arXiv subjects

Rehan Ahmed

Publications and source records attributed to Rehan Ahmed.

9 recordsLinked to original sources

arXiv2026

Direction-dependent photo-voltage detection in multifunctional ZnO micro rod/PBTTT-C14 polymer sensor due to gold nanoparticles

A sensor that can detect the direction of the incoming light plays a crucial role in further enhancing the versatility of the multifunction sensors for future applications, where the sensor can read multiple pieces of information, similar to the biological senses, like skin. A hybrid sensor based on an n-type ZnO micro-rod with p-type optically active organic polymer (PBTTT-C14) is developed for low-cost, large-area piezoelectric and optical sensing applications for future artificial electronic skin. The multi-functionality of the device is achieved due to the heterostructure configuration of vertically aligned piezoelectric ZnO micro rod arrays and PBTTT-C14 polymer between two gold electrodes. The deposition of the top gold electrode also led to the formation of two regions where it forms a continuous film and isolated gold particles (Au NPs). The isolated NPs, when activated, has shown surface plasmon resonance (SPR) and F\"orster resonance energy transfer (FRET), which generate a potential opposite to the normal working of the device, depending on the number of excited Au NPs by the incident light. The polarity flipping/opposite potential development can be attributed to the rise in electron density near the top Au contact due to the SPR and FRET mechanism of isolated Au NPs over the PBTTT-C14 which depends on the illumination direction. As a result, direction-dependent photo voltage polarity flipping was realized in the device. The device has produced piezoelectric and direction-dependent photovoltage flipping responses, leading the way for a multifunction sensor that can detect the direction of incident light and touch.

physics.app-ph↗

arXiv2023

Determining the most efficient geometry through simulation study of ZnO nanorods for the development of high-performance tactile sensors and energy harvesting devices

The piezoelectric nanomaterial ZnO exhibits an excellent piezoelectric response that can transduce mechanical energy into electrical signals by applying pressure. The piezoelectric behavior of ZnO nanostructures (especially nanorods or microrods) is getting considerable attention in the fabrications of piezo tactile sensors, energy harvesting devices, and other self-powering implantable devices. Especially vertically aligned ZnO nanorods are of high interest due to their higher value of piezoelectric coefficient along the z-direction. In this report, various geometries and alignments of ZnO nanorods are explored and their effect on strength of piezoelectric output potential has been simulated by COMSOL Multiphysics software. Best suited geometry and inclination are explored in this simulation to achieve high piezoelectric output in haptic and energy harvester devices. The simulation results show out of many geometries and inclinations the highest piezoelectric output is demonstrated by the inclined ZnO nanorods due to the application of higher torque force or shear stress in similar applied force. The high torque force or shear stress at 60 degree orientation and optimized contributions from all the piezoelectric coefficients resulted in a high piezoelectric output potential close to 215 mV which is much higher than the vertically aligned ZnO nanorod which is approximately 25 mV. The results are contrary to the accepted understanding that the vertical ZnO nanorods should produce the highest output voltage due to the high piezoelectric coefficient along the z-axis.

physics.app-ph↗

arXiv2022

Bayesian Optimization for Macro Placement

Macro placement is the problem of placing memory blocks on a chip canvas. It can be formulated as a combinatorial optimization problem over sequence pairs, a representation which describes the relative positions of macros. Solving this problem is particularly challenging since the objective function is expensive to evaluate. In this paper, we develop a novel approach to macro placement using Bayesian optimization (BO) over sequence pairs. BO is a machine learning technique that uses a probabilistic surrogate model and an acquisition function that balances exploration and exploitation to efficiently optimize a black-box objective function. BO is more sample-efficient than reinforcement learning and therefore can be used with more realistic objectives. Additionally, the ability to learn from data and adapt the algorithm to the objective function makes BO an appealing alternative to other black-box optimization methods such as simulated annealing, which relies on problem-dependent heuristics and parameter-tuning. We benchmark our algorithm on the fixed-outline macro placement problem with the half-perimeter wire length objective and demonstrate competitive performance.

cs.LG↗

arXiv2022

Bias and Fairness on Multimodal Emotion Detection Algorithms

Numerous studies have shown that machine learning algorithms can latch onto protected attributes such as race and gender and generate predictions that systematically discriminate against one or more groups. To date the majority of bias and fairness research has been on unimodal models. In this work, we explore the biases that exist in emotion recognition systems in relationship to the modalities utilized, and study how multimodal approaches affect system bias and fairness. We consider audio, text, and video modalities, as well as all possible multimodal combinations of those, and find that text alone has the least bias, and accounts for the majority of the models' performances, raising doubts about the worthiness of multimodal emotion recognition systems when bias and fairness are desired alongside model performance.

cs.LG↗

arXiv2021

Deep Learning for EEG Seizure Detection in Preterm Infants

EEG is the gold standard for seizure detection in the newborn infant, but EEG interpretation in the preterm group is particularly challenging; trained experts are scarce and the task of interpreting EEG in real-time is arduous. Preterm infants are reported to have a higher incidence of seizures compared to term infants. Preterm EEG morphology differs from that of term infants, which implies that seizure detection algorithms trained on term EEG may not be appropriate. The task of developing preterm specific algorithms becomes extra-challenging given the limited amount of annotated preterm EEG data available. This paper explores novel deep learning (DL) architectures for the task of neonatal seizure detection in preterm infants. The study tests and compares several approaches to address the problem: training on data from full-term infants; training on data from preterm infants; training on age-specific preterm data and transfer learning. The system performance is assessed on a large database of continuous EEG recordings of 575h in duration. It is shown that the accuracy of a validated term-trained EEG seizure detection algorithm, based on a support vector machine classifier, when tested on preterm infants falls well short of the performance achieved for full-term infants. An AUC of 88.3% was obtained when tested on preterm EEG as compared to 96.6% obtained when tested on term EEG. When re-trained on preterm EEG, the performance marginally increases to 89.7%. An alternative DL approach shows a more stable trend when tested on the preterm cohort, starting with an AUC of 93.3% for the term-trained algorithm and reaching 95.0% by transfer learning from the term model using available preterm data.

eess.SP↗

arXiv2020

SSCNets: Robustifying DNNs using Secure Selective Convolutional Filters

In this paper, we introduce a novel technique based on the Secure Selective Convolutional (SSC) techniques in the training loop that increases the robustness of a given DNN by allowing it to learn the data distribution based on the important edges in the input image. We validate our technique on Convolutional DNNs against the state-of-the-art attacks from the open-source Cleverhans library using the MNIST, the CIFAR-10, and the CIFAR-100 datasets. Our experimental results show that the attack success rate, as well as the imperceptibility of the adversarial images, can be significantly reduced by adding effective pre-processing functions, i.e., Sobel filtering.

cs.LG↗

arXiv2020

QuSecNets: Quantization-based Defense Mechanism for Securing Deep Neural Network against Adversarial Attacks

Adversarial examples have emerged as a significant threat to machine learning algorithms, especially to the convolutional neural networks (CNNs). In this paper, we propose two quantization-based defense mechanisms, Constant Quantization (CQ) and Trainable Quantization (TQ), to increase the robustness of CNNs against adversarial examples. CQ quantizes input pixel intensities based on a "fixed" number of quantization levels, while in TQ, the quantization levels are "iteratively learned during the training phase", thereby providing a stronger defense mechanism. We apply the proposed techniques on undefended CNNs against different state-of-the-art adversarial attacks from the open-source \textit{Cleverhans} library. The experimental results demonstrate 50%-96% and 10%-50% increase in the classification accuracy of the perturbed images generated from the MNIST and the CIFAR-10 datasets, respectively, on commonly used CNN (Conv2D(64, 8x8) - Conv2D(128, 6x6) - Conv2D(128, 5x5) - Dense(10) - Softmax()) available in \textit{Cleverhans} library.

cs.LG↗

arXiv2020

TrISec: Training Data-Unaware Imperceptible Security Attacks on Deep Neural Networks

Most of the data manipulation attacks on deep neural networks (DNNs) during the training stage introduce a perceptible noise that can be catered by preprocessing during inference or can be identified during the validation phase. Therefore, data poisoning attacks during inference (e.g., adversarial attacks) are becoming more popular. However, many of them do not consider the imperceptibility factor in their optimization algorithms, and can be detected by correlation and structural similarity analysis, or noticeable (e.g., by humans) in a multi-level security system. Moreover, the majority of the inference attack relies on some knowledge about the training dataset. In this paper, we propose a novel methodology which automatically generates imperceptible attack images by using the back-propagation algorithm on pre-trained DNNs, without requiring any information about the training dataset (i.e., completely training data-unaware). We present a case study on traffic sign detection using the VGGNet trained on the German Traffic Sign Recognition Benchmarks dataset in an autonomous driving use case. Our results demonstrate that the generated attack images successfully perform misclassification while remaining imperceptible in both "subjective" and "objective" quality tests.

cs.LG↗

arXiv2019

RED-Attack: Resource Efficient Decision based Attack for Machine Learning

Due to data dependency and model leakage properties, Deep Neural Networks (DNNs) exhibit several security vulnerabilities. Several security attacks exploited them but most of them require the output probability vector. These attacks can be mitigated by concealing the output probability vector. To address this limitation, decision-based attacks have been proposed which can estimate the model but they require several thousand queries to generate a single untargeted attack image. However, in real-time attacks, resources and attack time are very crucial parameters. Therefore, in resource-constrained systems, e.g., autonomous vehicles where an untargeted attack can have a catastrophic effect, these attacks may not work efficiently. To address this limitation, we propose a resource efficient decision-based methodology which generates the imperceptible attack, i.e., the RED-Attack, for a given black-box model. The proposed methodology follows two main steps to generate the imperceptible attack, i.e., classification boundary estimation and adversarial noise optimization. Firstly, we propose a half-interval search-based algorithm for estimating a sample on the classification boundary using a target image and a randomly selected image from another class. Secondly, we propose an optimization algorithm which first, introduces a small perturbation in some randomly selected pixels of the estimated sample. Then to ensure imperceptibility, it optimizes the distance between the perturbed and target samples. For illustration, we evaluate it for CFAR-10 and German Traffic Sign Recognition (GTSR) using state-of-the-art networks.

cs.CR↗