{"id":2324,"date":"2025-10-18T15:49:41","date_gmt":"2025-10-18T15:49:41","guid":{"rendered":"https:\/\/hafizimtiaz.buet.ac.bd\/?page_id=2324"},"modified":"2026-03-17T14:29:11","modified_gmt":"2026-03-17T14:29:11","slug":"project","status":"publish","type":"page","link":"http:\/\/hafizimtiaz.buet.ac.bd\/index.php\/project\/","title":{"rendered":"Project"},"content":{"rendered":"\t\t
\n\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Below, you can find brief descriptions of some previous projects I completed during my time at Bangladesh University of Engineering and Technology and Rutgers University. You can also find link to the corresponding publication\/presentation.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t \n
\n

\n Research Projects <\/h2>\n \n
\n
\n

\n \n Fault Detection in PV Panels with Neural Networks <\/a>\n <\/h3>\n
\n Photovoltaic (PV) panels can develop many physical faults\u2014like cracks, dirt, shading, or temperature damage\u2014that reduce their power output. Detecting these faults early is important for keeping solar systems efficient. In this work, we present a machine learning method that detects PV faults using unlabeled electroluminescence (EL) images. We first label the images automatically using k\u2011means […] <\/div>\n <\/div>\n
\n

\n \n Generalized Deepfake Image Detection with Spatial and Frequency Domain Features <\/a>\n <\/h3>\n
\n Detecting deepfakes is increasingly important, but it is difficult because deepfakes can be created in many different ways. In the 2025 IEEE Signal Processing Cup, the dataset included many types of deepfake images but had a large imbalance between real and fake samples. To address this, we developed a multistage training approach using CAE\u2011Net, an […] <\/div>\n <\/div>\n
\n

\n \n Privacy-preserving Dataset Synthesis using Randomized Mixing <\/a>\n <\/h3>\n
\n As data grows in areas like healthcare, finance, and security, it offers many benefits but also raises serious privacy concerns because personal identity can often be inferred even from anonymized data. Existing machine\u2011learning and data\u2011sharing methods struggle to protect privacy when dealing with high\u2011dimensional data. To address this, we propose a new data\u2011publishing method called […] <\/div>\n <\/div>\n
\n

\n \n Privacy-preserving recommendation system with Neural Networks <\/a>\n <\/h3>\n
\n Recommendation systems use a lot of user data, which can risk exposing sensitive personal information. Differential privacy can protect users, but when applied to neural\u2011network\u2011based recommenders, it often reduces accuracy\u2014creating a trade\u2011off between privacy and performance. Traditional matrix\u2011factorization ethods struggle to balance this trade\u2011off. In this work, we propose a neural\u2011network\u2011based collaborative filtering model that […] <\/div>\n <\/div>\n
\n

\n \n Electronic band-edge shapes and properties prediction of 2D TMD alloys using ML models <\/a>\n <\/h3>\n
\n We deveeloped fast machine\u2011learning method to predict the full electronic band structure of monolayer TMD alloys, which are usually computed using computationally expensive DFT simulations. Using DFT data for alloys made from W, Mo, and S\/Se\/Te, the researchers trained an \u201cextra trees\u201d model to predict both conduction and valence bands. The model identifies important factors\u2014like […] <\/div>\n <\/div>\n
\n

\n \n Differentially Private Distributed Principal Component Analysis <\/a>\n <\/h3>\n
\n Developed an algorithm for differentially private distributed principal component analysis (PCA). The algorithm provides a way of computing the PCA subspace in a distributed setting, while satisfying differential privacy. PCA subspaces are used in numerous machine learning algorithms as a pre-processing step. This work led to this publication. <\/div>\n <\/div>\n
\n

\n \n Differentially Private Orthogonal Tensor Decomposition <\/a>\n <\/h3>\n
\n Developed an algorithm for differentially private orthogonal tensor decomposition (OTD). The algorithm provides a way of estimating the parameters of latent variable models. Tensor decomposition for such models has been shown to provide much better accuracy than matrix-based methods. This work led to this publication. <\/div>\n <\/div>\n
\n

\n \n Differentially Private Canonical Correlation Analysis <\/a>\n <\/h3>\n
\n Developed an algorithm for differentially private canonical correlation analysis (CCA). The algorithm provides a way of computing the CCA subspaces satisfying differential privacy. CCA subspaces can be used to exploit the maximum correlation between different modalities. This work led to this publication. <\/div>\n <\/div>\n
\n

\n \n Differentially Private Robust Non-negative Matrix Factorization <\/a>\n <\/h3>\n
\n Developed a novel non-negative matrix factorization (NMF) algorithm capable of operating on sensitive data, while closely approximating the results of the non-private algorithm. Additionally, we consider the effect of outliers by specifically modeling them, such that the presence of outliers has very little effect on our estimated differentially-private basis matrix. This theoretical work is also […] <\/div>\n <\/div>\n
\n

\n \n A Novel Functional Mechanism for Decentralized Differentially Private Computations <\/a>\n <\/h3>\n
\n Developed a novel function computation scheme Gaussian Functional mechanism that ensures strict privacy guaratnee and offers much better utility than existing methods. Additionally, we extend our novel mechanism such that it works seemlessly in decentralized-data settings and propose capeFM, which offers the same privacy-utility trade-off as centralized schemes. This theoretical work is also validated on […] <\/div>\n <\/div>\n
\n

\n \n An Efficient Wavelet-based Framework for Human Activity Recognition using WiFi Channel State Information <\/a>\n <\/h3>\n
\n Developed an efficient, novel, and implementation-friendly framework for human activity recognition (HAR) using Channel State Information (CSI) of WiFi signal. The framework employs wavelet-based feature extraction and principal component analysis (PCA) based subcarrier fusion to achieve excellent recognition performance of human activity on multiple real datasets, that include variety of environmental conditions. This work led […] <\/div>\n <\/div>\n
\n

\n \n Work in progress: exploration of multi-modal data geo-spatial data <\/a>\n <\/h3>\n
\n Work in progress: exploration of multi-modal data geo-spatial data for correlation analysis and points-of-interests detection while satisfying privacy. A poster based on preliminary work is found here. <\/div>\n <\/div>\n
\n

\n \n Work in progress: development of algorithms for COINSTAC <\/a>\n <\/h3>\n
\n Work in progress: development of algorithms for the collaborative neuroimaging data analysis tool COINSTAC. It provides an easy-to-use platform for computations on distributed datasets and satisfies privacy. A poster based on explanation of this project is found here. <\/div>\n <\/div>\n
\n

\n \n Differentially private distributed joint Independent Component Analysis (djICA) <\/a>\n <\/h3>\n
\n Developed an algorithm for differentially private distributed joint Independent Component Analysis (djICA). The algorithm provides a way of source separation\/matrix factorization in a distributed setting with fMRI data. This work led to this publication. <\/div>\n <\/div>\n
\n

\n \n Correlated Noise Can Make Decentralized Differentially Private Computations Efficient <\/a>\n <\/h3>\n
\n Developed a novel and robust protocol for decentralized differentially private computations that are common in signal processing and machine learning in decentralized data settings. The protocol achieves the same privacy-utility trade-off in the decentralized data setting by employing a correlated noise scheme. We show the effectiveness of the scheme on a decentralized independent component analysis […] <\/div>\n <\/div>\n
\n

\n \n Decentralized Differentially Private Computations that Match the Pooled-data Scenario <\/a>\n <\/h3>\n
\n Developed a protocol for decentralized differentially private computations that can achieve the same utility as the pooled-data scenario. The protocol employs a correlated noise scheme and does not require a trusted third party. We analytically show that our framework benefits many machine learning and signal processing problems that appear in practice. This work led to […] <\/div>\n <\/div>\n
\n

\n \n Differentially Private Distributed Canonical Correlation Analysis <\/a>\n <\/h3>\n
\n Developed an algorithm for distributed differentially private canonical correlation analysis (CCA). The algorithm provides a way of computing the CCA subspaces satisfying differential privacy in a distributed setting. The primary achievement of this algorithm is to achieve the same utility as the pooled-data scenario in a distributed setting under the honest-but-curious model. This work led […] <\/div>\n <\/div>\n
\n

\n \n Improved Distributed Differentially Private PCA and Orthogonal Tensor Decomposition <\/a>\n <\/h3>\n
\n Developed improved algorithms for distributed differentially private PCA and orthogonal tensor decomposition. These algorithms employ a correlated noise scheme and exploit the “honest-but-curious” network to achieve the same utility as the pooled-data scenario in the distributed setting. This is also the first work for distributed privacy-preserving orthogonal tensor decomposition. This work led to this publication. <\/div>\n <\/div>\n
\n

\n \n Developed an open-source Python library dp-stats <\/a>\n <\/h3>\n
\n Developed an open-source Python library dp-stats for commonly used statistics and machine learning algorithms with differential privacy. Included functions: mean, variance, histogram, Principal Component Analysis (PCA), Support Vector Machine (SVM) and Logistic Regression. It also includes examples in iPython notebook format for each function. A poster based on preliminary work and status of the project […] <\/div>\n <\/div>\n
\n

\n \n A novel method for privacy-preserving non-negative matrix factorization <\/a>\n <\/h3>\n
\n Several matrix factorization algorithms are employed in machine learning applications. Among these, Non-negative Matrix Factorization (NMF) gained attention due to the ability to extract meaningful features from inherently non-negative data, such as documents, images or videos. In this work we propose a novel method and demonstrate our results in such a way that the clients\/data […] <\/div>\n <\/div>\n
\n

\n \n Differentially private human activity recognition using WiFi CSI data <\/a>\n <\/h3>\n
\n Human activity recognition (HAR) is crucial in applications such as smart homes, interactive games, surveillance, security, and healthcare. Channel State Information (CSI) data extracted from Wi-Fi signals has garnered significant interest for applications in HAR. We introduce a Differentially Private Principal Component-based Wavelet Convolutional Neural Network (DP-PCWCNN) that offers accurate and robust HAR performance across […] <\/div>\n <\/div>\n
\n

\n \n Differentially private matrix factorization with applications to recommendation systems <\/a>\n <\/h3>\n
\n Developing differentially private machine learning algorithms typically involve adding randomness into the algorithm pipeline, which evidently degrades the performance of the algorithm\u2014giving raise to privacy-utility trade-off. Existing differentially private matrix factorization algorithms offer poor privacy-utility trade-off for use in practical systems. Motivated by this, we propose two differentially private matrix factorization algorithms for application in […] <\/div>\n <\/div>\n
\n

\n \n A machine learning approach for enhancing the performance of perovskite solar cells <\/a>\n <\/h3>\n
\n Proposed a machine learning-based approach to enhance the performance of perovskite solar cells (PSCs) using carbon nanotubes as both hole transport layer (HTL) and back contact. Carbon-based PSCs offer low fabrication costs, long-term mechanical stability, high charge transport, and broad wavelength transparency. Our study estimates and enhances power conversion efficiency (PCE) of carbon-based PSCs through […] <\/div>\n <\/div>\n
\n

\n \n A light and robust deep neural network for differentially private heart rate estimation from ECG and PPG signals <\/a>\n <\/h3>\n
\n Proposed a computationally-light and robust neural network for estimating heart rate in remote healthcare systems. The model can be trained on consumer-grade graphics processing units (GPUs), and can be deployed on edge devices for swift inference. The proposed hybrid model is based on convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) architectures for […] <\/div>\n <\/div>\n <\/div>\n <\/div>\n \t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t \n
\n

\n Course Projects <\/h2>\n \n
\n
\n

\n \n Phone Number Detection from Dialing Sounds <\/a>\n <\/h3>\n
\n

as a part of the course Digital Signals and Filters.<\/p>\n <\/div>\n <\/div>\n

\n

\n \n STFT Analysis of Bat Sounds <\/a>\n <\/h3>\n
\n

as a part of the course Digital Signals and Filters.<\/p>\n <\/div>\n <\/div>\n

\n

\n \n A Study of Simple and Practical Algorithm for Sparse Fourier Transform <\/a>\n <\/h3>\n
\n

final course project for the course Digital Signals and Filters.<\/p>\n <\/div>\n <\/div>\n

\n

\n \n Analysis of the Performance of a Bank Queue System using Markov Chain <\/a>\n <\/h3>\n
\n

final course project for the course Stochastic Signals and Systems.<\/p>\n <\/div>\n <\/div>\n

\n

\n \n Empirical Comparison of Classification Performance of Differentially-private PCA Algorithms Using SVM <\/a>\n <\/h3>\n
\n

final course project for the course Convex Optimization.<\/p>\n <\/div>\n <\/div>\n

\n

\n \n Implementation and Empirical Comparison of Four Face Recognition Algorithms <\/a>\n <\/h3>\n
\n

as a part of the course Advanced Topics in DSP - Biometrics.<\/p>\n <\/div>\n <\/div>\n

\n

\n \n Empirical Comparison of Sparse Embedding and K-SVD <\/a>\n <\/h3>\n
\n

final course project for the course Advanced Topics in DSP - Biometrics.<\/p>\n <\/div>\n <\/div>\n

\n

\n \n Empirical Comparison of Tensor and Matrix based Methods for Image Classification <\/a>\n <\/h3>\n
\n

final course project for the course Image Coding and Processing.<\/p>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n \t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"

Below, you can find brief descriptions of some previous projects I completed during my time at Bangladesh University of Engineering and Technology and Rutgers University. You can also find link to the corresponding publication\/presentation. Research Projects Fault Detection in PV Panels with Neural Networks Photovoltaic (PV) panels can develop many physical faults\u2014like cracks, dirt, shading, […]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-2324","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"http:\/\/hafizimtiaz.buet.ac.bd\/index.php\/wp-json\/wp\/v2\/pages\/2324","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/hafizimtiaz.buet.ac.bd\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"http:\/\/hafizimtiaz.buet.ac.bd\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"http:\/\/hafizimtiaz.buet.ac.bd\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/hafizimtiaz.buet.ac.bd\/index.php\/wp-json\/wp\/v2\/comments?post=2324"}],"version-history":[{"count":46,"href":"http:\/\/hafizimtiaz.buet.ac.bd\/index.php\/wp-json\/wp\/v2\/pages\/2324\/revisions"}],"predecessor-version":[{"id":2692,"href":"http:\/\/hafizimtiaz.buet.ac.bd\/index.php\/wp-json\/wp\/v2\/pages\/2324\/revisions\/2692"}],"wp:attachment":[{"href":"http:\/\/hafizimtiaz.buet.ac.bd\/index.php\/wp-json\/wp\/v2\/media?parent=2324"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}