arXiv subjects

Muhammad Tahir

Publications and source records attributed to Muhammad Tahir.

At least 19 recordsLinked to original sources

arXiv2026

Motion-Coupled Sensing: When the State Change Powers Its Own Sensing

Batteryless IoT systems have largely followed two paths: ambient-energy sensing, where energy arrival is decoupled from the event being monitored, and kinetic event telegrams, where a user actuation powers a short report of the actuation itself. Mechanically gated states expose a third case: the access motion is not only an event to report, but the moment at which a latent physical state may have changed and must be measured. We show that routine hinge motion can supply enough energy for one bounded wake-sense-transmit transaction, including ultrasonic sensing and a long-range LoRa uplink. We call this principle motion-coupled sensing and instantiate it with an open-source compact electromagnetic harvester that retrofits to bins, doors, and cabinets with no structural modification. We size the platform for the most demanding workload, waste-bin monitoring, where each actuation must power both an ultrasonic measurement and a long-range LoRa uplink. Across five campus locations and 5,945 lid actuations, the bin deployment achieves 99.3% per-event transmission reliability. Field deployments on room doors with 1,870 actuations and office cabinets with 1,636 actuations achieve 92% and 94% transmission success respectively, demonstrating that the same energy envelope transfers across hinge geometries without hardware redesign. These results show that mechanical access can be treated as a self-powered sensing transaction, removing periodic polling and scheduled battery maintenance for IoT deployments.

cs.NI↗

arXiv2026

Spectral Unforgetting: Post-Hoc Recovery of Damaged Capabilities Without Retraining

Fine-tuning a language model for a target task routinely degrades capabilities the training data never explicitly threatened. We study this phenomenon, known as catastrophic forgetting, and propose a post-hoc repair solution that uses only the pretrained checkpoint $W_{\mathrm{base}}$ and its fine-tuned descendant $W_{\mathrm{ft}}$. The goal is not merely to revert the model toward the base checkpoint, but to recover capabilities damaged by fine-tuning while preserving both the target-task gains and any beneficial held-out improvements. We introduce DG-Hard, a checkpoint-only spectral repair method for the fine-tuning update $\Delta = W_{\mathrm{ft}} - W_{\mathrm{base}}$. DG-Hard treats $\Delta$ as a low-rank task-aligned signal embedded in an IID-like noise residual that gradient descent has no incentive to remove, and applies the Donoho-Gavish hard singular-value threshold to each weight-delta matrix, keeping the structured high-energy part of the update and removing the spectral bulk. This reduces repair to a closed-form SVD filtering step requiring no data-dependent tuning. A central difficulty is evaluation: average accuracy hides per-benchmark failures, while naive recovery scores reward models that simply revert toward the base. We therefore introduce a partition-conditional metric that separately tracks healing, preservation, non-damage, and target-task retention. Across $14$ (model, task) settings and nine cross-domain held-out benchmarks, DG-Hard achieves the strongest balanced repair among post-hoc baselines. DG-Hard also restores safety alignment degraded by benign fine-tuning on three independent safety axes, despite using no alignment data. These results suggest that part of fine-tuning-induced capability loss is not an unavoidable consequence of specialization, but a removable spectral residue in the weight update itself.

cs.LG↗

arXiv2025

Mechanistic Evidence for Preserved-but-Misaligned Representations in Non-IID FedAvg

Federated Averaging (FedAvg) often degrades under non-IID client data, but it remains unclear whether this degradation reflects the loss of client-learned representations or a failure to use representations that are still present. We study this question mechanistically in sparse client-trained vision models, using dense-model controls to test whether the observed effects depend on sparsity. Our analysis combines class-specific circuit discovery, linear probing of frozen representations, head-only finetuning, and sparse feature dictionaries. Across CNN and ResNet models on CIFAR-10 and Fashion-MNIST, severe label skew can drive some per-class accuracies near zero even when class-specific internal structure remains recoverable. Linear probes substantially outperform the aggregated classifier, head-only finetuning partially restores accuracy, and USAE transfer reveals a largely shared feature basis between IID and non-IID models. Together, these diagnostics suggest that, in our setting, non-IID FedAvg degradation is not fully explained by representational erasure; it also reflects misalignment between preserved internal structure and the final prediction pathway.

cs.LG↗

arXiv2025

EMORF-II: Adaptive EM-based Outlier-Robust Filtering with Correlated Measurement Noise

We present a learning-based outlier-robust filter for a general setup where the measurement noise can be correlated. Since it is an enhanced version of EM-based outlier robust filter (EMORF), we call it as EMORF-II. As it is equipped with an additional powerful feature to learn the outlier characteristics during inference along with outlier-detection, EMORF-II has improved outlier-mitigation capability. Numerical experiments confirm performance gains as compared to the state-of-the-art methods in terms of accuracy with an increased computational overhead. However, thankfully the computational complexity order remains at par with other practical methods making it a useful choice for diverse applications.

cs.LG↗

arXiv2025

LOCO-EPI: Leave-one-chromosome-out (LOCO) as a benchmarking paradigm for deep learning based prediction of enhancer-promoter interactions

In mammalian and vertebrate genomes, the promoter regions of the gene and their distal enhancers may be located millions of base-pairs from each other, while a promoter may not interact with the closest enhancer. Since base-pair proximity is not a good indicator of these interactions, there is considerable work toward developing methods for predicting Enhancer-Promoter Interactions (EPI). Several machine learning methods have reported increasingly higher accuracies for predicting EPI. Typically, these approaches randomly split the dataset of Enhancer-Promoter (EP) pairs into training and testing subsets followed by model training. However, the aforementioned random splitting causes information leakage by assigning EP pairs from the same genomic region to both testing and training sets, leading to performance overestimation. In this paper we propose to use a more thorough training and testing paradigm i.e., Leave-one-chromosome-out (LOCO) cross-validation for EPI-prediction. We demonstrate that a deep learning algorithm, which gives higher accuracies when trained and tested on random-splitting setting, drops drastically in performance under LOCO setting, confirming overestimation of performance. We further propose a novel hybrid deep neural network for EPI-prediction that fuses k-mer features of the nucleotide sequence. We show that the hybrid architecture performs significantly better in the LOCO setting, demonstrating it can learn more generalizable aspects of EP interactions. With this paper we are also releasing the LOCO splitting-based EPI dataset. Research data is available in this public repository: https://github.com/malikmtahir/EPI

cs.LG↗

arXiv2025

Artificial Intelligence and Deep Learning Algorithms for Epigenetic Sequence Analysis: A Review for Epigeneticists and AI Experts

Epigenetics encompasses mechanisms that can alter the expression of genes without changing the underlying genetic sequence. The epigenetic regulation of gene expression is initiated and sustained by several mechanisms such as DNA methylation, histone modifications, chromatin conformation, and non-coding RNA. The changes in gene regulation and expression can manifest in the form of various diseases and disorders such as cancer and congenital deformities. Over the last few decades, high throughput experimental approaches have been used to identify and understand epigenetic changes, but these laboratory experimental approaches and biochemical processes are time-consuming and expensive. To overcome these challenges, machine learning and artificial intelligence (AI) approaches have been extensively used for mapping epigenetic modifications to their phenotypic manifestations. In this paper we provide a narrative review of published research on AI models trained on epigenomic data to address a variety of problems such as prediction of disease markers, gene expression, enhancer promoter interaction, and chromatin states. The purpose of this review is twofold as it is addressed to both AI experts and epigeneticists. For AI researchers, we provided a taxonomy of epigenetics research problems that can benefit from an AI-based approach. For epigeneticists, given each of the above problems we provide a list of candidate AI solutions in the literature. We have also identified several gaps in the literature, research challenges, and recommendations to address these challenges.

q-bio.GN↗

arXiv2025

Investigation of pairing correlations on computed Gamow-Teller strength distributions and associated $\beta$-decay half-lives

We investigate the effect of pairing correlations on the computed Gamow-Teller (GT) strength distributions and corresponding $\beta$-decay half-lives. The calculations are performed for a total of 47 sd-shell nuclei, for $20 < A < 30$, employing the pn-QRPA model. Our calculations use three different values of pairing gaps computed using three different empirical formulae. The GT strength distribution and centroid values change considerably with a change in the pairing gap values. This, in turn, leads to differences in computed half-lives. The pairing gaps computed using the mass-dependent formula result in the calculated half-lives being in better agreement with the measured data.

nucl-th↗

arXiv2025

Investigation of effects of pairing correlations on calculated $\beta$-decay half-lives of fp-shell nuclei

Pairing of nucleons plays a key role in solving various nuclear physics problems. We investigate the probable effects of pairing correlations on the calculated Gamow-Teller (GT) strength distributions and the associated $\beta$-decay half-lives. Computations are performed for a total of 35 fp-shell nuclei using the proton-neutron quasiparticle random phase approximation (pn-QRPA) model. The nuclei were selected because of their importance in various astrophysical environments. Pairing gaps are one of the key parameters in the pn-QRPA model to compute GT transitions. We employed three different values of the pairing gaps obtained from three different empirical formulae in our calculation. The GT strength distributions changed significantly as the pairing gap values changed. This in turn resulted in contrasting centroid and total strength values of the calculated GT distributions and led to differences in calculated half-lives using the three schemes. The half-life values computed via the three-term pairing formula, based on separation energies of nucleons, were in best agreement with the measured data. We conclude that the traditional choice of pairing gap values, $\Delta_p = \Delta_n = 12/\sqrt{A}$, may not lead to half-life values in good agreement with measured data. The findings of this study are interesting but warrant further investigation.

nucl-th↗

arXiv2025

Spatiotemporal Air Quality Mapping in Urban Areas Using Sparse Sensor Data, Satellite Imagery, Meteorological Factors, and Spatial Features

Monitoring air pollution is crucial for protecting human health from exposure to harmful substances. Traditional methods of air quality monitoring, such as ground-based sensors and satellite-based remote sensing, face limitations due to high deployment costs, sparse sensor coverage, and environmental interferences. To address these challenges, this paper proposes a framework for high-resolution spatiotemporal Air Quality Index (AQI) mapping using sparse sensor data, satellite imagery, and various spatiotemporal factors. By leveraging Graph Neural Networks (GNNs), we estimate AQI values at unmonitored locations based on both spatial and temporal dependencies. The framework incorporates a wide range of environmental features, including meteorological data, road networks, points of interest (PoIs), population density, and urban green spaces, which enhance prediction accuracy. We illustrate the use of our approach through a case study in Lahore, Pakistan, where multi-resolution data is used to generate the air quality index map at a fine spatiotemporal scale.

cs.LG↗

arXiv2024

Re analysis of Temperature Dependent Neutron Capture Rates and Stellar \b{eta} decay Rates of 95 98Mo

The neutron capture rates and temperature dependent stellar beta decay rates of Mo isotopes are investigated within the framework of the statistical code (Talys v1.96) and proton neutron quasi particle random phase approximation (pnQRPA) models. The Maxwellian average cross section (MACS) and neutron capture rates for 95 98Mo(n,{\gamma}) 96 99Mo radiative capture processes are analyzed within the framework of statistical code Talys v1.96 based on the phenomenological nuclear level density (NLD) parameters and gamma strength functions (GSFs). The current model based computed data for MACS provide a good comparison with the existing measured data. The temperature dependent stellar \b{eta} decay rates of 95 98Mo are investigated at different densities within the framework of the pn-QRPA model. For the considered temperature range, the neutron capture rates were found to be higher, by orders of magnitude, than the stellar \b{eta} rates.

astro-ph.SR↗

arXiv2023

TFNet: Tuning Fork Network with Neighborhood Pixel Aggregation for Improved Building Footprint Extraction

This paper considers the problem of extracting building footprints from satellite imagery -- a task that is critical for many urban planning and decision-making applications. While recent advancements in deep learning have made great strides in automated detection of building footprints, state-of-the-art methods available in existing literature often generate erroneous results for areas with densely connected buildings. Moreover, these methods do not incorporate the context of neighborhood images during training thus generally resulting in poor performance at image boundaries. In light of these gaps, we propose a novel Tuning Fork Network (TFNet) design for deep semantic segmentation that not only performs well for widely-spaced building but also has good performance for buildings that are closely packed together. The novelty of TFNet architecture lies in a a single encoder followed by two parallel decoders to separately reconstruct the building footprint and the building edge. In addition, the TFNet design is coupled with a novel methodology of incorporating neighborhood information at the tile boundaries during the training process. This methodology further improves performance, especially at the tile boundaries. For performance comparisons, we utilize the SpaceNet2 and WHU datasets, as well as a dataset from an area in Lahore, Pakistan that captures closely connected buildings. For all three datasets, the proposed methodology is found to significantly outperform benchmark methods.

cs.CV↗

arXiv2023

Logistics Hub Location Optimization: A K-Means and P-Median Model Hybrid Approach Using Road Network Distances

Logistic hubs play a pivotal role in the last-mile delivery distance; even a slight increment in distance negatively impacts the business of the e-commerce industry while also increasing its carbon footprint. The growth of this industry, particularly after Covid-19, has further intensified the need for optimized allocation of resources in an urban environment. In this study, we use a hybrid approach to optimize the placement of logistic hubs. The approach sequentially employs different techniques. Initially, delivery points are clustered using K-Means in relation to their spatial locations. The clustering method utilizes road network distances as opposed to Euclidean distances. Non-road network-based approaches have been avoided since they lead to erroneous and misleading results. Finally, hubs are located using the P-Median method. The P-Median method also incorporates the number of deliveries and population as weights. Real-world delivery data from Muller and Phipps (M&P) is used to demonstrate the effectiveness of the approach. Serving deliveries from the optimal hub locations results in the saving of 815 (10%) meters per delivery.

math.OC↗

arXiv2023

PD-SEG: Population Disaggregation Using Deep Segmentation Networks For Improved Built Settlement Mask

Any policy-level decision-making procedure and academic research involving the optimum use of resources for development and planning initiatives depends on accurate population density statistics. The current cutting-edge datasets offered by WorldPop and Meta do not succeed in achieving this aim for developing nations like Pakistan; the inputs to their algorithms provide flawed estimates that fail to capture the spatial and land-use dynamics. In order to precisely estimate population counts at a resolution of 30 meters by 30 meters, we use an accurate built settlement mask obtained using deep segmentation networks and satellite imagery. The Points of Interest (POI) data is also used to exclude non-residential areas.

cs.CV↗

arXiv2023

EMORF/S: EM-Based Outlier-Robust Filtering and Smoothing With Correlated Measurement Noise

In this article, we consider the problem of outlier-robust state estimation where the measurement noise can be correlated. Outliers in data arise due to many reasons like sensor malfunctioning, environmental behaviors, communication glitches, etc. Moreover, noise correlation emerges in several real-world applications e.g. sensor networks, radar data, GPS-based systems, etc. We consider these effects in system modeling which is subsequently used for inference. We employ the Expectation-Maximization (EM) framework to derive both outlier-resilient filtering and smoothing methods, suitable for online and offline estimation respectively. The standard Gaussian filtering and the Gaussian Rauch-Tung-Striebel (RTS) smoothing results are leveraged to devise the estimators. In addition, Bayesian Cramer-Rao Bounds (BCRBs) for a filter and a smoother which can perfectly detect and reject outliers are presented. These serve as useful theoretical benchmarks to gauge the error performance of different estimators. Lastly, different numerical experiments, for an illustrative target tracking application, are carried out that indicate performance gains compared to similarly engineered state-of-the-art outlier-rejecting state estimators. The advantages are in terms of simpler implementation, enhanced estimation quality, and competitive computational performance.

eess.SP↗

arXiv2023

STEF-DHNet: Spatiotemporal External Factors Based Deep Hybrid Network for Enhanced Long-Term Taxi Demand Prediction

Accurately predicting the demand for ride-hailing services can result in significant benefits such as more effective surge pricing strategies, improved driver positioning, and enhanced customer service. By understanding the demand fluctuations, companies can anticipate and respond to consumer requirements more efficiently, leading to increased efficiency and revenue. However, forecasting demand in a particular region can be challenging, as it is influenced by several external factors, such as time of day, weather conditions, and location. Thus, understanding and evaluating these factors is essential for predicting consumer behavior and adapting to their needs effectively. Grid-based deep learning approaches have proven effective in predicting regional taxi demand. However, these models have limitations in integrating external factors in their spatiotemporal complexity and maintaining high accuracy over extended time horizons without continuous retraining, which makes them less suitable for practical and commercial applications. To address these limitations, this paper introduces STEF-DHNet, a demand prediction model that combines Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) to integrate external features as spatiotemporal information and capture their influence on ride-hailing demand. The proposed model is evaluated using a long-term performance metric called the rolling error, which assesses its ability to maintain high accuracy over long periods without retraining. The results show that STEF-DHNet outperforms existing state-of-the-art methods on three diverse datasets, demonstrating its potential for practical use in real-world scenarios.

cs.LG↗

arXiv2023

Feature Selection on Sentinel-2 Multi-spectral Imagery for Efficient Tree Cover Estimation

This paper proposes a multi-spectral random forest classifier with suitable feature selection and masking for tree cover estimation in urban areas. The key feature of the proposed classifier is filtering out the built-up region using spectral indices followed by random forest classification on the remaining mask with carefully selected features. Using Sentinel-2 satellite imagery, we evaluate the performance of the proposed technique on a specified area (approximately 82 acres) of Lahore University of Management Sciences (LUMS) and demonstrate that our method outperforms a conventional random forest classifier as well as state-of-the-art methods such as European Space Agency (ESA) WorldCover 10m 2020 product as well as a DeepLabv3 deep learning architecture.

cs.CV↗

arXiv2022

Bayesian Heuristics for Robust Spatial Perception

Spatial perception is a key task in several machine intelligence applications such as robotics and computer vision. In general, it involves the nonlinear estimation of hidden variables that represent the system's state. However, in the presence of measurement outliers, the standard nonlinear least squared formulation results in poor estimates. Several methods have been considered in the literature to improve the reliability of the estimation process. Most methods are based on heuristics since guaranteed global robust estimation is not generally practical due to high computational costs. Recently general purpose robust estimation heuristics have been proposed that leverage existing non-minimal solvers available for the outlier-free formulations without the need for an initial guess. In this work, we propose three Bayesian heuristics that have similar structures. We evaluate these heuristics in practical scenarios to demonstrate their merits in different applications including 3D point cloud registration, mesh registration and pose graph optimization. The general computational advantages our proposals offer make them attractive candidates for spatial perception tasks.

cs.RO↗

arXiv2022

A Deep-Unfolded Spatiotemporal RPCA Network For L+S Decomposition

Low-rank and sparse decomposition based methods find their use in many applications involving background modeling such as clutter suppression and object tracking. While Robust Principal Component Analysis (RPCA) has achieved great success in performing this task, it can take hundreds of iterations to converge and its performance decreases in the presence of different phenomena such as occlusion, jitter and fast motion. The recently proposed deep unfolded networks, on the other hand, have demonstrated better accuracy and improved convergence over both their iterative equivalents as well as over other neural network architectures. In this work, we propose a novel deep unfolded spatiotemporal RPCA (DUST-RPCA) network, which explicitly takes advantage of the spatial and temporal continuity in the low-rank component. Our experimental results on the moving MNIST dataset indicate that DUST-RPCA gives better accuracy when compared with the existing state of the art deep unfolded RPCA networks.

cs.CV↗