Browsing by Author "Rudra, B."

Now showing 1 - 20 of 68

A Hybrid Framework for Secure Group Communication Using Quantum-Classical Cryptography and Reinforcement Learning
(Institute of Electrical and Electronics Engineers Inc., 2025) Renisha, P.S.; Rudra, B.
This research work describes a framework for secured and effective way of group interaction incorporating classical cryptography and quantum communication technique. This framework employs a classical cryptographic methods for group logistics like as transmitting of messages and membership management while employing quantum communication strategy for secure key distribution and related authentication. In order to increase the flexibility and data-security of the proposed system further, a supervisor learning based mechanism is incorporated into the framework where reinforcement learning will employed in controlling the interaction of the protocols and the decision-making processes in an active manner. This combination of classical, quantum and supervisor learning strategies gives a solution to the issues of scalability, efficiency, effective and timely actionable response to increasing cyber threats especially in the era of quantum computing. The framework is highly effective and secured for group interaction in distributed network infrastructures. It will be a leading the approach for advanced cryptographic mechanism in the future. Â© 2025 IEEE.
A hybrid model of convo-GAN to detect fake images
(Grenze Scientific Society, 2021) Saha, S.; Rudra, B.
With advancements in the field of Deep Learning, it has become easy to generate face swaps, thereby creating fake images which look extremely realistic, leaving few traces which cannot be detected by bare human eyes. Such images are known as â€˜DeepFakesâ€™ that can be used to create a ruckus and affect the quality of public discourse on sensitive issues, defame an individualâ€™s profile, create political distress, blackmail a person or envision fake cyber terrorists. This paper proposes methods to detect fake images with the help of hybrid models having Convolutional Neural Network with Error Level Analysis, Gated Recurrent Unit neural network, Long Short Term Memory recurrent neural network and Generative Adversarial Network respectively. The 2019 â€˜Real and Fake Face Detectionâ€™ dataset from Kaggle [7] is used to train the models and by experimentation we are able to prove that the combined model of Convolutional Neural Network and Generative Adversarial Network outperforms other models. Â© Grenze Scientific Society, 2021.
A Novel Approach for Asymmetric Quantum Error Correction With Syndrome Measurement
(Institute of Electrical and Electronics Engineers Inc., 2022) Mummadi, M.; Rudra, B.
Most of the quantum error correction methods are symmetric. Symmetric methods are implemented by considering the amplitude of bit flip(X) and phase flip(Z) errors as same. With the quantum experiments, it is observed that the amplitude of Z errors are more compared to X errors. Due to which the need of asymmetric error correction has increased. This paved a path for the development of asymmetric error correction methods. In this paper, we discussed the concept of asymmetric quantum error correction (AQEC) and proposed an efficient approach for AQEC with encoding, syndrome measurement and decoding operations with increased fidelity to 85.89% and reduced circuit depth to 48%. © 2013 IEEE.
A Novel Architecture forÂ Binary Code toÂ Gray Code Converter Using Quantum Cellular Automata
(Springer Science and Business Media Deutschland GmbH, 2022) Mummadi, M.; Rudra, B.
In CMOS, the channel length is sinking day by day which raises a lot of questions about its future. Quantum dot computation is an alternative solution to the CMOS technology, which has the strength to increase the speed of computations and reduce the power while performing those computations as well as it reduces the area when compared to CMOS technology. To perform computations using quantum, we generate arithmetic circuits where code converters play a significant role. In this paper, we are discussing 2-, 3-, and 4-bit binary to gray code converters that are designed with a minimum number of qubits using 0.0251, 0.0382, 0.06 Î¼ m 2 area respectively. Â© 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Advancing Security and Scalability - A Protocol Extension for Dynamic Group Membership Management
(AnaPub Publications, 2025) Renisha, P.S.; Rudra, B.
The integration of Contributory Group Key Agreement (CGKA) for group formation revolutionizes the collaborative process of generating group keys, instilling trust and fostering collaboration among group members. By ensuring that each member actively contributes to the generation of the group key, CGKA distributes the responsibility of key generation across the group, thereby enhancing the security and resilience of the group's cryptographic infrastructure. Concurrently, the utilization of Lattice Diffie-Hellman (LDH) for key generation leverages the mathematical properties of lattices to securely derive shared secret keys. LDH offers a robust and efficient method for generating keys in cryptographic applications, ensuring the confidentiality and integrity of communication channels. Furthermore, the incorporation of blockchain technology for implementing membership changes introduces a decentralized and transparent approach to managing group membership dynamics. By leveraging blockchain's distributed ledger technology and smart contracts, membership changes can be executed securely, transparently, and efficiently. This enhances the integrity and resilience of the group's membership management system, allowing for the secure addition and removal of members from the group while maintaining the integrity of the cryptographic infrastructure. Together, the integration of CGKA, LDH, and blockchain technology presents a comprehensive solution for advancing the security and scalability of dynamic group membership management protocols, offering a robust framework for secure and efficient communication in contemporary environments. Moreover, the proposed integration of CGKA, LDH, and blockchain technology facilitates seamless adaptation to dynamic changes in group membership, ensuring that security and scalability are maintained even as the composition of the group evolves. Through simulations and performance evaluations, the effectiveness of the integrated approach that is implemented in Python Software is demonstrated compared to existing protocols like Elliptic Curve Diffie-Hellman (ECDH), RSA Key Exchange, and Post-Quantum Cryptography (PQC). ©2025 The Authors.
An Effective Approach for Deepfake Video Detection using Binarized Neural Network
(Institute of Electrical and Electronics Engineers Inc., 2025) Praveen, K.; Pandey, A.; Rudra, B.
The rise of DeepFake technologies, especially in audio and video, poses significant threats to information integrity, security, and privacy. Artificially driven Artificial Intelligence (AI) methods and their advancement make it difficult to trace synthetic media through deepfakes that closely approximate real speech, facial expressions, and body movements. Consequently, traditional methods of detecting these are losing the race because they cannot compete with the newly invented methods that are more advanced in comparison. This paper proposes a lightweight and scalable approach to deepfake video detection using Binarized Neural Networks (BNNs). We integrate BNNs with Convolutional Neural Networks (CNNs) and Multi-task Cascaded Convolutional Networks (MTCNN) to boost feature extraction and analysis while making sure that this is done at a computational efficiency, especially to be deployed in resource-constrained systems such as mobile and embedded devices. The binarization of network weights and activations naturally deals with the trade-off regarding detection accuracy and computational cost. Our approach introduces a practical solution for real-time deepfake detection, thus advancing toward more secure and trusted digital environments. Our proposed model has achieved an accuracy of 80%. Â© 2025 IEEE.
An efficient approach for quantum entanglement purification
(World Scientific, 2022) Mummadi, M.; Rudra, B.
Entanglement plays a major role in quantum information process and is a principal resource for various quantum applications like quantum teleportation, quantum key distribution, quantum communication, etc. Strong entangled pairs are required for efficient information process but system impurities during the transportation diminishes the entanglement by reducing the fidelity of the entangled pair. In order to reduce this, purification techniques can be used. In this paper, we propose an efficient entanglement purification method to distill the entanglement using entanglement swapping. The proposed method increases the fidelity of the entanglement and can be a proficient for various applications of quantum computing. © 2022 World Scientific Publishing Company.
An Intelligent Decision Support System for Bid Prediction of Undervalued Football Players
(Institute of Electrical and Electronics Engineers Inc., 2022) Datta, M.; Rudra, B.
The process of selecting football team players will determines a team's performance. An effective team is made up of a successful group of individual talented players. In general, a football team player selection is a decision made by the club based on the best available information. Club managers and scouts travel to different countries to watch matches and hire the best talent that can help their club to perform better. But for the lower leagues, it becomes difficult to hire the same talents because of strict budget. Here we devise a method so that we can leverage the undervalued players to get selected by the clubs. Clearly the benefit will be in two fold. First, the smaller clubs can get better players at an affordable cost. Second, the bigger clubs can get same performance players at a lower price helping them in cost cutting. We employ novelty detection methods to find out the undervalued players from our data and investigate our method by using five machine learning models. For performance evaluation, the five machine learning models used are support vector machine, Random Forest, Decision Tree, Linear Regression and XGBoost. Here XGboost performed best both for 10 fold cross-validation and external testing with a RMSE of 0.0122 and 0.0107 respectively. Â© 2022 IEEE.
An Optimized Question Classification Framework Using Dual-Channel Capsule Generative Adversarial Network and Atomic Orbital Search Algorithm
(Institute of Electrical and Electronics Engineers Inc., 2023) Revanesh, M.; Rudra, B.; Guddeti, R.M.R.
The advancement in education has emphasized the need to evaluate the quality of the examination questions and the cognitive levels of students. Many educational institutions now acknowledge Bloom's taxonomy-based students' cognitive levels evaluating subject-related learning. Therefore, in this paper, a novel optimized Examination Question Classification framework, referred to as QC-DcCapsGAN-AOSA, is proposed by combining the Dual-channel Capsule generative Adversarial Network (DcCapsGAN) with Atomic Orbital Search Algorithm (AOSA) for preprocessing a real-time online dataset of university examination questions, thus identify the key features from the raw data using Term Frequency Inverse Document Frequency (TF-IDF) and finally classifying the examination questions. Atomic Orbital Search Algorithm is used to fine-tune the parameters' weights of the DcCapsGAN, and then uses these weights to categorize questions as Knowledge Level, Comprehension Level, Application Level, Analysis Level, Synthesis Level, and Evaluation Level. Experimental results demonstrate the superiority of the proposed method (QC-DcCapsGAN-AOSA) when compared to the state-of-the-art methods such as QC-LSTM-CNN and QC-BiGRU-CNN with an accuracy improvement of 23.65% and 29.04%, respectively. © 2013 IEEE.
Analysis ofÂ Magnitude ofÂ Threats forÂ V2X Authentication Schemes Under Quantum Powered Adversary
(Springer Science and Business Media Deutschland GmbH, 2023) Sawant, S.V.; Rudra, B.
The Internet has revolutionized the way we communicate. We are now able to connect to anyone across the globe with little or no effort. This revolution has empowered various technological inventions. The Internet has fixed numerous challenges that were difficult to address before. Today, even Vehicular Communication is possible due to the Internet. From providing situational vigilance to taking sound decisions, vehicles have traveled a smart journey. These technological marvels were possible due to the remarkable progress in the computational power of devices. Now, with the world moving towards quantum computing, we stare at future with an ocean of possibilities. Such capabilities in the hands of adversaries can lead to unpleasant consequences. Hence, it is important to determine whether our existing systems are safe against such powerful adversaries. Also, it is equally important to develop techniques that can defend vehicles from adversaries. In this paper, we have listed out various authentication schemes against quantum adversaries and presented our observations. Â© 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Architecture and Deployment Models-SDN Protocols, APIs, and Layers, Applications and Implementations
(Springer Science and Business Media Deutschland GmbH, 2022) Rudra, B.; S, T.
The current Internet infrastructure is not anticipating such a growth of IoT and increasing the network complexity. New network architecture for the management of IoT data flow and also catering to the Quality of Service of different IoT services is required. The existing incompatible solutions are limited to the early adoption of IoT. The standardization bodies, industries, researches were involved in developing standards to support end-to-end connection, interoperation between devices from different vendors and also provide cost-efficient solutions. The Working Groups (WG) at the IETF introduced new solutions that have allowed the connection of low-power wireless networks to the Internet. In spite of the vast exploration of solutions for deploying IoT, the management of IoT networks requires complex routing topologies with a simplified user operation. This gives rise to the need for centralized network control which is facilitated by Software Defined Networking (SDN). SDN was a standard technology for Wireless Sensor Networks (WSNs) already available which is the early version of IoT as the world knows it today. SDN provides a framework to ease the complexity involved in the management of sophisticated networks. We discuss various protocols present in the architecture along with the research challenges for the future. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Atm theft investigation using convolutional neural network
(Springer Science and Business Media Deutschland GmbH info@springer-sbm.com, 2021) Satish, Y.C.; Rudra, B.
Image processing in a surveillance video has been a challenging task in research and development for several years. Crimes in Automated Teller Machine (ATM) is common nowadays, in spite of having a surveillance camera inside an ATM as it is not fully integrated to detect crime/theft. On the other hand, we have many image processing algorithms that can help us to detect the covered faces, a person wearing a helmet and some other abnormal features. This paper proposes an alert system, by extracting various features like face-covering, helmet-wearing inside an ATM system to detect theft/crime that may happen. We cannot judge theft/crime as it may happen at any time but we can alert the authorized persons to monitor the video surveillance. Â© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2021.
Autoencoder-Based Anomaly Detection in ECG Image Time Series Data: A Comparative Evaluation of Three Different Architectures
(Institute of Electrical and Electronics Engineers Inc., 2023) Chouhan, S.; Rudra, B.
Anomaly detection is an essential component of machine learning that renders the outcomes neutral to any category or class. Due to the wide range of anomalies that might exist in time-series data, it plays a crucial role in time-series modelling. This research paper presents an image reconstruction-based approach for anomaly detection in electrocardiogram (ECG) time series data and image data using three different autoencoders, and concludes with a comparison analysis. Anomaly detection is crucial for accurate diagnosis and treatment of heart diseases, and the proposed approach utilizes three types of autoencoders to learn the normal patterns in image data and identify any deviations from these patterns as anomalies. The approach uses a dataset of normal images and is tested on a dataset containing both normal and anomalous images. To reconstruct unseen data like anomalies, models trained only on normal sets will not be able to do so. The results demonstrate that all three types of autoencoders can effectively reconstruct the images, but the Convolutional Autoencoder was able to reconstruct most of the anomaly images correctly, which may not be ideal for anomaly detection. On the other hand, the Deep Autoencoder and Stacked Autoencoder show the reconstruction of the anomalies similar to the normal images, hence, can be very effective for detecting anomalies in ECG image time-series data and similar problems. The proposed approach demonstrates the effectiveness of autoencoder-based anomaly detection for image data and provides a comparative analysis of different types of autoencoders for this task. This can potentially improve the accuracy and efficiency of anomaly detection in various image datasets. Â© 2023 IEEE.
Automated Traffic Light Signal Violation Detection System Using Convolutional Neural Network
(Springer, 2020) Bordia, B.; Nishanth, N.; Patel, S.; Anand Kumar, M.; Rudra, B.
Automated traffic light violation detection system relies on the detection of traffic light color from the video captured with the CCTV camera, detection of the white safety line before the traffic signal and vehicles. Detection of the vehicles crossing traffic signals is generally done with the help of sensors which get triggered when the traffic signal turns red or yellow. Sometimes, these sensors get triggered even when the person crosses the line or some animal crossover or because of some bad weather that gives false results. In this paper, we present a software which will work on image processing and convolutional neural network to detect the traffic signals, vehicles and the white safety line present in front of the traffic signals. We present an efficient way to detect the white safety line in this paper combined with the detection of traffic lights trained on the Bosch dataset and vehicle detection using the TensorFlow object detection SSD model. Â© 2020, Springer Nature Singapore Pte Ltd.
Binarization in DeepFake Audio Detection: A Comparative Study and Performance Analysis
(Institute of Electrical and Electronics Engineers Inc., 2025) Gowhar, S.; Pandey, A.; Rudra, B.
DeepFake audio, generated through advanced AI techniques, poses significant risks such as fraud, misinformation, and identity theft. As the quality of synthetic audio improves, detecting such fakes has become increasingly challenging. Traditional detection methods struggle to keep pace as AI-generated voices replicate speech patterns, tone, and pitch convincingly. While computationally intensive large-scale models can help detect DeepFakes generated by AI, their resource requirements make them impractical for deployment on mobile devices as well as on resource-constrained devices. This paper proposes a lightweight yet effective approach using binarized neural networks (BNNs) and further enhancements using additional dense layers and stacked modeling to overcome these challenges. We conduct a comprehensive performance analysis of the network and compare it with various machine learning and neural network methods to evaluate the tradeoff between detection accuracy and computational efficiency as an effect of binarization and precision loss in feature embeddings. Â© 2025 IEEE.
Blockchain based Framework for Student Identity and Educational Certificate Verification
(Institute of Electrical and Electronics Engineers Inc., 2021) Chowdhary, A.; Agrawal, S.; Rudra, B.
With the rise in digitization of documents stored online, it is important to have a document verification process. It involves customized verification and authentication of a document based on the content of the document. Among all the certificates, the educational certificate is one of the most important certificates, especially for students. Unfortunately, it is very easy to fake documents that are hard to identify nowadays and are often considered original. Blockchain has recently emerged as a potential alternative to manual verification of certificates. It provides a distributed ledger that is verifiable with cryptographic mechanisms. Also, it provides a common platform for easily sharing, storing, and accessing documents. The identity of the students can be verified using government authorized identity proofs. This paper proposes the use of such unique identity number and secret phrase provided by the student to further improve the security of the certificate verification system. The student's identity and document are both verified by matching the hashes already present in the Blockchain. Also, in the proposed method the documents are linked to the student to add another layer of verification. The implementation of this proposed platform can be used to issue, receive and verify the certificates. Â© 2021 IEEE.
Classification of Arecanut X-Ray Images for Quality Assessment Using Adaptive Genetic Algorithm and Deep Learning
(Institute of Electrical and Electronics Engineers Inc., 2023) Naik, P.M.; Rudra, B.
The traditional approach for analyzing the quality of arecanuts is based on their external appearance. However, using machine learning and deep learning techniques, automated classifications were performed. But the true quality can only be analyzed when the internal structure of the arecanut is examined. Therefore, we use the X-ray imaging technique to determine the internal quality of arecanuts. We prepared a novel dataset of arecanut X-ray images and used a YOLOv5 based deep learning architecture for classification. The present study employs an adaptive genetic algorithm based approach for hyperparameter optimization to enhance the mean average precision (mAP) using a light weight model generated using a ghost network and a feature pyramid network (FPN). We have achieved the highest mAP of 97.84% using our method with a lower model size of 15 MB. Our method has excelled in detecting the arecanut compared to cutting-edge object detection algorithms such as YOLOv3, YOLOv4, Detetron, YOLOv6, YOLOv8, and YOLOX. We also acknowledged the performance enhancement using the adaptive genetic algorithm on the Pascal VOC 2007 image dataset. Despite of significant computational requirements for executing genetic algorithms, we proved that genetic algorithms can boost mAP. Additionally, the methodology developed in this investigation produced multiple models with the best mAP featuring optimized hyperparameters. This methodical strategy is helpful for the design of an automatic, non-destructive, integrated X-ray image based classification system. This system has the potential to revolutionize the quality assessment of arecanuts by offering a more efficient evaluation method. © ; 2023 The Authors.
Comparative Study of Machine Learning Algorithms for Fraud Detection in Blockchain
(Institute of Electrical and Electronics Engineers Inc., 2021) Bhowmik, M.; Sai Siri Chandana, T.; Rudra, B.
Fraudulent transactions have a huge impact on the economy and trust of a blockchain network. Consensus algorithms like proof of work or proof of stake can verify the validity of the transaction but not the nature of the users involved in the transactions or those who verify the transactions. This makes a blockchain network still vulnerable to fraudulent activities. One of the ways to eliminate fraud is by using machine learning techniques. Machine learning can be of supervised or unsupervised nature. In this paper, we use various supervised machine learning techniques to check for fraudulent and legitimate transactions. We also provide an extensive comparative study of various supervised machine learning techniques like decision trees, Naive Bayes, logistic regression, multilayer perceptron, and so on for the above task. Â© 2021 IEEE.
Crack Density and Length Detection using Machine Learning
(Avestia Publishing, 2024) Koushik, M.; Hegde, P.; Rudra, B.
This study presents a comprehensive approach for detecting and analyzing microscopic cracks in rock samples using computer vision techniques and machine learning algorithms. The proposed methodology involves image segmentation, crack detection, length, and density prediction, utilizing a combination of image processing techniques and linear regression modeling. Microscopic rock images captured at various temperatures were analyzed to detect and measure cracks accurately. The developed system demonstrated effective crack detection and length measurement capabilities, aided by image segmentation, edge detection, and feature extraction methods. Moreover, the application of linear regression facilitated the prediction of crack parameters, exhibiting a clear relationship between crack characteristics and temperature variations. The findings contribute to a deeper understanding of crack formation mechanisms in rocks under different temperature conditions, offering valuable insights for geological studies and infrastructure integrity assessments. Â© 2024, Avestia Publishing. All rights reserved.
Cyber-Physical Systems: Historical Evolution and Role in Future Autonomous Transportation
(Springer Science and Business Media Deutschland GmbH, 2022) Rudra, B.; Thanmayee, S.
The revolutionary research and experiments in the field of computing and communicating technologies have resulted in a dramatic impact on the applications with societal and economic benefit. With the evolution of the Internet, it is now possible to connect every object or thing in the physical world. These things can communicate and also perform computations. It is now possible for humans to communicate with the physical things around us. This leads us to explore a whole new technology called Cyber Physical System (CPS). CPS combines computation, communication and control technologies in order to integrate the existing networked systems and embedded systems. It has modules to perform accurate data acquisition. These modules are basically distributed devices. Further the acquired data is sent to a layer of information processing as per the service requirements. There are enormous applications of CPS namely: digital medical devices, autonomous vehicles, robotic systems, intelligent highways, aerospace systems, industry automation, building and environment control and physical process control. Among the listed applications, autonomous transportation is evolving through the ongoing research trends. In autonomous transportation systems, there is a high requirement for reliable communication between the communicating entities, accurate data acquisition and processing and high computing capabilities. Thus CPS is a novel engineering system that can suit the requirements of autonomous transportation. In this chapter we discuss the evolution of CPS and its role in future autonomous transportation. We explore the research challenges in the CPS based on autonomous transportation. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.