Searcharxiv⌕ Search

arXiv subjects

Imtiaz Ahmed

Publications and source records attributed to Imtiaz Ahmed.

At least 55 records · Page 3Linked to original sources
arXiv2023

Applications of Federated Learning in Manufacturing: Identifying the Challenges and Exploring the Future Directions with Industry 4.0 and 5.0 Visions

In manufacturing settings, data collection and analysis are often a time-consuming, challenging, and costly process. It also hinders the use of advanced machine learning and data-driven methods which require a substantial amount of offline training data to generate good results. It is particularly challenging for small manufacturers who do not share the resources of a large enterprise. Recently, with the introduction of the Internet of Things (IoT), data can be collected in an integrated manner across the factory in real-time, sent to the cloud for advanced analysis, and used to update the machine learning model sequentially. Nevertheless, small manufacturers face two obstacles in reaping the benefits of IoT: they may be unable to afford or generate enough data to operate a private cloud, and they may be hesitant to share their raw data with a public cloud. Federated learning (FL) is an emerging concept of collaborative learning that can help small-scale industries address these issues and learn from each other without sacrificing their privacy. It can bring together diverse and geographically dispersed manufacturers under the same analytics umbrella to create a win-win situation. However, the widespread adoption of FL across multiple manufacturing organizations remains a significant challenge. This study aims to review the challenges and future directions of applying federated learning in the manufacturing industry, with a specific emphasis on the perspectives of Industry 4.0 and 5.0.

cs.LG↗
arXiv2023

A Data Driven Sequential Learning Framework to Accelerate and Optimize Multi-Objective Manufacturing Decisions

Manufacturing advanced materials and products with a specific property or combination of properties is often warranted. To achieve that it is crucial to find out the optimum recipe or processing conditions that can generate the ideal combination of these properties. Most of the time, a sufficient number of experiments are needed to generate a Pareto front. However, manufacturing experiments are usually costly and even conducting a single experiment can be a time-consuming process. So, it's critical to determine the optimal location for data collection to gain the most comprehensive understanding of the process. Sequential learning is a promising approach to actively learn from the ongoing experiments, iteratively update the underlying optimization routine, and adapt the data collection process on the go. This paper presents a novel data-driven Bayesian optimization framework that utilizes sequential learning to efficiently optimize complex systems with multiple conflicting objectives. Additionally, this paper proposes a novel metric for evaluating multi-objective data-driven optimization approaches. This metric considers both the quality of the Pareto front and the amount of data used to generate it. The proposed framework is particularly beneficial in practical applications where acquiring data can be expensive and resource intensive. To demonstrate the effectiveness of the proposed algorithm and metric, the algorithm is evaluated on a manufacturing dataset. The results indicate that the proposed algorithm can achieve the actual Pareto front while processing significantly less data. It implies that the proposed data-driven framework can lead to similar manufacturing decisions with reduced costs and time.

cs.LG↗
arXiv2023

Chatbots and ChatGPT: A Bibliometric Analysis and Systematic Review of Publications in Web of Science and Scopus Databases

This paper presents a bibliometric analysis of the scientific literature related to chatbots, focusing specifically on ChatGPT. Chatbots have gained increasing attention recently, with an annual growth rate of 19.16% and 27.19% on the Web of Sciences (WoS) and Scopus, respectively. In this study, we have explored the structure, conceptual evolution, and trends in this field by analyzing data from both Scopus and WoS databases. The research consists of two study phases: (i) an analysis of chatbot literature and (ii) a comprehensive review of scientific documents on ChatGPT. In the first phase, a bibliometric analysis is conducted on all published literature, including articles, book chapters, conference papers, and reviews on chatbots from both Scopus (5839) and WoS (2531) databases covering the period from 1998 to 2023. An in-depth analysis focusing on sources, countries, authors' impact, and keywords has revealed that ChatGPT is the latest trend in the chatbot field. Consequently, in the second phase, bibliometric analysis has been carried out on ChatGPT publications, and 45 published studies have been analyzed thoroughly based on their methods, novelty, and conclusions. The key areas of interest identified from the study can be classified into three groups: artificial intelligence and related technologies, design and evaluation of conversational agents, and digital technologies and mental health. Overall, the study aims to provide guidelines for researchers to conduct their research more effectively in the field of chatbots and specifically highlight significant areas for future investigation into ChatGPT.

cs.DL↗
arXiv2023

Multi model LSTM architecture for Track Association based on Automatic Identification System Data

For decades, track association has been a challenging problem in marine surveillance, which involves the identification and association of vessel observations over time. However, the Automatic Identification System (AIS) has provided a new opportunity for researchers to tackle this problem by offering a large database of dynamic and geo-spatial information of marine vessels. With the availability of such large databases, researchers can now develop sophisticated models and algorithms that leverage the increased availability of data to address the track association challenge effectively. Furthermore, with the advent of deep learning, track association can now be approached as a data-intensive problem. In this study, we propose a Long Short-Term Memory (LSTM) based multi-model framework for track association. LSTM is a recurrent neural network architecture that is capable of processing multivariate temporal data collected over time in a sequential manner, enabling it to predict current vessel locations from historical observations. Based on these predictions, a geodesic distance based similarity metric is then utilized to associate the unclassified observations to their true tracks (vessels). We evaluate the performance of our approach using standard performance metrics, such as precision, recall, and F1 score, which provide a comprehensive summary of the accuracy of the proposed framework.

cs.LG↗
arXiv2023

Phase-field Simulations of Polarization Variations in Polycrystalline Hf0.5Zr0.5O2 based MFIM: Voltage-Dependence and Dynamics

In this work, we investigate the device-to-device variations in remanent polarization of Hafnium-Zirconium-Oxide based Metal-Ferroelectric-Insulator-Metal (MFIM) stacks. We consider the effects of polycrystallinity in conjunction with multi-domain effects in HZO to understand the dependencies of variations on static and dynamic voltage stimuli using our 3D dynamic multi-grain phase-field simulation framework. We examine the trends in variations due to various design factors - set voltage, pulse amplitude and pulse width and correlate them to the dynamics of polarization switching and the underlying mechanisms. According to our analysis, variations exhibit a non-monotonic dependence on set voltage due to the interplay between voltage-dependent switching mechanisms and the polycrystalline structure. We further report that towards the higher end of the set voltages, collapsing of oppositely polarized domains can lead to increase in variations. We also show that ferroelectric thickness scaling lowers the device-to-device variations. In addition, considering the dynamics of polarization switching, we signify the key role of voltage and temporal dependence of domain nucleation in dictating the trends in variations. Finally, we show that to reach a target mean polarization, using a pulse with lower amplitude for longer duration results in lower variations compared to higher amplitude pulse for a shorter duration.

physics.comp-ph↗
arXiv2023

A Bi-LSTM Autoencoder Framework for Anomaly Detection -- A Case Study of a Wind Power Dataset

Anomalies refer to data points or events that deviate from normal and homogeneous events, which can include fraudulent activities, network infiltrations, equipment malfunctions, process changes, or other significant but infrequent events. Prompt detection of such events can prevent potential losses in terms of finances, information, and human resources. With the advancement of computational capabilities and the availability of large datasets, anomaly detection has become a major area of research. Among these, anomaly detection in time series has gained more attention recently due to the added complexity imposed by the time dimension. This study presents a novel framework for time series anomaly detection using a combination of Bidirectional Long Short Term Memory (Bi-LSTM) architecture and Autoencoder. The Bi-LSTM network, which comprises two unidirectional LSTM networks, can analyze the time series data from both directions and thus effectively discover the long-term dependencies hidden in the sequential data. Meanwhile, the Autoencoder mechanism helps to establish the optimal threshold beyond which an event can be classified as an anomaly. To demonstrate the effectiveness of the proposed framework, it is applied to a real-world multivariate time series dataset collected from a wind farm. The Bi-LSTM Autoencoder model achieved a classification accuracy of 96.79% and outperformed more commonly used LSTM Autoencoder models.

cs.LG↗
arXiv2023

Wireless Sensor Networks anomaly detection using Machine Learning: A Survey

Wireless Sensor Networks (WSNs) have become increasingly valuable in various civil/military applications like industrial process control, civil engineering applications such as buildings structural strength monitoring, environmental monitoring, border intrusion, IoT (Internet of Things), and healthcare. However, the sensed data generated by WSNs is often noisy and unreliable, making it a challenge to detect and diagnose anomalies. Machine learning (ML) techniques have been widely used to address this problem by detecting and identifying unusual patterns in the sensed data. This survey paper provides an overview of the state of the art applications of ML techniques for data anomaly detection in WSN domains. We first introduce the characteristics of WSNs and the challenges of anomaly detection in WSNs. Then, we review various ML techniques such as supervised, unsupervised, and semi-supervised learning that have been applied to WSN data anomaly detection. We also compare different ML-based approaches and their performance evaluation metrics. Finally, we discuss open research challenges and future directions for applying ML techniques in WSNs sensed data anomaly detection.

cs.LG↗
arXiv2023

Android Malware Detection using Machine learning: A Review

Malware for Android is becoming increasingly dangerous to the safety of mobile devices and the data they hold. Although machine learning(ML) techniques have been shown to be effective at detecting malware for Android, a comprehensive analysis of the methods used is required. We review the current state of Android malware detection us ing machine learning in this paper. We begin by providing an overview of Android malware and the security issues it causes. Then, we look at the various supervised, unsupervised, and deep learning machine learning approaches that have been utilized for Android malware detection. Addi tionally, we present a comparison of the performance of various Android malware detection methods and talk about the performance evaluation metrics that are utilized to evaluate their efficacy. Finally, we draw atten tion to the drawbacks and difficulties of the methods that are currently in use and suggest possible future directions for research in this area. In addition to providing insights into the current state of Android malware detection using machine learning, our review provides a comprehensive overview of the subject.

cs.CR↗
arXiv2023

Guiding the Sequential Experiments in Autonomous Experimentation Platforms through EI-based Bayesian Optimization and Bayesian Model Averaging

Autonomous Experimentation Platforms (AEPs) are advanced manufacturing platforms that, under intelligent control, can sequentially search the material design space (MDS) and identify parameters with the desired properties. At the heart of the intelligent control of these AEPs is the policy guiding the sequential experiments, which is to choose the location to carry out the next experiment. In such cases, a balance between exploitation and exploration must be achieved. A Bayesian Optimization (BO) framework with Expected Improvement based (EI-based) acquisition function can effectively search the MDS and guide where to conduct the next experiments so that the underlying relationship can be identified with a smaller number of experiments. The traditional BO framework tries to optimize a black box objective function in a sequential manner by relying on a single model. However, this single-model approach does not account for model uncertainty. Bayesian Model Averaging (BMA) addresses this issue by working with multiple models and thus considering the uncertainty in the models. In this work, we first apply the conventional BO algorithm with the most popular EI-based experiment policy in a real-life fatigue dataset for steel to predict the fatigue strength of steel. Afterward, we apply BMA to the same dataset by working with a set of predictive models and compare the performance of BMA with the traditional BO algorithm, which relies on a single model for approximation. We compare the results in terms of RMSE and find that BMA performs better than EI-based BO in the prediction task by considering the model uncertainty in its framework.

cs.LG↗
arXiv2022

Super-High-Frequency Low-Loss Sezawa Mode SAW Devices in a GaN/SiC Platform

This paper presents a comprehensive study of the performance of Sezawa surface acoustic wave (SAW) devices in SweGaN QuanFINE ultrathin GaN/SiC platform, reaching frequencies above 14 GHz for the first time. Sezawa mode frequency scaling is achieved due to the elimination of the thick buffer layer typically present in epitaxial GaN technology. Finite element analysis (FEA) is first performed to find the range of frequencies over which the Sezawa mode is supported in the grown structure. Transmission lines and resonance cavities driven with Interdigital Transducers (IDTs) are designed, fabricated, and characterized. Modified Mason circuit models are developed for each class of devices to extract critical performance metrics. We observe a strong correlation between measured and simulated dispersion of the phase velocity (vp) and piezoelectric coupling coefficient (k^2). Maximum k^2 of 0.61% and frequency-quality factor product (f.Qm) of 6x10^12 1/s are achieved for Sezawa resonators at 11 GHz, with a minimum propagation loss of 0.26 dB/wavelength for the two-port devices. Sezawa modes are observed at frequencies spanning up to 14.3 GHz, achieving a record high in GaN microelectromechanical systems (MEMS) to the best of the authors' knowledge.

physics.app-ph↗
arXiv2022

A Spatio-temporal Track Association Algorithm Based on Marine Vessel Automatic Identification System Data

Tracking multiple moving objects in real-time in a dynamic threat environment is an important element in national security and surveillance system. It helps pinpoint and distinguish potential candidates posing threats from other normal objects and monitor the anomalous trajectories until intervention. To locate the anomalous pattern of movements, one needs to have an accurate data association algorithm that can associate the sequential observations of locations and motion with the underlying moving objects, and therefore, build the trajectories of the objects as the objects are moving. In this work, we develop a spatio-temporal approach for tracking maritime vessels as the vessel's location and motion observations are collected by an Automatic Identification System. The proposed approach is developed as an effort to address a data association challenge in which the number of vessels as well as the vessel identification are purposely withheld and time gaps are created in the datasets to mimic the real-life operational complexities under a threat environment. Three training datasets and five test sets are provided in the challenge and a set of quantitative performance metrics is devised by the data challenge organizer for evaluating and comparing resulting methods developed by participants. When our proposed track association algorithm is applied to the five test sets, the algorithm scores a very competitive performance.

cs.LG↗
arXiv2021

Room temperature ferroic orders in Zr and (Zr, Ni) doped SrTiO$_3$

We synthesized strontium titanate SrTiO$_3$ (STO), Zr doped $\text{Sr}_\text{1-x}\text{Zr}_\text{x}\text{Ti}\text{O}_3$ and (Zr, Ni) co-doped $\text{Sr}_\text{1-x}\text{Zr}_\text{x}\text{Ti}_\text{1-y}\text{Ni}_\text{y}\text{O}_3$ samples using solid state reaction technique to report their structural, electrical and magnetic properties. The cubic $Pm$-$3m$ phase of the synthesized samples has been confirmed using Rietveld analysis of the powder X-ray diffraction pattern. The grain size of the synthesized materials was reduced significantly due to Zr doping as well as (Zr, Ni) co-doping in STO. The chemical species of the samples were identified using energy-dispersive X-ray spectroscopy. We observed forbidden first order Raman scattering at 148, 547 and 797 cm$^{-1}$ which may indicate nominal loss of inversion symmetry in cubic STO. The absence of absorption at 500 cm$^{-1}$ and within 600-700 cm$^{-1}$ band in Fourier Transform Infrared spectra corroborates Zr and Ni as substitutional dopants in our samples. Due to 4% Zr doping in $\text{Sr}_\text{0.96}\text{Zr}_\text{0.04}\text{Ti}\text{O}_3$ sample dielectric constant, remnant electric polarization, remnant magnetization and coercivity were increased. Notably, in the case of 4% Zr and 10% Ni co-doping we have observed clearly the existence of both FE and FM hysteresis loops in $\text{Sr}_{0.96}\text{Zr}_{0.04}\text{Ti}_{0.90}\text{Ni}_{0.10}\text{O}_3$ sample. In this co-doped sample, the remnant magnetization and coercivity were increased by $\sim$1 and $\sim$2 orders of magnitude respectively as compared to those of undoped STO. The coexistence of FE and FM orders in (Zr, Ni) co-doped STO might have the potential for interesting multiferroic applications.

cond-mat.mtrl-sci↗
arXiv2021

Graph Regularized Autoencoder and its Application in Unsupervised Anomaly Detection

Dimensionality reduction is a crucial first step for many unsupervised learning tasks including anomaly detection and clustering. Autoencoder is a popular mechanism to accomplish dimensionality reduction. In order to make dimensionality reduction effective for high-dimensional data embedding nonlinear low-dimensional manifold, it is understood that some sort of geodesic distance metric should be used to discriminate the data samples. Inspired by the success of geodesic distance approximators such as ISOMAP, we propose to use a minimum spanning tree (MST), a graph-based algorithm, to approximate the local neighborhood structure and generate structure-preserving distances among data points. We use this MST-based distance metric to replace the Euclidean distance metric in the embedding function of autoencoders and develop a new graph regularized autoencoder, which outperforms a wide range of alternative methods over 20 benchmark anomaly detection datasets. We further incorporate the MST regularizer into two generative adversarial networks and find that using the MST regularizer improves the performance of anomaly detection substantially for both generative adversarial networks. We also test our MST regularized autoencoder on two datasets in a clustering application and witness its superior performance as well.

cs.LG↗
arXiv2021

Neighborhood Structure Assisted Non-negative Matrix Factorization and its Application in Unsupervised Point-wise Anomaly Detection

Dimensionality reduction is considered as an important step for ensuring competitive performance in unsupervised learning such as anomaly detection. Non-negative matrix factorization (NMF) is a popular and widely used method to accomplish this goal. But NMF do not have the provision to include the neighborhood structure information and, as a result, may fail to provide satisfactory performance in presence of nonlinear manifold structure. To address that shortcoming, we propose to consider and incorporate the neighborhood structural similarity information within the NMF framework by modeling the data through a minimum spanning tree. We label the resulting method as the neighborhood structure assisted NMF. We further devise both offline and online algorithmic versions of the proposed method. Empirical comparisons using twenty benchmark datasets as well as an industrial dataset extracted from a hydropower plant demonstrate the superiority of the neighborhood structure assisted NMF and support our claim of merit. Looking closer into the formulation and properties of the neighborhood structure assisted NMF with other recent, enhanced versions of NMF reveals that inclusion of the neighborhood structure information using MST plays a key role in attaining the enhanced performance in anomaly detection.

cs.LG↗
arXiv2020

Structural, Elastic and Electronic Properties of $SmFeO_3$ using Density Functional Theory

We perform first principles simulations for the structural, elastic and electronic properties of orthorhombic samarium orthoferrite $SmFeO_3$ within the framework of density functional theory. A number of different density functionals, such as local density approximation, generalized gradient approximation, Hubbard interaction modified functional, modified Becke$-$Johnson approximation and Heyd$-$Scuseria$-$Ernzerhof hybrid functional have been used to model the exact electron exchange-correlation. We estimate the energy of the ground state for different magnetic configurations of $SmFeO_3$. The crystal structure of $SmFeO_3$ is characterized in terms of the lattice parameters, atomic positions, relevant ionic radii, bond lengths and bond angles. The stability of the $SmFeO_3$ orthorhombic structure is simulated in terms of its elastic properties. For the electronic structure simulations, we provide estimates based on density functionals with varying degrees of computational complexities in the Jacob's ladder.

cond-mat.mtrl-sci↗
arXiv2018

Electric-field tuning of the valley splitting in silicon corner dots

We perform an excited state spectroscopy analysis of a silicon corner dot in a nanowire field-effect transistor to assess the electric field tunability of the valley splitting. First, we demonstrate a back-gate-controlled transition between a single quantum dot and a double quantum dot in parallel that allows tuning the device in to corner dot formation. We find a linear dependence of the valley splitting on back-gate voltage, from $880~μ\text{eV}$ to $610~μ\text{eV}$ with a slope of $-45\pm 3~μ\text{eV/V}$ (or equivalently a slope of $-48\pm 3~μ\text{eV/(MV/m)}$ with respect to the effective field). The experimental results are backed up by tight-binding simulations that include the effect of surface roughness, remote charges in the gate stack and discrete dopants in the channel. Our results demonstrate a way to electrically tune the valley splitting in silicon-on-insulator-based quantum dots, a requirement to achieve all-electrical manipulation of silicon spin qubits.

cond-mat.mes-hall↗
arXiv2018

Primary thermometry of a single reservoir using cyclic electron tunneling in a CMOS transistor

Temperature is a fundamental parameter in the study of physical phenomena. At the nanoscale, local temperature differences can be harnessed to design novel thermal nanoelectronic devices or test quantum thermodynamical concepts. Determining temperature locally is hence of particular relevance. Here, we present a primary electron thermometer that allows probing the local temperature of a single electron reservoir in single-electron devices. The thermometer is based on cyclic electron tunneling between a system with discrete energy levels and a single electron reservoir. When driven at a finite rate, close to a charge degeneracy point, the system behaves like a variable capacitor whose magnitude and line-shape varies with temperature. In this experiment, we demonstrate this type of thermometer using a quantum dot in a CMOS nanowire transistor. We drive cyclic electron tunneling by embedding the device in a radio-frequency resonator which in turn allows us to read the thermometer dispersively. We find that the full width at half maximum of the resonator phase response depends linearly with temperature via well known physical law by using the ratio $k_\text{B}/e$ between the Boltzmann constant and the electron charge. Overall, the thermometer shows potential for local probing of fast heat dynamics in nanoelectronic devices and for seamless integration with silicon-based quantum circuits.

cond-mat.mes-hall↗
arXiv2018

A Physically based compact I-V model for monolayer TMDC channel MOSFET and DMFET biosensor

In this work, a compact transport model has been developed for monolayer transition metal dichalcogenide (TMDC) channel MOSFET. The analytical model solves the Poisson's equation for the inversion charge density to get the electrostatic potential in the channel. Current is then calculated by solving the drift-diffusion equation. The model makes gradual channel approximation to simplify the solution procedure. The appropriate density of states obtained from the first principle density functional theory simulation has been considered to keep the model physically accurate for monolayer TMDC channel FET. The outcome of the model has been benchmarked against both experimental and numerical quantum simulation results with the help of a few fitting parameters. Using the compact model, detailed output and transfer characteristics of monolayer $WSe_2$ FET have been studied, and various performance parameters have been determined. The study confirms excellent ON and OFF state performances of monolayer $WSe_2$ FET which could be viable for the next generation high-speed, low power applications. Also, the proposed model has been extended to study the operation of a biosensor. A monolayer $MoS_2$ channel based dielectric modulated FET is investigated using the compact model for detection of a biomolecule in a dry environment.

cond-mat.mes-hall↗