Pub Date : 2022-08-04DOI: 10.1109/RI2C56397.2022.9910276
Farinaz Nemati, R. Gavagsaz-Ghoachani, M. Phattanasak
With the growth of population and industrialization of societies, the need for energy has increased. Due to the limited resources of non-renewable energy and the creation of various types of pollution, they should be replaced. Nowadays, renewable energy systems have been considered due to their compatibility with the environment. Polymer electrolyte fuel cells (PEMFCs) are an example of the use of renewable energy systems. PEMFCs, along with all their advantages, face the challenge of durability. The Snowball effect is a phenomenon that is followed by continuous reactions that reduce the durability of PEMFCs. The cause of this effect is the existence of various heterogeneities in fuel cells, which are controlled by water management through the current management strategy. On the other hand, efficient content training is valuable and necessary because it leads to a better understanding and, ultimately, progress in the field of fuel cells. With the spread of the Coronavirus and the virtualization of education, the need for change and diversity in education became more and more felt. Also, with the advancement of technology, it is better to use all available facilities to improve education. In this article, the effect of snowball and its solution has been easily taught by using new educational methods and visual abstracts.
{"title":"Teaching the snowball effect on polymer electrolyte fuel cells through visual abstract","authors":"Farinaz Nemati, R. Gavagsaz-Ghoachani, M. Phattanasak","doi":"10.1109/RI2C56397.2022.9910276","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910276","url":null,"abstract":"With the growth of population and industrialization of societies, the need for energy has increased. Due to the limited resources of non-renewable energy and the creation of various types of pollution, they should be replaced. Nowadays, renewable energy systems have been considered due to their compatibility with the environment. Polymer electrolyte fuel cells (PEMFCs) are an example of the use of renewable energy systems. PEMFCs, along with all their advantages, face the challenge of durability. The Snowball effect is a phenomenon that is followed by continuous reactions that reduce the durability of PEMFCs. The cause of this effect is the existence of various heterogeneities in fuel cells, which are controlled by water management through the current management strategy. On the other hand, efficient content training is valuable and necessary because it leads to a better understanding and, ultimately, progress in the field of fuel cells. With the spread of the Coronavirus and the virtualization of education, the need for change and diversity in education became more and more felt. Also, with the advancement of technology, it is better to use all available facilities to improve education. In this article, the effect of snowball and its solution has been easily taught by using new educational methods and visual abstracts.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123490937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-04DOI: 10.1109/RI2C56397.2022.9910286
Tanapeak Pexyean, K. Saraubon, P. Nilsook
The objective of this research is to Present the use of Digital Twin. Internet of Things and Intelligence Technology to Intelligently Develop The Energy Management Potential of Campuses By using Digital Twin to manage energy consumption, it enables the creation of work and life on campus, whether it is personal. Teachers and students, including those with disabilities, have a better quality of life. Living on campus is more comfortable Collect energy consumption data, organizations to manage power management systems, reduce energy consumption, simplify management in all departments, and reduce campus costs. It can transparently monitor energy consumption and use educational equipment on campus, especially cost and expenditure management, and sustainable energy consumption, as well as management. Control usage data, energy consumption results, and budget allocations related to educational institutions can create reliability in managing information about electrical energy and energy competency assessment results, and can be recorded and controlled in Digital Twin that can be as if it were with a control center. IoT and Cloud Computing are also integrated with AI systems embedded in state-of-the-art equipment for use in environmental management and intelligent energy management. As well as creating new energy models and management that can resolve future emergencies by controlling virtual energy within the organization from outside anytime, anywhere.
{"title":"IoT, AI and Digital Twin For Smart Campus","authors":"Tanapeak Pexyean, K. Saraubon, P. Nilsook","doi":"10.1109/RI2C56397.2022.9910286","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910286","url":null,"abstract":"The objective of this research is to Present the use of Digital Twin. Internet of Things and Intelligence Technology to Intelligently Develop The Energy Management Potential of Campuses By using Digital Twin to manage energy consumption, it enables the creation of work and life on campus, whether it is personal. Teachers and students, including those with disabilities, have a better quality of life. Living on campus is more comfortable Collect energy consumption data, organizations to manage power management systems, reduce energy consumption, simplify management in all departments, and reduce campus costs. It can transparently monitor energy consumption and use educational equipment on campus, especially cost and expenditure management, and sustainable energy consumption, as well as management. Control usage data, energy consumption results, and budget allocations related to educational institutions can create reliability in managing information about electrical energy and energy competency assessment results, and can be recorded and controlled in Digital Twin that can be as if it were with a control center. IoT and Cloud Computing are also integrated with AI systems embedded in state-of-the-art equipment for use in environmental management and intelligent energy management. As well as creating new energy models and management that can resolve future emergencies by controlling virtual energy within the organization from outside anytime, anywhere.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128457077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-04DOI: 10.1109/RI2C56397.2022.9910313
Saranlita Chotirat, P. Meesad, H. Unger
The potential of automated question generation is role play in the multi-fields and multi-applications such as question and answering systems, examination systems, and information retrieval. Before learning the question generated, one should understand how to classify questions. This research aims to generate possible questions considering the possible question categories from question classification based on Natural Language Processing. In this research, we compared the results on Logistic Regression, Support Vector Machine, and Multinomial Naï ve Bayes, which were traditional classification models. The deep learning techniques were Convolutional Neural Networks, Bidirectional Long Short-Term Memory, combined CNN and BiLSTM models, and BERT models. The experimental results show that the preprocessing phase using Natural Language Processing could enhance question classification. The classification of the sentence to question classification attained an average micro $F_{1} -$ score of 91.40% when applied BERT model by pre-trained WangchanBERTa on simple sentences. In contrast, the satisfying score with an average micro $F_{1} -$ score of 82.07% (from 80.37% on original input) when applied to add all POS tags unigram + bigram TF-IDF by using the SVM model. The experimental results when the CNN model with GloVe on adding focusing POS tags is a satisfactory score with an average micro $F_{1} -$ score of 79.79%.
{"title":"Question Classification from Thai Sentences by Considering Word Context to Question Generation","authors":"Saranlita Chotirat, P. Meesad, H. Unger","doi":"10.1109/RI2C56397.2022.9910313","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910313","url":null,"abstract":"The potential of automated question generation is role play in the multi-fields and multi-applications such as question and answering systems, examination systems, and information retrieval. Before learning the question generated, one should understand how to classify questions. This research aims to generate possible questions considering the possible question categories from question classification based on Natural Language Processing. In this research, we compared the results on Logistic Regression, Support Vector Machine, and Multinomial Naï ve Bayes, which were traditional classification models. The deep learning techniques were Convolutional Neural Networks, Bidirectional Long Short-Term Memory, combined CNN and BiLSTM models, and BERT models. The experimental results show that the preprocessing phase using Natural Language Processing could enhance question classification. The classification of the sentence to question classification attained an average micro $F_{1} -$ score of 91.40% when applied BERT model by pre-trained WangchanBERTa on simple sentences. In contrast, the satisfying score with an average micro $F_{1} -$ score of 82.07% (from 80.37% on original input) when applied to add all POS tags unigram + bigram TF-IDF by using the SVM model. The experimental results when the CNN model with GloVe on adding focusing POS tags is a satisfactory score with an average micro $F_{1} -$ score of 79.79%.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127273323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-04DOI: 10.1109/RI2C56397.2022.9910296
Natdanai Phumirin, Kitiphon Sukpreecha, K. Phaebua, A. Boonpoonga, T. Lertwiriyaprapa
This paper presents low-cost automatic antenna polarization measurement system. The portable vector network analyzer (VNA) namely nanoVNA is employed instead of an expensive high-precision laboratory VNA. NanoVNA supports frequency range of 50 kHz to 1.5 GHz that provide a good capability to measure an electrical characteristics of antennas, filters, duplexers, amplifiers and etc. The wide-band Vivaldi antenna is employed as the measurement electric field probe which is supported by the rotating shaft and drive by stepping motor. MALAB GUI post-processing is implemented to automatically control the stepping motor and NanoVNA. The orthogonal components of probe amplitudes and phases of antenna under test (AUT) are measured by NanoVNA. The axial-ratio value of AUT polarization can be obtained by MALAB post processing. Therefore, the proposed low-cost automatic antenna polarization measurement system is well suited to understand antenna polarization with hands-on experience.
{"title":"Low-cost Automatic Antenna Polarization Measurement system","authors":"Natdanai Phumirin, Kitiphon Sukpreecha, K. Phaebua, A. Boonpoonga, T. Lertwiriyaprapa","doi":"10.1109/RI2C56397.2022.9910296","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910296","url":null,"abstract":"This paper presents low-cost automatic antenna polarization measurement system. The portable vector network analyzer (VNA) namely nanoVNA is employed instead of an expensive high-precision laboratory VNA. NanoVNA supports frequency range of 50 kHz to 1.5 GHz that provide a good capability to measure an electrical characteristics of antennas, filters, duplexers, amplifiers and etc. The wide-band Vivaldi antenna is employed as the measurement electric field probe which is supported by the rotating shaft and drive by stepping motor. MALAB GUI post-processing is implemented to automatically control the stepping motor and NanoVNA. The orthogonal components of probe amplitudes and phases of antenna under test (AUT) are measured by NanoVNA. The axial-ratio value of AUT polarization can be obtained by MALAB post processing. Therefore, the proposed low-cost automatic antenna polarization measurement system is well suited to understand antenna polarization with hands-on experience.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125857054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-04DOI: 10.1109/RI2C56397.2022.9910264
C. Phromsuthirak, Orawan Chunhapran, Maposee Hama, P. Boonrawd, Siranee Nuchitprasitchai
COVID-19 Pandemic affects daily life and the global economy. The COVID-19 virus can be spread by small liquid particles, which can be filtered using a face mask. Wearing masks in public areas is an excellent approach to preventing illness. As a result, mask detection is necessary to stop the spread of the disease before a person enters the facility. Regarding Single Shot Multibox Detector-MobileNetV2 (SSD-MobileNetV2) was used in this research to build tools to detect and monitor unmasked people in the facility or working rooms that consist of many people. In this paper, we showed the experimental performance of SSDMobileNetv2 based on an application that runs on an edge device to detect unmasked people in the room and compromise with very high accuracy of 97% in rooms smaller than 16 square meters, which is sufficient to detect the wearing of masks in public places or various locations.
{"title":"A Real-Time Unmasked Detection Using SSD-MobileNetV2 on Edge Device for the COVID-19 Pandemic","authors":"C. Phromsuthirak, Orawan Chunhapran, Maposee Hama, P. Boonrawd, Siranee Nuchitprasitchai","doi":"10.1109/RI2C56397.2022.9910264","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910264","url":null,"abstract":"COVID-19 Pandemic affects daily life and the global economy. The COVID-19 virus can be spread by small liquid particles, which can be filtered using a face mask. Wearing masks in public areas is an excellent approach to preventing illness. As a result, mask detection is necessary to stop the spread of the disease before a person enters the facility. Regarding Single Shot Multibox Detector-MobileNetV2 (SSD-MobileNetV2) was used in this research to build tools to detect and monitor unmasked people in the facility or working rooms that consist of many people. In this paper, we showed the experimental performance of SSDMobileNetv2 based on an application that runs on an edge device to detect unmasked people in the room and compromise with very high accuracy of 97% in rooms smaller than 16 square meters, which is sufficient to detect the wearing of masks in public places or various locations.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117133355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-04DOI: 10.1109/RI2C56397.2022.9910308
K. Phaebua, T. Lertwiriyaprapa, D. Torrungrueng, A. Boonpoonga
A truncation error study in the cylindrical near-field (NF) measurement technique is proposed. The maximum angle span of the far-field (FF) radiation pattern from the bore-sight of the antenna under test (AUT) is studied. The truncated NF scan length will be varied. The cylindrical wave expansion is employed to transform the near-field to far-field (NF-FF), where the two-dimensional (2D) numerical integration is employed to calculate associated double integration in the cylindrical wave expansion. The referenced far-field radiation pattern of AUT is simulated by three-dimensional (3D) electromagnetic (EM) software. It is found that the maximum angle span of the FF radiation pattern is dependent on truncated NF scan length and AUT to probe distance. The simulated radiation patterns and the radiation patterns from numerical NF-FF transformation in the valid angle span are in good agreement. Therefore, the greater the truncated NF scans length, the higher the valid angle span of the FF radiation pattern. The actual valid angle span is a bit wider than the estimated maximum angle span, under the condition of the truncated NF scan length is two times larger than the antenna size.
{"title":"Truncation Error Study in Cylindrical Near-field Measurement Technique","authors":"K. Phaebua, T. Lertwiriyaprapa, D. Torrungrueng, A. Boonpoonga","doi":"10.1109/RI2C56397.2022.9910308","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910308","url":null,"abstract":"A truncation error study in the cylindrical near-field (NF) measurement technique is proposed. The maximum angle span of the far-field (FF) radiation pattern from the bore-sight of the antenna under test (AUT) is studied. The truncated NF scan length will be varied. The cylindrical wave expansion is employed to transform the near-field to far-field (NF-FF), where the two-dimensional (2D) numerical integration is employed to calculate associated double integration in the cylindrical wave expansion. The referenced far-field radiation pattern of AUT is simulated by three-dimensional (3D) electromagnetic (EM) software. It is found that the maximum angle span of the FF radiation pattern is dependent on truncated NF scan length and AUT to probe distance. The simulated radiation patterns and the radiation patterns from numerical NF-FF transformation in the valid angle span are in good agreement. Therefore, the greater the truncated NF scans length, the higher the valid angle span of the FF radiation pattern. The actual valid angle span is a bit wider than the estimated maximum angle span, under the condition of the truncated NF scan length is two times larger than the antenna size.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131988109","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}
The efficiency of photovoltaic modules decreases over time, and this decrease can be accelerated by environmental factors such as high temperatures. It is important to detect defective photovoltaic modules as soon as possible to prevent further degradation and loss of power output. Aerial thermographic inspections are a non-invasive method of detecting defective photovoltaic modules. This method uses thermal imaging to detect differences in the temperature of photovoltaic modules. By detecting defective photovoltaic modules early, the owner can save money on replacement costs and loss of power output.
{"title":"CNN based Automatic Detection of Defective Photovoltaic Modules using Aerial Imagery","authors":"Pornthep Sarakon, Benya Lertpornsuksawat, Temsiri Sapsaman, Titan Janthori","doi":"10.1109/RI2C56397.2022.9910319","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910319","url":null,"abstract":"The efficiency of photovoltaic modules decreases over time, and this decrease can be accelerated by environmental factors such as high temperatures. It is important to detect defective photovoltaic modules as soon as possible to prevent further degradation and loss of power output. Aerial thermographic inspections are a non-invasive method of detecting defective photovoltaic modules. This method uses thermal imaging to detect differences in the temperature of photovoltaic modules. By detecting defective photovoltaic modules early, the owner can save money on replacement costs and loss of power output.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114200526","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-04DOI: 10.1109/RI2C56397.2022.9910284
Sukanya Chudpooti, Patchadaporn Sangpet, N. Chudpooti, N. Sathitanon, N. Somjit, P. Akkaraekthalin
This paper presents an improvement gain of a dual-polarized microstrip patch antenna by using the partially reflective surface (PRS). The PRS is designed from a $10 times 10$ array patches structure, which is patterned on a 0.8-mm FR-4 substrate. A-dual-port fed by two SMA connectors, which is selected to use as the source of an experiment. The square metallic patch is used to design the PRS layer. The dimension of the square patch is 5 mm $times 5$ mm. The length of the square patch is varied from 3.0mm to 4.5 mm by step of 0.5 mm to investigate the reflection coefficients, e.g., magnitude response and phase response. Based on the simulated results, a 4.5-mm square patch provides the highest reflection coefficient of 0.53. To prove the design concept, the size of a square patch of 4.5 mm is selected to fabricate and measure the radiation pattern. At an operating frequency of 3.5 GHz, the maximum gain at the zero degrees is increased from 1.2 dBi to 4.96 dBi when compared without and with PRS.
提出了利用部分反射面提高双极化微带贴片天线增益的方法。PRS采用$10 × 10$阵列贴片结构设计，贴片结构设计在0.8 mm FR-4基板上。a -双端口由两个SMA连接器馈电，选择作为实验源。采用方形金属贴片设计PRS层。方形贴片的尺寸为5 mm × 5 mm。方形贴片的长度从3.0mm到4.5 mm，以0.5 mm的速度变化，以研究反射系数，如幅度响应和相位响应。仿真结果表明，4.5 mm方形贴片的反射系数最高，为0.53。为了验证设计理念，选择4.5 mm大小的方形贴片制作和测量辐射方向图。在工作频率为3.5 GHz时，与无PRS和有PRS相比，零度处的最大增益从1.2 dBi增加到4.96 dBi。
{"title":"A Square Patch Partially Reflective Surface for Improving the Antenna Gain Characteristic of Low-Cost Dual Polarized Microstrip Antenna","authors":"Sukanya Chudpooti, Patchadaporn Sangpet, N. Chudpooti, N. Sathitanon, N. Somjit, P. Akkaraekthalin","doi":"10.1109/RI2C56397.2022.9910284","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910284","url":null,"abstract":"This paper presents an improvement gain of a dual-polarized microstrip patch antenna by using the partially reflective surface (PRS). The PRS is designed from a $10 times 10$ array patches structure, which is patterned on a 0.8-mm FR-4 substrate. A-dual-port fed by two SMA connectors, which is selected to use as the source of an experiment. The square metallic patch is used to design the PRS layer. The dimension of the square patch is 5 mm $times 5$ mm. The length of the square patch is varied from 3.0mm to 4.5 mm by step of 0.5 mm to investigate the reflection coefficients, e.g., magnitude response and phase response. Based on the simulated results, a 4.5-mm square patch provides the highest reflection coefficient of 0.53. To prove the design concept, the size of a square patch of 4.5 mm is selected to fabricate and measure the radiation pattern. At an operating frequency of 3.5 GHz, the maximum gain at the zero degrees is increased from 1.2 dBi to 4.96 dBi when compared without and with PRS.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":"20 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124916443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-04DOI: 10.1109/RI2C56397.2022.9910290
Junjiraporn Thongprasit, Pallop Piriyasurawong
The objective of this research is to develop a metaverse framework for engineering competency development. This research is divided into two phases. In the first phase, it will study and synthesize the elements of a metaverse framework for engineering competency development. The researcher has studied, analyzed, and synthesized data on various issues from related documents and research. It was then developed into a metaverse framework for engineering competency development. We found that a metaverse framework for engineering competency development comprises three components, namely: metaverse, metaverse platform, and engineering competency for future ready. Using the metaverse in engineering will help improve and develop the engineering management system. It is also useful for workforce production or engineering personnel to have appropriate performance and meet the needs of the world workforce market. So, using the metaverse to train engineers who can meet international standards and play a full role in engineering is a good way to get ready for the digital transformation that will happen in the future.
{"title":"Metaverse for Developing Engineering Competency","authors":"Junjiraporn Thongprasit, Pallop Piriyasurawong","doi":"10.1109/RI2C56397.2022.9910290","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910290","url":null,"abstract":"The objective of this research is to develop a metaverse framework for engineering competency development. This research is divided into two phases. In the first phase, it will study and synthesize the elements of a metaverse framework for engineering competency development. The researcher has studied, analyzed, and synthesized data on various issues from related documents and research. It was then developed into a metaverse framework for engineering competency development. We found that a metaverse framework for engineering competency development comprises three components, namely: metaverse, metaverse platform, and engineering competency for future ready. Using the metaverse in engineering will help improve and develop the engineering management system. It is also useful for workforce production or engineering personnel to have appropriate performance and meet the needs of the world workforce market. So, using the metaverse to train engineers who can meet international standards and play a full role in engineering is a good way to get ready for the digital transformation that will happen in the future.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114885540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-04DOI: 10.1109/RI2C56397.2022.9910270
Phuriwat Rasameekunwit, Wutthichai Puangmanee
This paper aims to present the result of a comparative study of Deep Convolutional Neural Networks (CNN) using the AlexNet architecture to use the car image classification of a small dataset. We have proposed the experiment result from a comparative study dropout value using Cuckoo Search (CS), of the optimization techniques for a small data set solving problem of overfitting. The car images for the experiment are different in color, size, and position. As a result, the training time average of $sim 59.16$ minutes, and the model accuracy of 91.41%.
{"title":"A Comparative Study of Deep Convolutional Neural Networks for Car Image Classification","authors":"Phuriwat Rasameekunwit, Wutthichai Puangmanee","doi":"10.1109/RI2C56397.2022.9910270","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910270","url":null,"abstract":"This paper aims to present the result of a comparative study of Deep Convolutional Neural Networks (CNN) using the AlexNet architecture to use the car image classification of a small dataset. We have proposed the experiment result from a comparative study dropout value using Cuckoo Search (CS), of the optimization techniques for a small data set solving problem of overfitting. The car images for the experiment are different in color, size, and position. As a result, the training time average of $sim 59.16$ minutes, and the model accuracy of 91.41%.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114889854","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：