Pub Date : 2022-10-22DOI: 10.1109/UV56588.2022.10185471
Ruixin Zhang, Yan Jia, Meng Zhang
China is rapidly moving into an aging society. The fast aging population and lack of necessary elderly care resources and organizational capacity make it necessary for policymakers to amass information about current elderly care resources, either in the public or private sector, and elderly care service demands, and make informed and intelligent policies to enable collaborative efforts from different social entities to deal with this new challenge. This paper studies elderly care data resources management practices in Northeast China and analyzes how the studied capital cities build platforms, select, gather, manage, and utilize elderly care data for elderly care policy making and service provision. These data come from different sources, have other formats, are normalized differently, and are owned by various social entities. To enable their standardization, compatibility, and efficient use, skills, collaborative methods, principles, and institutions are needed to constitute the conceptual framework for collaborative governance. The study shall extract lessons and experiences from the studied cases in the context of this theoretical guidance and develop policy recommendations for future digital-enabled elderly care practice.
{"title":"Conceptual Framework for Collaborative Governance of Urban Smart Elderly Care Services Data Resources -Based on the Case Analysis of the Capital Cities of Three Provinces in Northeast China","authors":"Ruixin Zhang, Yan Jia, Meng Zhang","doi":"10.1109/UV56588.2022.10185471","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185471","url":null,"abstract":"China is rapidly moving into an aging society. The fast aging population and lack of necessary elderly care resources and organizational capacity make it necessary for policymakers to amass information about current elderly care resources, either in the public or private sector, and elderly care service demands, and make informed and intelligent policies to enable collaborative efforts from different social entities to deal with this new challenge. This paper studies elderly care data resources management practices in Northeast China and analyzes how the studied capital cities build platforms, select, gather, manage, and utilize elderly care data for elderly care policy making and service provision. These data come from different sources, have other formats, are normalized differently, and are owned by various social entities. To enable their standardization, compatibility, and efficient use, skills, collaborative methods, principles, and institutions are needed to constitute the conceptual framework for collaborative governance. The study shall extract lessons and experiences from the studied cases in the context of this theoretical guidance and develop policy recommendations for future digital-enabled elderly care practice.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"53 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":"130010112","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/UV56588.2022.10185508
Yunyan Zhang, Haibo Wang, Xiufeng Ding, Fengchun Hu
To overcome the disadvantages of existing infrared earphones and Bluetooth earphones, such as poor stability, low performance and much interference, an optical communication headsetis designed based on visible light communication technology. The photoelectric transmission system, which takes the visible light as the carrier to transmit the audio signal, is composed of the transmitting part and the receiving part. The modulation and demodulation of signal is realized by using a single-chip microcomputer. Experimental results show that the visible light headset system has the advantages of stability, flexibility in operation, high signal strength, and adjustable volume.
{"title":"Design of Optical Communication Headset Based on Visible Light Communication Technology","authors":"Yunyan Zhang, Haibo Wang, Xiufeng Ding, Fengchun Hu","doi":"10.1109/UV56588.2022.10185508","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185508","url":null,"abstract":"To overcome the disadvantages of existing infrared earphones and Bluetooth earphones, such as poor stability, low performance and much interference, an optical communication headsetis designed based on visible light communication technology. The photoelectric transmission system, which takes the visible light as the carrier to transmit the audio signal, is composed of the transmitting part and the receiving part. The modulation and demodulation of signal is realized by using a single-chip microcomputer. Experimental results show that the visible light headset system has the advantages of stability, flexibility in operation, high signal strength, and adjustable volume.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"22 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":"130963952","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/UV56588.2022.10185523
Yang Liu, Shuai Wang, Yubin Wu, Hao Sheng, Z. Xiong
Person image generation is to synthesize realistic pedestrian images that follow the same distribution as the given dataset. Previous attempts can be generally categorized into two classes: some methods use human pose information as guidance and others try to generate person images from scratch. The former is to transfer the pose of a source image to a reference pose. The generated person image have the same identity as the source image. The latter takes a random noise from latent space as input, and the real person images are only used as references for the discriminator. While pose-guided person image generation is widely studied, generating-from-scratch methods are also worth exploring because they can synthesize person image with new identity, which is a useful manner of data augmentation. These two types of generating methods have their different advantages and disadvantages, and sometimes they are complementary. In this work, the authors design a Generative Cooperative Network (GCN) to jointly train two types of GANs. The two GANs serve different purposes, and can learn from each other during the cooperative learning procedure. The proposed approach is verified on public datasets, and the results show that our GCN improves the performance of the baseline methods. Comparisons with state-of-the-art methods also prove the effectiveness of the proposed method.
{"title":"Generative Cooperative Network for Person Image Generation","authors":"Yang Liu, Shuai Wang, Yubin Wu, Hao Sheng, Z. Xiong","doi":"10.1109/UV56588.2022.10185523","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185523","url":null,"abstract":"Person image generation is to synthesize realistic pedestrian images that follow the same distribution as the given dataset. Previous attempts can be generally categorized into two classes: some methods use human pose information as guidance and others try to generate person images from scratch. The former is to transfer the pose of a source image to a reference pose. The generated person image have the same identity as the source image. The latter takes a random noise from latent space as input, and the real person images are only used as references for the discriminator. While pose-guided person image generation is widely studied, generating-from-scratch methods are also worth exploring because they can synthesize person image with new identity, which is a useful manner of data augmentation. These two types of generating methods have their different advantages and disadvantages, and sometimes they are complementary. In this work, the authors design a Generative Cooperative Network (GCN) to jointly train two types of GANs. The two GANs serve different purposes, and can learn from each other during the cooperative learning procedure. The proposed approach is verified on public datasets, and the results show that our GCN improves the performance of the baseline methods. Comparisons with state-of-the-art methods also prove the effectiveness of the proposed method.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"45 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":"114045108","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/UV56588.2022.10185482
Guangli Luo, Jiaqi Yan, Yixuan Guo
These days, the epidemic have evolved from a huge disaster to a protracted war. And as a precious and indispensable protecting resource, vaccine is definitely deserved our reminding because of its lack to some extents. In this paper, we develop mathematical models to predict the daily vaccination numbers in a short phase and more crucially, analysis a number of factors to Figure out a more efficient plan to allocate the vaccine among the central hospitals, community hospitals and health centers. And based on the conclusion, we give a brief note to the medical institutions.
{"title":"A New Mindset about the Vaccination Allocation","authors":"Guangli Luo, Jiaqi Yan, Yixuan Guo","doi":"10.1109/UV56588.2022.10185482","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185482","url":null,"abstract":"These days, the epidemic have evolved from a huge disaster to a protracted war. And as a precious and indispensable protecting resource, vaccine is definitely deserved our reminding because of its lack to some extents. In this paper, we develop mathematical models to predict the daily vaccination numbers in a short phase and more crucially, analysis a number of factors to Figure out a more efficient plan to allocate the vaccine among the central hospitals, community hospitals and health centers. And based on the conclusion, we give a brief note to the medical institutions.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"50 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":"123534534","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/UV56588.2022.10185468
Cheuk Wang Su, Ruiyang Gao, Mingyu Hu, Yajun Fang
At present, rapid urbanization has resulted in increased production of commodities, thereby enhancing the convenience of human lives. However, these products generate a lot of waste, which leads to severe environmental challenges damaging mother earth. Plastic has been an essential part of the world as society continues to develop. Bottles, toys, cars, and electronic products all have plastic components. With plastic becoming an increasingly ubiquitous presence in our daily lives, the production of plastic has also soared. A study estimated that 8.3 billion metric tons of plastic have been produced from the early 1950s to 2017 [1]. As production increases, disposal methods also need to improve. However, according to UNEP, less than 10% are recycled [2]. If plastic is not properly processed, it would remain in the world forever and create mass destruction to our environment. The oceans serve as a pertinent example, wherein a significant influx of plastic finds its way through waterways and beaches. As time moves on, plastic will start to degrade and become microplastic. According to the data, there is 51 trillion microplastic litter in the ocean [3]. They then affect our health entering the food chain, since a lot of sea animals see them as food. Overwhelmed plastics also affect human health. A research found that an apple has around 195,500 plastic particles per gram, ranking the highest among items they tested [4]. A report estimates that a person could eat a credit-card-size of plastics per week. Out of all types of plastics, including PET, HDPE, PVC, LDPE, PP, PS, and others [5]. PVC is estimated to be the most toxic to the human body. It contains a lot of phthalates, which can damage the liver, kidneys, lungs, and reproductive system. In this paper, we evaluate plastic pollution based on the framework of a closed feedback control loop: data acquisition, communication, decision-making, and action. Currently, there are multiple ways to collect data. For example, researchers can capture images from unmanned aerial vehicles and self-designed trucks. There are existing operational technologies that are actively engaged in the collection of plastics, particularly within the marine environment, such as 4ocean’s skimmer and Mr. Trash Wheel in Baltimore [6], [7]. There are also innovations such as turning used plastics into bricks [8]. In addition, We propose that effective smart plastic recycling should ideally interact with the other seven smart city subsystems proposed by UV: Smart Home, Smart Medicine and Healthcare, Smart ITS, Urban planning and Crowd management, Smart Energy Management, Smart City Infrastructure, Smart Response System for City Emergencies, and Smart Humanity.
{"title":"Evaluation of Plastic Recycling and Novel UV-Oriented Solution for Integration, Resilience, Inclusiveness, and Sustainability","authors":"Cheuk Wang Su, Ruiyang Gao, Mingyu Hu, Yajun Fang","doi":"10.1109/UV56588.2022.10185468","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185468","url":null,"abstract":"At present, rapid urbanization has resulted in increased production of commodities, thereby enhancing the convenience of human lives. However, these products generate a lot of waste, which leads to severe environmental challenges damaging mother earth. Plastic has been an essential part of the world as society continues to develop. Bottles, toys, cars, and electronic products all have plastic components. With plastic becoming an increasingly ubiquitous presence in our daily lives, the production of plastic has also soared. A study estimated that 8.3 billion metric tons of plastic have been produced from the early 1950s to 2017 [1]. As production increases, disposal methods also need to improve. However, according to UNEP, less than 10% are recycled [2]. If plastic is not properly processed, it would remain in the world forever and create mass destruction to our environment. The oceans serve as a pertinent example, wherein a significant influx of plastic finds its way through waterways and beaches. As time moves on, plastic will start to degrade and become microplastic. According to the data, there is 51 trillion microplastic litter in the ocean [3]. They then affect our health entering the food chain, since a lot of sea animals see them as food. Overwhelmed plastics also affect human health. A research found that an apple has around 195,500 plastic particles per gram, ranking the highest among items they tested [4]. A report estimates that a person could eat a credit-card-size of plastics per week. Out of all types of plastics, including PET, HDPE, PVC, LDPE, PP, PS, and others [5]. PVC is estimated to be the most toxic to the human body. It contains a lot of phthalates, which can damage the liver, kidneys, lungs, and reproductive system. In this paper, we evaluate plastic pollution based on the framework of a closed feedback control loop: data acquisition, communication, decision-making, and action. Currently, there are multiple ways to collect data. For example, researchers can capture images from unmanned aerial vehicles and self-designed trucks. There are existing operational technologies that are actively engaged in the collection of plastics, particularly within the marine environment, such as 4ocean’s skimmer and Mr. Trash Wheel in Baltimore [6], [7]. There are also innovations such as turning used plastics into bricks [8]. In addition, We propose that effective smart plastic recycling should ideally interact with the other seven smart city subsystems proposed by UV: Smart Home, Smart Medicine and Healthcare, Smart ITS, Urban planning and Crowd management, Smart Energy Management, Smart City Infrastructure, Smart Response System for City Emergencies, and Smart Humanity.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"13 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":"122883279","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/UV56588.2022.10185529
Mostafa Zaman, Maher Al Islam, A. Tantawy, S. Abdelwahed
A well-designed water distribution system is crucial for maintaining high service standards in any modern smart city. Moreover, as the population is sky-rocketing, the demand for energy and water is increasing more rapidly than a decade before. Therefore, ensuring a steady clean water supply with optimized energy and water consumption has become necessary. To accurately monitor water distribution systems, the accuracy of input data plays a vital role in determining how accurate the system’s status estimations are. There must be a way for system operators to know what is going on at any given time to make practical decisions about how reliable the data they are receiving is. The input data uncertainty can induce flow and pressure calculation inaccuracies, which can be fatal while planning for future demands and needs to be quantified.Knowing the degree of uncertainty in predicting the water distribution system’s capacity or load can help people better prepare for future capacity or load predictions. Accurate uncertainty calculations are critical to time series forecasting. Probabilistic formulae are widely employed with classical time series models to estimate uncertainty. But incorporating new data and fine-tuning these models is a challenging task. This research paper presents a Bayesian LSTM network that computes both time series prediction and uncertainty assessment at the same time. In this paper, a real-time data set from VCU’s OpenCity test bed is employed to evaluate the efficacy of the suggested strategy.
{"title":"An Uncertainty Based Predictive Analysis of Smart Water Distribution System Using Bayesian LSTM Approach","authors":"Mostafa Zaman, Maher Al Islam, A. Tantawy, S. Abdelwahed","doi":"10.1109/UV56588.2022.10185529","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185529","url":null,"abstract":"A well-designed water distribution system is crucial for maintaining high service standards in any modern smart city. Moreover, as the population is sky-rocketing, the demand for energy and water is increasing more rapidly than a decade before. Therefore, ensuring a steady clean water supply with optimized energy and water consumption has become necessary. To accurately monitor water distribution systems, the accuracy of input data plays a vital role in determining how accurate the system’s status estimations are. There must be a way for system operators to know what is going on at any given time to make practical decisions about how reliable the data they are receiving is. The input data uncertainty can induce flow and pressure calculation inaccuracies, which can be fatal while planning for future demands and needs to be quantified.Knowing the degree of uncertainty in predicting the water distribution system’s capacity or load can help people better prepare for future capacity or load predictions. Accurate uncertainty calculations are critical to time series forecasting. Probabilistic formulae are widely employed with classical time series models to estimate uncertainty. But incorporating new data and fine-tuning these models is a challenging task. This research paper presents a Bayesian LSTM network that computes both time series prediction and uncertainty assessment at the same time. In this paper, a real-time data set from VCU’s OpenCity test bed is employed to evaluate the efficacy of the suggested strategy.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"157 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":"114546647","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/UV56588.2022.10185504
Lei Wang, Tian-Ze Zhang, Yingting Chen, Yongyang Huang, Xitong Yin, Xiao Fan Liu, Daning Hu
Start-ups have emerged as key drivers of economic growth, fostering innovation, job creation, and knowledge dissemination across various industries. Accurately forecasting start-up life spans is critical for investors, policymakers, and entrepreneurs to make informed decisions and optimize resource allocation. However, existing predictive models, such as linear regression and survival analysis, face challenges in capturing the complex interactions and dynamic nature of factors influencing start-up success. This paper proposes applying the XGBoost algorithm, an advanced machine learning technique, to enhance the accuracy and reliability of start-up life span predictions. XGBoost offers several advantages over traditional methods, including adaptability to various data types, robustness to outliers, and efficient computational performance. By incorporating a wide range of features, such as financial, organizational, and death reasons, the algorithm can effectively capture the complex relationships among these factors without explicit feature engineering. Moreover, applying SHAP values provides an additional layer of interpretability, aiding stakeholders in better understanding the factors driving start-up life span. Utilizing the IT Orange dataset, we investigate the determinants of startup life spans, offering valuable insights for stakeholders in the entrepreneurial ecosystem.
{"title":"Machine Learning-based Start-up Company Lifespan Prediction: the Chinese Market as an Example","authors":"Lei Wang, Tian-Ze Zhang, Yingting Chen, Yongyang Huang, Xitong Yin, Xiao Fan Liu, Daning Hu","doi":"10.1109/UV56588.2022.10185504","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185504","url":null,"abstract":"Start-ups have emerged as key drivers of economic growth, fostering innovation, job creation, and knowledge dissemination across various industries. Accurately forecasting start-up life spans is critical for investors, policymakers, and entrepreneurs to make informed decisions and optimize resource allocation. However, existing predictive models, such as linear regression and survival analysis, face challenges in capturing the complex interactions and dynamic nature of factors influencing start-up success. This paper proposes applying the XGBoost algorithm, an advanced machine learning technique, to enhance the accuracy and reliability of start-up life span predictions. XGBoost offers several advantages over traditional methods, including adaptability to various data types, robustness to outliers, and efficient computational performance. By incorporating a wide range of features, such as financial, organizational, and death reasons, the algorithm can effectively capture the complex relationships among these factors without explicit feature engineering. Moreover, applying SHAP values provides an additional layer of interpretability, aiding stakeholders in better understanding the factors driving start-up life span. Utilizing the IT Orange dataset, we investigate the determinants of startup life spans, offering valuable insights for stakeholders in the entrepreneurial ecosystem.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"80 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":"134550583","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/UV56588.2022.10185507
Yiqiao Zhang, Ping Cui, Guijin Xie
This paper uses the LSTM network to predict the number of vaccinations in China from December 2022 to February 2023. In addition, according to the number of residents in different regions, the number of medical staff and other factors, the vaccine allocation optimization model is built. The model is solved by particle swarm optimization. The distribution strategy is applied to the analog data of Gongshu District of Hangzhou City and Daoli District of Harbin City. Finally, we give some implementable suggestions for the vaccination.
{"title":"Predict The Number of Vaccinated People and Formulate Vaccine Distribution Strategy of COVID-19 Based on LSTM and Particle Swarm optimization","authors":"Yiqiao Zhang, Ping Cui, Guijin Xie","doi":"10.1109/UV56588.2022.10185507","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185507","url":null,"abstract":"This paper uses the LSTM network to predict the number of vaccinations in China from December 2022 to February 2023. In addition, according to the number of residents in different regions, the number of medical staff and other factors, the vaccine allocation optimization model is built. The model is solved by particle swarm optimization. The distribution strategy is applied to the analog data of Gongshu District of Hangzhou City and Daoli District of Harbin City. Finally, we give some implementable suggestions for the vaccination.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"60 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":"127620712","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}
This report summarizes the fourth-place solution of the “Vision Meets Algae” object detection challenge held on IEEE UV’2022 focuses on object detection in marine biology images obtained through the microscope. First, we experimented with a large number of backbones and necks to improve mAP by enhancing the model structure. Then, we designed and tested a variety of data augmentation schemes based on algal characteristics from a data perspective. Finally, with multiple models ensembled adopted, our methods achieve 57.579% mAP on the test set.
{"title":"Multi-model Fusion Solution for IEEE UV 2022 “Vision Meets Algae” Object Detection Challenge","authors":"Xiaoxiao Peng, Yueyi Wang, Dayu Chen, Yuchen Tian, Keyu Huang, Jianfeng Zheng","doi":"10.1109/UV56588.2022.10185512","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185512","url":null,"abstract":"This report summarizes the fourth-place solution of the “Vision Meets Algae” object detection challenge held on IEEE UV’2022 focuses on object detection in marine biology images obtained through the microscope. First, we experimented with a large number of backbones and necks to improve mAP by enhancing the model structure. Then, we designed and tested a variety of data augmentation schemes based on algal characteristics from a data perspective. Finally, with multiple models ensembled adopted, our methods achieve 57.579% mAP on the test set.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"458 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":"123418949","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}
Aqueous ammonia is a commonly working fluid used in absorption refrigeration cycles, and high energy consumption exists during the working process due to incomplete separation of ammonia and water. To address this problem, several cations and anions are selected to form ionic liquids in this paper. Then these substances are added into the ammonia-water system to form ternary systems. The energy analysis between different particles of new systems is carried out by using the density flooding theory. The results indicate that dimethylimidazolium-dimethylphosphate has a high affinity for water and shows a more obvious potential to promote ammonia to separate from water in the energy calculation, and the theoretically predicted results are also consistent with the experimental data in the literature.
{"title":"Density Functional Theory Study of Adding Ionic Liquid to Aqueous Ammonia System","authors":"Zhibin Wu, Yun Li, Ping Cheng, Zhenbin Lei, Weijia Huang","doi":"10.1109/UV56588.2022.10185493","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185493","url":null,"abstract":"Aqueous ammonia is a commonly working fluid used in absorption refrigeration cycles, and high energy consumption exists during the working process due to incomplete separation of ammonia and water. To address this problem, several cations and anions are selected to form ionic liquids in this paper. Then these substances are added into the ammonia-water system to form ternary systems. The energy analysis between different particles of new systems is carried out by using the density flooding theory. The results indicate that dimethylimidazolium-dimethylphosphate has a high affinity for water and shows a more obvious potential to promote ammonia to separate from water in the energy calculation, and the theoretically predicted results are also consistent with the experimental data in the literature.","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":"114541985","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：