Pub Date : 2022-10-22DOI: 10.1109/UV56588.2022.10185513
Jeremy S. Zimman, Dezhi Yang
LCA metrics: Durability, performance, and recyclability. The BROAD Group has conducted research into the use of stainless steel to improve the safety and durability of high rise buildings. The research has proven the unique properties of austenitic and duplex stainless steels in particular, including the “B-CORE” sandwich structure stainless steel construction material developed by the BROAD Group, make stainless steel excellent for use in all structural load bearing members of buildings.
{"title":"Sustainable Modular Construction Using B-CORE Stainless Steel","authors":"Jeremy S. Zimman, Dezhi Yang","doi":"10.1109/UV56588.2022.10185513","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185513","url":null,"abstract":"LCA metrics: Durability, performance, and recyclability. The BROAD Group has conducted research into the use of stainless steel to improve the safety and durability of high rise buildings. The research has proven the unique properties of austenitic and duplex stainless steels in particular, including the “B-CORE” sandwich structure stainless steel construction material developed by the BROAD Group, make stainless steel excellent for use in all structural load bearing members of buildings.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"496 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120879113","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}
Marine microalgae detection is of great importance to the environment and ecosystem. In this paper, we consider microalgae detection as a computer vision task and use a two-stage object detection network, Cascade R-CNN, to build our detector and deal with the dataset which contains a variety of small targets. Firstly, We proposed a novel data augmentation strategy called SimpleCopy for microscopic images, which typically have more small targets and sparse target distributions. Secondly, we leverage the strengths of different backbone and employ model ensemble techniques to enhance the performance of our detector. Finally, with carefully designed post-processing methods, the recall and precision of our detector can be further improved. Extensive experiments conducted on the marine dataset show the superiority of our model. We verified the effectiveness of our method by achieving 58.18 mAP and ranked 3/347 on the official leadboard.
{"title":"SimpleCopy: A Strong Data Augmentation for Microalgae Detection","authors":"Shaojin Wu, Junjie Zhang, Bingrong Xu, Zhigang Zeng","doi":"10.1109/UV56588.2022.10185499","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185499","url":null,"abstract":"Marine microalgae detection is of great importance to the environment and ecosystem. In this paper, we consider microalgae detection as a computer vision task and use a two-stage object detection network, Cascade R-CNN, to build our detector and deal with the dataset which contains a variety of small targets. Firstly, We proposed a novel data augmentation strategy called SimpleCopy for microscopic images, which typically have more small targets and sparse target distributions. Secondly, we leverage the strengths of different backbone and employ model ensemble techniques to enhance the performance of our detector. Finally, with carefully designed post-processing methods, the recall and precision of our detector can be further improved. Extensive experiments conducted on the marine dataset show the superiority of our model. We verified the effectiveness of our method by achieving 58.18 mAP and ranked 3/347 on the official leadboard.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122604039","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 : 2022-10-22DOI: 10.1109/UV56588.2022.10185446
Fusheng Yu
Universal Village (UV) is a new concept proposed by MIT’s Universal Village Program, which envisions an ideal future society that prioritizes environmental and ecosystem preservation while fulfilling human needs, thereby ensuring sustainable wellbeing for society’s residents. Marine ecological conservation is an integral part of the Global Village plan, and algae are essential marine biological resources. The organic matter and accumulated energy they produce serve as the foundation for the survival and development of the entire marine biological community. With the rapid development of computer vision technology, there is now the possibility of combining advanced object detection algorithms with traditional algae detection methods. In this work, we leveraged Swin Transformer and Covnext as feature extractors and Cascade RCNN as the main network to detect and classify eight types of microalgae in microscope images. We also employed Weighted Boxes Fusion in post-processing to improve detection accuracy and model generalization.
{"title":"When Computer Vision Meets Algae","authors":"Fusheng Yu","doi":"10.1109/UV56588.2022.10185446","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185446","url":null,"abstract":"Universal Village (UV) is a new concept proposed by MIT’s Universal Village Program, which envisions an ideal future society that prioritizes environmental and ecosystem preservation while fulfilling human needs, thereby ensuring sustainable wellbeing for society’s residents. Marine ecological conservation is an integral part of the Global Village plan, and algae are essential marine biological resources. The organic matter and accumulated energy they produce serve as the foundation for the survival and development of the entire marine biological community. With the rapid development of computer vision technology, there is now the possibility of combining advanced object detection algorithms with traditional algae detection methods. In this work, we leveraged Swin Transformer and Covnext as feature extractors and Cascade RCNN as the main network to detect and classify eight types of microalgae in microscope images. We also employed Weighted Boxes Fusion in post-processing to improve detection accuracy and model generalization.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130540579","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}
The solid oxide fuel cell (SOFC) system, with almost no pollution, low noise and high efficiency, is playing a more and more significant role in power supply. However, the regulation of output voltage and desired range of the fuel utilization, caused by its strong nonlinearity, system uncertainty and ever-changing external current load, are challengeable. To relieve these challenges, this paper proposes a hybrid control scheme combing the physical feedforward and desired dynamic equation (DDE) control. By analyzing these control challenges theoretically, a physical feedforward is applied to accelerate the system response and keep the fuel utilization in the desired range, and DDE control is proposed to handle system nonlinearity, uncertainty and external disturbances. Then a practical and effective tuning method for the DDE parameters is provided. Finally, the proposed and comparative control strategies are applied to the SOFC system. Simulation results show that the proposed control scheme has the strongest ability to reject the external current load and handle system uncertainties. Besides, it can guarantee that fuel utilization always locates in a reasonable range.
{"title":"Feedforward and Desired Dynamic Equation Control for Solid Oxide Fuel Cell System","authors":"Zhenlong Wu, Pengzhen Li, Yanhong Liu, Xiaoyuan Li, Donghai Li, Yangquan Chen","doi":"10.1109/UV56588.2022.10185443","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185443","url":null,"abstract":"The solid oxide fuel cell (SOFC) system, with almost no pollution, low noise and high efficiency, is playing a more and more significant role in power supply. However, the regulation of output voltage and desired range of the fuel utilization, caused by its strong nonlinearity, system uncertainty and ever-changing external current load, are challengeable. To relieve these challenges, this paper proposes a hybrid control scheme combing the physical feedforward and desired dynamic equation (DDE) control. By analyzing these control challenges theoretically, a physical feedforward is applied to accelerate the system response and keep the fuel utilization in the desired range, and DDE control is proposed to handle system nonlinearity, uncertainty and external disturbances. Then a practical and effective tuning method for the DDE parameters is provided. Finally, the proposed and comparative control strategies are applied to the SOFC system. Simulation results show that the proposed control scheme has the strongest ability to reject the external current load and handle system uncertainties. Besides, it can guarantee that fuel utilization always locates in a reasonable range.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132030945","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 : 2022-10-22DOI: 10.1109/UV56588.2022.10185510
Maryam Taeb, H. Chi, S. Bernadin
By recording instances of significant forensic relevance, smartphones, which are becoming increasingly crucial for documenting ordinary life events, can produce pieces of evidence in court. Due to privacy or other issues, not everyone is open to having all the data on their phone collected and analyzed. In addition, Law Enforcement Organizations need a lot of memory to keep the information taken from a witness’s phone. Deepfakes which are purposefully utilized as a source of disinformation, manipulation, harassment, and persuasion in court, present another significant problem for law enforcement organizations. Recently, the introduction of blockchain has altered the way we conduct business. Decentralized Applications (Dapps) may be a fantastic way to verify the accuracy of the data, stop the spread of false information, extract specific data with precision, and offer a framework for sharing that takes into account privacy and memory issues. This article outlines the creation of a Dapp that provides users with a secure conduit through distributing evidence that has been verified. By utilizing machine learning (ML) classifiers, this platform not only distinguishes between altered and original material before allowing it, but also uses user-uploaded media to retrain its models to increase prediction accuracy and offer complete transparency. The end outcome of this activity can maintain a clear record (timestamp) of the occurrence, submitted proof, and helpful metadata with the aid of the blockchains’ consensus notion.
{"title":"Targeted Data Extraction and Deepfake Detection with Blockchain Technology","authors":"Maryam Taeb, H. Chi, S. Bernadin","doi":"10.1109/UV56588.2022.10185510","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185510","url":null,"abstract":"By recording instances of significant forensic relevance, smartphones, which are becoming increasingly crucial for documenting ordinary life events, can produce pieces of evidence in court. Due to privacy or other issues, not everyone is open to having all the data on their phone collected and analyzed. In addition, Law Enforcement Organizations need a lot of memory to keep the information taken from a witness’s phone. Deepfakes which are purposefully utilized as a source of disinformation, manipulation, harassment, and persuasion in court, present another significant problem for law enforcement organizations. Recently, the introduction of blockchain has altered the way we conduct business. Decentralized Applications (Dapps) may be a fantastic way to verify the accuracy of the data, stop the spread of false information, extract specific data with precision, and offer a framework for sharing that takes into account privacy and memory issues. This article outlines the creation of a Dapp that provides users with a secure conduit through distributing evidence that has been verified. By utilizing machine learning (ML) classifiers, this platform not only distinguishes between altered and original material before allowing it, but also uses user-uploaded media to retrain its models to increase prediction accuracy and offer complete transparency. The end outcome of this activity can maintain a clear record (timestamp) of the occurrence, submitted proof, and helpful metadata with the aid of the blockchains’ consensus notion.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"176 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126588430","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 : 2022-10-22DOI: 10.1109/UV56588.2022.10185518
Junjie Liang, Huilin Yao, Jiayi Wang, Ya-Hui Jia
Vaccination is essential for preventing epidemics likes COVID-19. Rational vaccine distribution can greatly improve vaccination efficiency and reduce costs. In this paper, to predict the number of future vaccinations, we utilize ARIMA model on the total number of new coronavirus vaccinations in China for a period. Based on the model, we propose a vaccine distribution method that is composed of two distribution strategies with different characteristics, namely “proximity based vaccine distribution” and “transfer based vaccine disritbution Specifically, we propose a hierarchical vaccination serving communities model to obtain the serving pressures, and construct a first order Marcov chain to explore the importance of different vaccination sites to decide the dynamic distribution with consideration of the rules based on some practical factors. Extensive experiments including two cities in China show that the proposed model can flexibly and effectively adapt to cities with different conditions.
{"title":"Dynamic Information Mining Based Vaccine Distribution Strategy","authors":"Junjie Liang, Huilin Yao, Jiayi Wang, Ya-Hui Jia","doi":"10.1109/UV56588.2022.10185518","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185518","url":null,"abstract":"Vaccination is essential for preventing epidemics likes COVID-19. Rational vaccine distribution can greatly improve vaccination efficiency and reduce costs. In this paper, to predict the number of future vaccinations, we utilize ARIMA model on the total number of new coronavirus vaccinations in China for a period. Based on the model, we propose a vaccine distribution method that is composed of two distribution strategies with different characteristics, namely “proximity based vaccine distribution” and “transfer based vaccine disritbution Specifically, we propose a hierarchical vaccination serving communities model to obtain the serving pressures, and construct a first order Marcov chain to explore the importance of different vaccination sites to decide the dynamic distribution with consideration of the rules based on some practical factors. Extensive experiments including two cities in China show that the proposed model can flexibly and effectively adapt to cities with different conditions.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127808989","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 : 2022-10-22DOI: 10.1109/UV56588.2022.10185514
Yitong Wang, Yajun Fang
Nowadays, the homeless situation is getting worse especially under the pandemic. The rates of homelessness in the United States have expanded by over 130 percent in just the past two years. Our society has been highly changed and our life quality has significantly improved thanks to technologies like Artificial Intelligence in nearly a decade. However, for people experiencing homelessness, and other such vulnerable groups are under social circumstances lacking humanistic consideration and facing moral issues. Over the past few years, many policies, technologies and approaches have been developed in directions like developing information-collecting platforms, building and classifying emergency shelters and creating robots dedicated to solving comprehensive problems to help people overcome the influences of poverty, illness and unaffordable housing that lead to homelessness, but the actions are never enough because of the partial absence of their focus on user experience, insufficient scope of application and the difficulty of promotion. Under this comprehensive circumstance of the crisis of homelessness, in this paper, we explore homeless status, difficulties and both internal and external challenges with their actual need and various technical solutions. More importantly, we are trying to analyze reasons for not being able to help homeless solve problems and evaluate breakthroughs in application and promotion, summarizing existing technologies and future innovations, proposing possible direction of improvement with a perspective of promoting sustainable development, universal design, and communicative action to help the homeless in various situations.
{"title":"Preliminary Exploration and Evaluation of Smart Support for Homeless Community","authors":"Yitong Wang, Yajun Fang","doi":"10.1109/UV56588.2022.10185514","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185514","url":null,"abstract":"Nowadays, the homeless situation is getting worse especially under the pandemic. The rates of homelessness in the United States have expanded by over 130 percent in just the past two years. Our society has been highly changed and our life quality has significantly improved thanks to technologies like Artificial Intelligence in nearly a decade. However, for people experiencing homelessness, and other such vulnerable groups are under social circumstances lacking humanistic consideration and facing moral issues. Over the past few years, many policies, technologies and approaches have been developed in directions like developing information-collecting platforms, building and classifying emergency shelters and creating robots dedicated to solving comprehensive problems to help people overcome the influences of poverty, illness and unaffordable housing that lead to homelessness, but the actions are never enough because of the partial absence of their focus on user experience, insufficient scope of application and the difficulty of promotion. Under this comprehensive circumstance of the crisis of homelessness, in this paper, we explore homeless status, difficulties and both internal and external challenges with their actual need and various technical solutions. More importantly, we are trying to analyze reasons for not being able to help homeless solve problems and evaluate breakthroughs in application and promotion, summarizing existing technologies and future innovations, proposing possible direction of improvement with a perspective of promoting sustainable development, universal design, and communicative action to help the homeless in various situations.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"489 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124426691","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 : 2022-10-22DOI: 10.1109/UV56588.2022.10185475
Yao Liu, Xiyu Chen, Zhongfu Jin, Yujie Zhang, Jiandang Yang
Traffic flow prediction is a crucial application in traffic guidance and control. Existing approaches rarely consider the dynamically correlated spatial-temporal features between multiple road segments. To effectively capture the spatial-temporal features between multiple road segments, we propose a novel approach, Spatial-Temporal Correlation Unit (STCU). STCU utilizes a fast Fourier transform-based autocorrelation mechanism to extract the correlations between temporal sequences, a graph attention mechanism to extract the correlations between spatial traffic monitors, and a feedforward neural network to fuse the interacting spatial-temporal correlations. We construct a traffic flow prediction model with a stacked STCU module called Sequential STCU (SSTCU). We conduct a lot of experiments and compared them with the several baselines to verify the effectiveness of SSTCU. The results show that the proposed method outperforms the baselines and achieves state-of-the-art performance. We also conduct ablation experiments to verify the effectiveness of the STCU module. Moreover, we change the layer depth of the model to find the most efficient setting for a computation efficiency consideration.
{"title":"SSTCU:A Spatial-Temporal Correlation Unit based Traffic Flow Prediction Approach","authors":"Yao Liu, Xiyu Chen, Zhongfu Jin, Yujie Zhang, Jiandang Yang","doi":"10.1109/UV56588.2022.10185475","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185475","url":null,"abstract":"Traffic flow prediction is a crucial application in traffic guidance and control. Existing approaches rarely consider the dynamically correlated spatial-temporal features between multiple road segments. To effectively capture the spatial-temporal features between multiple road segments, we propose a novel approach, Spatial-Temporal Correlation Unit (STCU). STCU utilizes a fast Fourier transform-based autocorrelation mechanism to extract the correlations between temporal sequences, a graph attention mechanism to extract the correlations between spatial traffic monitors, and a feedforward neural network to fuse the interacting spatial-temporal correlations. We construct a traffic flow prediction model with a stacked STCU module called Sequential STCU (SSTCU). We conduct a lot of experiments and compared them with the several baselines to verify the effectiveness of SSTCU. The results show that the proposed method outperforms the baselines and achieves state-of-the-art performance. We also conduct ablation experiments to verify the effectiveness of the STCU module. Moreover, we change the layer depth of the model to find the most efficient setting for a computation efficiency consideration.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123231351","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 : 2022-10-22DOI: 10.1109/UV56588.2022.10185526
Sarwar Shahidi, Mahmudul Kabir Peyal, K. M. Salim, Mahady Hasan
For agricultural production, water is a crucial resource. Because of agricultural mismanagement, groundwater is being pumped in large quantities, resulting in groundwater depletion. Surface irrigation dissolves fertilizer and pesticides in water, allowing toxins to enter groundwater and ultimately surface waters including dams, rivers, and canals. Addressing this problem this paper describes a methodical irrigation system with IoT-based monitoring for sustainable farming. One of the effective instruments for eradicating poverty is agricultural advancement. The majority of agricultural activities utilize physical material handling or outdated technology. Farmers are falling behind in terms of adequately maintaining soil and water resources, which are key components of sustainable agriculture. The proposed irrigation system is the way forward if we want to solve the problem. In this system, different sensors are placed in different places of farmland to monitor the environment and decide when irrigation is needed. The system will fetch data from API to predict the weather so that irrigation can be optimized and solve the problem of water logging and wastage of water. The water flow will be controlled by the sprinkler integrated with programmable flow valves. For user accessibility and observation, hardware will interface with a mobile app over the internet.
{"title":"Design of Smart Irrigation Monitoring and Control System Based on the Internet of Things","authors":"Sarwar Shahidi, Mahmudul Kabir Peyal, K. M. Salim, Mahady Hasan","doi":"10.1109/UV56588.2022.10185526","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185526","url":null,"abstract":"For agricultural production, water is a crucial resource. Because of agricultural mismanagement, groundwater is being pumped in large quantities, resulting in groundwater depletion. Surface irrigation dissolves fertilizer and pesticides in water, allowing toxins to enter groundwater and ultimately surface waters including dams, rivers, and canals. Addressing this problem this paper describes a methodical irrigation system with IoT-based monitoring for sustainable farming. One of the effective instruments for eradicating poverty is agricultural advancement. The majority of agricultural activities utilize physical material handling or outdated technology. Farmers are falling behind in terms of adequately maintaining soil and water resources, which are key components of sustainable agriculture. The proposed irrigation system is the way forward if we want to solve the problem. In this system, different sensors are placed in different places of farmland to monitor the environment and decide when irrigation is needed. The system will fetch data from API to predict the weather so that irrigation can be optimized and solve the problem of water logging and wastage of water. The water flow will be controlled by the sprinkler integrated with programmable flow valves. For user accessibility and observation, hardware will interface with a mobile app over the internet.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"448 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123628493","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}
The development of image recognition technology has made lots of opportunities to the manufacturing industry, speed up the intelligentization of manufacturing systems such as product quality assurance, automated assembly, and industrial robot control. In IC industry, manual inspection of industrial products for flaws is costly and inaccurate. Therefore, technicians have researched and developed computer vision technology and applied it to defect detection. However, most of the existing CNN models are only aimed at a certain dataset, and the effect is not good for the mixed data set. In the paper, we use machine vision to identify different classes of defects and imperfections. Specifically, an improved model based on UNet and SegNet is proposed for flaw detection of cables and transistors. This paper starts with the traditional SegNet model, integrates skip-connection and Atrous Spatial Pyramid Pooling (ASPP) to improve the performance of the model, and integrates a 13-layer convolutional neural network (ECON) in the experiment for classification to improve the model’s performance. Accuracy. A dataset of electronic component images from industrial production is used to compare the improved model, SegNet and UNet, and consider the performance of the combined classification model. The results show that the combined ECON and improved models have higher accuracy in the confounding of the two datasets compared to other networks.
{"title":"A New Convolutional Neural Network for Identification of Damaged Electronic Components","authors":"Fei Teng, Longfei Zhou, Haoliang Liu, Qingyang Zhao, Zehang Li, Pengfei Liu, Yonggen Dai, Lu Gao, Zhichao Gou, Jiazheng Chen, Jiasheng Yang","doi":"10.1109/UV56588.2022.10185470","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185470","url":null,"abstract":"The development of image recognition technology has made lots of opportunities to the manufacturing industry, speed up the intelligentization of manufacturing systems such as product quality assurance, automated assembly, and industrial robot control. In IC industry, manual inspection of industrial products for flaws is costly and inaccurate. Therefore, technicians have researched and developed computer vision technology and applied it to defect detection. However, most of the existing CNN models are only aimed at a certain dataset, and the effect is not good for the mixed data set. In the paper, we use machine vision to identify different classes of defects and imperfections. Specifically, an improved model based on UNet and SegNet is proposed for flaw detection of cables and transistors. This paper starts with the traditional SegNet model, integrates skip-connection and Atrous Spatial Pyramid Pooling (ASPP) to improve the performance of the model, and integrates a 13-layer convolutional neural network (ECON) in the experiment for classification to improve the model’s performance. Accuracy. A dataset of electronic component images from industrial production is used to compare the improved model, SegNet and UNet, and consider the performance of the combined classification model. The results show that the combined ECON and improved models have higher accuracy in the confounding of the two datasets compared to other networks.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124811151","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：