Pub Date : 2022-12-10DOI: 10.1109/STCR55312.2022.10009074
Sanjay V, S. P.
A neurological disease is Parkinson's disease. It causes trembling in the hands, trouble walking, losing balance, and coordination. In the high-level stage, there is no access to medical care. Blood test reports, CT scan results, and X-ray reports are not accessible early enough. Early Parkinson’s disease detection is crucial to implement effective treatment. The purpose of the proposed effort was to identify Parkinson’s disease in early prediction using clinical imaging and machine learning technologies. Despite the fact that there are numerous methods for detecting Parkinson’s disease, using MRI scan images still it is a big challenge. In this study, an Adaboost classifier is used with a hybrid PSO algorithm to propose a novel technique for detecting Parkinson’s disease. Adaboost acted as the best classifier among other classifiers. Initially, MRI image best features are extracted and identified by the curvelet transform and principal component analysis. This Ad boost classifier receives optimal features as input. Finally, Adaboost classifieds the MRI images and gave excellent classification accuracy. To evaluate the proposed method three methods metrics namely accuracy, specificity, and sensitivity are used. Based on the results the proposed methods yield greater accuracy than the existing systems.
{"title":"Machine Learning Techniques for Parkinson's Disease Detection","authors":"Sanjay V, S. P.","doi":"10.1109/STCR55312.2022.10009074","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009074","url":null,"abstract":"A neurological disease is Parkinson's disease. It causes trembling in the hands, trouble walking, losing balance, and coordination. In the high-level stage, there is no access to medical care. Blood test reports, CT scan results, and X-ray reports are not accessible early enough. Early Parkinson’s disease detection is crucial to implement effective treatment. The purpose of the proposed effort was to identify Parkinson’s disease in early prediction using clinical imaging and machine learning technologies. Despite the fact that there are numerous methods for detecting Parkinson’s disease, using MRI scan images still it is a big challenge. In this study, an Adaboost classifier is used with a hybrid PSO algorithm to propose a novel technique for detecting Parkinson’s disease. Adaboost acted as the best classifier among other classifiers. Initially, MRI image best features are extracted and identified by the curvelet transform and principal component analysis. This Ad boost classifier receives optimal features as input. Finally, Adaboost classifieds the MRI images and gave excellent classification accuracy. To evaluate the proposed method three methods metrics namely accuracy, specificity, and sensitivity are used. Based on the results the proposed methods yield greater accuracy than the existing systems.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115282889","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009283
V. E., R. D
There is an enormous increase in number of diseases worldwide. The non-communicable diseases such as cardio vascular disease will leads to death. The second major reason of death in people worldwide occurs due to stroke. It affects any portion of brain due to interruption or reduction of Blood supply. The brain damage can be reduced if required actions taken earlier. So there is necessary requirement to build stroke predictive models. The combined techniques of Machine Learning (ML) and Deep Learning (DL) techniques play the vital role in Disease Prediction. There are many researches has been done for stroke prediction using various ML Algorithms. In order to improve accuracy, the proposed model will work on the hybrid ANNRF (Artificial Neural Network-Random Forest). The proposed method can be reached 94% in classification accuracy.
{"title":"A Systematic Method of Stroke Prediction Model based on Big Data and Machine Learning","authors":"V. E., R. D","doi":"10.1109/STCR55312.2022.10009283","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009283","url":null,"abstract":"There is an enormous increase in number of diseases worldwide. The non-communicable diseases such as cardio vascular disease will leads to death. The second major reason of death in people worldwide occurs due to stroke. It affects any portion of brain due to interruption or reduction of Blood supply. The brain damage can be reduced if required actions taken earlier. So there is necessary requirement to build stroke predictive models. The combined techniques of Machine Learning (ML) and Deep Learning (DL) techniques play the vital role in Disease Prediction. There are many researches has been done for stroke prediction using various ML Algorithms. In order to improve accuracy, the proposed model will work on the hybrid ANNRF (Artificial Neural Network-Random Forest). The proposed method can be reached 94% in classification accuracy.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115633857","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009100
Siva Satya Sreedhar, R. Anitha, Priya Rachel, S. Suganya, C. Ramesh Babu Durai, G. S. Uthayakumar
Energy distribution is vital in an IoT-based Wireless Sensor Network (WSN).There is no other fuel source for WSN since they deal with battery systems. This means that when the battery runs out, they have no option except to replace it on a regular basis, which isn't always possible. Information may be lost during transmission as another problem with WSNs. Despite the fact that information disasters are rare, it remains a constant threat. The greatest danger lies in a loss of data. B) CH-to-sink data lost. This article saves energy by forecasting missing node values.
{"title":"Energy Conservation for Environment Monitoring System in an IoT based WSN","authors":"Siva Satya Sreedhar, R. Anitha, Priya Rachel, S. Suganya, C. Ramesh Babu Durai, G. S. Uthayakumar","doi":"10.1109/STCR55312.2022.10009100","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009100","url":null,"abstract":"Energy distribution is vital in an IoT-based Wireless Sensor Network (WSN).There is no other fuel source for WSN since they deal with battery systems. This means that when the battery runs out, they have no option except to replace it on a regular basis, which isn't always possible. Information may be lost during transmission as another problem with WSNs. Despite the fact that information disasters are rare, it remains a constant threat. The greatest danger lies in a loss of data. B) CH-to-sink data lost. This article saves energy by forecasting missing node values.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130310643","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009552
D. Deepa, M. S. Raj, S. Gowthami, K. Hemalatha, C. Poongodi, P. Thangavel
Alzheimer’s Disease is a neurological brain disorder that damages the cells in brain and reduce the ability of the brain from the regular activities. It is a representation of the most common form of adult-onset dementias. Earlier detection of Alzheimer’s disease can be more helpful in predetermining the symptomatic conditions of patients suffering with this problem. By diagnosing the consequences of this disease, with the help of medical scan images, it would be more useful in classifying the patients whether they are suffering from this deadly disease. Machine Learning tends to be more beneficial in diagnosing diseases and implementation of this technique, to Magnetic Resonance Imaging (MRI) inputs in identification of Alzheimer’s disease, resulted in faster prediction of the disease and in the contribution of the evolution of the disease. Carrying out this technique, it is possible to diagnose and predict the individual dementia of adults by screening data of Alzheimer’s disease and inducing Machine Learning classifiers. This work focuses on building an evolving framework to detect Alzheimer’s disease efficiently with the help of neuroimaging technologies and prediction at a very earlier stage by using the data stacked up for Alzheimer’s disease patients.
{"title":"Identification and Analysis of Alzheimer’s Disease using DenseNet Architecture with Minimum Path Length Between Input and Output Layers","authors":"D. Deepa, M. S. Raj, S. Gowthami, K. Hemalatha, C. Poongodi, P. Thangavel","doi":"10.1109/STCR55312.2022.10009552","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009552","url":null,"abstract":"Alzheimer’s Disease is a neurological brain disorder that damages the cells in brain and reduce the ability of the brain from the regular activities. It is a representation of the most common form of adult-onset dementias. Earlier detection of Alzheimer’s disease can be more helpful in predetermining the symptomatic conditions of patients suffering with this problem. By diagnosing the consequences of this disease, with the help of medical scan images, it would be more useful in classifying the patients whether they are suffering from this deadly disease. Machine Learning tends to be more beneficial in diagnosing diseases and implementation of this technique, to Magnetic Resonance Imaging (MRI) inputs in identification of Alzheimer’s disease, resulted in faster prediction of the disease and in the contribution of the evolution of the disease. Carrying out this technique, it is possible to diagnose and predict the individual dementia of adults by screening data of Alzheimer’s disease and inducing Machine Learning classifiers. This work focuses on building an evolving framework to detect Alzheimer’s disease efficiently with the help of neuroimaging technologies and prediction at a very earlier stage by using the data stacked up for Alzheimer’s disease patients.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130563487","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009274
Sanjay V, S. P.
Alzheimer’s disease affects most of the elderly in today's world. It directly affects the neurotransmitters and leads to dementia. MRI images can spot brain irregularities related to mild cognitive damage. It can be useful for predicting Alzheimer’s disease, though it is a big challenge. In this research, a novel technique is proposed to find to detect Alzheimer’s disease using Adaboost classifier with a hybrid PSO algorithm. Initially, MRI image features are extracted, and the best features are identified by the curvelet transform and Principal Component Analysis (PCA). Adaboost proposed methods yield greater accuracy than the existing systems for analyzing MRI images and give excellent classification accuracy. To evaluate the proposed method three methods metrics namely accuracy, specificity, and sensitivity are used. Based on the results the proposed methods yield greater accuracy than the existing systems.
{"title":"An Enhanced Approach for Detecting Alzheimer’s Disease","authors":"Sanjay V, S. P.","doi":"10.1109/STCR55312.2022.10009274","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009274","url":null,"abstract":"Alzheimer’s disease affects most of the elderly in today's world. It directly affects the neurotransmitters and leads to dementia. MRI images can spot brain irregularities related to mild cognitive damage. It can be useful for predicting Alzheimer’s disease, though it is a big challenge. In this research, a novel technique is proposed to find to detect Alzheimer’s disease using Adaboost classifier with a hybrid PSO algorithm. Initially, MRI image features are extracted, and the best features are identified by the curvelet transform and Principal Component Analysis (PCA). Adaboost proposed methods yield greater accuracy than the existing systems for analyzing MRI images and give excellent classification accuracy. To evaluate the proposed method three methods metrics namely accuracy, specificity, and sensitivity are used. Based on the results the proposed methods yield greater accuracy than the existing systems.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126003968","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009414
S. Udaiyakumar, CL Chinnadurrai, C. Anandhakumar, S. Ravindran
In this paper, electricity price forecasting using a hybrid multilayer perceptron, back propagation and modified particle swarm optimization is implemented. Here modified particle swarm optimization technique is used to improve the performance of the backpropagation algorithm while training the multilayer perceptron. Two different MLP are used for electricity price forecasting one MLP is with a single hidden layer and another MLP is with three hidden layers, both the neural networks are trained by BP and initial parameters such as weights between different layers, the bias of the layers, and activation function of each layer except input layer are selected by MPSO. Normally MLP trained by BP uses linear activation functions for all layers and neurons, but in this case, we use three different functions namely linear function, sigmoid function, and tangent function as activation functions. These three different activation functions are independently selected for each neuron by MPSO based on the data set which is used. Because of the independent selection of activation function to each neuron the overall performance, convergence time, and convergence efficiency of the BP are greatly improved. The proposed method is implemented to predict Austria and Northern Italy electricity price.
{"title":"Electricity Price Forecasting using Multilayer Perceptron Optimized by Particle Swarm Optimization","authors":"S. Udaiyakumar, CL Chinnadurrai, C. Anandhakumar, S. Ravindran","doi":"10.1109/STCR55312.2022.10009414","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009414","url":null,"abstract":"In this paper, electricity price forecasting using a hybrid multilayer perceptron, back propagation and modified particle swarm optimization is implemented. Here modified particle swarm optimization technique is used to improve the performance of the backpropagation algorithm while training the multilayer perceptron. Two different MLP are used for electricity price forecasting one MLP is with a single hidden layer and another MLP is with three hidden layers, both the neural networks are trained by BP and initial parameters such as weights between different layers, the bias of the layers, and activation function of each layer except input layer are selected by MPSO. Normally MLP trained by BP uses linear activation functions for all layers and neurons, but in this case, we use three different functions namely linear function, sigmoid function, and tangent function as activation functions. These three different activation functions are independently selected for each neuron by MPSO based on the data set which is used. Because of the independent selection of activation function to each neuron the overall performance, convergence time, and convergence efficiency of the BP are greatly improved. The proposed method is implemented to predict Austria and Northern Italy electricity price.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124584250","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009089
Kalpesh P. Modi, S. Chakole, Sandeep R Sonaskar, Neema Ukani
This paper describes the design and development of SpO2 based simple healthcare system, as an application of embedded system and Internet of Things (IOT). In this paper, minimal open-source hardware based on Infrared (IR) and LEDs is integrated to perform tasks related to healthcare monitoring such as measurement of oxygen level in blood (SpO2) and recording heart rate (beats per minute). It is demonstrated that the prototype is working and reliable readings are obtained repeatedly, through the assembled device. Although it is common to achieve such a prototype [1],[2], this work also illustrates the feasibility of viewing the measurements in real-time on a portable device such as a mobile or PDA, which is suitable for early diagnosis and preventive healthcare. The prototype is further designed and implemented into a compact wearable device, conducive for trials.
{"title":"An Application of Embedded System and IOT: Development of SpO2 based Simple Healthcare System","authors":"Kalpesh P. Modi, S. Chakole, Sandeep R Sonaskar, Neema Ukani","doi":"10.1109/STCR55312.2022.10009089","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009089","url":null,"abstract":"This paper describes the design and development of SpO2 based simple healthcare system, as an application of embedded system and Internet of Things (IOT). In this paper, minimal open-source hardware based on Infrared (IR) and LEDs is integrated to perform tasks related to healthcare monitoring such as measurement of oxygen level in blood (SpO2) and recording heart rate (beats per minute). It is demonstrated that the prototype is working and reliable readings are obtained repeatedly, through the assembled device. Although it is common to achieve such a prototype [1],[2], this work also illustrates the feasibility of viewing the measurements in real-time on a portable device such as a mobile or PDA, which is suitable for early diagnosis and preventive healthcare. The prototype is further designed and implemented into a compact wearable device, conducive for trials.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132324204","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009430
S. Sanjayprabu, R. Sathish Kumar, K. Somasundaram, R. Karthikamani
In December 2019, the SARS-CoV-2 virus, often referred to as COVID-19, was discovered in Wuhan, China. It is very virulent and has spread very quickly throughout the world. With COVID-19, people have described a wide variety of symptoms, from little discomfort to life-threatening respiratory illness. In this study, chest X-ray scan images are preprocessed using an anisotropic diffusion filter and three classifiers, and the Covid-19 cases are classified from the chest X-ray images using the GLRLM feature extraction approach. Common metrics like sensitivity, selectivity, and accuracy are utilized to compare the performance of the classifiers. When compared to other classifiers in this study, the Gaussian Mixture Model had the best accuracy of 91.07%.
{"title":"Mathematical Model for Anisotropic diffusion Filter and GLRLM Feature Extraction to Detect Covid-19 from Chest X-Ray Images","authors":"S. Sanjayprabu, R. Sathish Kumar, K. Somasundaram, R. Karthikamani","doi":"10.1109/STCR55312.2022.10009430","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009430","url":null,"abstract":"In December 2019, the SARS-CoV-2 virus, often referred to as COVID-19, was discovered in Wuhan, China. It is very virulent and has spread very quickly throughout the world. With COVID-19, people have described a wide variety of symptoms, from little discomfort to life-threatening respiratory illness. In this study, chest X-ray scan images are preprocessed using an anisotropic diffusion filter and three classifiers, and the Covid-19 cases are classified from the chest X-ray images using the GLRLM feature extraction approach. Common metrics like sensitivity, selectivity, and accuracy are utilized to compare the performance of the classifiers. When compared to other classifiers in this study, the Gaussian Mixture Model had the best accuracy of 91.07%.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132383815","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009501
R. K, G. Flora, S. K, Lakshmi Priya. P, N. V
The rise of Covid-19 pandemic has exaggerated the necessity for safe, quick and sensitive diagnostic tools to confirm the protection of tending employees and patients. Although ML has shown success in medical imaging, existing studies concentrate on Covid-19 medicine victimization using Deep Learning (DL) with X-ray and computed axial Tomography (CT) scans. During this study we tend to aim to implement CNN model on Lung Ultrasound (LUS), to assist doctors with the designation of Covid-19 patients. We selected LUS since it's quicker, cheaper and additional out there in rural areas compared to CT and X- ray. We have used the biggest public dataset containing LUS pictures and videos of Covid, Pneumonia and healthy patients that has been collected from totally different resources. We tried out frame level approach that extracted 5 frames per patient video. We'll use this dataset to experiment with a CNN model that has hyper parameter calibration. We conjointly enclosed explainable AI using Grad-CAM that uses gradients of a selected target that flows through the convolutional network to localize and highlight regions of the target within the image. Moreover, we'll experiment with completely different data preprocessing techniques that may aid with pattern recognition and increasing the DL model’s accuracy like histogram equalization, standardization, Principle Component Analysis (PCA) and Synthetic Minority Oversampling Technique (SMOTE). Lastly, we tend to create a straightforward application that diagnoses LUS videos with our CNN model, and shows the frame results with visual illustration of why the model has taken certain prediction with the help of Gradient-Weighted category Activation Mapping (Grad-CAM).
{"title":"Viral Pneumonia and Covid Screening on Lung Ultrasound","authors":"R. K, G. Flora, S. K, Lakshmi Priya. P, N. V","doi":"10.1109/STCR55312.2022.10009501","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009501","url":null,"abstract":"The rise of Covid-19 pandemic has exaggerated the necessity for safe, quick and sensitive diagnostic tools to confirm the protection of tending employees and patients. Although ML has shown success in medical imaging, existing studies concentrate on Covid-19 medicine victimization using Deep Learning (DL) with X-ray and computed axial Tomography (CT) scans. During this study we tend to aim to implement CNN model on Lung Ultrasound (LUS), to assist doctors with the designation of Covid-19 patients. We selected LUS since it's quicker, cheaper and additional out there in rural areas compared to CT and X- ray. We have used the biggest public dataset containing LUS pictures and videos of Covid, Pneumonia and healthy patients that has been collected from totally different resources. We tried out frame level approach that extracted 5 frames per patient video. We'll use this dataset to experiment with a CNN model that has hyper parameter calibration. We conjointly enclosed explainable AI using Grad-CAM that uses gradients of a selected target that flows through the convolutional network to localize and highlight regions of the target within the image. Moreover, we'll experiment with completely different data preprocessing techniques that may aid with pattern recognition and increasing the DL model’s accuracy like histogram equalization, standardization, Principle Component Analysis (PCA) and Synthetic Minority Oversampling Technique (SMOTE). Lastly, we tend to create a straightforward application that diagnoses LUS videos with our CNN model, and shows the frame results with visual illustration of why the model has taken certain prediction with the help of Gradient-Weighted category Activation Mapping (Grad-CAM).","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"107 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121559820","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009199
N. Sowmya, I. Babu
Latent fingerprints were found frequently in criminal investigations. Thus, Overlapped Fingerprint Recognition (OFR) technology plays key role in many applications. The OFR technology is a relatively new area which is a challenging and critical area of research work. The conventional methods are struggles in achieving high accuracy due to improper features. Thus, this article focused on implementation of OFR technology with multiple descriptors based modified dimensionality reduction mechanism. The proposed OFR is developed with gradient variation approach by using Kirsch edge detection to overcome the problems of conventional approaches. The dimension of the extracted feature space is reduced using the Kernel Principal Component Analysis (KPCA) method. Finally, Support Vector Machine (SVM) classifier is applied to classify the overlapped region of test image by comparing with the training database. Simulation results shows that the proposed method increases accuracy, specificity and sensitivity as compared to the existing methods.
{"title":"Machine Learning System for Recognition and Classification of Overlapped Fingerprints","authors":"N. Sowmya, I. Babu","doi":"10.1109/STCR55312.2022.10009199","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009199","url":null,"abstract":"Latent fingerprints were found frequently in criminal investigations. Thus, Overlapped Fingerprint Recognition (OFR) technology plays key role in many applications. The OFR technology is a relatively new area which is a challenging and critical area of research work. The conventional methods are struggles in achieving high accuracy due to improper features. Thus, this article focused on implementation of OFR technology with multiple descriptors based modified dimensionality reduction mechanism. The proposed OFR is developed with gradient variation approach by using Kirsch edge detection to overcome the problems of conventional approaches. The dimension of the extracted feature space is reduced using the Kernel Principal Component Analysis (KPCA) method. Finally, Support Vector Machine (SVM) classifier is applied to classify the overlapped region of test image by comparing with the training database. Simulation results shows that the proposed method increases accuracy, specificity and sensitivity as compared to the existing methods.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"181 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125473281","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：