arXiv subjects

Muhammad Afzal

Publications and source records attributed to Muhammad Afzal.

9 recordsLinked to original sources

arXiv2026

An AI-Powered Culturally Aware Chatbot for Stress Detection and Wellness Support among Pakistani University Students Using NLP and Machine Learning

With the existing digital mental health tools specifically developed for Western settings, Pakistani students are exposed to a uniquely compounded stress situation in their university that includes academic, financial, familial, and relational stressors, which have become a serious concern for academic and psychological development of students in Pakistani universities. This paper introduces a new, AI-driven and culturally sensitive stress detection and wellness support system that is tailored to the context of Pakistani university students. The system is based on a machine learning model called Random Forest which is trained using a validated student stress data set of 1100 responses on 20 features from psychological, physiological, academic, environmental and social aspects, with an accuracy of 89.09% and a macro F1-score of 0.89, in three stress severity levels. The classification outputs are passed on to an open-source large language model through OpenRouter API, where an appropriately crafted system prompt, culturally aware, gives the model a conversation about wellness, in English, Urdu and Roman Urdu. The second most predictive stress factor in this population identified by feature importance analysis was teacher-student relationship, which is a culturally important stress factor highlighting the need for region-aware mental health systems. Future research will involve primary data collection from students at various academic levels of Pakistani Universities with the validated DASS-21 instrument focusing on the students who are moving from FSc to undergraduate studies, which is a time of being psychologically vulnerable which is under-researched.

cs.AI↗

arXiv2026

A robust a posteriori error estimator for the Oseen problem

A residual-based a posteriori error estimator is proposed for the incompressible Oseen problem in the convection-dominated regime. The SUPG/PSPG/grad-div stabilized finite element method is used as discretization. The error estimator estimates the global error in a norm that is used in the a priori error analysis of the method. Based on several hypotheses concerning the error and interpolation errors, the robustness of the estimator in the convection-dominated regime is proved. Numerical studies support the analytic results. Finally, the extension of the a posteriori error estimator to the steady-state Navier--Stokes equations is discussed.

math.NA↗

arXiv2025

Energy-Efficient Eimeria Parasite Detection Using a Two-Stage Spiking Neural Network Architecture

Coccidiosis, a disease caused by the Eimeria parasite, represents a major threat to the poultry and rabbit industries, demanding rapid and accurate diagnostic tools. While deep learning models offer high precision, their significant energy consumption limits their deployment in resource-constrained environments. This paper introduces a novel two-stage Spiking Neural Network (SNN) architecture, where a pre-trained Convolutional Neural Network is first converted into a spiking feature extractor and then coupled with a lightweight, unsupervised SNN classifier trained with Spike-Timing-Dependent Plasticity (STDP). The proposed model sets a new state-of-the-art, achieving 98.32\% accuracy in Eimeria classification. Remarkably, this performance is accomplished with a significant reduction in energy consumption, showing an improvement of more than 223 times compared to its traditional ANN counterpart. This work demonstrates a powerful synergy between high accuracy and extreme energy efficiency, paving the way for autonomous, low-power diagnostic systems on neuromorphic hardware.

cs.NE↗

arXiv2025

Vacuum Spiker: A Spiking Neural Network-Based Model for Efficient Anomaly Detection in Time Series

Anomaly detection is a key task across domains such as industry, healthcare, and cybersecurity. Many real-world anomaly detection problems involve analyzing multiple features over time, making time series analysis a natural approach for such problems. While deep learning models have achieved strong performance in this field, their trend to exhibit high energy consumption limits their deployment in resource-constrained environments such as IoT devices, edge computing platforms, and wearables. To address this challenge, this paper introduces the \textit{Vacuum Spiker algorithm}, a novel Spiking Neural Network-based method for anomaly detection in time series. It incorporates a new detection criterion that relies on global changes in neural activity rather than reconstruction or prediction error. It is trained using Spike Time-Dependent Plasticity in a novel way, intended to induce changes in neural activity when anomalies occur. A new efficient encoding scheme is also proposed, which discretizes the input space into non-overlapping intervals, assigning each to a single neuron. This strategy encodes information with a single spike per time step, improving energy efficiency compared to conventional encoding methods. Experimental results on publicly available datasets show that the proposed algorithm achieves competitive performance while significantly reducing energy consumption, compared to a wide set of deep learning and machine learning baselines. Furthermore, its practical utility is validated in a real-world case study, where the model successfully identifies power curtailment events in a solar inverter. These results highlight its potential for sustainable and efficient anomaly detection.

cs.LG↗

arXiv2025

Mobile-Driven Incentive Based Exercise for Blood Glucose Control in Type 2 Diabetes

We propose and create an incentive based recommendation algorithm aimed at improving the lifestyle of diabetic patients. This algorithm is integrated into a real world mobile application to provide personalized health recommendations. Initially, users enter data such as step count, calorie intake, gender, age, weight, height and blood glucose levels. When the data is preprocessed, the app identifies the personalized health and glucose management goals. The recommendation engine suggests exercise routines and dietary adjustments based on these goals. As users achieve their goals and follow these recommendations, they receive incentives, encouraging adherence and promoting positive health outcomes. Furthermore, the mobile application allows users to monitor their progress through descriptive analytics, which displays their daily activities and health metrics in graphical form. To evaluate the proposed methodology, the study was conducted with 10 participants, with type 2 diabetes for three weeks. The participants were recruited through advertisements and health expert references. The application was installed on the patient phone to use it for three weeks. The expert was also a part of this study by monitoring the patient health record. To assess the algorithm performance, we computed efficiency and proficiency. As a result, the algorithm showed proficiency and efficiency scores of 90% and 92%, respectively. Similarly, we computed user experience with application in terms of attractiveness, hedonic and pragmatic quality, involving 35 people in the study. As a result, it indicated an overall positive user response. The findings show a clear positive correlation between exercise and rewards, with noticeable improvements observed in user outcomes after exercise.

cs.HC↗

arXiv2022

Acoustic scattering from a wave-bearing cavity with flexible inlet and outlet

In this article, we substantiate the appositeness of the \emph{mode-matching technique} to study the scattering response of bridging elastic plates connecting two flexible duct regions of different heights. We present two different solution schemes to analyze the structure-borne and fluid-borne radiations in the elastic plate-bounded waveguide. The first scheme supplements the mode-matching technique with the so-called \emph{tailored-Galerkin approach} which uses a solution ansatz with homogeneous and integral parts corresponding to the vibrations of the bridging elastic plate and the cavity, respectively. In the second scheme, we supplement the mode-matching technique with the \emph{modal approach} wherein the displacement of the bridging elastic plate is projected onto the eigenmodes of the cavity. To handle the non-orthogonality of the eigenfunctions, we invoke generalized orthogonality relations. An advantage of the proposed mode-matching schemes is that they provide a convenient way of incorporating a variety of edge conditions on the joints of the plates, including clamped, pin-joint, or restraint connections. The numerical analysis of the waveguide scattering problems substantiates that edge connections on the joints have a significant impact on the scattering energies and transmission loss.

physics.class-ph↗

arXiv2019

Precision Medicine Informatics: Principles, Prospects, and Challenges

Precision Medicine (PM) is an emerging approach that appears with the impression of changing the existing paradigm of medical practice. Recent advances in technological innovations and genetics, and the growing availability of health data have set a new pace of the research and imposes a set of new requirements on different stakeholders. To date, some studies are available that discuss about different aspects of PM. Nevertheless, a holistic representation of those aspects deemed to confer the technological perspective, in relation to applications and challenges, is mostly ignored. In this context, this paper surveys advances in PM from informatics viewpoint and reviews the enabling tools and techniques in a categorized manner. In addition, the study discusses how other technological paradigms including big data, artificial intelligence, and internet of things can be exploited to advance the potentials of PM. Furthermore, the paper provides some guidelines for future research for seamless implementation and wide-scale deployment of PM based on identified open issues and associated challenges. To this end, the paper proposes an integrated holistic framework for PM motivating informatics researchers to design their relevant research works in an appropriate context.

cs.CY↗

arXiv2019

Acoustomicrofluidic separation of tardigrades from raw cultures for sample preparation

Tardigrades are microscopic animals widely known for their survival capabilities under extreme conditions. They are the focus of current research in the fields of taxonomy, biogeography, genomics, proteomics, development, space biology, evolution, and ecology. Tardigrades, such as Hypsibius exemplaris, are being advocated as a next-generation model organism for genomic and developmental studies. The raw culture of H. exemplaris usually contains tardigrades themselves, their eggs, and algal food and feces. Experimentation with tardigrades often requires the demanding and laborious separation of tardigrades from raw samples to prepare pure and contamination-free tardigrade samples. In this paper, we propose a two-step acousto-microfluidic separation method to isolate tardigrades from raw samples. In the first step, a passive microfluidic filter composed of an array of traps is used to remove large algal clusters in the raw sample. In the second step, a surface acoustic wave-based active microfluidic separation device is used to continuously deflect tardigrades from their original streamlines inside the microchannel and thus selectively isolate them from algae and eggs. The experimental results demonstrated the efficient tardigrade separation with a recovery rate of 96% and an algae impurity of 4% on average in a continuous, contactless, automated, rapid, biocompatible manner.

q-bio.QM↗

arXiv2018

Microparticles self-assembly induced by travelling surface acoustic waves

We present an acoustofluidic method based on travelling surface acoustic waves (TSAWs) for the induction of the self-assembly of microparticles inside a microfluidic channel. The particles are trapped above an interdigitated transducer, placed directly beneath the microchannel, by the TSAW-based direct acoustic radiation force (ARF). This approach was applied to 10 {\mu}m polystyrene particles, which were pushed towards the ceiling of the microchannel by 72 MHz TSAWs to form single- and multiple-layer colloidal structures. The repair of cracks and defects within the crystal lattice occurs as part of the self-assembly process. The sample flow through the first inlet can be switched with a buffer flow through a second inlet to control the number of particles in the crystalline structure. The constant flow-induced Stokes drag force on the parti-cles is balanced by the opposing TSAW-based ARF. This force balance is essential for the acoustics-based self-assembly of microparticles inside the microchannel. Moreover, we studied the effects of varying the input voltage and fluid flow rate on the position and shape of the colloidal structure. The active self-assembly of microparticles into crystals with multiple layers can be used in the bottom-up fabrication of colloidal structures with dimensions greater than 500 {\mu}m x 500 {\mu}m, which is expected to have important applications in various fields.

cond-mat.soft↗