Sudarsan Sadasivuni

Sudarsan Sadasivuni

Auto-generated profile, based on publicly available information

Sudarsan Sadasivuni

Department of Electrical Engineering, University at Buffalo, Buffalo, NY, 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
1 November 2020 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Closed access
MDMohammadhadi Danesh
Mohammadhadi Danesh
AVAishwarya Bahudhanam Venkatasubramaniyan
Aishwarya Bahudhanam Venkatasubramaniyan
GKGaurav Kapoor
Gaurav Kapoor
NRNaveen Ramesh
Naveen Ramesh
SSSudarsan Sadasivuni
Sudarsan Sadasivuni
Arindam SanyalArindam Sanyal
Arindam Sanyal
This work presents a unified weak physical unclonable function (PUF) and a true random number generator (TRNG) based on the current-steering digital-to-analog converter (DAC) and ring voltage-controlled oscillator (VCO). Entropy source for the weak PUF is the mismatch between NMOS and PMOS transistors in a cascode current DAC as well as the mismatch between VCO quantizers, while entropy source for the TRNG is thermal noise in the DAC and VCO and clock jitter. Instead of using spatial entropy sources for the PUF, i.e., multiple unit PUF elements, the proposed architecture utilizes temporal entropy source by capturing the output of unit PUF element over multiple cycles, which reduces area significantly. A unified PUF/TRNG prototype is fabricated in 65-nm CMOS and consumes 0.36 pJ/bit at a throughput of 100 Mb/s. The PUF has a measured intra-HD of 0.0906 and inter-HD of 0.4859, while the raw TRNG bitstream has an entropy of 0.9991 and passes all the NIST statistical randomness tests.

22 December 2022 in Physiological Measurement
Verified
Journal Article
Closed access
ABAmartya Bhattacharya
Amartya Bhattacharya
SSSudarsan Sadasivuni
Sudarsan Sadasivuni
CCChieh-Ju Chao
Chieh-Ju Chao
PAPradyumna Agasthi
Pradyumna Agasthi
CAChadi Ayoub
Chadi Ayoub
IBImon Banerjee
Imon Banerjee
Background. Clinical medicine relies heavily on the synthesis of information and data from multiple sources. However, often simple feature concatenation is used as a strategy for developing a multimodal machine learning model in the cardiovascular domain, and thus the models are often limited by pre-selected features and moderate accuracy. Method. We proposed a two-branched joint fusion model for fusing the 12-lead electrocardiogram (ECG) signal data with clinical variables from the electronic medical record (EMR) in an end-to-end deep learning architecture. The model follows the joint fusion scheme and learns complementary information from ECG and EMR. Retrospective data from the Mayo Clinic Health Systems across four sites for patients that underwent percutaneous coronary intervention (PCI) were obtained. Model performance was assessed by area under the receiver-operating characteristics (AUROC) and Delong’s test. Results. The final cohort included 17,356 unique patients with a mean age of 67.2 ± 12.6 year (mean ± std) and 9,163 (52.7%) were male. The joint fusion model outperformed the ECG time-domain model with statistical margin. The model with clinical data obtained the highest AUROC for all-cause mortality (0.91 at 6 months) but the joint fusion model outperformed for cardiovascular outcomes - heart failure hospitalization and ischemic stroke with a significant margin (Delong’s p < 0.05). Conclusion. To the best of our knowledge, this is the first study that developed a deep learning model with joint fusion architecture for the prediction of post-PCI prognosis and outperformed machine learning models developed using traditional single-source features (clinical variables or ECG features). Adding ECG data with clinical variables did not improve prediction of all-cause mortality as may be expected, but the improved performance of related cardiac outcomes shows that the fusion of ECG generates additional value.

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.

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.