P. G. K. Prince, J. J. Bethanney, S. Poojahsri, S.K Sounder, J. Premalatha, D. Marshiana
{"title":"Recognition of emotions using non-contact breadth analyzer","authors":"P. G. K. Prince, J. J. Bethanney, S. Poojahsri, S.K Sounder, J. Premalatha, D. Marshiana","doi":"10.1109/ICCPC55978.2022.10072117","DOIUrl":"https://doi.org/10.1109/ICCPC55978.2022.10072117","url":null,"abstract":"Automation of emotion detection has been done in many methods. The method followed here is detection of emotions through the pattern of respiration. A non-contact infrared temperature sensor is used to detect the pattern of respiration. The signals acquired from the sensor in analyzed. 10 statistical features are extracted. Feature reduction is done by applying Principle component analysis and 4 PCAs are obtained. These features are applied to supervised and unsupervised classification algorithm. Trilayered neural network has an accuracy of 95.5%","PeriodicalId":367848,"journal":{"name":"2022 International Conference on Computer, Power and Communications (ICCPC)","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132941338","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}
J. Shirisha, M. Rajkumar, D. Sangeetha, R. Sabitha, B. Kannan, S. Renukadevi
{"title":"Elliptical Curve Diffe-Hellman Algorithm for discovering Duplication Attack in Mobile WSN","authors":"J. Shirisha, M. Rajkumar, D. Sangeetha, R. Sabitha, B. Kannan, S. Renukadevi","doi":"10.1109/ICCPC55978.2022.10072042","DOIUrl":"https://doi.org/10.1109/ICCPC55978.2022.10072042","url":null,"abstract":"Wireless Sensor Network (WSN) is the greatest susceptible of all the wireless sensor nodes. In the WSN, several widespread attacks were launched in the rival world. The most problematic are complete attack identification and avoidance of node duplication. The period it takes to recognize and separate a duplicated sensor node is typically higher than other attack recognition methods owing to the related identity and features copied through the attacker. Elliptical Curve Diffe-Hellman Algorithm is employed for discovering duplication attack (ECDD) in Mobile WSN. This approach aims to distinguish duplicated sensor nodes in the mobile WSN. In this approach, the public and private keys are used for verification. The ECDD method interacts with the secret key to distinguish the duplicate sensor node and separate it from routing, raising the network function. The simulation examination demonstrates a lesser false negative ratio and increases duplicate attack detection in the network.","PeriodicalId":367848,"journal":{"name":"2022 International Conference on Computer, Power and Communications (ICCPC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122227594","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}
V. Venkatesh, Pethuru Rai, Kalluru Amarnath Reddy, S. Praba, R. Anushiadevi
{"title":"An intelligent framework for heart disease prediction deep learning-based ensemble Method","authors":"V. Venkatesh, Pethuru Rai, Kalluru Amarnath Reddy, S. Praba, R. Anushiadevi","doi":"10.1109/ICCPC55978.2022.10072285","DOIUrl":"https://doi.org/10.1109/ICCPC55978.2022.10072285","url":null,"abstract":"Recently, wearable sensors used in Body Area Networks (BANs) have more competencies for sensing the environments, data storage, processing, and information transfer. BANs furnish different techniques to monitor activities in various medical field applications to accurately detect heart disease. Forgiving efficient treatment for heart disease to heart patients, exact prediction is more important in medical research. A machine learning model over health care data is an important goal for heart disease prediction. Different machine learning techniques have been used in existing research that pointed out inaccurate decision-making over clinical data obtained; some improvements are needed to predict heart disease before a heart attack occurs accurately. This paper proposes an intelligent framework for heart disease prediction using edge computing, Cloud computing and ensemble learning techniques. The proposed system is evaluated with heart disease data and compared with traditional ensemble classifiers based on precision, weighting techniques and temporal metrics like arbitration delay and computational expense. The architecture also provides a facility for distributed learning at the node level, ensuring proper resource utilization and boosting accuracy, making it a suitable choice for health care and heavy-load applications. Accuracy of 96.5% was obtained based on the proposed intelligent framework for heart disease prediction at a reasonable latency, making this a unique pick compared to existing works.","PeriodicalId":367848,"journal":{"name":"2022 International Conference on Computer, Power and Communications (ICCPC)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114301741","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}
P. Rathnavel, T. Muthamizhan, G. Prakash, M. Kumar, T. Immanuel, A. Sivakumar
{"title":"Wind Energy Conversion system for Industrial Adaptation Control using IoT","authors":"P. Rathnavel, T. Muthamizhan, G. Prakash, M. Kumar, T. Immanuel, A. Sivakumar","doi":"10.1109/ICCPC55978.2022.10072098","DOIUrl":"https://doi.org/10.1109/ICCPC55978.2022.10072098","url":null,"abstract":"Wind energy is the world's second largest source of renewable energy generation, only after the most extensively employed hydro power, the most extensively employed. A technical revolution is experienced as a result of the development of advanced wind energy conversion systems (WECS), which include multilevel inverters (MLIs). Ripples present in the output waveforms of the traditional rectifier is more, and the MLI exhibits voltage balance concerns across the DC-link capacitor, which is equally a major problem with the conventional rectifier. The design is based on the “Vienna rectifier” architecture for power electronics evaluation and design, over a range of applications, including variable-speed and continuous sinusoidal current and voltage control. This article proposes a simplified proportional-integral (PI) control for minimizing the output waveform ripples, fixing voltage complications, and producing higher-quality waveforms at the output. This results in the development of a substantial alternatives in the field of high-power and medium-voltage energy regulation. Through the use of a new design, low-harmonic multilayer voltage source inverters with low harmonics are able to provide enormous voltages without the use of synchronized switching devices or series-connected transformers.","PeriodicalId":367848,"journal":{"name":"2022 International Conference on Computer, Power and Communications (ICCPC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121103349","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}
Venkatesh Kumar, S. Amirthasri, M. Ananya, S. Esther
{"title":"A Novel Method of IoT Based Smart Notice Board Using Raspberry PI","authors":"Venkatesh Kumar, S. Amirthasri, M. Ananya, S. Esther","doi":"10.1109/ICCPC55978.2022.10072128","DOIUrl":"https://doi.org/10.1109/ICCPC55978.2022.10072128","url":null,"abstract":"Raspberry PI was used in the design of digital notice boards. This works on the principle of IoT. Notice can post through a website and the data can be viewed on a digital notice board. From a distance, notice can update the through the website and additionally, registered users receive notifications on their android phone. Notice board is a typical instrument that is used to display important data. Colleges and other societies rely on pin boards used for posting announcements. This study focuses on the fundamental concept of an IOT- based digital display using a raspberry pi. The objective of this project which has been proposed is to ensure the updating of data and the output is displaced in any internet connected devices. Notice boards are quite important in our daily lives. Information dissemination in a society without paper can be greatly facilitated by replacing the traditional analogue type notice board with a digital notice board. The admin can do this here, update the notice board through the created website via the internet. So, data can be sent anywhere and can be showed in a matter of seconds. The data is usually in the format of texts and images. PC is used for storing and send information and Raspberry pi is linked via WIFI at the receiving position.","PeriodicalId":367848,"journal":{"name":"2022 International Conference on Computer, Power and Communications (ICCPC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121292856","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}
{"title":"Security Enhanced Federated Learning Approach using Blockchain","authors":"S. Revathy, S. Priya","doi":"10.1109/ICCPC55978.2022.10072091","DOIUrl":"https://doi.org/10.1109/ICCPC55978.2022.10072091","url":null,"abstract":"In traditional machine learning approach, data gathered from all the edge devices are sent to centralized server for training and prediction of the output. In the centralized approach, user has to compromise on the data privacy and integrity in sharing their own data to centralized server. To overcome this issue federated machine learning approach was introduced, in which model and data are decentralized and the machine learning model will be trained on the data in local devices and parameters will be sent to cloud server for consensus change, enhancing the data privacy of the users. But still authentication of the nodes to cloud server and vice versa is a major concern to be addressed in federated machine learning as malicious nodes can impersonate as authenticated node and communicate to cloud server. In the proposed model, node authentication is implemented using Ethereum based blockchain with smart contracts thereby enhancing security of Federated machine learning approach. The efficiency of the node authentication is measured and compared with machine learning algorithms which achieves 99% accuracy.","PeriodicalId":367848,"journal":{"name":"2022 International Conference on Computer, Power and Communications (ICCPC)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115984484","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}
R. Srinath, P. Maragathavalli, C. Shalini, Syed Asadh
{"title":"Classification of Diabetic Disorder using Machine Learning Approaches","authors":"R. Srinath, P. Maragathavalli, C. Shalini, Syed Asadh","doi":"10.1109/ICCPC55978.2022.10072213","DOIUrl":"https://doi.org/10.1109/ICCPC55978.2022.10072213","url":null,"abstract":"Diabetes is a serious metabolic condition that can affect the entire body. Untreated diabetes raises the risk of heart stroke, diabetes, and other conditions. Millions of individuals are impacted by this disease around the globe. A chronic illness like diabetes may have an effect on world health. In Accordance to the International Diabetes Federation, 382 million people suffer from diabetes all over the world. This would increase to 592 million by 2035. High blood glucose levels cause diabetes, also referred to as diabetes mellitus. Numerous conventional methods based on physical and chemical investigations can be used to diagnose diabetes. Maintaining a healthy lifestyle requires early diabetes identification. Mechanical studies are a potential technique that can aid in early disease diagnosis and assist medical professionals in making diagnoses. Our goal is to use the Scikit-learn tool to develop a classification model that uses the KNN, MLP, SVM, RFC, and CART algorithms to predict diabetes.","PeriodicalId":367848,"journal":{"name":"2022 International Conference on Computer, Power and Communications (ICCPC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116500634","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}
{"title":"Towards Improving Cloud Security and Performance by using Proposed Controlled Replication Model","authors":"K. Rajalakshmi, M. Sambath, Linda Joseph","doi":"10.1109/ICCPC55978.2022.10072157","DOIUrl":"https://doi.org/10.1109/ICCPC55978.2022.10072157","url":null,"abstract":"Unlike traditional data centres, cloud computing can be used for data hosting and management, allowing the resources to be used in comparable ways. To host data, cloud companies employ a variety of ways. The most popular data is copied using the fewest resources, while the remainder is not. Placing data fragments in the middle and closest nodes to the user reduces access time. Through replication, data is always available, so its availability is ensured. Data files stored in the cloud should always be available to users. Users can replicate data files based on their reputation degree and replication benefits. The purpose of replication is to ensure consistency, availability, and reliability of data by maintaining different copies of the same data on multiple storage servers. Using a cloud provider creates a sense of trust in the belief that data is available whenever needed. Several factors have been considered when developing the Controlled Replication Model for reducing such instances on the cloud platform. These factors are the level of data reputation, the replication benefit, and the replication cost. As a result, it controls replication costs and lowers resource use. Denial of service and reflection attacks are reduced to a certain level, and the system's stability, availability, load balancing, and fault tolerance are increased.","PeriodicalId":367848,"journal":{"name":"2022 International Conference on Computer, Power and Communications (ICCPC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128760224","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}
{"title":"Prediction of Cardio Vascular Disease by Deep Learning and Machine Learning-A Combined Data Science Approach","authors":"A. A. Romalt, R. Kumar","doi":"10.1109/ICCPC55978.2022.10072141","DOIUrl":"https://doi.org/10.1109/ICCPC55978.2022.10072141","url":null,"abstract":"Machine learning is the process in which the computer system can automatically learn from the data. It's an application of Artificial Intelligence without being explicitly programmed. Making use of Machine learning and AI an efficient algorithm for prediction of Cardio Vascular Disease (CVD) can be done. By combing Deep learning method to the ML model, a high-level abstract feature with improved performance can be obtained. Heart disease or Cardio Vascular disease is the predominant disease all over the world. Accurate prediction of heart disease is a challenging task. The accuracy of prediction can be improved by applying Machine learning algorithms. Results with high accuracy can be produced by combining a Machine learning model with Statistical concepts. The main objective of this research is to predict high accurate CVD by applying Deep learning model combined with Machine learning algorithm. By recognizing the symptoms of the disease, people can get prompt treatment on time.","PeriodicalId":367848,"journal":{"name":"2022 International Conference on Computer, Power and Communications (ICCPC)","volume":"30 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130573004","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}
M. Soundarya, P. R. Karthikeyan, K. Ganapathy, Gunasekar Thangarasu
{"title":"Automatic Speech Recognition using the Melspectrogram-based method for English Phonemes","authors":"M. Soundarya, P. R. Karthikeyan, K. Ganapathy, Gunasekar Thangarasu","doi":"10.1109/ICCPC55978.2022.10072076","DOIUrl":"https://doi.org/10.1109/ICCPC55978.2022.10072076","url":null,"abstract":"An automatic speech recognition (ASR) technique may be set up to forecast the pronunciation of textual identifiers (such as song names) based on assumptions about the language or languages in which the textual identifier was originally written. To identify mispronunciation, custom acoustic-phonetic elements are typically used. This study examines the use of deep convolutional neural networks to identify English phonemes that have been mispronounced in musical samples. Convolutional neural networks (CNNs) are now often employed in systems recognizing speech. In this work, a decoded-based architecture is proposed in which the spectrogram feature that corresponds with the auditory features is proposed by comparing the various inputs to the model. Following the selection of the input features, this research examines the design principles of learning parameters and their application to voice recognition with various parameters. To identify mispronunciation, custom acoustic-phonetic elements are typically used. This research work also examines the application of learning models. The proposed method achieves better results with 85% of accuracy and a Word Error Rate of 8.1 on comparing with existing works.","PeriodicalId":367848,"journal":{"name":"2022 International Conference on Computer, Power and Communications (ICCPC)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129783232","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}