Brain tumors, especially malignant ones, can be life-threatening if not detected and treated early. Identifying benign tumors, such as Meningiomas or Pituitary tumors, enables preventive measures and long-term monitoring to detect any changes in tumor size or behavior. This ensures timely intervention if needed. ML related methods for analyzing types of brain tumors have made significant advancements but brain tumour records often have a mismatch of classes, which means that some kinds of tumours are much less common than others. This may result in models that are biased and work well for the majority of the class but not so well for the minority class. Latest research techniques have focused on deep learning approaches. Identifying brain tumor types using neural networks is a complex but promising approach in medical image analysis. Combining NN with ML techniques is what the suggested model does to get to the exact type of brain tumour. In this regard, the proposed model has extracted the features from the tuned model of VGG-16 and after extracting the features from the network to further classify the stage, the model has applied ensemble voting mechanism.
脑肿瘤，尤其是恶性肿瘤，如果不及早发现和治疗，可能会危及生命。通过识别脑膜瘤或脑垂体瘤等良性肿瘤，可以采取预防措施并进行长期监测，以发现肿瘤大小或行为的任何变化。这样就能确保在必要时进行及时干预。分析脑肿瘤类型的 ML 相关方法已取得重大进展，但脑肿瘤记录往往存在类别不匹配的情况，这意味着某些类型的肿瘤比其他类型的肿瘤要少见得多。这可能会导致模型出现偏差，对大多数类别效果良好，但对少数类别效果不佳。最新的研究技术主要集中在深度学习方法上。使用神经网络识别脑肿瘤类型是医学图像分析中一种复杂但有前景的方法。建议的模型将神经网络与多重学习技术相结合，从而准确识别出脑肿瘤的类型。在这方面，建议的模型从 VGG-16 的调整模型中提取了特征，在从网络中提取特征以进一步分类阶段后，该模型应用了集合投票机制。
{"title":"Voting Based VGG-16 for Feature Selection and Classification of The Brain Tumor Types","authors":"B. Thimma Reddy","doi":"10.52783/jes.3668","DOIUrl":"https://doi.org/10.52783/jes.3668","url":null,"abstract":"Brain tumors, especially malignant ones, can be life-threatening if not detected and treated early. Identifying benign tumors, such as Meningiomas or Pituitary tumors, enables preventive measures and long-term monitoring to detect any changes in tumor size or behavior. This ensures timely intervention if needed. ML related methods for analyzing types of brain tumors have made significant advancements but brain tumour records often have a mismatch of classes, which means that some kinds of tumours are much less common than others. This may result in models that are biased and work well for the majority of the class but not so well for the minority class. Latest research techniques have focused on deep learning approaches. Identifying brain tumor types using neural networks is a complex but promising approach in medical image analysis. Combining NN with ML techniques is what the suggested model does to get to the exact type of brain tumour. In this regard, the proposed model has extracted the features from the tuned model of VGG-16 and after extracting the features from the network to further classify the stage, the model has applied ensemble voting mechanism.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141128613","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}
Grammar correction is crucial for essential documents such as research, business articles, formal papers, but with language evolving every century, some rules for grammar correction are added or changed. There have been created grammar correction online, which has helped most students create academic writing. Some tools focus on correcting the paper by following specific rules; some run an algorithm based on what type of document you are writing. In this paper, we reviewed documents published from 2017 up to 2021 related to grammar correction and Grammar error detection, with numerous Natural Language Processing and models provided by past researchers, which may aid this paper towards a solution on creating a grammar correction tool.
{"title":"Natural Language Processing of Grammar Checker Tools for Academic Writing: A Systematic Literature Review","authors":"Paulo Miguel A. Cano","doi":"10.52783/jes.3611","DOIUrl":"https://doi.org/10.52783/jes.3611","url":null,"abstract":"Grammar correction is crucial for essential documents such as research, business articles, formal papers, but with language evolving every century, some rules for grammar correction are added or changed. There have been created grammar correction online, which has helped most students create academic writing. Some tools focus on correcting the paper by following specific rules; some run an algorithm based on what type of document you are writing. In this paper, we reviewed documents published from 2017 up to 2021 related to grammar correction and Grammar error detection, with numerous Natural Language Processing and models provided by past researchers, which may aid this paper towards a solution on creating a grammar correction tool.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140982390","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}
Due to current lifestyle most of the peoples suffering from numerous diseases, heart disease, diabetes, obesity, etc. diabetes is one of the disease is found at an every age group of peoples nowadays. Here discussion is based on diabetes disease detection at an early stage and finding the pattern or recognizing diseases in patients. Artificial intelligence techniques very popular in health care sector, AI based techniques such as machine learning and deep learning techniques are having very tremendous growth in health care and information security sectors for providing best results than traditional techniques. In this paper, we discuss comparative performance analysis between different machine learning techniques among them random forest classifier gives best performance than other techniques.
{"title":"Improving Diabetes Detection Using Machine Learning Random Forest Algorithm","authors":"Amit Dubey","doi":"10.52783/jes.3674","DOIUrl":"https://doi.org/10.52783/jes.3674","url":null,"abstract":"Due to current lifestyle most of the peoples suffering from numerous diseases, heart disease, diabetes, obesity, etc. diabetes is one of the disease is found at an every age group of peoples nowadays. Here discussion is based on diabetes disease detection at an early stage and finding the pattern or recognizing diseases in patients. Artificial intelligence techniques very popular in health care sector, AI based techniques such as machine learning and deep learning techniques are having very tremendous growth in health care and information security sectors for providing best results than traditional techniques. In this paper, we discuss comparative performance analysis between different machine learning techniques among them random forest classifier gives best performance than other techniques.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141128660","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}
Neurodevelopmental issues such as Autism spectrum disorder (ASD) and Attention deficit hyperactive disorders (ADHD) are quite prevalent in small children detecting and differentiating them at a very early stage is necessary for the future of the affected children and their parents or care giver. This may require 24 hours of surveillance in level 3 cases in which the affected may experience meltdown situation. It is well known by clinical psychologist that sudden meltdowns are common in autistic children, which makes the situation difficult for the parents or care givers and is also a physical threat to the affected children and people around them as they most likely injure themselves. Research has shown that children diagnosed with autism spectrum disorder display specific behaviors that allow us to predict their violent outbursts. Our aim is to develop a CNN-based system that can identify these kinds of behaviors using real time camera. In our study, we are trying to make a model that can perform Human Activity Recognition (HAR) in real time. Based on the available training data we have trained our model on a few common pre meltdown actions or gestures creating two classes of dataset. but in future we may take huge number of video frame of different types of gestures (using HMBD51 datasets) to train the algorithm so that it can practically identify the situation in real time and alarm the caregiver before they enter the meltdown situation, this will save the patients from self-inflicted injuries and panic attacks not just in the above mentioned two cases but many other brain disorders. The present model has achieved a training accuracy of 100% ,a satisfactory FPS(Frame processed per Second) and the validation accuracy is slightly increasing in each epoch.
{"title":"Predicting meltdown situation in Autism and ADHD in real-time through camera using deep learning algorithm.","authors":"Sumbul Alam","doi":"10.52783/jes.3658","DOIUrl":"https://doi.org/10.52783/jes.3658","url":null,"abstract":"Neurodevelopmental issues such as Autism spectrum disorder (ASD) and Attention deficit hyperactive disorders (ADHD) are quite prevalent in small children detecting and differentiating them at a very early stage is necessary for the future of the affected children and their parents or care giver. This may require 24 hours of surveillance in level 3 cases in which the affected may experience meltdown situation. It is well known by clinical psychologist that sudden meltdowns are common in autistic children, which makes the situation difficult for the parents or care givers and is also a physical threat to the affected children and people around them as they most likely injure themselves. Research has shown that children diagnosed with autism spectrum disorder display specific behaviors that allow us to predict their violent outbursts. Our aim is to develop a CNN-based system that can identify these kinds of behaviors using real time camera. \u0000In our study, we are trying to make a model that can perform Human Activity Recognition (HAR) in real time. Based on the available training data we have trained our model on a few common pre meltdown actions or gestures creating two classes of dataset. but in future we may take huge number of video frame of different types of gestures (using HMBD51 datasets) to train the algorithm so that it can practically identify the situation in real time and alarm the caregiver before they enter the meltdown situation, this will save the patients from self-inflicted injuries and panic attacks not just in the above mentioned two cases but many other brain disorders. The present model has achieved a training accuracy of 100% ,a satisfactory FPS(Frame processed per Second) and the validation accuracy is slightly increasing in each epoch.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141128633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The rapid growth of smart grids has ushered in new opportunities for enhancing energy efficiency through advanced control strategies. This paper explores the potential of reinforcement learning (RL) to improve the energy efficiency of smart grids, focusing on RL-based control strategies. We begin with a comprehensive review of existing technologies, examining a range of architectures and methods used to implement RL in smart grid environments. This review highlights both the benefits and limitations of these approaches, offering a balanced analysis of their effectiveness in addressing the unique challenges of smart grid management. Following this review, we propose a new RL-based control strategy designed to optimize energy efficiency. Our approach leverages the strengths of state-of-the-art RL algorithms while addressing common shortcomings identified in previous work. We evaluate our strategy using a detailed simulation that reflects real-world smart grid scenarios. The results demonstrate significant improvements in energy efficiency compared to traditional control methods. Finally, we discuss best practices for applying RL in smart grids, providing guidelines for researchers and practitioners seeking to implement these strategies. Our recommendations focus on maximizing energy efficiency while ensuring stability and scalability in smart grid systems. Through this work, we aim to contribute to the ongoing development of sustainable and efficient smart grid technologies.
{"title":"Enhancing Energy Efficiency in Smart Grids through Reinforcement Learning-Based Control Strategies","authors":"Nilam B. Panchal","doi":"10.52783/jes.3660","DOIUrl":"https://doi.org/10.52783/jes.3660","url":null,"abstract":"The rapid growth of smart grids has ushered in new opportunities for enhancing energy efficiency through advanced control strategies. This paper explores the potential of reinforcement learning (RL) to improve the energy efficiency of smart grids, focusing on RL-based control strategies. We begin with a comprehensive review of existing technologies, examining a range of architectures and methods used to implement RL in smart grid environments. This review highlights both the benefits and limitations of these approaches, offering a balanced analysis of their effectiveness in addressing the unique challenges of smart grid management. Following this review, we propose a new RL-based control strategy designed to optimize energy efficiency. Our approach leverages the strengths of state-of-the-art RL algorithms while addressing common shortcomings identified in previous work. We evaluate our strategy using a detailed simulation that reflects real-world smart grid scenarios. The results demonstrate significant improvements in energy efficiency compared to traditional control methods. Finally, we discuss best practices for applying RL in smart grids, providing guidelines for researchers and practitioners seeking to implement these strategies. Our recommendations focus on maximizing energy efficiency while ensuring stability and scalability in smart grid systems. Through this work, we aim to contribute to the ongoing development of sustainable and efficient smart grid technologies.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141128480","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}
Syam Sundar, Dr. B. Chaitanya Krishna, Dr. B. Chaitanya
Finding small things quickly and correctly in remote sensing pictures (RSI) is very hard because you need to use strong feature extraction and complex deep neural networks need a lot of computing power. The study introduces SuperYOLO, a novel approach to identifying objects that seeks to achieve a good combination of speed and accuracy in RSI analysis. SuperYOLO uses a multimodal data fusion method to combine information from different data sources in a way that makes it better at finding small items in RSI. This multimodal fusion (MF) process is both symmetric and compact, which makes it easy to combine data. SuperYOLO has an enhanced super-resolution (SR) learning branch in addition to MF. This SR branch lets the model make high-resolution (HR) feature representations, which lets it tell small items apart from the background when the input is low-resolution (LR). This makes recognition much more accurate without adding too much work to the computer. One great thing about SuperYOLO is that the SR branch is only used during training and is thrown away during inference. This method reduces the need for extra computing power, making sure that object recognition works quickly and efficiently. When tested on the well-known VEDAI RS dataset, SuperYOLO does better at accuracy than cutting-edge models like YOLOv5l, YOLOv5x, and YOLOrs. Additionally, SuperYOLO gets this level of accuracy while greatly lowering the model's parameter size and processing needs. Compared to YOLOv5x, SuperYOLO has 18 times fewer parameters and 3.8 times fewer GFLOPs. To sum up, SuperYOLO makes a strong case for choosing between accuracy and speed when it comes to finding small objects in RSI. The model does a better job than other options because it combines multimodal data fusion with assisted SR learning in a way that makes it more efficient and less complicated to use. This big step forward could have big effects in areas like remote sensing, where finding small things accurately is important for many jobs.
{"title":"Superyolo: Super Resolution Assisted Object Detection in Multimodal Remote Sensing Imagery","authors":"Syam Sundar, Dr. B. Chaitanya Krishna, Dr. B. Chaitanya","doi":"10.52783/jes.3664","DOIUrl":"https://doi.org/10.52783/jes.3664","url":null,"abstract":"Finding small things quickly and correctly in remote sensing pictures (RSI) is very hard because you need to use strong feature extraction and complex deep neural networks need a lot of computing power. The study introduces SuperYOLO, a novel approach to identifying objects that seeks to achieve a good combination of speed and accuracy in RSI analysis. SuperYOLO uses a multimodal data fusion method to combine information from different data sources in a way that makes it better at finding small items in RSI. This multimodal fusion (MF) process is both symmetric and compact, which makes it easy to combine data. SuperYOLO has an enhanced super-resolution (SR) learning branch in addition to MF. This SR branch lets the model make high-resolution (HR) feature representations, which lets it tell small items apart from the background when the input is low-resolution (LR). This makes recognition much more accurate without adding too much work to the computer. One great thing about SuperYOLO is that the SR branch is only used during training and is thrown away during inference. This method reduces the need for extra computing power, making sure that object recognition works quickly and efficiently. When tested on the well-known VEDAI RS dataset, SuperYOLO does better at accuracy than cutting-edge models like YOLOv5l, YOLOv5x, and YOLOrs. Additionally, SuperYOLO gets this level of accuracy while greatly lowering the model's parameter size and processing needs. Compared to YOLOv5x, SuperYOLO has 18 times fewer parameters and 3.8 times fewer GFLOPs. To sum up, SuperYOLO makes a strong case for choosing between accuracy and speed when it comes to finding small objects in RSI. The model does a better job than other options because it combines multimodal data fusion with assisted SR learning in a way that makes it more efficient and less complicated to use. This big step forward could have big effects in areas like remote sensing, where finding small things accurately is important for many jobs.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141128552","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}
Digitizing handwritten documents and enabling efficient information processing and retrieval require systems that can recognize handwritten characters. This research offers a unique approach for handwritten character detection using state-of-the-art machine learning algorithms. The proposed technique automatically extracts discriminative features from photos of handwritten characters using convolutional neural networks (CNNs). These attributes are then used by a classifier to determine which characters are related. The dataset used for training and assessment is made up of a large collection of handwritten characters gathered under various writing styles, sizes, and orientations in order to guarantee the durability and generalization power of the model. To enhance its quality and diversity, the training data is put through a rigorous preparation procedure that includes picture augmentation, noise removal, and normalization. The studies' results demonstrate how well and precisely the proposed system can recognize handwritten characters in a range of languages and writing styles. The system performs competitively compared to state-of-the-art methods and demonstrates robustness against variations in handwriting style and quality. Furthermore, the system has potential in terms of efficiency and scalability, making it suitable for real-time applications such as document digitalization, handwritten word recognition in electronic devices, and automatic form processing.
{"title":"Handwritten Character Recognition System","authors":"Tirapathi Reddy, Elangovan Guruva, Reddy","doi":"10.52783/jes.3553","DOIUrl":"https://doi.org/10.52783/jes.3553","url":null,"abstract":"Digitizing handwritten documents and enabling efficient information processing and retrieval require systems that can recognize handwritten characters. This research offers a unique approach for handwritten character detection using state-of-the-art machine learning algorithms. The proposed technique automatically extracts discriminative features from photos of handwritten characters using convolutional neural networks (CNNs). These attributes are then used by a classifier to determine which characters are related. The dataset used for training and assessment is made up of a large collection of handwritten characters gathered under various writing styles, sizes, and orientations in order to guarantee the durability and generalization power of the model. To enhance its quality and diversity, the training data is put through a rigorous preparation procedure that includes picture augmentation, noise removal, and normalization. The studies' results demonstrate how well and precisely the proposed system can recognize handwritten characters in a range of languages and writing styles. The system performs competitively compared to state-of-the-art methods and demonstrates robustness against variations in handwriting style and quality. Furthermore, the system has potential in terms of efficiency and scalability, making it suitable for real-time applications such as document digitalization, handwritten word recognition in electronic devices, and automatic form processing.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141129090","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}
With the widespread popularity of the internet and smart electronic devices in China, the construction of MOOC quality courses in Chinese universities has developed rapidly with significant achievements. However, in the swift advancement of MOOC quality course construction in Chinese universities, some problems have gradually surfaced. This paper takes the “Chinese University MOOC” platform course “Performance and Appreciation of Chinese National Female Soprano Works” as a research case to discuss the existing problems in the construction of MOOC quality courses in Chinese universities. The results indicate that low registration numbers of learners, a student structure dominated by students from the host university, low participation in tests and assignments, and unsatisfactory interactive communication are the main existing problems. The primary causes of these issues include the focus of MOOC quality course construction primarily on students from the host university, neglecting social learners; an emphasis on construction over management, neglecting the organization and management of the teaching process; and excessive reliance on the MOOC platform for course promotion. Based on this, optimization suggestions are proposed, mainly to enhance the integration of MOOC course content, strengthen the organization and management of the MOOC course teaching process, innovate MOOC teaching models combining online and offline methods, and promote MOOC courses through multiple pathways and channels.
{"title":"Problems and Optimization Strategies in the Construction of MOOC Quality Courses in Universities under the Perspective of Online Education","authors":"Han Zhou","doi":"10.52783/jes.3531","DOIUrl":"https://doi.org/10.52783/jes.3531","url":null,"abstract":"With the widespread popularity of the internet and smart electronic devices in China, the construction of MOOC quality courses in Chinese universities has developed rapidly with significant achievements. However, in the swift advancement of MOOC quality course construction in Chinese universities, some problems have gradually surfaced. This paper takes the “Chinese University MOOC” platform course “Performance and Appreciation of Chinese National Female Soprano Works” as a research case to discuss the existing problems in the construction of MOOC quality courses in Chinese universities. The results indicate that low registration numbers of learners, a student structure dominated by students from the host university, low participation in tests and assignments, and unsatisfactory interactive communication are the main existing problems. The primary causes of these issues include the focus of MOOC quality course construction primarily on students from the host university, neglecting social learners; an emphasis on construction over management, neglecting the organization and management of the teaching process; and excessive reliance on the MOOC platform for course promotion. Based on this, optimization suggestions are proposed, mainly to enhance the integration of MOOC course content, strengthen the organization and management of the MOOC course teaching process, innovate MOOC teaching models combining online and offline methods, and promote MOOC courses through multiple pathways and channels.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141129143","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The research examines the marine fishing sector and highlights the urgent need for an electronic monitoring system designed to meet the unique needs of fishermen. The initiative’s motive is emphasized in the paper, which highlights how cutting-edge technology like object detection and tracking could revolutionize the fishing industry when integrated into an electronic monitoring framework. The research proposes an electronic monitoring system based on YOLOv8 (You Only Look Once) as a comprehensive solution to address current issues, such as out-of-date data collection methods and a lack of guiding applications. The review of the literature, which highlights gaps in the current fishing applications, is an important component of the paper. The research is geared towards training an object detection model on the fishnet dataset. The focus is on data processing created by an electronic monitoring system to rectify the current state of the fishing industry’s deficiencies.
{"title":"YOLOv8 based fish detection and classification on fishnet dataset","authors":"Omkar Mahajan","doi":"10.52783/jes.3552","DOIUrl":"https://doi.org/10.52783/jes.3552","url":null,"abstract":"The research examines the marine fishing sector and highlights the urgent need for an electronic monitoring system designed to meet the unique needs of fishermen. The initiative’s motive is emphasized in the paper, which highlights how cutting-edge technology like object detection and tracking could revolutionize the fishing industry when integrated into an electronic monitoring framework. The research proposes an electronic monitoring system based on YOLOv8 (You Only Look Once) as a comprehensive solution to address current issues, such as out-of-date data collection methods and a lack of guiding applications. The review of the literature, which highlights gaps in the current fishing applications, is an important component of the paper. The research is geared towards training an object detection model on the fishnet dataset. The focus is on data processing created by an electronic monitoring system to rectify the current state of the fishing industry’s deficiencies.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141129271","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}
Unmanned aerial vehicles (UAVs), also known as drones, are widely used in real-time applications such as remote sensing, disaster management and recovery, logistics applications, military operations, search and rescue systems, law enforcement operations, and crowd monitoring and controlling due to their low cost, quick processing, and high-resolution photos. Furthermore, drones reduce the risk of threats such as terrorism, disease transmission, temperature disruptions, crop pests, and criminal activities. As a result, the primary purpose of this paper is to present an extensive examination of UAV-based surveillance systems to provide insight into the opportunities, challenges, techniques, and future trends of drones. The paper discusses typical picture preprocessing approaches for drones, as well as prominent one and two-stage deep Learning algorithms used by researchers to detect objects captured by drone cameras. This paper also includes a useful list for researchers of online datasets that include photographs acquired using drone cameras. In addition, the paper includes a comparative examination of recent UAV-based imaging applications, demonstrating the purpose, description, findings, and limitations of each application. Finally, this paper discusses potential research trends and difficulties associated with the utilization of drones.
{"title":"A Survey on the Use of Unmanned Aerial Vehicles (UAVs) in Monitoring Applications","authors":"Ayman Yafoz","doi":"10.52783/jes.3547","DOIUrl":"https://doi.org/10.52783/jes.3547","url":null,"abstract":"Unmanned aerial vehicles (UAVs), also known as drones, are widely used in real-time applications such as remote sensing, disaster management and recovery, logistics applications, military operations, search and rescue systems, law enforcement operations, and crowd monitoring and controlling due to their low cost, quick processing, and high-resolution photos. Furthermore, drones reduce the risk of threats such as terrorism, disease transmission, temperature disruptions, crop pests, and criminal activities. As a result, the primary purpose of this paper is to present an extensive examination of UAV-based surveillance systems to provide insight into the opportunities, challenges, techniques, and future trends of drones. The paper discusses typical picture preprocessing approaches for drones, as well as prominent one and two-stage deep Learning algorithms used by researchers to detect objects captured by drone cameras. This paper also includes a useful list for researchers of online datasets that include photographs acquired using drone cameras. In addition, the paper includes a comparative examination of recent UAV-based imaging applications, demonstrating the purpose, description, findings, and limitations of each application. Finally, this paper discusses potential research trends and difficulties associated with the utilization of drones.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141129194","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：