SearcharxivSearch

arXiv subjects

Bilal Ahmed

Publications and source records attributed to Bilal Ahmed.

14 recordsLinked to original sources

Stability and Wandering of Bumps in Neural Fields with Interneuron Subtypes

The maintenance of continuous variable information in working memory is thought to rely on persistent patterns of cortical activity. In delayed-estimation tasks, neural activity can form localized activity peaks, or ``bumps,'' whose positions track the remembered variable. Such activity is well described by continuous-attractor neural field models, but most existing models collapse cortical inhibition into a single homogeneous population. Here, we introduce a stochastic neural field model with distinct excitatory, parvalbumin-expressing (PV), and somatostatin-expressing (SST) populations to examine how inhibitory subtype structure shapes persistent activity. Using a Heaviside firing-rate approximation, we derive stationary bump solutions and reduce their linear stability to separate shifting and scaling modes. We show that population thresholds and inhibitory timescales determine both bump stability and the mechanism by which stability is lost, while inhibitory connection strengths and spatial scales substantially reshape the stable parameter region. In particular, broader SST connectivity promotes stable bump states. Finally, we derive an effective diffusion coefficient for noise-driven bump wandering and show that increasing the SST spatial footprint reduces the rate of memory diffusion. Together, these results demonstrate how inhibitory subtype structure can shape both the deterministic stability and stochastic precision of continuous-attractor memories.

math.DS

Advancing Accessible Underwater Robotics: The Mini-Girona I-AUV at RAMI 2025

The Mini-Girona Intervention Autonomous Underwater Vehicle (I-AUV) represents an advancement in accessible underwater robotics, designed to bridge the gap between costly, specialized research AUVs and basic Remotely Operated Vehicles (ROVs). Developed with a focus on affordability and usability, the Mini-Girona, priced at approximately $50,000, integrates advanced components such as a 5-DOF manipulator arm, stereo vision, and AI-driven processing for autonomous navigation and intervention tasks. This paper presents the design and development of the Mini-Girona, detailing its performance during the RAMI 2025 student competition. Despite challenges such as thermal management issues and restricted team access, the Mini-Girona achieved second place overall, excelling in vision-based perception and intervention tasks. This work highlights the platform's potential as a tool for underwater robotics research and education, fostering innovation in real-world underwater applications.

cs.RO

Physics-Audited Agentic Discovery in Scientific Machine Learning

In agentic scientific machine learning (SciML), large language model (LLM) agents can discover surrogate models and select one by an automated score, typically an error metric. A low error, however, does not establish that the predicted fields satisfy the physics that matter for mechanics, such as boundary conditions, superposition, stiffness scaling, or causality. We introduce Physics-Audited Agentic SciML (PA-SciML), a verification-first workflow for agentic SciML discovery. The workflow fixes a scoring evaluator before search, derives reviewable machine-checkable physics requirements, checks each trained candidate on its outputs, and separately searches prescribed input ranges or measured load-history spans for high-violation cases without reference solution fields. A surrogate is reported as verified only under the stated checks. When enabled, the workflow also adds advisory numerical probes before training and tests one modeling change at a time to record which isolated edits are associated with score gains before reuse. In the reported computational-solid-mechanics numerical examples, the static elasticity run selects a surrogate with lower validation error than the error-only baseline while both selected models pass the common linear-elastic checks. In the transient elastodynamics run, an error-only baseline with similar mean error fails a stricter causality check by responding to future parts of the loading history, while the selected surrogate passes the stated checks. The main distinction is per-candidate physics evidence on predicted fields, not a richer aggregate score.

cs.AI

Adaptive Distance-Aware Trunk Deep Operator Learning for Long-Span Roadway Bridges

Long-span roadway bridges exhibit highly localized structural responses under vehicular loading, making repeated FE analysis computationally expensive for applications such as influence surface generation and structural digital twins. Existing SciML approaches struggle to accurately capture these localized responses. To address this challenge, this study proposes an adaptive-trunk DeepONet for localized structural response prediction in large-scale bridge systems. The framework dynamically constructs a load-dependent learning domain using a KNN strategy, allowing the network to focus on structural influence zones. The trunk network is further enhanced using distance-aware features that encode the geometric relationship between the load and structural nodes. A physics-based full-field reconstruction is incorporated through a stiffness-informed Schur complement formulation, enabling predictions at adaptive nodes to be extended to the entire structural domain. To enable scalable training, response data are generated using a reduced-order equivalent shell model that preserves the dominant global behavior while significantly reducing computational cost. The proposed framework is validated on both a benchmark bridge model and the real-world Mussafah Bridge. Results show that the method achieves FEM-level accuracy with relative errors below 5%, while reducing the total response evaluation time (including full-field reconstruction) by approximately 60x; excluding the post-processing reconstruction step, the AD-DeepONet inference is up to four orders of magnitude faster than FEM. In addition, the framework enables rapid generation of full-field responses, influence lines, and influence surfaces under arbitrary vehicular loading configurations, demonstrating strong potential for large-scale bridge analysis and digital twin applications.

cs.LG

Solving Diffusion Inverse Problems with Restart Posterior Sampling

Inverse problems are fundamental to science and engineering, where the goal is to infer an underlying signal or state from incomplete or noisy measurements. Recent approaches employ diffusion models as powerful implicit priors for such problems, owing to their ability to capture complex data distributions. However, existing diffusion-based methods for inverse problems often rely on strong approximations of the posterior distribution, require computationally expensive gradient backpropagation through the score network, or are restricted to linear measurement models. In this work, we propose Restart for Posterior Sampling (RePS), a general and efficient framework for solving both linear and non-linear inverse problems using pre-trained diffusion models. RePS builds on the idea of restart-based sampling, previously shown to improve sample quality in unconditional diffusion, and extends it to posterior inference. Our method employs a conditioned ODE applicable to any differentiable measurement model and introduces a simplified restart strategy that contracts accumulated approximation errors during sampling. Unlike some of the prior approaches, RePS avoids backpropagation through the score network, substantially reducing computational cost. We demonstrate that RePS achieves faster convergence and superior reconstruction quality compared to existing diffusion-based baselines across a range of inverse problems, including both linear and non-linear settings.

cs.LG

Physics-informed Multiple-Input Operators for efficient dynamic response prediction of structures

Finite element (FE) modeling is essential for structural analysis but remains computationally intensive, especially under dynamic loading. While operator learning models have shown promise in replicating static structural responses at FEM level accuracy, modeling dynamic behavior remains more challenging. This work presents a Multiple Input Operator Network (MIONet) that incorporates a second trunk network to explicitly encode temporal dynamics, enabling accurate prediction of structural responses under moving loads. Traditional DeepONet architectures using recurrent neural networks (RNNs) are limited by fixed time discretization and struggle to capture continuous dynamics. In contrast, MIONet predicts responses continuously over both space and time, removing the need for step wise modeling. It maps scalar inputs including load type, velocity, spatial mesh, and time steps to full field structural responses. To improve efficiency and enforce physical consistency, we introduce a physics informed loss based on dynamic equilibrium using precomputed mass, damping, and stiffness matrices, without solving the governing PDEs directly. Further, a Schur complement formulation reduces the training domain, significantly cutting computational costs while preserving global accuracy. The model is validated on both a simple beam and the KW-51 bridge, achieving FEM level accuracy within seconds. Compared to GRU based DeepONet, our model offers comparable accuracy with improved temporal continuity and over 100 times faster inference, making it well suited for real-time structural monitoring and digital twin applications.

cs.LG

Damage identification for bridges using machine learning: Development and application to KW51 bridge

The available tools for damage identification in civil engineering structures are known to be computationally expensive and data-demanding. This paper proposes a comprehensive machine learning based damage identification (CMLDI) method that integrates modal analysis and dynamic analysis strategies. The proposed approach is applied to a real structure - KW51 railway bridge in Leuven. CMLDI diligently combines signal processing, machine learning (ML), and structural analysis techniques to achieve a fast damage identification solver that relies on minimal monitoring data. CMLDI considers modal analysis inputs and extracted features from acceleration responses to inform the damage identification based on the long-term and short-term monitoring data. Results of operational modal analysis, through the analysis of long-term monitoring data, are analyzed using pre-trained k-nearest neighbor (kNN) classifiers to identify damage existence, location, and magnitude. A well-crafted assembly of signal processing and ML methods is used to analyze acceleration time histories. Stacked gated recurrent unit (Stacked GRU) networks are used to identify damage existence, kNN classifiers are used to identify damage magnitude, and convolutions neural networks (CNN) are used to identify damage location. The damage identification results for the KW51 bridge demonstrate this approach's high accuracy, efficiency, and robustness. In this work, the training data is retrieved from the sensor of the KW51 bridge as well as the numerical finite element model (FEM). The proposed approach presents a systematic path to the generation of training data using a validated FEM. The data generation relies on modeling combinations of damage locations and magnitudes along the bridge.

eess.SP

Physics-informed DeepONet with stiffness-based loss functions for structural response prediction

Finite element modeling is a well-established tool for structural analysis, yet modeling complex structures often requires extensive pre-processing, significant analysis effort, and considerable time. This study addresses this challenge by introducing an innovative method for real-time prediction of structural static responses using DeepOnet which relies on a novel approach to physics-informed networks driven by structural balance laws. This approach offers the flexibility to accurately predict responses under various load classes and magnitudes. The trained DeepONet can generate solutions for the entire domain, within a fraction of a second. This capability effectively eliminates the need for extensive remodeling and analysis typically required for each new case in FE modeling. We apply the proposed method to two structures: a simple 2D beam structure and a comprehensive 3D model of a real bridge. To predict multiple variables with DeepONet, we utilize two strategies: a split branch/trunk and multiple DeepONets combined into a single DeepONet. In addition to data-driven training, we introduce a novel physics-informed training approaches. This method leverages structural stiffness matrices to enforce fundamental equilibrium and energy conservation principles, resulting in two novel physics-informed loss functions: energy conservation and static equilibrium using the Schur complement. We use various combinations of loss functions to achieve an error rate of less than 5% with significantly reduced training time. This study shows that DeepONet, enhanced with hybrid loss functions, can accurately and efficiently predict displacements and rotations at each mesh point, with reduced training time.

cs.LG

BIOPAK Flasher: Epidemic disease monitoring and detection in Pakistan using text mining

Infectious disease outbreak has a significant impact on morbidity, mortality and can cause economic instability of many countries. As global trade is growing, goods and individuals are expected to travel across the border, an infected epidemic area carrier can pose a great danger to his hostile. If a disease outbreak is recognized promptly, then commercial products and travelers (traders/visitors) will be effectively vaccinated, and therefore the disease stopped. Early detection of outbreaks plays an important role here, and beware of the rapid implementation of control measures by citizens, public health organizations, and government. Many indicators have valuable information, such as online news sources (RSS) and social media sources (Twitter, Facebook) that can be used, but are unstructured and bulky, to extract information about disease outbreaks. Few early warning outbreak systems exist with some limitation of linguistic (Urdu) and covering areas (Pakistan). In Pakistan, few channels are published the outbreak news in Urdu or English. The aim is to procure information from Pakistan's English and Urdu news channels and then investigate process, integrate, and visualize the disease epidemic. Urdu ontology is not existed before to match extracted diseases, so we also build that ontology of disease.

cs.IR

Fusion of laser diffraction and chord length distribution data for estimation of particle size distribution using multi-objective optimisation

The in situ measurement of the particle size distribution (PSD) of a suspension of particles presents huge challenges. Various effects from the process could introduce noise to the data from which the PSD is estimated. This in turn could lead to the occurrence of artificial peaks in the estimated PSD. Limitations in the models used in the PSD estimation could also lead to the occurrence of these artificial peaks. This could pose a significant challenge to in situ monitoring of particulate processes, as there will be no independent estimate of the PSD to allow a discrimination of the artificial peaks to be carried out. Here, we present an algorithm which is capable of discriminating between artificial and true peaks in PSD estimates based on fusion of multiple data streams. In this case, chord length distribution and laser diffraction data have been used. The data fusion is done by means of multi-objective optimisation using the weighted sum approach. The algorithm is applied to two different particle suspensions. The estimated PSDs from the algorithm are compared with offline estimates of PSD from the Malvern Mastersizer and Morphologi G3. The results show that the algorithm is capable of eliminating an artificial peak in a PSD estimate when this artificial peak is sufficiently displaced from the true peak. However, when the artificial peak is too close to the true peak, it is only suppressed but not completely eliminated.

physics.data-an

Monitoring crystal breakage in wet milling processes using inline imaging and chord length distribution measurements

The success of the various secondary operations involved in the production of particulate products depends on the production of particles with a desired size and shape from a previous primary operation such as crystallisation. This is because these properties of size and shape affect the behaviour of the particles in the secondary processes. The size and the shape of the particles are very sensitive to the conditions of the crystallisation processes, and so control of these processes is essential. This control requires the development of software tools that can effectively and efficiently process the sensor data captured in situ. However, these tools have various strengths and limitations depending on the process conditions and the nature of the particles. In this work, we employ wet milling of crystalline particles as a case study of a process which produces effects typical to crystallisation processes. We study some of the strengths and limitations of our previously introduced tools for estimating the particle size distribution (PSD) and the aspect ratio from chord length distribution (CLD) and imaging data. We find situations where the CLD tool works better than the imaging tool and vice versa. However, in general both tools complement each other, and can therefore be employed in a suitable multi-objective optimisation approach to estimate PSD and aspect ratio.

physics.data-an

Multi-task Learning with Weak Class Labels: Leveraging iEEG to Detect Cortical Lesions in Cryptogenic Epilepsy

Multi-task learning (MTL) is useful for domains in which data originates from multiple sources that are individually under-sampled. MTL methods are able to learn classification models that have higher performance as compared to learning a single model by aggregating all the data together or learning a separate model for each data source. The performance of these methods relies on label accuracy. We address the problem of simultaneously learning multiple classifiers in the MTL framework when the training data has imprecise labels. We assume that there is an additional source of information that provides a score for each instance which reflects the certainty about its label. Modeling this score as being generated by an underlying ranking function, we augment the MTL framework with an added layer of supervision. This results in new MTL methods that are able to learn accurate classifiers while preserving the domain structure provided through the rank information. We apply these methods to the task of detecting abnormal cortical regions in the MRIs of patients suffering from focal epilepsy whose MRI were read as normal by expert neuroradiologists. In addition to the noisy labels provided by the results of surgical resection, we employ the results of an invasive intracranial-EEG exam as an additional source of label information. Our proposed methods are able to successfully detect abnormal regions for all patients in our dataset and achieve a higher performance as compared to baseline methods.

cs.CV

Lexical Normalisation of Twitter Data

Twitter with over 500 million users globally, generates over 100,000 tweets per minute . The 140 character limit per tweet, perhaps unintentionally, encourages users to use shorthand notations and to strip spellings to their bare minimum "syllables" or elisions e.g. "srsly". The analysis of twitter messages which typically contain misspellings, elisions, and grammatical errors, poses a challenge to established Natural Language Processing (NLP) tools which are generally designed with the assumption that the data conforms to the basic grammatical structure commonly used in English language. In order to make sense of Twitter messages it is necessary to first transform them into a canonical form, consistent with the dictionary or grammar. This process, performed at the level of individual tokens ("words"), is called lexical normalisation. This paper investigates various techniques for lexical normalisation of Twitter data and presents the findings as the techniques are applied to process raw data from Twitter.

cs.CL

Predictive Capacity of Meteorological Data - Will it rain tomorrow

With the availability of high precision digital sensors and cheap storage medium, it is not uncommon to find large amounts of data collected on almost all measurable attributes, both in nature and man-made habitats. Weather in particular has been an area of keen interest for researchers to develop more accurate and reliable prediction models. This paper presents a set of experiments which involve the use of prevalent machine learning techniques to build models to predict the day of the week given the weather data for that particular day i.e. temperature, wind, rain etc., and test their reliability across four cities in Australia {Brisbane, Adelaide, Perth, Hobart}. The results provide a comparison of accuracy of these machine learning techniques and their reliability to predict the day of the week by analysing the weather data. We then apply the models to predict weather conditions based on the available data.

cs.LG