Pub Date : 2021-09-02DOI: 10.1109/ICIRCA51532.2021.9544589
Apurb Kumar, M.Jogendra Kumar, N. Sai, T. R. Kumar
With an expanding number of organizations related with the web, including circulated figuring systems and the Internet of Things (IoT), the reaction to cyberattacks has become more testing because of the huge dimensionality of data and steps association traffic. As of late, experts have proposed profound learning (DL) estimations to portray the features of interruption by planning test data and adjusting instances of animosity abnormalities. Notwithstanding, because of the huge things and unequal nature of the data, current DL classifiers are not completely practical to perceive surprising and normal arrangement relationship for the present associations. Then, plan a self-adaptable model for a disturbance discovery structure (IDS) to deal with distinguishing attacks.
{"title":"Identification of Network Data security inside the IOT by using Deep learning approach","authors":"Apurb Kumar, M.Jogendra Kumar, N. Sai, T. R. Kumar","doi":"10.1109/ICIRCA51532.2021.9544589","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9544589","url":null,"abstract":"With an expanding number of organizations related with the web, including circulated figuring systems and the Internet of Things (IoT), the reaction to cyberattacks has become more testing because of the huge dimensionality of data and steps association traffic. As of late, experts have proposed profound learning (DL) estimations to portray the features of interruption by planning test data and adjusting instances of animosity abnormalities. Notwithstanding, because of the huge things and unequal nature of the data, current DL classifiers are not completely practical to perceive surprising and normal arrangement relationship for the present associations. Then, plan a self-adaptable model for a disturbance discovery structure (IDS) to deal with distinguishing attacks.","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125714493","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 : 2021-09-02DOI: 10.1109/ICIRCA51532.2021.9544569
Dinubhau B. Alaspure, S. Dixit
Mathematics is an integral part of the engineering. Mathematical formulas are implemented in electronics circuit which makes complex computations executed in promising time. Different researchers proposed several shortcut techniques which executes some of the mathematical calculations in much short time. Through this paper, primarily, detailed information regarding different applications which have been developed so far, by different authors, using fundamentals of vedic mathematics, through their research work are collected to identify the problem statement. In the subsequent section, a detailed literature survey and critical analysis on different short-cut techniques which are implemented using electronics circuit and computer software for realizing different applications in different domains.
{"title":"FPGA based Vedic Mathematics Applications: An Eagle Eye","authors":"Dinubhau B. Alaspure, S. Dixit","doi":"10.1109/ICIRCA51532.2021.9544569","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9544569","url":null,"abstract":"Mathematics is an integral part of the engineering. Mathematical formulas are implemented in electronics circuit which makes complex computations executed in promising time. Different researchers proposed several shortcut techniques which executes some of the mathematical calculations in much short time. Through this paper, primarily, detailed information regarding different applications which have been developed so far, by different authors, using fundamentals of vedic mathematics, through their research work are collected to identify the problem statement. In the subsequent section, a detailed literature survey and critical analysis on different short-cut techniques which are implemented using electronics circuit and computer software for realizing different applications in different domains.","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127954013","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 : 2021-09-02DOI: 10.1109/ICIRCA51532.2021.9544951
Rahul Das. P, K. G, S. V, Rupa. B
Malaria is a serious infection caused by a blood parasite called Plasmodiums pp. Every year, the World Health Organization [WHO] estimates 300–500 million malaria cases and over one deaths worldwide. Manually counting and arranging epithetical contaminated erythrocytes is a time-consuming and exhausting operation. Computerized parasite detection using mobile phones is a potential alternative to manual parasite meaning intestinal illness assessment, especially in remote areas without expert parasitologists. As a result, the relevance of developing novel devices to facilitate quick and simple detection of epithetical malaria in areas with limited access to social insurance administrations cannot be overstated. The preceding study investigates the possibility of epithetical mechanised intestinal illness parasite recognition trig thick blood distributes around cell phones. We have developed a primary deep learning approach that can recognize malaria parasites, generate dense blood smear images, and can run forth cell phones. Along with the aforementioned research, we created a dataset of 1819 thick smear images from 150 patients that is publicly accessible via examination network.
{"title":"An efficient smartphone based Parasite Malaria Detection with Deep Neural Networks","authors":"Rahul Das. P, K. G, S. V, Rupa. B","doi":"10.1109/ICIRCA51532.2021.9544951","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9544951","url":null,"abstract":"Malaria is a serious infection caused by a blood parasite called Plasmodiums pp. Every year, the World Health Organization [WHO] estimates 300–500 million malaria cases and over one deaths worldwide. Manually counting and arranging epithetical contaminated erythrocytes is a time-consuming and exhausting operation. Computerized parasite detection using mobile phones is a potential alternative to manual parasite meaning intestinal illness assessment, especially in remote areas without expert parasitologists. As a result, the relevance of developing novel devices to facilitate quick and simple detection of epithetical malaria in areas with limited access to social insurance administrations cannot be overstated. The preceding study investigates the possibility of epithetical mechanised intestinal illness parasite recognition trig thick blood distributes around cell phones. We have developed a primary deep learning approach that can recognize malaria parasites, generate dense blood smear images, and can run forth cell phones. Along with the aforementioned research, we created a dataset of 1819 thick smear images from 150 patients that is publicly accessible via examination network.","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131963173","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 : 2021-09-02DOI: 10.1109/ICIRCA51532.2021.9544559
S. P, Pradhyumna P, Mohana
The need to integrate actual or real-time audio-visual communications infrastructure in networks and their uses, along with the web, sparked a development that resulted in introduction of numerous new technologies. In today's converging networks, real-time communication is critical. Today, Ip - based services such as collaborative video calls, videoconferencing, conferencing, chatting, message, and appearance are highly famous and widespread utilized. Such services completely dismantled communications boundaries throughout the world. Many parts of our life are now influenced by these technology, including schooling. One of the most essential are the Session Initiation Protocol (SIP) and Web Real-Time Communication (WebRTC). If 2 computers using different service providers wish to communicate with each other, they need a VoIP signalling protocol like SIP to do so. Gateway is the element that works as an intermediary between WebRTC and SIP. This paper describes technology of the elements of merging these two key internet technologies, SIP and WebRTC, to build a bridge between them.
{"title":"Internetworking Gateway between WebRTC to SIP to Integrate Real-Time Audio Video Communication","authors":"S. P, Pradhyumna P, Mohana","doi":"10.1109/ICIRCA51532.2021.9544559","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9544559","url":null,"abstract":"The need to integrate actual or real-time audio-visual communications infrastructure in networks and their uses, along with the web, sparked a development that resulted in introduction of numerous new technologies. In today's converging networks, real-time communication is critical. Today, Ip - based services such as collaborative video calls, videoconferencing, conferencing, chatting, message, and appearance are highly famous and widespread utilized. Such services completely dismantled communications boundaries throughout the world. Many parts of our life are now influenced by these technology, including schooling. One of the most essential are the Session Initiation Protocol (SIP) and Web Real-Time Communication (WebRTC). If 2 computers using different service providers wish to communicate with each other, they need a VoIP signalling protocol like SIP to do so. Gateway is the element that works as an intermediary between WebRTC and SIP. This paper describes technology of the elements of merging these two key internet technologies, SIP and WebRTC, to build a bridge between them.","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134405757","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 : 2021-09-02DOI: 10.1109/ICIRCA51532.2021.9544745
R. Subasri, R. Meenakumari, R. Velnath, Srinivethaa Pongiannan, M. S. S. M. R. Kumar
The robot is used in many industries for various important purposes like welding, soldering, painting and material handling works like sorting, palletizing, picking, packing, etc. To do the work perfectly the robot's inverse kinematics model is very much important. Usually, the traditional method such as iterative, geometric, and algebraic is used to calculate the inverse kinematics model. A robot with 2 or fewer degrees of freedom, the finding of inverse kinematics by the traditional method is quite simple. But if the degree of freedom increases then the model identification becomes more complex and too expensive in computation. To overcome this solution the emerging artificial intelligence techniques are used. Two methods of artificial intelligence like neural network and adaptive neuro-fuzzy inference system are used to identify the inverse kinematics of 3R planar robot. The input data like X and Y coordinates and output data like joint angles $theta_{1}, theta_{2}$ and $theta_{3}$ are generated using the forward kinematics equation of the robot. In both methods, the input and output data are given to train the model. The training of the model is stopped and finalized when the error of the model comes under the tolerable limit. For evaluating the designed model, both models are compared with the derived algebraic model of the robot. The comparison helps to prove that the ANFIS model is better than the NN model
{"title":"Model Identification of 3R Palnar Robot using Neural Network and Adaptive Neuro-Fuzzy Inference System","authors":"R. Subasri, R. Meenakumari, R. Velnath, Srinivethaa Pongiannan, M. S. S. M. R. Kumar","doi":"10.1109/ICIRCA51532.2021.9544745","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9544745","url":null,"abstract":"The robot is used in many industries for various important purposes like welding, soldering, painting and material handling works like sorting, palletizing, picking, packing, etc. To do the work perfectly the robot's inverse kinematics model is very much important. Usually, the traditional method such as iterative, geometric, and algebraic is used to calculate the inverse kinematics model. A robot with 2 or fewer degrees of freedom, the finding of inverse kinematics by the traditional method is quite simple. But if the degree of freedom increases then the model identification becomes more complex and too expensive in computation. To overcome this solution the emerging artificial intelligence techniques are used. Two methods of artificial intelligence like neural network and adaptive neuro-fuzzy inference system are used to identify the inverse kinematics of 3R planar robot. The input data like X and Y coordinates and output data like joint angles $theta_{1}, theta_{2}$ and $theta_{3}$ are generated using the forward kinematics equation of the robot. In both methods, the input and output data are given to train the model. The training of the model is stopped and finalized when the error of the model comes under the tolerable limit. For evaluating the designed model, both models are compared with the derived algebraic model of the robot. The comparison helps to prove that the ANFIS model is better than the NN model","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134331127","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 : 2021-09-02DOI: 10.1109/ICIRCA51532.2021.9545021
Raziya Begum, M. R. Narasingarao, Niranjan Polala
The radical change of brain cells that causes dopamine, a component that allows brain cells to exchange information with one another, causes Parkinson's disease. Control, adaptation, and fluency of movement are all controlled by dopamine-producing cells in the brain. To reduce this production of dopamine, these cells should die at least 50%, resulting in Parkinson's motor symptoms. The diagnosis of Parkinson's disease using SVM and Navie bayes algorithms is presented in this paper. A feature selection and classification process is used in the proposed diagnosis method. In the experiments, the classification of diseased was done using Classification algorithms and Regression algorithms and Support Vector Machines. Our results compared Support Vector Machines with Feature Extraction outperformed the Naïve bayes. With the fewest number of features, 81.77 percent accuracy in Parkinson's diagnosis was achieved. This research work has preprocessed the dataset worked on Parkinson's Progression Markers Initiative (PPMI) and then used one of the classification methods, Support Vector Machine (SVM), to distinguish people with Parkinson's disease from healthy people. This article explained, how the ROC curve changes as the number of cross validation folds increases, as well as how the value of true positive and false positive rates changes.
{"title":"Neurodegenerative disorder diagnosis using support vector machine and Naive bayes algorithms","authors":"Raziya Begum, M. R. Narasingarao, Niranjan Polala","doi":"10.1109/ICIRCA51532.2021.9545021","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9545021","url":null,"abstract":"The radical change of brain cells that causes dopamine, a component that allows brain cells to exchange information with one another, causes Parkinson's disease. Control, adaptation, and fluency of movement are all controlled by dopamine-producing cells in the brain. To reduce this production of dopamine, these cells should die at least 50%, resulting in Parkinson's motor symptoms. The diagnosis of Parkinson's disease using SVM and Navie bayes algorithms is presented in this paper. A feature selection and classification process is used in the proposed diagnosis method. In the experiments, the classification of diseased was done using Classification algorithms and Regression algorithms and Support Vector Machines. Our results compared Support Vector Machines with Feature Extraction outperformed the Naïve bayes. With the fewest number of features, 81.77 percent accuracy in Parkinson's diagnosis was achieved. This research work has preprocessed the dataset worked on Parkinson's Progression Markers Initiative (PPMI) and then used one of the classification methods, Support Vector Machine (SVM), to distinguish people with Parkinson's disease from healthy people. This article explained, how the ROC curve changes as the number of cross validation folds increases, as well as how the value of true positive and false positive rates changes.","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131803449","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 : 2021-09-02DOI: 10.1109/ICIRCA51532.2021.9544584
S. Routray, A. Javali, Anindita Sahoo, Laxmi Sharma, K. Sharmila, Aritri Ghosh
The Internet of things (IoT) plays important roles in the modern digital world. It has several important roles in the modern power systems and power grids. IoT presents a lot of potential in the power systems and power grids. Some of the support functions are direct and several others are found to be indirect. Either way, IoT can play a lot of important roles in the modern power systems. It can help significantly in the measurement, control, and monitoring of the physical parameters in the power grids. It helps to in the reduction of energy consumption in the power electronic components. It has the potential to provide a lot of operational flexibilities in the power electronic components. Implementation of advanced operational algorithms using artificial intelligence and machine learning is facilitated by the IoT based sensors, actuators and other key components. It can provide smart operational assistance to the power electronic systems used in the power grids. Due to their logical flexibilities IoT sensors can be deployed alongside the power electronic components to track their performances. Consequently, using the IoT sensors' information, the actuators are driven to deliver optimal outcome. IoT sensors' information can be sent directly to the central servers in regular intervals to monitor the overall performances of the power electronic components. In addition to the aforesaid applications, several other potential uses of IoT in power electronics include monitoring of critical power grid parameters such as temperature, current, voltage and vibration at different key locations. In this paper, we analyze the use of IoT in power electronic components in the modern power systems.
{"title":"IoT Assisted Power Electronics for Modern Power Systems","authors":"S. Routray, A. Javali, Anindita Sahoo, Laxmi Sharma, K. Sharmila, Aritri Ghosh","doi":"10.1109/ICIRCA51532.2021.9544584","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9544584","url":null,"abstract":"The Internet of things (IoT) plays important roles in the modern digital world. It has several important roles in the modern power systems and power grids. IoT presents a lot of potential in the power systems and power grids. Some of the support functions are direct and several others are found to be indirect. Either way, IoT can play a lot of important roles in the modern power systems. It can help significantly in the measurement, control, and monitoring of the physical parameters in the power grids. It helps to in the reduction of energy consumption in the power electronic components. It has the potential to provide a lot of operational flexibilities in the power electronic components. Implementation of advanced operational algorithms using artificial intelligence and machine learning is facilitated by the IoT based sensors, actuators and other key components. It can provide smart operational assistance to the power electronic systems used in the power grids. Due to their logical flexibilities IoT sensors can be deployed alongside the power electronic components to track their performances. Consequently, using the IoT sensors' information, the actuators are driven to deliver optimal outcome. IoT sensors' information can be sent directly to the central servers in regular intervals to monitor the overall performances of the power electronic components. In addition to the aforesaid applications, several other potential uses of IoT in power electronics include monitoring of critical power grid parameters such as temperature, current, voltage and vibration at different key locations. In this paper, we analyze the use of IoT in power electronic components in the modern power systems.","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133028542","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 : 2021-09-02DOI: 10.1109/ICIRCA51532.2021.9544600
Rui Gu
In recent years, blockchain technology is receiving more and more people's attention. The reason why it has received so many people's attention is that through blockchain technology, the openness and transparency of information can be effectively guaranteed, and because of the immutability of blockchain, so that it has great application value in various fields. In corporate financial management, the application of blockchain technology to corporate tax planning and management will have a profound impact on corporate tax planning. Based on the analysis of the definition and characteristics of the blockchain, this paper can study the impact of the application of the blockchain in corporate tax planning through decentralized modeling for in-depth research. This article first introduces the steps, key points and research status of corporate tax planning, then introduces the application, development and characteristics of blockchain technology, and finally models and simulates corporate tax planning based on blockchain technology, and the results prove the reliability of the model.
{"title":"Blockchain and Decentralized Modeling for Corporate Tax Planning","authors":"Rui Gu","doi":"10.1109/ICIRCA51532.2021.9544600","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9544600","url":null,"abstract":"In recent years, blockchain technology is receiving more and more people's attention. The reason why it has received so many people's attention is that through blockchain technology, the openness and transparency of information can be effectively guaranteed, and because of the immutability of blockchain, so that it has great application value in various fields. In corporate financial management, the application of blockchain technology to corporate tax planning and management will have a profound impact on corporate tax planning. Based on the analysis of the definition and characteristics of the blockchain, this paper can study the impact of the application of the blockchain in corporate tax planning through decentralized modeling for in-depth research. This article first introduces the steps, key points and research status of corporate tax planning, then introduces the application, development and characteristics of blockchain technology, and finally models and simulates corporate tax planning based on blockchain technology, and the results prove the reliability of the model.","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133796847","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 : 2021-09-02DOI: 10.1109/ICIRCA51532.2021.9544932
Amit Kundaliya, P. Juyal
Deep-learning techniques are utilized extensively to construct an intrusion detection system (IDS) for the timely and automated detection as well as classification of cyber assaults at network and host levels. Many difficulties exist, however, because harmful attacks continue to change and require a scalable solution in very high numbers. Various IDS big datasets are freely available by the cyber security community for future investigation. However, no current work has shown an exhaustive evaluation the malware data sets made available to the public must be consistently updated and benchmarked. The construction of a flexible and efficiently Hybrid FFNN, a kind of deep learning model, to recognize and classify unforeseen and unplanned cyber-attacks is discussed in this document.
{"title":"Advance Deep Learning Technique for Big Data Classification in IDS Environment","authors":"Amit Kundaliya, P. Juyal","doi":"10.1109/ICIRCA51532.2021.9544932","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9544932","url":null,"abstract":"Deep-learning techniques are utilized extensively to construct an intrusion detection system (IDS) for the timely and automated detection as well as classification of cyber assaults at network and host levels. Many difficulties exist, however, because harmful attacks continue to change and require a scalable solution in very high numbers. Various IDS big datasets are freely available by the cyber security community for future investigation. However, no current work has shown an exhaustive evaluation the malware data sets made available to the public must be consistently updated and benchmarked. The construction of a flexible and efficiently Hybrid FFNN, a kind of deep learning model, to recognize and classify unforeseen and unplanned cyber-attacks is discussed in this document.","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"256 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115420235","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 : 2021-09-02DOI: 10.1109/ICIRCA51532.2021.9544616
Ankit Vishwakarma, Sahil Sawant, Prerana Sawant, R. Shankarmani
Mental health is a leading cause of deaths, affecting over 450 million people globally. There are existing emotion recognition models to help and understand the state of a person but mainly via text. The proposed model in the paper is developed in a personalized multi-modal architecture to incorporate all the necessary aspects to predict the cumulative emotional status of a person by his/her text context, speech features, and facial expressions. There are mainly 3 different models: Bidirectional Encoder Representations from Transformers, Multi-layer Perceptron Classifier and Convolutional Neural Network working together in synchronization to cater to the need. Along with it, the advancement implemented includes General Adversarial Networks (GAN), to generate a human entity and help the human to cope up with their emotional state and practically save them from any kind of grave danger. The model with the help of GAN and lip-synced model manages to converse with the user after analyzing and considering their mental state, helping them to find a solution accordingly.
{"title":"An Emotionally Aware Friend: Moving Towards Artificial General Intelligence","authors":"Ankit Vishwakarma, Sahil Sawant, Prerana Sawant, R. Shankarmani","doi":"10.1109/ICIRCA51532.2021.9544616","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9544616","url":null,"abstract":"Mental health is a leading cause of deaths, affecting over 450 million people globally. There are existing emotion recognition models to help and understand the state of a person but mainly via text. The proposed model in the paper is developed in a personalized multi-modal architecture to incorporate all the necessary aspects to predict the cumulative emotional status of a person by his/her text context, speech features, and facial expressions. There are mainly 3 different models: Bidirectional Encoder Representations from Transformers, Multi-layer Perceptron Classifier and Convolutional Neural Network working together in synchronization to cater to the need. Along with it, the advancement implemented includes General Adversarial Networks (GAN), to generate a human entity and help the human to cope up with their emotional state and practically save them from any kind of grave danger. The model with the help of GAN and lip-synced model manages to converse with the user after analyzing and considering their mental state, helping them to find a solution accordingly.","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124143542","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：