An Ensemble Framework for Effective Detection and Classification of Cyber Attacks Using Machine Learning
Dr M Naveen Kumar, Dr M Naveen Kumar, Krishna Siva Prasad Mudigonda
Source Title: AI Solutions for Detecting Cyber- Attacks in Information Systems,
A Comparative Study of 2D and 3D Convolutional Neural Networks for Melanoma Classification
Dr Mudassir Rafi, Dr M Naveen Kumar, Ms Thireesha Suryadevara, Ms Thireesha Suryadevara; Mudassir Rafi; Naveenkumar Mahamkali; Rushitha Nalamothu
Source Title: Intelligent Computing and Emerging Communication Technologies (ICEC), International Conference,
View abstract ⏷
Skin Melanoma is a lethal type of cancer. The early diagnosis of which is crucial to improve the survival rate of the patients. Convolution neural networks are at the heart of the deep learning algorithms. In the present work authors have experimentally compared 2D and 3D Convolution Neural Network (CNN) models to identify the melanoma. We have employed three different types of datasets namely PH2, ISIC archive, and ISIC skin cancer datasets. We applied the two models on each of the datasets to determine their accuracy, precision, recall, f1 score and ROC curves. The experimental results provide the insights about the advantages and limitations of using 2D and 3D CNN models for the identification of skin melanoma. The authors have observed that 2D CNN model shows enhanced capabilities to detect skin lesion structures compared to 3D CNN. Moreover, the classification accuracy of the 2D CNN is also found better than 3D CNN.
Comparative Study of ML Techniques for Classification of Crop Pests
Dr M Naveen Kumar, Jaanaki Swaroop Pamidimukkala., Tarun Teja P., Suman Paul K., Divya Sri Kosaraju
Source Title: 2024 4th International Conference on Artificial Intelligence and Signal Processing (AISP),
View abstract ⏷
Crop pests pose a great threat to global food security; thus, the best pest prevention measures must be implemented. By using different machine learning (ML) techniques to perform crop pest classification, this research provides ways to improve the accuracy and speed of identifying pests in agricultural sectors. Conventional methods for identifying pests frequently depend on manual observation, which is tedious, error-prone, and labor-intensive. On the other hand, machine learning (ML) presents an effective way to automate this procedure by using sophisticated techniques to analyze massive data sets and produce precise predictions. The study applies a variety of machine learning approaches, such as Random Forests, K-Nearest Neighbor, and Naive Bayes, to classify agricultural pests according to features that have been extracted from images. For model training and validation, an extensive collection of high-resolution images of different agricultural pests taken in a range of environmental settings is used. Metrics like accuracy are used to determine how well the machine learning models perform. The potential of machine learning approaches to revolutionize pest management in agriculture is evident from the results, which indicate how accurately they can identify and classify agricultural pests. The suggested method improves the overall effectiveness of pest management procedures and drastically reduces the time and effort required to identify pests. Ultimately, this research promotes more resilient and productive farming systems by supporting efforts to develop sustainable and technologically advanced solutions for addressing agricultural difficulties. The results demonstrate the potential of machine learning (ML) as an invaluable tool for farmers, agronomists, and policymakers, encouraging a proactive and data-driven approach to pest management in contemporary agriculture
Synergistic Integration of Skeletal Kinematic Features for Vision-Based Fall Detection
Source Title: Sensors, Quartile: Q1
View abstract ⏷
According to the World Health Organisation, falling is a major health problem with potentially fatal implications. Each year, thousands of people die as a result of falls, with seniors making up 80% of these fatalities. The automatic detection of falls may reduce the severity of the consequences. Our study focuses on developing a vision-based fall detection system. Our work proposes a new feature descriptor that results in a new fall detection framework. The body geometry of the subject is analyzed and patterns that help to distinguish falls from non-fall activities are identified in our proposed method. An AlphaPose network is employed to identify 17 keypoints on the human skeleton. Thirteen keypoints are used in our study, and we compute two additional keypoints. These 15 keypoints are divided into five segments, each of which consists of a group of three non-collinear points. These five segments represent the left hand, right hand, left leg, right leg and craniocaudal section. A novel feature descriptor is generated by extracting the distances from the segmented parts, angles within the segmented parts and the angle of inclination for every segmented part. As a result, we may extract three features from each segment, giving us 15 features per frame that preserve spatial information. To capture temporal dynamics, the extracted spatial features are arranged in the temporal sequence. As a result, the feature descriptor in the proposed approach preserves the spatio-temporal dynamics. Thus, a feature descriptor of size (Formula presented.) is formed where m is the number of frames. To recognize fall patterns, machine learning approaches such as decision trees, random forests, and gradient boost are applied to the feature descriptor. Our system was evaluated on the UPfall dataset, which is a benchmark dataset. It has shown very good performance compared to the state-of-the-art approaches.
Spatio temporal joint distance maps for skeleton-based action recognition using convolutional neural networks
Source Title: International Journal of Image and Graphics,
Deep ensemble network using distance maps and body part features for skeleton based action recognition
Source Title: Pattern Recognition, Quartile: Q1
Learning representations from quadrilateral based geometric features for skeleton-based action recognition using LSTM networks
Source Title: Intelligent Decision Technologies,
Ensemble Spatio-Temporal Distance Net for Skeleton Based Action Recognition.
Source Title: Scalable Comput. Pract.,
Learning Representations from Spatio-Temporal Distance Maps for 3D Action Recognition with Convolutional Neural Networks
Source Title: ADCAIJ: Advances in Distributed Computing and Artificial Intelligence,
