Pub Date : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986459
Hanif Zafor, Nabajyoti Mazumdar, A. Nag
A huge number of sensor hubs constitute wireless sensor networks (WSNs), each of which has at least one sensor, a power unit, a radio device for data transfer, and a processing unit. Sensor nodes are deployed geographically and equipped with low limited energy to monitor our environment and transfer data to a Sink node called base station (B.S). The data transmission may be in a single-hop or multiple-hop for the further processing. WSN confronts a number of difficulties, including energy constraints, coverage issues, and sensor node failure owing to a variety of factors. The survey research gives you quick and easy access to the notion of existing energy-efficient, coverage-aware, and fault-tolerant solutions. With this motive in mind, and taking into account the influence of the clustering process on the control and management of WSN energy usage. To address these issues, we looked at various current solutions in survey articles on cluster-based WSN routing protocols in terms of energy efficiency, coverage awareness, and fault tolerance. In this study, we assessed the articles in a static sink node based on their Characteristics and Objectives of different WSN clustering approaches, which we presented in two tables. Researchers may find this survey useful at the beginning for a quick understanding on gaps or shortcomings in the area of WSN static sink in order to conduct future research.
{"title":"A comparative study of survey papers based on energy efficient, coverage-aware, and fault tolerant in static sink node of WSN","authors":"Hanif Zafor, Nabajyoti Mazumdar, A. Nag","doi":"10.1109/UPCON56432.2022.9986459","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986459","url":null,"abstract":"A huge number of sensor hubs constitute wireless sensor networks (WSNs), each of which has at least one sensor, a power unit, a radio device for data transfer, and a processing unit. Sensor nodes are deployed geographically and equipped with low limited energy to monitor our environment and transfer data to a Sink node called base station (B.S). The data transmission may be in a single-hop or multiple-hop for the further processing. WSN confronts a number of difficulties, including energy constraints, coverage issues, and sensor node failure owing to a variety of factors. The survey research gives you quick and easy access to the notion of existing energy-efficient, coverage-aware, and fault-tolerant solutions. With this motive in mind, and taking into account the influence of the clustering process on the control and management of WSN energy usage. To address these issues, we looked at various current solutions in survey articles on cluster-based WSN routing protocols in terms of energy efficiency, coverage awareness, and fault tolerance. In this study, we assessed the articles in a static sink node based on their Characteristics and Objectives of different WSN clustering approaches, which we presented in two tables. Researchers may find this survey useful at the beginning for a quick understanding on gaps or shortcomings in the area of WSN static sink in order to conduct future research.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114595975","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 : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986484
Md. Shahbaz Hussain, Jyoti Kandpal, M. Hasan, Mohd Muqeem
This research presents a novel hybrid complementary metal oxide semiconductor (CMOS) design for a 1-bit complete adder. The investigation of the hybrid-CMOS design style was prompted by the search for good drivability, low-energy, and noise-robustness operation for deep submicron. Various CMOS logic style circuits are used in hybrid-CMOS design style to design a novel design of full adders with desired performance. This dramatically reduces design efforts by giving designers more freedom to focus on various applications. This work implements a novel full adder design using the FinFET 16 nm technology. At first, an XOR-XNOR circuit is presented that concurrently generates the XOR-XNOR full swing outputs, which is used to implement the full adder. The proposed design reports 23.64% to 74.95% and 13.47% to 81.31 % improvement in power delay product (PDP) and energy-delay product (EDP), respectively, over existing adders.
{"title":"A High-Performance Hybrid Full Adder Circuit","authors":"Md. Shahbaz Hussain, Jyoti Kandpal, M. Hasan, Mohd Muqeem","doi":"10.1109/UPCON56432.2022.9986484","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986484","url":null,"abstract":"This research presents a novel hybrid complementary metal oxide semiconductor (CMOS) design for a 1-bit complete adder. The investigation of the hybrid-CMOS design style was prompted by the search for good drivability, low-energy, and noise-robustness operation for deep submicron. Various CMOS logic style circuits are used in hybrid-CMOS design style to design a novel design of full adders with desired performance. This dramatically reduces design efforts by giving designers more freedom to focus on various applications. This work implements a novel full adder design using the FinFET 16 nm technology. At first, an XOR-XNOR circuit is presented that concurrently generates the XOR-XNOR full swing outputs, which is used to implement the full adder. The proposed design reports 23.64% to 74.95% and 13.47% to 81.31 % improvement in power delay product (PDP) and energy-delay product (EDP), respectively, over existing adders.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114631911","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}
Identification and segregation of defective fruits from healthy ones is an important task in the fruit processing industry. In this research paper, we showcase a method for defective lemon fruit classification using different versions of Generative Adversarial Networks (GANs) and Transfer Learning. The algorithm begins with preprocessing the lemon images followed by data augmentation using GANs. GANs generated different versions of original lemon images, which further helped in increasing the size of training data which is required for improving the classification accuracy. After this, all the original and augmented images used as training dataset, which has been utilized by pre-trained Convolutional Networks (CNNs) model where fine-tuning helped in classifying test images. Here, the Lemons Quality Control Dataset was used as the base dataset for conducting all experiments throughout this work.
{"title":"Defective Fruit Classification using Variations of GAN for Augmentation","authors":"Prateek Durgapal, Divyesh Rana, Saksham Aggarwal, Anjali Gautam","doi":"10.1109/UPCON56432.2022.9986472","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986472","url":null,"abstract":"Identification and segregation of defective fruits from healthy ones is an important task in the fruit processing industry. In this research paper, we showcase a method for defective lemon fruit classification using different versions of Generative Adversarial Networks (GANs) and Transfer Learning. The algorithm begins with preprocessing the lemon images followed by data augmentation using GANs. GANs generated different versions of original lemon images, which further helped in increasing the size of training data which is required for improving the classification accuracy. After this, all the original and augmented images used as training dataset, which has been utilized by pre-trained Convolutional Networks (CNNs) model where fine-tuning helped in classifying test images. Here, the Lemons Quality Control Dataset was used as the base dataset for conducting all experiments throughout this work.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125004378","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 : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986464
Vipin Kumar Chaudhary, Mukesh Singh, Bharat Lal
Future transportation is expected to rely on electric vehicles due to their durability and the reduced emissions of greenhouse gases and $CO_{2}$. However, the continual increase in the penetration of an electrical load leads to several other problems, including voltage configuration, identifying the best placement location for electric vehicle charging stations, and increasing net operating power losses of the distribution system. And also reduced voltage stability amplitude after deploying electric vehicle charging stations to the distribution network. As mentioned, it is essential to deploy the two algorithm-based appropriate electric vehicle charging stations in the proper location. One is the mathematical modeling-based electric vehicle charging station load, and the other is the random modeling-based electric vehicle charging station load. This study is based on the type of electric vehicle charging stations and their location and observed the voltage profile configuration, total power of the system, total line losses, real power, and reactive power. The proposed approach is verified on the IEEE-33 bus system with and without electric vehicle charging station modes and simulated using MATLAB programming tools. Finally, to signify the importance of electric vehicle charging station load systems, the authors will discuss the strengths and weaknesses of each solution. And also discuss the comparison between mathematical modeling-based electric vehicle charging station load and random modeling-based electric vehicle charging station load.
{"title":"Deployment Impact of Electric Vehicle Charging Stations on Radial Distribution System","authors":"Vipin Kumar Chaudhary, Mukesh Singh, Bharat Lal","doi":"10.1109/UPCON56432.2022.9986464","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986464","url":null,"abstract":"Future transportation is expected to rely on electric vehicles due to their durability and the reduced emissions of greenhouse gases and $CO_{2}$. However, the continual increase in the penetration of an electrical load leads to several other problems, including voltage configuration, identifying the best placement location for electric vehicle charging stations, and increasing net operating power losses of the distribution system. And also reduced voltage stability amplitude after deploying electric vehicle charging stations to the distribution network. As mentioned, it is essential to deploy the two algorithm-based appropriate electric vehicle charging stations in the proper location. One is the mathematical modeling-based electric vehicle charging station load, and the other is the random modeling-based electric vehicle charging station load. This study is based on the type of electric vehicle charging stations and their location and observed the voltage profile configuration, total power of the system, total line losses, real power, and reactive power. The proposed approach is verified on the IEEE-33 bus system with and without electric vehicle charging station modes and simulated using MATLAB programming tools. Finally, to signify the importance of electric vehicle charging station load systems, the authors will discuss the strengths and weaknesses of each solution. And also discuss the comparison between mathematical modeling-based electric vehicle charging station load and random modeling-based electric vehicle charging station load.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116951641","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 : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986416
Radhakrishna Dodmane, R. K. R., Surendra Shetty, K. N. S., B. K., Sardar M. N. Islam
In a modern computing world, transmission of the confidential information over public network is very challenge. Various solutions have been proposed to provide the confidentiality, authenticity against the unauthorized access the information's. One of the secure solutions considered in this work under symmetric block cipher technique is Advanced Encryption Standard (AES). To enhance the efficiency of the AES, two non-linear feedback shift operations are enabled. The first non-linearity is achieved through Cipher Feedback mode (CFB), whereas the second non-linearity is through Output Feedback mode (OFB). The non-linearity and value-based rotation in each round would help in increasing the resistivity against the attacks. Whereas the reduction of one round of AES while processing every block of data would help in reducing the overall time required to process the information's. The proposed implementation has tested to verify the possible improvement in the efficiency, the same is discussed in result and discussion.
{"title":"Implementation of Non-Linear Feedback Stream Cipher System through Hybrid block Cipher Mode to Enhance the Resistivity and Computation Speed of AES","authors":"Radhakrishna Dodmane, R. K. R., Surendra Shetty, K. N. S., B. K., Sardar M. N. Islam","doi":"10.1109/UPCON56432.2022.9986416","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986416","url":null,"abstract":"In a modern computing world, transmission of the confidential information over public network is very challenge. Various solutions have been proposed to provide the confidentiality, authenticity against the unauthorized access the information's. One of the secure solutions considered in this work under symmetric block cipher technique is Advanced Encryption Standard (AES). To enhance the efficiency of the AES, two non-linear feedback shift operations are enabled. The first non-linearity is achieved through Cipher Feedback mode (CFB), whereas the second non-linearity is through Output Feedback mode (OFB). The non-linearity and value-based rotation in each round would help in increasing the resistivity against the attacks. Whereas the reduction of one round of AES while processing every block of data would help in reducing the overall time required to process the information's. The proposed implementation has tested to verify the possible improvement in the efficiency, the same is discussed in result and discussion.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126353608","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 : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986415
P. Prakash, K. Kumar
Reliability is a very well-known matter in now day's Grid systems and it is anticipated to become still more difficult in the next generation systems. Because the ongoing fault tolerance approaches like checkpoint and replication techniques are examined to be ineffectual due to performance and suitability issues, improved fault tolerance approaches are today under inspection. The fault tolerance used taking place fault prediction and detection in organize to minimize collision of failure on system and detect faulty and non-faulty resources. In this research, we traverse the tradition of artificial neural network for fault prediction and fault detection improvement in a fault tolerance context. Outcomes display the prediction and detection performance improvement of the prior thresholds trigger and classifying approach.
{"title":"Artificial Neural Network Based Fault Prediction and Detection in Grid Computing","authors":"P. Prakash, K. Kumar","doi":"10.1109/UPCON56432.2022.9986415","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986415","url":null,"abstract":"Reliability is a very well-known matter in now day's Grid systems and it is anticipated to become still more difficult in the next generation systems. Because the ongoing fault tolerance approaches like checkpoint and replication techniques are examined to be ineffectual due to performance and suitability issues, improved fault tolerance approaches are today under inspection. The fault tolerance used taking place fault prediction and detection in organize to minimize collision of failure on system and detect faulty and non-faulty resources. In this research, we traverse the tradition of artificial neural network for fault prediction and fault detection improvement in a fault tolerance context. Outcomes display the prediction and detection performance improvement of the prior thresholds trigger and classifying approach.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"258 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132840719","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 : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986450
Bhoomika R, Shreyas Shahane, Siri T C, T. Rao, Ashwini Kodipalli, Pradeep Kumar Chodon
Parkinson's disease is a neurodegenerative disorder that occurs in elder people and affects movement with visible symptoms gradually escalates to a maximum over a period of time. Basic body functions namely walking, hearing, speaking, etc., are affected by this disease. Analysis of this disease can be done using ensemble learning algorithms that produce good results. As a result, the best one picked will have the maximum accuracy in determining if the patient has the condition. Dataset is obtained from the UCI ML (Machine Learning) depository, and is named Parkinson disease dataset which has repeated features that are acoustic in nature and contains a list of 240 cases with 48 different features whose performance metrics are measured by utilizing various ensemble learning techniques. As a consequence, the ideal outcome is chosen with the greatest precision since applications in medical management often demand greater precision and efficiency is of the utmost importance. Random forest, Bagging, AdaBoosting and Gradient Boosting are the models used in the process. These models can be useful to doctors in predicting disease by anticipating the symptoms exhibited in patients.
{"title":"Ensemble Learning Approaches for Detecting Parkinson's Disease","authors":"Bhoomika R, Shreyas Shahane, Siri T C, T. Rao, Ashwini Kodipalli, Pradeep Kumar Chodon","doi":"10.1109/UPCON56432.2022.9986450","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986450","url":null,"abstract":"Parkinson's disease is a neurodegenerative disorder that occurs in elder people and affects movement with visible symptoms gradually escalates to a maximum over a period of time. Basic body functions namely walking, hearing, speaking, etc., are affected by this disease. Analysis of this disease can be done using ensemble learning algorithms that produce good results. As a result, the best one picked will have the maximum accuracy in determining if the patient has the condition. Dataset is obtained from the UCI ML (Machine Learning) depository, and is named Parkinson disease dataset which has repeated features that are acoustic in nature and contains a list of 240 cases with 48 different features whose performance metrics are measured by utilizing various ensemble learning techniques. As a consequence, the ideal outcome is chosen with the greatest precision since applications in medical management often demand greater precision and efficiency is of the utmost importance. Random forest, Bagging, AdaBoosting and Gradient Boosting are the models used in the process. These models can be useful to doctors in predicting disease by anticipating the symptoms exhibited in patients.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131155543","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 : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986427
Anurag Tiwari, V. K. Srivastava
Image watermarking techniques provides security, reliability copyright protection for various multimedia contents. In this paper Integer Wavelet Transform Schur decomposition and Singular value decomposition (SVD) based image watermarking scheme is suggested for the integrity protection of dicom images. In the proposed technique 3-level Integer wavelet transform (IWT) is subjected into the Dicom ultrasound image of liver cover image and in HH sub-band Schur decomposition is applied. The upper triangular matrix obtained from Schur decomposition of HH sub-band is further processed with SVD to attain the singular values. The X-ray watermark image is pre-processed before embedding into cover image by applying 3-level IWT is applied into it and singular matrix of LL sub-band is embedded. The watermarked image is encrypted using Arnold chaotic encryption for its integrity protection. The performance of suggested scheme is tested under various attacks like filtering (median, average, Gaussian) checkmark (histogram equalization, rotation, horizontal and vertical flipping, contrast enhancement, gamma correction) and noise (Gaussian, speckle, Salt & Pepper Noise). The proposed technique provides strong robustness against various attacks and chaotic encryption provides integrity to watermarked image.
{"title":"Integer Wavelet Transform and Dual Decomposition Based Image Watermarking scheme for Reliability of DICOM Medical Image","authors":"Anurag Tiwari, V. K. Srivastava","doi":"10.1109/UPCON56432.2022.9986427","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986427","url":null,"abstract":"Image watermarking techniques provides security, reliability copyright protection for various multimedia contents. In this paper Integer Wavelet Transform Schur decomposition and Singular value decomposition (SVD) based image watermarking scheme is suggested for the integrity protection of dicom images. In the proposed technique 3-level Integer wavelet transform (IWT) is subjected into the Dicom ultrasound image of liver cover image and in HH sub-band Schur decomposition is applied. The upper triangular matrix obtained from Schur decomposition of HH sub-band is further processed with SVD to attain the singular values. The X-ray watermark image is pre-processed before embedding into cover image by applying 3-level IWT is applied into it and singular matrix of LL sub-band is embedded. The watermarked image is encrypted using Arnold chaotic encryption for its integrity protection. The performance of suggested scheme is tested under various attacks like filtering (median, average, Gaussian) checkmark (histogram equalization, rotation, horizontal and vertical flipping, contrast enhancement, gamma correction) and noise (Gaussian, speckle, Salt & Pepper Noise). The proposed technique provides strong robustness against various attacks and chaotic encryption provides integrity to watermarked image.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131290225","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}
Sound localization by human listeners are capable of identifying a particular speaker, by listening to the voice of the speaker over the telephone or an entrance-way out of sight. Machines are incapable of understanding and expressing emotions. Emotions play a important role in today's digital world of remote communication. Emotion recognition can be defined as an act of predicting human's emotion through their voice samples and get the accuracy of prediction thus creating a better Human-Computer Interaction (HCI). There are various states to predict human's emotion based on behaviour, expression, pitch, tone, etc. Few of the emotions are considered to recognize the emotions of a speaker behind the speech. This research was conducted to test an speech emotion recognition (SER) system based on voice samples in two-stage approach, namely feature extraction and classification engine. The first one, the key features used for classification of emotions such as extraction of Mel Frequency Cepstral Coefficients (MFCCs), Mel Spectrogram along with Chroma features. Secondly, we use the Multilayer Perceptron (MLP) classifier, elementary classifying Support Vector Machines (SVM) and dimensionality reductionPrincipal Component Analysis (PCA) as classification methods. The research work is considered on the Toronto Emotional Speech Set (TESS) dataset. The proposed approaches gives us 94.17%, 93.43% and 97.86% classification accuracy respectively.
{"title":"Investigation Using MLP-SVM-PCA Classifiers on Speech Emotion Recognition","authors":"Kabir Jain, Anjali Chaturvedi, Jahnvi Dua, Ramesh Kumar Bhukya","doi":"10.1109/UPCON56432.2022.9986457","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986457","url":null,"abstract":"Sound localization by human listeners are capable of identifying a particular speaker, by listening to the voice of the speaker over the telephone or an entrance-way out of sight. Machines are incapable of understanding and expressing emotions. Emotions play a important role in today's digital world of remote communication. Emotion recognition can be defined as an act of predicting human's emotion through their voice samples and get the accuracy of prediction thus creating a better Human-Computer Interaction (HCI). There are various states to predict human's emotion based on behaviour, expression, pitch, tone, etc. Few of the emotions are considered to recognize the emotions of a speaker behind the speech. This research was conducted to test an speech emotion recognition (SER) system based on voice samples in two-stage approach, namely feature extraction and classification engine. The first one, the key features used for classification of emotions such as extraction of Mel Frequency Cepstral Coefficients (MFCCs), Mel Spectrogram along with Chroma features. Secondly, we use the Multilayer Perceptron (MLP) classifier, elementary classifying Support Vector Machines (SVM) and dimensionality reductionPrincipal Component Analysis (PCA) as classification methods. The research work is considered on the Toronto Emotional Speech Set (TESS) dataset. The proposed approaches gives us 94.17%, 93.43% and 97.86% classification accuracy respectively.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115913943","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 : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986435
Narayana Darapaneni, Sandeep R Rao, Datta Rajaram Sagare, A. Paduri, B. Ds, Soundarya Desai, Sudha Bg, Harsha R
Recent study reveals that the mortality rate due to chronic diseases like heart disease is increasing year on year. Predicting heart disease at an early stage is posing a challenge to the healthcare industry due to multiple contributory factors like high blood pressure, uncontrolled cholesterol, obesity, sedentary lifestyle, smoking, alcohol consumption, etc. An accurate and effective diagnosis of heart disease at an early stage can prevent fatal complications such as heart attacks and strokes significantly. This research will not only help the medical fraternity, medico research scientists, and insurance agencies to assess the probability of heart disease but also help the common man to prevent hospitalization and reduce the expenses for the diagnosis significantly. In the past, multiple studies have been conducted on heart disease prediction using regular human vital parameters. We have expanded the research with family hereditary data of the person and by effectively using this feature we have evaluated model performance changes. We have used machine learning classification algorithms like Logistic Regression, KNN, Naive Bayes, and Decision Tree along with ensemble techniques like Random Forest with boosting algorithms like Ada Boost, XG Boost, etc. We evaluated the model performance with various metrics like precision, F1-score, and recall with more importance to the accuracy of the prediction.
{"title":"Machine Learning Based Classification Algorithms Performance Analysis for Heart Disease Prediction","authors":"Narayana Darapaneni, Sandeep R Rao, Datta Rajaram Sagare, A. Paduri, B. Ds, Soundarya Desai, Sudha Bg, Harsha R","doi":"10.1109/UPCON56432.2022.9986435","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986435","url":null,"abstract":"Recent study reveals that the mortality rate due to chronic diseases like heart disease is increasing year on year. Predicting heart disease at an early stage is posing a challenge to the healthcare industry due to multiple contributory factors like high blood pressure, uncontrolled cholesterol, obesity, sedentary lifestyle, smoking, alcohol consumption, etc. An accurate and effective diagnosis of heart disease at an early stage can prevent fatal complications such as heart attacks and strokes significantly. This research will not only help the medical fraternity, medico research scientists, and insurance agencies to assess the probability of heart disease but also help the common man to prevent hospitalization and reduce the expenses for the diagnosis significantly. In the past, multiple studies have been conducted on heart disease prediction using regular human vital parameters. We have expanded the research with family hereditary data of the person and by effectively using this feature we have evaluated model performance changes. We have used machine learning classification algorithms like Logistic Regression, KNN, Naive Bayes, and Decision Tree along with ensemble techniques like Random Forest with boosting algorithms like Ada Boost, XG Boost, etc. We evaluated the model performance with various metrics like precision, F1-score, and recall with more importance to the accuracy of the prediction.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124457889","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：