Neurons in a Spiking Neural Network (SNN) communicate using electrical pulses or spikes. They fire or trigger conditionally, and learning is sensitive to such triggers' timing and duration. The Leaky Integrate and Fire (LIF) model is the most widely used SNN neuron model. Most existing LIF-based neurons use a fixed spike frequency, which prevents them from attaining near-optimal accuracy. A research challenge is to design energy and area-efficient SNN neural cells that provide high learning accuracy and are scalable. Recently, the idea of tuning the spiking pulses in SNN was proposed and found promising. This work builds on the pulse-tuning idea by proposing an area and energy-efficient, stable, and reconfigurable SNN cell that generates spikes and reconfigures its pulse width to achieve near-optimal learning. It auto-adapts spike rate and duration to attain near-optimal accuracies for various SNN applications. The …

This paper presents a lightweight hybrid random number generator (HRNG), implemented and evaluated on a Field-Programmable Gate Array (FPGA). The proposed design enhances security and randomness by synergizing jitter and metastability using a feedforward topology, which achieves a near-perfect Shannon entropy. Moreover, it is validated using three distinct entropy metrics, guaranteeing statistically robust random numbers for security-sensitive applications. In addition to entropy evaluations, this design is also rigorously analyzed using multiple industry-standard randomness test suites. Beyond the FPGA implementation, this work presents performance metrics, including area utilization, power consumption, maximum frequency, and energy usage per random bit, which are synthesized across three different technology nodes in Synopsys Design Compiler (SDC). All of the results from the FPGA and the …

In recent years, the automotive industry has experienced a digital revolution, with vehicles increasingly equipped with computer systems, transitioning from purely mechanical machines to sophisticated autonomous entities. This evolution extends beyond individual vehicles to encompass Intelligent Transportation Systems (ITS), fundamentally altering transportation networks. While these advancements promise enhanced efficiency, safety, and travel experience, they also introduce new challenges, particularly in security and privacy. For example, AI-based systems are now used for real-time congestion prediction, allowing for optimized traffic flow; and predictive car maintenance, minimizing breakdowns and enhancing safety. However, these systems can be vulnerable to cyberattacks and data breaches. Integrating diverse technologies into transportation systems offers undeniable benefits, but it also has …

Hardware implementation of neural networks (NNs) is challenging due to varying application requirements. This often necessitates creating specific field programmable gate arrays (FPGAs) configurations from scratch for each application. This article proposes a flexible, self-supervised reconfigurable method to fit several application requirements by providing only the maximum available computational nodes a priori. The proposed method dynamically reconfigures the required number of hidden layers and nodes based on the application. The goal is to automatically determine the optimal NN configuration through reconfigurability to achieve maximum accuracy. Optimality is demonstrated through minimum average power, average delay, and area overhead, as well as maximum throughput and accuracy. Experimental results show that the proposed approach significantly reduces the optimized architecture search …

The Internet of Things (IoT) is a transformative technology facilitating seamless communication between diverse devices and systems, including resource-constrained devices. Speed efficiency and energy efficiency in communication protocols for IoT devices are crucial. The constrained application protocol (CoAP) is a promising, lightweight, and efficient protocol for IoT, offering robust messaging capabilities while conserving resources. An emerging research focus and challenge is designing hardware accelerators for CoAP that are fast, energy-efficient, and reliable. This article addresses that research challenge by proposing a CoAP hardware accelerator for optimizing message processing in resource-constrained IoT environments. The proposed accelerator’s architecture uses virtual channels (VCs) to manage incoming message traffic efficiently, enabling concurrent processing and enhancing throughput capacity.

Epilepsy triggers seizures, which develop before clinical onset in patients, and a timely and accurate prediction can save lives. A research challenge is to design accurate, fast, and energy-efficient hardware predictors. This work advances hardware-based seizure prediction research by proposing a new machine-learning-based predictor. It proposes a novel reconfigurable electroencephalogram (EEG) signal segmentation for increased learning. The proposed reconfigurable segmentation adaptively adjusts the overlap extent between consecutive segments and prepares new segments. Such prepared segments are fed into a Convolutional Auto-Encoder (CAE) using a proposed convolution module. The proposed convolution module uses optimized hyperparameters, including the number of layers, filters, filter size, pooling method, stride value, and padding for high learning and feature extraction. The learned CAE …

Due to technological advancement, the advent of smart cities has facilitated the deployment of advanced urban management systems. This integration has been made possible through the Internet of Vehicles (IoV), a foundational technology. By connecting smart cities with vehicles, the IoV enhances the safety and efficiency of transportation. This interconnected system facilitates wireless communication among vehicles, enabling the exchange of crucial traffic information. However, this significant technological advancement also raises concerns regarding privacy for individual users. This paper presents an innovative privacy-preserving authentication scheme focusing on IoV using physical unclonable functions (PUFs). This scheme employs the k-nearest neighbor (KNN) encryption technique, which possesses a multi-multi searching property. The main objective of this scheme is to authenticate autonomous vehicles (AVs) within the IoV framework. An innovative PUF design is applied to generate random keys for our authentication scheme to enhance security. This two-layer security approach protects against various cyber-attacks, including fraudulent identities, man-in-the-middle attacks, and unauthorized access to individual user information. Due to the substantial amount of information that needs to be processed for authentication purposes, our scheme is implemented using hardware acceleration on an Nexys A7-100T FPGA board. Our analysis of privacy and security illustrates the effective accomplishment of specified design goals. Furthermore, the performance analysis reveals that our approach imposes a minimal communication and …

Alzheimer’s Disease (AD), the prevailing form of dementia, is a neurological condition that significantly impacts individuals globally, leading to devastating effects. The early detection of AD is of paramount importance in mitigating its impact. Numerous methodologies have been suggested for diagnosing AD through medical imaging techniques such as positron emission tomography (PET) and magnetic resonance imaging (MRI). Nevertheless, it is anticipated that utilizing blood biomarkers would enhance the identification of individuals with AD and cognitive impairments. This paper introduces an innovative distributed deep-learning methodology for the early identification of AD through the analysis of blood samples. This study aims to investigate the application of federated learning (FL) in the analysis of blood samples to predict the likelihood of getting AD. Our study employed a dataset of many blood …

Electrical stimulation of neuromuscular tissues has been proven to treat many spinal cord injury-related clinical disorders, such as motor function restoration, epilepsy treatment, and other biomedical applications. Implantable electrical stimulators have emerged as promising solutions for long-term therapeutic and scientific biomedical purposes. However, designing such stimulators presents many challenges. This paper introduces an integrated circuit for an implantable electrical stimulator with high stimulation efficiency and a small on-chip area of 0.0833 mm 2. The device is capable of delivering a programmable stimulation current of up to 800 μ A to a load impedance of 2.5 k Ω while maintaining linearity. A power efficiency of 75.15% was achieved. The stimulator can deliver higher currents when connected to lower load impedances.

Glass fiber-reinforced plastics are an important composite material in the marine, automotive, and military industries due to their excellent mechanical properties, such as high strength, corrosion resistance and lightweight. This study aims to determine the effect of the number of glass fiber layers on the hardness of glass fiber/polyester composite materials. Random chopped strand mat glass fibers with a mass per unit area of ​​450 g/m² were used to prepare samples using the hand layup technique. The number of layers varied between 3 to 6 layers. The thickness of all samples is 3 mm. The Vickers microhardness device is used to measure the hardness, with a load of 50 g applied for a dwell time of 15 s. The results indicated that when increasing the number of glass fiber layers decreases the hardness values. The sample of three-layer listed the highest hardness value of 14.34 HV, while the values ​​for the four-layer sample decreased to 11.42 HV, the five-layer sample to 9.72 HV, and the six-layer sample had the lowest value of 7.7 HV. This decrease in hardness is attributed to the increased number of interfaces between layers, which may lead to the appearance of weak points or air voids that affect the mechanical properties of the composite material.