Syed Islam

Dr. Syed Islam

Department of Electrical Engineering and Computer Science, The University of Tennessee, 1520 Middle Drive, Knoxville, TN 37996-2250, USA
+1
orcid

Research Focus & Metrics

Academic Career Length

24Years (2003-Present)

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

Representative Publications

View All Publications
14 December 2022 in Proceedings of the IEEE
Verified
Journal Article
Open access
MSMd Maruf Hossain Shuvo
Md Maruf Hossain Shuvo
Syed IslamSyed Islam
Syed Islam
JCJianlin Cheng
Jianlin Cheng
BMBashir Morshed
Bashir Morshed
Successful integration of deep neural networks (DNNs) or deep learning (DL) has resulted in breakthroughs in many areas. However, deploying these highly accurate models for data-driven, learned, automatic, and practical machine learning (ML) solutions to end-user applications remains challenging. DL algorithms are often computationally expensive, power-hungry, and require large memory to process complex and iterative operations of millions of parameters. Hence, training and inference of DL models are typically performed on high-performance computing (HPC) clusters in the cloud. Data transmission to the cloud results in high latency, round-trip delay, security and privacy concerns, and the inability of real-time decisions. Thus, processing on edge devices can significantly reduce cloud transmission cost. Edge devices are end devices closest to the user, such as mobile phones, cyber–physical systems (CPSs), wearables, the Internet of Things (IoT), embedded and autonomous systems, and intelligent sensors. These devices have limited memory, computing resources, and power-handling capability. Therefore, optimization techniques at both the hardware and software levels have been developed to handle the DL deployment efficiently on the edge. Understanding the existing research, challenges, and opportunities is fundamental to leveraging the next generation of edge devices with artificial intelligence (AI) capability. Mainly, four research directions have been pursued for efficient DL inference on edge devices: 1) novel DL architecture and algorithm design; 2) optimization of existing DL methods; 3) development of algorithm–hardware codesign; and 4) efficient accelerator design for DL deployment. This article focuses on surveying each of the four research directions, providing a comprehensive review of the state-of-the-art tools and techniques for efficient edge inference.

20 November 2018 in Sensors
Verified
Journal Article
Open access
PDF file
Salvatore Andrea PullanoSalvatore Andrea Pullano
Salvatore Andrea Pullano
CCCostantino Davide Critello
Costantino Davide Critello
Ifana MahbubIfana Mahbub
Ifana Mahbub
Nishat TasneemNishat Tasneem
Nishat Tasneem
SSSamira Shamsir
Samira Shamsir
Antonino S. FiorilloAntonino S. Fiorillo
Antonino S. Fiorillo
Since the 1970s, a great deal of attention has been paid to the development of semiconductor-based biosensors because of the numerous advantages they offer, including high sensitivity, faster response time, miniaturization, and low-cost manufacturing for quick biospecific analysis with reusable features. Commercial biosensors have become highly desirable in the fields of medicine, food, and environmental monitoring as well as military applications, whereas increasing concerns about food safety and health issues have resulted in the introduction of novel legislative standards for these sensors. Numerous devices have been developed for monitoring biological processes such as nucleic acid hybridization, protein–protein interaction, antigen–antibody bonds, and substrate–enzyme reactions, just to name a few. Since the 1980s, scientific interest moved to the development of semiconductor-based devices, which also include integrated front-end electronics, such as the extended-gate field-effect transistor (EGFET) biosensor, one of the first miniaturized chemical sensors. This work is intended to be a review of the state of the art focused on the development of biosensors and chemosensors based on extended-gate field-effect transistor within the field of bioanalytical applications, which will highlight the most recent research reported in the literature. Moreover, a comparison among the diverse EGFET devices will be presented, giving particular attention to the materials and technologies.

12 October 2022 in Energies
Verified
Journal Article
Open access
PDF file
MSMd Maruf Hossain Shuvo
Md Maruf Hossain Shuvo
TTTwisha Titirsha
Twisha Titirsha
NANazmul Amin
Nazmul Amin
Syed IslamSyed Islam
Syed Islam
Modern healthcare is transforming from hospital-centric to individual-centric systems. Emerging implantable and wearable medical (IWM) devices are integral parts of enabling affordable and accessible healthcare. Early disease diagnosis and preventive measures are possible by continuously monitoring clinically significant physiological parameters. However, most IWM devices are battery-operated, requiring replacement, which interrupts the proper functioning of these devices. For the continuous operation of medical devices for an extended period of time, supplying uninterrupted energy is crucial. A sustainable and health-compatible energy supply will ensure the high-performance real-time functioning of IWM devices and prolong their lifetime. Therefore, harvesting energy from the human body and ambient environment is necessary for enduring precision healthcare and maximizing user comfort. Energy harvesters convert energy from various sources into an equivalent electrical form. This paper presents a state-of-the-art comprehensive review of energy harvesting techniques focusing on medical applications. Various energy harvesting approaches, working principles, and the current state are discussed. In addition, the advantages and limitations of different methods are analyzed and existing challenges and prospects for improvement are outlined. This paper will help with understanding the energy harvesting technologies for the development of high-efficiency, reliable, robust, and battery-free portable medical devices.

2 January 2023 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
MSMd Maruf Hossain Shuvo
Md Maruf Hossain Shuvo
Syed IslamSyed Islam
Syed Islam
The adverse glycemic events triggered by the inaccurate insulin infusion in Type I diabetes (T1D) can lead to fatal complications. Predicting blood glucose concentration (BGC) based on clinical health records is critical for control algorithms in the artificial pancreas (AP) and aiding in medical decision support. This paper presents a novel deep learning (DL) model incorporating multitask learning (MTL) for personalized blood glucose prediction. The network architecture consists of shared and clustered hidden layers. Two layers of stacked long short-term memory (LSTM) form the shared hidden layers that learn generalized features from all subjects. The clustered hidden layers comprise two dense layers adapting to the gender-specific variability in the data. Finally, the subject-specific dense layers offer additional fine-tuning to personalized glucose dynamics resulting in an accurate BGC prediction at the output. OhioT1DM clinical dataset is used for the training and performance evaluation of the proposed model. A detailed analytical and clinical assessment have been performed using root mean square (RMSE), mean absolute error (MAE), and Clarke error grid analysis (EGA), respectively, which demonstrates the robustness and reliability of the proposed method. Consistently leading performance has been achieved for 30- (RMSE = 16.06 $\pm$ 2.74, MAE = 10.64 $\pm$ 1.35), 60- (RMSE = 30.89 $\pm$ 4.31, MAE = 22.07 $\pm$ 2.96), 90- (RMSE = 40.51 $\pm$ 5.16, MAE = 30.16 $\pm$ 4.10), and 120-minute (RMSE = 47.39 $\pm$ 5.62, MAE = 36.36 $\pm$ 4.54) prediction horizon (PH). In addition, the EGA analysis confirms the clinical feasibility by maintaining more than 94 % BGC predictions in the clinically safe zone for up to 120-minute PH. Moreover, the improvement is established by benchmarking against the state-of-the-art statistical, machine learning (ML), and deep learning (DL) methods.

13 April 2017 in Sensors
Verified
Journal Article
Open access
PDF file
Salvatore Andrea PullanoSalvatore Andrea Pullano
Salvatore Andrea Pullano
Ifana MahbubIfana Mahbub
Ifana Mahbub
Syed IslamSyed Islam
Syed Islam
Antonino S. FiorilloAntonino S. Fiorillo
Antonino S. Fiorillo
This paper presents a ferroelectric polymer-based temperature sensor designed for microfluidic devices. The integration of the sensor into a system-on-a-chip platform facilitates quick monitoring of localized temperature of a biological fluid, avoiding errors in the evaluation of thermal evolution of the fluid during analysis. The contact temperature sensor is fabricated by combining a thin pyroelectric film together with an infrared source, which stimulates the active element located on the top of the microfluidic channel. An experimental setup was assembled to validate the analytical model and to characterize the response rate of the device. The evaluation procedure and the operating range of the temperature also make this device suitable for applications where the localized temperature monitoring of biological samples is necessary. Additionally, ease of integration with standard microfluidic devices makes the proposed sensor an attractive option for in situ analysis of biological fluids.

2 March 2019 in Sensors
Verified
Journal Article
Open access
PDF file
Salvatore Andrea PullanoSalvatore Andrea Pullano
Salvatore Andrea Pullano
Nishat TasneemNishat Tasneem
Nishat Tasneem
Ifana MahbubIfana Mahbub
Ifana Mahbub
SSSamira Shamsir
Samira Shamsir
Marta GrecoMarta Greco
Marta Greco
Antonino S. FiorilloAntonino S. Fiorillo
Antonino S. Fiorillo
Extended-gate field-effect transistor (EGFET) is an electronic interface originally developed as a substitute for an ion-sensitive field-effect transistor (ISFET). Although the literature shows that commercial off-the-shelf components are widely used for biosensor fabrication, studies on electronic interfaces are still scarce (e.g., noise processes, scaling). Therefore, the incorporation of a custom EGFET can lead to biosensors with optimized performance. In this paper, the design and characterization of a transistor association (TA)-based EGFET was investigated. Prototypes were manufactured using a 130 nm standard complementary metal-oxide semiconductor (CMOS) process and compared with devices presented in recent literature. A DC equivalence with the counterpart involving a single equivalent transistor was observed. Experimental results showed a power consumption of 24.99 mW at 1.2 V supply voltage with a minimum die area of 0.685 × 1.2 mm2. The higher aspect ratio devices required a proportionally increased die area and power consumption. Conversely, the input-referred noise showed an opposite trend with a minimum of 176.4 nVrms over the 0.1 to 10 Hz frequency band for a higher aspect ratio. EGFET as a pH sensor presented further validation of the design with an average voltage sensitivity of 50.3 mV/pH, a maximum current sensitivity of 15.71 mA1/2/pH, a linearity higher than 99.9%, and the possibility of operating at a lower noise level with a compact design and a low complexity.