More Like this

1. Improving Out-of-distribution Human Activity Recognition via IMU-Video Cross-modal Representation Learning

   Cheshmi, Seyyed Saeid; Lyu, Buyao; Lisko, Thomas; Rajamani, Rajesh; McGovern, Robert A; Varatharajah, Yogatheesan (August 2025, Proceedings of the 10th Machine Learning for Healthcare Conference, PMLR)

   Human Activity Recognition (HAR) based on wearable inertial sensors plays a critical role in remote health monitoring. In patients with movement disorders, the ability to detect abnormal patient movements in their home environments can enable continuous optimization of treatments and help alert caretakers as needed. Machine learning approaches have been proposed for HAR tasks using Inertial Measurement Unit (IMU) data; however, most rely on application-specific labels and lack generalizability to data collected in different environments or populations. To address this limitation, we propose a new cross-modal self-supervised pretraining approach to learn representations from large-sale unlabeled IMU-video data and demonstrate improved generalizability in HAR tasks on out of distribution (OOD) IMU datasets, including a dataset collected from patients with Parkinson’s disease. Specifically, our results indicate that the proposed cross-modal pretraining approach outperforms the current state-of-the-art IMU-video pretraining approach and IMU-only pretraining under zero-shot and few-shot evaluations. Broadly, our study provides evidence that in highly dynamic data modalities, such as IMU signals, cross-modal pretraining may be a useful tool to learn generalizable data representations. 

   more » « less
2. VideoSSL: Semi-Supervised Learning for Video Classification

   Jing, L; Parag, T; Wu, Z; Tian, Y; Wang, H. (January 2021, Winter Conference on Applications of Computer Vision (WACV), 2021.)

   null (Ed.)

   We propose a semi-supervised learning approach for video classification, VideoSSL, using convolutional neural networks (CNN). Like other computer vision tasks, existing supervised video classification methods demand a large amount of labeled data to attain good performance. However, annotation of a large dataset is expensive and time consuming. To minimize the dependence on a large annotated dataset, our proposed semi-supervised method trains from a small number of labeled examples and exploits two regulatory signals from unlabeled data. The first signal is the pseudo-labels of unlabeled examples computed from the confidences of the CNN being trained. The other is the normalized probabilities, as predicted by an image classifier CNN, that captures the information about appearances of the interesting objects in the video. We show that, under the supervision of these guiding signals from unlabeled examples, a video classification CNN can achieve impressive performances utilizing a small fraction of annotated examples on three publicly available datasets: UCF101, HMDB51, and Kinetics. 

   more » « less
3. A Multi-Sensor Dataset for Human Activity Recognition Using Inertial and Orientation Data

   https://doi.org/10.3390/data10080129  

   Rivas-Caicedo, Jhonathan L; Saldaña-Aristizabal, Laura; Niño-Tejada, Kevin; Patarroyo-Montenegro, Juan F (August 2025, Data)

   Human Activity Recognition (HAR) using wearable sensors is an increasingly relevant area for applications in healthcare, rehabilitation, and human–computer interaction. However, publicly available datasets that provide multi-sensor, synchronized data combining inertial and orientation measurements are still limited. This work introduces a publicly available dataset for Human Activity Recognition, captured using wearable sensors placed on the chest, hands, and knees. Each device recorded inertial and orientation data during controlled activity sessions involving participants aged 20 to 70. A standardized acquisition protocol ensured consistent temporal alignment across all signals. The dataset was preprocessed and segmented using a sliding window approach. An initial baseline classification experiment, employing a Convolutional Neural Network (CNN) and Long-Short Term Memory (LSTM) model, demonstrated an average accuracy of 93.5% in classifying activities. The dataset is publicly available in CSV format and includes raw sensor signals, activity labels, and metadata. This dataset offers a valuable resource for evaluating machine learning models, studying distributed HAR approaches, and developing robust activity recognition pipelines utilizing wearable technologies. 

   more » « less
4. Self-Supervised Learning for Online Anomaly Detection in High-Dimensional Data Streams

   https://doi.org/10.3390/electronics12091971  

   Mozaffari, Mahsa; Doshi, Keval; Yilmaz, Yasin (May 2023, Electronics)

   In this paper, we address the problem of detecting and learning anomalies in high-dimensional data-streams in real-time. Following a data-driven approach, we propose an online and multivariate anomaly detection method that is suitable for the timely and accurate detection of anomalies. We propose our method for both semi-supervised and supervised settings. By combining the semi-supervised and supervised algorithms, we present a self-supervised online learning algorithm in which the semi-supervised algorithm trains the supervised algorithm to improve its detection performance over time. The methods are comprehensively analyzed in terms of computational complexity, asymptotic optimality, and false alarm rate. The performances of the proposed algorithms are also evaluated using real-world cybersecurity datasets, that show a significant improvement over the state-of-the-art results. 

   more » « less
5. SensorGAN: A Novel Data Recovery Approach for Wearable Human Activity Recognition

   https://doi.org/10.1145/3609425  

   Hussein, Dina; Bhat, Ganapati (May 2024, ACM Transactions on Embedded Computing Systems)

   Human activity recognition (HAR) and, more broadly, activities of daily life recognition using wearable devices have the potential to transform a number of applications, including mobile healthcare, smart homes, and fitness monitoring. Recent approaches for HAR use multiple sensors on various locations on the body to achieve higher accuracy for complex activities. While multiple sensors increase the accuracy, they are also susceptible to reliability issues when one or more sensors are unable to provide data to the application due to sensor malfunction, user error, or energy limitations. Training multiple activity classifiers that use a subset of sensors is not desirable, since it may lead to reduced accuracy for applications. To handle these limitations, we propose a novel generative approach that recovers the missing data of sensors using data available from other sensors. The recovered data are then used to seamlessly classify activities. Experiments using three publicly available activity datasets show that with data missing from one sensor, the proposed approach achieves accuracy that is within 10% of the accuracy with no missing data. Moreover, implementation on a wearable device prototype shows that the proposed approach takes about 1.5 ms for recovering data in the w-HAR dataset, which results in an energy consumption of 606 μJ. The low-energy consumption ensures that SensorGAN is suitable for effectively recovering data in tinyML applications on energy-constrained devices. 

   more » « less