Pub Date : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645679
Hyunjin Joo, Y. Lim
Traffic congestion is one of the common urban problems caused by increased traffic. Traffic congestion accelerates environmental pollution by wasting drivers’ time and fuel and generating more fumes. Therefore, traffic congestion is an important issue to be solved. Currently, as technologies develop, a smart city that efficiently manages data information collected is in the spotlight. The smart transportation system utilizes the infrastructure and network built in the smart city to analyze traffic flow and control traffic in real-time. Accordingly, traffic congestion can be effectively alleviated. This paper proposes a smart traffic signal control system using a Deep Q-network (DQN), a type of reinforcement learning. The proposed algorithm distributes the optimal green signal time by collecting and learning information about the intersection situation. The proposed algorithm is designed to improve the performance in terms of throughput. As a result, the number of waiting vehicles also decreased. To validate the algorithm, we evaluate the performance in various traffic scenarios.
{"title":"Intelligent Traffic Signal Control System using Deep Q-network","authors":"Hyunjin Joo, Y. Lim","doi":"10.1109/ECICE52819.2021.9645679","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645679","url":null,"abstract":"Traffic congestion is one of the common urban problems caused by increased traffic. Traffic congestion accelerates environmental pollution by wasting drivers’ time and fuel and generating more fumes. Therefore, traffic congestion is an important issue to be solved. Currently, as technologies develop, a smart city that efficiently manages data information collected is in the spotlight. The smart transportation system utilizes the infrastructure and network built in the smart city to analyze traffic flow and control traffic in real-time. Accordingly, traffic congestion can be effectively alleviated. This paper proposes a smart traffic signal control system using a Deep Q-network (DQN), a type of reinforcement learning. The proposed algorithm distributes the optimal green signal time by collecting and learning information about the intersection situation. The proposed algorithm is designed to improve the performance in terms of throughput. As a result, the number of waiting vehicles also decreased. To validate the algorithm, we evaluate the performance in various traffic scenarios.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115561064","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645600
Ting-lei Huang
Smart tourism has recently received widespread attention from academia and practitioners. The concept aims to improve the tourism experience and increase the competitiveness of destinations based on the development of technologies such as the Internet, communications, and big data. In order to cope with the industry development challenges brought by personalized tourism in the era of big data, this paper uses the text of online travel notes with Guizhou as the destination as the data source, and proposes a travel destination review sentiment classification model based on convolutional neural network. Compared with several other machine learning models, this model has the highest accuracy of emotion classification, reaching 91.6%, and it has a very good effect on text emotion classification.
{"title":"Research on Sentiment Classification of Tourist Destinations Based on Convolutional Neural Network","authors":"Ting-lei Huang","doi":"10.1109/ECICE52819.2021.9645600","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645600","url":null,"abstract":"Smart tourism has recently received widespread attention from academia and practitioners. The concept aims to improve the tourism experience and increase the competitiveness of destinations based on the development of technologies such as the Internet, communications, and big data. In order to cope with the industry development challenges brought by personalized tourism in the era of big data, this paper uses the text of online travel notes with Guizhou as the destination as the data source, and proposes a travel destination review sentiment classification model based on convolutional neural network. Compared with several other machine learning models, this model has the highest accuracy of emotion classification, reaching 91.6%, and it has a very good effect on text emotion classification.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129681414","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645699
Youngjin Ye, T. Wu
Dye-sensitized solar cells (DSSC) emerge as promising devices for solar energy conversion owing to their high theoretical PCE and low-cost fabrication processes, as well as good tunability of dye band structure and device transparency [1]. Thus, DSSC is developing fast. Silver nanowires have excellent photoelectrochemical properties such as good electrical conductivity, excellent surface plasmon resonance, and low resistance. These parameters have an important impact on the performance improvement of DSSC. In this study, the effect of the concentration of silver nanowires in titanium dioxide was investigated to analyze the effects of different concentrations on DSSC. First, different concentrations of silver nanowires were added to the titanium dioxide sauce, and coated on the Indium tin oxide (ITO) conductive glass substrate by a doctor blade method, and then subjected to compression molding. The thickness of the film after compression is about 10 μm on average. The film is put into a high-temperature furnace for annealing treatment, then into N3 to adsorb the dye, and finally encapsulated by the sandwich stacking method to complete the production of the DSSC. The results show the DSSC with a concentration of 0.05 wt% silver nanowire achieves the photoelectric conversion efficiency has reached 4.14%, the short-term current density (Jsc) is 8.14 mA/cm2, and the photoelectric conversion efficiency without the addition of silver nanowire is only 3.54%. The short current density is only 7.71 mA/cm2, and the photoelectric conversion efficiency is improved by 17%.
染料敏化太阳能电池(dye -sensitized solar cells, DSSC)因其较高的理论PCE和低成本的制造工艺，以及良好的染料能带结构可调性和器件透明度而成为太阳能转换的有前途的器件[1]。因此，DSSC发展迅速。银纳米线具有良好的导电性、优异的表面等离子体共振和低电阻等优异的光电化学性能。这些参数对DSSC的性能提升有重要影响。本研究考察了二氧化钛中银纳米线浓度的影响，分析了不同浓度对DSSC的影响。首先，在二氧化钛酱中加入不同浓度的银纳米线，采用医生刀法将其涂覆在氧化铟锡(ITO)导电玻璃基板上，然后进行压缩成型。压缩后的薄膜厚度平均约为10 μm。将薄膜放入高温炉中进行退火处理，然后放入N3中吸附染料，最后采用夹心堆叠法封装，完成DSSC的生产。结果表明，添加0.05 wt%银纳米线时，DSSC的光电转换效率达到4.14%，短期电流密度(Jsc)为8.14 mA/cm2，而未添加银纳米线的光电转换效率仅为3.54%。短电流密度仅为7.71 mA/cm2，光电转换效率提高17%。
{"title":"Preparation of Photoanode Composite Layers with Different Concentrations of Silver Nanowires Combined with TiO2 for Dye-sensitized Solar Cells","authors":"Youngjin Ye, T. Wu","doi":"10.1109/ECICE52819.2021.9645699","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645699","url":null,"abstract":"Dye-sensitized solar cells (DSSC) emerge as promising devices for solar energy conversion owing to their high theoretical PCE and low-cost fabrication processes, as well as good tunability of dye band structure and device transparency [1]. Thus, DSSC is developing fast. Silver nanowires have excellent photoelectrochemical properties such as good electrical conductivity, excellent surface plasmon resonance, and low resistance. These parameters have an important impact on the performance improvement of DSSC. In this study, the effect of the concentration of silver nanowires in titanium dioxide was investigated to analyze the effects of different concentrations on DSSC. First, different concentrations of silver nanowires were added to the titanium dioxide sauce, and coated on the Indium tin oxide (ITO) conductive glass substrate by a doctor blade method, and then subjected to compression molding. The thickness of the film after compression is about 10 μm on average. The film is put into a high-temperature furnace for annealing treatment, then into N3 to adsorb the dye, and finally encapsulated by the sandwich stacking method to complete the production of the DSSC. The results show the DSSC with a concentration of 0.05 wt% silver nanowire achieves the photoelectric conversion efficiency has reached 4.14%, the short-term current density (Jsc) is 8.14 mA/cm2, and the photoelectric conversion efficiency without the addition of silver nanowire is only 3.54%. The short current density is only 7.71 mA/cm2, and the photoelectric conversion efficiency is improved by 17%.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128717351","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645654
Junyeol Yu, Jongseok Kim, Euiseong Seo
Graphics Processing Units (GPUs) are widely used for deep learning training as well as inference due to their high processing speed and programmability. Modern GPUs dynamically adjust the clock frequency according to their power management scheme. However, under the default scheme, the clock frequency of a GPU is only determined by utilization rate while being blind to target latency SLO, leading to unnecessary high clock frequency which causes excessive power consumption. In this paper, we propose a method to increase the energy efficiency of a GPU while satisfying latency SLO through performance scaling. It dynamically monitors the queue length of the inference engine to determine the optimal clock that can satisfy latency SLO. We implemented an efficient inference service using GPU DVFS on the existing inference engine. According to the result of experiments on inference over image classification models using three types of GPUs, all the 99th percentile latency in our method satisfied latency SLO while exhibiting better power efficiency. In particular, when processing the VGG19 model on Titan RTX, the energy consumption of the GPU is reduced by up to 49.5% compared to the default clock management when processing the same request rates.
{"title":"A DNN Inference Latency-aware GPU Power Management Scheme","authors":"Junyeol Yu, Jongseok Kim, Euiseong Seo","doi":"10.1109/ECICE52819.2021.9645654","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645654","url":null,"abstract":"Graphics Processing Units (GPUs) are widely used for deep learning training as well as inference due to their high processing speed and programmability. Modern GPUs dynamically adjust the clock frequency according to their power management scheme. However, under the default scheme, the clock frequency of a GPU is only determined by utilization rate while being blind to target latency SLO, leading to unnecessary high clock frequency which causes excessive power consumption. In this paper, we propose a method to increase the energy efficiency of a GPU while satisfying latency SLO through performance scaling. It dynamically monitors the queue length of the inference engine to determine the optimal clock that can satisfy latency SLO. We implemented an efficient inference service using GPU DVFS on the existing inference engine. According to the result of experiments on inference over image classification models using three types of GPUs, all the 99th percentile latency in our method satisfied latency SLO while exhibiting better power efficiency. In particular, when processing the VGG19 model on Titan RTX, the energy consumption of the GPU is reduced by up to 49.5% compared to the default clock management when processing the same request rates.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128298015","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645632
Jonghyung Lee, Insoo Lee
Lithium batteries are being employed as primary power sources in various applications, including cell phones, electric vehicles, unmanned submarines, and energy storage systems. Therefore, for stable and safe use of a system, it is important to quickly detect defects in the battery and effectively diagnose faults. In this work, we proposed an algorithm that evaluates the state of charge (SOC) and state of health (SOH) online using long short-term memory (LSTM). The SOC is estimated using an LSTM model bank with three LSTM models in which a battery data group has learned normal, caution, and fault. The SOH is estimated by receiving SOC and battery parameters from the LSTM model bank to output SOH as one of the three states: normal, caution, and fault. Experimental results show that the proposed battery SOC and SOH estimation algorithm have high accuracy.
{"title":"Online Estimation Algorithm of SOC and SOH Using Neural Network for Lithium Battery","authors":"Jonghyung Lee, Insoo Lee","doi":"10.1109/ECICE52819.2021.9645632","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645632","url":null,"abstract":"Lithium batteries are being employed as primary power sources in various applications, including cell phones, electric vehicles, unmanned submarines, and energy storage systems. Therefore, for stable and safe use of a system, it is important to quickly detect defects in the battery and effectively diagnose faults. In this work, we proposed an algorithm that evaluates the state of charge (SOC) and state of health (SOH) online using long short-term memory (LSTM). The SOC is estimated using an LSTM model bank with three LSTM models in which a battery data group has learned normal, caution, and fault. The SOH is estimated by receiving SOC and battery parameters from the LSTM model bank to output SOH as one of the three states: normal, caution, and fault. Experimental results show that the proposed battery SOC and SOH estimation algorithm have high accuracy.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"159 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121392637","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645672
Cheng-Yan Siao, Rong-Guey Chang, Miao-Hua Chen, Shu-Yin Wang
The global hospital's capacity can gradually decline, especially after the outbreak of the COVID-19, and thus traditional medical methods can no longer bear a large number of patients. At present, most hospitals rely on doctors and nursing staff to diagnose and treat patients. This not only increases the burden on doctors and nursing staff but also greatly reduces the burden on health care quality. In order to obtain better health care quality, automation is one of the important factors in solving medical quality problems. We are conducting automated introduction research for the ultrasonic scanner. Robotic arms are used to replace doctors for consultations by adding jelly and injection buttons to the robotic arm. In terms of the contact between the end of the robotic arm and the human body, we introduced the force sensor and the depth camera into the robotic arm. With the force sensor and the depth camera feedback data, we perceive the feedback of the ultrasonic scanner and the human body contact force. The results show that our design can greatly increase the amount of hospital’s capacity and reduce the burden on doctors.
{"title":"Design of Contact Force for Ultrasonic Scanner","authors":"Cheng-Yan Siao, Rong-Guey Chang, Miao-Hua Chen, Shu-Yin Wang","doi":"10.1109/ECICE52819.2021.9645672","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645672","url":null,"abstract":"The global hospital's capacity can gradually decline, especially after the outbreak of the COVID-19, and thus traditional medical methods can no longer bear a large number of patients. At present, most hospitals rely on doctors and nursing staff to diagnose and treat patients. This not only increases the burden on doctors and nursing staff but also greatly reduces the burden on health care quality. In order to obtain better health care quality, automation is one of the important factors in solving medical quality problems. We are conducting automated introduction research for the ultrasonic scanner. Robotic arms are used to replace doctors for consultations by adding jelly and injection buttons to the robotic arm. In terms of the contact between the end of the robotic arm and the human body, we introduced the force sensor and the depth camera into the robotic arm. With the force sensor and the depth camera feedback data, we perceive the feedback of the ultrasonic scanner and the human body contact force. The results show that our design can greatly increase the amount of hospital’s capacity and reduce the burden on doctors.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116332249","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645652
Haïfa Souifi, Y. Bouslimani, M. Ghribi
Applying to many commercial and residential applications, air-to-air heat/energy exchangers are extensively considered as one of the promising technologies for improving indoor air quality (IAQ), providing thermal comfort, and dwindling energy consumption costs as well. The present paper proposes an IoT-based platform to experimentally assess the performances of a heat recovery ventilator (HRV) system in terms of heat recovery and IAQ enhancement. To gather and log measurements, the developed IoT platform is integrated into the mechanical ventilation system without affecting its operation modes. For more than 12 months, the proposed IoT approach successfully collected and sent every 60 s, real-time measurements related to the indoor and outdoor air quality, with a focus on TVOC and CO2, and the related temperature, humidity, and pressure used to assess the system’s sensible heat recovery potential. Results from a real environment located in New Brunswick, Canada are presented, and the system performances are evaluated under extreme weather conditions. The developed IoT platform was flexible in terms of deployment and data exchange and proved to be efficient in collecting real-time data.
{"title":"IoT-based Platform for an Air-to-Air Heat Exchanger Evaluation","authors":"Haïfa Souifi, Y. Bouslimani, M. Ghribi","doi":"10.1109/ECICE52819.2021.9645652","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645652","url":null,"abstract":"Applying to many commercial and residential applications, air-to-air heat/energy exchangers are extensively considered as one of the promising technologies for improving indoor air quality (IAQ), providing thermal comfort, and dwindling energy consumption costs as well. The present paper proposes an IoT-based platform to experimentally assess the performances of a heat recovery ventilator (HRV) system in terms of heat recovery and IAQ enhancement. To gather and log measurements, the developed IoT platform is integrated into the mechanical ventilation system without affecting its operation modes. For more than 12 months, the proposed IoT approach successfully collected and sent every 60 s, real-time measurements related to the indoor and outdoor air quality, with a focus on TVOC and CO2, and the related temperature, humidity, and pressure used to assess the system’s sensible heat recovery potential. Results from a real environment located in New Brunswick, Canada are presented, and the system performances are evaluated under extreme weather conditions. The developed IoT platform was flexible in terms of deployment and data exchange and proved to be efficient in collecting real-time data.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116545774","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645692
Cheng-Yan Siao, Rong-Guey Chang, Robert Kuo Chung Lin, F. Foo
At present, COVID-19 still affects the world. In order to avoid contact among people, we build site simulation maps for specific areas of the region and introduce mobile robots. In the hospital, it is possible to simulate the route between the corridor and the ward, and use mobile robots to complete specific location guidance and regional patrols, replacing medical manpower. With our proposed system, the user can reach the desired destination through the voice guidance of the robot without the assistance of medical staff. When the user is in danger, the robot can provide a video phone to complete the emergency contact, so that the staff can remotely control the robot to assist the user. We add automatic patrol and detection to the robot's travel route. When the robot finds suspicious objects in the process of moving, the system immediately returns to the alarm guard. The results show that mobile robots can effectively reduce manpower and avoid contact between people.
{"title":"Automatic Guidance and Assistance in Specific Areas Based on Mobile Robot","authors":"Cheng-Yan Siao, Rong-Guey Chang, Robert Kuo Chung Lin, F. Foo","doi":"10.1109/ECICE52819.2021.9645692","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645692","url":null,"abstract":"At present, COVID-19 still affects the world. In order to avoid contact among people, we build site simulation maps for specific areas of the region and introduce mobile robots. In the hospital, it is possible to simulate the route between the corridor and the ward, and use mobile robots to complete specific location guidance and regional patrols, replacing medical manpower. With our proposed system, the user can reach the desired destination through the voice guidance of the robot without the assistance of medical staff. When the user is in danger, the robot can provide a video phone to complete the emergency contact, so that the staff can remotely control the robot to assist the user. We add automatic patrol and detection to the robot's travel route. When the robot finds suspicious objects in the process of moving, the system immediately returns to the alarm guard. The results show that mobile robots can effectively reduce manpower and avoid contact between people.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115799148","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645613
Fan Jiang, Zhenglin Li, Minghao Tan, Qingteng Zhao
The current situation makes it difficult to find free parking spaces when cars enter the parking lot. Thus the management of parking systems requires an intelligent system based on RFID technology. By using the control chip and conveyor belts, the collection, transportation, and unloading of vehicles are managed. The infrared digital obstacle avoidance sensor module detects the parking space. RC522 card reading module records the times of swiping card and parking time. The serial screen display module displays parking space and exhaust gas concentration, and the real-time view of free parking space. The information of parking space availability is transmitted to the computer through a Bluetooth module for remote monitoring.
{"title":"Design and Strategy of Intelligent Management System for Parking","authors":"Fan Jiang, Zhenglin Li, Minghao Tan, Qingteng Zhao","doi":"10.1109/ECICE52819.2021.9645613","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645613","url":null,"abstract":"The current situation makes it difficult to find free parking spaces when cars enter the parking lot. Thus the management of parking systems requires an intelligent system based on RFID technology. By using the control chip and conveyor belts, the collection, transportation, and unloading of vehicles are managed. The infrared digital obstacle avoidance sensor module detects the parking space. RC522 card reading module records the times of swiping card and parking time. The serial screen display module displays parking space and exhaust gas concentration, and the real-time view of free parking space. The information of parking space availability is transmitted to the computer through a Bluetooth module for remote monitoring.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122284615","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 : 2021-10-29DOI: 10.1109/ECICE52819.2021.9645712
C. Chang, Huang-Ming Chang
Nowadays, recommendation systems are widely used to help users locate the items they want. Collaborative filtering (CF) is a commonly used method for the recommendation. CF techniques use user-item ratings for prediction but suffer from the problems of data sparsity, cold start, and scalability. Though the Matrix Factorization (MF) techniques like Singular Value Decomposition (SVD) or Principal Component Analysis (PCA) overcome the above-mentioned problems, these methods are possible to deliver unmeaningful results in the condition of a low ranked approximation and denser singular vectors. In this paper, we review strategies of collaborative filtering recommendation mechanisms and propose an approach based on an autoencoder of convolutional neural network. Autoencoders are unsupervised learning methods in which neural networks are supported for the task of representation learning. We identify the user’s features through learning, and then use these features to combine the collaborative filtering algorithm to recommend items. The experimental results show that the convolutional autoencoder can effectively reduce the computations when the amount of data is huge and benefited from the performance of its convolutional neural network.
{"title":"Strategies of Collaborative Filtering Recommendation Mechanism Using a Deep Learning Approach","authors":"C. Chang, Huang-Ming Chang","doi":"10.1109/ECICE52819.2021.9645712","DOIUrl":"https://doi.org/10.1109/ECICE52819.2021.9645712","url":null,"abstract":"Nowadays, recommendation systems are widely used to help users locate the items they want. Collaborative filtering (CF) is a commonly used method for the recommendation. CF techniques use user-item ratings for prediction but suffer from the problems of data sparsity, cold start, and scalability. Though the Matrix Factorization (MF) techniques like Singular Value Decomposition (SVD) or Principal Component Analysis (PCA) overcome the above-mentioned problems, these methods are possible to deliver unmeaningful results in the condition of a low ranked approximation and denser singular vectors. In this paper, we review strategies of collaborative filtering recommendation mechanisms and propose an approach based on an autoencoder of convolutional neural network. Autoencoders are unsupervised learning methods in which neural networks are supported for the task of representation learning. We identify the user’s features through learning, and then use these features to combine the collaborative filtering algorithm to recommend items. The experimental results show that the convolutional autoencoder can effectively reduce the computations when the amount of data is huge and benefited from the performance of its convolutional neural network.","PeriodicalId":176225,"journal":{"name":"2021 IEEE 3rd Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127229269","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：