SATISH BASAVARAJ BASAPUR

Scopus Publications

Latent Feature-Based Trust-Aware Model for Service Delegation in Social Internet of Things (SIoT)
Rahul, Venkatesh, Satish B Basapur
Journal of Computer Science, 2026
The integration of social networking concepts into the Internet of Things (IoT) paradigm has given rise to Social IoT (SIoT) ecosystems, aiming to address challenges related to network navigation, service discovery, and service composition. A fundamental issue in SIoT is the careful selection of trustworthy devices that provide services. A service provider can offer multiple and diverse services, and different service providers may offer the same services with varying parameters, making it difficult for service requesters to navigate and identify the best service provider that meets their requirements. Moreover, heterogeneous devices and dynamic social relationships in SIoT networks pose challenges in recommending reliable service providers. This research focuses on identifying and recommending consistent and trustworthy service providers in SIoT. The proposed trust model evaluates interactions, friendships, community similarity, cooperativeness, hidden features of service providers and their services, and predicts uncertainties associated with service providers while assessing their trustworthiness. A set of research experiments is conducted on an available dataset to demonstrate the effectiveness and efficiency of the proposed method. The trust model leverages device interactions, cooperativeness, trustworthy relationships, usage patterns, and uncertainty features of service providers. The Root Mean Square Error (RMSE) and Mean Square Error (MSE) metrics are used to evaluate the accuracy of service provider recommendations in the SIoT environment. The proposed model achieves lower RMSE and MSE values, indicating improved recommendation performance. Additionally, the Normalized Discounted Cumulative Gain (NDCG) metric is employed to assess the quality and efficiency of the recommended service providers. The proposed trust model achieves an NDCG score of approximately 90%, demonstrating its ability to recommend highly trusted service providers effectively.
BacilliFinder: Revolutionizing Tuberculosis Detection with Computer Vision
Nagaraju Y, Venkatesh, Rajani G, Satish Basapur
Indian Journal of Tuberculosis, 2025
PD-UHD features: Phishing Detection Approach using uncooked URL, HTML content and Domain Name Features
M Manjula, Venkatesh, R H Kenchamma, Satish B Basapur
2nd IEEE International Conference on Networks Multimedia and Information Technology Nmitcon 2024, 2024
Phishing is a strategy aimed at stealing users’ sensitive information. Facilitated by carefully designed counterfeit websites, phishing lures online users to visit deceitful web pages to obtain their private and sensitive information. Efficient phishing detection techniques are prevalent due to the growing use of online services.The efficacy of phishing detection depends on lexical and statistical features, local patterns, and contextual information contained in the textual content of the webpage and domain name. This research article proposes a phishing identification approach using uncooked URLs, HTML content, and domain name features (PD-UHD features).The proposed method takes raw URLs, HTML content, and domain names as input. It extracts detailed semantic features at the character level to understand nuances and contextual information at the word level in the raw URLs and HTML content. In the next step, it combines character and word embedding matrices. This research uses a Convolutional Neural Network (CNN) to identify local patterns and semantic dependencies. The proposed method uses a Long Short-Term Memory (LSTM) network to capture the sequential nature of the dependencies in the input.Comprehensive research experiments are conducted on datasets such as MUPD and D1, which have a large number of phishing URLs and lawful URLs. The PD-UHD features approach achieves a phishing detection accuracy of 98.10%, an AUC of about 98.34%, and an FPR of about 1.89%. The PD-UHD features approach outperforms existing baseline strategies in the literature.
SEGC-PP: structure entropy-based graph clustering algorithm for privacy preservation in social internet of things
N.A. Rahul, N.A. Venkatesh, M. Karthik, K.R. Venugopal, Satish B. Basapur
International Journal of Information and Computer Security, 2024
The results of data analysis depend solely on the techniques that extract essential information from the underlying structure of SIoT with huge uncertainty of data embedded in it. Extracting structural essential information and preserving private sensitive information in SIoT is hindering the knowledge discovery process. The methods proposed in this research paper extracts original and essential structural information from a set of IoT objects and a set of social relations in SIoT. From extracted essential structural information, user sensitive and private information are encrypted using a homomorphic encryption algorithm to produce a graph structure in an encrypted state. The degree of information exchange between graph nodes and the node-optimal module partition method are used to divide the encrypted graph structure into several modules. Further, a k-dimensional essential information algorithm is used to cluster nodes in the module. Normalised essential information, residual uncertainty, and clustering similarity algorithms are used to evaluate the correctness and similarity in clustering results. The simulation experiment results demonstrate results of SIoT graph structure clustering in ciphertext state have better efficiency and scalability. In conclusion, theoretical and security analyses demonstrate that the proposed model produces correct clustering results.
BoneSegNet: Enhanced 2D-TransUnet Model for Multiclass Semantic Segmentation of X-Ray Images of Human Hand Bone
Venkatesh, Nagaraju Y, Darshan D, Sahanashree K J, Nagamani P N, Satish B Basapur
Proceedings of Nkcon 2024 3rd Edition of IEEE Nkss S Flagship International Conference Digital Transformation Unleashing the Power of Information, 2024
Multiclass segmentation of hand bones in X-ray images is crucial for various medical applications, including diagnostic assistance and surgical planning. This study presents BoneSegNet, a deep learning-based segmentation model designed to classify hand bones into seven distinct anatomical classes: Distal phalanges, Intermediate phalanges, Proximal phalanges, Metacarpals, Carpals, Ulna, and Radius. Our model, BoneSegNet leverages the strengths of both convolutional neural networks (CNNs) and transformer encoders incorporating the UNet architecture. Our model architecture begins with patch and positional embeddings of the input image, followed by a series of transformer encoder layers to capture long-range dependencies and contextual information. The transformer encoder is equipped with multi-head attention mechanisms and multi-layer perceptron’s (MLPs) with GELU activation and dropout for regularization. Skip connections at specific layers are stored and later utilized in the decoder. The decoding path consists of a series of deconvolution and convolution blocks designed to progressively upscale the feature maps while incorporating skip connections from the encoder. This hierarchical structure ensures detailed spatial information is preserved and enhanced. The final output layer employs a 1x1 convolution with a sigmoid activation function to produce the multiclass segmentation map. The model is trained and evaluated on a dataset of hand X-ray images. It achieves an average accuracy of 99.25%, an average Dice score of 0.81, an average mIoU score of 0.70, sensitivity of 0.79, and specificity of 0.997. These results demonstrate the model’s effectiveness in accurately segmenting and classifying hand bones, making it a valuable tool for medical professionals.
Deep Learning based Automated Wheat Disease Diagnosis System
Priynka R Navale, Venkatesh, Satish B Basapur
2023 International Conference for Advancement in Technology Iconat 2023, 2023
The conditions of the crop reduce the product and are largely to blame for global profitable losses in agrarian assiduity. The conditions in crops need to be under control and effectively cover in order to improve mortality rates. For image bracketing and recognition, researchers have initially utilized hand-drafted features. Currently, researchers have been able to significantly improve the delicateness of object discovery and bracket thanks to developments in Deep Learning. In this project, we classified wheat conditions with colorful judgments using images captured in situ by camera bias using a deep literacy frame. Stem rust, heroic rust, Powderly rust, and normal are the four orders of wheat complaints that are included in our dataset.207 images were included in each order. Our classifier was trained using a convolutional neural network (CNN). CNN’s ability to automatically reward features by recycling the raw images directly is one of its greatest advantages. Our model achieved a delicacy of 94.54 and can be used by farmers to cover wheat crops against forested conditions.
Constraints-Relaxed Functional Dependency based Data Privacy Preservation Model
Engineering Letters, 2023
CRipS: Coconut Ripeness Stage Detection System
Venkatesh, Prajwal K P, Preeti Patil, Priyanka G, Prajwal Poojary, Satish B Basapur
2023 International Conference on Network Multimedia and Information Technology Nmitcon 2023, 2023
Manual Coconut harvesting requires tree-climbing skill, it is hazardous because of the tree's hard shell, height and high occlusions on the tree. Further, it is difficult to determine whether a coconut is ripe or not because of the outside illumination and various background. The development of a coconut ripen stages detection system with the help of deep learning techniques is of great interest to farmers. This research work proposes a deep learning-based instance segmentation technique to identify different coconut ripeness stages. To improve instance segmentation accuracy to identify different coconut ripeness stages, the SOLOv2 model is used. In this research work, collected image dataset consisting of approximately 500 RGB images of different types of coconut fruits in coconut plantations during daylight under natural lighting conditions using a handheld digital single-lens reflex camera. The proposed SOLOv2 model was trained, validated, and tested on 500 manually acquired and augmented images. On the test dataset, the mean average precision (mAP) and Average Precision (at different intersections-over-union (IoU) thresholds), Average Precision (at different intersection-over-union (IoU) thresholds) attained by the model were 0.628, 0.628 and 0.811, respectively, with an average precision and recall for identifying ripeness stages as 0.912 and 0.883, respectively. I data enables the creation of a comprehensive vision system to pinpoint the cutting spot on the coconut cluster and select the harvesting method. The experimental results enable us to develop an automated ripeness detection system to determine the ripeness stages for harvesting and pinpointing the cutting spot on the coconut tree.
S-CPM: Semantic-Similarity Cluster based Privacy Preservation Model with Cell Generalization Principle
Satish B Basapur, B S Shylaja, Venkatesh
Journal of Computer Science, 2022
Corresponding Author: Satish B Basapur Department of Information Science and Engineering, Dr. Ambedkar Institute of Technology, Bengaluru560056, India Email: satish.basapur@gmail.com Abstract: Timely data analysis on a wide variety and a large volume of data unveil valuable information or new insights. The analysis results could be used to innovate new avenues in health care service, business and e-service, etc. However, releasing, storing and reusing sensitive data to third parties results in breaching the data privacy of the individual. To combat privacy breach invasion, privacy-preserving techniques such as suppression, generalization and encryption-based privacy models have been proposed in the literature. The widely used privacy preservation model k-anonymity model prevents record-linkage invasions but fails to satisfy monotonicity property. It has more data distortion and fails to defend semantic-similarity, closeness, nearest-neighborhood data privacy breaches. Moreover, existing approaches are not scalable for the large-scale data set. The paper proposes a semantic similarity two-phase cluster based privacy preservation model. The proposed model considers both numerical and categorical attribute values for data anonymization. Two-phase clustering contains two phases. In the first phase, the t-centroid clustering algorithm is designed and used to partition a set of transaction records of data set D into a set of t-centroids based on the Euclidean distance between transaction records. In the second phase, the neighborhood-aware hierarchical clustering algorithm is designed. It is used to split a set of transaction records within clusters based on neighborhood aware attribute values. Two-phase clustering operations are carried out in parallel and scalable for Big Data sets. The proposed privacy model relies on cell generalization to combat records linkage and semantic-similarity, closeness, nearest-neighborhood privacy breach invasion. All experiments are carried out on two different datasets: Income-Census (KDD) and Bank Credit Card dataset. The experimental results demonstrate that the proposed privacy model can combat privacy breach invasion with cell generalization principles. The proposed privacy model is scalable and time efficient for large-scale data sets.
DistilBERT-CNN-LSTM Model with GloVe for Sentiment Analysis on Football Specific Tweets
Iaeng International Journal of Computer Science, 2022
Attribute Assailability and Sensitive Attribute Frequency based Data Generalization Algorithm for Privacy Preservation
Satish B Basapur, B S Shylaja, Venkatesh
2021 International Conference on Forensics Analytics Big Data Security Fabs 2021, 2021
A Hybrid Cryptographic Model Using AES and RSA for Sensitive Data Privacy Preserving
Satish B Basapur
Webology, 2021

SATISH BASAVARAJ BASAPUR

RESEARCH INTERESTS

Scopus Publications