Rapid deterioration of maintenance strategies brings us to the focal point of building a strong and efficient maintenance system which can not only automatically maintain the assets but also predict the vulnerability of the asset in the future so as to give the company an idea of a future breakdown which might occur. Such maintenance systems will not only help the company in saving costs but also make the procedure of checking the assets much more streamlined. Thus several research study of already existing maintenance systems were looked up and studied. These included the concepts of dynamic programming along with heuristic and genetic algorithms which were being used in an industry to assign relevant work to relevant technicians. RFID is used in the refining industry to the tree classification algorithms being implemented in the Railway maintenance system. Reading such research work gives us an idea of challenges that industries continue to face and what more could be done to eliminate the existing negatives in the maintenance system strategies.
{"title":"A Study on Deploying Smart and Predictive Industry Maintenance System","authors":"Sarita P. Ambadekar, Amodh Praveen Pandey, Khushi Rajesh Singh, Shriyans Shailesh Naik","doi":"10.1109/ICOEI56765.2023.10125995","DOIUrl":"https://doi.org/10.1109/ICOEI56765.2023.10125995","url":null,"abstract":"Rapid deterioration of maintenance strategies brings us to the focal point of building a strong and efficient maintenance system which can not only automatically maintain the assets but also predict the vulnerability of the asset in the future so as to give the company an idea of a future breakdown which might occur. Such maintenance systems will not only help the company in saving costs but also make the procedure of checking the assets much more streamlined. Thus several research study of already existing maintenance systems were looked up and studied. These included the concepts of dynamic programming along with heuristic and genetic algorithms which were being used in an industry to assign relevant work to relevant technicians. RFID is used in the refining industry to the tree classification algorithms being implemented in the Railway maintenance system. Reading such research work gives us an idea of challenges that industries continue to face and what more could be done to eliminate the existing negatives in the maintenance system strategies.","PeriodicalId":168942,"journal":{"name":"2023 7th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126416550","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 : 2023-04-11DOI: 10.1109/ICOEI56765.2023.10125949
N. Bhuvaneswary, M. Karthik, Nilayam Kumar, P. Kumar, P. Harsha
Developing sustainable alternatives that won't hurt the environment has become more important as a result of our need to protect the world we leave behind. One such option that functions without emitting any emissions is the use of electric automobiles. Rechargeable batteries used in electric vehicles are constructed of numerous sequential and parallel arrangements of cell modules. Several hundred volts are generated by these battery packs' electricity. They are essential since they are a requirement for many internal automotive functions, a part of the car that needs regular oversight and management. This calls for a battery management system, which is made up of many parts that make sure the battery operates effectively with no danger of failure. In this study, IoT is used to showcase quick charging for electric vehicles as well as battery management systems. The EV metering architecture, which contains real-time data to provide current information about the operations and behaviors at the energy distribution network, is also made available to EV consumers at each charging site.
{"title":"Universal Charging Station for EV and BMS","authors":"N. Bhuvaneswary, M. Karthik, Nilayam Kumar, P. Kumar, P. Harsha","doi":"10.1109/ICOEI56765.2023.10125949","DOIUrl":"https://doi.org/10.1109/ICOEI56765.2023.10125949","url":null,"abstract":"Developing sustainable alternatives that won't hurt the environment has become more important as a result of our need to protect the world we leave behind. One such option that functions without emitting any emissions is the use of electric automobiles. Rechargeable batteries used in electric vehicles are constructed of numerous sequential and parallel arrangements of cell modules. Several hundred volts are generated by these battery packs' electricity. They are essential since they are a requirement for many internal automotive functions, a part of the car that needs regular oversight and management. This calls for a battery management system, which is made up of many parts that make sure the battery operates effectively with no danger of failure. In this study, IoT is used to showcase quick charging for electric vehicles as well as battery management systems. The EV metering architecture, which contains real-time data to provide current information about the operations and behaviors at the energy distribution network, is also made available to EV consumers at each charging site.","PeriodicalId":168942,"journal":{"name":"2023 7th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"153 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128201108","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 : 2023-04-11DOI: 10.1109/ICOEI56765.2023.10125877
E. D, S. M
Extraction of fetal electrocardiogram (FECG) plays a major role in monitoring fetal growth and in the diagnosis of fetal heart disorder. This research study proposes a linearization process in a Non-Causal filtering structure for extracting the fetal ECG. The linearization aims to match the baselines of abdominal and thorax ECG which improves the performance in adaptive filtering. The method initially detects the maternal R-peaks from the thorax ECG (TECG) recordings and abdominal ECG (AECG) recordings. The slope is then estimated using the amplitude of the detected peak points. Based on the estimated slopes, the abdominal ECG is then linearized which is then fed as the primary input for the non-casual adaptive filter. The non-casual filter uses both the future and past samples to extract the fetal ECG at sample index n. The metrics like, fetal to maternal signal-to-noise ratio (FmSNR), Correlation coefficient, peak root mean square difference (PRD), and R-peak detection accuracy (RPDA) were used to evaluate the algorithm performance. The datasets namely Daisy and Physionet are used for analysis. The method provides an FmSNR, correlation coefficient, PRD, and RPDA of 8.63dB, 0.9872, 81.98%, and 97.21 % respectively when evaluated on the Physionet dataset.
{"title":"Impact of Linearization in Abdominal ECG for Non-Causal Filtering Structure in Fetal ECG Extraction","authors":"E. D, S. M","doi":"10.1109/ICOEI56765.2023.10125877","DOIUrl":"https://doi.org/10.1109/ICOEI56765.2023.10125877","url":null,"abstract":"Extraction of fetal electrocardiogram (FECG) plays a major role in monitoring fetal growth and in the diagnosis of fetal heart disorder. This research study proposes a linearization process in a Non-Causal filtering structure for extracting the fetal ECG. The linearization aims to match the baselines of abdominal and thorax ECG which improves the performance in adaptive filtering. The method initially detects the maternal R-peaks from the thorax ECG (TECG) recordings and abdominal ECG (AECG) recordings. The slope is then estimated using the amplitude of the detected peak points. Based on the estimated slopes, the abdominal ECG is then linearized which is then fed as the primary input for the non-casual adaptive filter. The non-casual filter uses both the future and past samples to extract the fetal ECG at sample index n. The metrics like, fetal to maternal signal-to-noise ratio (FmSNR), Correlation coefficient, peak root mean square difference (PRD), and R-peak detection accuracy (RPDA) were used to evaluate the algorithm performance. The datasets namely Daisy and Physionet are used for analysis. The method provides an FmSNR, correlation coefficient, PRD, and RPDA of 8.63dB, 0.9872, 81.98%, and 97.21 % respectively when evaluated on the Physionet dataset.","PeriodicalId":168942,"journal":{"name":"2023 7th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115923798","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 : 2023-04-11DOI: 10.1109/ICOEI56765.2023.10126028
Maria Christina Blessy A, S. Brindha, Bhargavi Kv, Kamali T
Vehicular ad hoc networks (VANETs) are Instantaneous networks built by vehicles communicating wirelessly to one another. It is difficult to make this connection possible and reliable because the vehicles move at a faster rate and the link between them is unreliable. Multiple methods are adapted to establish a reliable and stable connection. One of which is cluster-based. Clusters are groups of vehicles that are virtually linked to form a small network. VANET is able to provide a reliable and stable connection through the use of clusters. Several algorithms are proposed for the formation of a cluster that is both efficient and reliable. The proposed modified tuna swarm optimization algorithm aims to decrease the number of clusters while simultaneously boosting the packet delivery ratio and throughput. The results indicate that the proposed method yields results that are close to optimal, making it an efficient method for performing vehicular clustering to improve network performance.
{"title":"Optimal Cluster Minimization for VANETs using Modified Tuna Swarm Optimization","authors":"Maria Christina Blessy A, S. Brindha, Bhargavi Kv, Kamali T","doi":"10.1109/ICOEI56765.2023.10126028","DOIUrl":"https://doi.org/10.1109/ICOEI56765.2023.10126028","url":null,"abstract":"Vehicular ad hoc networks (VANETs) are Instantaneous networks built by vehicles communicating wirelessly to one another. It is difficult to make this connection possible and reliable because the vehicles move at a faster rate and the link between them is unreliable. Multiple methods are adapted to establish a reliable and stable connection. One of which is cluster-based. Clusters are groups of vehicles that are virtually linked to form a small network. VANET is able to provide a reliable and stable connection through the use of clusters. Several algorithms are proposed for the formation of a cluster that is both efficient and reliable. The proposed modified tuna swarm optimization algorithm aims to decrease the number of clusters while simultaneously boosting the packet delivery ratio and throughput. The results indicate that the proposed method yields results that are close to optimal, making it an efficient method for performing vehicular clustering to improve network performance.","PeriodicalId":168942,"journal":{"name":"2023 7th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132404072","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 : 2023-04-11DOI: 10.1109/ICOEI56765.2023.10125840
Nikhil N. Pawar, Umesh Kubade, Pranjali M. Jumle
There is a significant need for robotics, particularly in the healthcare field, as a result of the rising amount of Covid-19 patients. Keeping social distance has become a necessary preventative precaution since SARS-CoV-2 predominantly spreads through direct people contact and infected objects. The initiative provides an innovative impression of the patient's health. This necessitates treating sick people with a minimal doctor-patient contact. Robotics in the medical industry reduces the requirement for hospital staff by preventing primary medical employees from contracting the coronavirus and by preventing certain medicinal tasks from being partly performed by robots. Such a study aims to draw attention to the growing significance of robotic technologies in the medical industry and related fields. To do this, a thorough analysis of the numerous robotics used globally throughout the Covid-19 outbreak to attenuate and confine the virus was carried out. The findings indicate that using robots in the medical industry can significantly reduce the transmission of SARS-CoV-2 since it prevents the virus from spreading between sick people and medical personnel while also providing additional benefits like sanitation and cleanliness.
{"title":"Application of Multipurpose Robot for Covid-19","authors":"Nikhil N. Pawar, Umesh Kubade, Pranjali M. Jumle","doi":"10.1109/ICOEI56765.2023.10125840","DOIUrl":"https://doi.org/10.1109/ICOEI56765.2023.10125840","url":null,"abstract":"There is a significant need for robotics, particularly in the healthcare field, as a result of the rising amount of Covid-19 patients. Keeping social distance has become a necessary preventative precaution since SARS-CoV-2 predominantly spreads through direct people contact and infected objects. The initiative provides an innovative impression of the patient's health. This necessitates treating sick people with a minimal doctor-patient contact. Robotics in the medical industry reduces the requirement for hospital staff by preventing primary medical employees from contracting the coronavirus and by preventing certain medicinal tasks from being partly performed by robots. Such a study aims to draw attention to the growing significance of robotic technologies in the medical industry and related fields. To do this, a thorough analysis of the numerous robotics used globally throughout the Covid-19 outbreak to attenuate and confine the virus was carried out. The findings indicate that using robots in the medical industry can significantly reduce the transmission of SARS-CoV-2 since it prevents the virus from spreading between sick people and medical personnel while also providing additional benefits like sanitation and cleanliness.","PeriodicalId":168942,"journal":{"name":"2023 7th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"192 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133861483","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 : 2023-04-11DOI: 10.1109/ICOEI56765.2023.10125720
L. Srinivasan, A. Jeevika, R. Navina, S. Priyadharshini
Numerous factors might affect a person's stress level, which results in hair loss. Due to variables such as increased employee dominance, job pressure, and work overload, among others employees in IT sectors are more prone to experience stress. Depression, anxiety, somatization, and attention deficit disorder are just a few of the mental health issues that stress can lead to, and even mortality. As a result, it's critical to recognize human stress early so that the proper treatments may be given and tension can be reduced. Numerous studies have been conducted on stress prediction. An extension of the skin, hair is an essentialcomponent of a person's facial beauty. The outcomes of some learning algorithms, like KNN, are superior. Other intelligent methods such as ML algorithms can be used to diagnose the diseases.
{"title":"An Enhanced Stress based Hairfall Detection and Prevention using KNN and Machine Learning Techniques","authors":"L. Srinivasan, A. Jeevika, R. Navina, S. Priyadharshini","doi":"10.1109/ICOEI56765.2023.10125720","DOIUrl":"https://doi.org/10.1109/ICOEI56765.2023.10125720","url":null,"abstract":"Numerous factors might affect a person's stress level, which results in hair loss. Due to variables such as increased employee dominance, job pressure, and work overload, among others employees in IT sectors are more prone to experience stress. Depression, anxiety, somatization, and attention deficit disorder are just a few of the mental health issues that stress can lead to, and even mortality. As a result, it's critical to recognize human stress early so that the proper treatments may be given and tension can be reduced. Numerous studies have been conducted on stress prediction. An extension of the skin, hair is an essentialcomponent of a person's facial beauty. The outcomes of some learning algorithms, like KNN, are superior. Other intelligent methods such as ML algorithms can be used to diagnose the diseases.","PeriodicalId":168942,"journal":{"name":"2023 7th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134545494","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 : 2023-04-11DOI: 10.1109/ICOEI56765.2023.10125980
Rohit R V, V. R., V. R., K. S. Kumar, S. Mathew
As high-wind energy potential regions are less common now; it is becoming more crucial to generate wind energy in places where the wind velocity is light to moderate. This study uses the WERA model to estimate and compare the performances of 4 commercial wind turbines under low power density wind regimes. Wind turbines of 5 kW-rated capacity, from four prominent manufacturers, were considered in the study. The turbine's velocity power response and the site's Rayleigh probability density of wind velocity were used to model these turbines' performance at four typical sites with different average wind speeds in Kerala namely Thiruvananthapuram, Kollam, Kottayam, Pathanamthitta. The turbine's performances are quantified with the energy production and capacity factor at different locations. It was revealed that the turbine's velocity power response is a crucial factor influencing the system performance. Reduction in the cut-in and rated wind speeds seems to improve the system's output in areas with low wind velocity.
{"title":"Realization of Small Wind Turbines for Low-Speed Wind Regions","authors":"Rohit R V, V. R., V. R., K. S. Kumar, S. Mathew","doi":"10.1109/ICOEI56765.2023.10125980","DOIUrl":"https://doi.org/10.1109/ICOEI56765.2023.10125980","url":null,"abstract":"As high-wind energy potential regions are less common now; it is becoming more crucial to generate wind energy in places where the wind velocity is light to moderate. This study uses the WERA model to estimate and compare the performances of 4 commercial wind turbines under low power density wind regimes. Wind turbines of 5 kW-rated capacity, from four prominent manufacturers, were considered in the study. The turbine's velocity power response and the site's Rayleigh probability density of wind velocity were used to model these turbines' performance at four typical sites with different average wind speeds in Kerala namely Thiruvananthapuram, Kollam, Kottayam, Pathanamthitta. The turbine's performances are quantified with the energy production and capacity factor at different locations. It was revealed that the turbine's velocity power response is a crucial factor influencing the system performance. Reduction in the cut-in and rated wind speeds seems to improve the system's output in areas with low wind velocity.","PeriodicalId":168942,"journal":{"name":"2023 7th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133908783","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 : 2023-04-11DOI: 10.1109/ICOEI56765.2023.10125907
N. K. Anushkannan, G. Balde, D. Suganthi, P. M. Pandian, B. Kaur, K. Sagar
Brain tumors, like many other disorders, can cause brain injury through the formation of clots. The MRI picture clearly shows the brain tumor. Healthy brain tissue and brain tumor tissue seem quite similar under the microscope, making it easy to confuse the two. The brain tumor must be properly diagnosed. When assessing brain tumors, segmentation is the gold standard. Brain tumor segmentation is conducted to get around this difficulty by isolating tumor tissue from normal brain tissue, edematous brain tissue, and cerebrospinal fluid. However, this cannot be accomplished until the MRI picture has been median filtered to preserve its edges. An iterative thresholding approach is required to extract the greatest area from the tumor segmentation. After using the watershed method to separate the brain from the rest of the head, the cropping procedure is used to remove any remaining skull tissue. After ALO has improved the settings of ELM, a brain tumor detection system based on the ALO-ELM combination will have been created by identifying the input nodes, hidden layer nodes, and output nodes. The technique outperforms both the ALO and ELM models, with an accuracy of around 98.8%.
{"title":"A Novel Method for Categorizing Brain Tumors using the Hybrid ALO-ELM Model","authors":"N. K. Anushkannan, G. Balde, D. Suganthi, P. M. Pandian, B. Kaur, K. Sagar","doi":"10.1109/ICOEI56765.2023.10125907","DOIUrl":"https://doi.org/10.1109/ICOEI56765.2023.10125907","url":null,"abstract":"Brain tumors, like many other disorders, can cause brain injury through the formation of clots. The MRI picture clearly shows the brain tumor. Healthy brain tissue and brain tumor tissue seem quite similar under the microscope, making it easy to confuse the two. The brain tumor must be properly diagnosed. When assessing brain tumors, segmentation is the gold standard. Brain tumor segmentation is conducted to get around this difficulty by isolating tumor tissue from normal brain tissue, edematous brain tissue, and cerebrospinal fluid. However, this cannot be accomplished until the MRI picture has been median filtered to preserve its edges. An iterative thresholding approach is required to extract the greatest area from the tumor segmentation. After using the watershed method to separate the brain from the rest of the head, the cropping procedure is used to remove any remaining skull tissue. After ALO has improved the settings of ELM, a brain tumor detection system based on the ALO-ELM combination will have been created by identifying the input nodes, hidden layer nodes, and output nodes. The technique outperforms both the ALO and ELM models, with an accuracy of around 98.8%.","PeriodicalId":168942,"journal":{"name":"2023 7th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131014610","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 : 2023-04-11DOI: 10.1109/ICOEI56765.2023.10125854
Kritika Pandey, Sanskruti Patel
In the changing era of AI, Deep Learning plays a vital role. It is basically a part of Machine Learning. The main attribute of Deep Learning is that its models works without any human intervention. As the new technologies taking place day by day Deep Learning models are used in several areas such as in Healthcare, Agriculture, Bioinformatics and so on. This study discusses about one of the deep learning model, namely CNN, its introduction, overview, building blocks of CNN, different architecture of CNN, applications in several Domain areas, issues and challenges where researchers used CNN model successfully.
{"title":"Deep Learning with Convolutional Neural Networks: from Theory to Practice","authors":"Kritika Pandey, Sanskruti Patel","doi":"10.1109/ICOEI56765.2023.10125854","DOIUrl":"https://doi.org/10.1109/ICOEI56765.2023.10125854","url":null,"abstract":"In the changing era of AI, Deep Learning plays a vital role. It is basically a part of Machine Learning. The main attribute of Deep Learning is that its models works without any human intervention. As the new technologies taking place day by day Deep Learning models are used in several areas such as in Healthcare, Agriculture, Bioinformatics and so on. This study discusses about one of the deep learning model, namely CNN, its introduction, overview, building blocks of CNN, different architecture of CNN, applications in several Domain areas, issues and challenges where researchers used CNN model successfully.","PeriodicalId":168942,"journal":{"name":"2023 7th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132096030","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 : 2023-04-11DOI: 10.1109/ICOEI56765.2023.10125676
Taslima Akter Sathi, Md Abid Hasan, M. J. Alam
Helianthus annuus, often known as sunflower, is a crop that is only mildly affected by drought. The agricultural sector of the economy benefits greatly from this. However, various illnesses have imposed a halt on sunflower cultivation over the world. However, many severe diseases will affect plants if corrective measures are not taken sooner. Therefore, it will have a negative impact on sunflower yield, quantity, and quality. Diagnosing a disease by hand can be a time-consuming and difficult process. Object recognition methods that use deep learning are becoming increasingly commonplace today. This study has developed a strategy for identifying diseases in sunflowers. A total of 1428 photos were utilized to complete this task. Images have also been processed using methods like resizing, adjusting contrast, and boosting color. Here, the area of the photos afflicted by the disease is segmented by using k-means clustering, and then retrieved characteristics from those regions. Four deep-learning classifiers were used to complete the classification. For the purpose of comparing classifier quality, four performance evaluation measures are computed. The best-performing classifier overall was a ResNet50 classifier, which had an average accuracy of 97.88% and the lowest accuracy is obtained from Inception V3.
{"title":"SunNet: A Deep Learning Approach to Detect Sunflower Disease","authors":"Taslima Akter Sathi, Md Abid Hasan, M. J. Alam","doi":"10.1109/ICOEI56765.2023.10125676","DOIUrl":"https://doi.org/10.1109/ICOEI56765.2023.10125676","url":null,"abstract":"Helianthus annuus, often known as sunflower, is a crop that is only mildly affected by drought. The agricultural sector of the economy benefits greatly from this. However, various illnesses have imposed a halt on sunflower cultivation over the world. However, many severe diseases will affect plants if corrective measures are not taken sooner. Therefore, it will have a negative impact on sunflower yield, quantity, and quality. Diagnosing a disease by hand can be a time-consuming and difficult process. Object recognition methods that use deep learning are becoming increasingly commonplace today. This study has developed a strategy for identifying diseases in sunflowers. A total of 1428 photos were utilized to complete this task. Images have also been processed using methods like resizing, adjusting contrast, and boosting color. Here, the area of the photos afflicted by the disease is segmented by using k-means clustering, and then retrieved characteristics from those regions. Four deep-learning classifiers were used to complete the classification. For the purpose of comparing classifier quality, four performance evaluation measures are computed. The best-performing classifier overall was a ResNet50 classifier, which had an average accuracy of 97.88% and the lowest accuracy is obtained from Inception V3.","PeriodicalId":168942,"journal":{"name":"2023 7th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128880942","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：