- Tactile and Sensory Interactions
- Mobile Ad Hoc Networks
- Advanced Image and Video Retrieval Techniques
- IoT-based Smart Home Systems
- Visual Attention and Saliency Detection
- 3D Surveying and Cultural Heritage
- Cloud Data Security Solutions
- Opportunistic and Delay-Tolerant Networks
- Smart Parking Systems Research
- Handwritten Text Recognition Techniques
- Algorithms and Data Compression
- Video Analysis and Summarization
- Indoor and Outdoor Localization Technologies
- Natural Language Processing Techniques
- Human Pose and Action Recognition
- Topic Modeling
- Service-Oriented Architecture and Web Services
- Spatial Cognition and Navigation
- Interactive and Immersive Displays
- COVID-19 diagnosis using AI
- Digital Imaging for Blood Diseases
- Gaze Tracking and Assistive Technology
- Age of Information Optimization
- Pharmacogenetics and Drug Metabolism
- Network Packet Processing and Optimization
Chandigarh University
2023-2024
Columbia University
2023-2024
Amity University
2021
Delhi Technological University
2019-2020
Indian Institute of Science Bangalore
2020
SRM Institute of Science and Technology
2020
Sinhgad Dental College and Hospital
2017
Indian Institute of Technology Roorkee
2014
University of California, Irvine
2014
Indian Institute of Space Science and Technology
2014
Photoacoustic tomography (PAT) is a noninvasive imaging modality combining the benefits of optical contrast at ultrasonic resolution. Analytical reconstruction algorithms for photoacoustic (PA) signals require large number data points accurate image reconstruction. However, in practical scenarios, are collected using limited transducers along with being often corrupted noise resulting only qualitative images. Furthermore, boundary band-limited due to bandwidth (BW) transducer, making PA...
Multimodal biometric systems offer numerous advantages over unimodal counterparts and are being used extensively in diverse applications. However, fusion of data is a non-trivial task curtail employability multimodal for varying set characteristics with different type dimension. Moreover, comprehensive solutions against adversary attacks that ensure template protection prevent presentation not place. In this article, secure cancelable system proposed to address these concerns. This approach...
Navigation assistance systems (NASs) aim to help visually impaired people (VIPs) navigate unfamiliar environments. Most of today's NASs support VIPs via turn-by-turn navigation, but a growing body work highlights the importance exploration as well. It is unclear, however, how should be designed explore In this paper, we perform qualitative study understand VIPs' information needs and challenges with respect exploring environments inform design that exploration. Our findings reveal types...
Blind and low-vision (BLV) people watch sports through radio broadcasts that offer a play-by-play description of the game. However, recent trends show decline in availability quality due to rise video streaming platforms on internet cost hiring professional announcers. As result, have now become even more inaccessible BLV people. In this work, we present Immersive A/V, technique for making —in our case, tennis broadcasts— accessible immersive viewers by automatically extracting gameplay...
Blind and low-vision (BLV) people face challenges watching sports due to the lack of accessibility broadcasts. Currently, BLV rely on descriptions from TV commentators, radio announcers, or their friends understand game. These descriptions, however, do not allow viewers visualize action by themselves. We present Front Row, a system that automatically generates an immersive audio representation broadcasts, specifically tennis, allowing more directly perceive what is happening in Row first...
For the past few decades, machines have replaced humans in several disciplines. However, machine cognition still lags behind human capabilities. We address machines' ability to recognize drawn sketches this work. Visual representations, such as long been a medium of communication for humans. artificially intelligent systems effectively immerse interactive environments, it is required that understand notations. The abstract nature and varied artistic styling these make automatic recognition...
In the past decades, people have gained a wide range of options as availability information expands.To help them make decisions, recommendation systems play an important role in all kinds aspects, e.g.news, books, movies and so on.One such aspect is Restaurant where recommendations can be provided using user attributes activity.A noticeable similarity found belonging to same categories based on like age, native place, gender, work-type, etc.Using Collaborative approach these individuals...
Information gathering during a disaster management has crucial role in designing the response mechanism. Several factors such as geography, infrastructure, and population influence information process. The task is particularly complex when disasters strike shanty town. A town terrain characterized by its high density, considerable level of under-development, poor infrastructure. Mobile Data Collection agents (MDCs) can be assigned with data collection aftermath disaster. In this paper, we...
Recent technological advancements in the field of nanotechnology have increased computation power wireless nodes while adhering to energy constraints. This has made use Wireless Sensor Networks (WSNs), more widespread, used applications such as area monitoring, industrial vehicle detection or military monitoring. it possible collect data even hostile environments, but because severe security and constraints faced by sensor networks, their deployment on a large scale is still tricky job. A...
Any disease whether it is curable or not, must be diagnosed properly with some time in hand to take the appropriate actions time. As popularly said that early detection of any half cured. For diseases like Pneumonia, Covid-19, Brain Tumor Radiography, Computed Tomography are a technique used nowadays. The motivation towards study topic was due our country's population density, vulnerability getting infected and not being treated nicely exposed during outbreak Covid-19. ratio doctors India...
Cloud Computing (CC) offers recent facilities to enterprises, companies, and the general, public delivers low cost computing infrastructure for IT-based solutions. CC is not organizations e.g. academies, research laboratories, military in developed countries has long utilized networks communiqué, but conditions cloud more recent. being, increasingly offered over web as technology become faster complex. A network, there no complete security solution secure data applications or services,...
Passenger information aims at improving the user-friendliness of public transport systems while influencing passenger route choices to satisfy transit user’s travel requirements. The integration from multiple agencies is a major challenge in implementation multi-modal systems. problem sharing further compounded by multi-lingual and multi-cultural population developing countries such as India. Ontology, explicit specification conceptualisation, not only addresses issues pertaining syntactic...
Delay Tolerant Networking (DTN) is an approach to networking which handles network disruptions and high delays that may occur in many kinds of communication networks. The major reasons for delay include partial connectivity networks as can be seen types ad hoc wireless with frequent partitions, long propagation time experienced inter-planetary deep space networks, link due the mobility nodes observed terrestrial environments. Experimenting architectures, protocols, models such real-world...
Passenger information is vital for developing a user-friendly public transportation system. Websites are rapidly gaining popularity transport dissemination, particularly due to their anytime-anywhere availability and suitability the multimodal applications multilingual interface. Internet-based Information Systems (PIS), therefore, have become common in developed countries. The development of PIS urban India however, at an experimental stage with very few operational deployments. This paper...
Blind and low-vision (BLV) people use GPS-based systems for outdoor navigation assistance, which provide instructions to get from one place another. However, such do not users with real-time, precise information about their location surroundings is crucial safe navigation. In this work, we investigate whether street cameras can be used address aspects of that BLV still find challenging existing assistive technologies. We conducted formative interviews six participants identify specific...
Transformers have emerged as the underpinning architecture for Large Language Models (LLMs). In generative language models, inference process involves two primary phases: prompt processing and token generation. Token generation, which constitutes majority of computational workload, primarily entails vector-matrix multiplications interactions with Key-Value (KV) Cache. This phase is constrained by memory bandwidth due to overhead transferring weights KV cache values from system computing...