Dheryta Jaisinghani

Dr. Dheryta Jaisinghani

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 August 2020 in IEEE Transactions on Mobile Computing
Verified
Journal Article
Closed access
SSSara Garcia Sanchez
Sara Garcia Sanchez
SMSubhramoy Mohanti
Subhramoy Mohanti
DJDheryta Jaisinghani
Dheryta Jaisinghani
KCKaushik Roy Chowdhury
Kaushik Roy Chowdhury
This paper adopts a systems approach to study how millimeter wave (mmWave) radio transmitters on UAVs provide high throughput links under typical hovering conditions. With Terragraph channel sounder units, we experimentally study the impact of signal fluctuations and sub-optimal beam selection on a testbed involving DJI M600 UAVs. From the hovering-related insights and the measured antenna radiation patterns, we develop and validate the first stochastic UAV-to-Ground mmWave channel model with UAVs as transmitters. Our UAV-centric analytical model complements the classical fading with additional losses expected in the mmWave channel during hovering, considering 3-D antenna configuration and beamforming training parameters. We specifically consider lateral displacement, roll, pitch, and yaw, whose magnitude vary depending on the availability of specialized hardware such as real-time kinematic GPS. We then leverage this model to mitigate the hovering impact on the UAV-to-Ground link by selecting a near-to-optimum pair of beams. Importantly, our work does not change the wireless standard nor require any cross-layer information, making it compatible with current mmWave devices. Results demonstrate that our channel model drops estimation error to $\approx$ 0.2 percent, i.e., 18x lower, and improves the average PHY bit-rate by $\approx$ 10 percent when compared to existing state-of-the-art channel models and beamforming methods for UAVs.

25 March 2022 in International Journal of Human-Computer Studies
Verified
Journal Article
Closed access
NPNishtha Phutela
Nishtha Phutela
ACAtluri Nikhitha Chowdary
Atluri Nikhitha Chowdary
SAShreyansh Anchlia
Shreyansh Anchlia
DJDheryta Jaisinghani
Dheryta Jaisinghani
GGGoldie Gabrani
Goldie Gabrani

24 July 2023 in Sensors
Verified
Journal Article
Open access
PDF file
DJDheryta Jaisinghani
Dheryta Jaisinghani
NPNishtha Phutela
Nishtha Phutela
A good night’s sleep is of the utmost importance for the seamless execution of our cognitive capabilities. Unfortunately, the research shows that one-third of the US adult population is severely sleep deprived. With college students as our focused group, we devised a contactless, unobtrusive mechanism to detect sleep patterns, which, contrary to existing sensor-based solutions, does not require the subject to put on any sensors on the body or buy expensive sleep sensing equipment. We named this mechanism Packets-to-Predictions(P2P) because we leverage the WiFi MAC layer traffic collected in the home and university environments to predict “sleep” and “awake” periods. We first manually established that extracting such patterns is feasible, and then, we trained various machine learning models to identify these patterns automatically. We trained six machine learning models—K nearest neighbors, logistic regression, random forest classifier, support vector classifier, gradient boosting classifier, and multilayer perceptron. K nearest neighbors gave the best performance with 87% train accuracy and 83% test accuracy.

1 December 2020
Verified
Conference Paper
Closed access
DJDheryta Jaisinghani
Dheryta Jaisinghani
NGNaman Gupta
Naman Gupta
MMMukulika Maity
Mukulika Maity
VNVinayak Naik
Vinayak Naik
We address the problem of connecting IoT nodes to the Internet via challenged networks, which are characterized by minimal or intermittent network association. Examples of such networks can be found in forests with distant access points or in railway stations with overburdened access points. In such places, it is difficult for a node to establish and maintain an association with the access point. There exist several solutions that demonstrate the feasibility of data transfer using low bit-rate broadcast of discovery frames that do not necessitate association. We categorize them into a representative protocol called ViFi. However, the low bit-rate broadcast traffic hampers the performance of heavilyutilized networks by consuming significant airtime and resulting in a severe drop in goodput. We come up with a novel adaptive version of ViFi, Adaptive ViFi, that adapts to network conditions and intelligently selects a channel and an interval for the data transmission. In principle, our proposed solution is agnostic to WiFi standard, client, or AP in use. We develop an end-to-end working prototype on Raspberry Pi and hostapd-based access points. With a set of extensive experiments, we find that Adaptive ViFi gracefully addresses the limitations of ViFi in a heavily utilized network, at the same time it achieves up to 10.7x higher goodput than the ViFi. It co-exists well with other WiFi-based non-IoT clients with minimal impact on their goodput (4%). It scales well with a delivery rate of 77% and 50% with 150 and 300 nodes, respectively.

3 June 2024
Verified
Conference Paper
Open access
BSBlake Schleter
Blake Schleter
MAMarina Avdonina
Marina Avdonina
RARishiraj Adhikary
Rishiraj Adhikary
DJDheryta Jaisinghani
Dheryta Jaisinghani
SSSougata Sen
Sougata Sen
Oral diseases affect an estimated 3.5 billion people globally, posing significant health challenges. According to the World Health Organization (WHO), adopting self-care practices and maintaining personal oral hygiene can substantially mitigate the prevalence of dental caries. While smartwatches have previously been utilized to track activities of daily living (ADL), their widespread availability has yet to be harnessed for accurately identifying tooth brushing activity among other common ADL. In this Work in Progress (WIP), we demonstrate how motion sensors integrated into smartwatches can effectively distinguish tooth brushing from seven other very similar ADL. We present our initial results that show a promising 94% accuracy with 84% sensitivity.