Pub Date : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10140458
Monika Meena, Rakesh Kumar Tiwari
Analyzing network packets to determine whether they are genuine or suspicious are called “Intrusion Detection.” The significant difficulties associated with this space incorporates the tremendous volume of information for preparing and the quick and streaming information that will be accommodated the expectation interaction. In addition, the intrusion detection model faces additional difficulties as a result of the domain's inherent data imbalance. The classification accuracy and other parameters of enhanced LSTM are contrasted with those of conventional deep learning and other machine learning methods in this study. In addition to classifying the tweets, this framework can be used to investigate user attitudes toward Indian higher education. Two algorithms form the basis of the proposed framework: Using the evolutionary algorithm to improve LSTM. Because the standard LSTM algorithm can select parameter values at random, the enhanced LSTM algorithm uses the evolutionary algorithm to enhance its functionality.
{"title":"Optimum Analysis of Imbalanced Network for Intrusion Detection using LSTM Convolution Technique","authors":"Monika Meena, Rakesh Kumar Tiwari","doi":"10.1109/ICAAIC56838.2023.10140458","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10140458","url":null,"abstract":"Analyzing network packets to determine whether they are genuine or suspicious are called “Intrusion Detection.” The significant difficulties associated with this space incorporates the tremendous volume of information for preparing and the quick and streaming information that will be accommodated the expectation interaction. In addition, the intrusion detection model faces additional difficulties as a result of the domain's inherent data imbalance. The classification accuracy and other parameters of enhanced LSTM are contrasted with those of conventional deep learning and other machine learning methods in this study. In addition to classifying the tweets, this framework can be used to investigate user attitudes toward Indian higher education. Two algorithms form the basis of the proposed framework: Using the evolutionary algorithm to improve LSTM. Because the standard LSTM algorithm can select parameter values at random, the enhanced LSTM algorithm uses the evolutionary algorithm to enhance its functionality.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121263878","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10141274
Mayank Virmani, A. M. Michael, Manjiri Pathak, K. S. Pai, V. B. Prasad
Due to the presence of complex literary devices such as metaphors and imagery, poetry can be difficult to comprehend. This is especially true for literary works of classical poets like Kaalidasa that employ intricate, often conflicting themes which tend to be particularly tedious to interpret and decipher. The beauty of these works of art tends to get lost in translation. A visual representation in the form of images corresponding to the various themes in the poetry, greatly aids in providing a clearer understanding of the meaning and imagery described. The main aim here is to make classical poetry more accessible by generating detailed images that capture and depict the metaphors and themes used in various works of literature. The core task in this paper is to employ novel machine learning (NLP) techniques to detect and extract the central themes and keywords from the poems that encapsulate the essence of the literary work. This is done using transformer models fine-tuned specifically on a summarization dataset, that generate an abstractive summary of the segment of input text. Maintaining context while doing so is essential to the accuracy of the images being generated. Further, this summary is then provided as an input to a Latent Diffusion Model to generate detailed images corresponding to the poetry. The goal of the project is to make it easier to consume and enjoy classical works of literature by providing additional context and information in the form of images complementing the poetry.
{"title":"Image Synthesis from Themes Captured in Poems using Latent Diffusion Models","authors":"Mayank Virmani, A. M. Michael, Manjiri Pathak, K. S. Pai, V. B. Prasad","doi":"10.1109/ICAAIC56838.2023.10141274","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10141274","url":null,"abstract":"Due to the presence of complex literary devices such as metaphors and imagery, poetry can be difficult to comprehend. This is especially true for literary works of classical poets like Kaalidasa that employ intricate, often conflicting themes which tend to be particularly tedious to interpret and decipher. The beauty of these works of art tends to get lost in translation. A visual representation in the form of images corresponding to the various themes in the poetry, greatly aids in providing a clearer understanding of the meaning and imagery described. The main aim here is to make classical poetry more accessible by generating detailed images that capture and depict the metaphors and themes used in various works of literature. The core task in this paper is to employ novel machine learning (NLP) techniques to detect and extract the central themes and keywords from the poems that encapsulate the essence of the literary work. This is done using transformer models fine-tuned specifically on a summarization dataset, that generate an abstractive summary of the segment of input text. Maintaining context while doing so is essential to the accuracy of the images being generated. Further, this summary is then provided as an input to a Latent Diffusion Model to generate detailed images corresponding to the poetry. The goal of the project is to make it easier to consume and enjoy classical works of literature by providing additional context and information in the form of images complementing the poetry.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127356755","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10141161
Siddharth Magadum, Srikar S, Suprith Hattikal, Y. M., Priya Badrinath
Automating the disease detection in plants is one of the most complex recent challenges faced by agricultural experts and farmers worldwide. The traditional laboratory testing methods are inefficient for detecting diseases in crops such as cassava. Unlike rice and maize, cassava is the third-largest source of carbohydrates. It is nutritious, it consists of resistant starch and its root is high in vitamin C. These plants suffer from four major diseases which spread to neighboring cassava plants and affect the cultivation. This paper describes the work done to detect and classify the disease, which will help in figuring out if the crop is healthy and can prevent further spread of disease. Computer vision is a subset of deep learning, which trains computers to interpret and understand the visual world. The paper discusses various ways for training models and their results for disease classification. The work achieves the best accuracy of 89.01% by using the EfficientNetB3 model.
{"title":"Identification of Disease in Cassava Leaf using Deep Learning","authors":"Siddharth Magadum, Srikar S, Suprith Hattikal, Y. M., Priya Badrinath","doi":"10.1109/ICAAIC56838.2023.10141161","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10141161","url":null,"abstract":"Automating the disease detection in plants is one of the most complex recent challenges faced by agricultural experts and farmers worldwide. The traditional laboratory testing methods are inefficient for detecting diseases in crops such as cassava. Unlike rice and maize, cassava is the third-largest source of carbohydrates. It is nutritious, it consists of resistant starch and its root is high in vitamin C. These plants suffer from four major diseases which spread to neighboring cassava plants and affect the cultivation. This paper describes the work done to detect and classify the disease, which will help in figuring out if the crop is healthy and can prevent further spread of disease. Computer vision is a subset of deep learning, which trains computers to interpret and understand the visual world. The paper discusses various ways for training models and their results for disease classification. The work achieves the best accuracy of 89.01% by using the EfficientNetB3 model.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114917964","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10140281
A. K, R. O, J. D, S. S
Phishing attacks, in which victims are handed dangerous URLs, are among the cyberthreats. When you engage with these sites, a process of credential stealing begins. Furthermore, there has been an increase in the transmission of terrorist and extremist tweets, as well as cyberstalking operations, in recent days. As technology advances this can be addressed with machine learning approaches and artificial intelligence by developing models and conducting automated tweet identification. Cyberthreats, cyberstalking, and extremist comments are anticipated using this live algorithm. The dataset obtained from Kaggle is given as input to the model and are trained using the Bi-LSTM method based on a twitter dataset. The algorithm has outstanding performance scores, with a total accuracy of 93% and F1 score of 95%.
{"title":"Bi-LSTM Neural Network Approach to Detect and Recognize Cyberthreats, Cyberstalking and Extremist Tweets in Twitter","authors":"A. K, R. O, J. D, S. S","doi":"10.1109/ICAAIC56838.2023.10140281","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10140281","url":null,"abstract":"Phishing attacks, in which victims are handed dangerous URLs, are among the cyberthreats. When you engage with these sites, a process of credential stealing begins. Furthermore, there has been an increase in the transmission of terrorist and extremist tweets, as well as cyberstalking operations, in recent days. As technology advances this can be addressed with machine learning approaches and artificial intelligence by developing models and conducting automated tweet identification. Cyberthreats, cyberstalking, and extremist comments are anticipated using this live algorithm. The dataset obtained from Kaggle is given as input to the model and are trained using the Bi-LSTM method based on a twitter dataset. The algorithm has outstanding performance scores, with a total accuracy of 93% and F1 score of 95%.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115186395","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10141525
S. Yazhini, Jeyam StudentCSE, StudentCSE, MS. T. Savitha, Devi Apcse, StudentCSE S. Vignesh
Kids who use their phones excessively may experience a range of concerns, including impaired attention, sleep disruptions, mental health problems, eye problems, and obesity. To solve this problem, a system for safety monitoring has been proposed that would let parents watch their kids' whereabouts from a distance. This system functions covertly in the background, gathering phone records, message information, contact lists, and precise location without the child's knowledge. It locates the child's position using the AGPS, and Dijkstra algorithm. The algorithms RSA and AES are employed. The programme, which functions like a spy app, is meant to shield youngsters from offensive material, exploitation, and cyberbullying.
{"title":"Child Digital Monitoring and Controlling System","authors":"S. Yazhini, Jeyam StudentCSE, StudentCSE, MS. T. Savitha, Devi Apcse, StudentCSE S. Vignesh","doi":"10.1109/ICAAIC56838.2023.10141525","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10141525","url":null,"abstract":"Kids who use their phones excessively may experience a range of concerns, including impaired attention, sleep disruptions, mental health problems, eye problems, and obesity. To solve this problem, a system for safety monitoring has been proposed that would let parents watch their kids' whereabouts from a distance. This system functions covertly in the background, gathering phone records, message information, contact lists, and precise location without the child's knowledge. It locates the child's position using the AGPS, and Dijkstra algorithm. The algorithms RSA and AES are employed. The programme, which functions like a spy app, is meant to shield youngsters from offensive material, exploitation, and cyberbullying.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115576841","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10140404
Arifur Rahman, Anik Mahmud, Pintu Chandra Shill
Protein Secondary structure prediction is an emerging topic in bioinformatics to understand briefly the functions of protein and their role in drug invention, medicine and biology. In our research we have applied two recurrent neural network based approach Bi-LSTM (Bidirectional Long Short-Term Memory) and LSTM (Long Short-Term Memory). Our research was focused on primary structure up to 134 in length of amino acids. Initially our proposed model produced a ‘Indexed Lexicon of corpus’ using tri-gram conversion for primary structure strings. Each primary structure tri-gram transformed snippets is substituted with its associated index mentioned in ‘Indexed corpus’. The indexed parameter vector inputted into our proposed Bi-LSTM and LSTM model. We got best accuracy when we have used two Bi-LSTM and three LSTM layers respectively in Bi-LSTM and LSTM models. To prevent biasness and minimize overfitting problem we have utilized two dropout layers for each of Bi-LSTM and LSTM model. We have operated our model on ccPDB 2.0 benchmark dataset. There is total eight states protein secondary structure in this dataset. For this sst8 secondary structure we have achieved 83.24% accuracy for our proposed LSTM model and 89.10% accuracy for our Bi-LSTM model. We have configured our model to run for 50 epochs with batch size 64. For compilation of our models we have utilized ‘adam’ optimizer and the ‘categorical crossentropy’ loss function. To make dataset balanced to our model we have also employed 5-fold cross validation.
{"title":"Neural Network-based Approach to Predict Protein Secondary Structure","authors":"Arifur Rahman, Anik Mahmud, Pintu Chandra Shill","doi":"10.1109/ICAAIC56838.2023.10140404","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10140404","url":null,"abstract":"Protein Secondary structure prediction is an emerging topic in bioinformatics to understand briefly the functions of protein and their role in drug invention, medicine and biology. In our research we have applied two recurrent neural network based approach Bi-LSTM (Bidirectional Long Short-Term Memory) and LSTM (Long Short-Term Memory). Our research was focused on primary structure up to 134 in length of amino acids. Initially our proposed model produced a ‘Indexed Lexicon of corpus’ using tri-gram conversion for primary structure strings. Each primary structure tri-gram transformed snippets is substituted with its associated index mentioned in ‘Indexed corpus’. The indexed parameter vector inputted into our proposed Bi-LSTM and LSTM model. We got best accuracy when we have used two Bi-LSTM and three LSTM layers respectively in Bi-LSTM and LSTM models. To prevent biasness and minimize overfitting problem we have utilized two dropout layers for each of Bi-LSTM and LSTM model. We have operated our model on ccPDB 2.0 benchmark dataset. There is total eight states protein secondary structure in this dataset. For this sst8 secondary structure we have achieved 83.24% accuracy for our proposed LSTM model and 89.10% accuracy for our Bi-LSTM model. We have configured our model to run for 50 epochs with batch size 64. For compilation of our models we have utilized ‘adam’ optimizer and the ‘categorical crossentropy’ loss function. To make dataset balanced to our model we have also employed 5-fold cross validation.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122580566","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10141099
Joseph K.A, Joshua Sony C, Lakshmi Rajkumar M, Syam Krishna P.S, Ambily Francis, Anju Babu
Robots are now more autonomous and effective than ever because to the quick development of digital technologies. Future advancements in robotics could change how people and robots interact. Robots will likely carry out a range of tasks in public areas. Robots could significantly enhance our quality of life and add to the atmosphere, capacity for creativity, and safety of public spaces. However, as this tendency advances, there is a danger that robots will negatively alter public areas and social relationships. This research study investigates how public policy may both improve opportunities brought about by the presence of robots in public spaces and lessen the risks of unfavorable consequences by analyzing prior methods to utilizing and controlling disruptive technology. Robots are effective in waste management also. By using object detection robots could clean the wastes automatically and efficiently by making the surroundings clean.
{"title":"Deep Learning based Beach Cleaning Robot","authors":"Joseph K.A, Joshua Sony C, Lakshmi Rajkumar M, Syam Krishna P.S, Ambily Francis, Anju Babu","doi":"10.1109/ICAAIC56838.2023.10141099","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10141099","url":null,"abstract":"Robots are now more autonomous and effective than ever because to the quick development of digital technologies. Future advancements in robotics could change how people and robots interact. Robots will likely carry out a range of tasks in public areas. Robots could significantly enhance our quality of life and add to the atmosphere, capacity for creativity, and safety of public spaces. However, as this tendency advances, there is a danger that robots will negatively alter public areas and social relationships. This research study investigates how public policy may both improve opportunities brought about by the presence of robots in public spaces and lessen the risks of unfavorable consequences by analyzing prior methods to utilizing and controlling disruptive technology. Robots are effective in waste management also. By using object detection robots could clean the wastes automatically and efficiently by making the surroundings clean.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122473535","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10141120
Sripriya Arunachalam, Shanthi H J, G. Sivagurunathan, Shyamali Das, D. Anand, Thanga Raj M
Over the past few years, there has been a meteoric surge in the quantity of digital information available online for instantaneous sharing, persistent archiving, and inquiring. It has expanded the possibilities for using digital data that is both decentralised and ad hoc in order to make decisions quickly. At present, e-Healthcare is among the most sought-after sectors for EHR and telemedicine communication. Securing electronic health records (EHR) has become a topic of intense interest in recent years, with previous works employing a wide range of methods to better ensure the confidentiality and security of EHR at a reasonable price. There are a number of serious problems with the current research, including computational complexity, increased process time, information leakage, vulnerability to various assaults, scalability difficulty, etc. Clinical data analysis presents several difficulties, but disease prediction is one of the most significant ones. The suggested study aims to apply deep learning (DL) classification algorithms for disease prediction. A technique that utilises cloud computing, fog computing, and IoMT more recently has been presented for diagnosing illness. Fast DL classification analysis is performed in the fog layer. When compared to the alternative proposed model Bi-CNN, the healthcare model's efficiency in the Bi-LSTM simulation yields significantly better results: 97.31% of accuracy, 97.58% of recall, 96.90% of precision, 94.90% of F1-measure, 97.25% of specificity, and 94.80% of G-mean.
{"title":"Cloud-based Decentralized Smart Healthcare for Patient Monitoring on Deep Learning","authors":"Sripriya Arunachalam, Shanthi H J, G. Sivagurunathan, Shyamali Das, D. Anand, Thanga Raj M","doi":"10.1109/ICAAIC56838.2023.10141120","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10141120","url":null,"abstract":"Over the past few years, there has been a meteoric surge in the quantity of digital information available online for instantaneous sharing, persistent archiving, and inquiring. It has expanded the possibilities for using digital data that is both decentralised and ad hoc in order to make decisions quickly. At present, e-Healthcare is among the most sought-after sectors for EHR and telemedicine communication. Securing electronic health records (EHR) has become a topic of intense interest in recent years, with previous works employing a wide range of methods to better ensure the confidentiality and security of EHR at a reasonable price. There are a number of serious problems with the current research, including computational complexity, increased process time, information leakage, vulnerability to various assaults, scalability difficulty, etc. Clinical data analysis presents several difficulties, but disease prediction is one of the most significant ones. The suggested study aims to apply deep learning (DL) classification algorithms for disease prediction. A technique that utilises cloud computing, fog computing, and IoMT more recently has been presented for diagnosing illness. Fast DL classification analysis is performed in the fog layer. When compared to the alternative proposed model Bi-CNN, the healthcare model's efficiency in the Bi-LSTM simulation yields significantly better results: 97.31% of accuracy, 97.58% of recall, 96.90% of precision, 94.90% of F1-measure, 97.25% of specificity, and 94.80% of G-mean.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121893044","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10140790
G. Surekha, Patlolla Sai Keerthana, Nallantla Jaswanth Varma, Tummala Sai Gopi
Deep convolution neural networks have made sig-nificant advances in object identification. The popularity of machine learning-based image classification has increased as a result of developments in deep learning algorithms that makes it possible to extract features from images. Yet, conventional image classification algorithms are far too incorrect and untrustworthy to address the problem. Automation is crucial due to the vast geographic areas that must be explored and the scarcity of researchers available to carry out the searches. The proposed work employs deep learning-based image classification using a hybrid model of ResNet101 and VGG16 to address the challenges of image classification in large geographic areas using satellite images.
{"title":"Hybrid Image Classification Model using ResNet101 and VGG16","authors":"G. Surekha, Patlolla Sai Keerthana, Nallantla Jaswanth Varma, Tummala Sai Gopi","doi":"10.1109/ICAAIC56838.2023.10140790","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10140790","url":null,"abstract":"Deep convolution neural networks have made sig-nificant advances in object identification. The popularity of machine learning-based image classification has increased as a result of developments in deep learning algorithms that makes it possible to extract features from images. Yet, conventional image classification algorithms are far too incorrect and untrustworthy to address the problem. Automation is crucial due to the vast geographic areas that must be explored and the scarcity of researchers available to carry out the searches. The proposed work employs deep learning-based image classification using a hybrid model of ResNet101 and VGG16 to address the challenges of image classification in large geographic areas using satellite images.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"160 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122039161","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}
Breast cancer is a complicated and diverse illness that affects millions of women worldwide. A correct diagnosis and early detection are essential for effective therapy and better patient outcomes. In the past few years, developing predictive models and machine learning algorithms has received a lot of interest in the detection and diagnosis of breast cancer. This research study intends to present a thorough overview of the most recent breast cancer prognostic models, covering risk assessment, diagnosis, and prognosis. This paper addresses many different data types, including clinical, genetic, and imaging data, used in breast cancer prediction, as well as the several machine learning techniques used, including SVM, naïve Bayes, and random forests. A comparative analysis of different algorithms with methodology has been provided in this research study.
{"title":"Machine Learning Approach for Breast Cancer Prediction: A Review","authors":"Yashwant Wankhade, Shrividya Toutam, Khushboo Thakre, Kamlesh Kalbande, Prasheel N. Thakre","doi":"10.1109/ICAAIC56838.2023.10141164","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10141164","url":null,"abstract":"Breast cancer is a complicated and diverse illness that affects millions of women worldwide. A correct diagnosis and early detection are essential for effective therapy and better patient outcomes. In the past few years, developing predictive models and machine learning algorithms has received a lot of interest in the detection and diagnosis of breast cancer. This research study intends to present a thorough overview of the most recent breast cancer prognostic models, covering risk assessment, diagnosis, and prognosis. This paper addresses many different data types, including clinical, genetic, and imaging data, used in breast cancer prediction, as well as the several machine learning techniques used, including SVM, naïve Bayes, and random forests. A comparative analysis of different algorithms with methodology has been provided in this research study.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116591739","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：