Pub Date : 2023-03-22DOI: 10.1109/ECTIDAMTNCON57770.2023.10139505
T. Yooyativong, Chayapol Kamyod, Chong Ghil Kim
Traditional or rural dryers or Thai farmers' dryers have some drawbacks when compared to modern or commercial dryers on the market. Despite the fact that the dryer is vital and may be utilized as postharvest technology to preserve or produce some agricultural products, the farmer chose to build the traditional structure because of his limited income and resources. This research examined the needs of rural farmers and developed an integration of typical rural solar dryers or dryers using IoT technologies. The integrated design will preserve the structure's materials while increasing the system's capacity and efficiency to reduce costs. Farmers may now manage the temperature inside the dryer using the newly created mechanism. Remote monitoring and management are also made possible by the technology, minimizing the need for physical intervention. This leads to increased efficiency, lower costs, and a more sustainable energy source.
{"title":"The Integration of Traditional Rural Solar Dryer with LoRa and IoT Technology","authors":"T. Yooyativong, Chayapol Kamyod, Chong Ghil Kim","doi":"10.1109/ECTIDAMTNCON57770.2023.10139505","DOIUrl":"https://doi.org/10.1109/ECTIDAMTNCON57770.2023.10139505","url":null,"abstract":"Traditional or rural dryers or Thai farmers' dryers have some drawbacks when compared to modern or commercial dryers on the market. Despite the fact that the dryer is vital and may be utilized as postharvest technology to preserve or produce some agricultural products, the farmer chose to build the traditional structure because of his limited income and resources. This research examined the needs of rural farmers and developed an integration of typical rural solar dryers or dryers using IoT technologies. The integrated design will preserve the structure's materials while increasing the system's capacity and efficiency to reduce costs. Farmers may now manage the temperature inside the dryer using the newly created mechanism. Remote monitoring and management are also made possible by the technology, minimizing the need for physical intervention. This leads to increased efficiency, lower costs, and a more sustainable energy source.","PeriodicalId":38808,"journal":{"name":"Transactions on Electrical Engineering, Electronics, and Communications","volume":"24 1","pages":"434-437"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84408463","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 : 2023-03-22DOI: 10.1109/ECTIDAMTNCON57770.2023.10139672
P. Sureephong, Komalaporn Kummalue, S. Chernbumroong, Orathai Khiawcha-Um
The training Course under project “City Data Planner (CDP)” aimed to facilitate the change of sustainable smart city development. The local governance organization over 70 municipalities around Thailand were involved in the project. Knowledge and comprehension of city data is required to construct smart cities in multiple aspects. The utilization of information and technology to drive local government organizations has the potential to create a viable smart city. The aim of this paper is to survey the requirement of local government organization in order to adopt smart city technology in their workplace.
{"title":"Smart City Problem Analysis By Using Design Thinking","authors":"P. Sureephong, Komalaporn Kummalue, S. Chernbumroong, Orathai Khiawcha-Um","doi":"10.1109/ECTIDAMTNCON57770.2023.10139672","DOIUrl":"https://doi.org/10.1109/ECTIDAMTNCON57770.2023.10139672","url":null,"abstract":"The training Course under project “City Data Planner (CDP)” aimed to facilitate the change of sustainable smart city development. The local governance organization over 70 municipalities around Thailand were involved in the project. Knowledge and comprehension of city data is required to construct smart cities in multiple aspects. The utilization of information and technology to drive local government organizations has the potential to create a viable smart city. The aim of this paper is to survey the requirement of local government organization in order to adopt smart city technology in their workplace.","PeriodicalId":38808,"journal":{"name":"Transactions on Electrical Engineering, Electronics, and Communications","volume":"17 1","pages":"568-572"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86192526","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 : 2023-03-22DOI: 10.1109/ECTIDAMTNCON57770.2023.10139396
Sakkayaphop Pravesjit, Ponnipa Jantawong, A. Jitpattanakul, S. Mekruksavanich
Understanding human actions via the analysis of sensor data captured by wearable sensors is the goal of the complex subject of study known as sensor-based human activity recognition (S-HAR). Human participants' characteristics are only periodically included in deep learning (DL) approaches to S-HAR. Recognizing people was challenging for these DL methods because of the variety of physical characteristics people have. To address this challenge, we introduce a physique-based S-HAR architecture that could support deep learning networks to achieve higher identification a ccuracies a nd F1-scores. The HARSense dataset, a publicly available benchmark S-HAR dataset that compiles raw sensor data acquired from smartphones, was employed to build and evaluate five DL networks. A ccording to the experiments, the five models' detection performance improves dramatically when given access to biological data.
{"title":"Physique- Based Human Activity Recognition Using Deep Learning Approaches and Smartphone Sensors","authors":"Sakkayaphop Pravesjit, Ponnipa Jantawong, A. Jitpattanakul, S. Mekruksavanich","doi":"10.1109/ECTIDAMTNCON57770.2023.10139396","DOIUrl":"https://doi.org/10.1109/ECTIDAMTNCON57770.2023.10139396","url":null,"abstract":"Understanding human actions via the analysis of sensor data captured by wearable sensors is the goal of the complex subject of study known as sensor-based human activity recognition (S-HAR). Human participants' characteristics are only periodically included in deep learning (DL) approaches to S-HAR. Recognizing people was challenging for these DL methods because of the variety of physical characteristics people have. To address this challenge, we introduce a physique-based S-HAR architecture that could support deep learning networks to achieve higher identification a ccuracies a nd F1-scores. The HARSense dataset, a publicly available benchmark S-HAR dataset that compiles raw sensor data acquired from smartphones, was employed to build and evaluate five DL networks. A ccording to the experiments, the five models' detection performance improves dramatically when given access to biological data.","PeriodicalId":38808,"journal":{"name":"Transactions on Electrical Engineering, Electronics, and Communications","volume":"17 1","pages":"479-482"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86814576","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 : 2023-03-22DOI: 10.1109/ECTIDAMTNCON57770.2023.10139478
Kittititouch Suteeca
Very small entities (VSEs) have experienced numerous difficulties in the midst of the extremely competitive software market. They typically manifest as increased customer expectations, frequent changes in user needs, and the need for rapid deployment. The most popular choice for development architecture is software as a service (SaaS). It can replace the role of an outdated system and react immediately to user input. The service delivery standard ISO/IEC 29110-4-3 outlines the process for implementing services while guaranteeing their quality. In this study, the requirement traceability matrix was designed to solve the requirement of service problems.
{"title":"Requirement Traceability Matrix for SaaS Development","authors":"Kittititouch Suteeca","doi":"10.1109/ECTIDAMTNCON57770.2023.10139478","DOIUrl":"https://doi.org/10.1109/ECTIDAMTNCON57770.2023.10139478","url":null,"abstract":"Very small entities (VSEs) have experienced numerous difficulties in the midst of the extremely competitive software market. They typically manifest as increased customer expectations, frequent changes in user needs, and the need for rapid deployment. The most popular choice for development architecture is software as a service (SaaS). It can replace the role of an outdated system and react immediately to user input. The service delivery standard ISO/IEC 29110-4-3 outlines the process for implementing services while guaranteeing their quality. In this study, the requirement traceability matrix was designed to solve the requirement of service problems.","PeriodicalId":38808,"journal":{"name":"Transactions on Electrical Engineering, Electronics, and Communications","volume":"52 1","pages":"183-187"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79297932","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 : 2023-03-22DOI: 10.1109/ECTIDAMTNCON57770.2023.10139562
J. P. Degel, S. Haehnlein, Lars Boschert, Christian Kloeffer, M. Doppelbauer
The present work describes an extension of current slope estimation for parameter estimation of permanent magnet synchronous machines operated at inverters. The area of operation for current slope estimation in the individual switching states of the inverter is limited due to measurement noise, bandwidth limitation of the current sensors and the commutation processes of the inverter's switching operations. Therefore, a minimum duration of each switching state is necessary, limiting the final area of operation of a robust current slope estimation. This paper presents an extension of existing current slope estimation algorithms resulting in a greater area of operation and a more robust estimation result.
{"title":"Extended algorithm for current slope estimation in inverter fed synchronous machines","authors":"J. P. Degel, S. Haehnlein, Lars Boschert, Christian Kloeffer, M. Doppelbauer","doi":"10.1109/ECTIDAMTNCON57770.2023.10139562","DOIUrl":"https://doi.org/10.1109/ECTIDAMTNCON57770.2023.10139562","url":null,"abstract":"The present work describes an extension of current slope estimation for parameter estimation of permanent magnet synchronous machines operated at inverters. The area of operation for current slope estimation in the individual switching states of the inverter is limited due to measurement noise, bandwidth limitation of the current sensors and the commutation processes of the inverter's switching operations. Therefore, a minimum duration of each switching state is necessary, limiting the final area of operation of a robust current slope estimation. This paper presents an extension of existing current slope estimation algorithms resulting in a greater area of operation and a more robust estimation result.","PeriodicalId":38808,"journal":{"name":"Transactions on Electrical Engineering, Electronics, and Communications","volume":"107 1","pages":"273-278"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84734978","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 : 2023-03-22DOI: 10.1109/ECTIDAMTNCON57770.2023.10139537
Captain Sukchayanan, Sujitra Arwatchananukul, P. Temdee
Currently, metabolic syndrome, the leading cause of most of non-communicable diseases, has been overlooked because it is common and does not cause illness at the early stage. The purpose of this study was to classify the group of metabolic syndromes including diabetes, cardiovascular disease, and high blood pressure using machine learning based method. The data was collected from three sub-districts in the province of Chiang Rai: Mae Khao Tom, Nang Lae, and Tha Sud totally 1,605 records. The Gradient Boosting is proposed for the multi-class classification model. From the comparison results with other existing methods, including Random Forest, Extra Trees, K-nearest Neighbor, Support Vector Machines, and Decision Trees, Gradient Boosting outperforms other existing methods having 95.27% accuracy, 95.24% precision, 95.26% recall, and 95.24% F1 score, respectively.
{"title":"Multi-Class Classification of Metabolic Syndrome Group Using Gradient Boosting","authors":"Captain Sukchayanan, Sujitra Arwatchananukul, P. Temdee","doi":"10.1109/ECTIDAMTNCON57770.2023.10139537","DOIUrl":"https://doi.org/10.1109/ECTIDAMTNCON57770.2023.10139537","url":null,"abstract":"Currently, metabolic syndrome, the leading cause of most of non-communicable diseases, has been overlooked because it is common and does not cause illness at the early stage. The purpose of this study was to classify the group of metabolic syndromes including diabetes, cardiovascular disease, and high blood pressure using machine learning based method. The data was collected from three sub-districts in the province of Chiang Rai: Mae Khao Tom, Nang Lae, and Tha Sud totally 1,605 records. The Gradient Boosting is proposed for the multi-class classification model. From the comparison results with other existing methods, including Random Forest, Extra Trees, K-nearest Neighbor, Support Vector Machines, and Decision Trees, Gradient Boosting outperforms other existing methods having 95.27% accuracy, 95.24% precision, 95.26% recall, and 95.24% F1 score, respectively.","PeriodicalId":38808,"journal":{"name":"Transactions on Electrical Engineering, Electronics, and Communications","volume":"38 1","pages":"564-567"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90946820","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 : 2023-03-22DOI: 10.1109/ECTIDAMTNCON57770.2023.10139512
Ajchara Phu-ang
This article is designed for solving the routing problem that limit of the electric energy and workload, called the Capacitated Electric Vehicle Routing Problem (CEVRP). The objective of this problem is to search for the optimal routing of a vehicle contain a limited electric energy and goods. The proposed model is based on the concepts of the differential evolutionary (DE) algorithm and the adaptive k-mean algorithm, in addition, the fuzzy technique is also applied with the aim to achieve best overall performance. In order to improve the efficiency of the DE, several aspects have been adopted, such as (1) The proposed model is employed the adaptive K-means algorithm to obtain the ability to search for the best initial solution, (2) The fuzzy technique is determined as the decision making technique which decided when one customer is in-between several clusters and (3) The local and global swap method is introduced to increase the exploitation and exploration capability. The proposed model has been evaluated and compared to the state-of-the-art algorithm in term of the average percentage deviation from the lower bound.
{"title":"Solving the Capacitated Electric Vehicle (EV) Routing Problem by The Differential Evolutionary Algorithm with Adaptive K-Means","authors":"Ajchara Phu-ang","doi":"10.1109/ECTIDAMTNCON57770.2023.10139512","DOIUrl":"https://doi.org/10.1109/ECTIDAMTNCON57770.2023.10139512","url":null,"abstract":"This article is designed for solving the routing problem that limit of the electric energy and workload, called the Capacitated Electric Vehicle Routing Problem (CEVRP). The objective of this problem is to search for the optimal routing of a vehicle contain a limited electric energy and goods. The proposed model is based on the concepts of the differential evolutionary (DE) algorithm and the adaptive k-mean algorithm, in addition, the fuzzy technique is also applied with the aim to achieve best overall performance. In order to improve the efficiency of the DE, several aspects have been adopted, such as (1) The proposed model is employed the adaptive K-means algorithm to obtain the ability to search for the best initial solution, (2) The fuzzy technique is determined as the decision making technique which decided when one customer is in-between several clusters and (3) The local and global swap method is introduced to increase the exploitation and exploration capability. The proposed model has been evaluated and compared to the state-of-the-art algorithm in term of the average percentage deviation from the lower bound.","PeriodicalId":38808,"journal":{"name":"Transactions on Electrical Engineering, Electronics, and Communications","volume":"4 1","pages":"225-228"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85330809","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 : 2023-03-22DOI: 10.1109/ECTIDAMTNCON57770.2023.10139491
S. Chernbumroong, Patnarin Korboon, Noppanut Wannapee
Cultural tourism is a type of tourism that aims to learn about the culture and way of life of indigenous peoples who have their own culture. Tambon San Pu Loei in Doi Saket District, Chiang Mai is also known as cultural tourism destination where tourist gain information and experience about historical and local people way of life. However, the report from local governments mentioned that tourists had difficulty acquiring information. As a result, the community lacked the ability to communicate the local knowledge in a variety of disciplines since improper storing of data sources and met the problem of coordinates not matching the actual location of the place. In this study, the two-dimensional bar code technology (QR Code) was improved and employed on location-based services for promoting the cultural tourism and utilizing to tackle the problem of tourists accessing information. 83 travelers were involved in this study. Satisfaction level is measured based on 3 parts: content, design, and useful. The overall result of tourist satisfaction who scanned the QR code and visited the website (www.dekdoi-travel.com) is also presented in this paper.
文化旅游是一种旅游，目的是了解文化和生活方式的土著人民谁拥有自己的文化。Tambon San Pu Loei在Doi Saket区，清迈也被称为文化旅游目的地，游客在那里获得有关历史和当地人生活方式的信息和体验。然而，当地政府的报告提到，游客很难获得信息。因此，由于数据源存储不当，社区缺乏沟通当地各种学科知识的能力，并且遇到了坐标与当地实际位置不匹配的问题。本研究将二维条码技术(QR code)改进并应用于地理定位服务，促进文化旅游，解决游客获取信息的问题。83名旅行者参与了这项研究。满意度是基于3个部分来衡量的:内容、设计和有用。本文还给出了扫描二维码访问网站(www.dekdoi-travel.com)的游客满意度的总体结果。
{"title":"The Application Of Quick Response Code Technology To Promote Cultural Tourism: Case Study of San Pu Loie","authors":"S. Chernbumroong, Patnarin Korboon, Noppanut Wannapee","doi":"10.1109/ECTIDAMTNCON57770.2023.10139491","DOIUrl":"https://doi.org/10.1109/ECTIDAMTNCON57770.2023.10139491","url":null,"abstract":"Cultural tourism is a type of tourism that aims to learn about the culture and way of life of indigenous peoples who have their own culture. Tambon San Pu Loei in Doi Saket District, Chiang Mai is also known as cultural tourism destination where tourist gain information and experience about historical and local people way of life. However, the report from local governments mentioned that tourists had difficulty acquiring information. As a result, the community lacked the ability to communicate the local knowledge in a variety of disciplines since improper storing of data sources and met the problem of coordinates not matching the actual location of the place. In this study, the two-dimensional bar code technology (QR Code) was improved and employed on location-based services for promoting the cultural tourism and utilizing to tackle the problem of tourists accessing information. 83 travelers were involved in this study. Satisfaction level is measured based on 3 parts: content, design, and useful. The overall result of tourist satisfaction who scanned the QR code and visited the website (www.dekdoi-travel.com) is also presented in this paper.","PeriodicalId":38808,"journal":{"name":"Transactions on Electrical Engineering, Electronics, and Communications","volume":"197 1","pages":"560-563"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85445226","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 : 2023-03-22DOI: 10.1109/ECTIDAMTNCON57770.2023.10139655
Abhishek Koti, A. Khare, J. P. Kumar
Many people in India are subjected to visual impairment and blindness which are not curable. Most of such people are poor and cannot afford digital equipment for assistance. Visually Impaired or visually challenged people face a lot of difficulty in recognizing the paper currencies during their financial transactions due to the similar texture of paper and dimensions of currency notes. This makes it time-consuming, complex and erroneous at times. The proposed framework is to help visually impaired or blind people by providing them with digital assistance, which will take a photo of the note and notify the user the denomination via speech medium.
{"title":"Netrahitha: Currency Detector Jacket for visually impaired people","authors":"Abhishek Koti, A. Khare, J. P. Kumar","doi":"10.1109/ECTIDAMTNCON57770.2023.10139655","DOIUrl":"https://doi.org/10.1109/ECTIDAMTNCON57770.2023.10139655","url":null,"abstract":"Many people in India are subjected to visual impairment and blindness which are not curable. Most of such people are poor and cannot afford digital equipment for assistance. Visually Impaired or visually challenged people face a lot of difficulty in recognizing the paper currencies during their financial transactions due to the similar texture of paper and dimensions of currency notes. This makes it time-consuming, complex and erroneous at times. The proposed framework is to help visually impaired or blind people by providing them with digital assistance, which will take a photo of the note and notify the user the denomination via speech medium.","PeriodicalId":38808,"journal":{"name":"Transactions on Electrical Engineering, Electronics, and Communications","volume":"6 1","pages":"364-368"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75793713","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 : 2023-03-22DOI: 10.1109/ECTIDAMTNCON57770.2023.10139572
Nitiphong Kaewman, Phasit Charoenkwan, Jinnapat Yana, Phon-ubon Suanoi, K. Duangjan, J. Pekkoh, Chayakorn Pumas
The utilization of microalgae as a bioindicator for water quality assessment has traditionally relied on the expertise of morphological identification. With the advent of technological advancements, particularly the smartphone camera, there has been increasing interest in using it as a tool for various fields of microbiological and medical diagnostics, including image analysis of microalgae. Despite the growing popularity of smartphone-based image analysis, the image quality of smartphone cameras for detecting microalgae has yet to be thoroughly evaluated. Therefore, the purpose of this study was to investigate the suitability of smartphone-based camera for collecting microalgae images and compare it to that of a digital microscope camera. Additionally, the effect of different microscopic magnifications at 100x and 400x on model performance was thoroughly studied. Four models, YOLOv5, RetinaNet, EfficientDet, and Faster-RCNN, were trained on microalgae image datasets taken by both a smartphone camera (SC) and a digital microscope camera (DMC) under 100x and 400x magnification. A total of 11,608 images were divided into three parts: train (70%), validation (10%), and test (20%), with the test dataset separated into four parts for each device and magnification. The results of the study indicated that Faster-RCNN was the best model for microalgae detection, with the highest average precision $(mathbf{AP}^{0.5})$ values of 0.60, 0.84, 0.91, and 0.96 at 100x magnification of SC and DMC and 400x magnification of SC and DMC, respectively. The comparison between the image quality of SC and DMC at each magnification revealed that the SC was less suitable for microalgae identification, particularly at 100x magnification. Conversely, the 400x magnification of SC had the potential to identify microalgae through the use of smartphone-based photography, as well as digital microscope camera.
{"title":"A Deep Learning Approach for Locating Microalgae in Image Captured by Smartphone and Digital Microscope Camera","authors":"Nitiphong Kaewman, Phasit Charoenkwan, Jinnapat Yana, Phon-ubon Suanoi, K. Duangjan, J. Pekkoh, Chayakorn Pumas","doi":"10.1109/ECTIDAMTNCON57770.2023.10139572","DOIUrl":"https://doi.org/10.1109/ECTIDAMTNCON57770.2023.10139572","url":null,"abstract":"The utilization of microalgae as a bioindicator for water quality assessment has traditionally relied on the expertise of morphological identification. With the advent of technological advancements, particularly the smartphone camera, there has been increasing interest in using it as a tool for various fields of microbiological and medical diagnostics, including image analysis of microalgae. Despite the growing popularity of smartphone-based image analysis, the image quality of smartphone cameras for detecting microalgae has yet to be thoroughly evaluated. Therefore, the purpose of this study was to investigate the suitability of smartphone-based camera for collecting microalgae images and compare it to that of a digital microscope camera. Additionally, the effect of different microscopic magnifications at 100x and 400x on model performance was thoroughly studied. Four models, YOLOv5, RetinaNet, EfficientDet, and Faster-RCNN, were trained on microalgae image datasets taken by both a smartphone camera (SC) and a digital microscope camera (DMC) under 100x and 400x magnification. A total of 11,608 images were divided into three parts: train (70%), validation (10%), and test (20%), with the test dataset separated into four parts for each device and magnification. The results of the study indicated that Faster-RCNN was the best model for microalgae detection, with the highest average precision $(mathbf{AP}^{0.5})$ values of 0.60, 0.84, 0.91, and 0.96 at 100x magnification of SC and DMC and 400x magnification of SC and DMC, respectively. The comparison between the image quality of SC and DMC at each magnification revealed that the SC was less suitable for microalgae identification, particularly at 100x magnification. Conversely, the 400x magnification of SC had the potential to identify microalgae through the use of smartphone-based photography, as well as digital microscope camera.","PeriodicalId":38808,"journal":{"name":"Transactions on Electrical Engineering, Electronics, and Communications","volume":"75 1","pages":"457-462"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86176468","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：