Pub Date : 2023-01-06DOI: 10.1109/ICCECE58074.2023.10135513
Lianrong Chen, Naidan Mei, Lianjie Wang, Jianhong Li
Colorization is the process of adding color to grayscale images using computer algorithms. There are several approaches to color an image, including precise image segmentation algorithms, deep learning algorithms, and manually colored local color expansion methods. However, one common problem with these approaches is the occurrence of “color bleeding”, where colors from one region of the image spill over into adjacent regions. In this paper, we propose a new manually colored local color expansion algorithm that considers the intensity value difference and distance difference between the central pixel in the window and its neighbor pixels comprehensively. Combined with side window filtering, our algorithm significantly reduces the occurrence of colors bleeding at the edges of the colored image. The experiments demonstrate the effectiveness of the proposed algorithm.
{"title":"A New Debleeding Algorithm for Image colorization","authors":"Lianrong Chen, Naidan Mei, Lianjie Wang, Jianhong Li","doi":"10.1109/ICCECE58074.2023.10135513","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135513","url":null,"abstract":"Colorization is the process of adding color to grayscale images using computer algorithms. There are several approaches to color an image, including precise image segmentation algorithms, deep learning algorithms, and manually colored local color expansion methods. However, one common problem with these approaches is the occurrence of “color bleeding”, where colors from one region of the image spill over into adjacent regions. In this paper, we propose a new manually colored local color expansion algorithm that considers the intensity value difference and distance difference between the central pixel in the window and its neighbor pixels comprehensively. Combined with side window filtering, our algorithm significantly reduces the occurrence of colors bleeding at the edges of the colored image. The experiments demonstrate the effectiveness of the proposed algorithm.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117184880","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 : 2023-01-06DOI: 10.1109/ICCECE58074.2023.10135515
Yongzhe Chang, Xinhang Xiao, Yang Yu
A point process is a collection of positional variables in a given space, while a marked point process (MPP) is basically a point process that measures some additional feature or value at each point. Existing applications such as financial market models and hospitalization models have demonstrated that MPPS are suitable for modeling random events with meaningful values. A big challenge is to study the relationship between different types of events, or how different types of markers affect each other. While Hawkes procedures are an effective and efficient way to model point processes with internal influences, inferential methods of intensity functions can be expensive, especially for multi-dimensional processes. Graph convolutional Network (GCN) is a powerful neural network designed to directly process graphs. A GCN-based model is presented to study potential patterns in the marking process and to predict the location of future events without estimating the Hawkes intensity function. A real data set of water pipe leakage and rupture records over the last 50 years was used in the experiment, modeled as a marker point process, where leakage and rupture are two marker forms. Experimental results on synthetic data sets and real water pipe data sets show that the proposed model is superior to recent state-of-the-art methods.
{"title":"Graph Convolutional Neural Networks based Marked Point Process","authors":"Yongzhe Chang, Xinhang Xiao, Yang Yu","doi":"10.1109/ICCECE58074.2023.10135515","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135515","url":null,"abstract":"A point process is a collection of positional variables in a given space, while a marked point process (MPP) is basically a point process that measures some additional feature or value at each point. Existing applications such as financial market models and hospitalization models have demonstrated that MPPS are suitable for modeling random events with meaningful values. A big challenge is to study the relationship between different types of events, or how different types of markers affect each other. While Hawkes procedures are an effective and efficient way to model point processes with internal influences, inferential methods of intensity functions can be expensive, especially for multi-dimensional processes. Graph convolutional Network (GCN) is a powerful neural network designed to directly process graphs. A GCN-based model is presented to study potential patterns in the marking process and to predict the location of future events without estimating the Hawkes intensity function. A real data set of water pipe leakage and rupture records over the last 50 years was used in the experiment, modeled as a marker point process, where leakage and rupture are two marker forms. Experimental results on synthetic data sets and real water pipe data sets show that the proposed model is superior to recent state-of-the-art methods.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117354156","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 : 2023-01-06DOI: 10.1109/ICCECE58074.2023.10135287
Guimin Gong, Wen-hong Lv, Ge Gao, Qi Wang
Based on the urban road traffic capacity, the identification of key nodes of urban road network is studied. Firstly, the urban road network model of undirected rights is constructed: the bearing capacity of nodes is measured by the number of lanes and the corresponding road traffic capacity of each lane, and the node importance function is established through three factors: node degree value, road section traffic capacity (edge weight) and distance between nodes. The global efficiency of the network and the maximum network connectivity subgraph were selected as the evaluation indicators to measure the network performance. The simulation analysis of the road network within Xin'an Street, Huangdao District, Qingdao City shows that compared with the degree centrality algorithm and mapping entropy algorithm, the proposed algorithm can identify the key nodes of the road network more accurately.
{"title":"Capacity-based identification of key nodes in urban road networks","authors":"Guimin Gong, Wen-hong Lv, Ge Gao, Qi Wang","doi":"10.1109/ICCECE58074.2023.10135287","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135287","url":null,"abstract":"Based on the urban road traffic capacity, the identification of key nodes of urban road network is studied. Firstly, the urban road network model of undirected rights is constructed: the bearing capacity of nodes is measured by the number of lanes and the corresponding road traffic capacity of each lane, and the node importance function is established through three factors: node degree value, road section traffic capacity (edge weight) and distance between nodes. The global efficiency of the network and the maximum network connectivity subgraph were selected as the evaluation indicators to measure the network performance. The simulation analysis of the road network within Xin'an Street, Huangdao District, Qingdao City shows that compared with the degree centrality algorithm and mapping entropy algorithm, the proposed algorithm can identify the key nodes of the road network more accurately.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124867005","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 : 2023-01-06DOI: 10.1109/ICCECE58074.2023.10135366
Ruyu Li, Lihua Yin, Yuanfei Zhang, Kexiang Qian, Xi Luo
Along with the progression in technology, Internet of Things (IoT) has been dramatically developed in recent ten years. It connects physical world and digital world, which makes people's life more convenient. However, IoT devices have bring great vulnerability to Internet security since they usually under weak protection, which makes them easy to be exploited by criminals to launch multiple attacks. In fact, IoT devices have been a crucial part of botnets that launch horrible Distributed Denial of Service (DDoS) with explosive traffic. Unfortunately, traditional detection works have limited effectiveness face IoT botnets because of the restricted resources of IoT devices and unprecedented huge scale of IoT botnets. To mitigate the threat of IoT botnets, in this paper, we propose a lightweight system, named FastIoTBot, to discover compromised IoT devices in a fast way. FastIoTBot can distinguish compromised IoT devices instantly and prevent potential malicious behaviors by examining domain query activities. Specifically, FastIoTBot monitors the DNS query for a device and generates its NXDOMAIN query sequence. Then, for each domain in the sequence, FastIoTBot takes the domain name string as input and calculates its malicious score using long short-term memory (LSTM) model. Finally, FastIoTBot identifies compromised IoT devices through analyzing NXDOMAIN sequences with internal domains' malicious score leveraging threshold random walk (TRW) algorithm. The effectiveness of FastIoTBot is evaluate with real world DNS data of two large ISP networks. The results show that FastIoTBot perform well with over 99% accuracy.
{"title":"FastIoTBot: Identifying IoT Bots by Fast Detecting Anomalous Domain Queries with Long Short-Term Memory Networks","authors":"Ruyu Li, Lihua Yin, Yuanfei Zhang, Kexiang Qian, Xi Luo","doi":"10.1109/ICCECE58074.2023.10135366","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135366","url":null,"abstract":"Along with the progression in technology, Internet of Things (IoT) has been dramatically developed in recent ten years. It connects physical world and digital world, which makes people's life more convenient. However, IoT devices have bring great vulnerability to Internet security since they usually under weak protection, which makes them easy to be exploited by criminals to launch multiple attacks. In fact, IoT devices have been a crucial part of botnets that launch horrible Distributed Denial of Service (DDoS) with explosive traffic. Unfortunately, traditional detection works have limited effectiveness face IoT botnets because of the restricted resources of IoT devices and unprecedented huge scale of IoT botnets. To mitigate the threat of IoT botnets, in this paper, we propose a lightweight system, named FastIoTBot, to discover compromised IoT devices in a fast way. FastIoTBot can distinguish compromised IoT devices instantly and prevent potential malicious behaviors by examining domain query activities. Specifically, FastIoTBot monitors the DNS query for a device and generates its NXDOMAIN query sequence. Then, for each domain in the sequence, FastIoTBot takes the domain name string as input and calculates its malicious score using long short-term memory (LSTM) model. Finally, FastIoTBot identifies compromised IoT devices through analyzing NXDOMAIN sequences with internal domains' malicious score leveraging threshold random walk (TRW) algorithm. The effectiveness of FastIoTBot is evaluate with real world DNS data of two large ISP networks. The results show that FastIoTBot perform well with over 99% accuracy.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123255640","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 : 2023-01-06DOI: 10.1109/ICCECE58074.2023.10135308
Xiaochen Lai, Sixuan Zeng, Wenkai Xu, Lu Tong, Jialiu Yang
Educational data mining is a popular research area in data mining, and predicting student performance is one of the important research topics in educational data mining. In order to predict student performance in a timely and accurate manner, this paper proposes a Graph Pearson correlation Sample and AggreGatE (GPcSAGE) model based on graph neural networks. The sampling probability of neighboring nodes similar to the target node is optimized to weaken the influence of abnormal target node attributes on the prediction results and reduce the sampling variance. The algorithm efficiency and prediction accuracy are improved by reconfiguring the aggregation function to aggregate more important information. The experiments demonstrate the effectiveness of the method, which helps to predict students' learning trends and effects for precise teaching interventions to improve teaching quality.
{"title":"Predicting the academic performance of students with GPcSAGE","authors":"Xiaochen Lai, Sixuan Zeng, Wenkai Xu, Lu Tong, Jialiu Yang","doi":"10.1109/ICCECE58074.2023.10135308","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135308","url":null,"abstract":"Educational data mining is a popular research area in data mining, and predicting student performance is one of the important research topics in educational data mining. In order to predict student performance in a timely and accurate manner, this paper proposes a Graph Pearson correlation Sample and AggreGatE (GPcSAGE) model based on graph neural networks. The sampling probability of neighboring nodes similar to the target node is optimized to weaken the influence of abnormal target node attributes on the prediction results and reduce the sampling variance. The algorithm efficiency and prediction accuracy are improved by reconfiguring the aggregation function to aggregate more important information. The experiments demonstrate the effectiveness of the method, which helps to predict students' learning trends and effects for precise teaching interventions to improve teaching quality.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126726358","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 : 2023-01-06DOI: 10.1109/ICCECE58074.2023.10135378
Yue Chang
With the rapid popularization of the Internet and the rapid development of network technology, people are increasingly inclined to online shopping. This paper uses B/S three-layer structure, and uses JSP technology for dynamic page design. From the perspective of system security and code reusability, JavaBean is used to encapsulate the key code of the program. The background database is MySQL database. “SanWei” e-commerce bookstore platform includes foreground management and background management, mainly including shopping cart management, commodity search, user data modification, commodity management and order management. The system is more efficient and can create more value.
{"title":"Research on “SanWei” Web Application System Based on Java Technology","authors":"Yue Chang","doi":"10.1109/ICCECE58074.2023.10135378","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135378","url":null,"abstract":"With the rapid popularization of the Internet and the rapid development of network technology, people are increasingly inclined to online shopping. This paper uses B/S three-layer structure, and uses JSP technology for dynamic page design. From the perspective of system security and code reusability, JavaBean is used to encapsulate the key code of the program. The background database is MySQL database. “SanWei” e-commerce bookstore platform includes foreground management and background management, mainly including shopping cart management, commodity search, user data modification, commodity management and order management. The system is more efficient and can create more value.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126953436","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}
In these years, there are dramatic development in the fake news detection field. The spread of fake news influences people's daily life, reduces the value of real news, and sometimes blemishes people's images. This phenomenon has raised our attention, so we are interested in making some effort to reduce the negative impact of it. We focus on the point that whether the users will spread the news if all the news is read by the users (from the causal inference aspect). We use negative sampling to avoid the problem that there is only positive feedback in the real-world dataset. Then we compare IPS, MF, NCF and BPR to discover the best to help us to solve this question.
{"title":"Understanding of Fake News Dissemination on Social Media by Comparing IPS, MF, NCF and BPR","authors":"Haotong Xin, Yimin Wei, Tianda Fan, Shang Peng, Haohua Liu, Junxiang Su","doi":"10.1109/ICCECE58074.2023.10135245","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135245","url":null,"abstract":"In these years, there are dramatic development in the fake news detection field. The spread of fake news influences people's daily life, reduces the value of real news, and sometimes blemishes people's images. This phenomenon has raised our attention, so we are interested in making some effort to reduce the negative impact of it. We focus on the point that whether the users will spread the news if all the news is read by the users (from the causal inference aspect). We use negative sampling to avoid the problem that there is only positive feedback in the real-world dataset. Then we compare IPS, MF, NCF and BPR to discover the best to help us to solve this question.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122884278","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 : 2023-01-06DOI: 10.1109/ICCECE58074.2023.10135472
Lin Ding, Wenfeng Shen, Weijia Lu, Peng Liu, Shengbo Chen, Sisi Chen
Model-agnostic meta-learning schemes adopt gradient descent to learn task commonalities and obtain the initialization parameters of the meta-model to rapidly adjust to new tasks with only a few training samples. Therefore, such schemes have become the mainstream meta-learning approach for studying few shot learning problems. This study mainly addresses the challenge of task uncertainty in few-shot learning and proposes an improved meta-learning approach, which first enables a task specific learner to select the initial parameter that minimize the loss of a new task, then generates weights by comparing meta-loss differences, and finally leads into the homoscedastic uncertainty of the task to weight the diverse losses. Our model conducts superior on few shot learning task than previous meta learning approach and improves its robustness regardless of the initial learning rates and query sets.
{"title":"Gradient-Based Meta-Learning Using Adaptive Multiple Loss Weighting and Homoscedastic Uncertainty","authors":"Lin Ding, Wenfeng Shen, Weijia Lu, Peng Liu, Shengbo Chen, Sisi Chen","doi":"10.1109/ICCECE58074.2023.10135472","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135472","url":null,"abstract":"Model-agnostic meta-learning schemes adopt gradient descent to learn task commonalities and obtain the initialization parameters of the meta-model to rapidly adjust to new tasks with only a few training samples. Therefore, such schemes have become the mainstream meta-learning approach for studying few shot learning problems. This study mainly addresses the challenge of task uncertainty in few-shot learning and proposes an improved meta-learning approach, which first enables a task specific learner to select the initial parameter that minimize the loss of a new task, then generates weights by comparing meta-loss differences, and finally leads into the homoscedastic uncertainty of the task to weight the diverse losses. Our model conducts superior on few shot learning task than previous meta learning approach and improves its robustness regardless of the initial learning rates and query sets.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128255574","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 : 2023-01-06DOI: 10.1109/ICCECE58074.2023.10135261
Jiajie Xu, Chin-Yin Chen, Si-lu Chen, Qiang Liu
Existing researchs on multi-robots task assignment focus on improving the task assignment efficiency without considering the task execution time and ignoring the overall task completion efficiency, which leads to its low computational efficiency in dynamic task assignment scenarios. In addition, the use of a centralized control structure requires high communication quality between robots. To address the above issues, we propose a distributed task assignment method for multiple robots based on dynamic auction rules. The method uses distributed control of robot swarms to share and dynamically update each other's task sets, employs dynamic auction rules for task bidding, adds links to adjust the task execution order, and considers the overall task completion efficiency. Finally, relevant experiments are designed, and the experimental results show that the algorithm is more efficient in terms of distribution and stability, balancing higher execution efficiency and lower motion cost.
{"title":"Distributed Task Assignment Method for Multiple Robots Based on Dynamic Auction Rules","authors":"Jiajie Xu, Chin-Yin Chen, Si-lu Chen, Qiang Liu","doi":"10.1109/ICCECE58074.2023.10135261","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135261","url":null,"abstract":"Existing researchs on multi-robots task assignment focus on improving the task assignment efficiency without considering the task execution time and ignoring the overall task completion efficiency, which leads to its low computational efficiency in dynamic task assignment scenarios. In addition, the use of a centralized control structure requires high communication quality between robots. To address the above issues, we propose a distributed task assignment method for multiple robots based on dynamic auction rules. The method uses distributed control of robot swarms to share and dynamically update each other's task sets, employs dynamic auction rules for task bidding, adds links to adjust the task execution order, and considers the overall task completion efficiency. Finally, relevant experiments are designed, and the experimental results show that the algorithm is more efficient in terms of distribution and stability, balancing higher execution efficiency and lower motion cost.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124580875","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 : 2023-01-06DOI: 10.1109/ICCECE58074.2023.10135213
Ruishi Liang, Yizhu Chen, Shuaibing Li, Huizhi Yang
To identify mask wearing quickly and automatically in public places is particularly important for epidemic prevention and control. In this paper, we present a real-time mask wearing detection algorithm based on improved YOLOv5s, which speeds up the reasoning speed by 5~10% and achieves a detection accuracy of more than 96%. The proposed algorithm can be easily deployed in Raspberry PI. We also design a Web-based mask wearing detection system consisting of two parts: the cloud subsystem and the edge subsystem. The cloud part mainly realizes data storage, model training, equipment monitoring, big data visualization and other functions. The edge part uses Raspberry Pie as the core deployment equipment to complete data collection, model reasoning, information early warning and other functions. Our system features the advantages of high real-time, low cost and low network traffic. It can be widely deployed in the supermarket, parks, intelligent light poles and other open scenes, resulting in greater practical application value.
{"title":"Mask Wearing Detection System Based On YOLO And Raspberry Pi","authors":"Ruishi Liang, Yizhu Chen, Shuaibing Li, Huizhi Yang","doi":"10.1109/ICCECE58074.2023.10135213","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135213","url":null,"abstract":"To identify mask wearing quickly and automatically in public places is particularly important for epidemic prevention and control. In this paper, we present a real-time mask wearing detection algorithm based on improved YOLOv5s, which speeds up the reasoning speed by 5~10% and achieves a detection accuracy of more than 96%. The proposed algorithm can be easily deployed in Raspberry PI. We also design a Web-based mask wearing detection system consisting of two parts: the cloud subsystem and the edge subsystem. The cloud part mainly realizes data storage, model training, equipment monitoring, big data visualization and other functions. The edge part uses Raspberry Pie as the core deployment equipment to complete data collection, model reasoning, information early warning and other functions. Our system features the advantages of high real-time, low cost and low network traffic. It can be widely deployed in the supermarket, parks, intelligent light poles and other open scenes, resulting in greater practical application value.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129921136","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：