Pub Date : 2022-12-14DOI: 10.1109/IC3I56241.2022.10072500
V. Veeraiah, G. K. Ravikaumar, D. Bhuva, Rajesh Singh, Adusupalle Muni Raju, Unnati Joshi
A brand-new paradigm known as the Internet of Things (IoT) offers a variety of innovative services for the upcoming wave of technological breakthroughs. There are several IoT applications that enable seamless connections between the real and digital worlds. Notwithstanding the huge endeavors of normalization bodies, alliances, organizations, scientists, and others, there are as yet various issues to be settled before the capability of IoT can be totally understood. While breaking down these concerns, various perspectives, for example, empowering innovation, applications, plans of action, cultural implications, and natural effects, ought to be thought about. This exposition centers on recent concerns and difficulties as seen according to an innovative viewpoint. To empower a superior comprehension of the IoT’s parts, we have highlighted many views that support this paradigm.Additionally, this thorough analysis offers insights into the most recent developments in emerging and IoT supporting technologies. Details are provided for the ones that are the most important. The primary goal is to provide a thorough review of the problems and obstacles that need to be overcome by future research. In order to aid future study, we offer some insights into certain specific emerging theories. Additionally, this publication organises the body of literature by categorising contributions into various research areas.
{"title":"Definitions, Difficulties and Current Research Directions for the Internet of Things","authors":"V. Veeraiah, G. K. Ravikaumar, D. Bhuva, Rajesh Singh, Adusupalle Muni Raju, Unnati Joshi","doi":"10.1109/IC3I56241.2022.10072500","DOIUrl":"https://doi.org/10.1109/IC3I56241.2022.10072500","url":null,"abstract":"A brand-new paradigm known as the Internet of Things (IoT) offers a variety of innovative services for the upcoming wave of technological breakthroughs. There are several IoT applications that enable seamless connections between the real and digital worlds. Notwithstanding the huge endeavors of normalization bodies, alliances, organizations, scientists, and others, there are as yet various issues to be settled before the capability of IoT can be totally understood. While breaking down these concerns, various perspectives, for example, empowering innovation, applications, plans of action, cultural implications, and natural effects, ought to be thought about. This exposition centers on recent concerns and difficulties as seen according to an innovative viewpoint. To empower a superior comprehension of the IoT’s parts, we have highlighted many views that support this paradigm.Additionally, this thorough analysis offers insights into the most recent developments in emerging and IoT supporting technologies. Details are provided for the ones that are the most important. The primary goal is to provide a thorough review of the problems and obstacles that need to be overcome by future research. In order to aid future study, we offer some insights into certain specific emerging theories. Additionally, this publication organises the body of literature by categorising contributions into various research areas.","PeriodicalId":274660,"journal":{"name":"2022 5th International Conference on Contemporary Computing and Informatics (IC3I)","volume":"98 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":"122402357","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 : 2022-12-14DOI: 10.1109/IC3I56241.2022.10073457
Manpreet Singh, Prerna Agarwal, P. Shrivastava, Harpreet Kaur
Since inception of Corona Virus, 47.6 Cr. individuals got infected and 61L deaths occurred. Still it’s going on and spreading across the world. Many health workers, researchers, experts, scientists are making efforts to slow down its pace & putting efforts in evaluating the techniques to detect it. For this, it is highly required to understand the virus & its versions. It is a part of SARS – Severe acute respiratory syndrome. To detect COVID, there are numerous ways but using Chest X-beams we are able to reduce the detection time and cost. To evaluate the Chest X-beams we need radiologists. So here, we develop a model to identify COVID X-beam in comparison to Normal X-beam. These days DL algo’s are producing best results in classification. A pre-trained CNN models using large datasets is to preferred for image classification. Firstly our models need to be trained and then tested to recognize the images of X-beams of one of the either case. Logically we have to locate the best CNN model for diagnosis.
{"title":"Detecting COVID using CNN from Chest X-Beams","authors":"Manpreet Singh, Prerna Agarwal, P. Shrivastava, Harpreet Kaur","doi":"10.1109/IC3I56241.2022.10073457","DOIUrl":"https://doi.org/10.1109/IC3I56241.2022.10073457","url":null,"abstract":"Since inception of Corona Virus, 47.6 Cr. individuals got infected and 61L deaths occurred. Still it’s going on and spreading across the world. Many health workers, researchers, experts, scientists are making efforts to slow down its pace & putting efforts in evaluating the techniques to detect it. For this, it is highly required to understand the virus & its versions. It is a part of SARS – Severe acute respiratory syndrome. To detect COVID, there are numerous ways but using Chest X-beams we are able to reduce the detection time and cost. To evaluate the Chest X-beams we need radiologists. So here, we develop a model to identify COVID X-beam in comparison to Normal X-beam. These days DL algo’s are producing best results in classification. A pre-trained CNN models using large datasets is to preferred for image classification. Firstly our models need to be trained and then tested to recognize the images of X-beams of one of the either case. Logically we have to locate the best CNN model for diagnosis.","PeriodicalId":274660,"journal":{"name":"2022 5th International Conference on Contemporary Computing and Informatics (IC3I)","volume":"408 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":"122944320","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}
Diabetes is a chronic illness that develops when the blood glucose level is elevated above normal. Diabetes has a variety of reasons, making diagnosis and treatment more difficult than necessary. A patient’s treatment can benefit greatly from a healthy diet. It is important to keep the diet under control so that it doesn’t include an excessive amount of carbohydrates. This study offers assistance in this case by creating a mobile application and website that can suggest a meal item based on the patient’s needs. For this construction, a dataset with basic data about more than fifty different food items is taken from Kaggle. This dataset is then preprocessed utilizingstandardization and encoding methods. To create two Machine Learning (ML)models, two different ML algorithms were applied. In this study, the K Nearest Neighbor (KNN) and Naïve Bayes (NB) algorithms were used. The models are subsequently trained using the preprocessed dataset. The models are also put to the test to see which one forecasts the patient’s ideal food item the most accurately. The NBalgorithm is the best method that may be used for carbohydrate recommendation, according to the testing of these models. This model’s accuracy is 93.12%.The model is therefore installed in the firebase. Another database that contains the patient’s real-time readings is linked to the firebase software as well. The best meal item with the right amount of carbohydrates is then given by the doctor through the website. A food proposal is provided to the patient’s mobile phone together with information like the values of the vital metrics. Based on the patient’s vital signs and required carbohydrate intake, the ML system particularly selects this meal item.
{"title":"Carbohydrate Recommendation for Type-1 Diabetics Patient Using Machine Learning","authors":"S. Sreenivasu, Sakshi Gupta, Ghanshyam Vatsa, Anurag Shrivastava, Swati Vashisht, Aparna Srivastava","doi":"10.1109/IC3I56241.2022.10072919","DOIUrl":"https://doi.org/10.1109/IC3I56241.2022.10072919","url":null,"abstract":"Diabetes is a chronic illness that develops when the blood glucose level is elevated above normal. Diabetes has a variety of reasons, making diagnosis and treatment more difficult than necessary. A patient’s treatment can benefit greatly from a healthy diet. It is important to keep the diet under control so that it doesn’t include an excessive amount of carbohydrates. This study offers assistance in this case by creating a mobile application and website that can suggest a meal item based on the patient’s needs. For this construction, a dataset with basic data about more than fifty different food items is taken from Kaggle. This dataset is then preprocessed utilizingstandardization and encoding methods. To create two Machine Learning (ML)models, two different ML algorithms were applied. In this study, the K Nearest Neighbor (KNN) and Naïve Bayes (NB) algorithms were used. The models are subsequently trained using the preprocessed dataset. The models are also put to the test to see which one forecasts the patient’s ideal food item the most accurately. The NBalgorithm is the best method that may be used for carbohydrate recommendation, according to the testing of these models. This model’s accuracy is 93.12%.The model is therefore installed in the firebase. Another database that contains the patient’s real-time readings is linked to the firebase software as well. The best meal item with the right amount of carbohydrates is then given by the doctor through the website. A food proposal is provided to the patient’s mobile phone together with information like the values of the vital metrics. Based on the patient’s vital signs and required carbohydrate intake, the ML system particularly selects this meal item.","PeriodicalId":274660,"journal":{"name":"2022 5th International Conference on Contemporary Computing and Informatics (IC3I)","volume":"490 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":"122894772","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 : 2022-12-14DOI: 10.1109/IC3I56241.2022.10073356
P. Ramyavarshini, G. K. Sriram, Umamaheswari Rajasekaran, A. Malini
The recent advancements in networks facilitates faster communication to any part of the world. The widespread adoption of Internet of Things in daily life applications proposes networking of gadgets. With the applications of Network through interconnection being increased, the difficulty in maintaining a secure network state becomes a challenge. Intrusion Protection Systems and Intrusion Detection Systems are two widely used tools in network security maintenance. Anomaly based IDS designed with the help of AI, ML and DL algorithms is observed to be more efficient than conventional signature based systems in the literature. Even though the reported accuracy of IDS in all the literature so far is sufficiently high, false alarms raised by the system is a major issue. The lack of explainability in the designed classifier behaviour is an important reason which makes it inevitable to avoid raising false alarms. This paper proposes an Interpretable A-IDS using XAI techniques. LIME and SHAP explanations are easily Interpretable, reducing the chances of raising false alarms.
{"title":"Explainable AI for Intrusion Detection Systems","authors":"P. Ramyavarshini, G. K. Sriram, Umamaheswari Rajasekaran, A. Malini","doi":"10.1109/IC3I56241.2022.10073356","DOIUrl":"https://doi.org/10.1109/IC3I56241.2022.10073356","url":null,"abstract":"The recent advancements in networks facilitates faster communication to any part of the world. The widespread adoption of Internet of Things in daily life applications proposes networking of gadgets. With the applications of Network through interconnection being increased, the difficulty in maintaining a secure network state becomes a challenge. Intrusion Protection Systems and Intrusion Detection Systems are two widely used tools in network security maintenance. Anomaly based IDS designed with the help of AI, ML and DL algorithms is observed to be more efficient than conventional signature based systems in the literature. Even though the reported accuracy of IDS in all the literature so far is sufficiently high, false alarms raised by the system is a major issue. The lack of explainability in the designed classifier behaviour is an important reason which makes it inevitable to avoid raising false alarms. This paper proposes an Interpretable A-IDS using XAI techniques. LIME and SHAP explanations are easily Interpretable, reducing the chances of raising false alarms.","PeriodicalId":274660,"journal":{"name":"2022 5th International Conference on Contemporary Computing and Informatics (IC3I)","volume":"23 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":"129420154","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}
The engaging ambitions of regeneration & growth of manufacturing in several nations, as well as the speed, flexibility, or expense benefits that might arise from the architecture of the industrial Internet of Things (IIoT), are attracting considerable interest. While blockchain or machine learning techniques, particularly deep learning, might offer the latest viable use cases for IIoT, they operate in a rather antagonistic manner. Underneath the assumption of information regulatory standards such as information protections, blockchain helps the crucial information collecting for machine learning. However, it may be susceptible to a data breach as a result of big information insights using machine learning. To enable machine learning/blockchain relevant & applicable for a variety of industrialized applications, it is of the utmost essential to have a thorough grasp of their evolution within the framework of IIoT. In this paper, we present a summary & analytics of the opportunity of blockchain as well as machine learning in the IIoT, focusing on the agreement method, preservation, or transmission. This study gives a better knowledge of the protection & confidentiality issues of a blockchain’s vital aspects from the viewpoint of machine learning, and that is beneficial for the creation of viable blockchain alternatives for IIoT.
{"title":"Deep Learning Applications for Blockchain in Industrial IoT","authors":"Vipul Masal, P. Pavithra, Shivesh Tiwari, Rajesh Singh, Jeidy Panduro-Ramirez, Durgaprasad Gangodkar","doi":"10.1109/IC3I56241.2022.10073357","DOIUrl":"https://doi.org/10.1109/IC3I56241.2022.10073357","url":null,"abstract":"The engaging ambitions of regeneration & growth of manufacturing in several nations, as well as the speed, flexibility, or expense benefits that might arise from the architecture of the industrial Internet of Things (IIoT), are attracting considerable interest. While blockchain or machine learning techniques, particularly deep learning, might offer the latest viable use cases for IIoT, they operate in a rather antagonistic manner. Underneath the assumption of information regulatory standards such as information protections, blockchain helps the crucial information collecting for machine learning. However, it may be susceptible to a data breach as a result of big information insights using machine learning. To enable machine learning/blockchain relevant & applicable for a variety of industrialized applications, it is of the utmost essential to have a thorough grasp of their evolution within the framework of IIoT. In this paper, we present a summary & analytics of the opportunity of blockchain as well as machine learning in the IIoT, focusing on the agreement method, preservation, or transmission. This study gives a better knowledge of the protection & confidentiality issues of a blockchain’s vital aspects from the viewpoint of machine learning, and that is beneficial for the creation of viable blockchain alternatives for IIoT.","PeriodicalId":274660,"journal":{"name":"2022 5th International Conference on Contemporary Computing and Informatics (IC3I)","volume":"185 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":"124706603","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 : 2022-12-14DOI: 10.1109/IC3I56241.2022.10072576
Inderpreet Kaur, A. Sandhu, Yogesh Kumar
Vector-borne diseases considerably impact the worldwide population’s health and economic well-being. However, training deep-learning models requires significant time and training data. Therefore, a unique hybrid transfer learning approach was proposed for detecting vector-borne diseases (VBD) to solve these issues while retaining high accuracy. In the first phase, malaria and Lyme benchmark datasets were obtained. Then VGG16, VGG19, MobileNetV2, and DenseNet 169 were compared to the hybrid model results (MobileNetV2+DenseNet 169). The effectiveness of the hybrid transfer learning method was evaluated using several performance measures, namely precision, loss, accuracy, AUC and RMSE. On the malaria dataset, the proposed model (MobileNetV2+DenseNet 169) achieved the most excellent classification accuracy of 99.9%, and on the Lyme dataset, 99.3%.
{"title":"A Hybrid Deep Transfer Learning Approach For The Detection Of Vector-Borne Diseases","authors":"Inderpreet Kaur, A. Sandhu, Yogesh Kumar","doi":"10.1109/IC3I56241.2022.10072576","DOIUrl":"https://doi.org/10.1109/IC3I56241.2022.10072576","url":null,"abstract":"Vector-borne diseases considerably impact the worldwide population’s health and economic well-being. However, training deep-learning models requires significant time and training data. Therefore, a unique hybrid transfer learning approach was proposed for detecting vector-borne diseases (VBD) to solve these issues while retaining high accuracy. In the first phase, malaria and Lyme benchmark datasets were obtained. Then VGG16, VGG19, MobileNetV2, and DenseNet 169 were compared to the hybrid model results (MobileNetV2+DenseNet 169). The effectiveness of the hybrid transfer learning method was evaluated using several performance measures, namely precision, loss, accuracy, AUC and RMSE. On the malaria dataset, the proposed model (MobileNetV2+DenseNet 169) achieved the most excellent classification accuracy of 99.9%, and on the Lyme dataset, 99.3%.","PeriodicalId":274660,"journal":{"name":"2022 5th International Conference on Contemporary Computing and Informatics (IC3I)","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":"130336802","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 : 2022-12-14DOI: 10.1109/IC3I56241.2022.10072853
K. N. R. Praveen, Gadug Sudhamsu
This research reports on the software configuration of automated fault detection and recognition using neural networks (ANNs) in a class of 13.6 cross actuators. According to the findings, the suggested flaw detector is ideal for integrating knowledge into the devices in a way that is living thing. The seven often recurring defects in a batch of these sensors are directly determined by the automated fault tester that is being demonstrated. In this study, the suggested automated defect detector is trained using an ANN-based binary class system. If any of the mistakes occurs, logic Programming is applied to define a high or “1” output, whereas the returning is calculated whether the other 6 failures occurred lowest or “0”. The input outputs from the Or CAD programme are used as incoming signal, and indeed the produced train parameters, i.e., amplitude and biased of the artificial neural tool of Math, have been used.
{"title":"Using AIG in Verilog HDL, Autonomous Testing in a Family of Wien Bridge Cross Transducers","authors":"K. N. R. Praveen, Gadug Sudhamsu","doi":"10.1109/IC3I56241.2022.10072853","DOIUrl":"https://doi.org/10.1109/IC3I56241.2022.10072853","url":null,"abstract":"This research reports on the software configuration of automated fault detection and recognition using neural networks (ANNs) in a class of 13.6 cross actuators. According to the findings, the suggested flaw detector is ideal for integrating knowledge into the devices in a way that is living thing. The seven often recurring defects in a batch of these sensors are directly determined by the automated fault tester that is being demonstrated. In this study, the suggested automated defect detector is trained using an ANN-based binary class system. If any of the mistakes occurs, logic Programming is applied to define a high or “1” output, whereas the returning is calculated whether the other 6 failures occurred lowest or “0”. The input outputs from the Or CAD programme are used as incoming signal, and indeed the produced train parameters, i.e., amplitude and biased of the artificial neural tool of Math, have been used.","PeriodicalId":274660,"journal":{"name":"2022 5th International Conference on Contemporary Computing and Informatics (IC3I)","volume":"56 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":"129118166","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 : 2022-12-14DOI: 10.1109/IC3I56241.2022.10073429
V. Bansal, Siddharth Pandey, Surendra Kumar Shukla, Devendra Singh, Sunitha Aravind Rathod, J. L. Arias-Gonzáles
The IEEE 802.15.4 standard offers a number of security requirements that provide varying degrees of protections at the link layer. The decision of which security level to use while collecting IoT based nodes is critical since it impacts safety and also impacts network speed. In this paper, a network security approach takes collection and recommended risks into account, taking into account the dynamics of cyber threat & total efficiency. The model findings show that the concept may select the best secure protocols depending on cybersecurity risks, level of maintenance, and changeable energy gathered. When compared to conventional methods, the proposed solution can increase work hours, resulting in enhanced network quality. Furthermore, the proposed security setup technique may suit a wide range of service needs.
{"title":"A Frame Work of Security Attacks, Issues Classifications and Configuration Strategy for IoT Networks for the Successful Implementation","authors":"V. Bansal, Siddharth Pandey, Surendra Kumar Shukla, Devendra Singh, Sunitha Aravind Rathod, J. L. Arias-Gonzáles","doi":"10.1109/IC3I56241.2022.10073429","DOIUrl":"https://doi.org/10.1109/IC3I56241.2022.10073429","url":null,"abstract":"The IEEE 802.15.4 standard offers a number of security requirements that provide varying degrees of protections at the link layer. The decision of which security level to use while collecting IoT based nodes is critical since it impacts safety and also impacts network speed. In this paper, a network security approach takes collection and recommended risks into account, taking into account the dynamics of cyber threat & total efficiency. The model findings show that the concept may select the best secure protocols depending on cybersecurity risks, level of maintenance, and changeable energy gathered. When compared to conventional methods, the proposed solution can increase work hours, resulting in enhanced network quality. Furthermore, the proposed security setup technique may suit a wide range of service needs.","PeriodicalId":274660,"journal":{"name":"2022 5th International Conference on Contemporary Computing and Informatics (IC3I)","volume":"59 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":"130670086","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}
Heart attack is a major threat to human life. It occurs in one or more coronary arteries refilled by the oxygen-rich blood, which also supplies into the heart muscle, suddenly becomes blocked, and unfortunately, a few heart muscle sections can’t get sufficient oxygen. In past, most patients suffered heart attacks at some stage in life. Unfortunately, some of them lost their lives due to this. When the non-survival and survival variables both are examined that determines whether a patient will survive for one more year after suffering from a heart attack. A supervised learning technique has been applied to the Echocardiogram Dataset. The experimental outcomes show that the proposed methodology applied with several data preprocessing approaches achieved a decent 94.74% classification accuracy.
{"title":"Survival Prediction of a Patient afterward a Heart Attack by Machine Learning","authors":"Biswajit Giri, Suman Kumari Agarwal, Nandani Kumari, Rana Majumder, Sumita Gupta, Anirban Mitra","doi":"10.1109/IC3I56241.2022.10073329","DOIUrl":"https://doi.org/10.1109/IC3I56241.2022.10073329","url":null,"abstract":"Heart attack is a major threat to human life. It occurs in one or more coronary arteries refilled by the oxygen-rich blood, which also supplies into the heart muscle, suddenly becomes blocked, and unfortunately, a few heart muscle sections can’t get sufficient oxygen. In past, most patients suffered heart attacks at some stage in life. Unfortunately, some of them lost their lives due to this. When the non-survival and survival variables both are examined that determines whether a patient will survive for one more year after suffering from a heart attack. A supervised learning technique has been applied to the Echocardiogram Dataset. The experimental outcomes show that the proposed methodology applied with several data preprocessing approaches achieved a decent 94.74% classification accuracy.","PeriodicalId":274660,"journal":{"name":"2022 5th International Conference on Contemporary Computing and Informatics (IC3I)","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":"123391120","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 : 2022-12-14DOI: 10.1109/IC3I56241.2022.10073241
V. Kiruthiga, Sunanda Kondapalli, Varun Gupta, R. Aarthy, J. Sasidevi, C. S. Kumar
The next generation will require of such commerce site with the renaissance of conventional technology to more current technology and use of advanced technology, where a large portion of e-commerce are presently created on back of such revolution and inventive breakthroughs like robotization. Most of businesses or owner(s) of these sites are sending off more unique sites rather than conventional list and static sites, so machine learning, augmented with man-made brainpower, and deep learning, which are in demand and profoundly necessary, should be integrated into the present e-commerce sites to be best and profitable for the owners of these sites. The importance of artificial intelligence in various spheres of business and life has increased as a result of the accelerated technological advancement. The use of AI in voice recognition helps organisations and individuals understand how to provide stakeholders with better services and effectively completes the task. Therefore, this work focuses on utilising regression analysis to analyse the critical factors of employing AI in speech recognition for a successful multipurpose Machine Learning platform.
{"title":"Modelling of an Intelligent Voice System using MI Algorithm for E-Business","authors":"V. Kiruthiga, Sunanda Kondapalli, Varun Gupta, R. Aarthy, J. Sasidevi, C. S. Kumar","doi":"10.1109/IC3I56241.2022.10073241","DOIUrl":"https://doi.org/10.1109/IC3I56241.2022.10073241","url":null,"abstract":"The next generation will require of such commerce site with the renaissance of conventional technology to more current technology and use of advanced technology, where a large portion of e-commerce are presently created on back of such revolution and inventive breakthroughs like robotization. Most of businesses or owner(s) of these sites are sending off more unique sites rather than conventional list and static sites, so machine learning, augmented with man-made brainpower, and deep learning, which are in demand and profoundly necessary, should be integrated into the present e-commerce sites to be best and profitable for the owners of these sites. The importance of artificial intelligence in various spheres of business and life has increased as a result of the accelerated technological advancement. The use of AI in voice recognition helps organisations and individuals understand how to provide stakeholders with better services and effectively completes the task. Therefore, this work focuses on utilising regression analysis to analyse the critical factors of employing AI in speech recognition for a successful multipurpose Machine Learning platform.","PeriodicalId":274660,"journal":{"name":"2022 5th International Conference on Contemporary Computing and Informatics (IC3I)","volume":"59 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120898027","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：