INTRODUCTION: Medical imaging techniques are used to analyze the inner workings of the human body. In today's scientific world, medical image analysis is the most demanding and rising discipline, with brain tumor being the most deadly and destructive kind of malignancy. A brain tumor is an abnormal growth of cells within the skull that disrupts normal brain function by damaging neighboring cells. Brain tumors are regarded as one of the most dangerous, visible, and potentially fatal illnesses in the world. Because of the fast proliferation of tumor cells, brain tumors kill thousands of people each year all over the world. To save the lives of thousands of individuals worldwide, prompt analysis and automated identification of brain tumors are essential. OBJECTIVES: To design a enhanced deep learning model for brain tumor detection and classification from MRI analysis. METHODS: The proposed models Densenet-121, Resnet-101 Mobilenet-V2 is used to perform the task of Brain tumor detection for multi- class classification. RESULTS: The proposed models achieved an accuracy of up to 99% in our evaluations, and when compared to competing models, they yield superior results. CONCLUSION: The MRI image collection has been used to train deep learning models. The experimental findings show that the Densnet-121 model delivers the highest accuracy (99%) compared to other models. The system will have significant applications in the medical field. The presence or absence of a tumour can be ascertained using the proposed method.
{"title":"Brain Tumor Detection based on Multiple Deep Learning Models for MRI Images","authors":"Gokapay Dilip Kumar, S. Mohanty","doi":"10.4108/eetpht.10.5499","DOIUrl":"https://doi.org/10.4108/eetpht.10.5499","url":null,"abstract":"INTRODUCTION: Medical imaging techniques are used to analyze the inner workings of the human body. In today's scientific world, medical image analysis is the most demanding and rising discipline, with brain tumor being the most deadly and destructive kind of malignancy. A brain tumor is an abnormal growth of cells within the skull that disrupts normal brain function by damaging neighboring cells. Brain tumors are regarded as one of the most dangerous, visible, and potentially fatal illnesses in the world. Because of the fast proliferation of tumor cells, brain tumors kill thousands of people each year all over the world. To save the lives of thousands of individuals worldwide, prompt analysis and automated identification of brain tumors are essential. \u0000OBJECTIVES: To design a enhanced deep learning model for brain tumor detection and classification from MRI analysis. \u0000METHODS: The proposed models Densenet-121, Resnet-101 Mobilenet-V2 is used to perform the task of Brain tumor detection for multi- class classification. \u0000RESULTS: The proposed models achieved an accuracy of up to 99% in our evaluations, and when compared to competing models, they yield superior results. \u0000CONCLUSION: The MRI image collection has been used to train deep learning models. The experimental findings show that the Densnet-121 model delivers the highest accuracy (99%) compared to other models. The system will have significant applications in the medical field. The presence or absence of a tumour can be ascertained using the proposed method.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"163 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140222780","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}
A. R. Deepa, M. Chaurasia, Peram Sai, Harsha Vardhan, Ganishetti Ritwika, Mamillapalli Samanth Kumar, Yaswanth Chowdary Nettm
INTRODUCTION: Over the past several years analysis of image has moved from larger system to pervasive portable devices. For example, in pervasive biomedical systems like PACS-Picture achieving and Communication system, computing is the main element. Image processing application for biomedical diagnosis needs efficient and fast algorithms and architecture for their functionality. Future pervasive systems designed for biomedical application should provide computational efficiency and portability. The discrete wavelet transform (DWT) designed in on-chip been used in several applications like data, audio signal processing and machine learning. OBJECTIVES: The conventional convolution based scheme is easy to implement but occupies more memory , power and delay. The conventional lifting based architecture has multiplier blocks which increase the critical delay. Designing the wavelet transform without multiplier is a effective task especially for the 2-D image analysis. Without multiplier Daubechies wavelet implementation in forward and inverse transforms may find efficient. The objective of the work is on obtaining low power and less delay architecture. METHODS: The proposed lifting scheme for two dimensional architecture reduces critical path through multiplier less and provides low power, area and high throughput. The proposed multiplier is delay efficient. RESULTS: The architecture is Multiplier less in the predict and update stage and the implementation carried out in FPGA by the use of Quartus II 9.1 and it is found that there is reduction in consumption of power at approximately 56%. There is reduction in delay due to multiplier less architecture. CONCLUSION: multiplier less architecture provides less delay and low power. The power observed is in milliwatts and suitable for high speed application due to low critical path delay.
简介：在过去几年中，图像分析已从大型系统转向普及型便携设备。例如，在 PACS（图像实现与通信系统）等普及型生物医学系统中，计算是主要元素。用于生物医学诊断的图像处理应用需要高效、快速的算法和架构来实现其功能。为生物医学应用设计的未来普适系统应提供计算效率和可移植性。在芯片上设计的离散小波变换（DWT）已被用于数据、音频信号处理和机器学习等多个应用领域。目标：传统的基于卷积的方案易于实现，但占用更多内存、功耗和延迟。传统的基于提升的架构有乘法器块，这会增加临界延迟。设计不带乘法器的小波变换是一项有效的任务，尤其是在二维图像分析中。不使用乘法器的多贝希斯小波实现正向和反向变换可能会很有效。这项工作的目标是获得低功耗、低延迟的架构。方法：针对二维架构提出的提升方案通过减少乘法器来减少关键路径，并提供低功耗、低面积和高吞吐量。提议的乘法器具有延迟效率。结果：该架构在预测和更新阶段减少了乘法器，并使用 Quartus II 9.1 在 FPGA 中进行了实现，发现功耗降低了约 56%。由于采用了少乘法器架构，延迟也有所减少。结论：少乘法器架构提供了更少的延迟和更低的功耗。观察到的功耗单位为毫瓦，由于关键路径延迟低，适合高速应用。
{"title":"An Integrated Thresholding and Morphological Process with Histogram-based Method for Brain Tumor Analysis and MRI Tumor Detection","authors":"A. R. Deepa, M. Chaurasia, Peram Sai, Harsha Vardhan, Ganishetti Ritwika, Mamillapalli Samanth Kumar, Yaswanth Chowdary Nettm","doi":"10.4108/eetpht.10.5498","DOIUrl":"https://doi.org/10.4108/eetpht.10.5498","url":null,"abstract":"INTRODUCTION: Over the past several years analysis of image has moved from larger system to pervasive portable devices. For example, in pervasive biomedical systems like PACS-Picture achieving and Communication system, computing is the main element. Image processing application for biomedical diagnosis needs efficient and fast algorithms and architecture for their functionality. Future pervasive systems designed for biomedical application should provide computational efficiency and portability. The discrete wavelet transform (DWT) designed in on-chip been used in several applications like data, audio signal processing and machine learning. \u0000OBJECTIVES: The conventional convolution based scheme is easy to implement but occupies more memory , power and delay. The conventional lifting based architecture has multiplier blocks which increase the critical delay. Designing the wavelet transform without multiplier is a effective task especially for the 2-D image analysis. Without multiplier Daubechies wavelet implementation in forward and inverse transforms may find efficient. The objective of the work is on obtaining low power and less delay architecture. \u0000METHODS: The proposed lifting scheme for two dimensional architecture reduces critical path through multiplier less and provides low power, area and high throughput. The proposed multiplier is delay efficient. \u0000RESULTS: The architecture is Multiplier less in the predict and update stage and the implementation carried out in FPGA by the use of Quartus II 9.1 and it is found that there is reduction in consumption of power at approximately 56%. There is reduction in delay due to multiplier less architecture. \u0000CONCLUSION: multiplier less architecture provides less delay and low power. The power observed is in milliwatts and suitable for high speed application due to low critical path delay.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"16 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140223494","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}
INTRODUCTION: Alzheimer’s disease (AD), which is also a pervasive form of dementia primarily common among the elderly, causes progressive brain damage, which might lead to memory loss, language impairment, with cognitive decline. This research proposed a solution that leveraged wearable technology's potential for computer-aided diagnosis. This wearable device, which looks like a pendant, integrates a panic button to notify the closed ones during an emergency. OBJECTIVES: The primary objective is to effectively scrutinise and implement the wearable device for computer-aided diagnosis in AD. Specifically, this device aims to provide timely alerts to family members during emergencies and other symptoms. METHODS: The proposed system is developed with the help of a microcontroller and integrates the Android Studio. This device, which resembles a pendant, contains a panic button that connects to a mobile application which receives notifications. RESULTS: The system successfully achieved its objectives by providing timely alerts with accurate cognitive support for AD patients. The wearable device developed along with the mobile application, with the help of a microcontroller and Android Studio, contributed to the overall well-being of patients with AD. CONCLUSION: This research introduced a very innovative and promising solution for improving the lives of individuals with AD through this wearable device and mobile application. By addressing these challenges, the system demonstrated its true potential for enhancing the quality of life for individuals with dementia.
简介：阿尔茨海默病（AD）也是一种普遍的痴呆症，主要常见于老年人，会造成渐进性脑损伤，可能导致记忆力减退、语言障碍和认知能力下降。这项研究提出了一种解决方案，利用可穿戴技术在计算机辅助诊断方面的潜力。这种可穿戴设备看起来像一个吊坠，集成了一个紧急按钮，可在紧急情况下通知身边的人。目标：主要目的是有效检查和实施用于 AD 计算机辅助诊断的可穿戴设备。具体来说，该设备旨在在出现紧急情况和其他症状时及时向家人发出警报。方法：建议的系统是在微控制器的帮助下开发的，并集成了 Android Studio。该设备类似于一个吊坠，包含一个紧急按钮，可连接到一个接收通知的移动应用程序。结果：该系统成功实现了目标，为注意力缺失症患者提供了及时警报和准确的认知支持。在微控制器和 Android Studio 的帮助下，开发的可穿戴设备和移动应用程序为注意力缺失症患者的整体健康做出了贡献。结论：这项研究通过可穿戴设备和移动应用程序，为改善注意力缺失症患者的生活提出了一个极具创新性且前景广阔的解决方案。通过应对这些挑战，该系统展示了其在提高痴呆症患者生活质量方面的真正潜力。
{"title":"A Wearable Device for Assistance of Alzheimer’s disease with Computer Aided Diagnosis","authors":"Sarita, Tanupriya Choudhury, Saurabh Mukherjee, Chiranjit Dutta, Aviral Sharma, Ayan Sar","doi":"10.4108/eetpht.10.5483","DOIUrl":"https://doi.org/10.4108/eetpht.10.5483","url":null,"abstract":"INTRODUCTION: Alzheimer’s disease (AD), which is also a pervasive form of dementia primarily common among the elderly, causes progressive brain damage, which might lead to memory loss, language impairment, with cognitive decline. This research proposed a solution that leveraged wearable technology's potential for computer-aided diagnosis. This wearable device, which looks like a pendant, integrates a panic button to notify the closed ones during an emergency. \u0000OBJECTIVES: The primary objective is to effectively scrutinise and implement the wearable device for computer-aided diagnosis in AD. Specifically, this device aims to provide timely alerts to family members during emergencies and other symptoms. \u0000METHODS: The proposed system is developed with the help of a microcontroller and integrates the Android Studio. This device, which resembles a pendant, contains a panic button that connects to a mobile application which receives notifications. \u0000RESULTS: The system successfully achieved its objectives by providing timely alerts with accurate cognitive support for AD patients. The wearable device developed along with the mobile application, with the help of a microcontroller and Android Studio, contributed to the overall well-being of patients with AD. \u0000CONCLUSION: This research introduced a very innovative and promising solution for improving the lives of individuals with AD through this wearable device and mobile application. By addressing these challenges, the system demonstrated its true potential for enhancing the quality of life for individuals with dementia.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"362 22","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140228027","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}
Srinivas Kolli, Muniyandy Elangovan, M. Vamsikrishna, Pramoda Patro
INTRODUCTION: Although decades of experimental and clinical research have shed a lot of light on the pathogenesis of Alzheimer's disease (AD), there are still a lot of questions that need to be answered. The current proliferation of open data-sharing initiatives that collect clinical, routine, and biological data from individuals with Alzheimer's disease presents a potentially boundless wealth of information about a condition. METHODS: While it is possible to hypothesize that there is no comprehensive collection of puzzle pieces, there is currently a proliferation of such initiatives. This abundance of data surpasses the cognitive capacity of humans to comprehend and interpret fully. In addition, the psychophysiology mechanisms underlying the whole biological continuum of AD may be investigated by combining Big Data collected from multi-omics studies. In this regard, Artificial Intelligence (AI) offers a robust toolbox for evaluating large, complex data sets, which might be used to gain a deeper understanding of AD. This review looks at the recent findings in the field of AD research and the possible obstacles that AI may face in the future. RESULTS: This research explores the use of CAD tools for diagnosing AD and the potential use of AI in healthcare settings. In particular, investigate the feasibility of using AI to stratify patients according to their risk of developing AD and to forecast which of these patients would benefit most from receiving personalized therapies. CONCLUSION: To improve these, fuzzy membership functions and rule bases, fuzzy models are trained using fuzzy logic and machine learning.
{"title":"AI Fuzzy Based Prediction and Prorogation of Alzheimer's Cancer","authors":"Srinivas Kolli, Muniyandy Elangovan, M. Vamsikrishna, Pramoda Patro","doi":"10.4108/eetpht.10.5478","DOIUrl":"https://doi.org/10.4108/eetpht.10.5478","url":null,"abstract":"INTRODUCTION: Although decades of experimental and clinical research have shed a lot of light on the pathogenesis of Alzheimer's disease (AD), there are still a lot of questions that need to be answered. The current proliferation of open data-sharing initiatives that collect clinical, routine, and biological data from individuals with Alzheimer's disease presents a potentially boundless wealth of information about a condition. \u0000METHODS: While it is possible to hypothesize that there is no comprehensive collection of puzzle pieces, there is currently a proliferation of such initiatives. This abundance of data surpasses the cognitive capacity of humans to comprehend and interpret fully. In addition, the psychophysiology mechanisms underlying the whole biological continuum of AD may be investigated by combining Big Data collected from multi-omics studies. In this regard, Artificial Intelligence (AI) offers a robust toolbox for evaluating large, complex data sets, which might be used to gain a deeper understanding of AD. This review looks at the recent findings in the field of AD research and the possible obstacles that AI may face in the future. \u0000RESULTS: This research explores the use of CAD tools for diagnosing AD and the potential use of AI in healthcare settings. In particular, investigate the feasibility of using AI to stratify patients according to their risk of developing AD and to forecast which of these patients would benefit most from receiving personalized therapies. \u0000CONCLUSION: To improve these, fuzzy membership functions and rule bases, fuzzy models are trained using fuzzy logic and machine learning.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"343 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140228069","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}
Irfan Sadiq Rahat, Mohammed Altaf Ahmed, Donepudi Rohini, A. Manjula, Hritwik Ghosh, Abdus Sobur
INTRODUCTION: Deep Learning has significantly impacted various domains, including medical imaging and diagnostics, by enabling accurate classification tasks. This research focuses on leveraging deep learning models to automate the classification of different blood cell types, thus advancing hematology practices. OBJECTIVES: The primary objective of this study is to evaluate the performance of five deep learning models - ResNet50, AlexNet, MobileNetV2, VGG16, and VGG19 - in accurately discerning and classifying distinct blood cell categories: Eosinophils, Lymphocytes, Monocytes, and Neutrophils. The study aims to identify the most effective model for automating hematology processes. METHODS: A comprehensive dataset containing approximately 8,500 augmented images of the four blood cell types is utilized for training and evaluation. The deep learning models undergo extensive training using this dataset. Performance assessment is conducted using various metrics including accuracy, precision, recall, and F1-score. RESULTS: The VGG19 model emerges as the top performer, achieving an impressive accuracy of 99% with near-perfect precision and recall across all cell types. This indicates its robustness and effectiveness in automated blood cell classification tasks. Other models, while demonstrating competence, do not match the performance levels attained by VGG19. CONCLUSION: This research underscores the potential of deep learning in automating and enhancing the accuracy of blood cell classification, thereby addressing the labor-intensive and error-prone nature of traditional methods in hematology. The superiority of the VGG19 model highlights its suitability for practical implementation in real-world scenarios. However, further investigation is warranted to comprehend model performance variations and ensure generalization to unseen data. Overall, this study serves as a crucial step towards broader applications of artificial intelligence in medical diagnostics, particularly in the realm of automated hematology, fostering advancements in healthcare technology.
{"title":"A Step Towards Automated Haematology: DL Models for Blood Cell Detection and Classification","authors":"Irfan Sadiq Rahat, Mohammed Altaf Ahmed, Donepudi Rohini, A. Manjula, Hritwik Ghosh, Abdus Sobur","doi":"10.4108/eetpht.10.5477","DOIUrl":"https://doi.org/10.4108/eetpht.10.5477","url":null,"abstract":"INTRODUCTION: Deep Learning has significantly impacted various domains, including medical imaging and diagnostics, by enabling accurate classification tasks. This research focuses on leveraging deep learning models to automate the classification of different blood cell types, thus advancing hematology practices. \u0000OBJECTIVES: The primary objective of this study is to evaluate the performance of five deep learning models - ResNet50, AlexNet, MobileNetV2, VGG16, and VGG19 - in accurately discerning and classifying distinct blood cell categories: Eosinophils, Lymphocytes, Monocytes, and Neutrophils. The study aims to identify the most effective model for automating hematology processes. \u0000METHODS: A comprehensive dataset containing approximately 8,500 augmented images of the four blood cell types is utilized for training and evaluation. The deep learning models undergo extensive training using this dataset. Performance assessment is conducted using various metrics including accuracy, precision, recall, and F1-score. \u0000RESULTS: The VGG19 model emerges as the top performer, achieving an impressive accuracy of 99% with near-perfect precision and recall across all cell types. This indicates its robustness and effectiveness in automated blood cell classification tasks. Other models, while demonstrating competence, do not match the performance levels attained by VGG19. \u0000CONCLUSION: This research underscores the potential of deep learning in automating and enhancing the accuracy of blood cell classification, thereby addressing the labor-intensive and error-prone nature of traditional methods in hematology. The superiority of the VGG19 model highlights its suitability for practical implementation in real-world scenarios. However, further investigation is warranted to comprehend model performance variations and ensure generalization to unseen data. Overall, this study serves as a crucial step towards broader applications of artificial intelligence in medical diagnostics, particularly in the realm of automated hematology, fostering advancements in healthcare technology.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"90 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140225073","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}
INTRODUCTION: Parkinson's disease is a progressive and complex neurological condition that mostly affects coordination and motor control. Parkinson's disease is most commonly associated with its motor symptoms, which include tremors, bradykinesia (slowness of movement), rigidity, and postural instability. OBJECTIVES: Determine any minor alterations in walking patterns that could be early signs of Parkinson's disease. Track the course of Parkinson's disease over time by using gait data. METHODS: In this study, we applied three types of VGRF datasets ("Dual Tasking, RAS, and Treadmill Walking") and developed an ML-based model using six different classifier methods. The datasets were analysed using 16 sensors, of which 8 were applied to each foot and the total pressure of the left and right foot. The aforementioned three distinct gait patterns movement disorders were the sources of the dataset. The gait signals dataset benefited by the participant demographic data. RESULTS: Then, we passed the outcome of applying the model and measuring performance through a cross-validation operator to check the accuracy and decision-making of the five algorithms i) Deep Learning, ii) Neural Networks, iii) Support Vector Machine (SVM), iv) Gradient Boost Tree (GBT), v) Random Forest”. The following findings compare the effectiveness of the various algorithms utilized and the observed PD very well. CONCLUSION: The different ML classifier algorithms demonstrated good detection capability with different accuracy. Our proposed ensemble model is superior to compare with the existing models. Because we can observe the proposed ensemble model result and accuracy better than the other classifier model. The other classifier model’s highest accuracy is 92.08% whereas our ensemble model got 92.31%. So, it has proved that our proposed ensemble model is excellent and robust.
{"title":"Gait Data-Driven Analysis of Parkinson’s Disease Using Machine Learning","authors":"Archana Panda, Prachet Bhuyan","doi":"10.4108/eetpht.10.5467","DOIUrl":"https://doi.org/10.4108/eetpht.10.5467","url":null,"abstract":"INTRODUCTION: Parkinson's disease is a progressive and complex neurological condition that mostly affects coordination and motor control. Parkinson's disease is most commonly associated with its motor symptoms, which include tremors, bradykinesia (slowness of movement), rigidity, and postural instability. \u0000OBJECTIVES: Determine any minor alterations in walking patterns that could be early signs of Parkinson's disease. Track the course of Parkinson's disease over time by using gait data. \u0000METHODS: In this study, we applied three types of VGRF datasets (\"Dual Tasking, RAS, and Treadmill Walking\") and developed an ML-based model using six different classifier methods. The datasets were analysed using 16 sensors, of which 8 were applied to each foot and the total pressure of the left and right foot. The aforementioned three distinct gait patterns movement disorders were the sources of the dataset. The gait signals dataset benefited by the participant demographic data. \u0000RESULTS: Then, we passed the outcome of applying the model and measuring performance through a cross-validation operator to check the accuracy and decision-making of the five algorithms i) Deep Learning, ii) Neural Networks, iii) Support Vector Machine (SVM), iv) Gradient Boost Tree (GBT), v) Random Forest”. The following findings compare the effectiveness of the various algorithms utilized and the observed PD very well. \u0000CONCLUSION: The different ML classifier algorithms demonstrated good detection capability with different accuracy. Our proposed ensemble model is superior to compare with the existing models. Because we can observe the proposed ensemble model result and accuracy better than the other classifier model. The other classifier model’s highest accuracy is 92.08% whereas our ensemble model got 92.31%. So, it has proved that our proposed ensemble model is excellent and robust.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"73 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140229914","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}
Kishore Kanna R, S. Sahoo, B. K. Mandhavi, V. Mohan, G. S. Babu, B. Panigrahi
INTRODUCTION: Tumours are the second most frequent cause of cancer today. Numerous individuals are at danger owing to cancer. To detect cancers such as brain tumours, the medical sector demands a speedy, automated, efficient, and reliable procedure. OBJECTIVES: Early phases of therapy are critical for detection. If an accurate tumour diagnosis is possible, physicians safeguard the patient from danger. In this program, several image processing algorithms are utilized. METHODS: Utilizing this approach, countless cancer patients are treated, and their lives are spared. A tumor is nothing more than a collection of cells that proliferate uncontrolled. Brain failure is caused by the development of brain cancer cells, which devour all of the nutrition meant for healthy cells and tissues. Currently, physicians physically scrutinize MRI pictures of the brain to establish the location and size of a patient's brain tumour. This takes a large amount of time and adds to erroneous tumour detection. RESULTS: A tumour is a development of tissue that is uncontrolled. Transfer learning may be utilized to detect the brain cancer utilizing. The model's capacity to forecast the presence of a cancer in a picture is its best advantage. It returns TRUE if a tumor is present and FALSE otherwise. CONCLUSION: In conclusion, the use of CNN and deep learning algorithms to the identification of brain tumor has shown remarkable promise and has the potential to completely transform the discipline of radiology.
{"title":"Detection of Brain Tumour based on Optimal Convolution Neural Network","authors":"Kishore Kanna R, S. Sahoo, B. K. Mandhavi, V. Mohan, G. S. Babu, B. Panigrahi","doi":"10.4108/eetpht.10.5464","DOIUrl":"https://doi.org/10.4108/eetpht.10.5464","url":null,"abstract":" \u0000INTRODUCTION: Tumours are the second most frequent cause of cancer today. Numerous individuals are at danger owing to cancer. To detect cancers such as brain tumours, the medical sector demands a speedy, automated, efficient, and reliable procedure. \u0000OBJECTIVES: Early phases of therapy are critical for detection. If an accurate tumour diagnosis is possible, physicians safeguard the patient from danger. In this program, several image processing algorithms are utilized. \u0000METHODS: Utilizing this approach, countless cancer patients are treated, and their lives are spared. A tumor is nothing more than a collection of cells that proliferate uncontrolled. Brain failure is caused by the development of brain cancer cells, which devour all of the nutrition meant for healthy cells and tissues. Currently, physicians physically scrutinize MRI pictures of the brain to establish the location and size of a patient's brain tumour. This takes a large amount of time and adds to erroneous tumour detection. \u0000RESULTS: A tumour is a development of tissue that is uncontrolled. Transfer learning may be utilized to detect the brain cancer utilizing. The model's capacity to forecast the presence of a cancer in a picture is its best advantage. It returns TRUE if a tumor is present and FALSE otherwise. \u0000CONCLUSION: In conclusion, the use of CNN and deep learning algorithms to the identification of brain tumor has shown remarkable promise and has the potential to completely transform the discipline of radiology.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"71 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140229733","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}
INTORDUCTION: The goal of human posture detection technology applied in the field of sports is to realise the indexing of sports norms, to provide scientific guidance for training and teaching, which is of great significance to improve the quality of sports.OBJECITVES: Aiming at the problems of incomplete features, low accuracy and low real-time performance of sports posture detection and recognition methods.METHODS: In this paper, a method of sports pose detection based on snow melting heuristic optimisation algorithm of deep limit learning machine network is proposed. Firstly, by analyzing the process of motion pose detection, extracting the feature coordinates of Blaze-Pose and Blaze-Hands key nodes, and constructing the motion pose detection recognition system; then, optimizing the parameters of the deep extreme learning machine network through the snow-melt optimization algorithm, and constructing the motion pose detection recognition model; finally, through simulation experiments and analysis, the accuracy of the proposed method's motion pose detection recognition can reach 95% and the recognition time is less than 0.01 s.RESULTS: The results show that the proposed method improves the recognition accuracy precision, robustness and real-time performance.CONCLUSION: The problem of poor generalisation, low accuracy and insufficient real-time performance of the recognition application of the motion pose detection and recognition method is solved.
{"title":"Analysis and Improvement of the Application of Playground Sports Posture Detection Technology in Physical Education Teaching and Training","authors":"Jie Xu","doi":"10.4108/eetpht.10.5161","DOIUrl":"https://doi.org/10.4108/eetpht.10.5161","url":null,"abstract":" INTORDUCTION: The goal of human posture detection technology applied in the field of sports is to realise the indexing of sports norms, to provide scientific guidance for training and teaching, which is of great significance to improve the quality of sports.OBJECITVES: Aiming at the problems of incomplete features, low accuracy and low real-time performance of sports posture detection and recognition methods.METHODS: In this paper, a method of sports pose detection based on snow melting heuristic optimisation algorithm of deep limit learning machine network is proposed. Firstly, by analyzing the process of motion pose detection, extracting the feature coordinates of Blaze-Pose and Blaze-Hands key nodes, and constructing the motion pose detection recognition system; then, optimizing the parameters of the deep extreme learning machine network through the snow-melt optimization algorithm, and constructing the motion pose detection recognition model; finally, through simulation experiments and analysis, the accuracy of the proposed method's motion pose detection recognition can reach 95% and the recognition time is less than 0.01 s.RESULTS: The results show that the proposed method improves the recognition accuracy precision, robustness and real-time performance.CONCLUSION: The problem of poor generalisation, low accuracy and insufficient real-time performance of the recognition application of the motion pose detection and recognition method is solved.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"44 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140231384","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}
INTRODUCTION: In recent years, there has been a convergence between Artificial Intelligence and neuroscience, particularly in studying the brain and developing treatments for neurological disorders. Artificial neural networks and deep learning provide valuable insights into neural processing and brain functioning. Recent research tries to explain how neural processes influence an individual's happiness. OBJECTIVES: To evaluate the interaction between neuroscience and happiness based on the advances in Artificial Intelligence. METHODS: A bibliometric analysis was performed with articles from the Scopus database in 2013-2023; likewise, the VOSviewer was used for information processing. RESULTS A total of 603 articles were obtained, and it is evident that the most significant scientific production is centered in the United States (184), United Kingdom (74), and China (73). Three clusters are generated from the Co-occurrence - Author Keywords analysis. The first cluster, red, is related to Artificial Intelligence applications for predicting happiness; the second cluster, green, is associated with Artificial Intelligence tools in neuroscience; and the third cluster, blue, is related to neuroscience in psychology. CONCLUSION: Neuroscience research has made significant leaps in understanding mental processes such as emotions and consciousness. Neuroscience has encountered happiness and is opening up to an approach that seeks evidence to understand people's well-being supported by Artificial Intelligence.
{"title":"Interaction between neuroscience and happiness: assessment from Artificial Intelligence advances","authors":"Rolando Eslava-Zapata, Verenice Sánchez-Castillo, Edixón Chacón-Guerrero","doi":"10.4108/eetpht.10.5456","DOIUrl":"https://doi.org/10.4108/eetpht.10.5456","url":null,"abstract":"INTRODUCTION: In recent years, there has been a convergence between Artificial Intelligence and neuroscience, particularly in studying the brain and developing treatments for neurological disorders. Artificial neural networks and deep learning provide valuable insights into neural processing and brain functioning. Recent research tries to explain how neural processes influence an individual's happiness. \u0000OBJECTIVES: To evaluate the interaction between neuroscience and happiness based on the advances in Artificial Intelligence. \u0000METHODS: A bibliometric analysis was performed with articles from the Scopus database in 2013-2023; likewise, the VOSviewer was used for information processing. \u0000RESULTS A total of 603 articles were obtained, and it is evident that the most significant scientific production is centered in the United States (184), United Kingdom (74), and China (73). Three clusters are generated from the Co-occurrence - Author Keywords analysis. The first cluster, red, is related to Artificial Intelligence applications for predicting happiness; the second cluster, green, is associated with Artificial Intelligence tools in neuroscience; and the third cluster, blue, is related to neuroscience in psychology. \u0000CONCLUSION: Neuroscience research has made significant leaps in understanding mental processes such as emotions and consciousness. Neuroscience has encountered happiness and is opening up to an approach that seeks evidence to understand people's well-being supported by Artificial Intelligence.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"56 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140234318","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}
Mohammed Altaf Ahmed, Q. S. T. Naz, Raghav Agarwal, Mannava Yesubabu, Rajesh Tulasi
INTRODUCTION: Heart failure is a chronic condition that affects many people worldwide. Regrettably, it is now the biggest cause of mortality globally, and it is becoming more common. Before a cardiac event, early diagnosis of heart disease is challenging. Although healthcare institutions like hospitals and clinics have access to a wealth of heart disease data, it is rarely used to uncover underlying trends. OBJECTIVES: Algorithms for machine learning (ML) can turn this medical data into insightful information. These methods are used to create decision support systems (DSS) that can gain knowledge from the past and advance. It is essential to use an effective ML-based technique to identify early heart failure and take preventive action to address this worldwide issue. Accurately identifying heart illness is our main goal in this study. METHODS: For this work, we benchmark different datasets on heart illness, and we use feature engineering approaches to pick the most pertinent qualities for improved performance. Additionally, we assess nine ML methods using critical parameters including precision, f-measure, sensitivity, specificity, and accuracy. RESULTS: Iterative tests are carried out to evaluate the efficacy of different algorithms. With a flawless cross-validation accuracy score of 99.51% and 100% in all other metrics, our suggested Decision Tree approach performs better than other ML models and cutting-edge studies. CONCLUSION: Each methodology used in our study is validated using cross-validation techniques. The medical community benefits greatly from this research study.
导言：心力衰竭是一种慢性疾病，影响着全球许多人。令人遗憾的是，它目前是全球最大的死亡原因，而且越来越常见。在发生心脏事件之前，心脏病的早期诊断具有挑战性。尽管医院和诊所等医疗机构可以获得大量心脏病数据，但却很少利用这些数据来发现潜在趋势。目标：机器学习（ML）算法可以将这些医疗数据转化为有洞察力的信息。这些方法可用于创建决策支持系统 (DSS)，该系统可从过去获得知识并不断进步。使用有效的基于 ML 的技术来识别早期心力衰竭并采取预防措施来解决这一世界性问题至关重要。准确识别心脏病是我们这项研究的主要目标。方法：在这项工作中，我们对不同的心脏病数据集进行了基准测试，并使用特征工程方法挑选出最相关的特征以提高性能。此外，我们还使用精确度、f 值、灵敏度、特异性和准确度等关键参数对九种 ML 方法进行了评估。结果：我们进行了迭代测试，以评估不同算法的功效。我们建议的决策树方法的交叉验证准确率为 99.51%，其他指标均为 100%，表现优于其他 ML 模型和前沿研究。结论：我们研究中使用的每种方法都经过了交叉验证技术的验证。医学界将从这项研究中受益匪浅。
{"title":"Clinical Support System for Cardiovascular Disease Forecasting Using ECG","authors":"Mohammed Altaf Ahmed, Q. S. T. Naz, Raghav Agarwal, Mannava Yesubabu, Rajesh Tulasi","doi":"10.4108/eetpht.10.5455","DOIUrl":"https://doi.org/10.4108/eetpht.10.5455","url":null,"abstract":"INTRODUCTION: Heart failure is a chronic condition that affects many people worldwide. Regrettably, it is now the biggest cause of mortality globally, and it is becoming more common. Before a cardiac event, early diagnosis of heart disease is challenging. Although healthcare institutions like hospitals and clinics have access to a wealth of heart disease data, it is rarely used to uncover underlying trends. \u0000OBJECTIVES: Algorithms for machine learning (ML) can turn this medical data into insightful information. These methods are used to create decision support systems (DSS) that can gain knowledge from the past and advance. It is essential to use an effective ML-based technique to identify early heart failure and take preventive action to address this worldwide issue. Accurately identifying heart illness is our main goal in this study. \u0000METHODS: For this work, we benchmark different datasets on heart illness, and we use feature engineering approaches to pick the most pertinent qualities for improved performance. Additionally, we assess nine ML methods using critical parameters including precision, f-measure, sensitivity, specificity, and accuracy. \u0000RESULTS: Iterative tests are carried out to evaluate the efficacy of different algorithms. With a flawless cross-validation accuracy score of 99.51% and 100% in all other metrics, our suggested Decision Tree approach performs better than other ML models and cutting-edge studies. \u0000CONCLUSION: Each methodology used in our study is validated using cross-validation techniques. The medical community benefits greatly from this research study.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"56 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140234321","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：