Raqibul Hasan

Dr. Raqibul Hasan

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
13 March 2025 in Information
Verified
Journal Article
Open access
PDF file
MAMd Shahanur Alam
Md Shahanur Alam
CYChris Yakopcic
Chris Yakopcic
RHRaqibul Hasan
Raqibul Hasan
TTTarek M. Taha
Tarek M. Taha
An ultralow-power, high-performance online-learning and anomaly-detection system has been developed for edge security applications. Designed to support personalized learning without relying on cloud data processing, the system employs sample-wise learning, eliminating the need for storing entire datasets for training. Built using memristor-based analog neuromorphic and in-memory computing techniques, the system integrates two unsupervised autoencoder neural networks—one utilizing optimized crossbar weights and the other performing real-time learning to detect novel intrusions. Threshold optimization and anomaly detection are achieved through a fully analog Euclidean Distance (ED) computation circuit, eliminating the need for floating-point processing units. The system demonstrates 87% anomaly-detection accuracy; achieves a performance of 16.1 GOPS—774× faster than the ASUS Tinker Board edge processor; and delivers an energy efficiency of 783 GOPS/W, consuming only 20.5 mW during anomaly detection.

5 September 2025 in Chips
Verified
Journal Article
Open access
PDF file
RHRaqibul Hasan
Raqibul Hasan
MAMd Shahanur Alam
Md Shahanur Alam
TTTarek M. Taha
Tarek M. Taha
Memristor crossbar-based neural network systems offer high throughput with low energy consumption. A key advantage of on-chip training in these systems is their ability to mitigate the effects of device variability and faults. This paper presents an efficient on-chip training circuit for memristor crossbar-based multi-layer neural networks. We propose a novel method for storing the product of two analog signals directly in a memristor device, eliminating the need for ADC and DAC converters. Experimental results show that the proposed system is approximately twice as energy efficient and 1.5 times faster than existing memristor-based systems for training multi-layer neural networks.

18 December 2023
Verified
Conference Paper
Open access
RHRaqibul Hasan
Raqibul Hasan
Memristor crossbar-based neural networks perform parallel operation in the analog domain. Ex-situ training approach needs to program the predetermined resistance values in the memristor crossbar. Because of the stochasticity of the memristor devices, programming a memristor needs to read the device resistance value iteratively. Reading a single memristor in a crossbar (without isolation transistor) is challenging due to the sneak path current. Programming a memristor in a crossbar to either RON or ROFF state is relatively straightforward. A neural network implemented using higher precision weights provides higher classification accuracy compared to a Ternary Neural Network (TNN). This paper demonstrates the implementation of memristor-based neural networks using only the two resistance values (RON, ROFF). At the same time, it achieves higher weight precision. The experimental result shows that the proposed higher precision synapses are easy to program and provide better classification accuracy compared to a TNN.

15 October 2024 in Journal of High Speed Networks
Verified
Journal Article
Closed access
PDF file
RHRaqibul Hasan
Raqibul Hasan
Alireza SouriAlireza Souri
Alireza Souri
This paper proposes a low power consuming system for monitoring elderly people’s activities and their health conditions. The proposed system has two activity recognition modules: smartphone sensor-based wearable module; infrared grid sensor-based remote module. The two activity recognition modules work in a coordinated way. The fraction of the time the person is detected by the infrared sensor, the smartphone remains idle. As a result, energy consumption in the smartphone is reduced significantly, and hence the battery lifetime is increased. In the smartphone, a Feed-forward Neural Network (FNN) based activity recognition algorithm is implemented using fixed-point computation to further reduce energy consumption. A Convolutional Neural Network is used in the infrared sensor-based activity recognition module. The proposed system also has real-time health monitoring capability, which is based on ECG signal classification. A FNN leveraging fixed-point operation is used for ECG signal classification on an embedded ARM processor. Proposed fixed-point implementations of the FNNs are faster than floating-point implementation and require 50% less memory to store the neural network model parameters without loss of classification accuracy.

9 October 2023 in Research Square
Verified
Preprint
Open access
PDF file
RHRaqibul Hasan
Raqibul Hasan
Memristor crossbar-based neural networks perform parallel operation in the analog domain. Ex-situ training approach needs to program the predetermined resistance values to the memristor crossbar. Because of the stochasticity of the memristor devices, programming a memristor needs to read the device resistance value iteratively. Reading a single memristor in a crossbar (without isolation transistor) is challenging due to the sneak path current. Programming a memristor in a crossbar to either RON or ROFF state is relatively straightforward. A neural network implemented using higher precision weights provides higher classification accuracy compared to a Ternary Neural Network (TNN). This paper demonstrates the implementation of memristor-based neural networks using only the two resistance values (RON, ROFF). We have considered the crossbar scaling limits and proposed a novel technique to implement a large neural network using multiple smaller crossbar arrays. We have proposed novel neuron circuits to achieve higher weight precision. Our experimental result shows that the proposed higher precision synapses are easy to program and provide better classification accuracy compared to a TNN. Proposed technique of implementing a large neural network on memristor crossbar circuits has a slight loss in the classification accuracy compared to the software implementation. But the memristor-based implementation uses only 51.7% of the synapses used in the software implementation.

7 October 2025 in arXiv
Verified
Preprint
Open access
PDF file
OBOlolade Babatunde
Ololade Babatunde
TATomisin Ayodabo
Tomisin Ayodabo
RHRaqibul Hasan
Raqibul Hasan
This study addresses challenges in traditional assignment submission methods used in higher education by introducing and evaluating a customized Git-based submission system. Employing iterative software development and user-centered design methodologies, the system was integrated within a real-world university environment. Empirical evaluation, including usability testing and student feedback, indicated significant improvements in assignment tracking, collaboration, and submission efficiency. Students reported positive experiences using distributed version control workflows, highlighting improved learning outcomes and reduced administrative burden. Challenges related to initial adoption and student learning curves were identified and mitigated through iterative improvements. The proposed system contributes practical insights for integrating distributed version control into educational settings, enhancing both instructor oversight and student engagement in software engineering and related disciplines. Based on our results, the research showed that 85% of instructors found the git based system easier to use, with 84% of students preferring it over traditional methods, as it provides a 38% reduction in time taken for submission and review, while also leading to a 48% reduction in storage requirements.