Tinoosh Mohsenin

Tinoosh Mohsenin

Auto-generated profile, based on publicly available information

Tinoosh Mohsenin

Johns Hopkins University

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

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

Representative Publications

View All Publications
25 November 2021 in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
Verified
Journal Article
Open access
AMArnab Neelim Mazumder
Arnab Neelim Mazumder
JMJian Meng
Jian Meng
HRHasib-Al Rashid
Hasib-Al Rashid
UKUtteja Kallakuri
Utteja Kallakuri
XZXin Zhang
Xin Zhang
TMTinoosh Mohsenin
Tinoosh Mohsenin
Deep neural networks (DNNs) are being prototyped for a variety of artificial intelligence (AI) tasks including computer vision, data analytics, robotics, etc. The efficacy of DNNs coincides with the fact that they can provide state-of-the-art inference accuracy for these applications. However, this advantage comes from the high computational complexity of the DNNs in use. Hence, it is becoming increasingly important to scale these DNNs so that they can fit on resource-constrained hardware and edge devices. The main goal is to allow efficient processing of the DNNs on low-power micro-AI platforms without compromising hardware resources and accuracy. In this work, we aim to provide a comprehensive survey about the recent developments in the domain of energy-efficient deployment of DNNs on micro-AI platforms. To this extent, we look at different neural architecture search strategies as part of micro-AI model design, provide extensive details about model compression and quantization strategies in practice, and finally elaborate on the current hardware approaches towards efficient deployment of the micro-AI models on hardware. The main takeaways for a reader from this article will be understanding of different search spaces to pinpoint the best micro-AI model configuration, ability to interpret different quantization and sparsification techniques, and the realization of the micro-AI models on resource-constrained hardware and different design considerations associated with it.

23 November 2017 in IEEE Transactions on Biomedical Circuits and Systems
Verified
Journal Article
Open access
AJAli Jafari
Ali Jafari
NBNathanael Buswell
Nathanael Buswell
MGMaysam Ghovanloo
Maysam Ghovanloo
TMTinoosh Mohsenin
Tinoosh Mohsenin
This paper presents a low-power stand-alone tongue drive system (sTDS) used for individuals with severe disabilities to potentially control their environment such as computer, smartphone, and wheelchair using their voluntary tongue movements. A low-power local processor is proposed, which can perform signal processing to convert raw magnetic sensor signals to user-defined commands, on the sTDS wearable headset, rather than sending all raw data out to a PC or smartphone. The proposed sTDS significantly reduces the transmitter power consumption and subsequently increases the battery life. Assuming the sTDS user issues one command every 20 ms, the proposed local processor reduces the data volume that needs to be wirelessly transmitted by a factor of 64, from 9.6 to 0.15 kb/s. The proposed processor consists of three main blocks: serial peripheral interface bus for receiving raw data from magnetic sensors, external magnetic interference attenuation to attenuate external magnetic field from the raw magnetic signal, and a machine learning classifier for command detection. A proof-of-concept prototype sTDS has been implemented with a low-power IGLOO-nano field programmable gate array (FPGA), bluetooth low energy, battery and magnetic sensors on a headset, and tested. At clock frequency of 20 MHz, the processor takes 6.6 μs and consumes 27 nJ for detecting a command with a detection accuracy of 96.9%. To further reduce power consumption, an application-specified integrated circuit processor for the sTDS is implemented at the postlayout level in 65-nm CMOS technology with 1-V power supply, and it consumes 0.43 mW, which is 10× lower than FPGA power consumption and occupies an area of only 0.016 mm 2 .

11 May 2024 in ACM Transactions on Embedded Computing Systems
Verified
Journal Article
Open access
HRHasib-Al Rashid
Hasib-Al Rashid
UKUtteja Kallakuri
Utteja Kallakuri
TMTinoosh Mohsenin
Tinoosh Mohsenin
With the evaluation of Artificial Intelligence (AI), there has been a resurgence of interest in how to use AI algorithms on low-power embedded systems to broaden potential use cases of the Internet of Things (IoT). To mimic multimodal human perception, multimodal deep neural networks (M-DNN) have recently become very popular with the classification task due to their impressive performance for computer vision and audio processing tasks. This article presents TinyM 2 Net-V2 —a compact low-power software hardware architecture for m ulti m odal deep neural networks for resource-constrained tiny devices. To compress the models to implement on tiny devices, cyclicly sparsification and hybrid quantization (4-bits weights and 8-bits activations) methods are used. Although model compression techniques are an active research area, we are the first to demonstrate their efficacy for multimodal deep neural networks, using cyclicly sparsification and hybrid quantization of weights/activations. TinyM 2 Net-V2 shows that even a tiny multimodal deep neural network model can improve the classification accuracy more than that of any unimodal counterparts. Parameterized M-DNN model architecture was designed to be evaluated in two different case-studies: vehicle detection from multimodal images and audios and COVID-19 detection from multimodal audio recordings. The most compressed TinyM 2 Net-V2 achieves 92.5% COVID-19 detection accuracy (6.8% improvement from the unimodal full precision model) and 90.6% vehicle classification accuracy (7.7% improvement from the unimodal full precision model). A parameterized and flexible FPGA hardware accelerator was designed as well for TinyM 2 Net-V2 models. To the best of our knowledge, this is the first work accelerating multimodal deep neural network models on low-power Artix-7 FPGA hardware. We achieved energy efficiency of 9.04 GOP/s/W and 15.38 GOP/s/W for case-study 1 and case-study 2, respectively, which is comparable to the state-of-the-art results. Finally, we compared our tiny FPGA hardware implementation results with off-the-shelf resource-constrained devices and showed our implementation is faster and consumed less power compared to the off-the-shelf resource-constrained devices.

1 August 2015
Verified
Conference Paper
Closed access
APAdam Page
Adam Page
SOSiddharth Pramod Tim Oates
Siddharth Pramod Tim Oates
TMTinoosh Mohsenin
Tinoosh Mohsenin
In this paper we explore the use of a variety of machine learning algorithms for designing a reliable and low-power, multi-channel EEG feature extractor and classifier for predicting seizures from electroencephalographic data (scalp EEG). Different machine learning classifiers including k-nearest neighbor, support vector machines, naïve Bayes, logistic regression, and neural networks are explored with the goal of maximizing detection accuracy while minimizing power, area, and latency. The input to each machine learning classifier is a 198 feature vector containing 9 features for each of the 22 EEG channels obtained over 1-second windows. All classifiers were able to obtain F1 scores over 80% and onset sensitivity of 100% when tested on 10 patients. Among five different classifiers that were explored, logistic regression (LR) proved to have minimum hardware complexity while providing average F-1 score of 91%. Both ASIC and FPGA implementations of logistic regression are presented and show the smallest area, power consumption, and the lowest latency when compared to the previous work.

25 September 2023 in IEEE Micro
Verified
Journal Article
Closed access
MNMozhgan Navardi
Mozhgan Navardi
EHEdward Humes
Edward Humes
TMTejaswini Manjunath
Tejaswini Manjunath
TMTinoosh Mohsenin
Tinoosh Mohsenin
Metareasoning shows promise in efficiently using the computational resources of tiny edge devices while performing highly computationally intensive Reinforcement Learning (RL) algorithms. This work proposes MetaE2RL: a hardware-aware framework that incorporates low-power pre-processing solutions and metareasoning to enable the deployment of multi-goal RL on tiny autonomous devices. For this aim, a meta-level is proposed to allocate resources efficiently in real-time by switching between models with different complexities. Moreover, Squeezed Edge YOLO is proposed for energy-efficient object detection in the pre-processing phase. For the experimental results, the proposed Squeezed Edge YOLO was deployed onboard a tiny drone named Crazyflie with GAP8 processor that includes 8 parallel RISC-V cluster cores. We compared latency and power consumption of Squeezed Edge YOLO and a lighter CNN-based model while deploying them separately onboard on GAP8. Experimental results show Squeezed Edge YOLO is 8x smaller than previous work and consumes 541 mW on GAP8 with inference latency of 130 ms.

11 May 2021 in IEEE Design & Test
Verified
Journal Article
Closed access
AMArnab Neelim Mazumder
Arnab Neelim Mazumder
HRHaoran Ren
Haoran Ren
HRHasib-Al Rashid
Hasib-Al Rashid
MHMorteza Hosseini
Morteza Hosseini
VCVandana Chandrareddy
Vandana Chandrareddy
TMTinoosh Mohsenin
Tinoosh Mohsenin
Respiratory diseases are a leading cause of death in the world. This article proposes a deep convolutional neural network (DCNN) that can detect respiratory symptoms in a user using audio input, and with the assistance of additional physiological or demographic information.