Jagdish Chandra Patni

Jagdish Chandra Patni

Auto-generated profile, based on publicly available information

Jagdish Chandra Patni

Department of CSE, Alliance School of Advance Computing, Alliance University, Bengaluru, Karnataka, India

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 March 2024 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
SHSami Ahmed Haider
Sami Ahmed Haider
JRJANJHYAM VENKATA NAGA RAMESH
JANJHYAM VENKATA NAGA RAMESH
VRVikas Raina
Vikas Raina
RIRenato R. Maaliw III
Renato R. Maaliw III
MSMukesh Soni
Mukesh Soni
PSPavitar Parkash Singh
Pavitar Parkash Singh
In the context of Secure Artificial Intelligence for 6G Consumer Electronics, accurately predicting vehicle behavior in dynamic traffic scenarios is a significant challenge in intelligent transportation. To avoid sending all raw data to a centralized cloud server, this study presents an artificial intelligence (AI) based distributed machine learning framework (AICEML) that can run on local edge devices. This method protects user privacy while minimizing transmission and processing delays. Accurate predictions are maintained despite the presence of many cars because to AICEML’s use of the model on edge devices, which incorporates edge-enhanced attention and graph convolutional neural network features to swiftly collect and transmit vehicle interaction information. Each edge device can adapt its neural network type and scale based on its computing capabilities, accommodating various application scenarios. Experimental results using the NGGSIM dataset demonstrate AICEML’s superiority, achieving precision, recall, and F1 scores of 0.9391, 0.9557, and 0.9473, respectively. With a 1-second prediction horizon, it maintains 91.21% accuracy and low time complexity even as the number of vehicles increases. This framework holds promise for enhancing intelligent transportation systems in the 6G era while prioritizing security and efficiency.

1 April 2019
Verified
Conference Paper
Closed access
JPJagdish Chandra Patni
Jagdish Chandra Patni
HSHitesh Kumar Sharma
Hitesh Kumar Sharma
The forecast of air quality is getting to be fundamental for limiting the ecological awkward nature advance viably addresses the air contamination. Air contamination includes physical and substance process running over a wide size of time and space. Keeping in mind the end goal to demonstrate the Air quality prescient frameworks, broad information, for example, emanations from different sources (stationary and versatile), impact of structures and different obstructions, meteorology of the territory, data about disturbance profile, warm transition, past estimations of the poisons and so forth is required. It is basically exceptionally hard to gather the previously mentioned information (with the exception of toxin focuses), henceforth fleeting models are helpful in such circumstances. They can be utilized effectively to estimate reason in light of the fact that authentic arrangement of the toxin fixations is promptly accessible from contamination control experts of the nation. Air contamination is a period subordinate wonder which additionally legitimizes the utilization of time arrangement approach for anticipating criteria air toxins. A few systems are accessible to anticipate future poison focuses, including settled box techniques, direct relapse strategies, computational liquid elements (CFD) reenactment, man-made consciousness and so on. Customary procedure like numerical technique requires nitty gritty source data and expends a ton of time and exertion to conjecture and furthermore observed to be powerless especially when used to show nonlinear frameworks. This leaves an extension for another methodology like information driven procedures which are observed to be appropriate to show nonlinear frameworks. Fake Neural Networks (ANN) are as of now been viewed as a financially savvy strategy to accomplish the forecast of air poisons in time arrangement and have turned out to be prevalent since a decade ago. In this association we have contemplated the vast majority of the Soft Computing strategies with an extraordinary spotlight on ANN methods. Commitments from the different creators and productions have been looked into here.

5 July 2024 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
Mohammad ShabazMohammad Shabaz
Mohammad Shabaz
ZMZia Ur Rahman Mohammad
Zia Ur Rahman Mohammad
MAMahmood Alsaadi
Mahmood Alsaadi
MRMohan Raparthi
Mohan Raparthi
RIRenato R. Maaliw III
Renato R. Maaliw III
Haewon ByeonHaewon Byeon
Haewon Byeon
Wireless biosensor devices have significantly enhanced level of convenience associated with patient treatment. Presently, most uncertified aggregate signature methods struggle to withstand key attacks that employ only specific keys. This paper presents an uncertified parallel key-isolated aggregate signature framework that utilizes blockchain technology in wireless medical sensor networks and biosensor devices for consumer electronics to tackle the challenges. The proximity of the signature verification and aggregation processes to end users is increased by integrating a bio-sensor device for consumer electronics into the cutting-edge framework. This action simultaneously enhances the safeguarding of patient confidentiality and mitigates computational burden on primary cloud server. By integrating the advantages of key-isolated and uncertified technologies, the proposed solution circumvents exposure concerns, difficult certificate administration, and key storage. This study demonstrates that the proposed method is resistant to Type I, Type II, and wholly selected key attacks when implemented in a random oracle model. This scheme shows a reduction in calculation overhead of 82.97%, 74.03%, 84.58%, and 86.79% correspondingly when compared to other schemes. Analysis of performance indicates that in comparison to pertinent uncertified signature systems, this solution can reduce communication overhead by a minimum of 25% and computational cost by a minimum of 74.03%.

24 January 2024 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
SHSami Ahmed Haider
Sami Ahmed Haider
ZMZia Ur Rahman Mohammad
Zia Ur Rahman Mohammad
SGSachin Gupta
Sachin Gupta
AHAtaniyazov Jasurbek Hamidovich
Ataniyazov Jasurbek Hamidovich
Arsalan Muhammad SoomarArsalan Muhammad Soomar
Arsalan Muhammad Soomar
VCVenkata Chunduri
Venkata Chunduri
Within the realm of e-commerce networks, it is frequently observed that certain users exhibit behavior patterns that differ substantially from the normative behaviors exhibited by the majority of users. The identification of these atypical individuals and the understanding of their behavioral patterns are of significant practical significance in maintaining order on e-commerce platforms. One such method for accomplishing this objective entails examining the behavioral tendencies of atypical users through the abstraction of e-commerce networks as heterogeneous information networks. These networks are then transformed into a bipartite graph that establishes associations between users and devices. The Self-Supervised Aberrant Detection Model (SAD) has been proposed within this theoretical framework as a means to identify and detect users who exhibit aberrant behavior. The SSADM methodology utilizes a self-supervised learning process that utilizes autoencoders to encode representations of user nodes. The proposed method aims to maximize a combined objective function for backpropagation while utilizing support vector data description to detect abnormalities in the representations of user nodes. In summary, many tests have been conducted utilizing both authentic network datasets and partially synthetic network datasets to demonstrate the efficacy and superiority of the SAD technique, specifically within the domain of an energy-efficient 5G network.

22 April 2025 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
Haewon ByeonHaewon Byeon
Haewon Byeon
MAMahmood Alsaadi
Mahmood Alsaadi
SGSachin Gupta
Sachin Gupta
JPJagdish Chandra Patni
Jagdish Chandra Patni
TATariq Ahamed Ahanger
Tariq Ahamed Ahanger
SBSanthosh Boddupalli
Santhosh Boddupalli
In response to the lack of effective means for detecting and locating malicious exchange nodes in data flow transmission links within the Internet of Things (IoT), this paper proposes a zero-trust management method for data flow between edge nodes based on software defined networking (SDN) communication and control of cyber-physical systems (CPS). To detect and prevent anomalous behaviors like data tampering, forwarding path anomalies, and malicious packet drops through forwarding verification by exchange nodes, SDN-ZTM applies SDN to the data transmission process between IoT edge nodes. This approach applies the SDN architecture to the transmission process of data flows between edge nodes, utilizing a fixed-length header overhead for zero-trust management of data flows, nodes, and paths, thereby enabling lightweight packet forwarding verification and malicious exchange node localization. Simulation studies and theoretical research show that SDN-ZTM offers more extensive security features than similar methods. Additionally, SDN-ZTM is a lightweight, useful solution appropriate for IoT application scenarios since it introduces a fixed-length header and has a smaller performance overhead. Experimental results show that the method introduces less than 10% forwarding delay and less than 8% throughput loss.

28 November 2024 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
AKAjmeera Kiran
Ajmeera Kiran
JRJANJHYAM VENKATA NAGA RAMESH
JANJHYAM VENKATA NAGA RAMESH
AQAadam Quraishi
Aadam Quraishi
JPJagdish Chandra Patni
Jagdish Chandra Patni
IKIsmail Keshta
Ismail Keshta
MSMukesh Soni
Mukesh Soni
With the advancement in Tiny Machine Learning (ML) technologies, their application in enhancing unmanned aerial vehicles (UAVs) for hydraulic engineering surveying and mapping has become increasingly significant. TinyML’s integration offers a leap in processing efficiency and capabilities, particularly in addressing challenges such as UAV search and monitoring due to loss of contact or forced landings. The usage of medical cyber-physical systems in healthcare can revolutionize existing service delivery methods. The study focuses into the spatial grid mapping technique for three-dimensional information, the PTZ camera spatial grid target locking algorithm, and the UAV detection and image correction algorithm. The UAV target is processed using the surveying UAV target tracking method. TinyML techniques are essential for processing and analyzing these photos quickly. Precise UAV identification and tracking are made possible by the combination of image recognition and radar data, which are then processed using TinyML algorithms. This study explores the complexities of algorithms designed specifically for TinyML, such as tracking, UAV detection, grid mapping, and 3D grid space division. Experimental results validate the enhanced capability of this. The results show how well the proposed technique maps and surveys water conservation regions while promptly catching, locking onto, and tracking drones. The algorithm in this study betters than the YOLO, SSD, and RetinaNet algorithms in the recognition and detection of image-oriented surveying and mapping drones.