with High Efficiency Video Coding (HEVC). To avoid buffer overflow and underflow with a small buffer size constraint, we propose a new bit allocation and Quantization Parameter (QP) decision method based on the buffer status to control the buffer occupancy. Different from the heuristics design, the proposed RL-based rate control algorithm uses a neural network to allocate the target bit number and determine the QP value. Experimental results show that the proposed scheme effectively reduces the bit rate fluctuation and can avoid buffer overflow and underflow, which ensures a higher control accuracy and more consistent video quality than other existing methods.","PeriodicalId":240142,"journal":{"name":"2021 IEEE/ACIS 20th International Fall Conference on Computer and Information Science (ICIS Fall)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133354296","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：