arXiv subjects

Mohammad Arif Ul Alam

Publications and source records attributed to Mohammad Arif Ul Alam.

At least 19 recordsLinked to original sources

arXiv2026

Real-Time Musculoskeletal Surrogates for Pediatric Cerebral Palsy: a Credibility Pilot

Real-time musculoskeletal (MSK) surrogates could support personalized rehabilitation for children with cerebral palsy (CP), but their credibility depends on subject-wise evaluation, low inference latency, and calibrated uncertainty. We develop a subject-conditioned causal neural surrogate using OpenSim-derived static parameters, temporal joint kinematics, true muscle capacities, and training-only perturbations. On a real pediatric CP gait dataset comprising nine children, we use leave-one-subject-out validation on six development subjects and evaluate a frozen configuration once on three locked test subjects. The surrogate accurately reproduces musculotendon lengths (R-square = 0.92 in development validation and approximately 0.95 on locked subjects; nRMSE < 8%) while requiring only sub-millisecond to few-millisecond neural inference, well below a 100 ms interactive-rehabilitation target. In contrast, direct muscle-force estimation remains unstable at this small, heterogeneous scale: pooled metrics can overstate within-subject, per-muscle accuracy. A Monte Carlo credibility pilot further shows that propagating only +/-5% anthropometry and muscle-capacity variation produces severely overconfident nominal 90% intervals (approximately 4% force coverage and below 1% MT-length coverage). These results establish a leakage-free evaluation and credibility framework for pediatric MSK surrogates, while identifying force modeling and epistemic uncertainty as the central next challenges for clinically credible digital twins.

cs.CV↗

arXiv2026

Robust Cross-Modal Foundation Model Perception for Underwater Robots under Degraded Visual Conditions

Reliable underwater robotic perception remains difficult because optical imagery degrades under turbidity, wavelength-dependent attenuation, low illumination, scattering, and blur. Although sonar provides complementary information that is less affected by optical visibility, prior visual-sonar research has largely focused on feature alignment and nominal detection performance. We investigate cross-modal robustness as visual reliability deteriorates and assess whether pretrained visual foundation-model representations can be complemented by sonar under severe degradation. We use frozen DINOv2 as the visual encoder and construct a controlled five-level benchmark ranging from clean to extreme visual conditions. We compare conventional visual detection, frozen foundation-model representations, sonar context, fixed multimodal fusion, clean-trained adaptive gating, and degradation-aware gated fusion. Our method trains the fusion mechanism across the full range of degradation while keeping the visual and sonar encoders frozen, allowing modality contributions to adapt without fine-tuning the pretrained backbone. Under extreme combined degradation, the DINOv2 baseline achieves 0.4610 balanced accuracy, while degradation-aware visual-sonar fusion reaches 0.6152, a 33.5% relative improvement. The learned sonar contribution increases from 14.2% under clean conditions to 41.3% under extreme degradation, demonstrating adaptive redistribution of cross-modal reliance. Fusion provides the largest gains under severe turbidity and blur, whereas color attenuation alone yields little additional benefit. These results show that foundation-model representations remain valuable but insufficient under severe information loss, and that explicitly adapting fusion to modality reliability can improve robust underwater multimodal perception.

cs.CV↗

arXiv2026

Multi-Level Privacy-Preserving Dementia Detection from Speech via Targeted Adversarial Obfuscation and Representation Learning

Speech recordings used for dementia detection inherently expose speaker identity, raising critical privacy concerns. Existing methods typically address only singular threats and fail to resolve the privacy--utility trade-off. We propose a multi-level framework designed to neutralize two distinct eavesdropping vectors. At the signal level, a Cumulative Signal Attack (CSA) concentrates perturbations in keyword-aligned regions to maximize transcription error (Word Error Rate WER = 1.00) while preserving vital prosodic biomarkers. At the feature level, a Gradient Reversal Layer (GRL) with Mutual Information (MI)-guided noise injection suppresses speaker-discriminative dimensions while retaining dementia-relevant diagnostic structure. Evaluated on the DementiaBank Pitt Corpus, our framework achieves near-chance speaker identification (Equal Error Rate EER = 0.59, F1 = 0.003) while maintaining strong dementia classification performance (F1 = 0.78, AUC = 0.86).

cs.SD↗

arXiv2025

Wearable-based Fair and Accurate Pain Assessment Using Multi-Attribute Fairness Loss in Convolutional Neural Networks

The integration of diverse health data, such as IoT (Internet of Things), EHR (Electronic Health Record), and clinical surveys, with scalable AI(Artificial Intelligence) has enabled the identification of physical, behavioral, and psycho-social indicators of pain. However, the adoption of AI in clinical pain evaluation is hindered by challenges like personalization and fairness. Many AI models, including machine and deep learning, exhibit biases, discriminating against specific groups based on gender or ethnicity, causing skepticism among medical professionals about their reliability. This paper proposes a Multi-attribute Fairness Loss (MAFL) based Convolutional Neural Network (CNN) model designed to account for protected attributes in data, ensuring fair pain status predictions while minimizing disparities between privileged and unprivileged groups. We evaluate whether a balance between accuracy and fairness is achievable by comparing the proposed model with existing mitigation methods. Our findings indicate that the model performs favorably against state-of-the-art techniques. Using the NIH All-Of-US dataset, comprising data from 868 individuals over 1500 days, we demonstrate our model's effectiveness, achieving accuracy rates between 75% and 85%.

eess.SP↗

arXiv2024

HydroTrack: Spectroscopic Analysis Prototype Enabling Real-Time Hydration Monitoring in Wearables

In the rapidly growing field of wearable technology, optical devices are emerging as a significant innovation, offering non-invasive methods for analyzing skin and underlying tissue properties. Despite their promise, progress has been slowed by a lack of specialized prototypes and advanced analysis techniques. Addressing this gap, our study introduces, HydroTrack, an 18-channel spectroscopy sensor, ingeniously embedded in a smart-watch. Accompanying this hardware, we present signal processing and data analysis techniques implemented at the edge, designed to maximize the utility of our system in comprehensive health tracking. A pivotal application of our device is the real-time assessment of hydration levels in physically active individuals. We validated our prototype and analytical approach through experiments on six participants, focusing on hydration dynamics during physical exercises. Our findings reveal an accuracy of avg. 95% in determining hydration states.

cs.HC↗

arXiv2024

Enhancing Wearable based Real-Time Glucose Monitoring via Phasic Image Representation Learning based Deep Learning

In the U.S., over a third of adults are pre-diabetic, with 80\% unaware of their status. This underlines the need for better glucose monitoring to prevent type 2 diabetes and related heart diseases. Existing wearable glucose monitors are limited by the lack of models trained on small datasets, as collecting extensive glucose data is often costly and impractical. Our study introduces a novel machine learning method using modified recurrence plots in the frequency domain to improve glucose level prediction accuracy from wearable device data, even with limited datasets. This technique combines advanced signal processing with machine learning to extract more meaningful features. We tested our method against existing models using historical data, showing that our approach surpasses the current 87\% accuracy benchmark in predicting real-time interstitial glucose levels.

eess.SP↗

arXiv2023

Crowdotic: A Privacy-Preserving Hospital Waiting Room Crowd Density Estimation with Non-speech Audio

Privacy-preserving crowd density analysis finds application across a wide range of scenarios, substantially enhancing smart building operation and management while upholding privacy expectations in various spaces. We propose a non-speech audio-based approach for crowd analytics, leveraging a transformer-based model. Our results demonstrate that non-speech audio alone can be used to conduct such analysis with remarkable accuracy. To the best of our knowledge, this is the first time when non-speech audio signals are proposed for predicting occupancy. As far as we know, there has been no other similar approach of its kind prior to this. To accomplish this, we deployed our sensor-based platform in the waiting room of a large hospital with IRB approval over a period of several months to capture non-speech audio and thermal images for the training and evaluation of our models. The proposed non-speech-based approach outperformed the thermal camera-based model and all other baselines. In addition to demonstrating superior performance without utilizing speech audio, we conduct further analysis using differential privacy techniques to provide additional privacy guarantees. Overall, our work demonstrates the viability of employing non-speech audio data for accurate occupancy estimation, while also ensuring the exclusion of speech-related content and providing robust privacy protections through differential privacy guarantees.

cs.SD↗

arXiv2023

Augmenting Deep Learning Adaptation for Wearable Sensor Data through Combined Temporal-Frequency Image Encoding

Deep learning advancements have revolutionized scalable classification in many domains including computer vision. However, when it comes to wearable-based classification and domain adaptation, existing computer vision-based deep learning architectures and pretrained models trained on thousands of labeled images for months fall short. This is primarily because wearable sensor data necessitates sensor-specific preprocessing, architectural modification, and extensive data collection. To overcome these challenges, researchers have proposed encoding of wearable temporal sensor data in images using recurrent plots. In this paper, we present a novel modified-recurrent plot-based image representation that seamlessly integrates both temporal and frequency domain information. Our approach incorporates an efficient Fourier transform-based frequency domain angular difference estimation scheme in conjunction with the existing temporal recurrent plot image. Furthermore, we employ mixup image augmentation to enhance the representation. We evaluate the proposed method using accelerometer-based activity recognition data and a pretrained ResNet model, and demonstrate its superior performance compared to existing approaches.

cs.CV↗

arXiv2023

Internet of Things Fault Detection and Classification via Multitask Learning

This paper presents a comprehensive investigation into developing a fault detection and classification system for real-world IIoT applications. The study addresses challenges in data collection, annotation, algorithm development, and deployment. Using a real-world IIoT system, three phases of data collection simulate 11 predefined fault categories. We propose SMTCNN for fault detection and category classification in IIoT, evaluating its performance on real-world data. SMTCNN achieves superior specificity (3.5%) and shows significant improvements in precision, recall, and F1 measures compared to existing techniques.

cs.LG↗

arXiv2023

Recent Trend of Nanotechnology Applications to Improve Bio-accessibility of Lycopene by Nanocarrier: A Review

Lycopene, rich in red, yellow, or orange-colored fruits and vegetables, is the most potent antioxidant among the other carotenoids available in human blood plasma. It is evident that regular lycopene intake can prevent chronic diseases like cardiovascular diseases, type-2 diabetes, hypertension, kidney diseases and cancer. However, thermal processing, light, oxygen, and enzymes in gastrointestinal tract (GIT) compromise the bioaccessibility and bioavailability of lycopene ingested through diet. Nanoencapsulation provides a potential platform to prevent lycopene from light, air oxygen, thermal processing and enzymatic activity of the human digestive system. Physicochemical properties evidenced to be the potential indicator for determining the bioaccessibility of encapsulated bioactive compounds like lycopene. By manipulating the size or hydrodynamic diameter, zeta potential value or stability, polydispersity index or homogeneity and functional activity or retention of antioxidant properties observed to be the most prominent physicochemical properties to evaluate beneficial effect of implementation of nanotechnology on bioaccessibility study. Moreover, the molecular mechanism of the bioavailability of nanoparticles is not yet to be understood due to lack of comprehensive design to identify nanoparticles' behaviors if ingested through oral route as functional food ingredients. This review paper aims to study and leverage existing techniques about how nanotechnology can be used and verified to identify the bioaccessibility of lycopene before using it as a functional food ingredient for therapeutic treatments.

q-bio.BM↗

arXiv2022

PALMAR: Towards Adaptive Multi-inhabitant Activity Recognition in Point-Cloud Technology

With the advancement of deep neural networks and computer vision-based Human Activity Recognition, employment of Point-Cloud Data technologies (LiDAR, mmWave) has seen a lot interests due to its privacy preserving nature. Given the high promise of accurate PCD technologies, we develop, PALMAR, a multiple-inhabitant activity recognition system by employing efficient signal processing and novel machine learning techniques to track individual person towards developing an adaptive multi-inhabitant tracking and HAR system. More specifically, we propose (i) a voxelized feature representation-based real-time PCD fine-tuning method, (ii) efficient clustering (DBSCAN and BIRCH), Adaptive Order Hidden Markov Model based multi-person tracking and crossover ambiguity reduction techniques and (iii) novel adaptive deep learning-based domain adaptation technique to improve the accuracy of HAR in presence of data scarcity and diversity (device, location and population diversity). We experimentally evaluate our framework and systems using (i) a real-time PCD collected by three devices (3D LiDAR and 79 GHz mmWave) from 6 participants, (ii) one publicly available 3D LiDAR activity data (28 participants) and (iii) an embedded hardware prototype system which provided promising HAR performances in multi-inhabitants (96%) scenario with a 63% improvement of multi-person tracking than state-of-art framework without losing significant system performances in the edge computing device.

cs.CV↗

arXiv2022

PhysioGait: Context-Aware Physiological Context Modeling for Person Re-identification Attack on Wearable Sensing

Person re-identification is a critical privacy breach in publicly shared healthcare data. We investigate the possibility of a new type of privacy threat on publicly shared privacy insensitive large scale wearable sensing data. In this paper, we investigate user specific biometric signatures in terms of two contextual biometric traits, physiological (photoplethysmography and electrodermal activity) and physical (accelerometer) contexts. In this regard, we propose PhysioGait, a context-aware physiological signal model that consists of a Multi-Modal Siamese Convolutional Neural Network (mmSNN) which learns the spatial and temporal information individually and performs sensor fusion in a Siamese cost with the objective of predicting a person's identity. We evaluated PhysioGait attack model using 4 real-time collected datasets (3-data under IRB #HP-00064387 and one publicly available data) and two combined datasets achieving 89% - 93% accuracy of re-identifying persons.

eess.SP↗

arXiv2022

Semi-Supervised Domain Adaptation with Auto-Encoder via Simultaneous Learning

We present a new semi-supervised domain adaptation framework that combines a novel auto-encoder-based domain adaptation model with a simultaneous learning scheme providing stable improvements over state-of-the-art domain adaptation models. Our framework holds strong distribution matching property by training both source and target auto-encoders using a novel simultaneous learning scheme on a single graph with an optimally modified MMD loss objective function. Additionally, we design a semi-supervised classification approach by transferring the aligned domain invariant feature spaces from source domain to the target domain. We evaluate on three datasets and show proof that our framework can effectively solve both fragile convergence (adversarial) and weak distribution matching problems between source and target feature space (discrepancy) with a high `speed' of adaptation requiring a very low number of iterations.

cs.CV↗

arXiv2022

Enabling Heterogeneous Domain Adaptation in Multi-inhabitants Smart Home Activity Learning

Domain adaptation for sensor-based activity learning is of utmost importance in remote health monitoring research. However, many domain adaptation algorithms suffer with failure to operate adaptation in presence of target domain heterogeneity (which is always present in reality) and presence of multiple inhabitants dramatically hinders their generalizability producing unsatisfactory results for semi-supervised and unseen activity learning tasks. We propose \emph{AEDA}, a novel deep auto-encoder-based model to enable semi-supervised domain adaptation in the existence of target domain heterogeneity and how to incorporate it to empower heterogeneity to any homogeneous deep domain adaptation architecture for cross-domain activity learning. Experimental evaluation on 18 different heterogeneous and multi-inhabitants use-cases of 8 different domains created from 2 publicly available human activity datasets (wearable and ambient smart homes) shows that \emph{AEDA} outperforms (max. 12.8\% and 8.9\% improvements for ambient smart home and wearables) over existing domain adaptation techniques for both seen and unseen activity learning in a heterogeneous setting.

cs.AI↗

arXiv2022

Estimating Heterogeneous Causal Effect of Polysubstance Usage on Drug Overdose from Large-Scale Electronic Health Record

Drug overdose has become a public health crisis in the United States with devastating consequences. However, most of the drug overdose incidences are the consequence of recitative polysubstance usage over a defined period of time which can be happened by either the intentional usage of required drug with other drugs or by accident. Thus, predicting the effects of polysubstance usage is extremely important for clinicians to decide which combination of drugs should be prescribed. Recent advancement of structural causal models can provide ample insights of causal effects from observational data via identifiable causal directed graphs. In this paper, we propose a system to estimate heterogeneous concurrent drug usage effects on overdose estimation, that consists of efficient co-variate selection, sub-group selection and heterogeneous causal effect estimation. We apply our framework to answer a critical question, can concurrent usage of benzodiazepines and opioids have heterogeneous causal effects on the opioid overdose epidemic? Using Truven MarketScan claim data collected from 2001 to 2013 have shown significant promise of our proposed framework's efficacy.

cs.AI↗

arXiv2021

College Student Retention Risk Analysis From Educational Database using Multi-Task Multi-Modal Neural Fusion

We develop a Multimodal Spatiotemporal Neural Fusion network for Multi-Task Learning (MSNF-MTCL) to predict 5 important students' retention risks: future dropout, next semester dropout, type of dropout, duration of dropout and cause of dropout. First, we develop a general purpose multi-modal neural fusion network model MSNF for learning students' academic information representation by fusing spatial and temporal unstructured advising notes with spatiotemporal structured data. MSNF combines a Bidirectional Encoder Representations from Transformers (BERT)-based document embedding framework to represent each advising note, Long-Short Term Memory (LSTM) network to model temporal advising note embeddings, LSTM network to model students' temporal performance variables and students' static demographics altogether. The final fused representation from MSNF has been utilized on a Multi-Task Cascade Learning (MTCL) model towards building MSNF-MTCL for predicting 5 student retention risks. We evaluate MSNFMTCL on a large educational database consists of 36,445 college students over 18 years period of time that provides promising performances comparing with the nearest state-of-art models. Additionally, we test the fairness of such model given the existence of biases.

cs.CL↗

arXiv2021

Knowledge Transfer across Imaging Modalities Via Simultaneous Learning of Adaptive Autoencoders for High-Fidelity Mobile Robot Vision

Enabling mobile robots for solving challenging and diverse shape, texture, and motion related tasks with high fidelity vision requires the integration of novel multimodal imaging sensors and advanced fusion techniques. However, it is associated with high cost, power, hardware modification, and computing requirements which limit its scalability. In this paper, we propose a novel Simultaneously Learned Auto Encoder Domain Adaptation (SAEDA)-based transfer learning technique to empower noisy sensing with advanced sensor suite capabilities. In this regard, SAEDA trains both source and target auto-encoders together on a single graph to obtain the domain invariant feature space between the source and target domains on simultaneously collected data. Then, it uses the domain invariant feature space to transfer knowledge between different signal modalities. The evaluation has been done on two collected datasets (LiDAR and Radar) and one existing dataset (LiDAR, Radar and Video) which provides a significant improvement in quadruped robot-based classification (home floor and human activity recognition) and regression (surface roughness estimation) problems. We also integrate our sensor suite and SAEDA framework on two real-time systems (vacuum cleaning and Mini-Cheetah quadruped robots) for studying the feasibility and usability.

cs.RO↗

arXiv2021

Person Re-identification Attack on Wearable Sensing

Person re-identification is a critical privacy attack in publicly shared healthcare data as per Health Insurance Portability and Accountability Act (HIPAA) privacy rule. In this paper, we investigate the possibility of a new type of privacy attack, Person Re-identification Attack (PRI-attack) on publicly shared privacy insensitive wearable data. We investigate user's specific biometric signature in terms of two contextual biometric traits, physiological (photoplethysmography and electrodermal activity) and physical (accelerometer) contexts. In this regard, we develop a Multi-Modal Siamese Convolutional Neural Network (mmSNN) model. The framework learns the spatial and temporal information individually and combines them together in a modified weighted cost with an objective of predicting a person's identity. We evaluated our proposed model using real-time collected data from 3 collected datasets and one publicly available dataset. Our proposed framework shows that PPG-based breathing rate and heart rate in conjunction with hand gesture contexts can be utilized by attackers to re-identify user's identity (max. 71%) from HIPAA compliant wearable data. Given publicly placed camera can estimate heart rate and breathing rate along with hand gestures remotely, person re-identification using them imposes a significant threat to future HIPAA compliant server which requires a better encryption method to store wearable healthcare data.

cs.CR↗