{"title":"Online / Offline Capacity Allocation Method Considering Patient Choice Behavior","authors":"Wenwen Wang, Sen Li, Xiangling Li, Miao Yu","doi":"10.1109/ISCTIS58954.2023.10213105","DOIUrl":"https://doi.org/10.1109/ISCTIS58954.2023.10213105","url":null,"abstract":"For limited capacity of comprehensive hospitals, long waiting time for patients, and limited medical treatment in remote areas, this paper proposes the optimal capacity allocation of online/offline service channels in comprehensive hospitals under the patient's choice behavior. Under the dual-channel service strategy, a two-stage queuing game model is constructed, the decision-making relationship between offline service and online service of comprehensive hospitals is analyzed, and both the balanced decisions on patient arrival rate and capacity distribution rate are given. The results show that when the distribution rate is between a certain threshold, the waiting time of patients is greatly reduced, so that comprehensive hospital can maximize profits while improve social welfare; the necessary conditions for adopting a dual-channel service strategy are given; the optimal decisions of comprehensive hospital are given in different scenarios.","PeriodicalId":334790,"journal":{"name":"2023 3rd International Symposium on Computer Technology and Information Science (ISCTIS)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127747106","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":"Improved lightweight YOLOv5s Algorithm for Traffic Sign Recognition","authors":"Li Cao, Shao-bo Kang, Jin-peng Chen","doi":"10.1109/ISCTIS58954.2023.10213106","DOIUrl":"https://doi.org/10.1109/ISCTIS58954.2023.10213106","url":null,"abstract":"A lightweight traffic sign recognition method based on the YOLOv5s algorithm is proposed to address the drawbacks of the current road traffic sign model, such as sluggish detection speed, huge model, and many parameters. To increase the speed of detection, the lightweight GhostNet backbone network is first deployed, which further reduces the parameters and size of the model based on YOLOv5s. Second, the Anchor that is appropriate for the CCTSDB 2021 dataset is recreated using the K-means clustering technique. The NMS algorithm of the original network is then replaced with DIoU-NMS to enhance the recognition of veiled indicators and lower the missed detection rate. To increase the model's detection precision, the CIoU loss function of the original network is swapped out for the EIoU loss function. Research on the CCTSDB 2021 dataset reveals that while the parameters are lowered by 16.5%, the model size is reduced by 16%, and the FPS is increased by 7, the detection accuracy is only dropped by 2.1% when compared to the original YOLOv5s model. The improved algorithm can fulfill the mobile end of many scenarios with a balance of speed and accuracy requirements, as opposed to YOLOv3-tiny and other algorithms.","PeriodicalId":334790,"journal":{"name":"2023 3rd International Symposium on Computer Technology and Information Science (ISCTIS)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128017356","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 of Interactive Teaching System Based on Computer Vision Technology","authors":"Yanan Chen, Feng-ying Huang","doi":"10.1109/ISCTIS58954.2023.10213092","DOIUrl":"https://doi.org/10.1109/ISCTIS58954.2023.10213092","url":null,"abstract":"With the development of computer technology, visual algorithms and camera technology, non-contact human-computer interaction have gradually become the mainstream of people's daily life, and the campus should also follow the trend of the times to establish an epoch-making and more interactive modern teaching environment. This paper proposes a highly convenient and innovative interactive teaching system that integrates various cutting-edge technologies including gesture recognition technology, face recognition technology based on HOG feature computing, and Internet of Things technology. Teachers can use gestures to control computers after logging in through face recognition. Using subconscious and natural gestures to teach lesson can simplify computer-side operation and improve teachers' lecture efficiency.","PeriodicalId":334790,"journal":{"name":"2023 3rd International Symposium on Computer Technology and Information Science (ISCTIS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114211663","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":"Improved Fashion Classification Method Base on GooLeNet","authors":"Xiaojie Chen, Duzuo Qiang, Zhanghao Duan, Qian Zhao","doi":"10.1109/ISCTIS58954.2023.10213022","DOIUrl":"https://doi.org/10.1109/ISCTIS58954.2023.10213022","url":null,"abstract":"Traditional Image Classification algorithms have problems of high recognition error rate and low efficiency in fashion classification. So, the research proposes an improved model based on GooLeNet model.At first, we created a new inception network module which called inception-improved module.Compared with original inception module,Inception-improved module reduced the computational cost and improved the efficiency of the network.Secondly, we used Inception-improved modules to build the new model which named GooLeNet-improved and trained the model with Fashion image dataset. The experimental results show that the improved model GooLeNet-improved can obviously reduce the error rate of the fashion classification and improve the computational efficiency. The GooleNet-improved model achieved the accuracy of 87.1% on fashion image dataset, and the accuracy is respectively 0.8% higher than the original GooLeNet model.","PeriodicalId":334790,"journal":{"name":"2023 3rd International Symposium on Computer Technology and Information Science (ISCTIS)","volume":"238 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114754239","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":"Towards Designing an Intelligent Recommender System using Adaptive Collaborative Filtering Technique","authors":"Qi Zhang, Mideth B. Abisado","doi":"10.1109/ISCTIS58954.2023.10213045","DOIUrl":"https://doi.org/10.1109/ISCTIS58954.2023.10213045","url":null,"abstract":"In recent years, intelligent recommendation systems using adaptive collaborative filtering have received great attention due to their ability to provide personalized and relevant recommendations. The innovation of this study lies in proposing an adaptive collaborative intelligent recommendation model (ACIR), which combines adaptive collaborative filtering with context, user behavior, and movie feature information. It utilizes automatic encoders and deep learning algorithms to capture the characteristic relationships of the context, explore the internal connections between the context and users, and improve the accuracy and interpretability of the recommendation system to meet the personalized needs of users. The aim of this study is to predict user preferences by considering the characteristics of users, projects, and contexts, and to evaluate the potential changes in user preferences over time. In the experimental stage, LDOS CoMoDa was used to test and train the dataset, and the model was validated. Choose traditional collaborative recommendation, k-means algorithm, CAMF, and CAMF_ CM algorithm for comparison. After experimental verification, this article proposes that compared with other traditional recommendation algorithms, ACIR has higher accuracy and stronger application value","PeriodicalId":334790,"journal":{"name":"2023 3rd International Symposium on Computer Technology and Information Science (ISCTIS)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115804901","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":"An Enhanced Collision-Aware Min-Max A* Path Planning Algorithm (ECMMA*) in Automated Calibration Production Lines","authors":"Siying Li, Ling Zhu, Dongyan Wang, Yutian Cen, Guangyu Liu, Weiguo Fan","doi":"10.1109/ISCTIS58954.2023.10213017","DOIUrl":"https://doi.org/10.1109/ISCTIS58954.2023.10213017","url":null,"abstract":"In actual production, the collisions between components and surrounding objects often occur on automatic calibration lines. To solve these problems, an enhanced collision-aware min-max A* path planning algorithm (ECMMA*) based on the spatial and temporal features of component locations is proposed in this paper. ECMMA* determines in real time whether there is interference between the running path of the components and the coordinates of the surrounding objects. It also takes into account overall costs to optimize the path planning for automated calibration production lines. The experimental results show that the proposed method effectively reduces the distance and time of equipment movement, improves production efficiency and resource utilization, and ensures the effectiveness and safety of the paths.","PeriodicalId":334790,"journal":{"name":"2023 3rd International Symposium on Computer Technology and Information Science (ISCTIS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115246807","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 aircraft detection method based on improved YOLO","authors":"Beibei Zhang, Rui Zhang, Zhendong Hua","doi":"10.1109/ISCTIS58954.2023.10213115","DOIUrl":"https://doi.org/10.1109/ISCTIS58954.2023.10213115","url":null,"abstract":"This thesis presents an aircraft detection method based on the improved You Only Look Once (YOLO) algorithm. The traditional YOLO algorithm is efficient and accurate in target detection, but has some challenges in dealing with small and dense targets. To solve these problems, this paper proposes an aircraft detection method based on an improved YOLO algorithm.","PeriodicalId":334790,"journal":{"name":"2023 3rd International Symposium on Computer Technology and Information Science (ISCTIS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123042319","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":"CA-LAP: A Scheduling Model for Video Streaming Data Transcoding Tasks in a Distributed Environment","authors":"Chengxi Gao, Lan Shen, Yanhong Jing, Jien-Lung Wu","doi":"10.1109/ISCTIS58954.2023.10213057","DOIUrl":"https://doi.org/10.1109/ISCTIS58954.2023.10213057","url":null,"abstract":"For the task scheduling optimization of video stream transcoding in distributed environment, the traditional scheduling strategy is difficult to achieve load balancing. In this paper, we propose a distributed video streaming transcoding CA-LAP load balancing strategy, which is based on Dubbo and Zookeeper architecture, and uses the consistent hashing method to map transcoding requests to a hash ring of node hashes to initially achieve load balancing. Based on this, the least active priority method is applied and improved to achieve dynamic scheduling of local nodes around the request, and the availability of the selected nodes is guaranteed using the DVR policy. The experimental results show that the proposed CA-LAP policy shows superiority in node load variance metrics for large-scale distributed video stream transcoding compared to using only the consistent hashing method, and achieves better application results in real transcoding scenarios. This study provides a new load balancing solution for the field of distributed video stream transcoding, which helps to improve system performance and scalability.","PeriodicalId":334790,"journal":{"name":"2023 3rd International Symposium on Computer Technology and Information Science (ISCTIS)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123605979","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 prioritization approach based on a cross-network model of SDGs","authors":"Qiuyue Song, Rongxing Wu","doi":"10.1109/ISCTIS58954.2023.10213069","DOIUrl":"https://doi.org/10.1109/ISCTIS58954.2023.10213069","url":null,"abstract":"To create a world of shared prosperity, the Sustainable Development Goals (SDGs) promote cooperation among all people. In order to better explore the influence relationship between SDGs, this paper appropriately discusses solutions from a network perspective. We modeled the interactions between multiple SDGs through network analysis. We selected 17 specific policy development goals based on the degree of sustainability achieved in Germany in recent years. Then we developed a first-order network model based on a cross-influence matrix and test the validity of the model. This study finds the priority of each objective and proposes the highest priority.","PeriodicalId":334790,"journal":{"name":"2023 3rd International Symposium on Computer Technology and Information Science (ISCTIS)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123616116","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 of a Flexible Analysis System for Coal Mine Monitoring","authors":"J. Qian","doi":"10.1109/ISCTIS58954.2023.10213130","DOIUrl":"https://doi.org/10.1109/ISCTIS58954.2023.10213130","url":null,"abstract":"With the continuous development of the coal mining industry and the improvement of automation, monitoring software plays a crucial role in ensuring the safety and efficiency of mining operations. However, the reliability and accuracy of monitoring software are crucial for the safety and production of the coal mining industry. Traditional manual testing can no longer ensure accurate measurement of monitoring system stability and performance in complex scenarios. This paper will explore the background and challenges of monitoring software testing in the coal mining industry, and introduce a flexible analysis system for coal mining monitoring.","PeriodicalId":334790,"journal":{"name":"2023 3rd International Symposium on Computer Technology and Information Science (ISCTIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124243046","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}