Pub Date : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126151
Y. Kale, S. Rathkanthiwar, Sarvadnya Rajurkar, Himanshu Parate, Anshul Ninawe, Aditya Bharti
Numerous data points are generated by the healthcare sector and processed using certain procedures. There are many methods for processing a data among which data mining is one of the methods frequently employed. Heart condition is the main cause of death in the globe. This project determines the best algorithm for the system that anticipates the possibility of cardiac disease. The outcomes of this system provide the likelihood in percentage of acquiring heart disease. The datasets are categorised using medical parameters. To analyse such factors, our system employs a data mining classification method. The datasets are analysed using Naïve Bayes, Logistic Regression, Random Forest, K-Nearest Neighbour, XGboost, Decision Tree and Support Vector Machine, Machine learning algorithms with hybrid Classifiers and Neural Network.
{"title":"Analysis for Determining Best Machine learning Algorithm for Classification of Heart Diseases","authors":"Y. Kale, S. Rathkanthiwar, Sarvadnya Rajurkar, Himanshu Parate, Anshul Ninawe, Aditya Bharti","doi":"10.1109/I2CT57861.2023.10126151","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126151","url":null,"abstract":"Numerous data points are generated by the healthcare sector and processed using certain procedures. There are many methods for processing a data among which data mining is one of the methods frequently employed. Heart condition is the main cause of death in the globe. This project determines the best algorithm for the system that anticipates the possibility of cardiac disease. The outcomes of this system provide the likelihood in percentage of acquiring heart disease. The datasets are categorised using medical parameters. To analyse such factors, our system employs a data mining classification method. The datasets are analysed using Naïve Bayes, Logistic Regression, Random Forest, K-Nearest Neighbour, XGboost, Decision Tree and Support Vector Machine, Machine learning algorithms with hybrid Classifiers and Neural Network.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120942919","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126330
KG Deekshitha, Chaitanya Patange, M. Harshitha, Pavitra Y.J
The Automatic Writing Machine is a device used to automate the process of writing by eliminating the necessity of human aid for a physically challenged person. The proposed work aims to design a user-friendly automated writing machine with computer numerical control (CNC) along with Arduino and Raspberry Pi. The user input(image/text/audio) signal is converted into handwriting using Python programming to generate coordinates and drive your CNC machine through Arduino. The proposed work is a stand-alone system eliminating the requirement of high-end machines to process the coordinate data. The proposed work also eliminates the need of software such as Ben-box and G-code which restrict the user input to only images. The proposed work has increased the efficiency in handling user input over the work reported in literature along with reduced hardware and software requirements.
{"title":"Automated Handwriting Machine","authors":"KG Deekshitha, Chaitanya Patange, M. Harshitha, Pavitra Y.J","doi":"10.1109/I2CT57861.2023.10126330","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126330","url":null,"abstract":"The Automatic Writing Machine is a device used to automate the process of writing by eliminating the necessity of human aid for a physically challenged person. The proposed work aims to design a user-friendly automated writing machine with computer numerical control (CNC) along with Arduino and Raspberry Pi. The user input(image/text/audio) signal is converted into handwriting using Python programming to generate coordinates and drive your CNC machine through Arduino. The proposed work is a stand-alone system eliminating the requirement of high-end machines to process the coordinate data. The proposed work also eliminates the need of software such as Ben-box and G-code which restrict the user input to only images. The proposed work has increased the efficiency in handling user input over the work reported in literature along with reduced hardware and software requirements.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124855470","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126434
Vanlalruata Hnamte, J. Hussain
In this study, we provide Deep Neural Network (DNN) based approaches to detecting Distributed Denial-of-Service (DDoS) attacks. In order to improve the DNN’s accuracy, the suggested approaches use two different hybrid DNN scenario detections to demonstrate the possibilities. As training and testing data, we use the publicly available Intrusion Detection datasets; CIC-IDS2017 and CIC-DDoS2019. Experiments have shown that the presented approaches are 99.9% effective at detecting attacks.
{"title":"DDoS Detection Using Hybrid Deep Neural Network Approaches","authors":"Vanlalruata Hnamte, J. Hussain","doi":"10.1109/I2CT57861.2023.10126434","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126434","url":null,"abstract":"In this study, we provide Deep Neural Network (DNN) based approaches to detecting Distributed Denial-of-Service (DDoS) attacks. In order to improve the DNN’s accuracy, the suggested approaches use two different hybrid DNN scenario detections to demonstrate the possibilities. As training and testing data, we use the publicly available Intrusion Detection datasets; CIC-IDS2017 and CIC-DDoS2019. Experiments have shown that the presented approaches are 99.9% effective at detecting attacks.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123577644","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126349
K. Harsha, S. Yuva Nitya, Sravani Kota, K. Satyanarayana, Jaya Lakshmi
Approximately 1.6 million individuals use the e-commerce website “amazon” to buy things from a variety of categories, including food. Reviewing products by consumers who have already purchased them is beneficial to those who are considering doing so, however reviews can be either positive or negative. The buyer finds it difficult to read through such many evaluations before making a purchase, but machine learning ideas and training models make it possible. Our objective is to categorize the reviews based on the attributes that are present in the dataset in order to address issues like these. Redundancy is present in data when it is presented to us in its raw form. So, since evaluations with a score of 3 are regarded as impartial, we delete them along with redundancy. After that, we use the NLP tool kit (a column in the data set) to preprocess the text by removing any stop words (such as in, as, is, on, and punctuation), and we lowercase each letter. The suggested approach renders the text into machine-understandable language using word embedding techniques. Text processing is necessary because customer reviews written in language that is understood by humans cannot be read by machines. The data must be in a machine-readable language in order to apply any classification technique. We separate the data into train and test set after the preprocessing is complete. After the training is complete, we use this model on a test set of data to determine its accuracy. Next, we utilize classification methods like logistic regression and XG Boost to see how accurate our model is. This study’s conclusion involves using the model we developed to predict the review based on previous reviews. In this project, we build a model, feed it with existing reviews, apply it to upcoming reviews, and then forecast if the product is good or not. For this work we have taken the data set from Kaggle.
{"title":"Empirical evaluation of Amazon fine food reviews using Text Mining","authors":"K. Harsha, S. Yuva Nitya, Sravani Kota, K. Satyanarayana, Jaya Lakshmi","doi":"10.1109/I2CT57861.2023.10126349","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126349","url":null,"abstract":"Approximately 1.6 million individuals use the e-commerce website “amazon” to buy things from a variety of categories, including food. Reviewing products by consumers who have already purchased them is beneficial to those who are considering doing so, however reviews can be either positive or negative. The buyer finds it difficult to read through such many evaluations before making a purchase, but machine learning ideas and training models make it possible. Our objective is to categorize the reviews based on the attributes that are present in the dataset in order to address issues like these. Redundancy is present in data when it is presented to us in its raw form. So, since evaluations with a score of 3 are regarded as impartial, we delete them along with redundancy. After that, we use the NLP tool kit (a column in the data set) to preprocess the text by removing any stop words (such as in, as, is, on, and punctuation), and we lowercase each letter. The suggested approach renders the text into machine-understandable language using word embedding techniques. Text processing is necessary because customer reviews written in language that is understood by humans cannot be read by machines. The data must be in a machine-readable language in order to apply any classification technique. We separate the data into train and test set after the preprocessing is complete. After the training is complete, we use this model on a test set of data to determine its accuracy. Next, we utilize classification methods like logistic regression and XG Boost to see how accurate our model is. This study’s conclusion involves using the model we developed to predict the review based on previous reviews. In this project, we build a model, feed it with existing reviews, apply it to upcoming reviews, and then forecast if the product is good or not. For this work we have taken the data set from Kaggle.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125348162","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}
According to World Health Organization (WHO) statistics, monkeypox has been identified as an epidemic in 127 nations so far, and it is spreading quickly over the globe. While the rashes and skin lesions associated with monkeypox usually mimic those of other poxes, including chickenpox and measles. Due to these similarities, it could be challenging for medical professionals to identify monkeypox based just on the appearance of lesions and rashes. Because monkeypox was uncommon before in the current outbreak, healthcare professionals lack knowledge in this area. But the scientific community has demonstrated a rising interest in implementing Artificial Intelligence in Monkeypox prediction and detection from digital skin images as a result of the success of image processing approaches in COVID-19 detection. In this study, we have applied three cutting-edge deep learning models which are InceptionV3, MobileNetV3, and DenseNet201, referred to as transfer learning models, to detect monkeypox on skin images using the publicly available Monkeypox Skin Image Dataset 2022 with four classes. According to our research, transfer learning models can detect monkeypox with a top 93.59% accuracy for the InceptionNet-V3 pre-trained model from three implemented algorithms on digitized skin images. For further research, larger training images are required to train those deep learning models to achieve a higher vigorous detection rate.
{"title":"Monkeypox Detection from Various Types of Poxes: A Deep Learning Approach","authors":"Anik Pramanik, Fayazunnesa Chowdhury, Salma Sultana, Md. Mahbubur Rahman, Md. Hasan Imam Bijoy, Md. Sadekur Rahman","doi":"10.1109/I2CT57861.2023.10126223","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126223","url":null,"abstract":"According to World Health Organization (WHO) statistics, monkeypox has been identified as an epidemic in 127 nations so far, and it is spreading quickly over the globe. While the rashes and skin lesions associated with monkeypox usually mimic those of other poxes, including chickenpox and measles. Due to these similarities, it could be challenging for medical professionals to identify monkeypox based just on the appearance of lesions and rashes. Because monkeypox was uncommon before in the current outbreak, healthcare professionals lack knowledge in this area. But the scientific community has demonstrated a rising interest in implementing Artificial Intelligence in Monkeypox prediction and detection from digital skin images as a result of the success of image processing approaches in COVID-19 detection. In this study, we have applied three cutting-edge deep learning models which are InceptionV3, MobileNetV3, and DenseNet201, referred to as transfer learning models, to detect monkeypox on skin images using the publicly available Monkeypox Skin Image Dataset 2022 with four classes. According to our research, transfer learning models can detect monkeypox with a top 93.59% accuracy for the InceptionNet-V3 pre-trained model from three implemented algorithms on digitized skin images. For further research, larger training images are required to train those deep learning models to achieve a higher vigorous detection rate.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116398527","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126205
Bhagya Rathnayake, Kalpani Manathunga, D. Kasthurirathna
The ability for books to talk would be an exciting concept, and this research discussion paves the path for an identical approach. The research objectives discussed in this paper address several burning problems, solve them and adapt them to future technological enhancements from a Sri Lankan context. Burning problems include reducing printing costs for textbooks, addressing students’ health, promoting green technology, and identifying a suitable summarising approach to the native language, Sinhala resulting in students’ learning ease. Other symptoms for the betterment indicate paths taken to reduce the weight of school bags carried by students, reduce paper usage by the government on printing textbooks, and spread technological awareness to teenagers regarding e-Learning. Textbooks issued by the government will be digitized and centralized into a single system that the government officials themselves can administer. The paper discusses limited hindsight literature and proposes 2 new algorithms for abstractive and extractive summarization for Sinhala text. The 2 algorithms are compared against one another in terms of performance, efficiency, precision and accuracy. Experts in the education domain have verified the derived summary of both algorithms. The deliverable artefacts are the mobile application, a RESTful auto-summarization plugin service, and new data sets extracted to train the GPT-3 models.
{"title":"\"Talking Books\" : A Sinhala Abstractive Text Summarization Approach for Sinhala Textbooks","authors":"Bhagya Rathnayake, Kalpani Manathunga, D. Kasthurirathna","doi":"10.1109/I2CT57861.2023.10126205","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126205","url":null,"abstract":"The ability for books to talk would be an exciting concept, and this research discussion paves the path for an identical approach. The research objectives discussed in this paper address several burning problems, solve them and adapt them to future technological enhancements from a Sri Lankan context. Burning problems include reducing printing costs for textbooks, addressing students’ health, promoting green technology, and identifying a suitable summarising approach to the native language, Sinhala resulting in students’ learning ease. Other symptoms for the betterment indicate paths taken to reduce the weight of school bags carried by students, reduce paper usage by the government on printing textbooks, and spread technological awareness to teenagers regarding e-Learning. Textbooks issued by the government will be digitized and centralized into a single system that the government officials themselves can administer. The paper discusses limited hindsight literature and proposes 2 new algorithms for abstractive and extractive summarization for Sinhala text. The 2 algorithms are compared against one another in terms of performance, efficiency, precision and accuracy. Experts in the education domain have verified the derived summary of both algorithms. The deliverable artefacts are the mobile application, a RESTful auto-summarization plugin service, and new data sets extracted to train the GPT-3 models.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116438696","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126160
L. Chitra, K. S.
The Hybrid Renewable Energy System (HRES), which consists of multiple solar panels and wind turbines along with energy storage device, has been used in this work to satisfy the requirements of power consumers. Because of its multiple benefits like cheap maintenance, economic benefits, and fuel independence, photovoltaic power generation has gotten a lot of attention in recent decades. However, getting stable and enhanced power from the PV is the most difficult task and so the highly efficient LUO converter is developed in this work which generates a stable output voltage from an unregulated dc source. In order to optimize the performance of LUO converter and to get supreme power output, GWO based MPPT algorithm is used since it is the most adaptive methodology that is not dependent on system information. On the other hand, Wind Energy Conversion System (WECS) contribution to global energy supply has been steadily increasing. To enhance the wind power generation, a DFIG is utilized, also a PI controller has been assigned which controls the power delivered to the inverter through the PWM rectifier. Grid synchronization is achieved by employing a PI controller which analogize the real and reactive power and delivers it output to the 3ϕ inverter through the PWM generator. MATLAB/Simulink is used to simulate the overall system in this work.
{"title":"Power Quality Enhancements of AC Grid Using Luo Converter with GWO Based MPPT","authors":"L. Chitra, K. S.","doi":"10.1109/I2CT57861.2023.10126160","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126160","url":null,"abstract":"The Hybrid Renewable Energy System (HRES), which consists of multiple solar panels and wind turbines along with energy storage device, has been used in this work to satisfy the requirements of power consumers. Because of its multiple benefits like cheap maintenance, economic benefits, and fuel independence, photovoltaic power generation has gotten a lot of attention in recent decades. However, getting stable and enhanced power from the PV is the most difficult task and so the highly efficient LUO converter is developed in this work which generates a stable output voltage from an unregulated dc source. In order to optimize the performance of LUO converter and to get supreme power output, GWO based MPPT algorithm is used since it is the most adaptive methodology that is not dependent on system information. On the other hand, Wind Energy Conversion System (WECS) contribution to global energy supply has been steadily increasing. To enhance the wind power generation, a DFIG is utilized, also a PI controller has been assigned which controls the power delivered to the inverter through the PWM rectifier. Grid synchronization is achieved by employing a PI controller which analogize the real and reactive power and delivers it output to the 3ϕ inverter through the PWM generator. MATLAB/Simulink is used to simulate the overall system in this work.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122641194","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}
Software reliability estimation for systems operating in the field has been extensively discussed in the literature and several models have been developed. However, this approach of reliability estimation is a reactive approach, where the product has been deployed in the field and field returns are monitored for software issues. An area where there has been limited focus is on the evaluation of software reliability during the development phases of the software. The objective of this paper is to develop and present a methodology for embedded software reliability estimation before it has been deployed in the field. This approach involves assessing reliability risk at the requirements phase, and a method for mitigating and quantifying mitigation amount for reliability estimation through model-in-loop, processor-in-loop, and hardware-in-loop tests. This is a software reliability estimation through proactive risk mitigation strategies and enable guidelines for organizations on the software reliability at product launch.
{"title":"Embedded System Software Reliability Estimation During New Product Development","authors":"Ashutosh Biswal, Ramesh S, Ranjith Kumar Sreenilayam","doi":"10.1109/I2CT57861.2023.10126401","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126401","url":null,"abstract":"Software reliability estimation for systems operating in the field has been extensively discussed in the literature and several models have been developed. However, this approach of reliability estimation is a reactive approach, where the product has been deployed in the field and field returns are monitored for software issues. An area where there has been limited focus is on the evaluation of software reliability during the development phases of the software. The objective of this paper is to develop and present a methodology for embedded software reliability estimation before it has been deployed in the field. This approach involves assessing reliability risk at the requirements phase, and a method for mitigating and quantifying mitigation amount for reliability estimation through model-in-loop, processor-in-loop, and hardware-in-loop tests. This is a software reliability estimation through proactive risk mitigation strategies and enable guidelines for organizations on the software reliability at product launch.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129496228","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126455
Dipra Chaudhry, Harshi Goel, Bindu Verma
Face IDs are becoming the most acceptable modality used for authentication purposes in many recognition systems. This makes it crucial for the recognition and authentication systems to carry out a spoof detection operation before performing facial recognition. The Face Anti-Spoofing (FAS) systems handle the task of identifying fakes. Traditionally, Convolutional Neural Networks (CNNs) have been used to detect spoofs. But, CNNs have certain limitations. One such limitation is that they are not very efficient in extracting the relative placement of different objects. In this paper, we propose a novel TransFAS system. It is based on Video Vision Transformer (VVT). The system takes a bunch of frames at a time and then extracts tokens from them. These tokens are flattened and then loaded with positional information to store the relative placement of each entity in a token. These embedded tokens are passed on to the Transformer Encoder. In the transformer encoder, work is done in different layers. Its final output is a prediction of whether the input sample is live or spoof (print attack, replay attack or 3D Mask attack). Our model is trained on Replay-Attack and 3DMAD datasets. Results show that our model performs better than most of the existing models.
{"title":"TransFAS: Transformer-based network for Face Anti-Spoofing using Token Guided Inspection","authors":"Dipra Chaudhry, Harshi Goel, Bindu Verma","doi":"10.1109/I2CT57861.2023.10126455","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126455","url":null,"abstract":"Face IDs are becoming the most acceptable modality used for authentication purposes in many recognition systems. This makes it crucial for the recognition and authentication systems to carry out a spoof detection operation before performing facial recognition. The Face Anti-Spoofing (FAS) systems handle the task of identifying fakes. Traditionally, Convolutional Neural Networks (CNNs) have been used to detect spoofs. But, CNNs have certain limitations. One such limitation is that they are not very efficient in extracting the relative placement of different objects. In this paper, we propose a novel TransFAS system. It is based on Video Vision Transformer (VVT). The system takes a bunch of frames at a time and then extracts tokens from them. These tokens are flattened and then loaded with positional information to store the relative placement of each entity in a token. These embedded tokens are passed on to the Transformer Encoder. In the transformer encoder, work is done in different layers. Its final output is a prediction of whether the input sample is live or spoof (print attack, replay attack or 3D Mask attack). Our model is trained on Replay-Attack and 3DMAD datasets. Results show that our model performs better than most of the existing models.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128682089","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126492
Tushar Deshpande, Khushi Chavan, Priya Gandhi, Ramchandra S. Mangrulkar
Over the past ten years, advances in deep machine learning techniques, high-speed computing infrastructure development, and an improved understanding of deep learning algorithms have created new opportunities for advanced analysis of neuroimaging data. Neuroscientists can now use the data from neuroimaging to diagnose neurodegenerative diseases. Yet, due to the similarities in disease characteristics, it is challenging to identify such disorders from neuroimaging data accurately. The reason for such results is the current or inevitable limited availability of neuroimaging data. Thus, this paper suggests an unsupervised generative modeling technique using Deep Convolutional Adversarial Networks to produce synthetic images (DCGANs). This method uses the ADNI dataset, which contains data for four neurodegenerative diseases, namely: Alzheimer’s Disease(AD), Mild Cognitive Impairment(MCI), Early Mild Cognitive Impairment(EMCI), Late Mild Cognitive Impairment(LMCI), and subsequently uses DCGAN on the small quantity of data, so increasing the dataset’s size and variety by utilizing GAN. To outperform the conventional deep learning techniques, the artificial images, and the original dataset images are combined and trained into a convolutional neural network (CNN).
{"title":"Neurodegenerative Disease Detection using Deep Convolutional GANs and CNN","authors":"Tushar Deshpande, Khushi Chavan, Priya Gandhi, Ramchandra S. Mangrulkar","doi":"10.1109/I2CT57861.2023.10126492","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126492","url":null,"abstract":"Over the past ten years, advances in deep machine learning techniques, high-speed computing infrastructure development, and an improved understanding of deep learning algorithms have created new opportunities for advanced analysis of neuroimaging data. Neuroscientists can now use the data from neuroimaging to diagnose neurodegenerative diseases. Yet, due to the similarities in disease characteristics, it is challenging to identify such disorders from neuroimaging data accurately. The reason for such results is the current or inevitable limited availability of neuroimaging data. Thus, this paper suggests an unsupervised generative modeling technique using Deep Convolutional Adversarial Networks to produce synthetic images (DCGANs). This method uses the ADNI dataset, which contains data for four neurodegenerative diseases, namely: Alzheimer’s Disease(AD), Mild Cognitive Impairment(MCI), Early Mild Cognitive Impairment(EMCI), Late Mild Cognitive Impairment(LMCI), and subsequently uses DCGAN on the small quantity of data, so increasing the dataset’s size and variety by utilizing GAN. To outperform the conventional deep learning techniques, the artificial images, and the original dataset images are combined and trained into a convolutional neural network (CNN).","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128965321","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：