Mohammad Arif Ul Alam

Md Mahmudur Rahman, Mahta Mousavi, Peri Tarr et al.

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.

Yidong Zhu, Md Mahmudur Rahman, Mohammad Arif Ul Alam

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.

Yidong Zhu, Shao-Hsien Liu, Mohammad Arif Ul Alam

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%.

Forsad Al Hossain, Tanjid Hasan Tonmoy, Andrew A. Lover et al.

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.

Yidong Zhu, Nadia B Aimandi, Mohammad Arif Ul Alam

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.

Mohammad Arif Ul Alam

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.

Mohammad Arif Ul Alam

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.

Vaishali Mahipal, Mohammad Arif Ul Alam

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.

Md Mahmudur Rahman, Tauhidur Rahman, Donghyun Kim et al.

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.

Mohammad Arif Ul Alam

Cognitive fatigue has been a common problem among workers which has become an increasing global problem since the emergence of COVID-19 as a global pandemic. While existing multi-modal wearable sensors-aided automatic cognitive fatigue monitoring tools have focused on physical and physiological sensors (ECG, PPG, Actigraphy) analytic on specific group of people (say gamers, athletes, construction workers), activity-awareness is utmost importance due to its different responses on physiology in different person. In this paper, we propose a novel framework, Activity-Aware Recurrent Neural Network (\emph{AcRoNN}), that can generalize individual activity recognition and improve cognitive fatigue estimation significantly. We evaluate and compare our proposed method with state-of-art methods using one real-time collected dataset from 5 individuals and another publicly available dataset from 27 individuals achieving max. 19% improvement.