A5022024002- Anomaly Detection Techniques and Applications
- Explainable Artificial Intelligence (XAI)
- Adversarial Robustness in Machine Learning
- Microwave Imaging and Scattering Analysis
- Machine Learning and Data Classification
- Ultra-Wideband Communications Technology
- Geophysical Methods and Applications
- Artificial Intelligence in Healthcare
- Computational and Text Analysis Methods
- Natural Language Processing Techniques
- Music and Audio Processing
- Multisensory perception and integration
- Image and Signal Denoising Methods
- EEG and Brain-Computer Interfaces
- Essential Oils and Antimicrobial Activity
- Time Series Analysis and Forecasting
- ECG Monitoring and Analysis
- Piperaceae Chemical and Biological Studies
- Integrated Circuits and Semiconductor Failure Analysis
- Speech Recognition and Synthesis
- Advanced Chemical Sensor Technologies
- Neuroscience and Music Perception
- Non-Invasive Vital Sign Monitoring
- Topic Modeling
University of Reading
2020-2023
Ramakrishna Mission Vidyalaya
2021
We propose a novel deep learning based denoising filter selection algorithm for noisy Electrocardiograph (ECG) signal preprocessing. ECG signals measured under clinical conditions, such as those acquired using skin contact devices in hospitals, often contain baseline disturbances and unwanted artefacts; indeed obtained outside of environment, heart rate signatures recorded non-contact radar systems, the measurements greater levels noise than conditions. In this paper we focus on noncontact...
Medicinal plants are widely used in non-industrialized societies, mainly because they readily available and cheaper than modern medicines. These herbs that have medicinal quality provide rational means for the treatment of many internal diseases, which otherwise considered difficult to cure. This is reason why plant related analysis growing popularity across researchers. The prime this identification those plants. Without any expert, difficult. image processing methodologies dominant method...
SemEval Task 4 Commonsense Validation and Explanation Challenge is to validate whether a system can differentiate natural language statements that make sense from those do not sense. Two subtasks, A B, are focused in this work, i.e., detecting against-common-sense selecting explanations of why they false the given options. Intuitively, commonsense validation requires additional knowledge beyond statements. Therefore, we propose utilising pre-trained sentence transformer models based on BERT,...
We propose a systematic analysis of deep neural networks (DNNs) based on signal processing technique for network parameter removal, in the form synaptic filters that identifies fragility, robustness and antifragility characteristics DNN parameters. Our proposed investigates if performance is impacted negatively, invariantly, or positively both clean adversarially perturbed test datasets when undergoes filtering. define three \textit{filtering scores} quantifying parameters performances (i)...
We propose a systematic analysis of deep neural networks (DNNs) based on signal processing technique for network parameter removal, in the form synaptic filters that identifies fragility, robustness and antifragility characteristics DNN parameters. Our proposed investigates if performance is impacted negatively, invariantly, or positively both clean adversarially perturbed test datasets when undergoes filtering. define three filtering scores quantifying parameters performances (i) dataset,...