Zihan Cao, Yang Liu, Longfei Zhou, Yajun Fang, B. Horn
As the rapid development of AI, computer vision and automatic control technologies, self-driving cars have been well designed and developed. Since self-driving cars should coexist efficiently with human-driving cars, how to make practical strategies for them is increasingly significant. This paper optimizes cellular automaton to do simulation and quantizes the human factors as realistic and comprehensive as possible based on spectral clustering which is very suitable for large-scale simulation and crowd management for future smart cities. Compared with traditional analysis which record trajectories of cars, the new model employs unsupervised learning to augment average speed and reduce collision time by realizing algorithm optimization to reduce complexity and computational cost. This paper not only demonstrates the progress and results of traffic simulation, but also illustrates the concrete strategies for both self-driving cars and human drivers.
{"title":"A Macroscopic Traffic Simulation Model to Mingle Manually Operated and Self-driving Cars","authors":"Zihan Cao, Yang Liu, Longfei Zhou, Yajun Fang, B. Horn","doi":"10.1109/UV.2018.8642115","DOIUrl":"https://doi.org/10.1109/UV.2018.8642115","url":null,"abstract":"As the rapid development of AI, computer vision and automatic control technologies, self-driving cars have been well designed and developed. Since self-driving cars should coexist efficiently with human-driving cars, how to make practical strategies for them is increasingly significant. This paper optimizes cellular automaton to do simulation and quantizes the human factors as realistic and comprehensive as possible based on spectral clustering which is very suitable for large-scale simulation and crowd management for future smart cities. Compared with traditional analysis which record trajectories of cars, the new model employs unsupervised learning to augment average speed and reduce collision time by realizing algorithm optimization to reduce complexity and computational cost. This paper not only demonstrates the progress and results of traffic simulation, but also illustrates the concrete strategies for both self-driving cars and human drivers.","PeriodicalId":110658,"journal":{"name":"2018 4th International Conference on Universal Village (UV)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122444500","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}
Yixiao Wang, K. Green, R. Grupen, J. Brooks, I. Walker
The literature of communication theory suggests that people tend to interact with interactive artifacts as if these were human. For decades, this understanding has been applied to designing computer embedded devices at small physical scale (i.e. objects). In this paper, the authors extend this same understanding to the dimension of space—to designing intelligent, physical environments. The conceptual ground for this design intention is found in a “pattern language” developed by Alexander, et al. for designing static physical environments based on the “‘best guesses” of architects. Upon this foundation of a pattern language, the authors offer a design framework based on our novel concept of “space agency” whereby observed human-human interaction is translated into human-machine Interaction for spatial artifacts by way of two mapping techniques. Our intention is to strive for more human-human-like interactions between human beings and intelligent spaces whereby intelligent spaces become friendly, helpful, and welcoming. In this paper, the design of an interior space within a fully autonomous vehicle provides a case study. The framework presented here has significance for designing intelligent artifacts and interactions with them as these extend, inevitably, to the dimension of space, entertaining, serving, and augmenting our increasingly digital and human-centered society.
{"title":"Designing Intelligent Spaces as if They Were Human: A “Space Agent” Framework","authors":"Yixiao Wang, K. Green, R. Grupen, J. Brooks, I. Walker","doi":"10.1109/UV.2018.8642135","DOIUrl":"https://doi.org/10.1109/UV.2018.8642135","url":null,"abstract":"The literature of communication theory suggests that people tend to interact with interactive artifacts as if these were human. For decades, this understanding has been applied to designing computer embedded devices at small physical scale (i.e. objects). In this paper, the authors extend this same understanding to the dimension of space—to designing intelligent, physical environments. The conceptual ground for this design intention is found in a “pattern language” developed by Alexander, et al. for designing static physical environments based on the “‘best guesses” of architects. Upon this foundation of a pattern language, the authors offer a design framework based on our novel concept of “space agency” whereby observed human-human interaction is translated into human-machine Interaction for spatial artifacts by way of two mapping techniques. Our intention is to strive for more human-human-like interactions between human beings and intelligent spaces whereby intelligent spaces become friendly, helpful, and welcoming. In this paper, the design of an interior space within a fully autonomous vehicle provides a case study. The framework presented here has significance for designing intelligent artifacts and interactions with them as these extend, inevitably, to the dimension of space, entertaining, serving, and augmenting our increasingly digital and human-centered society.","PeriodicalId":110658,"journal":{"name":"2018 4th International Conference on Universal Village (UV)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121051608","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 recent years, aging of population and empty nest problem are becoming more and more severe. In addition, fall is the leading cause of death for seniors both in China and the U.S. Therefore, automatic fall detection for seniors is required in smart home and smart healthcare system. Currently, for its convenience and low cost, video-based method is the optimal method compared with other methods such as wearable sensor and ambient sensor in the field of indoor fall detection. In this paper, we propose a novel 2D video-based fall detection pipeline with human pose estimation. Firstly, we used OpenPose to extract the positions of human joints in raw data. Secondly, these data with augmented features became the input of a convolution neural network so that we can extract multi-layered features. Thirdly, a binary classification was conducted through neural network. For comparison, we also used SVM as the classifier. At last, we achieved relatively high sensitivity and specificity when compared our results with other state-of-the-art approaches on three public fall datasets.
{"title":"Video-based Fall Detection for Seniors with Human Pose Estimation","authors":"Zhanyuan Huang, Yang Liu, Yajun Fang, B. Horn","doi":"10.1109/UV.2018.8642130","DOIUrl":"https://doi.org/10.1109/UV.2018.8642130","url":null,"abstract":"In recent years, aging of population and empty nest problem are becoming more and more severe. In addition, fall is the leading cause of death for seniors both in China and the U.S. Therefore, automatic fall detection for seniors is required in smart home and smart healthcare system. Currently, for its convenience and low cost, video-based method is the optimal method compared with other methods such as wearable sensor and ambient sensor in the field of indoor fall detection. In this paper, we propose a novel 2D video-based fall detection pipeline with human pose estimation. Firstly, we used OpenPose to extract the positions of human joints in raw data. Secondly, these data with augmented features became the input of a convolution neural network so that we can extract multi-layered features. Thirdly, a binary classification was conducted through neural network. For comparison, we also used SVM as the classifier. At last, we achieved relatively high sensitivity and specificity when compared our results with other state-of-the-art approaches on three public fall datasets.","PeriodicalId":110658,"journal":{"name":"2018 4th International Conference on Universal Village (UV)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116866094","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 paper presents a model to design high-performance public transit system, where the optimal solution is directly selected from routes built up on real road structure. The objective function is the travel time for all travelers and the infrastructure cost can also be under consideration. The optimization procedure consists of four components, including a method to simulate downtown travel demand using open-source data on the Internet, a method to narrow down the decision variable space with the help of reasonable restriction and map api, an efficient a lgorithm to compute average travel time using block representation of the urban area and an improved evolutionary algorithm to search the optimal solution. Eventually, this method is applied to design the transit system for Changzhi, China. The optimal solution is compared to the original transit system of Changzhi to test both the effect and reasonability of the algorithm.
{"title":"A Bottom-Up Design Model for Improving Efficiency of Transit System","authors":"Jiayang Li, Ruzhang Zhao, Meng Li, Y. Ouyang","doi":"10.1109/UV.2018.8642126","DOIUrl":"https://doi.org/10.1109/UV.2018.8642126","url":null,"abstract":"This paper presents a model to design high-performance public transit system, where the optimal solution is directly selected from routes built up on real road structure. The objective function is the travel time for all travelers and the infrastructure cost can also be under consideration. The optimization procedure consists of four components, including a method to simulate downtown travel demand using open-source data on the Internet, a method to narrow down the decision variable space with the help of reasonable restriction and map api, an efficient a lgorithm to compute average travel time using block representation of the urban area and an improved evolutionary algorithm to search the optimal solution. Eventually, this method is applied to design the transit system for Changzhi, China. The optimal solution is compared to the original transit system of Changzhi to test both the effect and reasonability of the algorithm.","PeriodicalId":110658,"journal":{"name":"2018 4th International Conference on Universal Village (UV)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126878316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"UV 2018 Program Book","authors":"","doi":"10.1109/uv.2018.8642138","DOIUrl":"https://doi.org/10.1109/uv.2018.8642138","url":null,"abstract":"","PeriodicalId":110658,"journal":{"name":"2018 4th International Conference on Universal Village (UV)","volume":"207 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122666080","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 work, a Novel Adaptive Filter (NAF) is proposed for optimal control of grid-integrated solar PV (Photovoltaic) generating system. The proposed NAF is the improved form of classical adaptive vectorial filter (AVF), where inherent problems of AVF technique, like unable to handle the phase imbalance and phase shift issues, are successfully mitigated. For performance evaluation of NAF based control technique, a single-stage topology of three-phase grid integrated solar PV system is taken, where the loads are connected at the PCC (Point of Common Coupling). The prime objective of proposed NAF based control technique is to meet the active power requirement of loads from generated solar PV power, and after fulfill the load demand, the excess power is supplied to the grid. However, when generated PV power is not sufficient for the load then the NAF based control fulfills the load demand by taking extra required power from the grid. During this process, the power quality of the grid power is improved. The controller action provides, power factor correction, harmonics filtering and mitigation of other power quality issues. Moreover, when the solar irradiation is zero, then the voltage source converter acts as a distribution static compensator (DSTATCOM), which enhances the utilization factor of the system. The proposed techniques are modeled and their performances are verified experimentally on a developed prototype, in solar insolation variation conditions, unbalanced loading, as well as in different grid disturbances such as overvoltage, under-voltage, phase imbalance, harmonics distortion in the grid voltage etc.
{"title":"Integration of Solar PV Generation with Distribution Grid: Using Novel Adaptive Filter Based Control Technique","authors":"Nishant Kumar, Bhim Singh, B. K. Panigrahi","doi":"10.1109/UV.2018.8642120","DOIUrl":"https://doi.org/10.1109/UV.2018.8642120","url":null,"abstract":"In this work, a Novel Adaptive Filter (NAF) is proposed for optimal control of grid-integrated solar PV (Photovoltaic) generating system. The proposed NAF is the improved form of classical adaptive vectorial filter (AVF), where inherent problems of AVF technique, like unable to handle the phase imbalance and phase shift issues, are successfully mitigated. For performance evaluation of NAF based control technique, a single-stage topology of three-phase grid integrated solar PV system is taken, where the loads are connected at the PCC (Point of Common Coupling). The prime objective of proposed NAF based control technique is to meet the active power requirement of loads from generated solar PV power, and after fulfill the load demand, the excess power is supplied to the grid. However, when generated PV power is not sufficient for the load then the NAF based control fulfills the load demand by taking extra required power from the grid. During this process, the power quality of the grid power is improved. The controller action provides, power factor correction, harmonics filtering and mitigation of other power quality issues. Moreover, when the solar irradiation is zero, then the voltage source converter acts as a distribution static compensator (DSTATCOM), which enhances the utilization factor of the system. The proposed techniques are modeled and their performances are verified experimentally on a developed prototype, in solar insolation variation conditions, unbalanced loading, as well as in different grid disturbances such as overvoltage, under-voltage, phase imbalance, harmonics distortion in the grid voltage etc.","PeriodicalId":110658,"journal":{"name":"2018 4th International Conference on Universal Village (UV)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128212633","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}
With the continuous development of new-generation information technology and new-generation artificial intelligence technology, the manufacturing enterprises become more autonomous and associated with each other than before. In the cloud manufacturing environment which is a kind of intelligent manufacturing model, the production modes of manufacturing enterprises are of great concern. The production modes are transforming from the traditional mass production mode to the demand-oriented mode in which the individualized product attributes are prominent. Through modeling and simulation, this paper studies the impact of different production modes on the operational efficiency of enterprises in the cloud manufacturing environment, and preliminarily explores the operating strategies and survival modes of manufacturing enterprises in the future global collaborative manufacturing environment.
{"title":"Simulation of Production Modes for Cloud Manufacturing Enterprises","authors":"Longfei Zhou, Lin Zhang, L. Ren","doi":"10.1109/UV.2018.8642129","DOIUrl":"https://doi.org/10.1109/UV.2018.8642129","url":null,"abstract":"With the continuous development of new-generation information technology and new-generation artificial intelligence technology, the manufacturing enterprises become more autonomous and associated with each other than before. In the cloud manufacturing environment which is a kind of intelligent manufacturing model, the production modes of manufacturing enterprises are of great concern. The production modes are transforming from the traditional mass production mode to the demand-oriented mode in which the individualized product attributes are prominent. Through modeling and simulation, this paper studies the impact of different production modes on the operational efficiency of enterprises in the cloud manufacturing environment, and preliminarily explores the operating strategies and survival modes of manufacturing enterprises in the future global collaborative manufacturing environment.","PeriodicalId":110658,"journal":{"name":"2018 4th International Conference on Universal Village (UV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132646933","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}
Our current society is facing challenges in both sustainability and environmental pollution due to fast urbanization, limited resources, and increasing senior population. Smart cities which aim to increase efficiency and convenience would not be able to solve fundamental challenges caused by urban lifestyles. In 2013, the Universal Village concept was proposed to enhance human-nature harmony through prudent use of technologies and to address the eco-challenges due to fast urbanization.This paper first studies the environmental implications due to urban lifestyles and proposes the suitable UV framework and detailed content of universal village lifestyle in order to address the eco-challenges. The paper then evaluates the development of current smart city technologies and assesses their validity with regard to the concept of Universal Village through systematic studies of several major intelligent systems.Specifically, this paper discusses the subject of connectivity from four perspectives: mutual interaction, feedback loop, dynamic information loop, and material cycle. The paper evaluates whether information feedback loops could be formed for these major systems, and also explores the mutual interaction and dependence among the seemingly independent major systems. We discover that mutual interaction connects the aforementioned systems into an interconnected network and naturally forms dynamic information loops in which the decision of one system may be the required input of another system or vice versa. This implies that proper functioning of these systems requires extensive information sharing among them. One event might dynamically trigger different events. The last connectivity is a material cycle. We explore the whole life cycle of products, including impact from lifestyle, customers’ need, product design, cloud manufacturing, sale channel, feedback collection from customers, reuse and recycling, scrapping, to final waste-disposal, etc., and study how to reduce the demand for resource and waste during the procedure. The idea is to include the perspective of UV lifestyle when designing products: considering the possibility in proactively reducing the need, sharing a product with different people, reusing product parts into the manufacturing, recycling reusable components of finished products before the products’ being fully disassembled, etc. The advantage is to reduce the need for products and to avoid manufacturing the same components from raw materials directly, which demands less resource.In summary, connectivity, as discussed from the four perspectives, would greatly contribute to the effectiveness and efficiency of our connected smart systems. Dynamic information loop helps coordinate resource allocation, decreases the collective costs, and reduces demand of natural resources from the natural environment, resulting in less damage to the environment which ultimately enhances system-wide harmony between human and its natural environment, an
{"title":"Preliminary Study on Evaluation of Smart-Cities Technologies and Proposed UV Lifestyles","authors":"Shengsheng Cao, Yanxi Chen, Guanghua Cheng, Fuxin Du, Wen Gao, Ziyan He, Shuqing Li, Shijun Lun, Haoran Ma, Qikai Su, Chuyuan Zhang, Tianyi Zhang, Zejun Zhang, Jie Zheng, Longfei Zhou, Yajun Fang","doi":"10.1109/UV.2018.8642142","DOIUrl":"https://doi.org/10.1109/UV.2018.8642142","url":null,"abstract":"Our current society is facing challenges in both sustainability and environmental pollution due to fast urbanization, limited resources, and increasing senior population. Smart cities which aim to increase efficiency and convenience would not be able to solve fundamental challenges caused by urban lifestyles. In 2013, the Universal Village concept was proposed to enhance human-nature harmony through prudent use of technologies and to address the eco-challenges due to fast urbanization.This paper first studies the environmental implications due to urban lifestyles and proposes the suitable UV framework and detailed content of universal village lifestyle in order to address the eco-challenges. The paper then evaluates the development of current smart city technologies and assesses their validity with regard to the concept of Universal Village through systematic studies of several major intelligent systems.Specifically, this paper discusses the subject of connectivity from four perspectives: mutual interaction, feedback loop, dynamic information loop, and material cycle. The paper evaluates whether information feedback loops could be formed for these major systems, and also explores the mutual interaction and dependence among the seemingly independent major systems. We discover that mutual interaction connects the aforementioned systems into an interconnected network and naturally forms dynamic information loops in which the decision of one system may be the required input of another system or vice versa. This implies that proper functioning of these systems requires extensive information sharing among them. One event might dynamically trigger different events. The last connectivity is a material cycle. We explore the whole life cycle of products, including impact from lifestyle, customers’ need, product design, cloud manufacturing, sale channel, feedback collection from customers, reuse and recycling, scrapping, to final waste-disposal, etc., and study how to reduce the demand for resource and waste during the procedure. The idea is to include the perspective of UV lifestyle when designing products: considering the possibility in proactively reducing the need, sharing a product with different people, reusing product parts into the manufacturing, recycling reusable components of finished products before the products’ being fully disassembled, etc. The advantage is to reduce the need for products and to avoid manufacturing the same components from raw materials directly, which demands less resource.In summary, connectivity, as discussed from the four perspectives, would greatly contribute to the effectiveness and efficiency of our connected smart systems. Dynamic information loop helps coordinate resource allocation, decreases the collective costs, and reduces demand of natural resources from the natural environment, resulting in less damage to the environment which ultimately enhances system-wide harmony between human and its natural environment, an","PeriodicalId":110658,"journal":{"name":"2018 4th International Conference on Universal Village (UV)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122142097","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}
Plant growth is greatly affected by light. However, the uniformity of light in plant growth chambers has always been a common problem that was not appropriately addressed. As this, the uniformity of light in a plant growth chamber illuminated by light-emitting diodes (LEDs) was investigated in this paper. The orthogonal experimental design method was used to test the influence of various factors on the uniformity of light intensity in a plant growth chamber using the lighting simulation software DIALux. The major factors investigated in this paper include the divergence angle, number and arrangement of LED lamps, as well as the reflectivity of the inner walls of the chamber and the minor factors include the vertical distance from the LED board and the distance from the board edges. The relative importance of influence of each factor on the uniformity of light in the chamber was obtained and finally, an optimized model of the plant growth chamber with a uniformly distributed illumination was obtained.Simulation results showed that reflectivity of the inner walls had the highest influence on the uniformity of light on the working plane, followed by the divergence angle of the LED lamps, and the number of LEDs had the lowest influence. Therefore, the number of LEDs may mainly affect the intensity of light on the working plane but not the uniformity on the plane’s illumination significantly, especially when the distance from the LED board is relatively large. Results also showed that the uniformity of light increases vertically from the LED board and with the edge distance as well. Based on our simulation results, a three-dimensional optimal cultivation area in a plant growth chamber was suggested which achieved the uniformity of 0.93.
{"title":"Analysis of the Uniformity of Light in a Plant Growth Chamber","authors":"Yong Xu, Hanbin Wang, Walter Nsengiyumva","doi":"10.1109/UV.2018.8642131","DOIUrl":"https://doi.org/10.1109/UV.2018.8642131","url":null,"abstract":"Plant growth is greatly affected by light. However, the uniformity of light in plant growth chambers has always been a common problem that was not appropriately addressed. As this, the uniformity of light in a plant growth chamber illuminated by light-emitting diodes (LEDs) was investigated in this paper. The orthogonal experimental design method was used to test the influence of various factors on the uniformity of light intensity in a plant growth chamber using the lighting simulation software DIALux. The major factors investigated in this paper include the divergence angle, number and arrangement of LED lamps, as well as the reflectivity of the inner walls of the chamber and the minor factors include the vertical distance from the LED board and the distance from the board edges. The relative importance of influence of each factor on the uniformity of light in the chamber was obtained and finally, an optimized model of the plant growth chamber with a uniformly distributed illumination was obtained.Simulation results showed that reflectivity of the inner walls had the highest influence on the uniformity of light on the working plane, followed by the divergence angle of the LED lamps, and the number of LEDs had the lowest influence. Therefore, the number of LEDs may mainly affect the intensity of light on the working plane but not the uniformity on the plane’s illumination significantly, especially when the distance from the LED board is relatively large. Results also showed that the uniformity of light increases vertically from the LED board and with the edge distance as well. Based on our simulation results, a three-dimensional optimal cultivation area in a plant growth chamber was suggested which achieved the uniformity of 0.93.","PeriodicalId":110658,"journal":{"name":"2018 4th International Conference on Universal Village (UV)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128916554","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}
Activities of Daily Living (ADLs), or a person’s routine activities of self-care, are important factors influencing the feasibility of home health care or aging in place for many individuals. Automated, sensor-based recognition of such activities affords home stay, greater independence and privacy, and improved quality of life to individuals who would require stay in a supervised or medical facility. This paper describes a data-driven framework for the design and deployment of such an automated system for activity recognition using simple, unobtrusive, and privacy-friendly binary sensors. It presents the results of an experimental study, with both numerical and qualitative observations, of this framework on a publicly available real dataset.
{"title":"Recognizing Activities of Daily Living Using Binary Sensors","authors":"S. Chawathe","doi":"10.1109/UV.2018.8642134","DOIUrl":"https://doi.org/10.1109/UV.2018.8642134","url":null,"abstract":"Activities of Daily Living (ADLs), or a person’s routine activities of self-care, are important factors influencing the feasibility of home health care or aging in place for many individuals. Automated, sensor-based recognition of such activities affords home stay, greater independence and privacy, and improved quality of life to individuals who would require stay in a supervised or medical facility. This paper describes a data-driven framework for the design and deployment of such an automated system for activity recognition using simple, unobtrusive, and privacy-friendly binary sensors. It presents the results of an experimental study, with both numerical and qualitative observations, of this framework on a publicly available real dataset.","PeriodicalId":110658,"journal":{"name":"2018 4th International Conference on Universal Village (UV)","volume":"245 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131559131","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：