Pub Date : 2021-03-12DOI: 10.1109/ATiGB50996.2021.9423234
Song-Toan PHAM-PHU, M. Asari
The landfill sites in Vietnam are struggling to carry huge amounts of organic waste every day. While the domestic demand of using organic fertilizers for clean agriculture is increasing, these organic materials are disposed in a wasteful way. This study indicated that the nitrogen (N) concentration of the waste that include septic tank sludge (STS), food waste (FW) and sludge from seafood waste water treatment plant (SFS) is quite high by 965 mg/L, 34,314 mg/L and 1,756 mg/L. In this study, an Anaerobic Digester_Continuously Stirred Tank Reaction (ADCSTR) system was established to recover the N from these wastes. The ADCSTR was made of 5 mm thick tempered glass, with the dimension of the tank is H x D x R = 1,000 mm x 300 mm x 300 mm. The C/N ratio used for the ADCSTR was 25, which was identified by pre-testing seven small AD systems with different C/N ratios. The result revealed that after 50 d of anaerobic digestion, the Carbon (C) and Nitrogen (N) concentrations of liquid product was 9,628.3 mg/L and 648.5 mg/L, and the carbon to nitrogen ratio (C/N) was 11.35 as well, equivalent to 78.2 % of recovering efficiency. This study also indicated the potential to recover nutrition, produce organic fertilizer from recycling the STS, FW and SFS in Vietnam, significantly contribute to reducing waste to the disposals.
越南的垃圾填埋场每天都在努力处理大量的有机废物。虽然国内对清洁农业使用有机肥的需求正在增加，但这些有机材料的处理方式却很浪费。本研究表明，化粪池污泥(STS)、食物垃圾(FW)和海产污水处理厂污泥(SFS)的氮(N)浓度较高，分别为965 mg/L、34,314 mg/L和1,756 mg/L。本研究建立厌氧消化-连续搅拌槽反应(ADCSTR)系统，从这些废物中回收N。ADCSTR由5mm厚的钢化玻璃制成，箱体尺寸为高×深×深= 1,000 mm × 300 mm × 300 mm。用于ADCSTR的碳氮比为25，通过对7个不同碳氮比的小型AD系统进行预测试确定。结果表明，厌氧消化50 d后，液产物碳(C)和氮(N)浓度分别为9628.3 mg/L和648.5 mg/L，碳氮比(C/N)为11.35，回收率为78.2%。该研究还表明，在越南，通过回收化粪池、FW和SFS来回收营养，生产有机肥料的潜力，大大有助于减少废物的处置。
{"title":"Study on Nitrogen Recovery from Nutrient-Rich Waste by ADCSTR System","authors":"Song-Toan PHAM-PHU, M. Asari","doi":"10.1109/ATiGB50996.2021.9423234","DOIUrl":"https://doi.org/10.1109/ATiGB50996.2021.9423234","url":null,"abstract":"The landfill sites in Vietnam are struggling to carry huge amounts of organic waste every day. While the domestic demand of using organic fertilizers for clean agriculture is increasing, these organic materials are disposed in a wasteful way. This study indicated that the nitrogen (N) concentration of the waste that include septic tank sludge (STS), food waste (FW) and sludge from seafood waste water treatment plant (SFS) is quite high by 965 mg/L, 34,314 mg/L and 1,756 mg/L. In this study, an Anaerobic Digester_Continuously Stirred Tank Reaction (ADCSTR) system was established to recover the N from these wastes. The ADCSTR was made of 5 mm thick tempered glass, with the dimension of the tank is H x D x R = 1,000 mm x 300 mm x 300 mm. The C/N ratio used for the ADCSTR was 25, which was identified by pre-testing seven small AD systems with different C/N ratios. The result revealed that after 50 d of anaerobic digestion, the Carbon (C) and Nitrogen (N) concentrations of liquid product was 9,628.3 mg/L and 648.5 mg/L, and the carbon to nitrogen ratio (C/N) was 11.35 as well, equivalent to 78.2 % of recovering efficiency. This study also indicated the potential to recover nutrition, produce organic fertilizer from recycling the STS, FW and SFS in Vietnam, significantly contribute to reducing waste to the disposals.","PeriodicalId":6690,"journal":{"name":"2020 Applying New Technology in Green Buildings (ATiGB)","volume":"182 1","pages":"125-129"},"PeriodicalIF":0.0,"publicationDate":"2021-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80334494","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 : 2021-03-12DOI: 10.1109/ATiGB50996.2021.9423429
Chi-Phi Do, Quang-Huy Le, Duy-Phuoc Pham, Dinh-Kha Le
The hot air recirculating drying method has the advantage of handling large output. Moreover, in the drying chamber with a large volume of drying material, factors affecting the drying process such as air flow rate, temperature, drying agent humidity, and surface area of the drying product are always concerned. Because this is the deciding factor for the drying time as well as the quality of the drying product. However, the drying time is closely related to the energy consumed in the drying system. In particular, the temperature and humidity of the environment have a great influence on energy consumption. This paper has built a general mathematical model, using ARIMA algorithm to predict energy consumption for the industrial drying system and applying the mathematical model to actually survey the drying system with a capacity of 1000 kg /batch, 03 drying chambers are designed with a size of 3000mm. x 3000mm x 2500 (length x width x height), total drying tray area 192 m2. Energy sources use thermal oil furnace technology or resistive furnaces. The collected temperature and humidity data is based on the IoT platform. The simulation results forecast the temperature accurately to 99.09%, the humidity is accurate to 98.24% and the energy consumption reaches 96.31%.
{"title":"Forecast of Energy Consumption of Drying System According to The Environmental Temperature and Humidity on IoT by Arima Algorithm","authors":"Chi-Phi Do, Quang-Huy Le, Duy-Phuoc Pham, Dinh-Kha Le","doi":"10.1109/ATiGB50996.2021.9423429","DOIUrl":"https://doi.org/10.1109/ATiGB50996.2021.9423429","url":null,"abstract":"The hot air recirculating drying method has the advantage of handling large output. Moreover, in the drying chamber with a large volume of drying material, factors affecting the drying process such as air flow rate, temperature, drying agent humidity, and surface area of the drying product are always concerned. Because this is the deciding factor for the drying time as well as the quality of the drying product. However, the drying time is closely related to the energy consumed in the drying system. In particular, the temperature and humidity of the environment have a great influence on energy consumption. This paper has built a general mathematical model, using ARIMA algorithm to predict energy consumption for the industrial drying system and applying the mathematical model to actually survey the drying system with a capacity of 1000 kg /batch, 03 drying chambers are designed with a size of 3000mm. x 3000mm x 2500 (length x width x height), total drying tray area 192 m2. Energy sources use thermal oil furnace technology or resistive furnaces. The collected temperature and humidity data is based on the IoT platform. The simulation results forecast the temperature accurately to 99.09%, the humidity is accurate to 98.24% and the energy consumption reaches 96.31%.","PeriodicalId":6690,"journal":{"name":"2020 Applying New Technology in Green Buildings (ATiGB)","volume":"38 1","pages":"60-64"},"PeriodicalIF":0.0,"publicationDate":"2021-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86798089","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 : 2021-03-12DOI: 10.1109/ATiGB50996.2021.9423196
Son Thanh Nguyen, Ngoc Anh Ho-Tran
This study presents detailed energy efficiency analysis and comparison of two types of electric cooktops, i.e., infrared and induction cooktops, under Vietnamese conditions. The cooktops investigated are of nearly similar technical specifications, e.g., capacity, voltage, and the maximum temperature of the glass, and the manufacturing information. Experiments are conducted with both pot and pan in order to evaluate the heat-up time, self-cooling time, overshoot, cooking efficiency, and energy cost of each type of cooktop. Results show that the induction cooktop is considerably energy-efficient than the infrared one. In detail, the maximum cooking efficiency for the former is 98.8% (in the case of using a pan with 0.5 kg water) meanwhile that for the latter is only 63.81% (in the case of using a pot with 5 kg water). Moreover, the heat-up time of the infrared cooktop is significantly greater; for instance, its maximum heat-up time is 60% higher than that of the induction one. Additionally, the estimated annual costs for the induction cooktop is found to be 14.04% lower compared to the infrared one.
{"title":"An Investigation on Energy Efficiency of Infrared and Induction Cooktops","authors":"Son Thanh Nguyen, Ngoc Anh Ho-Tran","doi":"10.1109/ATiGB50996.2021.9423196","DOIUrl":"https://doi.org/10.1109/ATiGB50996.2021.9423196","url":null,"abstract":"This study presents detailed energy efficiency analysis and comparison of two types of electric cooktops, i.e., infrared and induction cooktops, under Vietnamese conditions. The cooktops investigated are of nearly similar technical specifications, e.g., capacity, voltage, and the maximum temperature of the glass, and the manufacturing information. Experiments are conducted with both pot and pan in order to evaluate the heat-up time, self-cooling time, overshoot, cooking efficiency, and energy cost of each type of cooktop. Results show that the induction cooktop is considerably energy-efficient than the infrared one. In detail, the maximum cooking efficiency for the former is 98.8% (in the case of using a pan with 0.5 kg water) meanwhile that for the latter is only 63.81% (in the case of using a pot with 5 kg water). Moreover, the heat-up time of the infrared cooktop is significantly greater; for instance, its maximum heat-up time is 60% higher than that of the induction one. Additionally, the estimated annual costs for the induction cooktop is found to be 14.04% lower compared to the infrared one.","PeriodicalId":6690,"journal":{"name":"2020 Applying New Technology in Green Buildings (ATiGB)","volume":"112 1","pages":"115-119"},"PeriodicalIF":0.0,"publicationDate":"2021-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80172841","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 : 2021-03-12DOI: 10.1109/ATiGB50996.2021.9423191
Thinh Do Duy, Ye Xuan, Trang Nguyen Thi Thuy, Thi Le Tung Diem
The recent introduction of pseudo-public space to Vietnam has significantly contributed to increasing the area of public spaces in urban area. Not only is coffee-shop space where people drink coffee and gossip as before, but now it is also a place for entertainment, relaxation and social interactions. Similarly to studies on such privately owned public spaces in foreign countries as pocket park, this research aims at understanding the usage nature of coffee-shop space in Vietnam’s cities, particularly Vinh Long city. The research also discovers the distribution of coffeeshop space network in urban configuration, types of coffee-shop space and their spatial properties on basis of data collected by observation, investigation, survey and Open Street Map. Furthermore, the research uses analytical tools deriving from space syntax theory. Findings will be detailed in this paper.
越南最近引入的伪公共空间极大地增加了城市公共空间的面积。咖啡馆不仅像以前一样是人们喝咖啡和闲聊的地方，现在它也是一个娱乐、放松和社交的地方。与国外对口袋公园等私人拥有的公共空间的研究类似，本研究旨在了解越南城市，特别是永隆市咖啡店空间的使用性质。通过观察、调查、调查和Open Street Map收集的数据，发现咖啡店空间网络在城市形态中的分布，咖啡店空间的类型及其空间属性。此外，本研究还运用了空间句法理论衍生的分析工具。研究结果将在本文中详细介绍。
{"title":"A study on the coffeeshop space in Vinh Long City, Vietnam","authors":"Thinh Do Duy, Ye Xuan, Trang Nguyen Thi Thuy, Thi Le Tung Diem","doi":"10.1109/ATiGB50996.2021.9423191","DOIUrl":"https://doi.org/10.1109/ATiGB50996.2021.9423191","url":null,"abstract":"The recent introduction of pseudo-public space to Vietnam has significantly contributed to increasing the area of public spaces in urban area. Not only is coffee-shop space where people drink coffee and gossip as before, but now it is also a place for entertainment, relaxation and social interactions. Similarly to studies on such privately owned public spaces in foreign countries as pocket park, this research aims at understanding the usage nature of coffee-shop space in Vietnam’s cities, particularly Vinh Long city. The research also discovers the distribution of coffeeshop space network in urban configuration, types of coffee-shop space and their spatial properties on basis of data collected by observation, investigation, survey and Open Street Map. Furthermore, the research uses analytical tools deriving from space syntax theory. Findings will be detailed in this paper.","PeriodicalId":6690,"journal":{"name":"2020 Applying New Technology in Green Buildings (ATiGB)","volume":"47 1","pages":"18-24"},"PeriodicalIF":0.0,"publicationDate":"2021-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76869820","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 : 2021-03-12DOI: 10.1109/ATiGB50996.2021.9423319
Nguyen Do Hoang Khoi, Cuong Pham Van, Hoang Vu Tran, C. Truong
In Reinforcement Learning, the reward is one of the main components to optimize the strategy. While other approaches are based on a simple scalar reward to get an optimal policy, we propose a model learning the designated reward in numerous conditions. Our method, which we call multi-objective exploration for proximal policy optimization (MOE-PPO), alleviates the dependence on the reward design by executing the Preferent Surrogate Objective (PSO). We also make full use of Curiosity Driven Exploration to increase exploration ability. Our experiments test MOE-PPO in the Super Mario Bros environment designed by OpenAIGym with three criteria to illustrate our approach's effectiveness. The result shows that MOE-PPO outperforms other on-policy algorithms under many conditions.
{"title":"Multi-Objective Exploration for Proximal Policy Optimization","authors":"Nguyen Do Hoang Khoi, Cuong Pham Van, Hoang Vu Tran, C. Truong","doi":"10.1109/ATiGB50996.2021.9423319","DOIUrl":"https://doi.org/10.1109/ATiGB50996.2021.9423319","url":null,"abstract":"In Reinforcement Learning, the reward is one of the main components to optimize the strategy. While other approaches are based on a simple scalar reward to get an optimal policy, we propose a model learning the designated reward in numerous conditions. Our method, which we call multi-objective exploration for proximal policy optimization (MOE-PPO), alleviates the dependence on the reward design by executing the Preferent Surrogate Objective (PSO). We also make full use of Curiosity Driven Exploration to increase exploration ability. Our experiments test MOE-PPO in the Super Mario Bros environment designed by OpenAIGym with three criteria to illustrate our approach's effectiveness. The result shows that MOE-PPO outperforms other on-policy algorithms under many conditions.","PeriodicalId":6690,"journal":{"name":"2020 Applying New Technology in Green Buildings (ATiGB)","volume":"14 1","pages":"105-109"},"PeriodicalIF":0.0,"publicationDate":"2021-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78564987","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 : 2021-03-12DOI: 10.1109/ATiGB50996.2021.9423017
Han Trong Thanh, P. H. Yen, Trinh Bich Ngoc
The article focuses on the research of image classification algorithms, namely the images indicate pathology of pneumonia caused by bacteria and viruses. The proposed method is based on using the VGG16, VGG19, DenseNet169 networks to extract data characteristics and train the model classification. The X-rays are classified including normal people, patients with viral pneumonia, and bacterial pneumonia. The provided source was medical data on chest X- ray images of patients who were manually classified by specialists. However, the accuracy of the classification is highly dependent on the number of images, the resolution of the images, and whether the X-ray image is correctly classified. In this study, the algorithms give relatively positive classification results with an accuracy of approximately 85%.
{"title":"Pneumonia Classification in X-ray Images Using Artificial Intelligence Technology","authors":"Han Trong Thanh, P. H. Yen, Trinh Bich Ngoc","doi":"10.1109/ATiGB50996.2021.9423017","DOIUrl":"https://doi.org/10.1109/ATiGB50996.2021.9423017","url":null,"abstract":"The article focuses on the research of image classification algorithms, namely the images indicate pathology of pneumonia caused by bacteria and viruses. The proposed method is based on using the VGG16, VGG19, DenseNet169 networks to extract data characteristics and train the model classification. The X-rays are classified including normal people, patients with viral pneumonia, and bacterial pneumonia. The provided source was medical data on chest X- ray images of patients who were manually classified by specialists. However, the accuracy of the classification is highly dependent on the number of images, the resolution of the images, and whether the X-ray image is correctly classified. In this study, the algorithms give relatively positive classification results with an accuracy of approximately 85%.","PeriodicalId":6690,"journal":{"name":"2020 Applying New Technology in Green Buildings (ATiGB)","volume":"88 1","pages":"25-30"},"PeriodicalIF":0.0,"publicationDate":"2021-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76670929","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 : 2021-03-12DOI: 10.1109/ATiGB50996.2021.9423324
Tran Thanh Son, Phan Qui Tra
Melaleuca oil is one of the most powerful immune system stimulants, which is capable of quickly eliminating most viral, bacterial, and fungal infections. Melaleuca oil in Vietnam is only produced on a small-scale using outdated technology. In this study, the materials were firstly processed with the steam explosion method before being put into the distillation pot. This pretreatment process helps to break down the structure of the materials and extract the essential oil efficiently. In the scope of this study, many different experiments had been done such as changing of heating time, pressure, and the number of steam explosions. The main purpose of the study is to find parameters suitable for oil dissociation regarding oil color and quantity. Research results show that the essential oil yield depends on explosion pressure, explosion time, and the number of explosions. In the scope of this study, it shows that for every 3 kg of raw melaleuca, about 10.2 ml of essential oil is extracted, which is almost twice as high as traditional methods without steam explosion. This process also saves 60% more time than the traditional method. These preliminary results demonstrate that pretreatment is an important part of improving the efficiency of essential oil extraction both in terms of essential oil yield and energy consumption.
{"title":"Research on melaleuca oil production by steam explosion method","authors":"Tran Thanh Son, Phan Qui Tra","doi":"10.1109/ATiGB50996.2021.9423324","DOIUrl":"https://doi.org/10.1109/ATiGB50996.2021.9423324","url":null,"abstract":"Melaleuca oil is one of the most powerful immune system stimulants, which is capable of quickly eliminating most viral, bacterial, and fungal infections. Melaleuca oil in Vietnam is only produced on a small-scale using outdated technology. In this study, the materials were firstly processed with the steam explosion method before being put into the distillation pot. This pretreatment process helps to break down the structure of the materials and extract the essential oil efficiently. In the scope of this study, many different experiments had been done such as changing of heating time, pressure, and the number of steam explosions. The main purpose of the study is to find parameters suitable for oil dissociation regarding oil color and quantity. Research results show that the essential oil yield depends on explosion pressure, explosion time, and the number of explosions. In the scope of this study, it shows that for every 3 kg of raw melaleuca, about 10.2 ml of essential oil is extracted, which is almost twice as high as traditional methods without steam explosion. This process also saves 60% more time than the traditional method. These preliminary results demonstrate that pretreatment is an important part of improving the efficiency of essential oil extraction both in terms of essential oil yield and energy consumption.","PeriodicalId":6690,"journal":{"name":"2020 Applying New Technology in Green Buildings (ATiGB)","volume":"18 1","pages":"100-104"},"PeriodicalIF":0.0,"publicationDate":"2021-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82927917","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 : 2021-03-12DOI: 10.1109/ATiGB50996.2021.9423027
H. Nguyen, V. N. Sereda, Duy Nam Pham, C. C. Vo
This paper presents the experimental results in applying air drying technology developed by the Vietnam- Russia Tropical Centre for protecting EC-155 helicopter against the adverse effects of high humidity in the tropical climate. The essence of this technology is using an ITM- OY7 air dryer, that is placed outside the helicopter, to force dry air into helicopter compartments through an air duct. The ITM- OY7 was fabricated by the Vietnam-Russia Tropical Centre. The test was conducted for 14 months (from April 2019 to June 2020) at an Air force unit in Hanoi. The results showed that air drying technology application helped reduce and maintain relative humidity in the EC-155 helicopter cabin at an average of 60%, while average humidity in the shelter ranges from 70% to 92%. These results are the basis for expanding application of the air drying technology in other Air and Air Defense Force units in protecting helicopters from harmful effects of the tropical climate.
{"title":"Application of air drying technology for helicopter protection in tropical conditions of Vietnam","authors":"H. Nguyen, V. N. Sereda, Duy Nam Pham, C. C. Vo","doi":"10.1109/ATiGB50996.2021.9423027","DOIUrl":"https://doi.org/10.1109/ATiGB50996.2021.9423027","url":null,"abstract":"This paper presents the experimental results in applying air drying technology developed by the Vietnam- Russia Tropical Centre for protecting EC-155 helicopter against the adverse effects of high humidity in the tropical climate. The essence of this technology is using an ITM- OY7 air dryer, that is placed outside the helicopter, to force dry air into helicopter compartments through an air duct. The ITM- OY7 was fabricated by the Vietnam-Russia Tropical Centre. The test was conducted for 14 months (from April 2019 to June 2020) at an Air force unit in Hanoi. The results showed that air drying technology application helped reduce and maintain relative humidity in the EC-155 helicopter cabin at an average of 60%, while average humidity in the shelter ranges from 70% to 92%. These results are the basis for expanding application of the air drying technology in other Air and Air Defense Force units in protecting helicopters from harmful effects of the tropical climate.","PeriodicalId":6690,"journal":{"name":"2020 Applying New Technology in Green Buildings (ATiGB)","volume":"14 1","pages":"70-74"},"PeriodicalIF":0.0,"publicationDate":"2021-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83758204","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 : 2021-03-12DOI: 10.1109/ATiGB50996.2021.9423307
Tuan D. Pham
Semantic segmentation is an important task in self-driving cars. The aims of semantic segmentation are to recognize pre-defined objects and its pixel-by-pixel location. The most popular method in semantic segmentation is Deep learning which has considerably improved semantic image segmentation. This work does an overview for semantic segmentation using Deep learning. This works also implement comparisons in term of precision, mean IOU and processing time. Three popular algorithms are PSPNet, FCN and SegNet that are examined carefully. In detail, the aim of this work points out a trade-off between processing time and mean IOU, and also between processing time and precision. Moreover, this paper concentrates on road segmentation for embedded devices, so processing time is significantly important. This work also figures out which method is suitable for embedded devices on road segmentation.
{"title":"Semantic Road Segmentation using Deep Learning","authors":"Tuan D. Pham","doi":"10.1109/ATiGB50996.2021.9423307","DOIUrl":"https://doi.org/10.1109/ATiGB50996.2021.9423307","url":null,"abstract":"Semantic segmentation is an important task in self-driving cars. The aims of semantic segmentation are to recognize pre-defined objects and its pixel-by-pixel location. The most popular method in semantic segmentation is Deep learning which has considerably improved semantic image segmentation. This work does an overview for semantic segmentation using Deep learning. This works also implement comparisons in term of precision, mean IOU and processing time. Three popular algorithms are PSPNet, FCN and SegNet that are examined carefully. In detail, the aim of this work points out a trade-off between processing time and mean IOU, and also between processing time and precision. Moreover, this paper concentrates on road segmentation for embedded devices, so processing time is significantly important. This work also figures out which method is suitable for embedded devices on road segmentation.","PeriodicalId":6690,"journal":{"name":"2020 Applying New Technology in Green Buildings (ATiGB)","volume":"30 1","pages":"45-48"},"PeriodicalIF":0.0,"publicationDate":"2021-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86053728","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 : 2021-03-12DOI: 10.1109/ATiGB50996.2021.9423111
Thanh Bao Doan, Chi Phi Do
When a power transformer is connected to the grid, the inrush current increases substantially with a high value of harmonic components. At that time, the amount of flux in the core increases causing the magnetic circuit to saturate with a duration up to many grid cycles. This may cause malfunction of protection relays or interfere the operating condition of nearby electrical instruments. Therefore, it is important to analyze the phenomenon of the inrush current and the magnetic field inside the transformer. This paper has derived a simulation model for three power transformers with capacity of 250kVA, 1500kVA and 2200kVA by using Ansys Maxwell 3D software when connecting the transformers to power grid under no load condition. The winding voltages, the inrush currents, and the flux density inside the core of each transformers have been analyzed. Furthermore, with the help of the finite element method, the overvoltage and/or overheating phenomenon of transformers can also be studied.
{"title":"Calculation of the Magnetic Field and Inrush Current in a Three-phase Transformer","authors":"Thanh Bao Doan, Chi Phi Do","doi":"10.1109/ATiGB50996.2021.9423111","DOIUrl":"https://doi.org/10.1109/ATiGB50996.2021.9423111","url":null,"abstract":"When a power transformer is connected to the grid, the inrush current increases substantially with a high value of harmonic components. At that time, the amount of flux in the core increases causing the magnetic circuit to saturate with a duration up to many grid cycles. This may cause malfunction of protection relays or interfere the operating condition of nearby electrical instruments. Therefore, it is important to analyze the phenomenon of the inrush current and the magnetic field inside the transformer. This paper has derived a simulation model for three power transformers with capacity of 250kVA, 1500kVA and 2200kVA by using Ansys Maxwell 3D software when connecting the transformers to power grid under no load condition. The winding voltages, the inrush currents, and the flux density inside the core of each transformers have been analyzed. Furthermore, with the help of the finite element method, the overvoltage and/or overheating phenomenon of transformers can also be studied.","PeriodicalId":6690,"journal":{"name":"2020 Applying New Technology in Green Buildings (ATiGB)","volume":"21 1","pages":"94-99"},"PeriodicalIF":0.0,"publicationDate":"2021-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86689405","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：