Pub Date : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088322
N. Deepa, S. Prabakeran, D. T
In the modern world, people's expectations and needs are automatically supportive and easy to use such as voice messages, playing music, or movies automatically which may reduce the manual operations mostly. In past decades technological advances such as machine learning and its application over many data like structured and unstructured are very much tedious. Whereas the operations based on non-categorical data, and categorical data are working rapidly using Natural Language Processing (NLP) comparatively, existing ones were not very productive. Each process on the internet is carrying an enormous amount of information which can lag in storage as well as performance. When any CRUD operations such as create, modify, update and delete are being analyzed one at a time, complex data such as unstructured and structured data are used in any field. In such a way the location analysis, social media data, health organization information, etc are categorized in natural language processing (NLP). The proposed work is organized as i) managing the huge amount of data in healthcare and log files created due to electronic health record management(EHR), ii) Unstructured data that are generated from all electronic equipment such as monitoring heartbeat, brain waves, etc that can be interpreted to classify using machine learning algorithms. To overcome the complications and medical records access inefficiency due to the complex structure of the dataset, Natural language processing uses the recurrent neural network along with the novel modified long and short-term memory unit (NMRNN-LSTM). Using the big data types such as structured, unstructured, and reinforcement kind of databases which handle images such as CTs, X-rays, MRI, raw texts, video streaming medical history to have effective systems and clinical records for enhancing the technological Medical care.
{"title":"(NMRNN-LSTM) - Novel Modified RNN with Long and Short-Term Memory Unit in Healthcare and Big Data Applications","authors":"N. Deepa, S. Prabakeran, D. T","doi":"10.1109/ASSIC55218.2022.10088322","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088322","url":null,"abstract":"In the modern world, people's expectations and needs are automatically supportive and easy to use such as voice messages, playing music, or movies automatically which may reduce the manual operations mostly. In past decades technological advances such as machine learning and its application over many data like structured and unstructured are very much tedious. Whereas the operations based on non-categorical data, and categorical data are working rapidly using Natural Language Processing (NLP) comparatively, existing ones were not very productive. Each process on the internet is carrying an enormous amount of information which can lag in storage as well as performance. When any CRUD operations such as create, modify, update and delete are being analyzed one at a time, complex data such as unstructured and structured data are used in any field. In such a way the location analysis, social media data, health organization information, etc are categorized in natural language processing (NLP). The proposed work is organized as i) managing the huge amount of data in healthcare and log files created due to electronic health record management(EHR), ii) Unstructured data that are generated from all electronic equipment such as monitoring heartbeat, brain waves, etc that can be interpreted to classify using machine learning algorithms. To overcome the complications and medical records access inefficiency due to the complex structure of the dataset, Natural language processing uses the recurrent neural network along with the novel modified long and short-term memory unit (NMRNN-LSTM). Using the big data types such as structured, unstructured, and reinforcement kind of databases which handle images such as CTs, X-rays, MRI, raw texts, video streaming medical history to have effective systems and clinical records for enhancing the technological Medical care.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116431523","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088331
K. Swathi, E. S. N. Joshua, B. Reddy, N. Rao
Diabetes is one of the hazardous diseases in present era. Diabetic retinopathy is an eye disease which is caused due to diabetes. This condition affects the retina (blood vessels at the back of the eye), resulting in blindness. Diabetic retinopathy can occur in numerous ways, from no symptoms to minor vision impairments. In order to check whether a person got affected or not, the patient should visit a hospital, for the reports and should wait for enormous time. With the development of deep learning techniques, we have the ability to look into the problem. The aim of the examination is to develop a system which might classify the diabetic retinopathy disease of a patient with a better accuracy. The model we develop will remove the noise from fundus images uploaded by user by using filtering techniques and give accurate result. This project is a deep learning model integrated with web application in order to interact with users. There by the Diabetic Retinopathy detection model enhances medical care.
{"title":"Diabetic Retinopathy Detection Using Deep Learning","authors":"K. Swathi, E. S. N. Joshua, B. Reddy, N. Rao","doi":"10.1109/ASSIC55218.2022.10088331","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088331","url":null,"abstract":"Diabetes is one of the hazardous diseases in present era. Diabetic retinopathy is an eye disease which is caused due to diabetes. This condition affects the retina (blood vessels at the back of the eye), resulting in blindness. Diabetic retinopathy can occur in numerous ways, from no symptoms to minor vision impairments. In order to check whether a person got affected or not, the patient should visit a hospital, for the reports and should wait for enormous time. With the development of deep learning techniques, we have the ability to look into the problem. The aim of the examination is to develop a system which might classify the diabetic retinopathy disease of a patient with a better accuracy. The model we develop will remove the noise from fundus images uploaded by user by using filtering techniques and give accurate result. This project is a deep learning model integrated with web application in order to interact with users. There by the Diabetic Retinopathy detection model enhances medical care.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125674575","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}
Nowadays, health is a top priority. People are putting in a lot of effort to improve their health and make their bodies healthier. The majority of people use fitness apps to track their daily activities. This Fitness App provides all users with one-stop exercise solutions such as fitness training, cycling, running, yoga, and fitness diet guidance. The Fitbit Kaggle dataset, which contains 18 CSV files and approximately 2.5K users, was used in this study. The data set was analyzed in terms of “sleep vs active minutes” and “logged activity vs not logged activity.” The K-means machine learning technique is used to cluster App users based on a variety of factors, and whether they are eligible for bonuses or reward points. This paper's research focused on user categorization using unsupervised learning based on cluster. Such a Fitness App integrated with machine learning technique could intelligently motivated their customer in staying active throughout the day.
{"title":"Employing Machine Learning Techniques to Categorize users in a Fitness Application","authors":"Shyamali Das, Pamela Chaudhury, Hrudaya Kumar Tripathy","doi":"10.1109/ASSIC55218.2022.10088294","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088294","url":null,"abstract":"Nowadays, health is a top priority. People are putting in a lot of effort to improve their health and make their bodies healthier. The majority of people use fitness apps to track their daily activities. This Fitness App provides all users with one-stop exercise solutions such as fitness training, cycling, running, yoga, and fitness diet guidance. The Fitbit Kaggle dataset, which contains 18 CSV files and approximately 2.5K users, was used in this study. The data set was analyzed in terms of “sleep vs active minutes” and “logged activity vs not logged activity.” The K-means machine learning technique is used to cluster App users based on a variety of factors, and whether they are eligible for bonuses or reward points. This paper's research focused on user categorization using unsupervised learning based on cluster. Such a Fitness App integrated with machine learning technique could intelligently motivated their customer in staying active throughout the day.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"158 13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125954509","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088401
T. Devi, K. Jaisharma, N. Deepa
In recent days most people are using the internet to know the latest news faster, parallel false information also spreads for many reasons. The fake news is artificially manipulated and elongated by the true information, this creates negativity and diverse the users in particular opinions. Fake news detection is a more complicated and labor-consuming process because the data has kept on growing as big data. The detection of fake news using a single parameter has become less reliable and so there is a need to use multiple parameters to improve the reliability of the model. The parameters such as text, audio, video, and time were traditionally for fake news detection. In this article, the proposed model is designed to work with three parameters namely geolocation, text feed, and image data of the user in their handy smart mobile phone. The proposed Novel Trio-Neural Network has a binary classifier to detect fake or real news, the location spoofing is avoided by checking the movement probability of the user using Bayesian Geolocation Timestamp, the text feed posted by the users is analyzed by using BERT Fact Checker, and image shared by the user on the internet are mapped to text with similarity checker extracted feature from the image using VGG16 Similarity Mapping. The integrated Novel Trio-Neural Network was trained, tested, and validated with the FakeNewsNet dataset. The proposed model reached the F1-Score of 82.31%, and the performance of the model has significantly improved by 4.01% from the existing model.
{"title":"Novel Trio-Neural Network towards Detecting Fake News on Social Media","authors":"T. Devi, K. Jaisharma, N. Deepa","doi":"10.1109/ASSIC55218.2022.10088401","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088401","url":null,"abstract":"In recent days most people are using the internet to know the latest news faster, parallel false information also spreads for many reasons. The fake news is artificially manipulated and elongated by the true information, this creates negativity and diverse the users in particular opinions. Fake news detection is a more complicated and labor-consuming process because the data has kept on growing as big data. The detection of fake news using a single parameter has become less reliable and so there is a need to use multiple parameters to improve the reliability of the model. The parameters such as text, audio, video, and time were traditionally for fake news detection. In this article, the proposed model is designed to work with three parameters namely geolocation, text feed, and image data of the user in their handy smart mobile phone. The proposed Novel Trio-Neural Network has a binary classifier to detect fake or real news, the location spoofing is avoided by checking the movement probability of the user using Bayesian Geolocation Timestamp, the text feed posted by the users is analyzed by using BERT Fact Checker, and image shared by the user on the internet are mapped to text with similarity checker extracted feature from the image using VGG16 Similarity Mapping. The integrated Novel Trio-Neural Network was trained, tested, and validated with the FakeNewsNet dataset. The proposed model reached the F1-Score of 82.31%, and the performance of the model has significantly improved by 4.01% from the existing model.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127458518","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088342
Subhashree Rout, S. Samantaray
Technology and agriculture are correlated where they share societal values and expertise. The development of the agricultural sector has been largely dependent on labour-saving agricultural technologies where innovation may operate with advanced AI solutions that is less labour-intensive, more reasonable and adaptable. The paper chronicles the benefits of implementing Artificial Intelligence, Cyborg Technologies, Robotics and Internet of Things in Agroecology to ensure the welfare of women and environment. Further, it accentuates on the various automation and precision, while stressing on agriculture related technical advancements like smart farms, automated weeding and spraying machines, molecular detection, smart eye software, and smart irrigation. The progressive strategies to uplift women labourers in the field of tea plantation, especially in India, is also highlighted. The paper brings out the benefits of implementing technological advancement that affects the relationship between gender and ecology and looks at the situation of women workers through the lens of eco-feministic perspective.
{"title":"Interplay of Artificial Intelligence and Ecofeminism: A Reassessment of Automated Agroecology and Biased Gender in the Tea Plantations","authors":"Subhashree Rout, S. Samantaray","doi":"10.1109/ASSIC55218.2022.10088342","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088342","url":null,"abstract":"Technology and agriculture are correlated where they share societal values and expertise. The development of the agricultural sector has been largely dependent on labour-saving agricultural technologies where innovation may operate with advanced AI solutions that is less labour-intensive, more reasonable and adaptable. The paper chronicles the benefits of implementing Artificial Intelligence, Cyborg Technologies, Robotics and Internet of Things in Agroecology to ensure the welfare of women and environment. Further, it accentuates on the various automation and precision, while stressing on agriculture related technical advancements like smart farms, automated weeding and spraying machines, molecular detection, smart eye software, and smart irrigation. The progressive strategies to uplift women labourers in the field of tea plantation, especially in India, is also highlighted. The paper brings out the benefits of implementing technological advancement that affects the relationship between gender and ecology and looks at the situation of women workers through the lens of eco-feministic perspective.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128126650","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088316
Aradhana Kar, S. Pradhan
This research concentrates on reconstruction of the output line segments of the paper in [1]. The Line Segmenting module of [1] in some scenarios segments the alphabets and the associated matras of a line text in two separate line segments. These line segments are reconstructed using the Reconstruct Module to produce a line text with all its alphabets and its associated matras. This module uses one of the measures of dispersions, that is, standard deviation to accomplish reconstruction of output line segments. Then words are segmented from the line segments using WordSegmenting Module. This module uses one of the measures of central tendencies, i.e. mean and one of the measure of dispersions i.e, standard deviation to achieve word segmentation. Then characters are segmented from words using CharacterSegmenting Module.
{"title":"Line Reconstruction and Segmentation of Words and Characters using Measures of Central Tendency and Measures of Dispersion","authors":"Aradhana Kar, S. Pradhan","doi":"10.1109/ASSIC55218.2022.10088316","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088316","url":null,"abstract":"This research concentrates on reconstruction of the output line segments of the paper in [1]. The Line Segmenting module of [1] in some scenarios segments the alphabets and the associated matras of a line text in two separate line segments. These line segments are reconstructed using the Reconstruct Module to produce a line text with all its alphabets and its associated matras. This module uses one of the measures of dispersions, that is, standard deviation to accomplish reconstruction of output line segments. Then words are segmented from the line segments using WordSegmenting Module. This module uses one of the measures of central tendencies, i.e. mean and one of the measure of dispersions i.e, standard deviation to achieve word segmentation. Then characters are segmented from words using CharacterSegmenting Module.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128164463","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088290
S. Ajmera, C. Kumar, P. Yakaiah, B. Kumar, K. Chowdary
the worldwide is advancing towards a self sufficient surrounding at a remarkable pace, and it has to turn out to be a want of an hour, especially, at some point of the present day pandemic situation. Numerous industries have been hampered by the epidemic, with road maintenance and improvement being one among them. Creating a secure running surrounding for employees is a prime problem of street preservation at some point of such tough times. This may be carried out to a degree with the assist of a self-sufficient gadget as a way to goal at decreasing human dependency. The suggested machine uses a Deep Learning based absolutely set of regulations YOLO (You Only Look Once) for the detection of pothole. Further, a picture processing primarily based totally triangular similarity degree is used for pothole size estimation. The proposed gadget affords moderately correct effects of each pothole detection and size estimation. The proposed gadget additionally allows in decreasing the time required for street preservation. The gadget makes use of a custom-made dataset along with pix of water-logged and dry potholes of diverse shapes and sizes. Detailed real-time overall performance evaluation of modernday deep mastering fashions and item detection frameworks (YOLOv1, YOLOv2, YOLOv3, YOLOv4, Tiny-YOLOv4 YOLOv5, and SSD-mobilenetv2) for detecting the pothole is included.
{"title":"Real-time Pothole Detection using YOLOv5","authors":"S. Ajmera, C. Kumar, P. Yakaiah, B. Kumar, K. Chowdary","doi":"10.1109/ASSIC55218.2022.10088290","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088290","url":null,"abstract":"the worldwide is advancing towards a self sufficient surrounding at a remarkable pace, and it has to turn out to be a want of an hour, especially, at some point of the present day pandemic situation. Numerous industries have been hampered by the epidemic, with road maintenance and improvement being one among them. Creating a secure running surrounding for employees is a prime problem of street preservation at some point of such tough times. This may be carried out to a degree with the assist of a self-sufficient gadget as a way to goal at decreasing human dependency. The suggested machine uses a Deep Learning based absolutely set of regulations YOLO (You Only Look Once) for the detection of pothole. Further, a picture processing primarily based totally triangular similarity degree is used for pothole size estimation. The proposed gadget affords moderately correct effects of each pothole detection and size estimation. The proposed gadget additionally allows in decreasing the time required for street preservation. The gadget makes use of a custom-made dataset along with pix of water-logged and dry potholes of diverse shapes and sizes. Detailed real-time overall performance evaluation of modernday deep mastering fashions and item detection frameworks (YOLOv1, YOLOv2, YOLOv3, YOLOv4, Tiny-YOLOv4 YOLOv5, and SSD-mobilenetv2) for detecting the pothole is included.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128450810","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088298
Subhashree Darshana, Kasturi Soumyakanta
Developing an automated classification system for medicinal herbs is indeed a time-consuming and complicated task. Plants have been used for medicinal purposes for millennia. Ayurvedic herbs are gaining popularity in the medical industry due to fewer dangerous side effects and lower costs compared to modern pharmaceuticals. According to these facts, we have expressed a strong interest in the discovery research of Ayurvedic herbal medicines. This study examines theefficiency and reliability of several algorithms of machine learning for plant classification based on photos of leaves used in current history. Assessments of their benefits and drawbacks are also presented. The paper includes image processing algorithms that are used to recognize leaf and obtain significant leaf properties for particular machine learning approaches.
{"title":"A Revolutionary Machine-Learning based approach for identifying Ayurvedic Medicinal Plants","authors":"Subhashree Darshana, Kasturi Soumyakanta","doi":"10.1109/ASSIC55218.2022.10088298","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088298","url":null,"abstract":"Developing an automated classification system for medicinal herbs is indeed a time-consuming and complicated task. Plants have been used for medicinal purposes for millennia. Ayurvedic herbs are gaining popularity in the medical industry due to fewer dangerous side effects and lower costs compared to modern pharmaceuticals. According to these facts, we have expressed a strong interest in the discovery research of Ayurvedic herbal medicines. This study examines theefficiency and reliability of several algorithms of machine learning for plant classification based on photos of leaves used in current history. Assessments of their benefits and drawbacks are also presented. The paper includes image processing algorithms that are used to recognize leaf and obtain significant leaf properties for particular machine learning approaches.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133556026","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088376
V. N. Reddy, N. Shaik, P. Rao, S. Nyamatulla
One of the most common cancers, particularly among women, is breast cancer. Cancer that originates in the breast tissue is called breast cancer. Indications of bosom disease could remember a protuberance for the bosom. Fluid emerges from the nipple by changing shape and dimpling the skin. When cells in the breast begin to grow out of control, breast cancer develops. Through screening and precise identification of masses, microcalcifications, and structural bends, mammography is the most effective and reliable method for the early detection of breasttumors. Breast disease is the leading cause of death for women worldwide. It is evident that recognizing danger early can aid in the investigation of a woman's infection and significantly increase the likelihood of survival. To find an abnormality in mammogram images, this novel segmentation technique, which is based on Iterative algorithms like the Markov random field (MRF) model, is proposed here. This algorithm processes the label with the lowest energy for all iterations. A label and boundary MRF can have a highly compressed relation thanks to this approach.
{"title":"Breast Cancer Detection by Using Radient Based Algorithm on Mammogram Images","authors":"V. N. Reddy, N. Shaik, P. Rao, S. Nyamatulla","doi":"10.1109/ASSIC55218.2022.10088376","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088376","url":null,"abstract":"One of the most common cancers, particularly among women, is breast cancer. Cancer that originates in the breast tissue is called breast cancer. Indications of bosom disease could remember a protuberance for the bosom. Fluid emerges from the nipple by changing shape and dimpling the skin. When cells in the breast begin to grow out of control, breast cancer develops. Through screening and precise identification of masses, microcalcifications, and structural bends, mammography is the most effective and reliable method for the early detection of breasttumors. Breast disease is the leading cause of death for women worldwide. It is evident that recognizing danger early can aid in the investigation of a woman's infection and significantly increase the likelihood of survival. To find an abnormality in mammogram images, this novel segmentation technique, which is based on Iterative algorithms like the Markov random field (MRF) model, is proposed here. This algorithm processes the label with the lowest energy for all iterations. A label and boundary MRF can have a highly compressed relation thanks to this approach.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115171599","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088299
A. Vashishtha, A. Acharya, Sujata Swain
Alzheimer's disease (AD) is a gradual, lifelong dementia that typically affects elderly adults. Alzheimer's disease affects memory, listening, and other cognitive skills. Early Alzheimer's diagnosis is difficult for clinicians. Machine learning and deep convolution neural network (CNN) based techniques can handle brain imaging data processing difficulties. Clinical studies have employed MRI to detect Alzheimer's. In the proposed work we are using a deep Siamese-based neural network to automatically diagnose Alzheimer's disease from a Brain MRI images. Each MRI image of the brain is separated into two segments, which are sent into a network that compares their symmetric structure and infection levels. We are using the Kaggle dataset to train and evaluate for Alzheimer's model. This algorithm could help doctors to identify Alzheimer's from MRI images. The model exceeds the state-of-the-art in every output metric, indicating reduced bias and better generalization.
{"title":"Automatically detection of multi-class Alzheimer disease using Deep Siamese Convolutional Neural Network","authors":"A. Vashishtha, A. Acharya, Sujata Swain","doi":"10.1109/ASSIC55218.2022.10088299","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088299","url":null,"abstract":"Alzheimer's disease (AD) is a gradual, lifelong dementia that typically affects elderly adults. Alzheimer's disease affects memory, listening, and other cognitive skills. Early Alzheimer's diagnosis is difficult for clinicians. Machine learning and deep convolution neural network (CNN) based techniques can handle brain imaging data processing difficulties. Clinical studies have employed MRI to detect Alzheimer's. In the proposed work we are using a deep Siamese-based neural network to automatically diagnose Alzheimer's disease from a Brain MRI images. Each MRI image of the brain is separated into two segments, which are sent into a network that compares their symmetric structure and infection levels. We are using the Kaggle dataset to train and evaluate for Alzheimer's model. This algorithm could help doctors to identify Alzheimer's from MRI images. The model exceeds the state-of-the-art in every output metric, indicating reduced bias and better generalization.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115772883","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：