Mohit Aggarwal

Mohit Aggarwal


Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
1 September 2006 in Chemical Engineering Science
Verified
Journal Article
Closed access
VKVimal Kumar
Vimal Kumar
MAMohit Aggarwal
Mohit Aggarwal
KNK.D.P. Nigam
K.D.P. Nigam

11 May 2024 in ACM Transactions on Embedded Computing Systems
Verified
Journal Article
Open access
SSSwapnil Sayan Saha
Swapnil Sayan Saha
SSSandeep Singh Sandha
Sandeep Singh Sandha
MAMohit Aggarwal
Mohit Aggarwal
BWBrian Wang
Brian Wang
LHLiying Han
Liying Han
MSMani Srivastava
Mani Srivastava
Machine learning at the extreme edge has enabled a plethora of intelligent, time-critical, and remote applications. However, deploying interpretable artificial intelligence systems that can perform high-level symbolic reasoning and satisfy the underlying system rules and physics within the tight platform resource constraints is challenging. In this article, we introduce TinyNS , the first platform-aware neurosymbolic architecture search framework for joint optimization of symbolic and neural operators. TinyNS provides recipes and parsers to automatically write microcontroller code for five types of neurosymbolic models, combining the context awareness and integrity of symbolic techniques with the robustness and performance of machine learning models. TinyNS uses a fast, gradient-free, black-box Bayesian optimizer over discontinuous, conditional, numeric, and categorical search spaces to find the best synergy of symbolic code and neural networks within the hardware resource budget. To guarantee deployability, TinyNS talks to the target hardware during the optimization process. We showcase the utility of TinyNS by deploying microcontroller-class neurosymbolic models through several case studies. In all use cases, TinyNS outperforms purely neural or purely symbolic approaches while guaranteeing execution on real hardware.

31 December 2011 in Journal of Process Control
Verified
Journal Article
Closed access
MAMohit Aggarwal
Mohit Aggarwal
SBS. Balaji
S. Balaji
BYB. Erik Ydstie
B. Erik Ydstie

17 April 2006 in AIChE Journal
Verified
Journal Article
Closed access
PDF file
MAMohit Aggarwal
Mohit Aggarwal
JCJérôme Carrayrou
Jérôme Carrayrou

9 August 2013 in AIChE Journal
Verified
Journal Article
Closed access
PDF file
MAMohit Aggarwal
Mohit Aggarwal
BYB. Erik Ydstie
B. Erik Ydstie

5 December 2019
Verified
Conference Paper
Closed access
PDF file
MAMohit Aggarwal
Mohit Aggarwal
JDJ. K. Dutt
J. K. Dutt
SCS. Chandraker
S. Chandraker
Flexible couplings are used to transmit power between two shafts and accommodate, more realistically, a combination of parallel, axial and angular misalignments, between them. Presence of misalignment of certain degree is considered unavoidable. The coupling also attenuates the transmission of fluctuation of torque and speed from one rotor to the other by flexing itself, and is thus helpful in providing nearly smooth transmission of speed and torque. However, in this process, the dynamic behavior of the rotors is also influenced by the coupling characteristics, as the coupling incorporates a flexible damped intermediate member between the shafts it couples. A detailed literature survey has shown that researchers so far have not attempted to find out the dynamic characteristics, the stiffness and damping of a coupling, and, instead, the effect of misalignment (combination of parallel and angular misalignment) is considered to generate forces independent of the coupling characteristics. This paper attempts to find out an analytical model for the dynamic characteristic of segmented link coupling in terms of suitable non-dimensional coefficients to generate the characteristics of a coupling element which may be used for dynamic analysis of coupled rotor shaft system.