Pub Date : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10140865
A. S. Vaishnavi, T. Greeshma, Ram Prudhvi Teja, T. Padma, C. Kumari
The paper provides an overview of the removal of noise cancellation in ECG signals using an LMS filter in a system generator for monitoring ECG parameters and the study of the P wave to diagnose cardiac arrhythmia. The real ECG signals were evaluated from MIT-BIH database. Using Xilinx system Generator., the LMS adaptive filters technique is implemented. In order to efficiently verify the algorithm., the simulation of the models was carried out in MATLAB and Simulink. The core LMS adaptive filter and its fundamental basic building blocks technique was implemented in Xilinx System Generator. Here., high-pass least-square linear phase Finite Impulse Response (FIR) filtering approach to remove the baseline wander noise from the system's input ECG signal. A digital filter used in adaptive filtering has weights that are managed using adaptive algorithm to reduce difference between output of the filter and a reference signal that matches and fulfills the criterion. The reference signal's characteristics depends on the application under consideration. Convergence rate and steady state mean square error are the two main measures to evaluate the efficiency and performance of an adaptive filter.
本文概述了在系统发生器中使用LMS滤波器去除心电信号中的噪声，用于监测心电参数和研究P波诊断心律失常。从MIT-BIH数据库中评估真实心电信号。使用Xilinx系统生成器。，实现了LMS自适应滤波技术。为了有效地验证算法。，在MATLAB和Simulink中对模型进行仿真。在Xilinx System Generator中实现了LMS自适应滤波器的核心及其基本构建模块技术。在这里。采用高通最小二乘线性相位有限脉冲响应(FIR)滤波方法去除系统输入心电信号中的基线漂移噪声。用于自适应滤波的数字滤波器具有使用自适应算法管理的权重，以减小滤波器输出与匹配并满足标准的参考信号之间的差。参考信号的特性取决于所考虑的应用。收敛速度和稳态均方误差是评价自适应滤波器效率和性能的两个主要指标。
{"title":"Noise Removal from ECG Signal using LMS Adaptive Filter Implementation in Xilinx System Generator","authors":"A. S. Vaishnavi, T. Greeshma, Ram Prudhvi Teja, T. Padma, C. Kumari","doi":"10.1109/ICAAIC56838.2023.10140865","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10140865","url":null,"abstract":"The paper provides an overview of the removal of noise cancellation in ECG signals using an LMS filter in a system generator for monitoring ECG parameters and the study of the P wave to diagnose cardiac arrhythmia. The real ECG signals were evaluated from MIT-BIH database. Using Xilinx system Generator., the LMS adaptive filters technique is implemented. In order to efficiently verify the algorithm., the simulation of the models was carried out in MATLAB and Simulink. The core LMS adaptive filter and its fundamental basic building blocks technique was implemented in Xilinx System Generator. Here., high-pass least-square linear phase Finite Impulse Response (FIR) filtering approach to remove the baseline wander noise from the system's input ECG signal. A digital filter used in adaptive filtering has weights that are managed using adaptive algorithm to reduce difference between output of the filter and a reference signal that matches and fulfills the criterion. The reference signal's characteristics depends on the application under consideration. Convergence rate and steady state mean square error are the two main measures to evaluate the efficiency and performance of an adaptive filter.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125630046","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10141504
Shikha Prasher, Leema Nelson
A million individuals per year die from diseases spread by mosquitoes. When a mosquito stings, saliva is injected into the body, causing the illness to spread to the victims. In a surveillance programmed for infections propagated through mosquito detection, categorization is the most crucial stage. Classification and labeling are difficult and time-consuming procedures when employing traditional method to collect data. Transfer learning is an advanced image processing techniques that offers a great solution to this problem. With very few training images, transfer learning is a form of CNN that can be beneficial and long-lasting for image analysis. This research will enhance human health and quality of life. The purpose of this approach is to create a systematic process for developing a categorization system using an EfficentNetB4 transfer learning algorithm for mosquitoes. The resultant performance analysis showed that the EfficentNetB4 model offers an accuracy of 85.79%, loss of 40.05%, val_loss of 40.42%, and val_accuracy of 86.30%.
{"title":"Mosquitoes Classification using EfficientNetB4 Transfer Learning Model","authors":"Shikha Prasher, Leema Nelson","doi":"10.1109/ICAAIC56838.2023.10141504","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10141504","url":null,"abstract":"A million individuals per year die from diseases spread by mosquitoes. When a mosquito stings, saliva is injected into the body, causing the illness to spread to the victims. In a surveillance programmed for infections propagated through mosquito detection, categorization is the most crucial stage. Classification and labeling are difficult and time-consuming procedures when employing traditional method to collect data. Transfer learning is an advanced image processing techniques that offers a great solution to this problem. With very few training images, transfer learning is a form of CNN that can be beneficial and long-lasting for image analysis. This research will enhance human health and quality of life. The purpose of this approach is to create a systematic process for developing a categorization system using an EfficentNetB4 transfer learning algorithm for mosquitoes. The resultant performance analysis showed that the EfficentNetB4 model offers an accuracy of 85.79%, loss of 40.05%, val_loss of 40.42%, and val_accuracy of 86.30%.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"3 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113934802","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10141445
N. Suresh, Kosuri Nitheesh, Reddy Venkata Siva Chaitanya, B. Vani
In densely populated areas, obtaining parking spaces is a major problem because the number of automobiles on the road is increasing daily. RFID is the most often used technique for removing or overcoming the cause. Checking the card's balance rather than hunting for parking spaces at far-off locations is the present RFID concept's procedure. The biggest problem with the existing approach is that it is hard to measure how much money is taken out because it varies over time and between various slots. Therefore, this research study provides a solution, namely the suggested method, which guarantees an efficient monitoring system and permits the monitoring of parking spaces in remote regions. These efforts The goal of this project is to tie the RFID concept to the Internet of Things (IoT). Users can communicate remotely regarding parking space availability thanks to IoT's client-server connection. The creation of a website that informs users when parking spaces are available would enhance the mobile-friendly environment. From a distance, users will be able to reserve a parking spot, and that spot will be held for 30 minutes while it waits for the user to arrive. After the time restriction has gone and the slot is still available, the user must rebook it. By doing this, parking lot traffic congestion is reduced to a minimum. This can be employed in retail areas where traffic congestion is regularly caused by parking concerns.
{"title":"Revolutionizing Parking Management with IoT-powered Smart Car Parking Solutions","authors":"N. Suresh, Kosuri Nitheesh, Reddy Venkata Siva Chaitanya, B. Vani","doi":"10.1109/ICAAIC56838.2023.10141445","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10141445","url":null,"abstract":"In densely populated areas, obtaining parking spaces is a major problem because the number of automobiles on the road is increasing daily. RFID is the most often used technique for removing or overcoming the cause. Checking the card's balance rather than hunting for parking spaces at far-off locations is the present RFID concept's procedure. The biggest problem with the existing approach is that it is hard to measure how much money is taken out because it varies over time and between various slots. Therefore, this research study provides a solution, namely the suggested method, which guarantees an efficient monitoring system and permits the monitoring of parking spaces in remote regions. These efforts The goal of this project is to tie the RFID concept to the Internet of Things (IoT). Users can communicate remotely regarding parking space availability thanks to IoT's client-server connection. The creation of a website that informs users when parking spaces are available would enhance the mobile-friendly environment. From a distance, users will be able to reserve a parking spot, and that spot will be held for 30 minutes while it waits for the user to arrive. After the time restriction has gone and the slot is still available, the user must rebook it. By doing this, parking lot traffic congestion is reduced to a minimum. This can be employed in retail areas where traffic congestion is regularly caused by parking concerns.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131969138","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10141240
G. Satish, C. Dalai, V. S. Dattu, K. Rayudu, T. Sathish, K. Purohit
This article presents an optimization model for energy management (EM) in a microgrid composed of renewable energy sources. The microgrid in question, corresponding to an electric vehicle (EVs) charging station, has solar panels, wind turbines, and a bank of batteries. The loads considered are EVs that enter the charging station requesting the charging of their batteries and equipment from a small convenience store, located in the charging station itself. This work maximize the supply of active power to EVs and, simultaneously, minimize the interruptions in the energy supply. An algorithm (with the aid of computational tools) will be used to deal with the decision-making process related to turbines, panels and loads. The implementations were made in MATLAB, for modeling the energy sources, and AMPL, for applying the optimization algorithm.
{"title":"Optimization Model for Energy Management in a Microgrid","authors":"G. Satish, C. Dalai, V. S. Dattu, K. Rayudu, T. Sathish, K. Purohit","doi":"10.1109/ICAAIC56838.2023.10141240","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10141240","url":null,"abstract":"This article presents an optimization model for energy management (EM) in a microgrid composed of renewable energy sources. The microgrid in question, corresponding to an electric vehicle (EVs) charging station, has solar panels, wind turbines, and a bank of batteries. The loads considered are EVs that enter the charging station requesting the charging of their batteries and equipment from a small convenience store, located in the charging station itself. This work maximize the supply of active power to EVs and, simultaneously, minimize the interruptions in the energy supply. An algorithm (with the aid of computational tools) will be used to deal with the decision-making process related to turbines, panels and loads. The implementations were made in MATLAB, for modeling the energy sources, and AMPL, for applying the optimization algorithm.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130165681","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10140306
S. S. Nalawade, Arun S. Patil
A study of a person's attitude in terms of using several unstructured texts is denoted as Sentimental analysis or opinion mining. Opinion mining or sentimental analysis distinguishes as the degree of polarity discover. The estimation of tweet review topics and a product is a high-grade sentimental analysis. Natural language understanding was essential for such data; many challenges were present in the natural language processing field for sentimental analysis. Nowadays, many pieces of research consider deep learning-based techniques for sentimental analysis in the natural language processing field. In this study, 25 papers were reviewed through deep learning-based approaches. Measures, as well as achievements attained by various methods, were simplified. The survey described the improvements and a limitation of each method as well as it regards the challenges and future potential research which is to acquire high accuracy and precision in sentimental analysis. Taxonomy represents the study gap and it elaborates on the various approaches.
{"title":"An Empirical Study on Sentimental Analysis using Deep Learning","authors":"S. S. Nalawade, Arun S. Patil","doi":"10.1109/ICAAIC56838.2023.10140306","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10140306","url":null,"abstract":"A study of a person's attitude in terms of using several unstructured texts is denoted as Sentimental analysis or opinion mining. Opinion mining or sentimental analysis distinguishes as the degree of polarity discover. The estimation of tweet review topics and a product is a high-grade sentimental analysis. Natural language understanding was essential for such data; many challenges were present in the natural language processing field for sentimental analysis. Nowadays, many pieces of research consider deep learning-based techniques for sentimental analysis in the natural language processing field. In this study, 25 papers were reviewed through deep learning-based approaches. Measures, as well as achievements attained by various methods, were simplified. The survey described the improvements and a limitation of each method as well as it regards the challenges and future potential research which is to acquire high accuracy and precision in sentimental analysis. Taxonomy represents the study gap and it elaborates on the various approaches.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130444719","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10140703
Kritesh Rauniyar, Shuvam Thakur, Aayush Nevatia, P. G. Shambharkar
Almost 50 million individuals throughout the world suffer from Alzheimer's disease (AD), a disease of the nervous system. There are no licensed medications on the market right now that can treat AD or halt its development. There are, however, treatments available that can help mediate AD in earlier stages. This demonstrates the necessity of early diagnosis. One of the notable symptoms of Alzheimer's can be in the patient's cognitive abilities. In daily chores, there is an indication of a diminished capacity for interpreting or producing speech. As a result, natural language processing can be a useful method for analyzing patient speech. Due to the rapid advancements in the field of computer science, we can use NLP to process these speech extracts from AD patients. NLP has a great deal of potential to help individuals who are suffering from mental illnesses receive better care. The study employs various Machine Learning models with ensemble learners and Deep Learning models for a comparative analysis to set a proper baseline for further research and advancements in the detection of Alzheimer's disease.
{"title":"Early Detection of Alzheimer's Disease: The Importance of Speech Analysis","authors":"Kritesh Rauniyar, Shuvam Thakur, Aayush Nevatia, P. G. Shambharkar","doi":"10.1109/ICAAIC56838.2023.10140703","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10140703","url":null,"abstract":"Almost 50 million individuals throughout the world suffer from Alzheimer's disease (AD), a disease of the nervous system. There are no licensed medications on the market right now that can treat AD or halt its development. There are, however, treatments available that can help mediate AD in earlier stages. This demonstrates the necessity of early diagnosis. One of the notable symptoms of Alzheimer's can be in the patient's cognitive abilities. In daily chores, there is an indication of a diminished capacity for interpreting or producing speech. As a result, natural language processing can be a useful method for analyzing patient speech. Due to the rapid advancements in the field of computer science, we can use NLP to process these speech extracts from AD patients. NLP has a great deal of potential to help individuals who are suffering from mental illnesses receive better care. The study employs various Machine Learning models with ensemble learners and Deep Learning models for a comparative analysis to set a proper baseline for further research and advancements in the detection of Alzheimer's disease.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"277 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133931508","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10140661
K. Manivannan, S. Sathiamoorthy
Accurate Tuberculosis (TB) screening using chest X-rays and artificial intelligence (AI) has the potential in increasing the quality of the healthcare services. Early detection of TB using automated tools find beneficial to decrease the severity level of the diseases. Therefore, the recent developments of the deep learning (DL) models are used in the design of automated TB detection tools. With this motivation, this article focuses on the design of new Harris Hawks optimization with Deep Learning Enabled Tuberculosis Classification (HHODL-TBC) model on chest X-rays. The proposed HHODL-TBC model focuses on the recognition and classification of TB effectually. It follows a three stage process: median filtering based noise removal, U-Net segmentation, MobileNetv2 feature extraction, HHO based hyperparameter tuning, and gated recurrent unit (GRU) classifier. The design of the HHO algorithm assist in the optimal hyperparameter selection of the GRU model. A comprehensive set of simulations were performed for illustrating the improvised results of the HHODL-TBC model, and the results demonstrate the improved outcomes of the HHODL-TBC model with higher accuracy of 99.33%.
{"title":"Robust Tuberculosis Detection using Optimal Deep Learning Model using Chest X-Rays","authors":"K. Manivannan, S. Sathiamoorthy","doi":"10.1109/ICAAIC56838.2023.10140661","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10140661","url":null,"abstract":"Accurate Tuberculosis (TB) screening using chest X-rays and artificial intelligence (AI) has the potential in increasing the quality of the healthcare services. Early detection of TB using automated tools find beneficial to decrease the severity level of the diseases. Therefore, the recent developments of the deep learning (DL) models are used in the design of automated TB detection tools. With this motivation, this article focuses on the design of new Harris Hawks optimization with Deep Learning Enabled Tuberculosis Classification (HHODL-TBC) model on chest X-rays. The proposed HHODL-TBC model focuses on the recognition and classification of TB effectually. It follows a three stage process: median filtering based noise removal, U-Net segmentation, MobileNetv2 feature extraction, HHO based hyperparameter tuning, and gated recurrent unit (GRU) classifier. The design of the HHO algorithm assist in the optimal hyperparameter selection of the GRU model. A comprehensive set of simulations were performed for illustrating the improvised results of the HHODL-TBC model, and the results demonstrate the improved outcomes of the HHODL-TBC model with higher accuracy of 99.33%.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133944512","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10140204
Shreya Srivastava, Niharika Dhyani, Vikrant Sharma, Satvik Vats, S. Yadav, V. Kukreja, Raghvendra Singh
Lung disease identification using heatmap is an automated diagnosis system that utilizes the visualization of heatmaps to identify and classify lung diseases from chest X- Radiation images. The system applies a deep learning-based approach to automatically extract and learn discriminative features from the input images, which are then used to generate heatmaps highlighting the regions of the lung that are affected by the disease. The heatmaps provide an intuitive visualization of the disease, which can be used to aid radiologists in making accurate diagnoses. The approach has the potential to increase the efficiency and accuracy of clinical diagnosis and has been proven to achieve high accuracy in the identification and categorization of a variety of lung infection, including pneumonia and Novel coronavirus. Lung diseases have become a major health concern worldwide, causing significant morbidity and mortality. Early identification and timely treatment of these diseases can significantly improve patient outcomes. This research paper, proposes a novel approach to identify lung diseases using heatmap analysis. CXR of patients was collected with various lung infection, including pneumonia and novel coronavirus. The images were pre-processed to enhance the features and reduce noise. A heatmap analysis technique was applied to these images to generate heatmaps that highlight the regions of the lung that are most affected by the disease. A deep learning model was then used to classify diseases using the heatmaps. The pictures were categorized into several types of lung infection groups using a convolutional neural network (CNN). The CNN obtained good illness classification accuracy after being trained on a huge dataset of CXR. The proposed approach was evaluated on a dataset of 317 CXR. The findings indicated that our method classified diseases with an overall accuracy of 98.55%. The suggested method may increase the precision and efficiency of diagnosing lung diseases. The heatmap analysis technique can help clinicians identify the regions of the lung that are most affected by the disease, which can aid in diagnosis and treatment planning. Furthermore, the deep learning model can be trained on large datasets to improve its accuracy and robustness.
{"title":"Lung Infection and Identification using Heatmap","authors":"Shreya Srivastava, Niharika Dhyani, Vikrant Sharma, Satvik Vats, S. Yadav, V. Kukreja, Raghvendra Singh","doi":"10.1109/ICAAIC56838.2023.10140204","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10140204","url":null,"abstract":"Lung disease identification using heatmap is an automated diagnosis system that utilizes the visualization of heatmaps to identify and classify lung diseases from chest X- Radiation images. The system applies a deep learning-based approach to automatically extract and learn discriminative features from the input images, which are then used to generate heatmaps highlighting the regions of the lung that are affected by the disease. The heatmaps provide an intuitive visualization of the disease, which can be used to aid radiologists in making accurate diagnoses. The approach has the potential to increase the efficiency and accuracy of clinical diagnosis and has been proven to achieve high accuracy in the identification and categorization of a variety of lung infection, including pneumonia and Novel coronavirus. Lung diseases have become a major health concern worldwide, causing significant morbidity and mortality. Early identification and timely treatment of these diseases can significantly improve patient outcomes. This research paper, proposes a novel approach to identify lung diseases using heatmap analysis. CXR of patients was collected with various lung infection, including pneumonia and novel coronavirus. The images were pre-processed to enhance the features and reduce noise. A heatmap analysis technique was applied to these images to generate heatmaps that highlight the regions of the lung that are most affected by the disease. A deep learning model was then used to classify diseases using the heatmaps. The pictures were categorized into several types of lung infection groups using a convolutional neural network (CNN). The CNN obtained good illness classification accuracy after being trained on a huge dataset of CXR. The proposed approach was evaluated on a dataset of 317 CXR. The findings indicated that our method classified diseases with an overall accuracy of 98.55%. The suggested method may increase the precision and efficiency of diagnosing lung diseases. The heatmap analysis technique can help clinicians identify the regions of the lung that are most affected by the disease, which can aid in diagnosis and treatment planning. Furthermore, the deep learning model can be trained on large datasets to improve its accuracy and robustness.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"08 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131241516","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10141515
Arul Raj A. M, Sugumar R
The ongoing COVID-19 pandemic has caused a global health crisis, and accurate diagnosis and early detection are essential for successful management of the outbreak. Convolutional neural networks(CNNs) and preprocessed chest X-ray pictures are the two main components of the unique proposed method for the identification of COVID-19, which is presented in this study. Image enhancement and segmentation are performed during the pre-processing stage. These operations increase the overall quality and contrast of the pictures, which in turn makes it simpler for the CNN to recognise significant aspects of the images. The CNN model was trained using a large dataset of pre-processed X-ray pictures that included both COVID-19 positive and negative instances. The dataset was used to train the model. In comparison to more conventional diagnostic approaches, and this strategy was successful in achieving high levels of accuracy, sensitivity, and specificity in the detection of COVID-19. Moreover, this model designed an automated reporting system that saves time and costs by providing healthcare providers with diagnostic reports that are both prompt and accurate. This research demonstrates the viability of using CNNs and pre-processed X-ray images for the purpose of early identification of COVID-19 and offers an important resource for the efficient management of this worldwide health concern.
{"title":"Enhancing COVID-19 Diagnosis with Automated Reporting using Preprocessed Chest X-Ray Image Analysis based on CNN","authors":"Arul Raj A. M, Sugumar R","doi":"10.1109/ICAAIC56838.2023.10141515","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10141515","url":null,"abstract":"The ongoing COVID-19 pandemic has caused a global health crisis, and accurate diagnosis and early detection are essential for successful management of the outbreak. Convolutional neural networks(CNNs) and preprocessed chest X-ray pictures are the two main components of the unique proposed method for the identification of COVID-19, which is presented in this study. Image enhancement and segmentation are performed during the pre-processing stage. These operations increase the overall quality and contrast of the pictures, which in turn makes it simpler for the CNN to recognise significant aspects of the images. The CNN model was trained using a large dataset of pre-processed X-ray pictures that included both COVID-19 positive and negative instances. The dataset was used to train the model. In comparison to more conventional diagnostic approaches, and this strategy was successful in achieving high levels of accuracy, sensitivity, and specificity in the detection of COVID-19. Moreover, this model designed an automated reporting system that saves time and costs by providing healthcare providers with diagnostic reports that are both prompt and accurate. This research demonstrates the viability of using CNNs and pre-processed X-ray images for the purpose of early identification of COVID-19 and offers an important resource for the efficient management of this worldwide health concern.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130743905","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10141019
Sai Tejashwin Eswarapu, Sesharhri S, Yashwanth Deshaboina, Bhargawa P., Ashly Ann Jo, Ebin Deni Raj
This research study provides an outlook on modeling an integrated customer analytic framework using complex black-box AutoML pipelines while providing insights and explanations to the predictions provided to the customer data mainly in two use cases: Customer Churn and Customer Segmentation. Upon the Literature Review conducted, a pipeline has been derived to integrate both the use cases using supervised and unsupervised models, and explanations were obtained using XAI techniques. The experiments were conducted on the model with desired results and fairness checks were done to check the integrity of the predictions and explanations. The purpose of this research study is to automate the customer analysis process with a comparatively better performance without building a manual pipeline from scratch.
{"title":"Integrated Customer Analytics using Explainability and AutoML for Telecommunications","authors":"Sai Tejashwin Eswarapu, Sesharhri S, Yashwanth Deshaboina, Bhargawa P., Ashly Ann Jo, Ebin Deni Raj","doi":"10.1109/ICAAIC56838.2023.10141019","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10141019","url":null,"abstract":"This research study provides an outlook on modeling an integrated customer analytic framework using complex black-box AutoML pipelines while providing insights and explanations to the predictions provided to the customer data mainly in two use cases: Customer Churn and Customer Segmentation. Upon the Literature Review conducted, a pipeline has been derived to integrate both the use cases using supervised and unsupervised models, and explanations were obtained using XAI techniques. The experiments were conducted on the model with desired results and fairness checks were done to check the integrity of the predictions and explanations. The purpose of this research study is to automate the customer analysis process with a comparatively better performance without building a manual pipeline from scratch.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133359595","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：