- EEG and Brain-Computer Interfaces
- Software Testing and Debugging Techniques
- Software Engineering Research
- Software Reliability and Analysis Research
- Biometric Identification and Security
- Functional Brain Connectivity Studies
- User Authentication and Security Systems
- Software System Performance and Reliability
- Cryptography and Data Security
- Advanced Authentication Protocols Security
- Face recognition and analysis
- Recommender Systems and Techniques
- Face and Expression Recognition
- Human-Automation Interaction and Safety
- Emotion and Mood Recognition
- Cloud Data Security Solutions
- Blind Source Separation Techniques
- Artificial Intelligence in Healthcare
- Model-Driven Software Engineering Techniques
- Image Retrieval and Classification Techniques
- Advanced Steganography and Watermarking Techniques
- Advanced Text Analysis Techniques
- Neural dynamics and brain function
- Cloud Computing and Resource Management
- Machine Learning in Healthcare
Indian Institute of Technology Kharagpur
2015-2025
National Remote Sensing Centre
2016-2024
Quality and Reliability (Greece)
2024
Indian Institute of Technology Indore
2012
National Institute of Technology Durgapur
2011
Siemens (Germany)
2010
Motor imagery (MI) signals recorded via electroencephalography (EEG) is the most convenient basis for designing brain-computer interfaces (BCIs). As MI based BCI provides high degree of freedom, it helps motor disabled people to communicate with device by performing sequence tasks. But inter-subject variability, extracting user-specific features and increasing accuracy classifier still a challenging task in BCIs. In this work, we propose an approach overcome above mentioned issues. The...
Power converters are essential in various applications such as aerospace, photovoltaic systems, smart grids, and electric vehicles etc. Component failures these pose significant risks to overall system reliability, especially safety-critical applications. Existing fault classification methods focus mostly on single faults within individual components but overlook the complex interactions of multiple real-world scenarios. This paper addresses challenge identifying classifying power using...
This paper presents a novel approach of generating test cases from UML design diagrams. Our consists transforming sequence diagram into graph called the (SDG) and augmenting SDG nodes with different information necessary to compose vectors. These are mined use case templates, class diagrams data dictionary. The is then traversed generate cases. thus generated suitable for system testing detect interaction scenario faults.
This paper presents a novel approach of generating test cases from UML design diagrams. We consider use case and sequence diagram in our generation scheme. Our consists transforming into graph called (UDG) the (SDG) then integrating UDG SDG to form system testing (STG). The STG is traversed generate cases. thus generated are suitable for detect operational, dependency, interaction scenario faults.
Abstract This paper presents an approach to generate test cases from UML 2.0 sequence diagrams and subsequently prioritize those using model information encapsulated in the diagrams. The generated according proposed satisfy scenario coverage criterion are suitable for system‐level testing. For prioritizing cases, three different prioritization metrics proposed. values of these can be analytically computed only. also data a concept called rule‐based matrix . used control number without...
Hadoop framework has been evolved to manage big data in cloud. distributed file system and MapReduce, the vital components of this framework, provide scalable fault-tolerant storage processing services at a lower cost. However, does not any robust authentication mechanism for principals' authentication. In fact, existing state-of-the-art protocols are vulnerable various security threats, such as man-in-the-middle, replay, password guessing, stolen-verifier, privileged-insider, identity...
Abstract This study presents a novel approach for generating unique identities from multi‐modal biometric data using ensemble feature descriptors extracted the consistent regions of fingerprint and iris images. The method employs prominent selection discriminant vector generation to enhance intra‐class similarity inter‐class separability. Finally, quantization mechanism is used generate identity. identity might be vulnerable many attacks. A shielding proposed address this issue. Experimental...
Traditional testing techniques may not always be suitable for adequate, thorough, and extensible of critical complex software in a resource time constrained development environment. Model-based (MBT) is an evolving technique generating test cases automatically from behavioral model system under test. For Siemens industrial project the healthcare domain high quality, reliable robust indispensable. Thus, we must ensure rigorous using based approach. We specify nine essential criteria to...
Knowledge of the level mental workload induced by any task is essential for optimizing load share among operators. This helps in assessing their capability; besides, helping allocation. Since a persistently high experienced operators such as aircraft pilots and automobile drivers many times compromises performance safety. Despite availability various evaluation techniques heart rate variability, pupil dilation, sac-cades, etc., assessment still challenging task. In this work, we aim to...