With the utilization and exploitation of marine resources, the consciousness of protecting the environment is rising, and the classification and localization of marine microalgae is a good solution. In this regard, we propose self-attention and online hard example mining based network for marine microalgae detection, which is based on Cascade-RCNN network. First, the Mixup method is introduced to enhance and augment data. In the backbone network, Transformer self-attention and feature pyramid network (FPN) are introduced to make the model getting stronger feature extraction ability and can adapt to objects of multi-scale. By introducing online hard example mining (OHEM) method, the training can be completed under the condition of imbalanced data distribution. We also use multi-scale training and multi-scale testing methods to improve the training performance of the model. Through experiments on the marine microalgae dataset provided by IEEE UV 2022 “Vision Meets Algae” Object Detection Challenge, compared with the baseline network, our proposed method improves by 3.97%.
{"title":"Self-attention and Online Hard Example Mining Based Network for Marine Microalgae Detection","authors":"Qizhi Zhang, Xiaohai He, Wangming Zeng, Zhengyong Wang, Honggang Chen","doi":"10.1109/UV56588.2022.10185503","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185503","url":null,"abstract":"With the utilization and exploitation of marine resources, the consciousness of protecting the environment is rising, and the classification and localization of marine microalgae is a good solution. In this regard, we propose self-attention and online hard example mining based network for marine microalgae detection, which is based on Cascade-RCNN network. First, the Mixup method is introduced to enhance and augment data. In the backbone network, Transformer self-attention and feature pyramid network (FPN) are introduced to make the model getting stronger feature extraction ability and can adapt to objects of multi-scale. By introducing online hard example mining (OHEM) method, the training can be completed under the condition of imbalanced data distribution. We also use multi-scale training and multi-scale testing methods to improve the training performance of the model. Through experiments on the marine microalgae dataset provided by IEEE UV 2022 “Vision Meets Algae” Object Detection Challenge, compared with the baseline network, our proposed method improves by 3.97%.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"40 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":"126385945","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/UV56588.2022.10185496
Ye Zheng, Bo Wang
This article introduces the solutions of the “MicroalgaeDetector” team for the IEEE UV 2022 Vision Meets Algae Object Detection Challenge. This challenge focus on developing computer vision detection algorithm to automatically detect marine microalgae from microscopy images. Automatic localization and identification of microalgae are anticipated to be accomplished concurrently during image analysis, which will simplify downstream cell analysis and lay the groundwork for algae identification using image data in conjunction with biomorphological traits. In this competition, we observe that the training dataset has a serious class imbalance problem, and some classes are in a state of few samples, which greatly limits the performance of both single stage detectors and multi-stage detectors. There are also issues with tiny objects in high-resolution images and serious bounding box annotation inconsistencies. To address the aforementioned competition challenges of few samples, unbalanced categories, noisy annotations and small objects in this competition, we propose a robust and high-performance algae detection method (RAD), which can precisely localize and identify marine microalgae in microscopy images. In the proposed RAD, we develop a class-specific copy-paste strategy to achieve instance-level re-sampling, which resolves the problem of the data imbalance. We also introduce several training/inference strategies and a bag of tricks that brings more or less performance boost. In order to increase robustness, we also train multiple expert models to ensemble them. Our RAD wins the competition after achieving 58.192% mAP in the test dataset.
{"title":"RAD: A Robust Algae Detection Solution to IEEE UV 2022 “Vision Meets Alage” Object Detection Challenge","authors":"Ye Zheng, Bo Wang","doi":"10.1109/UV56588.2022.10185496","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185496","url":null,"abstract":"This article introduces the solutions of the “MicroalgaeDetector” team for the IEEE UV 2022 Vision Meets Algae Object Detection Challenge. This challenge focus on developing computer vision detection algorithm to automatically detect marine microalgae from microscopy images. Automatic localization and identification of microalgae are anticipated to be accomplished concurrently during image analysis, which will simplify downstream cell analysis and lay the groundwork for algae identification using image data in conjunction with biomorphological traits. In this competition, we observe that the training dataset has a serious class imbalance problem, and some classes are in a state of few samples, which greatly limits the performance of both single stage detectors and multi-stage detectors. There are also issues with tiny objects in high-resolution images and serious bounding box annotation inconsistencies. To address the aforementioned competition challenges of few samples, unbalanced categories, noisy annotations and small objects in this competition, we propose a robust and high-performance algae detection method (RAD), which can precisely localize and identify marine microalgae in microscopy images. In the proposed RAD, we develop a class-specific copy-paste strategy to achieve instance-level re-sampling, which resolves the problem of the data imbalance. We also introduce several training/inference strategies and a bag of tricks that brings more or less performance boost. In order to increase robustness, we also train multiple expert models to ensemble them. Our RAD wins the competition after achieving 58.192% mAP in the test dataset.","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":"132033047","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/UV56588.2022.10185483
Haolei Liu, Lin Zhang
In patients’ medical service consumption behavior, patients’ choice of medical institution is an important link, which determines patients’ medical quality and medical cost, and even further affects the distribution of medical resources in the whole health service market. Patients may have problems such as high knowledge barrier and information redundancy in the process of choosing hospitals. Nowadays, with the continuous development of machine learning, the recommendation system using graph neural network has achieved good results in solving this kind of information overload problem. Therefore, we mainly focus on the application of the recommendation system in the process of patients choosing hospitals. Here we complete the construction of the initial data set through data simulation, and then we train and debug the six graph neural network recommendation system models. In addition, we propose a new comprehensive index to improve the traditional index, which is difficult to better represent the model performance. In the future, we plan to apply this research to our smart medical big data cloud platform. On the one hand, the cloud platform will provide a more solid data basis for our model; on the other hand, we can provide personalized medical recommendation services for platform users by using the recommendation system.
{"title":"Comparison of Multiple Models of Recommendation Systems","authors":"Haolei Liu, Lin Zhang","doi":"10.1109/UV56588.2022.10185483","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185483","url":null,"abstract":"In patients’ medical service consumption behavior, patients’ choice of medical institution is an important link, which determines patients’ medical quality and medical cost, and even further affects the distribution of medical resources in the whole health service market. Patients may have problems such as high knowledge barrier and information redundancy in the process of choosing hospitals. Nowadays, with the continuous development of machine learning, the recommendation system using graph neural network has achieved good results in solving this kind of information overload problem. Therefore, we mainly focus on the application of the recommendation system in the process of patients choosing hospitals. Here we complete the construction of the initial data set through data simulation, and then we train and debug the six graph neural network recommendation system models. In addition, we propose a new comprehensive index to improve the traditional index, which is difficult to better represent the model performance. In the future, we plan to apply this research to our smart medical big data cloud platform. On the one hand, the cloud platform will provide a more solid data basis for our model; on the other hand, we can provide personalized medical recommendation services for platform users by using the recommendation system.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"3 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":"133288944","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/UV56588.2022.10185520
Zewei Wu, Wei Ke, Cui Wang, Z. Xiong
Pedestrian tracking studies have been facilitated by a large amount of surveillance apparatus in the city while also raising public privacy concerns. In this paper, we propose X-Tracking, a privacy-aware pedestrian tracking paradigm designed for vision systems in Smart City. It allows low-cost compatibility with existing surveillance architecture. To protect entities’ privacy, X-Tracking uses video pre-processing with desensitization so that identity information is unexposed to the tracking algorithm. We implement system-level privacy protection by redesigning the tracking framework that decouples all services based on a single responsibility principle. Then, we elaborate on the roles, behaviors, and protocols used in the new system and illustrate how the paradigm strikes a favorable balance between privacy protection and convenience services. Furthermore, we propose a new tracking task that aims to track humans in masking surveillance video. It is comparable to previous tracking tasks but considering the target with a distorted appearance poses new challenges for visual tracking. Finally, we evaluate the baseline algorithm on the task with a demo dataset.
{"title":"X-Tracking: Tracking Human in Masking Surveillance Video","authors":"Zewei Wu, Wei Ke, Cui Wang, Z. Xiong","doi":"10.1109/UV56588.2022.10185520","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185520","url":null,"abstract":"Pedestrian tracking studies have been facilitated by a large amount of surveillance apparatus in the city while also raising public privacy concerns. In this paper, we propose X-Tracking, a privacy-aware pedestrian tracking paradigm designed for vision systems in Smart City. It allows low-cost compatibility with existing surveillance architecture. To protect entities’ privacy, X-Tracking uses video pre-processing with desensitization so that identity information is unexposed to the tracking algorithm. We implement system-level privacy protection by redesigning the tracking framework that decouples all services based on a single responsibility principle. Then, we elaborate on the roles, behaviors, and protocols used in the new system and illustrate how the paradigm strikes a favorable balance between privacy protection and convenience services. Furthermore, we propose a new tracking task that aims to track humans in masking surveillance video. It is comparable to previous tracking tasks but considering the target with a distorted appearance poses new challenges for visual tracking. Finally, we evaluate the baseline algorithm on the task with a demo dataset.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"79 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":"115415702","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/UV56588.2022.10185500
Xiaode Fu, Fei Shen, Xiaoyu Du, Zechao Li
In this paper, we introduce our solution to the “Vision Meets Algae” Workshop and Challenge (VisAlgae) in details. Since a large number of small objects and similar categories, the location and classification of algae are challenging. For that, we propose a bag of tricks for VisAlgae, including data augmentation, model architecture, and pipeline. For data augmentation, we introduce bounding-box jitter, mix-up, multi-scale, albu, and test time augmentation to increase sample diversity and randomness. We learn a better region of interest (RoI) features by adding global semantic information to RoI features. Especially a novelty double head is devised to enhance final features via reserving spatial and channel information. For the pipeline, We introduce the detector framework, backbone, stochastic weights averaging, pseudo labels, and weighted boxes fusion. Experimental results demonstrate that our approach can achieve an excellent mean average precision (mAP) performance of object detection.
{"title":"Bag of Tricks for “Vision Meet Alage” Object Detection Challenge","authors":"Xiaode Fu, Fei Shen, Xiaoyu Du, Zechao Li","doi":"10.1109/UV56588.2022.10185500","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185500","url":null,"abstract":"In this paper, we introduce our solution to the “Vision Meets Algae” Workshop and Challenge (VisAlgae) in details. Since a large number of small objects and similar categories, the location and classification of algae are challenging. For that, we propose a bag of tricks for VisAlgae, including data augmentation, model architecture, and pipeline. For data augmentation, we introduce bounding-box jitter, mix-up, multi-scale, albu, and test time augmentation to increase sample diversity and randomness. We learn a better region of interest (RoI) features by adding global semantic information to RoI features. Especially a novelty double head is devised to enhance final features via reserving spatial and channel information. For the pipeline, We introduce the detector framework, backbone, stochastic weights averaging, pseudo labels, and weighted boxes fusion. Experimental results demonstrate that our approach can achieve an excellent mean average precision (mAP) performance of object detection.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"36 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":"114399568","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}
Spine Magnetic resonance imaging (MRI) is a crucial diagnostic technique for illnesses of the spinal cord. The UNET network, the most prominent neural network model for segmenting medical images has opened up new opportunities for spin MRI segmentation as a result of the rapid development of deep-learning algorithms. In this study, we compared the difference between UNet and five other variants (Unet++, Unet+++, Attention-UNet, Dense-UNet, and R2UNet) in performance and efficiency by training and testing them on the same Spine MRI image dataset that contained 200 patients. The results showed that Attention-UNet performed best on the Miou (83.33 percent) and Average dice(89.15 percent) metrics; R2UNet performed best on the Accuracy (97.12 percent) metric. Attention-UNet has the slightest difference between the basic segmentation and the baseline value in terms of segmentation performance. This study could provide a better understanding of different networks on the Spine MRI Segmentation task.
{"title":"Performance Comparison between U-Net Variant Models in Spine Segmentation","authors":"Qiyong Zhong, Longfei Zhou, Taoyang Hang, Xiao Yu, Jiantao Wang, Jiasheng Yang, Zijun Zhou, Yukun Quan, Sihan Niu, Yujie Zhu, Zhe Fang, Xinyu Xie","doi":"10.1109/UV56588.2022.10185445","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185445","url":null,"abstract":"Spine Magnetic resonance imaging (MRI) is a crucial diagnostic technique for illnesses of the spinal cord. The UNET network, the most prominent neural network model for segmenting medical images has opened up new opportunities for spin MRI segmentation as a result of the rapid development of deep-learning algorithms. In this study, we compared the difference between UNet and five other variants (Unet++, Unet+++, Attention-UNet, Dense-UNet, and R2UNet) in performance and efficiency by training and testing them on the same Spine MRI image dataset that contained 200 patients. The results showed that Attention-UNet performed best on the Miou (83.33 percent) and Average dice(89.15 percent) metrics; R2UNet performed best on the Accuracy (97.12 percent) metric. Attention-UNet has the slightest difference between the basic segmentation and the baseline value in terms of segmentation performance. This study could provide a better understanding of different networks on the Spine MRI Segmentation task.","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":"115350078","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/UV56588.2022.10185525
Jaechul Roh, Yajun Fang
Over the past few years, the field of adversarial attack received numerous attention from various researchers with the help of successful attack success rate against well-known deep neural networks that were acknowledged to achieve high classification ability in various tasks. However, majority of the experiments were completed under a single model, which we believe it may not be an ideal case in a real-life situation. In this paper, we introduce a novel federated adversarial training method for smart home face recognition, named FLATS, where we observed some interesting findings that may not be easily noticed in a traditional adversarial attack to federated learning experiments. By applying different variations to the hyperparameters, we have spotted that our method can make the global model to be robust given a starving federated environment.
{"title":"Robust Smart Home Face Recognition Under Starving Federated Data","authors":"Jaechul Roh, Yajun Fang","doi":"10.1109/UV56588.2022.10185525","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185525","url":null,"abstract":"Over the past few years, the field of adversarial attack received numerous attention from various researchers with the help of successful attack success rate against well-known deep neural networks that were acknowledged to achieve high classification ability in various tasks. However, majority of the experiments were completed under a single model, which we believe it may not be an ideal case in a real-life situation. In this paper, we introduce a novel federated adversarial training method for smart home face recognition, named FLATS, where we observed some interesting findings that may not be easily noticed in a traditional adversarial attack to federated learning experiments. By applying different variations to the hyperparameters, we have spotted that our method can make the global model to be robust given a starving federated environment.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"48 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":"114693734","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/UV56588.2022.10185492
Shufan Jiang, Rafael Angarita, Stéphane Cormier, Francis Rousseaux
An important application scenario of precision agriculture is detecting and measuring crop health threats using sensors and data analysis techniques. However, the textual data are still under-explored among the existing solutions due to the lack of labelled data and fine-grained semantic resources. Recent research suggests that the increasing connectivity of farmers and the emergence of online farming communities make social media like Twitter a participatory platform for detecting unfamiliar plant health events if we can extract essential information from unstructured textual data. ChouBERT is a French pre-trained language model that can identify Tweets concerning observations of plant health issues with generalizability on unseen natural hazards. This paper tackles the lack of labelled data by further studying ChouBERT’s know-how on token-level annotation tasks over small labeled sets.
{"title":"Named Entity Recognition for Monitoring Plant Health Threats in Tweets: a ChouBERT Approach","authors":"Shufan Jiang, Rafael Angarita, Stéphane Cormier, Francis Rousseaux","doi":"10.1109/UV56588.2022.10185492","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185492","url":null,"abstract":"An important application scenario of precision agriculture is detecting and measuring crop health threats using sensors and data analysis techniques. However, the textual data are still under-explored among the existing solutions due to the lack of labelled data and fine-grained semantic resources. Recent research suggests that the increasing connectivity of farmers and the emergence of online farming communities make social media like Twitter a participatory platform for detecting unfamiliar plant health events if we can extract essential information from unstructured textual data. ChouBERT is a French pre-trained language model that can identify Tweets concerning observations of plant health issues with generalizability on unseen natural hazards. This paper tackles the lack of labelled data by further studying ChouBERT’s know-how on token-level annotation tasks over small labeled sets.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"46 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":"123641977","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 this paper, the machine learning method and mathematical model are used to predict the number of future vaccinations, and the problem of how to distribute vaccines to central hospitals, community hospitals and health centers is solved [1], [2]. In the context of the growing importance of vaccination, we need to rationalize the distribution of vaccines to central hospitals, community hospitals and health centers, taking into account the need and cost of vaccination. First, in order to predict the national daily vaccination figures for the next three months, we consulted relevant website data to obtain the vaccination figures for each day since the vaccination began in March 2021, and made the forecast for the next three months through the time series prediction method LSTM [3], [4]. Combined with the increment of the number of daily vaccinations as the label value, the final prediction results were obtained. Second, we first collected data and analyzed and processed the characteristics. Through collinearity analysis [5], we found that the number of residents and the number of medical personnel had strong collinearity, and the logarithm of the number of residents was calculated with log10. Then AHP [6] was used to analyze the impact of the number of nearby residents, convenient transportation, number of medical personnel, vaccine storage and transportation costs on vaccine distribution, and CR index was used to evaluate our model. The third question is to substitute the collected data of the two regions into the model of the previous question, and we subtract 10% number of nearby residents from the index of central hospitals as a penalty for crowd gathering. Got central hospitals, community hospitals, and health centers vaccine distribution ratio: Hangzhou Gongshu District 4.8:3.3:1.9; Harbin Daoli District 3.6:4.7:1.7 [7]. Fourth, in combination with our model and conclusions, we provide an adequate explanation for vaccine distribution.
{"title":"Wise in Vaccine Allocation","authors":"Baiqiao Yin, Jiaqing Yuan, Weichen Lv, Jiehui Huang, Guian Fang","doi":"10.1109/UV56588.2022.10185517","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185517","url":null,"abstract":"In this paper, the machine learning method and mathematical model are used to predict the number of future vaccinations, and the problem of how to distribute vaccines to central hospitals, community hospitals and health centers is solved [1], [2]. In the context of the growing importance of vaccination, we need to rationalize the distribution of vaccines to central hospitals, community hospitals and health centers, taking into account the need and cost of vaccination. First, in order to predict the national daily vaccination figures for the next three months, we consulted relevant website data to obtain the vaccination figures for each day since the vaccination began in March 2021, and made the forecast for the next three months through the time series prediction method LSTM [3], [4]. Combined with the increment of the number of daily vaccinations as the label value, the final prediction results were obtained. Second, we first collected data and analyzed and processed the characteristics. Through collinearity analysis [5], we found that the number of residents and the number of medical personnel had strong collinearity, and the logarithm of the number of residents was calculated with log10. Then AHP [6] was used to analyze the impact of the number of nearby residents, convenient transportation, number of medical personnel, vaccine storage and transportation costs on vaccine distribution, and CR index was used to evaluate our model. The third question is to substitute the collected data of the two regions into the model of the previous question, and we subtract 10% number of nearby residents from the index of central hospitals as a penalty for crowd gathering. Got central hospitals, community hospitals, and health centers vaccine distribution ratio: Hangzhou Gongshu District 4.8:3.3:1.9; Harbin Daoli District 3.6:4.7:1.7 [7]. Fourth, in combination with our model and conclusions, we provide an adequate explanation for vaccine distribution.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"59 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":"120912542","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}
At present, smart Homes are receiving more attention as they are becoming the predominant space that houses people’s activities. Even though intelligent home appliances are capable of ameliorating residents’ quality of life and decreasing their household workload, current Smart Homes are still limited to providing support and services to satisfy the needs of the aging society, small families, and busy lifestyles.In addition to their limited capability, current Smart Homes lack robustness and resilience and introduce some unexpected new challenges, including waste of energy and resource, safety and security concerns, compatibility, discontinued service due to technology obsolescence, and financial challenges which are further aggravated by the imbalanced development of different regions and communities.In this paper, we first discuss the new trend in people’s lifestyles, the major needs of the current society, and the special requirements for their future homes. We further elaborate on the significance and contribution of existing Smart Home systems, the challenges of Smart Home applications, the importance of human involvement, and future development.We then propose the concept of the UV Smart Home and its general framework and evaluate, from the UV perspective, the current status of the Smart Home system based on the framework of a closed feedback control loop: data acquisition, communication, decision-making, and action, as well as the available technologies relevant to each element of the systems.After that, we explore the information flow and material cycle associated with UV Smart Home systems and study how Smart Homes would be affected by these two major impacting factors: information flow and material cycle. The need for information flow and the current absence of centralized management and disorganized information-sharing practices are discussed. We also propose the concept of hierarchical information fusion, addressing the lack of fusion between data content, temporal and spatial information, data from different sources, and the lack of fusion between different informational layers, such as human know-how and system data. The paper also points out that the material cycle is a key element in Smart Homes as it connects all UV components through the exchange of physical products, energy, and natural resources. We investigate and highlight several issues within the current Smart Home material cycle, ranging from improper handling of hazardous materials and exposed electrical wires to unauthorized access to firearms and improper mixing of cleaning substances. This part also emphasizes the risk of cascading failures in interconnected systems and processes. It underscores the need for improved information management, fusion, and coordination, as well as proper handling of materials and resources to ensure the safety and functionality of the UV Smart Home system.In addition, we propose that an effective Smart Home should take into consideration
{"title":"Evaluation of Smart Home Systems and Novel UV-Oriented Solution for Integration, Resilience, Inclusiveness & Sustainability","authors":"Longling Geng, Xinzhang Xiong, Zhenyao Liu, Yifan Wei, Ziliang Lan, Mingyuan Hu, Mengxi Guo, Rebecca Xu, Hao Yuan, Zhiyuan Yang, Hanxia Li, Yifan Zhou, Huchong Jin, Chenyi Wang, Liuxuan Jiao, Qiuhang Huang, Fengyang Wang, Katrina Sung, Charles Zhang, Mingyang Sun, Xiaojing Li, Nanbo Zhang, Xuan Liu, Ruiyang Gao, Haihan Wang, Juntao Jiang, Yi Tao, Lifeng Zhang, Shengsheng Cao, Longfei Zhou, Xiaoman Duan, Yajun Fang","doi":"10.1109/UV56588.2022.10185519","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185519","url":null,"abstract":"At present, smart Homes are receiving more attention as they are becoming the predominant space that houses people’s activities. Even though intelligent home appliances are capable of ameliorating residents’ quality of life and decreasing their household workload, current Smart Homes are still limited to providing support and services to satisfy the needs of the aging society, small families, and busy lifestyles.In addition to their limited capability, current Smart Homes lack robustness and resilience and introduce some unexpected new challenges, including waste of energy and resource, safety and security concerns, compatibility, discontinued service due to technology obsolescence, and financial challenges which are further aggravated by the imbalanced development of different regions and communities.In this paper, we first discuss the new trend in people’s lifestyles, the major needs of the current society, and the special requirements for their future homes. We further elaborate on the significance and contribution of existing Smart Home systems, the challenges of Smart Home applications, the importance of human involvement, and future development.We then propose the concept of the UV Smart Home and its general framework and evaluate, from the UV perspective, the current status of the Smart Home system based on the framework of a closed feedback control loop: data acquisition, communication, decision-making, and action, as well as the available technologies relevant to each element of the systems.After that, we explore the information flow and material cycle associated with UV Smart Home systems and study how Smart Homes would be affected by these two major impacting factors: information flow and material cycle. The need for information flow and the current absence of centralized management and disorganized information-sharing practices are discussed. We also propose the concept of hierarchical information fusion, addressing the lack of fusion between data content, temporal and spatial information, data from different sources, and the lack of fusion between different informational layers, such as human know-how and system data. The paper also points out that the material cycle is a key element in Smart Homes as it connects all UV components through the exchange of physical products, energy, and natural resources. We investigate and highlight several issues within the current Smart Home material cycle, ranging from improper handling of hazardous materials and exposed electrical wires to unauthorized access to firearms and improper mixing of cleaning substances. This part also emphasizes the risk of cascading failures in interconnected systems and processes. It underscores the need for improved information management, fusion, and coordination, as well as proper handling of materials and resources to ensure the safety and functionality of the UV Smart Home system.In addition, we propose that an effective Smart Home should take into consideration ","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"117 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":"130727109","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：