The current global scenario is characterized by epidemics and various types of disasters, severely impacting communities' health, living conditions, and economic stability. Especially during such crises, the requirement for essential necessities becomes critical. Existing solution guidelines involve receiving donated items from public agencies through an offline system to provide assistance to victims. However, this implementation faces several limitations, such as a lack of understanding of people's needs in specific areas, leading to mismatches between assistance and actual requirements. Additionally, donators lack adequate information, resulting in further discrepancies between donated items and the victims' genuine needs. The available geospatial platforms primarily support surveillance and monitoring of epidemic or disaster situations but fail to address the management of needs related to donation and receipt. Through an extensive review of the literature and related research, it was identified that a geospatial platform specifically dedicated to donation management has not yet been developed. To address this gap, this research proposes the creation of a novel geospatial platform using data analysis and visualization methods, complemented by the integration of geofencing technology. By employing such an approach, the geospatial platform will play a pivotal role in enhancing disaster and epidemic assistance. It will facilitate efficient data processing and visualization, overcoming the limitations faced by the current offline system. Emphasis will be placed on improving the management of needs concerning donation and receipt, thereby mitigating mismatches between assistance and actual requirements. Consequently, this platform is expected to significantly enhance the effectiveness and targeting of aid distribution during times of crises.
{"title":"A Geospatial Donation Platform for COVID-19 and Beyond, Leveraging Location – Based Services and Geofencing","authors":"S. Puttinaovarat, Paramate Horkaew","doi":"10.18421/tem123-73","DOIUrl":"https://doi.org/10.18421/tem123-73","url":null,"abstract":"The current global scenario is characterized by epidemics and various types of disasters, severely impacting communities' health, living conditions, and economic stability. Especially during such crises, the requirement for essential necessities becomes critical. Existing solution guidelines involve receiving donated items from public agencies through an offline system to provide assistance to victims. However, this implementation faces several limitations, such as a lack of understanding of people's needs in specific areas, leading to mismatches between assistance and actual requirements. Additionally, donators lack adequate information, resulting in further discrepancies between donated items and the victims' genuine needs. The available geospatial platforms primarily support surveillance and monitoring of epidemic or disaster situations but fail to address the management of needs related to donation and receipt. Through an extensive review of the literature and related research, it was identified that a geospatial platform specifically dedicated to donation management has not yet been developed. To address this gap, this research proposes the creation of a novel geospatial platform using data analysis and visualization methods, complemented by the integration of geofencing technology. By employing such an approach, the geospatial platform will play a pivotal role in enhancing disaster and epidemic assistance. It will facilitate efficient data processing and visualization, overcoming the limitations faced by the current offline system. Emphasis will be placed on improving the management of needs concerning donation and receipt, thereby mitigating mismatches between assistance and actual requirements. Consequently, this platform is expected to significantly enhance the effectiveness and targeting of aid distribution during times of crises.","PeriodicalId":45439,"journal":{"name":"TEM Journal-Technology Education Management Informatics","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2023-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47286508","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}
I. Syahrini, Ariefia Sardini, Nurmaulidar Nurmaulidar, M. Ikhwan
The purpose of this study is to form several optimal portfolios based on the proportion of funds invested in stocks, then the most optimal portfolio will be selected among the optimal portfolios that have been formed. The method used in this study is the lexicographic goal programming method, which is to determine the optimal portfolio based on the proportion of invested funds, then the selection of the most optimal portfolio is determined using the expected shortfall method. This study used data from 5 companies contained in Indonesia Stock Exchange (IDX). The results showed that from the proportion of invested funds, 11 optimal portfolios were obtained. Using the expected shortfall method, the most optimal portfolio of 11 portfolios was obtained, namely type 5 portfolio.
{"title":"Application of Lexicographic Goal Programming Method on Stock Portfolio Optimization With Expected Shortfall Approach","authors":"I. Syahrini, Ariefia Sardini, Nurmaulidar Nurmaulidar, M. Ikhwan","doi":"10.18421/tem123-19","DOIUrl":"https://doi.org/10.18421/tem123-19","url":null,"abstract":"The purpose of this study is to form several optimal portfolios based on the proportion of funds invested in stocks, then the most optimal portfolio will be selected among the optimal portfolios that have been formed. The method used in this study is the lexicographic goal programming method, which is to determine the optimal portfolio based on the proportion of invested funds, then the selection of the most optimal portfolio is determined using the expected shortfall method. This study used data from 5 companies contained in Indonesia Stock Exchange (IDX). The results showed that from the proportion of invested funds, 11 optimal portfolios were obtained. Using the expected shortfall method, the most optimal portfolio of 11 portfolios was obtained, namely type 5 portfolio.","PeriodicalId":45439,"journal":{"name":"TEM Journal-Technology Education Management Informatics","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2023-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43636681","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}
Wagino Wagino, H. Maksum, W. Purwanto, K. Krismadinata, S. Suhendar, Rahmat Desman Koto
This systematic review examines the challenges and potential solutions to improve the implementation of collaborative learning and e-learning environments in universities. The article analyzes 200 relevant articles published between 2014-2022 using a qualitative approach to identify themes and sub-themes related to collaborative learning and e-learning environments. The study reveals various learning methods employed, including MOOC (Massive Open Online Course), digital mind maps, and tripartite learning, but also highlights challenges such as lack of digital infrastructure, low-quality internet networks, and inadequate practical tools. The research emphasizes the need for effective leadership and management in vocational institutions and recommends further research on curriculum development, learning evaluation methods, lecturer performance assessment, and improving digital infrastructure and educator training. Collaboration with industry and other training institutions is also suggested to improve students' employability and entrepreneurship skills.
{"title":"Exploring the Full Potential of Collaborative Learning and E-Learning Environments in Universities: A Systematic Review","authors":"Wagino Wagino, H. Maksum, W. Purwanto, K. Krismadinata, S. Suhendar, Rahmat Desman Koto","doi":"10.18421/tem123-60","DOIUrl":"https://doi.org/10.18421/tem123-60","url":null,"abstract":"This systematic review examines the challenges and potential solutions to improve the implementation of collaborative learning and e-learning environments in universities. The article analyzes 200 relevant articles published between 2014-2022 using a qualitative approach to identify themes and sub-themes related to collaborative learning and e-learning environments. The study reveals various learning methods employed, including MOOC (Massive Open Online Course), digital mind maps, and tripartite learning, but also highlights challenges such as lack of digital infrastructure, low-quality internet networks, and inadequate practical tools. The research emphasizes the need for effective leadership and management in vocational institutions and recommends further research on curriculum development, learning evaluation methods, lecturer performance assessment, and improving digital infrastructure and educator training. Collaboration with industry and other training institutions is also suggested to improve students' employability and entrepreneurship skills.","PeriodicalId":45439,"journal":{"name":"TEM Journal-Technology Education Management Informatics","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2023-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42105392","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}
M. F. Sapuri, Mohd Khairil Adzhar Mahmood, N. E. Abd Rashid, N. Zakaria, S. A. E. Ab Rahim, Z. I. Khan
This study describes a complementary split-ring resonator (CSRR)-based planar microwave sensor. Its capability in detecting several samples which are based on the usual water contaminant in Malaysia was investigated. The CSRR sensor was designed with an unloaded resonant frequency of 2.0 GHz, and it was fabricated on an FR-4 substrate with a thickness of 1.6 mm and a dielectric constant of 4.3. The S-parameter responses of the sensor were measured under two conditions; i) unloaded and ii) loaded. For the latter, samples of tap water, salt water, isopropyl alcohol, filtered water and cooking oil were used to load the resonant element of the CSRR. The measurement result of unloaded CSRR shows that the designed sensor resonates at 1.99 GHz, which is in line with the simulation. The measurement results also showed that the presence of all samples caused the resonant frequency of the CSRR to shift, with filtered water and cooking oil showing the biggest frequency shifts (0.84 GHz and 0.96 GHz, respectively). A sensitivity analysis of the CSRR was carried out and it shows that it achieves 0.25% sensitivity. The proposed sensor may be a useful substitute for pricey commercial sensors for applications involving water quality because of the inexpensive materials and ease of fabrication.
{"title":"Liquid Characterization of 2 GHz Complimentary Split Ring Resonator (CSRR) for Water Quality Applications","authors":"M. F. Sapuri, Mohd Khairil Adzhar Mahmood, N. E. Abd Rashid, N. Zakaria, S. A. E. Ab Rahim, Z. I. Khan","doi":"10.18421/tem123-20","DOIUrl":"https://doi.org/10.18421/tem123-20","url":null,"abstract":"This study describes a complementary split-ring resonator (CSRR)-based planar microwave sensor. Its capability in detecting several samples which are based on the usual water contaminant in Malaysia was investigated. The CSRR sensor was designed with an unloaded resonant frequency of 2.0 GHz, and it was fabricated on an FR-4 substrate with a thickness of 1.6 mm and a dielectric constant of 4.3. The S-parameter responses of the sensor were measured under two conditions; i) unloaded and ii) loaded. For the latter, samples of tap water, salt water, isopropyl alcohol, filtered water and cooking oil were used to load the resonant element of the CSRR. The measurement result of unloaded CSRR shows that the designed sensor resonates at 1.99 GHz, which is in line with the simulation. The measurement results also showed that the presence of all samples caused the resonant frequency of the CSRR to shift, with filtered water and cooking oil showing the biggest frequency shifts (0.84 GHz and 0.96 GHz, respectively). A sensitivity analysis of the CSRR was carried out and it shows that it achieves 0.25% sensitivity. The proposed sensor may be a useful substitute for pricey commercial sensors for applications involving water quality because of the inexpensive materials and ease of fabrication.","PeriodicalId":45439,"journal":{"name":"TEM Journal-Technology Education Management Informatics","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2023-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45393115","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}
Dimas Arya Soeadyfa Fridyatama, S. Suparji, M. Sumbawati
The widely-used ATC simulator laboratory in air traffic control education lacks research on its development. This study aims to develop a computer-based aerodrome control tower simulator for ATC using the research and development method. The simulator offers a realistic training environment, covering simulation, technicalities, facilities, configuration, equipment, specifications, software, operations, and development. It is a crucial facility in ATC courses at Indonesian aviation universities. Findings demonstrate its effectiveness in enhancing student proficiency and reducing reliance on external suppliers. The resulting design concept, developed through research and development, can be utilized by local experts to promote advanced technology mastery and cost efficiency in ATC training systems. It provides opportunities for local experts and serves as a model for other countries, advancing ATC education.
{"title":"Developing Air Traffic Control Simulator for Laboratory","authors":"Dimas Arya Soeadyfa Fridyatama, S. Suparji, M. Sumbawati","doi":"10.18421/tem123-26","DOIUrl":"https://doi.org/10.18421/tem123-26","url":null,"abstract":"The widely-used ATC simulator laboratory in air traffic control education lacks research on its development. This study aims to develop a computer-based aerodrome control tower simulator for ATC using the research and development method. The simulator offers a realistic training environment, covering simulation, technicalities, facilities, configuration, equipment, specifications, software, operations, and development. It is a crucial facility in ATC courses at Indonesian aviation universities. Findings demonstrate its effectiveness in enhancing student proficiency and reducing reliance on external suppliers. The resulting design concept, developed through research and development, can be utilized by local experts to promote advanced technology mastery and cost efficiency in ATC training systems. It provides opportunities for local experts and serves as a model for other countries, advancing ATC education.","PeriodicalId":45439,"journal":{"name":"TEM Journal-Technology Education Management Informatics","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2023-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48475468","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}
D. Syah, I. Muda, Prihatin Lumbanraja, Azizul Kholis
The hotel industry is a significant sector for Indonesian economic growth. Nowadays, cloud computing is bringing much potential for hotels to increase their competitive advantage, specifically in facilitating Information Systems (IS). However, we found still limited study that investigates cloud-based IS in accounting functions. Therefore, this study aims to analyze 1) the impact of the human aspect in determining cloud performance, 2) the impact of cloud performance on the relative advantage and compatibility of cloud-based Accounting Information Systems (AIS) in the hotel industry, and 3) the impact of its relative advantage and compatibility on cloud-based AIS quality. Using purposive sampling, the data was collected from accounting and/or information manager hotels in North Sumatra, Indonesia. The collected data were analyzed using variance-based Structural Equation Modeling (SEM). We found that human, cloud performance, and technology adaptability are the critical antecedents of cloud-based AIS quality in the hotel industry. Hotel leaders should consider user computer-self efficacy and cloud-AIS alignment design while developing and integrating cloud-based AIS into their general system.
{"title":"The Role of Cloud Computing on Accounting Information System Quality:A Study in Hotel Industry","authors":"D. Syah, I. Muda, Prihatin Lumbanraja, Azizul Kholis","doi":"10.18421/tem123-72","DOIUrl":"https://doi.org/10.18421/tem123-72","url":null,"abstract":"The hotel industry is a significant sector for Indonesian economic growth. Nowadays, cloud computing is bringing much potential for hotels to increase their competitive advantage, specifically in facilitating Information Systems (IS). However, we found still limited study that investigates cloud-based IS in accounting functions. Therefore, this study aims to analyze 1) the impact of the human aspect in determining cloud performance, 2) the impact of cloud performance on the relative advantage and compatibility of cloud-based Accounting Information Systems (AIS) in the hotel industry, and 3) the impact of its relative advantage and compatibility on cloud-based AIS quality. Using purposive sampling, the data was collected from accounting and/or information manager hotels in North Sumatra, Indonesia. The collected data were analyzed using variance-based Structural Equation Modeling (SEM). We found that human, cloud performance, and technology adaptability are the critical antecedents of cloud-based AIS quality in the hotel industry. Hotel leaders should consider user computer-self efficacy and cloud-AIS alignment design while developing and integrating cloud-based AIS into their general system.","PeriodicalId":45439,"journal":{"name":"TEM Journal-Technology Education Management Informatics","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2023-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42969262","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}
Individuals with hearing or speech impairments face challenges in communicating with others, requiring special techniques to express their thoughts and feelings. Sign language is an alternative way to communicate using a specific pattern of hand gestures to deliver messages instead of verbal speaking (oral communication). Unfortunately, most people do not know how to use and read sign language. Because of its complexity and many types of sign language worldwide, only well-trained personnel could use it as a communication medium. This research provides a solution in the form of a machine-learning Android-based application designed to recognize sign language captured by a smartphone camera and translate it into Latin characters. The recognition accommodates Convolutional Neural Network (CNN), one of the popular deep learning algorithms. This application recognizes 26 characters of Indonesian Sign Language (Bahasa Isyarat Indonesia/BISINDO) alphabets using MobileNetV3 architecture. To build the data model, dataset images were collected from 5 different models demonstrating 26 BISINDO characters in various lighting, background, and hand gesture position. These dataset images were also generated using image augmentation process to achieve the randomness by adjusting the image rotation, noise, and brightness. Based on the testing result using 6,240 dataset images, the application has 75.38% accuracy in recognizing Indonesian Sign Language alphabets.
{"title":"Android-Based Application for Real-Time Indonesian Sign Language Recognition Using Convolutional Neural Network","authors":"Raymond Sutjiadi","doi":"10.18421/tem123-35","DOIUrl":"https://doi.org/10.18421/tem123-35","url":null,"abstract":"Individuals with hearing or speech impairments face challenges in communicating with others, requiring special techniques to express their thoughts and feelings. Sign language is an alternative way to communicate using a specific pattern of hand gestures to deliver messages instead of verbal speaking (oral communication). Unfortunately, most people do not know how to use and read sign language. Because of its complexity and many types of sign language worldwide, only well-trained personnel could use it as a communication medium. This research provides a solution in the form of a machine-learning Android-based application designed to recognize sign language captured by a smartphone camera and translate it into Latin characters. The recognition accommodates Convolutional Neural Network (CNN), one of the popular deep learning algorithms. This application recognizes 26 characters of Indonesian Sign Language (Bahasa Isyarat Indonesia/BISINDO) alphabets using MobileNetV3 architecture. To build the data model, dataset images were collected from 5 different models demonstrating 26 BISINDO characters in various lighting, background, and hand gesture position. These dataset images were also generated using image augmentation process to achieve the randomness by adjusting the image rotation, noise, and brightness. Based on the testing result using 6,240 dataset images, the application has 75.38% accuracy in recognizing Indonesian Sign Language alphabets.","PeriodicalId":45439,"journal":{"name":"TEM Journal-Technology Education Management Informatics","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2023-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46651233","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}
Sustainable growth is a major global concern due to environmental challenges, social and corporate governance matters. Identifying and analyzing key indicators can provide valuable insights into the critical factors affecting sustainability in the EU-27 countries. This paper analyzes environmental, social and governance national composite indicators for monitoring sustainable growth conditions in the EU-27. The authors develop a simplified algorithm based on the ESG index methodology and composite indicators theory. The three pillars of the ESG methodology are examined with a focus on the ten most valuable indicators in each pillar. A sub-objective is to verify what percentage of the results are consistent with the original approach. The data were collected for the EU-27 countries for 2020–2021. The study's main outcome is a simplified approach to measuring sustainability that is 81% consistent with previous calculations. In line with previous studies, Norway, Sweden, and Finland rank highest on the ESG index, while Cyprus, Bulgaria, Lithuania, and Greece rank the lowest.
{"title":"ESG Performance and Disclosure: National Composite Indicators for Monitoring Sustainable Growth Conditions in the EU-27","authors":"Petra Jílková, Jana Kotěšovcová","doi":"10.18421/tem123-68","DOIUrl":"https://doi.org/10.18421/tem123-68","url":null,"abstract":"Sustainable growth is a major global concern due to environmental challenges, social and corporate governance matters. Identifying and analyzing key indicators can provide valuable insights into the critical factors affecting sustainability in the EU-27 countries. This paper analyzes environmental, social and governance national composite indicators for monitoring sustainable growth conditions in the EU-27. The authors develop a simplified algorithm based on the ESG index methodology and composite indicators theory. The three pillars of the ESG methodology are examined with a focus on the ten most valuable indicators in each pillar. A sub-objective is to verify what percentage of the results are consistent with the original approach. The data were collected for the EU-27 countries for 2020–2021. The study's main outcome is a simplified approach to measuring sustainability that is 81% consistent with previous calculations. In line with previous studies, Norway, Sweden, and Finland rank highest on the ESG index, while Cyprus, Bulgaria, Lithuania, and Greece rank the lowest.","PeriodicalId":45439,"journal":{"name":"TEM Journal-Technology Education Management Informatics","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2023-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47176486","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}
Ahmad Ihsan Yassin, K. K. Mohd Shariff, Mustapha Awang Kechik, A. Ali, Megat Syahirul Megat Amin
Monitoring vehicle traffic at a large scale is a challenging task for authorities, particularly considering the high cost of traffic sensors such as vision cameras. To meet the growing demand for more accurate traffic monitoring, the use of traffic sounds has become a popular approach, as it provides insight into the types of traffic present. This paper reports on an approach to vehicle classification based on acoustic signals, using the Mel-Frequency Cepstral Coefficients (MFCC) and the Long Short-Term Memory (LSTM) networks. This study exhibited classification accuracy scores of 82-86.2% across four vehicle categories: motorcycle, car, truck, and no traffic. The results demonstrated that large-scale, low-cost acoustic processing can be effectively used for vehicle monitoring.
{"title":"Acoustic Vehicle Classification Using Mel-Frequency Features with Long Short-Term Memory Neural Networks","authors":"Ahmad Ihsan Yassin, K. K. Mohd Shariff, Mustapha Awang Kechik, A. Ali, Megat Syahirul Megat Amin","doi":"10.18421/tem123-29","DOIUrl":"https://doi.org/10.18421/tem123-29","url":null,"abstract":"Monitoring vehicle traffic at a large scale is a challenging task for authorities, particularly considering the high cost of traffic sensors such as vision cameras. To meet the growing demand for more accurate traffic monitoring, the use of traffic sounds has become a popular approach, as it provides insight into the types of traffic present. This paper reports on an approach to vehicle classification based on acoustic signals, using the Mel-Frequency Cepstral Coefficients (MFCC) and the Long Short-Term Memory (LSTM) networks. This study exhibited classification accuracy scores of 82-86.2% across four vehicle categories: motorcycle, car, truck, and no traffic. The results demonstrated that large-scale, low-cost acoustic processing can be effectively used for vehicle monitoring.","PeriodicalId":45439,"journal":{"name":"TEM Journal-Technology Education Management Informatics","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2023-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45249186","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}
Convolutional neural networks are special types of artificial neural networks that can solve various tasks in computer vision, such as image classification, object detection, and general recognition. The paper presents the basic building blocks of convolutional neural networks and their architecture, and compares their recognition accuracy with other character recognition techniques using the example of character recognition from vehicle registration plates. The purpose of the experiments was to determine the optimal configuration of the convolutional neural network and the influence of the size and design method of the training set on the recognition rate. The study shows that although convolutional neural networks have recently gained attention, traditional recognition methods are still relevant, and the choice of the right classifier and its configuration depends on the type of recognition task.
{"title":"Using a Convolutional Neural Network for Machine Written Character Recognition","authors":"Ladislav Karrach, E. Pivarčiová","doi":"10.18421/tem123-03","DOIUrl":"https://doi.org/10.18421/tem123-03","url":null,"abstract":"Convolutional neural networks are special types of artificial neural networks that can solve various tasks in computer vision, such as image classification, object detection, and general recognition. The paper presents the basic building blocks of convolutional neural networks and their architecture, and compares their recognition accuracy with other character recognition techniques using the example of character recognition from vehicle registration plates. The purpose of the experiments was to determine the optimal configuration of the convolutional neural network and the influence of the size and design method of the training set on the recognition rate. The study shows that although convolutional neural networks have recently gained attention, traditional recognition methods are still relevant, and the choice of the right classifier and its configuration depends on the type of recognition task.","PeriodicalId":45439,"journal":{"name":"TEM Journal-Technology Education Management Informatics","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2023-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47432172","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：