Sumukh Prashant Bhanushali

Sumukh Prashant Bhanushali

Auto-generated profile, based on publicly available information

Sumukh Prashant Bhanushali

School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA

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
17 August 2020 in IEEE Solid-State Circuits Letters
Verified
Journal Article
Closed access
SCSanjeev Tannirkulam Chandrasekaran
Sanjeev Tannirkulam Chandrasekaran
SBSumukh Prashant Bhanushali
Sumukh Prashant Bhanushali
IBImon Banerjee
Imon Banerjee
Arindam SanyalArindam Sanyal
Arindam Sanyal
This work presents the first on-chip bio-inspired reservoir computer (RC) prototype implemented in 65nm CMOS. The RC comprises 50 time-multiplexed neurons, and each neuron embeds a strong non-linearity in a feedback loop. The RC applies a non-linear transformation to the input and projects it to high-dimensional space, thus allowing linear separation by a simple logistic regression (LR) layer implemented off-chip. We demonstrate real-time stress detection from electrocardiogram (ECG) signals using the RC. The RC achieves 93% classification accuracy which is 6% better than state-of-the-art digital classifiers. Operating at 40kHz, the prototype consumes 27.5nJ/classification which is 7× lower than state-of-the-art ECG processors performing similar complexity classification task.

16 November 2021 in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
Verified
Journal Article
Closed access
SCSanjeev Tannirkulam Chandrasekaran
Sanjeev Tannirkulam Chandrasekaran
SBSumukh Prashant Bhanushali
Sumukh Prashant Bhanushali
IBImon Banerjee
Imon Banerjee
Arindam SanyalArindam Sanyal
Arindam Sanyal
This work presents a mixed-signal, reservoir-computing neural network (RC-NN) for at-home, real-time health monitoring using intelligent wearable device. The proposed technique is demonstrated on stress detection from electrocardiogram (ECG) signal, and heart diseases detection using a fusion artificial intelligence (AI) model that combines demographic and physiological information. The RC-NN uses a static, random reservoir layer with short-term memory to nonlinearly project input data to high-dimensional plane, and allow easy separation using linear AI model at the output layer. The RC-NN is designed in 65nm CMOS process, and detects stress and heart-diseases with mean accuracies of 92.8% and 86.8% respectively, while consuming 10.97nJ/inference and 2.57nJ/inference respectively.

2 March 2023 in IEEE Transactions on Biomedical Circuits and Systems
Verified
Journal Article
Closed access
SSSudarsan Sadasivuni
Sudarsan Sadasivuni
MSMonjoy Saha
Monjoy Saha
SBSumukh Prashant Bhanushali
Sumukh Prashant Bhanushali
IBImon Banerjee
Imon Banerjee
Arindam SanyalArindam Sanyal
Arindam Sanyal
This work presents an artificial intelligence (AI) framework for real-time, personalized sepsis prediction four hours before onset through fusion of electrocardiogram (ECG) and patient electronic medical record. An on-chip classifier combines analog reservoir-computer and artificial neural network to perform prediction without front-end data converter or feature extraction which reduces energy by 13× compared to digital baseline at normalized power efficiency of 528 TOPS/W, and reduces energy by 159× compared to RF transmission of all digitized ECG samples. The proposed AI framework predicts sepsis onset with 89.9% and 92.9% accuracy on patient data from Emory University Hospital and MIMIC–III respectively. The proposed framework is non-invasive and does not require lab tests which makes it suitable for at-home monitoring.

19 October 2023
Verified
Conference Paper
Closed access
SBSumukh Prashant Bhanushali
Sumukh Prashant Bhanushali
SSSudarsan Sadasivuni
Sudarsan Sadasivuni
Josep Salvador Sánchez GarretaJosep Salvador Sánchez Garreta
Josep Salvador Sánchez Garreta
IBImon Banerjee
Imon Banerjee
Arindam SanyalArindam Sanyal
Arindam Sanyal
This work presents a fully integrated on-chip classifier for on-device detection of atrial fibrillation (AFib) from electrocardiogram (ECG) signal. The ECG signals are digitized using 14-bit analog-to-digital converter followed by time-domain feature extraction. The features are provided as inputs to an in-memory computing analog, 3-layer artificial neural network (ANN) for classification into normal sinus rhythm, AFib and noisy data. On-device AI classification reduces radio-frequency (RF) transmission and extends battery life of the sensing device by performing all the analysis locally and only transmitting in case of AFib detection. Prototype test-chip is fabricated in 65nm and achieves 99.6% accuracy in classification of AFib while consuming 58.3μJ/classification.

11 September 2023
Verified
Conference Paper
Closed access
SBSumukh Prashant Bhanushali
Sumukh Prashant Bhanushali
Arindam SanyalArindam Sanyal
Arindam Sanyal
This work presents an OTA-free pipelined passive noise-shaping SAR (NS-SAR) + VCO ADC that offers high resolution (>12-bit) with only a 5-bit NS-SAR stage and $ 4-36\times$ lower sampling capacitor compared to state-of-the-art NS-SARs with similar ENOB. Pipelining the NS-SAR and VCO stage linearizes VCO by reducing its input swing, increases the VCO integration time and its energy efficiency, and improves SFDR of ADC by suppressing frequency dependency of interstage gain. We demonstrate a simple calibration technique to extract interstage gain and track VCO gain accurately in the background. Fabricated in 65nm CMOS, the prototype ADC achieves the best Walden FoM among state-of-the-art passive NS-SAR ADCs in similar technology and consumes 0. 12mW with SNDR/SFDR of 74.3/S9.ldB at 13. 2fJ/step for OSR of 9.

14 August 2025 in IEEE Transactions on Circuits and Systems for Artificial Intelligence
Verified
Journal Article
Closed access
JSJose Sanchez
Jose Sanchez
SBSumukh Prashant Bhanushali
Sumukh Prashant Bhanushali
SSSudarsan Sadasivuni
Sudarsan Sadasivuni
IBImon Banerjee
Imon Banerjee
Arindam SanyalArindam Sanyal
Arindam Sanyal
This paper outlines a fully integrated on-chip classifier on a flexible substrate for real-time detection of atrial fibrillation (AFib) from electrocardiogram (ECG) signals. The ECG signals are digitized by means of a 14-bit analog-to-digital converter (ADC), followed by a time-domain feature extractor. These features are sent to a switched-capacitor compute-inmemory, analog, three-layer artificial neural network (ANN) for classification. The test-chip, fabricated in 65nm technology, consumes 58.3μJ/ per inference and achieves an average accuracy greater than 99.5’ on Physionet dataset, 80’ on a small, prospective human study performed at Mayo Clinic, Arizona and 99.9% on a large, retrospective dataset provided by Mayo Clinic Enterprise referred to as Rochester dataset.