arXiv subjects

Usman Ali

Publications and source records attributed to Usman Ali.

At least 37 records · Page 2Linked to original sources

arXiv2024

An Improved Fault Diagnosis Strategy for Induction Motors Using Weighted Probability Ensemble Deep Learning

Early detection of faults in induction motors is crucial for ensuring uninterrupted operations in industrial settings. Among the various fault types encountered in induction motors, bearing, rotor, and stator faults are the most prevalent. This paper introduces a Weighted Probability Ensemble Deep Learning (WPEDL) methodology, tailored for effectively diagnosing induction motor faults using high-dimensional data extracted from vibration and current features. The Short-Time Fourier Transform (STFT) is employed to extract features from both vibration and current signals. The performance of the WPEDL fault diagnosis method is compared against conventional deep learning models, demonstrating the superior efficacy of the proposed system. The multi-class fault diagnosis system based on WPEDL achieves high accuracies across different fault types: 99.05% for bearing (vibrational signal), 99.10%, and 99.50% for rotor (current and vibration signal), and 99.60%, and 99.52% for stator faults (current and vibration signal) respectively. To evaluate the robustness of our multi-class classification decisions, tests have been conducted on a combined dataset of 52,000 STFT images encompassing all three faults. Our proposed model outperforms other models, achieving an accuracy of 98.89%. The findings underscore the effectiveness and reliability of the WPEDL approach for early-stage fault diagnosis in IMs, offering promising insights for enhancing industrial operational efficiency and reliability.

eess.SP↗

arXiv2024

Gated-Attention Feature-Fusion Based Framework for Poverty Prediction

This research paper addresses the significant challenge of accurately estimating poverty levels using deep learning, particularly in developing regions where traditional methods like household surveys are often costly, infrequent, and quickly become outdated. To address these issues, we propose a state-of-the-art Convolutional Neural Network (CNN) architecture, extending the ResNet50 model by incorporating a Gated-Attention Feature-Fusion Module (GAFM). Our architecture is designed to improve the model's ability to capture and combine both global and local features from satellite images, leading to more accurate poverty estimates. The model achieves a 75% R2 score, significantly outperforming existing leading methods in poverty mapping. This improvement is due to the model's capacity to focus on and refine the most relevant features, filtering out unnecessary data, which makes it a powerful tool for remote sensing and poverty estimation.

cs.CV↗

arXiv2024

Locally-Focused Face Representation for Sketch-to-Image Generation Using Noise-Induced Refinement

This paper presents a novel deep-learning framework that significantly enhances the transformation of rudimentary face sketches into high-fidelity colour images. Employing a Convolutional Block Attention-based Auto-encoder Network (CA2N), our approach effectively captures and enhances critical facial features through a block attention mechanism within an encoder-decoder architecture. Subsequently, the framework utilises a noise-induced conditional Generative Adversarial Network (cGAN) process that allows the system to maintain high performance even on domains unseen during the training. These enhancements lead to considerable improvements in image realism and fidelity, with our model achieving superior performance metrics that outperform the best method by FID margin of 17, 23, and 38 on CelebAMask-HQ, CUHK, and CUFSF datasets; respectively. The model sets a new state-of-the-art in sketch-to-image generation, can generalize across sketch types, and offers a robust solution for applications such as criminal identification in law enforcement.

cs.CV↗

arXiv2024

Matroids with bases as minimal resolving sets of graphs

We define an independence system associated with simple graphs. We prove that the independence system is a matroid for certain families of graphs, including trees, with bases as minimal resolving sets. Consequently, the greedy algorithm on the matroid can be used to find the minimum-cost resolving set of weighted graphs, wherein the independent system is a matroid. We also characterize hyperplanes of the matroid for trees and prove that its dual matroid is loop-free.

math.CO↗

arXiv2024

Deblurring 3D Gaussian Splatting

Recent studies in Radiance Fields have paved the robust way for novel view synthesis with their photorealistic rendering quality. Nevertheless, they usually employ neural networks and volumetric rendering, which are costly to train and impede their broad use in various real-time applications due to the lengthy rendering time. Lately 3D Gaussians splatting-based approach has been proposed to model the 3D scene, and it achieves remarkable visual quality while rendering the images in real-time. However, it suffers from severe degradation in the rendering quality if the training images are blurry. Blurriness commonly occurs due to the lens defocusing, object motion, and camera shake, and it inevitably intervenes in clean image acquisition. Several previous studies have attempted to render clean and sharp images from blurry input images using neural fields. The majority of those works, however, are designed only for volumetric rendering-based neural radiance fields and are not straightforwardly applicable to rasterization-based 3D Gaussian splatting methods. Thus, we propose a novel real-time deblurring framework, Deblurring 3D Gaussian Splatting, using a small Multi-Layer Perceptron (MLP) that manipulates the covariance of each 3D Gaussian to model the scene blurriness. While Deblurring 3D Gaussian Splatting can still enjoy real-time rendering, it can reconstruct fine and sharp details from blurry images. A variety of experiments have been conducted on the benchmark, and the results have revealed the effectiveness of our approach for deblurring. Qualitative results are available at https://benhenryl.github.io/Deblurring-3D-Gaussian-Splatting/

cs.CV↗

arXiv2024

F-3DGS: Factorized Coordinates and Representations for 3D Gaussian Splatting

The neural radiance field (NeRF) has made significant strides in representing 3D scenes and synthesizing novel views. Despite its advancements, the high computational costs of NeRF have posed challenges for its deployment in resource-constrained environments and real-time applications. As an alternative to NeRF-like neural rendering methods, 3D Gaussian Splatting (3DGS) offers rapid rendering speeds while maintaining excellent image quality. However, as it represents objects and scenes using a myriad of Gaussians, it requires substantial storage to achieve high-quality representation. To mitigate the storage overhead, we propose Factorized 3D Gaussian Splatting (F-3DGS), a novel approach that drastically reduces storage requirements while preserving image quality. Inspired by classical matrix and tensor factorization techniques, our method represents and approximates dense clusters of Gaussians with significantly fewer Gaussians through efficient factorization. We aim to efficiently represent dense 3D Gaussians by approximating them with a limited amount of information for each axis and their combinations. This method allows us to encode a substantially large number of Gaussians along with their essential attributes -- such as color, scale, and rotation -- necessary for rendering using a relatively small number of elements. Extensive experimental results demonstrate that F-3DGS achieves a significant reduction in storage costs while maintaining comparable quality in rendered images.

cs.CV↗

arXiv2024

Floquet dynamics of ultracold atoms in optical lattices with a parametrically modulated trapping potential

Experiments with ultracold atoms in optical lattices usually involve a weak parabolic trapping potential which merely serves to confine the atoms, but otherwise remains negligible. In contrast, we suggest a different class of experiments in which the presence of a stronger trap is an essential part of the set-up. Because the trap-modified on-site energies exhibit a slowly varying level spacing, similar to that of an anharmonic oscillator, an additional time-periodic trap modulation with judiciously chosen parameters creates nonlinear resonances which enable efficient Floquet engineering. We employ a Mathieu approximation for constructing the near-resonant Floquet states in an accurate manner and demonstrate the emergence of effective ground states from the resonant trap eigenstates. Moreover, we show that the population of the Floquet states is strongly affected by the phase of a sudden turn-on of the trap modulation, which leads to significantly modified and rich dynamics. As a guideline for further studies, we argue that the deliberate population of only the resonance-induced effective ground states will allow one to realize Floquet condensates which follow classical periodic orbits, thus providing challenging future perspectives for the investigation of the quantum-classical correspondence.

cond-mat.quant-gas↗

arXiv2024

Sharp-NeRF: Grid-based Fast Deblurring Neural Radiance Fields Using Sharpness Prior

Neural Radiance Fields (NeRF) have shown remarkable performance in neural rendering-based novel view synthesis. However, NeRF suffers from severe visual quality degradation when the input images have been captured under imperfect conditions, such as poor illumination, defocus blurring, and lens aberrations. Especially, defocus blur is quite common in the images when they are normally captured using cameras. Although few recent studies have proposed to render sharp images of considerably high-quality, yet they still face many key challenges. In particular, those methods have employed a Multi-Layer Perceptron (MLP) based NeRF, which requires tremendous computational time. To overcome these shortcomings, this paper proposes a novel technique Sharp-NeRF -- a grid-based NeRF that renders clean and sharp images from the input blurry images within half an hour of training. To do so, we used several grid-based kernels to accurately model the sharpness/blurriness of the scene. The sharpness level of the pixels is computed to learn the spatially varying blur kernels. We have conducted experiments on the benchmarks consisting of blurry images and have evaluated full-reference and non-reference metrics. The qualitative and quantitative results have revealed that our approach renders the sharp novel views with vivid colors and fine details, and it has considerably faster training time than the previous works. Our project page is available at https://benhenryl.github.io/SharpNeRF/

cs.CV↗

arXiv2023

Enhancing Vehicle Entrance and Parking Management: Deep Learning Solutions for Efficiency and Security

The auto-management of vehicle entrance and parking in any organization is a complex challenge encompassing record-keeping, efficiency, and security concerns. Manual methods for tracking vehicles and finding parking spaces are slow and a waste of time. To solve the problem of auto management of vehicle entrance and parking, we have utilized state-of-the-art deep learning models and automated the process of vehicle entrance and parking into any organization. To ensure security, our system integrated vehicle detection, license number plate verification, and face detection and recognition models to ensure that the person and vehicle are registered with the organization. We have trained multiple deep-learning models for vehicle detection, license number plate detection, face detection, and recognition, however, the YOLOv8n model outperformed all the other models. Furthermore, License plate recognition is facilitated by Google's Tesseract-OCR Engine. By integrating these technologies, the system offers efficient vehicle detection, precise identification, streamlined record keeping, and optimized parking slot allocation in buildings, thereby enhancing convenience, accuracy, and security. Future research opportunities lie in fine-tuning system performance for a wide range of real-world applications.

cs.CV↗

arXiv2023

Chirped Bloch-Harmonic oscillations in a parametrically forced optical lattice

The acceleration theorem for wavepacket propagation in periodic potentials disentangles the kspace dynamics and real-space dynamics. This is well known and understood for Bloch oscillations and super Bloch oscillations in the presence of position-independent forces. Here, we analyze the dynamics of a model system in which the k-space dynamics and the real-space dynamics are inextricably intertwined due to a position-dependent force which is provided by a parabolic trap. We demonstrate that this coupling gives rise to significantly modified and rich dynamics when the lattice is shaken by a modulated parabolic potential. The dynamics range from chirped Bloch-Harmonic oscillations to the asymmetric spreading oscillations. We analyze these findings by tracing the spatio-temporal dynamics in real space and by visualizing the relative phase in the k-space dynamics which leads to an accurate explanation of the obtained phenomena. We also compare our numerical results to a local acceleration model and obtain very good agreement for the case of coherent oscillations, however, deviations for oscillations with spreading dynamics which altogether supports the interpretations of our findings.

quant-ph↗

arXiv2023

Harnessing the Potential of Blockchain in DevOps: A Framework for Distributed Integration and Development

As the use of DevOps practices continues to grow, organizations are seeking ways to improve collaboration, speed up development cycles, and increase security, transparency, and traceability. Blockchain technology has the potential to support these goals by providing a secure, decentralized platform for distributed integration and development. In this paper, we propose a framework for distributed DevOps that utilizes the benefits of blockchain technology that can eliminate the shortcomings of DevOps. We demonstrate the feasibility and potential benefits of the proposed framework that involves developing and deploying applications in a distributed environment. We present a benchmark result demonstrating the effectiveness of our framework in a real-world scenario, highlighting its ability to improve collaboration, reduce costs, and enhance the security of the DevOps pipeline. Conclusively, our research contributes to the growing body of literature on the intersection of blockchain and DevOps, providing a practical framework for organizations looking to leverage blockchain technology to improve their development processes.

cs.CR↗

arXiv2022

Super-Bloch oscillations with parametric modulation of a parabolic trap

Super-Bloch oscillations are the outcome of a relative phase between Bloch oscillations and modulations of the periodic lattice. We analyze the dynamics for a model system in which such a relative phase is intrinsically present due to the position-dependent force provided by a parabolic trap and therefore an external detuning is not required. The relative phase is not unique and the realized dynamics depends on the initial phase of the modulated parabolic potential. We provide accurate explanations for the different obtained oscillatory transport and spreading regimes by analyzing the spatio-temporal dynamics in real space and by visualizing the relative phase in the k-space dynamics. We also compare our numerical results to an approximate semiclassical analytical expression for the group velocity for a modulated constant force system and find good agreement for coherent oscillations but deviations for oscillations with spreading dynamics which altogether supports the interpretations of our findings.

cond-mat.quant-gas↗

arXiv2021

Functional Boxplots for Outlier Detection in Additive Manufacturing

Additive manufacturing (AM), also known as 3D printing, is one of the most promising digital manufacturing technologies, thanks to its potential to produce highly complex geometries rapidly. AM has been promoted from a prototyping methodology to a serial production platform for which precise process monitoring and control strategies to guarantee the accuracy of products are required. This need has motivated practitioners to focus on designing process monitoring tools to improve the accuracy of produced geometries. In line with the emerging interest, in the current investigation, a novel strategy is proposed which uses functional representation of in-plane contours to come up with statistical boxplots with the goal of detecting outlying AM products. The method can be used for process monitoring during AM production to automatically detect defective products in an online fashion. To ensure the considered method has an acceptable potential, different complex 3D geometries are considered and undergo different types of stochastic perturbations to collect data for outlier detection. The results of the conducted simulation are very promising and reveal the reliability of the proposed method for detecting products with statistically significant deformation.

stat.AP↗

arXiv2020

Temporal Continuity Based Unsupervised Learning for Person Re-Identification

Person re-identification (re-id) aims to match the same person from images taken across multiple cameras. Most existing person re-id methods generally require a large amount of identity labeled data to act as discriminative guideline for representation learning. Difficulty in manually collecting identity labeled data leads to poor adaptability in practical scenarios. To overcome this problem, we propose an unsupervised center-based clustering approach capable of progressively learning and exploiting the underlying re-id discriminative information from temporal continuity within a camera. We call our framework Temporal Continuity based Unsupervised Learning (TCUL). Specifically, TCUL simultaneously does center based clustering of unlabeled (target) dataset and fine-tunes a convolutional neural network (CNN) pre-trained on irrelevant labeled (source) dataset to enhance discriminative capability of the CNN for the target dataset. Furthermore, it exploits temporally continuous nature of images within-camera jointly with spatial similarity of feature maps across-cameras to generate reliable pseudo-labels for training a re-identification model. As the training progresses, number of reliable samples keep on growing adaptively which in turn boosts representation ability of the CNN. Extensive experiments on three large-scale person re-id benchmark datasets are conducted to compare our framework with state-of-the-art techniques, which demonstrate superiority of TCUL over existing methods.

cs.CV↗

arXiv2019

FH-GAN: Face Hallucination and Recognition using Generative Adversarial Network

There are many factors affecting visual face recognition, such as low resolution images, aging, illumination and pose variance, etc. One of the most important problem is low resolution face images which can result in bad performance on face recognition. Most of the general face recognition algorithms usually assume a sufficient resolution for the face images. However, in practice many applications often do not have sufficient image resolutions. The modern face hallucination models demonstrate reasonable performance to reconstruct high-resolution images from its corresponding low resolution images. However, they do not consider identity level information during hallucination which directly affects results of the recognition of low resolution faces. To address this issue, we propose a Face Hallucination Generative Adversarial Network (FH-GAN) which improves the quality of low resolution face images and accurately recognize those low quality images. Concretely, we make the following contributions: 1) we propose FH-GAN network, an end-to-end system, that improves both face hallucination and face recognition simultaneously. The novelty of this proposed network depends on incorporating identity information in a GAN-based face hallucination algorithm via combining a face recognition network for identity preserving. 2) We also propose a new face hallucination network, namely Dense Sparse Network (DSNet), which improves upon the state-of-art in face hallucination. 3) We demonstrate benefits of training the face recognition and GAN-based DSNet jointly by reporting good result on face hallucination and recognition.

cs.CV↗

arXiv2019

Spatial Shortcut Network for Human Pose Estimation

Like many computer vision problems, human pose estimation is a challenging problem in that recognizing a body part requires not only information from local area but also from areas with large spatial distance. In order to spatially pass information, large convolutional kernels and deep layers have been normally used, introducing high computation cost and large parameter space. Luckily for pose estimation, human body is geometrically structured in images, enabling modeling of spatial dependency. In this paper, we propose a spatial shortcut network for pose estimation task, where information is easier to flow spatially. We evaluate our model with detailed analyses and present its outstanding performance with smaller structure.

cs.CV↗

arXiv2019

An independence system as knot invariant

In this article, we define an independence system for a classical knot diagram and prove that the independence system is a knot invariant for alternating knots. We also discuss the exchange property for minimal unknotting sets. Finally, we show that there are knot diagrams where the independence system is a matroid and there are knot diagrams where it is not.

math.GT↗

arXiv2018

On some automorphism related parameters in graphs

In this paper, we deduce some properties of $f$-sets of connected graphs. Also, we introduce the concept of fixing share of each vertex of a fixing set $D$ to see the participation of each vertex when fixing a connected graph $G$. We define a parameter, called the fixing percentage, by using the concept of fixing share, which is helpful in determining the measure of the amount of fixing done by the elements of $D$ in $G$.

math.CO↗