Dr. Umakant P. Kulkarni

Scopus Publications

Janus: A Dual-Mask Attention Transformer for Log-based Anomaly Detection in Cellular Networks
Umakant Kulkarni, Sonia Fahmy
Proceedings of the ACM on Measurement and Analysis of Computing Systems, 2026
Modern cellular networks, such as 5G, generate complex operational logs that challenge traditional anomaly detection techniques. Existing deep learning approaches, including standard transformer models, treat logs as monolithic text streams and lack the specialization to reason about procedural correctness and semantic integrity, a key requirement for telecommunications software. We tackle this problem in our system Janus, a log-based anomaly detection system featuring a novel Single-Pass Dual-Mask (SPDM) attention mechanism. Janus introduces a domain-specific inductive bias by partitioning attention heads into two groups. Global heads learn the valid temporal grammar of 5G procedures using a causal mask, and local heads perform fine-grained audits on the consistency of critical data fields using a tag-based semantic mask. A multi-stage curriculum learning framework progressively adapts Janus from domain pre-training to discriminative fine-tuning and learns to detect complex, real-world software failures. Experimental evaluation with several 5G log datasets demonstrates that Janus consistently outperforms prior systems, achieving on average a 3× performance improvement over a DNN-based baseline and an 80% gain over a transformer-based system.
RUN: A Case for Cross-Layer Networked Virtual Reality
Yufeng Chen, Umakant Kulkarni, Voicu Popescu, Sonia Fahmy
Mm 2025 Proceedings of the 33rd ACM International Conference on Multimedia Co Located with mm 2025, 2025
Immersive virtual reality (VR) experiences require transmission and rendering of large-scale 3D content, often represented as point clouds or polygon meshes. Unfortunately, existing networked VR systems often fail to fully exploit the flexibility of VR data representations. To address this problem, we propose a cross-layer design that elevates a network data unit to a usable rendering unit for VR applications. Our aim is to bridge the gap between networks and applications in order to enhance visual quality, especially over constrained and variable networks. Our approach, Rendering Unit that is Network-aware (RUN), with two variants, RUN-Packet and RUN-Hybrid, includes mechanisms to effectively utilize network data units when encoding, transmitting, decoding, and rendering. Specifically, we develop additive detail refinement mechanisms and address streaming challenges such as head-of-line (HoL) blocking. We prototype our system in Unity 3D and evaluate it using synthetic network environments and real network traces. Our results with both static and dynamic point clouds demonstrate that RUN significantly reduces stalls and delivers smoother frame updates, enhancing visual quality.
Auto-metric Graph Neural Network for Attack Detection on IoT-based Smart Environment and Secure Data Transmission using Advanced Wild Horse Standard Encryption Method
Ranganath Yadawad, , Umakant P. Kulkarni, Jafar A. Alzubi
International Journal of Computer Network and Information Security, 2024
Smart cities (SCs) are being constructed with the huge placement of the Internet of Things (IoT). Real-time enhancements to life quality based on comfort and efficiency. The key concerns in most SCs that immediately impact network performance are security and privacy. Numerous approaches are proposed for secure data transmission, but the current methods do not provide high accuracy and it provide high computational time. To resolve these problems, an Auto-metric Graph Neural Network for Attack Detection and Secure Data Transmission using Optimized Enhanced Identity-Based Encryption in IoT (AGNN-AWHSE-ST-IoT) is proposed. Primarily, the input data is taken from the NSL-KDD dataset. The input data is gathered with the aid of NSL-KDD is pre-processed using three steps, crisp data conversion, splitting, and normalization. Then the Pre-processed input is fed into the Colour Harmony Algorithm (CHA) based feature selection to select the important features. After feature selection, the preferred features are given to the AGNN classifier. After classifying, the data is given to Enhanced Identity-Based Encryption (EIBE), and it is optimized using Wild Horse Optimizer (WHO) for transmitting the data more safely. The outcomes of the normal data are displayed using the LCD monitor. The AGNN-AWHSE-ST-IoT method is implemented in PYTHON. The AGNN-AWHSE-ST-IoT method attains 8.888%, 13.953%, 19.512% higher accuracy, 2.105%, 6.593%, 8.988% higher cumulative accuracy, 54.285%, 54.285%, 52.941% lower encryption time, 8.2%, 3.3%, 6.9% lower decryption time, 11.627%, 10.344%, 6.666% higher security level and 60.869%, 70% and 64% lower computational time than the existing approaches such as SBAS-ST-IoT, BDN-GWMNN-ST-IoT and DNN-LSTM-ST-IoT respectively.
Securing the Cloud-Native 5G Control Plane
Umakant Kulkarni, Sonia Fahmy
Proceedings IEEE Military Communications Conference MILCOM, 2024
The shift to cloud-native architectures in the 5G control plane introduces significant challenges in securing complex network functions deployed as microservices. Traditional security mechanisms, such as service mesh architectures and kernel-level solutions, often suffer from protocol limitations, high overhead, or incomplete inter-service encryption. Therefore, we present Zero Trust X Security Enforcement Microservice (ZTX-SEM), a protocol-agnostic zero-trust security solution designed specifically for cloud-native deployments. We propose a lightweight packet interception mechanism that operates across all protocols, a proactive authentication strategy that reduces latency and ensures continuous readiness, and an optimized secret key lookup that accelerates encrypted communication processing. Our experiments on a Kubernetes-deployed 5G control plane (core) demonstrate that ZTX-SEM outperforms existing solutions such as Istio, achieving 75% and 28% reductions in resource utilization and session setup times, respectively.
RPL-OFs analysis and dynamic of selection for QoS optimisation of RPL protocol
Sharwari S. Solapure, Harish H. Kenchannavar, Umakant P. Kulkarni
International Journal of Wireless and Mobile Computing, 2024
Quality-of-Service (QoS) requirements differ for various IoT applications such as for smart health, reliability is the need, for industry, delay is essential, etc. The Routing-Protocol-for-Low-Power-Lossy-Network (RPL) with Objective Function (OF) is used for routing in IoT-applications. Default RPL-OF is deficient to fulfil the QoS requirements of different IoT applications. Hence, several OF designs were proposed as per the QoS need in the earlier research. The work presented in this paper is the extension of previous research work. The analysis of these OF designs is carried out with the parameters such as number of nodes, simulation-time, data-rate, Media Access Control (MAC) protocols, communications ranges and different topologies. This analysis resulted in a data-set which addresses most of the QoS-requirements and is used to optimise the RPL protocol QoS performance. Decision tree algorithm is used to predict a suitable RPL-OF design. The accuracy achieved using Gini and Entropy method of decision tree is 87.14%, 88.57%, respectively. Thus, the contribution of this research is to prepare the data-set using comprehensive analysis and use the same for predicting suitable RPL-OF design according to QoS-requirements of IoT applications. The proposed methodology is useful in IoT-applications where dynamic-OF selection as per QoS-requirements is needed.
Understanding the Impact of Wi-Fi Configuration on Volumetric Video Streaming Applications
Umakant Kulkarni, Khaled Diab, Shivang Aggarwal, Lianjie Cao, Faraz Ahmed, Puneet Sharma, Sonia Fahmy
Proceedings of the 2023 Workshop on Emerging Multimedia Systems EMS 2023, 2023
Emerging multimedia applications often use a wireless LAN (Wi-Fi) infrastructure to stream content. These Wi-Fi deployments vary vastly in terms of their system configurations. In this paper, we take a step toward characterizing the Quality of Experience (QoE) of volumetric video streaming over an enterprise-grade Wi-Fi network to: (i) understand the impact of Wi-Fi control parameters on user QoE, (ii) analyze the relation between Quality of Service (QoS) metrics of Wi-Fi networks and application QoE, and (iii) compare the QoE of volumetric video streaming to traditional 2D video applications. We find that Wi-Fi configuration parameters such as channel width, radio interface, access category, and priority queues are important for optimizing Wi-Fi networks for streaming immersive videos.
Model view controller (MVC) architecture and client-to-client file transfer protocol with binarized spiking neural network for building a smart home appliances control in IoT
Ranganath Yadawad, Umakant P. Kulkarni
International Journal of Information Technology Singapore, 2023
Retraction Note: Research outlook and state-of-the-art methods in context awareness data modeling and retrieval(Evolutionary Intelligence, (2022), 15, (1025–1036), 10.1007/s12065-019-00274-x)
S. G. Gollagi, M. M. Math, U. P. Kulkarni
Evolutionary Intelligence, 2023
Toward QoE-based Routing Path Selection
Umakant Kulkarni, Yufeng Chen, Patrick Melampy, Sonia Fahmy
IEEE International Conference on High Performance Switching and Routing Hpsr, 2023
The increasing popularity of video streaming and conferencing services have altered the nature of Internet traffic. In this paper, we take a first step toward quantifying the impact of this changing nature of traffic on the Quality of Experience (QoE) of popular video streaming and conferencing applications. We first analyze the traffic characteristics of these applications and of backbone links, and show how simple multipath routing may adversely impact application QoE. To mitigate this problem, we propose a new routing path selection approach, inspired by the TCP timeout computation algorithm, that uses both the average and variation of path load. Preliminary results show that this approach improves application QoE by on average 14% and packet latency by 11% for video streaming and conferencing applications, respectively.1
Facial Emotion Recognition using Three-Layer ConvNet with Diversity in Data and Minimum Epochs
International Journal of Intelligent Systems and Applications in Engineering, 2022
Evaluation and Analysis of Goodness of Fit for Water Quality Parameters Using Linear Regression Through the Internet-of-Things-Based Water Quality Monitoring System
Harish H. Kenchannavar, Prasad M. Pujar, Raviraj M. Kulkarni, Umakant P. Kulkarni
IEEE Internet of Things Journal, 2022
Research outlook and state-of-the-art methods in context awareness data modeling and retrieval
S. G. Gollagi, M. M. Math, U. P. Kulkarni
Evolutionary Intelligence, 2022
An Effective Way of Implementing Experiential Learning for Laboratory Courses – A Case Study
Indira R. Umarji, Vidyagouri Kulkarni, Umakant P. Kulkarni
Journal of Engineering Education Transformations, 2022
Analysis of Various RPL Protocol Objective Functions for Quality of Service Parameters
Sharwari Solapure, Harish Kenchannavar, Umakant P. Kulkarni
2022 IEEE International Conference on Blockchain and Distributed Systems Security Icbds 2022, 2022
Towards A Low-Cost Stateless 5G Core
Umakant Kulkarni, Amit Sheoran, Sonia Fahmy
IEEE Workshop on Local and Metropolitan Area Networks, 2022
A framework for a curriculum to ensure minimum standard for flexible, experiential and multi-disciplinary learning towards achieving NEP-2020 goals
Journal of Engineering Education Transformations, 2022
The Cost of Stateless Network Functions in 5G
Umakant Kulkarni, Amit Sheoran, Sonia Fahmy
Ancs 2021 Proceedings of the 2021 Symposium on Architectures for Networking and Communications Systems, 2021
A Survey on On-Board Diagnostic in Vehicles
Deepa Saibannavar, Mallikarjun M. Math, Umakant Kulkarni
Eai Springer Innovations in Communication and Computing, 2021
Self-organising map-based dynamic decision-making algorithm for heterogeneous wireless sensor network
Umesh M. Kulkarni, Harish H. Kenchannavar, Umakant P. Kulkarni
International Journal of Parallel Emergent and Distributed Systems, 2021
A Comprehensive Survey of Fully Homomorphic Encryption from Its Theory to Applications
Rashmi Salavi, M. M. Math, U. P. Kulkarni
Cyber Security and Digital Forensics, 2021
Statistical Analysis of Stress Levels in Students Pursuing Professional Courses
Harish H. Kenchannavar, Shrivatsa D. Perur, U. P. Kulkarni, Rajeshwari Hegde
Smart Innovation Systems and Technologies, 2021
Novel Information Repository for Smart Environment
Ranganath Yadawad, Umakant P Kulkarni
2020 IEEE International Conference for Innovation in Technology Inocon 2020, 2020
Open assessment methodology-based decision support system in blended learning environments
G.M. Shivanagowda, R.H. Goudar, Umakanth P. Kulkarni
International Journal of Knowledge and Learning, 2020
Real-time water quality monitoring through Internet of Things and ANOVA-based analysis: a case study on river Krishna
Prasad M. Pujar, Harish H. Kenchannavar, Raviraj M. Kulkarni, Umakant P. Kulkarni
Applied Water Science, 2020
Estimating distance threshold for greedy subspace clustering
Bhagyashri Abhay Kelkar, Sunil F. Rodd, Umakant P. Kulkarni
Expert Systems with Applications, 2019
Water quality assessment and monitoring for river malaprabha using the internet of things(IoT) system
Prasad M. Pujar, Harish H. Kenchannavar, Umakant P. Kulkarni
International Journal of Recent Technology and Engineering, 2019
Accuracy prediction for distributed decision tree using machine learning approach
Siddalingeshwar Patil, Umakant Kulkarni
Proceedings of the International Conference on Trends in Electronics and Informatics Icoei 2019, 2019
Self-configurable deployment strategy for wireless sensor network
International Journal of Recent Technology and Engineering, 2019
A Novel Parameter-Light Subspace Clustering Technique Based on Single Linkage Method
Bhagyashri A. Kelkar, Sunil F. Rodd, Umakant P. Kulkarni
Journal of Information and Knowledge Management, 2019
Self adaptable deployment for heterogeneous Wireless Sensor Network
Umesh M. Kulkarni, Harish H., Umakant P.
International Journal of Advanced Computer Science and Applications, 2019
A Survey of Various Cryptographic Techniques: From Traditional Cryptography to Fully Homomorphic Encryption
Rashmi R. Salavi, Mallikarjun M. Math, U. P. Kulkarni
Lecture Notes in Networks and Systems, 2019
Classification of brain hemorrhages in MRI using naïve bayes-probabilistic kernel approach
Nita Kakhandaki, Shrinivas B Kulkarni, Ramesh K., Umakant P Kulkarni
Journal of Cases on Information Technology, 2019
Policy-level reforms for outcome based engineering education in India
U.P. Kulkarni, S.B. Kulkarni, K.C. Shindhe, A.N. Joshi
Proceedings 5th IEEE International Conference on Moocs Innovation and Technology in Education Mite 2017, 2018
A case study on curiosity point based teaching and learning– a step towards industry readiness
Journal of Engineering Education Transformations, 2018
Recognition of traffic sign based on support vector machine and creation of the Indian traffic sign recognition benchmark
Vidyagouri B. Hemadri, Umakant P. Kulkarni
Communications in Computer and Information Science, 2018
Neural deployment algorithm for WSN: A concept
Umesh M. Kulkarni, Harish H. Kenchannavar, Umakant P. Kulkarni
Advances in Intelligent Systems and Computing, 2018
CRETAL: A personalized learning environment in conventional setup
G. M. Shivanagowda, R. H. Goudar, U. P. Kulkarni
ACM International Conference Proceeding Series, 2017
A case study on an unrealized truth of an outcome based education and corrective strategies
Proceedings 2016 IEEE 4th International Conference on Moocs Innovation and Technology in Education Mite 2016, 2017
Effect of energy variation in WSN for static and Dynamic deployment
Umesh M. Kulkarni, Harish H. Kenchannavar, Umakant P. Kulkarni
Proceedings of the 2016 2nd International Conference on Applied and Theoretical Computing and Communication Technology Icatcct 2016, 2017
Wireless Sensor Network based Water Monitoring Systems: A survey
Prasad. M. Pujar, Harish. H. Kenchannavar, U. P. Kulkarni
Proceedings of the 2016 2nd International Conference on Applied and Theoretical Computing and Communication Technology Icatcct 2016, 2017
Optimization techniques to improve lifetime of wireless sensor networks: A review
Harish H Kenchannavar, Sandeep Beedakar, Umakant P Kulkarni
International Conference on Energy Systems and Applications Icesa 2015, 2016
Know-How: a design pattern for generic log adapter
M. M. Math, S. F. Rodd, Harish Kenchannavar, S. B. Kulkarni, U. P. Kulkarni, A. R. Yardi
Evolving Systems, 2015
Adaptive self-tuning techniques for performance tuning of database systems: a fuzzy-based approach with tuning moderation
S. F. Rodd, Umakant P. Kulkarni
Soft Computing, 2015
Analysis of new data sources in modern teaching and learning processes in the perspective of personalized recommendation
G. M. Shivanagowda, R. H. Goudar, U. P. Kulkarni
Smart Innovation Systems and Technologies, 2015
Localization of wireless sensor networks using leader based CDL in the wild
International Journal of Applied Engineering Research, 2015
GLCM-Based Multiclass Iris Recognition Using FKNN and KNN
S. B. Kulkarni, Raghavendrarao B. Kulkarni, U. P. Kulkarni, Ravindra S. Hegadi
International Journal of Image and Graphics, 2014
Energy-efficient cluster-based aggregation protocol for heterogeneous wireless sensor networks
Prakashgoud R. Patil, Umakant P. Kulkarni
Advances in Intelligent Systems and Computing, 2014
SVM based data redundancy elimination for data aggregation in Wireless Sensor Networks
Prakashgoud Patil, Umakant Kulkarni
Proceedings of the 2013 International Conference on Advances in Computing Communications and Informatics Icacci 2013, 2013
Innovative workflow for accreditation process to ensure quality engineering education in India
U.P. Kulkarni, K.C. Shindhe
Proceedings of 2013 IEEE International Conference on Teaching Assessment and Learning for Engineering Tale 2013, 2013
Iris data encryption based on Aztec Symbology
Shrinivasrao B. Kulkarni, Ravindra S. Hegadi, Umakant P. Kulkarni
Evolving Systems, 2013
Adaptive neuro-fuzzy technique for performance tuning of database management systems
S. F. Rodd, U. P. Kulkarni, A. R. Yardi
Evolving Systems, 2013
Detection of drowsiness using fusion of yawning and eyelid movements
Vidyagouri B. Hemadri, Umakant P. Kulkarni
Communications in Computer and Information Science, 2013
Adaptive self-tuning techniques for performance tuning of database systems: A Fuzzy-based approach
S. F. Rodd, U. P. Kulkarni
Proceedings 2nd International Conference on Advanced Computing Networking and Security Adcons 2013, 2013
ROI based iris segmentation and block reduction based pixel match for improved biometric applications
Shrinivas Rao B. Kulkarni, Ravindra S. Hegadi, Umakant P. Kulkarni
Communications in Computer and Information Science, 2013
Context-aware information processing in visual sensor network
H. H. Kenchannavar, Shridhar G. Domanal, Umakant P. Kulkarni
Communications in Computer and Information Science, 2013
Design and implementation of user context aware recommendation engine for mobile using Bayesian network, fuzzy logic and rule base
G.S. Thyagaraju, U.P. Kulkarni
International Journal of Pervasive Computing and Communications, 2012
Optimized overlapping based energy-aware node collaboration in visual sensor networks
Harish H. Kenchannavar, Umakant P. Kulkarni
Acwr 2011 Proceedings of the International Conference on Wireless Technologies for Humanitarian Relief, 2011
Wireless sensor network for precision agriculture
Prakashgoud Patil, Vidya H., Shreedevi Patil, Umakant Kulkarni
Proceedings 2011 International Conference on Computational Intelligence and Communication Systems Cicn 2011, 2011
Improvement to Libor Masek algorithm of template matching method for iris recognition
S. B. Kulkarni, R. S. Hegadi, U. P. Kulkarni
International Conference and Workshop on Emerging Trends in Technology 2011 Icwet 2011 Conference Proceedings, 2011
Modeling user context for Interactive Context Aware TV
G S Thyagaraju, U. P. Kulkarni
2010 IEEE International Conference on Computational Intelligence and Computing Research Iccic 2010, 2010
Interactive democratic group preference algorithm for interactive context aware TV
G S Thyagaraju, Umakanth P Kulkarni
2010 IEEE International Conference on Computational Intelligence and Computing Research Iccic 2010, 2010
Effect of data aggregation on wireless sensor network performance
Prakashgoud Patil, Nandini Patil, N. H. Ayachit, Umakant Kulkarni
Proceedings of the 2nd International Conference on Trendz in Information Sciences and Computing Tisc 2010, 2010
Modeling of coverage preserving algorithm using object oriented methodology with UML
H. Kenchannavar, G. S. Patkar, U. P. Kulakarni
Icwet 2010 International Conference and Workshop on Emerging Trends in Technology 2010 Conference Proceedings, 2010
Efficiency of FEC coding in IP networks
H. H. Kenchannavar, S. Thomas, U. P. Kulkarni
Icwet 2010 International Conference and Workshop on Emerging Trends in Technology 2010 Conference Proceedings, 2010
Conflict resolving algorithms to resolve conflict in multi-user context-aware environments
G. S. Thyagaraju, M. M. Math, Umakant P. Kulkarni, A. R. Yardi
2009 IEEE International Advance Computing Conference Iacc 2009, 2009
Enhancing mobile agent applications with security and fault tolerant capabilities
R.N Sreedevi, U.N Geeta, U.P. Kulkarni, A.R. Yardi
2009 IEEE International Advance Computing Conference Iacc 2009, 2009
Conflict resolution in multiuser context-aware environments
G. S. Thyagaraju, S. M. Joshi, Umakant P. Kulkarni, S. K. NarasimhaMurthy. A. R. Yardi
2008 International Conference on Computational Intelligence for Modelling Control and Automation Cimca 2008, 2008
Mobile agent based distributed data mining
K. Indira, S. Sethu Selvi
Proceedings International Conference on Computational Intelligence and Multimedia Applications Iccima 2007, 2008
Query language interface for ubiquitous objects
Fouzul Azim Shaikh, Zaheeruddin, M. S. Jameel Asghar, Gajendra Singh
Proceedings International Conference on Computational Intelligence and Multimedia Applications Iccima 2007, 2008
Software agents based home automation an intelligent electrical billing and maintenance system
R.G. Yadawad, U.P. Kulkarni, S.M. Joshi, J.V. Vadavi, A.R. Yardi
IEEE International Conference on Industrial Informatics Indin, 2007
Exploring the capabilities of mobile agents in distributed data mining
U.P. Kulkarni, K.K. Tangod, S. R. Mangalwede, A.R. Yardi
Proceedings of the International Database Engineering and Applications Symposium Ideas, 2006
Ubiquitous object categorization and identity
U.P. Kulkarni, J.V. Vadavi, S.M. Joshi, K. Chandra Sekaran, A.R. Yardi
Proceedings 2006 14th International Conference on Advanced Computing and Communications Adcom 2006, 2006
Distributed multi level security token based authentication for ubiquitous objects -DMSA
U. Kulkarni, J.V. Vadavi, S.M. Joshi, K.C. Sekaran, A.R. Yardi
Isahuc 06 Proceedings of 2006 International Symposium on Ad Hoc and Ubiquitous Computing, 2006
Mobile and ubiquitous objects
A.D. Joseph, A. Diaz, P. Merino, F.J. Rivas, U.P. Kulkarni, J.V. Vadavi, G.S. Thyagaraju, S.M. Joshi, A.R. Yardi
IEEE Pervasive Computing, 2006
Ubiquitous object categorization and identity
U.P. Kulkarni, J.V. Vadavi, S.M. Joshi, A.R. Yardi
Cimca 2006 International Conference on Computational Intelligence for Modelling Control and Automation Jointly with Iawtic 2006 International Conference on Intelligent Agents Web Technologies, 2006
Agent tracking: A reliable agent forwarding mechanism
Proceedings International Conference on Computational Intelligence for Modelling Control and Automation Cimca 2005 and International Conference on Intelligent Agents Web Technologies and Internet, 2005

Dr. Umakant P. Kulkarni

EDUCATION

RESEARCH INTERESTS

Scopus Publications

RECENT SCHOLAR PUBLICATIONS

MOST CITED SCHOLAR PUBLICATIONS