1.
Farooq, U.; Reddy, K. K. S.; Shishira, K. S.; Jayanthi, M. G.; Kannadaguli, P.
Comparing Hindustani Music Raga Prediction Systems using DL and ML Models Proceedings
Institute of Electrical and Electronics Engineers Inc., 2024, ISBN: 979-835037250-2 (ISBN), (1).
@proceedings{9,
title = {Comparing Hindustani Music Raga Prediction Systems using DL and ML Models},
author = {U. Farooq and K. K. S. Reddy and K. S. Shishira and M. G. Jayanthi and P. Kannadaguli},
doi = {10.1109/ICETCS61022.2024.10543647},
isbn = {979-835037250-2 (ISBN)},
year = {2024},
date = {2024-01-01},
journal = {International Conference on Emerging Technologies in Computer Science for Interdisciplinary Applications, ICETCS 2024},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {This project aims to employ DL and ML techniques to predict ragas in Indian classical music accurately. The focus is on developing a system that can process audio recordings and make precise raga predictions. The classification task utilizes CNN and RNN networks, to enhance performance. Extensive evaluation using diverse recordings is conducted, comparing the framework against traditional methods. The outcomes of this project has potential applications for music analysis, archiving, recommendation systems, and education in Indian classical music. The developed raga prediction framework can serve as a valuable tool for automatic raga identification. Additionally, it contributes to the field of music information retrieval by showcasing the capabilities of DL/ML techniques in tackling musical tasks. © 2024 IEEE.},
note = {1},
keywords = {CSE},
pubstate = {published},
tppubtype = {proceedings}
}
This project aims to employ DL and ML techniques to predict ragas in Indian classical music accurately. The focus is on developing a system that can process audio recordings and make precise raga predictions. The classification task utilizes CNN and RNN networks, to enhance performance. Extensive evaluation using diverse recordings is conducted, comparing the framework against traditional methods. The outcomes of this project has potential applications for music analysis, archiving, recommendation systems, and education in Indian classical music. The developed raga prediction framework can serve as a valuable tool for automatic raga identification. Additionally, it contributes to the field of music information retrieval by showcasing the capabilities of DL/ML techniques in tackling musical tasks. © 2024 IEEE.
2.
Devi, K. K.; Kumar, J. P.
Sustainable Food Development Based on Ensemble Machine Learning Assisted Crop and Fertilizer Recommendation System Journal Article
In: Journal of Machine and Computing, vol. 4, pp. 317-326,, 2024, ISBN: 27891801 (ISSN), (2).
@article{11,
title = {Sustainable Food Development Based on Ensemble Machine Learning Assisted Crop and Fertilizer Recommendation System},
author = {K. K. Devi and J. P. Kumar},
doi = {10.53759/7669/jmc202404030},
isbn = {27891801 (ISSN)},
year = {2024},
date = {2024-01-01},
journal = {Journal of Machine and Computing},
volume = {4},
pages = {317-326,},
publisher = {AnaPub Publications},
abstract = {Agriculture is the most vital sector for the global food supply, and it also provides raw materials for other types of industries. A crop recommendation system is essential for farmers who want to get the most out of their crop-choosing decisions. Over the last several decades, the world's ability to produce food has grown substantially owing to the extensive usage of fertilizers. Therefore, there has to be a more eco-friendly and effective way to utilize fertilizers that include nitrogen (N), phosphorous (P), and potassium (K) to ensure food security. For the reason, this study proposes an ensemble machine learning-assisted crop and fertilizer recommendation system (EML-CFRS) to maximize agricultural output while ensuring the correct use of mineral resources. The research used a dataset obtained from the Kaggle repository like that people can assess several distinct ML algorithms. The databases include data on three climate variables-temperature, rainfall, and humidity-and information on NPK and soil pH. The yields agricultural crops were used to train these models, including Decision Tree, KNN, XGBoost, Support Vector Machine, and Random Forest. Depending on the current weather and soil conditions, the trained model may then recommend the optimal fertiliser for a certain crop. Predicting the ideal kind and quantity of fertilizer for different crops was accomplished with a 96.5% accuracy rate by our suggested strategy. © 2024 The Authors.},
note = {2},
keywords = {CSE},
pubstate = {published},
tppubtype = {article}
}
Agriculture is the most vital sector for the global food supply, and it also provides raw materials for other types of industries. A crop recommendation system is essential for farmers who want to get the most out of their crop-choosing decisions. Over the last several decades, the world's ability to produce food has grown substantially owing to the extensive usage of fertilizers. Therefore, there has to be a more eco-friendly and effective way to utilize fertilizers that include nitrogen (N), phosphorous (P), and potassium (K) to ensure food security. For the reason, this study proposes an ensemble machine learning-assisted crop and fertilizer recommendation system (EML-CFRS) to maximize agricultural output while ensuring the correct use of mineral resources. The research used a dataset obtained from the Kaggle repository like that people can assess several distinct ML algorithms. The databases include data on three climate variables-temperature, rainfall, and humidity-and information on NPK and soil pH. The yields agricultural crops were used to train these models, including Decision Tree, KNN, XGBoost, Support Vector Machine, and Random Forest. Depending on the current weather and soil conditions, the trained model may then recommend the optimal fertiliser for a certain crop. Predicting the ideal kind and quantity of fertilizer for different crops was accomplished with a 96.5% accuracy rate by our suggested strategy. © 2024 The Authors.
3.
Rakesh, V. S.; Vasanthakumar, G. U.
Enhancing Network Security: A Novel Hybrid ML Approach for DDoS Attack Detection in SDN Proceedings
Grenze Scientific Society, vol. 1, 2024, ISBN: 979-833130057-9 (ISBN), (0).
@proceedings{17,
title = {Enhancing Network Security: A Novel Hybrid ML Approach for DDoS Attack Detection in SDN},
author = {V. S. Rakesh and G. U. Vasanthakumar},
isbn = {979-833130057-9 (ISBN)},
year = {2024},
date = {2024-01-01},
journal = {15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024},
volume = {1},
pages = {915-922,},
publisher = {Grenze Scientific Society},
abstract = {Software-defined networking represents a ground breaking advancement in network technology, characterized by its desirable attributes such as enhanced flexibility and manageability. Although ongoing, the issue of DDoS assaults in SDN is characterized by malicious and obtrusive network traffic that overwhelms SDN resources. Despite numerous security methodologies aimed at detecting DDoS attacks, the challenge of effectively addressing this issue continues to persist as an active area of research. The XG-Light Hybrid, a unique hybrid system, has been developed in this work as a solution to this problem. This discovery is significant because it has the potential to dramatically increase the reliability of DDoS attack detection in SDN environments, hence boosting network security and stability. Key findings reveal that the proposed hybrid approach outperforms individual machine learning algorithms with respect to DDoS detection. © Grenze Scientific Society, 2024.},
note = {0},
keywords = {CSE},
pubstate = {published},
tppubtype = {proceedings}
}
Software-defined networking represents a ground breaking advancement in network technology, characterized by its desirable attributes such as enhanced flexibility and manageability. Although ongoing, the issue of DDoS assaults in SDN is characterized by malicious and obtrusive network traffic that overwhelms SDN resources. Despite numerous security methodologies aimed at detecting DDoS attacks, the challenge of effectively addressing this issue continues to persist as an active area of research. The XG-Light Hybrid, a unique hybrid system, has been developed in this work as a solution to this problem. This discovery is significant because it has the potential to dramatically increase the reliability of DDoS attack detection in SDN environments, hence boosting network security and stability. Key findings reveal that the proposed hybrid approach outperforms individual machine learning algorithms with respect to DDoS detection. © Grenze Scientific Society, 2024.
4.
Patil, A.; Sanjana, M.; Shilpa, M.; Vaishnavi, R.; Priyadarshini, M.
Brain Tumor Detection and Classification with One-Hot Encoding and EfficientNetB0 using MRI Images Proceedings
Institute of Electrical and Electronics Engineers Inc., 2024, ISBN: 979-835036717-1 (ISBN), (0).
@proceedings{26,
title = {Brain Tumor Detection and Classification with One-Hot Encoding and EfficientNetB0 using MRI Images},
author = {A. Patil and M. Sanjana and M. Shilpa and R. Vaishnavi and M. Priyadarshini},
doi = {10.1109/ICIPCN63822.2024.00023},
isbn = {979-835036717-1 (ISBN)},
year = {2024},
date = {2024-01-01},
journal = {Proceedings - 2024 5th International Conference on Image Processing and Capsule Networks, ICIPCN 2024},
pages = {84-90,},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Convolutional Neural Networks (CNNs) perform well in accurately classifying brain tumors identified in medical scans such as MRI. This study presents a CNN architecture, which contains convolutional layers for extracting features followed by maximum pooling layers for spatial down-sampling, for dimensionality reduction. To mitigate overfitting, dropout layers are employed are strategically integrated, ensuring the generalizability within the model. The task is accomplished, incorporating using fully connected layers with the SoftMax activation function. The Convolutional Neural Network(CNN) proposed architecture demonstrates effectiveness in categorizing brain tumors into three distinct types: meningioma, glioma, and pituitary tumors. Experimental evaluation reveals promising results, with the model achieving an overall classification accuracy of 98%. Specifically, it detects glioma with 96% accuracy, identifies no tumor with 99% accuracy, differentiates meningioma with 97% accuracy, and identifies pituitary tumors with 99% accuracy. The dataset comprises 3264 images, 90% of which are for training and 10% for testing. The approach shows considerable promise to assist clinicians in accurate and timely diagnosis, thereby facilitating tailored treatment planning for patients with brain tumors. Further research can explore improvements to the network architecture and explore its applicability in different medical imaging datasets. © 2024 IEEE.},
note = {0},
keywords = {CSE},
pubstate = {published},
tppubtype = {proceedings}
}
Convolutional Neural Networks (CNNs) perform well in accurately classifying brain tumors identified in medical scans such as MRI. This study presents a CNN architecture, which contains convolutional layers for extracting features followed by maximum pooling layers for spatial down-sampling, for dimensionality reduction. To mitigate overfitting, dropout layers are employed are strategically integrated, ensuring the generalizability within the model. The task is accomplished, incorporating using fully connected layers with the SoftMax activation function. The Convolutional Neural Network(CNN) proposed architecture demonstrates effectiveness in categorizing brain tumors into three distinct types: meningioma, glioma, and pituitary tumors. Experimental evaluation reveals promising results, with the model achieving an overall classification accuracy of 98%. Specifically, it detects glioma with 96% accuracy, identifies no tumor with 99% accuracy, differentiates meningioma with 97% accuracy, and identifies pituitary tumors with 99% accuracy. The dataset comprises 3264 images, 90% of which are for training and 10% for testing. The approach shows considerable promise to assist clinicians in accurate and timely diagnosis, thereby facilitating tailored treatment planning for patients with brain tumors. Further research can explore improvements to the network architecture and explore its applicability in different medical imaging datasets. © 2024 IEEE.
5.
Kumar, Sandeep; Pai, Vaikunta; Shenoy, Ashwin; Santhosh, S.; Rakesh, V. S.; Prashanth, B. S.
Institute of Electrical and Electronics Engineers Inc., 2024, ISBN: 979-835030641-5 (ISBN), (0).
@proceedings{36,
title = {Optimizing Agricultural Productivity: A Data-Driven Ensemble Model for Crop Recommendation Based on Site-Specific Characteristics and Weather Conditions in India},
author = {Sandeep Kumar and Vaikunta Pai and Ashwin Shenoy and S. Santhosh and V. S. Rakesh and B. S. Prashanth},
doi = {10.1109/IITCEE59897.2024.10467680},
isbn = {979-835030641-5 (ISBN)},
year = {2024},
date = {2024-01-01},
journal = {Proceedings of the 2nd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {India's economy and employment are significantly impacted by agriculture. Indian farmers frequently make the mistake of selecting the incorrect crop for the characteristics of their land. The effect is a decrease in productivity. Careful crop selection is necessary for farmers to provide high-quality harvests. We have discovered a solution to the farmers' dilemma. Here, we introduce an ensemble model that uses a majority voting approach recommendation system to provide extremely precise crop recommendations for parameters unique to each site, such as soil nutrients (nitrogen, phosphorus, potassium, and pH level) and local weather conditions (temperature, humidity, and rainfall). The methods we use to do this include Decision Tree, Random Forest, K-Nearest Neighbors, and Naive Bayes. © 2024 IEEE.},
note = {0},
keywords = {CSE},
pubstate = {published},
tppubtype = {proceedings}
}
India's economy and employment are significantly impacted by agriculture. Indian farmers frequently make the mistake of selecting the incorrect crop for the characteristics of their land. The effect is a decrease in productivity. Careful crop selection is necessary for farmers to provide high-quality harvests. We have discovered a solution to the farmers' dilemma. Here, we introduce an ensemble model that uses a majority voting approach recommendation system to provide extremely precise crop recommendations for parameters unique to each site, such as soil nutrients (nitrogen, phosphorus, potassium, and pH level) and local weather conditions (temperature, humidity, and rainfall). The methods we use to do this include Decision Tree, Random Forest, K-Nearest Neighbors, and Naive Bayes. © 2024 IEEE.
6.
Vasantha, M.; Sudarsanan, D.; Santosh, M.; Madhura, G. K.
Developing smart cities by integrating blockchain-based GRNN with CSO-transformed paillier encryption model Book Chapter
In: pp. 94-108,, CRC Press, 2024, ISBN: 978-104011271-7 (ISBN); 978-103260708-5 (ISBN), (0).
@inbook{37,
title = {Developing smart cities by integrating blockchain-based GRNN with CSO-transformed paillier encryption model},
author = {M. Vasantha and D. Sudarsanan and M. Santosh and G. K. Madhura},
doi = {10.1201/9781003460367-7},
isbn = {978-104011271-7 (ISBN); 978-103260708-5 (ISBN)},
year = {2024},
date = {2024-01-01},
journal = {Blockchain for IoT Systems: Concept, Framework and Applications},
pages = {94-108,},
publisher = {CRC Press},
note = {0},
keywords = {CSE},
pubstate = {published},
tppubtype = {inbook}
}
7.
Ganesh, D. R.; William, P.; Biradar, V. S.; Varalatchoumy, M.; Singh, C.; Deepak, A.; Shrivastava, A.
Energy-Efficient Resource Allocation and Relay-Selection for Wireless Sensor Networks Journal Article
In: International Journal of Intelligent Systems and Applications in Engineering, vol. 12, pp. 113-121,, 2024, ISBN: 21476799 (ISSN), (20).
@article{38,
title = {Energy-Efficient Resource Allocation and Relay-Selection for Wireless Sensor Networks},
author = {D. R. Ganesh and P. William and V. S. Biradar and M. Varalatchoumy and C. Singh and A. Deepak and A. Shrivastava},
isbn = {21476799 (ISSN)},
year = {2024},
date = {2024-01-01},
journal = {International Journal of Intelligent Systems and Applications in Engineering},
volume = {12},
pages = {113-121,},
publisher = {Ismail Saritas},
abstract = {We study a cooperative wireless network in the framework of this inquiry. This network is made up of two transceiver nodes that connect with one another through two-way amplify-and-forward (AF) relay nodes that have a limited amount of energy. This network is used to study the problem. The energy that is included inside the signal that has been received is used by the relay nodes in order to magnify the signal before it is retransmitted to the transceiver nodes. As a consequence of this, the transceiver nodes are able to transfer both information and energy at the same time. In order to accomplish simultaneous information extraction and energy harvesting at the relay, we study a time switching-based relaying (TSR) protocol in addition to a power splitting-based relaying (PSR) mechanism. TSR stands for time switching relaying, while PSR stands for power splitting relaying. By using the dual decomposition strategy, we are able to provide a solution to the problem that is close to optimal. The findings of the simulation indicate that the joint resource allocation plan that was recommended fulfils the required requirements for service quality, and that the degree of energy efficiency that may be achieved is greater than that of some projects that are currently being worked on. In addition, the resource allocation approach that has been provided works better in terms of convergence under a variety of topologies. This demonstrates the high scalability of the resource allocation system. The results of an in-depth simulation are presented to illustrate how well our proposed method works in terms of the distribution of transmitting power among the nodes and the overall utility that the network provides. As a consequence of this, there is reason to be positive about the future of practical applications including the joint optimization technique. © 2024, Ismail Saritas. All rights reserved.},
note = {20},
keywords = {CSE},
pubstate = {published},
tppubtype = {article}
}
We study a cooperative wireless network in the framework of this inquiry. This network is made up of two transceiver nodes that connect with one another through two-way amplify-and-forward (AF) relay nodes that have a limited amount of energy. This network is used to study the problem. The energy that is included inside the signal that has been received is used by the relay nodes in order to magnify the signal before it is retransmitted to the transceiver nodes. As a consequence of this, the transceiver nodes are able to transfer both information and energy at the same time. In order to accomplish simultaneous information extraction and energy harvesting at the relay, we study a time switching-based relaying (TSR) protocol in addition to a power splitting-based relaying (PSR) mechanism. TSR stands for time switching relaying, while PSR stands for power splitting relaying. By using the dual decomposition strategy, we are able to provide a solution to the problem that is close to optimal. The findings of the simulation indicate that the joint resource allocation plan that was recommended fulfils the required requirements for service quality, and that the degree of energy efficiency that may be achieved is greater than that of some projects that are currently being worked on. In addition, the resource allocation approach that has been provided works better in terms of convergence under a variety of topologies. This demonstrates the high scalability of the resource allocation system. The results of an in-depth simulation are presented to illustrate how well our proposed method works in terms of the distribution of transmitting power among the nodes and the overall utility that the network provides. As a consequence of this, there is reason to be positive about the future of practical applications including the joint optimization technique. © 2024, Ismail Saritas. All rights reserved.
8.
Bharani, B. R.; Murtugudde, G.; Sreenivasa, B. R.; Verma, A.; Al-Yarimi, F. A. M.; Khan, M. I.; Eldin, S. M.
Grey wolf optimization and enhanced stochastic fractal search algorithm for exoplanet detection Journal Article
In: European Physical Journal Plus, vol. 138, pp. 424+, 2023, ISBN: 21905444 (ISSN), (5).
@article{1,
title = {Grey wolf optimization and enhanced stochastic fractal search algorithm for exoplanet detection},
author = {B. R. Bharani and G. Murtugudde and B. R. Sreenivasa and A. Verma and F. A. M. Al-Yarimi and M. I. Khan and S. M. Eldin},
doi = {10.1140/epjp/s13360-023-04024-y},
isbn = {21905444 (ISSN)},
year = {2023},
date = {2023-01-01},
journal = {European Physical Journal Plus},
volume = {138},
pages = {424+},
publisher = {Springer Science and Business Media Deutschland GmbH},
abstract = {Detection of Exoplanet had been an ‘intensely active’ exploration area within Astronomy where several attempts are made. In the proposed research work, exoplanet detection was done using a Kepler Dataset. Data pre-processing was carried out through Mean Imputation which was found to be the most common procedure of replacing missing value. For assessing Imputation Method’s performance, Normalized Root Mean Square Error was calculated. In feature selection method, a novel combination of Grey Wolf Optimizer (GWO) based on Enhanced Stochastic Fractal Search Algorithm (ESFSA) had been utilized, in a more advanced manner, for reducing the number of normalized input values to those which were highly beneficial. Lastly, after finding the best optimum values and delivering them to Random Forest (RF), the exoplanet got classified into 3 categories—False Positive, Not Detected as well as Candidate. The research work also showed the quantitative analysis of proposed GWO-based ESFSA with other feature selection methods and RF classifier with other existing classifiers. Overall comparative analysis of the proposed method with other related works (present in the literature) was also carried out. As observed, GWO-based ESFSA provided outstanding results—99.74% of recall, 99.80% of specificity, 99.81% of accuracy, 99.98% of sensitivity, 98.84% of precision and 97.21% of F1-score, and proved its superiority over existing methods. © 2023, The Author(s), under exclusive licence to Società Italiana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature.},
note = {5},
keywords = {CSE},
pubstate = {published},
tppubtype = {article}
}
Detection of Exoplanet had been an ‘intensely active’ exploration area within Astronomy where several attempts are made. In the proposed research work, exoplanet detection was done using a Kepler Dataset. Data pre-processing was carried out through Mean Imputation which was found to be the most common procedure of replacing missing value. For assessing Imputation Method’s performance, Normalized Root Mean Square Error was calculated. In feature selection method, a novel combination of Grey Wolf Optimizer (GWO) based on Enhanced Stochastic Fractal Search Algorithm (ESFSA) had been utilized, in a more advanced manner, for reducing the number of normalized input values to those which were highly beneficial. Lastly, after finding the best optimum values and delivering them to Random Forest (RF), the exoplanet got classified into 3 categories—False Positive, Not Detected as well as Candidate. The research work also showed the quantitative analysis of proposed GWO-based ESFSA with other feature selection methods and RF classifier with other existing classifiers. Overall comparative analysis of the proposed method with other related works (present in the literature) was also carried out. As observed, GWO-based ESFSA provided outstanding results—99.74% of recall, 99.80% of specificity, 99.81% of accuracy, 99.98% of sensitivity, 98.84% of precision and 97.21% of F1-score, and proved its superiority over existing methods. © 2023, The Author(s), under exclusive licence to Società Italiana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature.
9.
Devi, Vimala; Kavitha, K. S.
Adaptive deep Q learning network with reinforcement learning for crime prediction Journal Article
In: Evolutionary Intelligence, vol. 16, pp. 685-696,, 2023, ISBN: 18645909 (ISSN), (3).
@article{2,
title = {Adaptive deep Q learning network with reinforcement learning for crime prediction},
author = {Vimala Devi and K. S. Kavitha},
doi = {10.1007/s12065-021-00694-8},
isbn = {18645909 (ISSN)},
year = {2023},
date = {2023-01-01},
journal = {Evolutionary Intelligence},
volume = {16},
pages = {685-696,},
publisher = {Springer Science and Business Media Deutschland GmbH},
abstract = {Crime prediction models are very useful for the police force to prevent crimes from happening and to reduce the crime rate of the city. Existing crime prediction models are not efficient in handling the data imbalance and have an overfitting problem. In this research, an adaptive DRQN model is proposed to develop a robust crime prediction model. The proposed adaptive DRQN model includes the application of GRU instead of LSTM unit to store the relevant features for the effective classification of Sacramento city crime data. The storage of relevant features for a long time helps to handle the data imbalance problem and irrelevant features are eliminated to avoid overfitting problems. Adaptive agents based on the MDP are applied to adaptively learn the input data and provide effective predictions. The reinforcement learning method is applied in the proposed adaptive DRQN model to select the optimal state value and to identify the best reward value. The proposed adaptive DRQN model has an MAE of 36.39 which is better than the existing Recurrent Q-Learning model has 38.82 MAE. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.},
note = {3},
keywords = {CSE},
pubstate = {published},
tppubtype = {article}
}
Crime prediction models are very useful for the police force to prevent crimes from happening and to reduce the crime rate of the city. Existing crime prediction models are not efficient in handling the data imbalance and have an overfitting problem. In this research, an adaptive DRQN model is proposed to develop a robust crime prediction model. The proposed adaptive DRQN model includes the application of GRU instead of LSTM unit to store the relevant features for the effective classification of Sacramento city crime data. The storage of relevant features for a long time helps to handle the data imbalance problem and irrelevant features are eliminated to avoid overfitting problems. Adaptive agents based on the MDP are applied to adaptively learn the input data and provide effective predictions. The reinforcement learning method is applied in the proposed adaptive DRQN model to select the optimal state value and to identify the best reward value. The proposed adaptive DRQN model has an MAE of 36.39 which is better than the existing Recurrent Q-Learning model has 38.82 MAE. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
10.
Kumar, S.; Setty, S. L. N.
UFS-LSTM: unsupervised feature selection with long short-term memory network for remote sensing scene classification Journal Article
In: Evolutionary Intelligence, vol. 16, pp. 299-315,, 2023, ISBN: 18645909 (ISSN), (1).
@article{7,
title = {UFS-LSTM: unsupervised feature selection with long short-term memory network for remote sensing scene classification},
author = {S. Kumar and S. L. N. Setty},
doi = {10.1007/s12065-021-00660-4},
isbn = {18645909 (ISSN)},
year = {2023},
date = {2023-01-01},
journal = {Evolutionary Intelligence},
volume = {16},
pages = {299-315,},
publisher = {Springer Science and Business Media Deutschland GmbH},
abstract = {The aim of this research is to perform remote sensing scene classification, because it supports numerous strategic research fields like land use and land cover monitoring. However, classifying an enormous amount of remote sensing data is a challenging task in scene classification. In this research work, a new model is introduced to improve the feature extraction ability for better scene classification. A multiscale Retinex technique is employed for color restoration, and contrast enhancement in the aerial images that are collected from UC Merced, aerial image dataset, and RESISC45. Further, the feature extraction is carried out using steerable pyramid transform, gray level co-occurrence matrix features, and local ternary pattern. The feature extraction mechanism reduces overfitting risks, improves training process, and data visualization ability. Generally, the extracted features are high dimension, so an unsupervised feature selection based on multi subspace randomization and collaboration with state transition algorithm is proposed for selecting active features for better multiclass classification. The selected features are fed to long short term memory network for scene type classification. The experimental results showed that the proposed model achieved 99.14 %, 98.09%, and 99.25% of overall classification accuracy on UC Merced, RESISC45 and aerial image dataset. The proposed model showed a minimum of 0.03 % and maximum of 18.6 % improvement in classification accuracy compared to the existing models like self-attention based deep feature fusion, multitask learning system with convolutional neural network, multilayer feature fusion Wasserstein generative adversarial networks, and transfer learning model on UC Merced, RESISC45 and aerial dataset, respectively. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.},
note = {1},
keywords = {CSE},
pubstate = {published},
tppubtype = {article}
}
The aim of this research is to perform remote sensing scene classification, because it supports numerous strategic research fields like land use and land cover monitoring. However, classifying an enormous amount of remote sensing data is a challenging task in scene classification. In this research work, a new model is introduced to improve the feature extraction ability for better scene classification. A multiscale Retinex technique is employed for color restoration, and contrast enhancement in the aerial images that are collected from UC Merced, aerial image dataset, and RESISC45. Further, the feature extraction is carried out using steerable pyramid transform, gray level co-occurrence matrix features, and local ternary pattern. The feature extraction mechanism reduces overfitting risks, improves training process, and data visualization ability. Generally, the extracted features are high dimension, so an unsupervised feature selection based on multi subspace randomization and collaboration with state transition algorithm is proposed for selecting active features for better multiclass classification. The selected features are fed to long short term memory network for scene type classification. The experimental results showed that the proposed model achieved 99.14 %, 98.09%, and 99.25% of overall classification accuracy on UC Merced, RESISC45 and aerial image dataset. The proposed model showed a minimum of 0.03 % and maximum of 18.6 % improvement in classification accuracy compared to the existing models like self-attention based deep feature fusion, multitask learning system with convolutional neural network, multilayer feature fusion Wasserstein generative adversarial networks, and transfer learning model on UC Merced, RESISC45 and aerial dataset, respectively. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
11.
Sheela, J.; Meena, S. D.; Rao, T. P. C.; Chetty, B. M.; Gajula, S. K.; Reddy, R. R.; Kumar, M. S.; Nagesh, A. L.
Text clustering using fuzzy rule and lexical term Proceedings
American Institute of Physics Inc., vol. 2869, 2023, ISBN: 0094243X (ISSN); 978-073544684-7 (ISBN), (0).
@proceedings{29,
title = {Text clustering using fuzzy rule and lexical term},
author = {J. Sheela and S. D. Meena and T. P. C. Rao and B. M. Chetty and S. K. Gajula and R. R. Reddy and M. S. Kumar and A. L. Nagesh},
doi = {10.1063/5.0168206},
isbn = {0094243X (ISSN); 978-073544684-7 (ISBN)},
year = {2023},
date = {2023-01-01},
journal = {AIP Conference Proceedings},
volume = {2869},
pages = {050013+},
publisher = {American Institute of Physics Inc.},
abstract = {The fast development of data technology has created a straight system to store and access large quantities of information. The created system has the drawback of extracting potentially valuable knowledge not only in an efficient manner but also in a manner that is easily understood by human beings. One solution to it is in linguistic summarization. This enables the clearing of coherent data summaries that are more consistent with the human cognitive system. The major drawback of the existing applications is in involving high dimensional and distributed info which makes it tough to capture the relevant data. This research focuses on two tasks: one is in selecting the most significant content from source documents and the other is in generating coherent summary by using lexical chaining. In this research paper, an automatic method of text summarization depending on fuzzy sets to extract diversity of structures has been proposed to identify more significant information in the documents. The summary generated by the system is compared to a summary created by domain experts. This method is completely different from other proposed methods described in the literature survey. The text summary is created in the proposed method by testing eight connected features via reduced dimensionality and less fuzzy set rules used for text summarization. In this method, the documents have been summarized by probing connected features and subsequently by different fuzzy sets. The DUC dataset is used during the training and testing phases of the planned summary system. Base Line, weight, accuracy, memory, and F-measure assess the planned system. The outcome of the experiments demonstrations that the proposed technique provides well f-measure than baseline and weight approaches © 2023 Author(s).},
note = {0},
keywords = {CSE},
pubstate = {published},
tppubtype = {proceedings}
}
The fast development of data technology has created a straight system to store and access large quantities of information. The created system has the drawback of extracting potentially valuable knowledge not only in an efficient manner but also in a manner that is easily understood by human beings. One solution to it is in linguistic summarization. This enables the clearing of coherent data summaries that are more consistent with the human cognitive system. The major drawback of the existing applications is in involving high dimensional and distributed info which makes it tough to capture the relevant data. This research focuses on two tasks: one is in selecting the most significant content from source documents and the other is in generating coherent summary by using lexical chaining. In this research paper, an automatic method of text summarization depending on fuzzy sets to extract diversity of structures has been proposed to identify more significant information in the documents. The summary generated by the system is compared to a summary created by domain experts. This method is completely different from other proposed methods described in the literature survey. The text summary is created in the proposed method by testing eight connected features via reduced dimensionality and less fuzzy set rules used for text summarization. In this method, the documents have been summarized by probing connected features and subsequently by different fuzzy sets. The DUC dataset is used during the training and testing phases of the planned summary system. Base Line, weight, accuracy, memory, and F-measure assess the planned system. The outcome of the experiments demonstrations that the proposed technique provides well f-measure than baseline and weight approaches © 2023 Author(s).
12.
Dey, A.; Aishwaryasri, J.; Surya, Jai; Jayanthi, M. G.; Kannadaguli, P.
Exploring Social Media Trends - A Kannada Dataset Analysis Proceedings
Institute of Electrical and Electronics Engineers Inc., 2023, ISBN: 979-835031341-3 (ISBN), (0).
@proceedings{39,
title = {Exploring Social Media Trends - A Kannada Dataset Analysis},
author = {A. Dey and J. Aishwaryasri and Jai Surya and M. G. Jayanthi and P. Kannadaguli},
doi = {10.1109/EASCT59475.2023.10393243},
isbn = {979-835031341-3 (ISBN)},
year = {2023},
date = {2023-01-01},
journal = {2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Platforms for social media are dynamic tools that help ideas spread and develop quickly. This study introduces a novel way of locating popular Kannada-language subjects on social networking sites. This study also involves data preprocessing, feature extraction, and data visualization approaches to reveal underlying patterns and insights using a sizable dataset made up of Kannada text, tweets, hashtags, and news headlines. This method efficiently incorporates both sophisticated Machine Learning models, such as N-grams and word tokenization, and Deep Learning models, including sentence transformers and U-map embeddings. The examination of coherence and silhouette scores is used to validate the models. The main goal of this research is to offer an in-depth analysis of issues that regularly come up in Kannada debates on social media. This enables organizations, researchers, and content producers to make well-informed decisions, comprehend user opinion more thoroughly, and keep up with rapidly changing technological developments. In essence, this study helps provide a thorough understanding of the constantly changing digital ecosystem. © 2023 IEEE.},
note = {0},
keywords = {CSE},
pubstate = {published},
tppubtype = {proceedings}
}
Platforms for social media are dynamic tools that help ideas spread and develop quickly. This study introduces a novel way of locating popular Kannada-language subjects on social networking sites. This study also involves data preprocessing, feature extraction, and data visualization approaches to reveal underlying patterns and insights using a sizable dataset made up of Kannada text, tweets, hashtags, and news headlines. This method efficiently incorporates both sophisticated Machine Learning models, such as N-grams and word tokenization, and Deep Learning models, including sentence transformers and U-map embeddings. The examination of coherence and silhouette scores is used to validate the models. The main goal of this research is to offer an in-depth analysis of issues that regularly come up in Kannada debates on social media. This enables organizations, researchers, and content producers to make well-informed decisions, comprehend user opinion more thoroughly, and keep up with rapidly changing technological developments. In essence, this study helps provide a thorough understanding of the constantly changing digital ecosystem. © 2023 IEEE.
13.
Devi, K. K.; Kumar, J. P.
An efficient data collection tool for crop recommendations model using Robotic Process Automation Proceedings
Institute of Electrical and Electronics Engineers Inc., 2023, ISBN: 979-835033509-5 (ISBN), (4).
@proceedings{42,
title = {An efficient data collection tool for crop recommendations model using Robotic Process Automation},
author = {K. K. Devi and J. P. Kumar},
doi = {10.1109/ICCCNT56998.2023.10308274},
isbn = {979-835033509-5 (ISBN)},
year = {2023},
date = {2023-01-01},
journal = {2023 14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Farmers in rural areas make the crop decisions based on the forecasts and collective knowledge transferred over generation within their community. Farmers who rely on their own prediction for farming and other agricultural activities lead farmers to go through huge loss. A farmer take decision on which crop to be grown is mostly based on intuition and other factors like profit based crop and what their ancestors followed on choosing the crop. Due to changes in soil structure and climate condition farmers tend to make wrong decision. Crop recommending models involve huge collection of data's from various sources like soil data, weather data and historical yield data. It involves multiple stages of data collection, processing and analyzing. In this paper we proposed an efficient data collections tool for crop recommendations model using RPA.RPA (Robotic Process Automation) is a tool used for collecting data from various sources by automatically. By implementing RPA for crop recommendation model ensures that data's are to date and accurate. It also saves time and increase efficiency. In this proposal we presented an efficient predictive model that uses Robotic Process Automation (RPA) by developing software robots to automate the repetitive tasks and processes using UiPath tool. RPA is commonly used in healthcare and finance sectors. We found use cases of RPA in agriculture domain as well. On the basic of existing work this paper focus on RPA in Agriculture to automate data collection, processing and analysis. A Challenging work in Crop Recommendation is collecting metrological data and climate data and making connecting between them. This research paper proposes an efficient predictive modelto choose the best crop to grow by integrating RPA into Crop recommendation model. © 2023 IEEE.},
note = {4},
keywords = {CSE},
pubstate = {published},
tppubtype = {proceedings}
}
Farmers in rural areas make the crop decisions based on the forecasts and collective knowledge transferred over generation within their community. Farmers who rely on their own prediction for farming and other agricultural activities lead farmers to go through huge loss. A farmer take decision on which crop to be grown is mostly based on intuition and other factors like profit based crop and what their ancestors followed on choosing the crop. Due to changes in soil structure and climate condition farmers tend to make wrong decision. Crop recommending models involve huge collection of data's from various sources like soil data, weather data and historical yield data. It involves multiple stages of data collection, processing and analyzing. In this paper we proposed an efficient data collections tool for crop recommendations model using RPA.RPA (Robotic Process Automation) is a tool used for collecting data from various sources by automatically. By implementing RPA for crop recommendation model ensures that data's are to date and accurate. It also saves time and increase efficiency. In this proposal we presented an efficient predictive model that uses Robotic Process Automation (RPA) by developing software robots to automate the repetitive tasks and processes using UiPath tool. RPA is commonly used in healthcare and finance sectors. We found use cases of RPA in agriculture domain as well. On the basic of existing work this paper focus on RPA in Agriculture to automate data collection, processing and analysis. A Challenging work in Crop Recommendation is collecting metrological data and climate data and making connecting between them. This research paper proposes an efficient predictive modelto choose the best crop to grow by integrating RPA into Crop recommendation model. © 2023 IEEE.
14.
Subhashini, R.; Khang, A.
The Role of Internet of Things (IoT) in Smart City Framework Book Chapter
In: pp. 31-56,, CRC Press, 2023, ISBN: 978-100099029-4 (ISBN); 978-103245111-4 (ISBN), (28).
@inbook{43,
title = {The Role of Internet of Things (IoT) in Smart City Framework},
author = {R. Subhashini and A. Khang},
doi = {10.1201/9781003376064-3},
isbn = {978-100099029-4 (ISBN); 978-103245111-4 (ISBN)},
year = {2023},
date = {2023-01-01},
journal = {Smart Cities: IoT Technologies, Big Data Solutions, Cloud Platforms, and Cybersecurity Techniques},
pages = {31-56,},
publisher = {CRC Press},
note = {28},
keywords = {CSE},
pubstate = {published},
tppubtype = {inbook}
}
15.
Rohith, S. V.; Khan, L. A.; Archana, V.; Jayanthi, M. G.; Kannadaguli, P.
Human Age Estimation from Images in Real-Time Application Using Machine Learning and Deep Learning Models Proceedings
Institute of Electrical and Electronics Engineers Inc., 2023, ISBN: 979-835030082-6 (ISBN), (0).
@proceedings{45,
title = {Human Age Estimation from Images in Real-Time Application Using Machine Learning and Deep Learning Models},
author = {S. V. Rohith and L. A. Khan and V. Archana and M. G. Jayanthi and P. Kannadaguli},
doi = {10.1109/NMITCON58196.2023.10275901},
isbn = {979-835030082-6 (ISBN)},
year = {2023},
date = {2023-01-01},
journal = {2023 International Conference on Network, Multimedia and Information Technology, NMITCON 2023},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {The objective of the project is to build an accurate age estimation system applying machine learning (ML) and deep learning (DL) techniques. Due to its numerous applications in areas including biometrics, recognition of faces, age-based promotion, and forensic investigations, accurately calculating human age from photos of faces has attracted a lot of attention. To understand the complex correlations between face features and age, the model will be trained on a broad dataset of facial images with associated age labels. Data gathering and exploratory data analysis are the first steps in the project's phased strategy, which aims to comprehend the dataset's features and spot any biases or outliers. The utilization of feature engineering approaches, such as landmark detection, texture analysis, and geometric features, will be utilized to extract pertinent and discriminative characteristics from the facial photos. The machine learning (ML) and deep learning (DL) algorithms will use these constructed attributes as input. Training multiple machine learning (ML) and deep learning (DL) models are being carried out. Accuracy is being put to use for evaluating the models' performance. To evaluate the advancements in age estimation accuracy, the results had been compared to previous research. The Gradio platform been applied to incorporate the models into a user-friendly interface which permits to enter facial image data and get results for real-time age estimate. © 2023 IEEE.},
note = {0},
keywords = {CSE},
pubstate = {published},
tppubtype = {proceedings}
}
The objective of the project is to build an accurate age estimation system applying machine learning (ML) and deep learning (DL) techniques. Due to its numerous applications in areas including biometrics, recognition of faces, age-based promotion, and forensic investigations, accurately calculating human age from photos of faces has attracted a lot of attention. To understand the complex correlations between face features and age, the model will be trained on a broad dataset of facial images with associated age labels. Data gathering and exploratory data analysis are the first steps in the project's phased strategy, which aims to comprehend the dataset's features and spot any biases or outliers. The utilization of feature engineering approaches, such as landmark detection, texture analysis, and geometric features, will be utilized to extract pertinent and discriminative characteristics from the facial photos. The machine learning (ML) and deep learning (DL) algorithms will use these constructed attributes as input. Training multiple machine learning (ML) and deep learning (DL) models are being carried out. Accuracy is being put to use for evaluating the models' performance. To evaluate the advancements in age estimation accuracy, the results had been compared to previous research. The Gradio platform been applied to incorporate the models into a user-friendly interface which permits to enter facial image data and get results for real-time age estimate. © 2023 IEEE.
16.
Poojari, B. L.; Paul, T.; Singh, V.; Jayanthi, M. G.; Kannadaguli, P.
Indian Driving Scene Description Generator Using Deep Learning Proceedings
Institute of Electrical and Electronics Engineers Inc., 2023, ISBN: 979-835030816-7 (ISBN), (0).
@proceedings{49,
title = {Indian Driving Scene Description Generator Using Deep Learning},
author = {B. L. Poojari and T. Paul and V. Singh and M. G. Jayanthi and P. Kannadaguli},
doi = {10.1109/GCITC60406.2023.10426481},
isbn = {979-835030816-7 (ISBN)},
year = {2023},
date = {2023-01-01},
journal = {2023 Global Conference on Information Technologies and Communications, GCITC 2023},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Driving scene description generation plays a crucial role in various applications, including driver assistance systems, traffic monitoring and autonomous driving. This study proposes a comprehensive approach for driving scene description generation using deep learning (DL) techniques. The methodology involves the collection and preprocessing of a large-scale driving scene dataset, which consists of diverse driving scenarios captured from dashcam videos. The dataset is carefully labelled for different scene categories, such as highways, urban areas, night scenes, and rural roads. Frames from video datasets are collected and are captioned for DL-Model for various scene. In addition, DL-based approaches are employed to leverage the power of convolutional neural networks (CNNs) for scene detection. The CNN architecture, such as VGGNet-16 is evaluated to extract high-level features and enable accurate scene captioning from recurrent neural network (RNN) architectures such as LSTM and GRU for caption generation. The evaluation of the proposed DL models is done using BLEU score. The scores depict the level of effectiveness of the approach in accurate generation of captions for driving scenes, achieving high performance across various scene categories. The system can be deployed on embedded platforms or integrated into existing driver assistance systems to enhance situational awareness and improve decision-making processes. © 2023 IEEE.},
note = {0},
keywords = {CSE},
pubstate = {published},
tppubtype = {proceedings}
}
Driving scene description generation plays a crucial role in various applications, including driver assistance systems, traffic monitoring and autonomous driving. This study proposes a comprehensive approach for driving scene description generation using deep learning (DL) techniques. The methodology involves the collection and preprocessing of a large-scale driving scene dataset, which consists of diverse driving scenarios captured from dashcam videos. The dataset is carefully labelled for different scene categories, such as highways, urban areas, night scenes, and rural roads. Frames from video datasets are collected and are captioned for DL-Model for various scene. In addition, DL-based approaches are employed to leverage the power of convolutional neural networks (CNNs) for scene detection. The CNN architecture, such as VGGNet-16 is evaluated to extract high-level features and enable accurate scene captioning from recurrent neural network (RNN) architectures such as LSTM and GRU for caption generation. The evaluation of the proposed DL models is done using BLEU score. The scores depict the level of effectiveness of the approach in accurate generation of captions for driving scenes, achieving high performance across various scene categories. The system can be deployed on embedded platforms or integrated into existing driver assistance systems to enhance situational awareness and improve decision-making processes. © 2023 IEEE.