A5038871705- Pulsars and Gravitational Waves Research
- Gamma-ray bursts and supernovae
- Software-Defined Networks and 5G
- Robotic Path Planning Algorithms
- Advanced Image Processing Techniques
- Image and Video Stabilization
- Face recognition and analysis
- Water Quality Monitoring Technologies
- Seismology and Earthquake Studies
- Context-Aware Activity Recognition Systems
Birla Institute of Technology and Science, Pilani - Goa Campus
2022-2024
Birla Institute of Technology and Science, Pilani
2022-2024
Enabling continuous obstacle detection and providing real-time navigational assistance for people with visual impairment allows them to navigate in an indoor space without dependence on others. In this paper, we present the design, development, evaluation of SonicGlass, a wearable navigation system. SonicGlass consists custom 3D printed smartglass that can replace individual's existing smartglasses. The is embedded multiple sensors microcontrollers. We performed user study 10 participants...
Ubiquitous sensing technologies, leveraging a network of interconnected sensors and devices, offer multifaceted benefits to society. However, the use batteries has persistently posed challenge their advancement. In recent years, researchers have explored establishing communication between battery-free nodes. The primary objective this work is expedite testing algorithms for multiple nodes by isolating algorithm from underlying hardware. Isolating hardware allows faster tuning algorithms,...
Recently, Convolutional neural network (CNN), a class of deep network, has been widely used for processing images and video data. The reason that CNN performs better than the classic on is basically because convolutional layers take advantage inherent properties images. Therefore, in this paper, we propose investigate two-step cascaded classification model using detection gravitational wave (GW) signals emitting from two different heavenly astronomical objects noisy time-series To build...
In this work, we present a FaceNet based 'two branch' model for employee face recognition in low resolution images captured using substandard camera sensors. Our involves common space mapping approach two deep convolutional neural networks (DCNNs) that map the and high to space. The is trained such distance between mapped minimized. Then, logistic regression classifier used classify image by identity of employee. We show through simulations presented achieves accuracy 99.84%, 98.88%, 95.53%...