A Wearable Multi-Modal Edge-Computing System for Real-Time Kitchen Activity Recognition

In the human activity recognition research area, prior studies predominantly concentrate on leveraging advanced algorithms on public datasets to enhance recognition performance, little attention has been paid to executing real-time kitchen activity recognition on energy-efficient, cost-effective edge devices. Besides, the prevalent approach of segregating data collection and context extraction across different devices escalates power usage, latency, and user privacy risks, impeding widespread adoption. This work presents a multi-modal wearable edge computing system for human activity recognition in real-time. Integrating six different sensors, ranging from inertial measurement units (IMUs) to thermal cameras, and two different microcontrollers, this system achieves end-to-end activity recognition, from data capture to context extraction, locally. Evaluation in an unmodified realistic kitchen validates its efficacy in recognizing fifteen activities, including a null class. Employing a compact machine learning model (184.5 kbytes) yields an average accuracy of 87.83 \%, with model inference completed in 25.26 ms on the microcontroller. Comparative analysis with alternative microcontrollers showcases power consumption and inference speed performance, demonstrating the proposed system's viability.

TSAK: Two-Stage Semantic-Aware Knowledge Distillation for Efficient Wearable Modality and Model Optimization in Manufacturing Lines

Smaller machine learning models, with less complex architectures and sensor inputs, can benefit wearable sensor-based human activity recognition (HAR) systems in many ways, from complexity and cost to battery life. In the specific case of smart factories, optimizing human-robot collaboration hinges on the implementation of cutting-edge, human-centric AI systems. To this end, workers' activity recognition enables accurate quantification of performance metrics, improving efficiency holistically. We present a two-stage semantic-aware knowledge distillation (KD) approach, TSAK, for efficient, privacy-aware, and wearable HAR in manufacturing lines, which reduces the input sensor modalities as well as the machine learning model size, while reaching similar recognition performance as a larger multi-modal and multi-positional teacher model. The first stage incorporates a teacher classifier model encoding attention, causal, and combined representations. The second stage encompasses a semantic classifier merging the three representations from the first stage. To evaluate TSAK, we recorded a multi-modal dataset at a smart factory testbed with wearable and privacy-aware sensors (IMU and capacitive) located on both workers' hands. In addition, we evaluated our approach on OpenPack, the only available open dataset mimicking the wearable sensor placements on both hands in the manufacturing HAR scenario. We compared several KD strategies with different representations to regulate the training process of a smaller student model. Compared to the larger teacher model, the student model takes fewer sensor channels from a single hand, has 79% fewer parameters, runs 8.88 times faster, and requires 96.6% less computing power (FLOPS).

ALS-HAR: Harnessing Wearable Ambient Light Sensors to Enhance IMU-based Human Activity Recogntion

Despite the widespread integration of ambient light sensors (ALS) in smart devices commonly used for screen brightness adaptation, their application in human activity recognition (HAR), primarily through body-worn ALS, is largely unexplored. In this work, we developed ALS-HAR, a robust wearable light-based motion activity classifier. Although ALS-HAR achieves comparable accuracy to other modalities, its natural sensitivity to external disturbances, such as changes in ambient light, weather conditions, or indoor lighting, makes it challenging for daily use. To address such drawbacks, we introduce strategies to enhance environment-invariant IMU-based activity classifications through augmented multi-modal and contrastive classifications by transferring the knowledge extracted from the ALS. Our experiments on a real-world activity dataset for three different scenarios demonstrate that while ALS-HAR's accuracy strongly relies on external lighting conditions, cross-modal information can still improve other HAR systems, such as IMU-based classifiers.Even in scenarios where ALS performs insufficiently, the additional knowledge enables improved accuracy and macro F1 score by up to 4.2 % and 6.4 %, respectively, for IMU-based classifiers and even surpasses multi-modal sensor fusion models in two of our three experiment scenarios. Our research highlights the untapped potential of ALS integration in advancing sensor-based HAR technology, paving the way for practical and efficient wearable ALS-based activity recognition systems with potential applications in healthcare, sports monitoring, and smart indoor environments.

BeSound: Bluetooth-Based Position Estimation Enhancing with Cross-Modality Distillation

Smart factories leverage advanced technologies to optimize manufacturing processes and enhance efficiency. Implementing worker tracking systems, primarily through camera-based methods, ensures accurate monitoring. However, concerns about worker privacy and technology protection make it necessary to explore alternative approaches. We propose a non-visual, scalable solution using Bluetooth Low Energy (BLE) and ultrasound coordinates. BLE position estimation offers a very low-power and cost-effective solution, as the technology is available on smartphones and is scalable due to the large number of smartphone users, facilitating worker localization and safety protocol transmission. Ultrasound signals provide faster response times and higher accuracy but require custom hardware, increasing costs. To combine the benefits of both modalities, we employ knowledge distillation (KD) from ultrasound signals to BLE RSSI data. Once the student model is trained, the model only takes as inputs the BLE-RSSI data for inference, retaining the advantages of ubiquity and low cost of BLE RSSI. We tested our approach using data from an experiment with twelve participants in a smart factory test bed environment. We obtained an increase of 11.79% in the F1-score compared to the baseline (target model without KD and trained with BLE-RSSI data only).

Text me the data: Generating Ground Pressure Sequence from Textual Descriptions for HAR

In human activity recognition (HAR), the availability of substantial ground truth is necessary for training efficient models. However, acquiring ground pressure data through physical sensors itself can be cost-prohibitive, time-consuming. To address this critical need, we introduce Text-to-Pressure (T2P), a framework designed to generate extensive ground pressure sequences from textual descriptions of human activities using deep learning techniques. We show that the combination of vector quantization of sensor data along with simple text conditioned auto regressive strategy allows us to obtain high-quality generated pressure sequences from textual descriptions with the help of discrete latent correlation between text and pressure maps. We achieved comparable performance on the consistency between text and generated motion with an R squared value of 0.722, Masked R squared value of 0.892, and FID score of 1.83. Additionally, we trained a HAR model with the the synthesized data and evaluated it on pressure dynamics collected by a real pressure sensor which is on par with a model trained on only real data. Combining both real and synthesized training data increases the overall macro F1 score by 5.9 percent.

ContextMix: A context-aware data augmentation method for industrial visual inspection systems

While deep neural networks have achieved remarkable performance, data augmentation has emerged as a crucial strategy to mitigate overfitting and enhance network performance. These techniques hold particular significance in industrial manufacturing contexts. Recently, image mixing-based methods have been introduced, exhibiting improved performance on public benchmark datasets. However, their application to industrial tasks remains challenging. The manufacturing environment generates massive amounts of unlabeled data on a daily basis, with only a few instances of abnormal data occurrences. This leads to severe data imbalance. Thus, creating well-balanced datasets is not straightforward due to the high costs associated with labeling. Nonetheless, this is a crucial step for enhancing productivity. For this reason, we introduce ContextMix, a method tailored for industrial applications and benchmark datasets. ContextMix generates novel data by resizing entire images and integrating them into other images within the batch. This approach enables our method to learn discriminative features based on varying sizes from resized images and train informative secondary features for object recognition using occluded images. With the minimal additional computation cost of image resizing, ContextMix enhances performance compared to existing augmentation techniques. We evaluate its effectiveness across classification, detection, and segmentation tasks using various network architectures on public benchmark datasets. Our proposed method demonstrates improved results across a range of robustness tasks. Its efficacy in real industrial environments is particularly noteworthy, as demonstrated using the passive component dataset.

The Power of Training: How Different Neural Network Setups Influence the Energy Demand

This work examines the effects of variations in machine learning training regimes and learning paradigms on the corresponding energy consumption. While increasing data availability and innovation in high-performance hardware fuels the training of sophisticated models, it also supports the fading perception of energy consumption and carbon emission. Therefore, the goal of this work is to create awareness about the energy impact of general training parameters and processes, from learning rate over batch size to knowledge transfer. Multiple setups with different hyperparameter initializations are evaluated on two different hardware configurations to obtain meaningful results. Experiments on pretraining and multitask training are conducted on top of the baseline results to determine their potential towards sustainable machine learning.

CoSS: Co-optimizing Sensor and Sampling Rate for Data-Efficient AI in Human Activity Recognition

Recent advancements in Artificial Neural Networks have significantly improved human activity recognition using multiple time-series sensors. While employing numerous sensors with high-frequency sampling rates usually improves the results, it often leads to data inefficiency and unnecessary expansion of the ANN, posing a challenge for their practical deployment on edge devices. Addressing these issues, our work introduces a pragmatic framework for data-efficient utilization in HAR tasks, considering the optimization of both sensor modalities and sampling rate simultaneously. Central to our approach are the designed trainable parameters, termed 'Weight Scores,' which assess the significance of each sensor modality and sampling rate during the training phase. These scores guide the sensor modalities and sampling rate selection. The pruning method allows users to make a trade-off between computational budgets and performance by selecting the sensor modalities and sampling rates according to the weight score ranking. We tested our framework's effectiveness in optimizing sensor modality and sampling rate selection using three public HAR benchmark datasets. The results show that the sensor and sampling rate combination selected via CoSS achieves similar classification performance to configurations using the highest sampling rate with all sensors but at a reduced hardware cost.

Remaining Useful Life Prediction of Lithium-ion Batteries using Spatio-temporal Multimodal Attention Networks

Lithium-ion batteries are widely used in various applications, including electric vehicles and renewable energy storage. The prediction of the remaining useful life (RUL) of batteries is crucial for ensuring reliable and efficient operation, as well as reducing maintenance costs. However, determining the life cycle of batteries in real-world scenarios is challenging, and existing methods have limitations in predicting the number of cycles iteratively. In addition, existing works often oversimplify the datasets, neglecting important features of the batteries such as temperature, internal resistance, and material type. To address these limitations, this paper proposes a two-stage remaining useful life prediction scheme for Lithium-ion batteries using a spatio-temporal multimodal attention network (ST-MAN). The proposed model is designed to iteratively predict the number of cycles required for the battery to reach the end of its useful life, based on available data. The proposed ST-MAN is to capture the complex spatio-temporal dependencies in the battery data, including the features that are often neglected in existing works. Experimental results demonstrate that the proposed ST-MAN model outperforms existing CNN and LSTM-based methods, achieving state-of-the-art performance in predicting the remaining useful life of Li-ion batteries. The proposed method has the potential to improve the reliability and efficiency of battery operations and is applicable in various industries, including automotive and renewable energy.

A Novel Local-Global Feature Fusion Framework for Body-weight Exercise Recognition with Pressure Mapping Sensors

We present a novel local-global feature fusion framework for body-weight exercise recognition with floor-based dynamic pressure maps. One step further from the existing studies using deep neural networks mainly focusing on global feature extraction, the proposed framework aims to combine local and global features using image processing techniques and the YOLO object detection to localize pressure profiles from different body parts and consider physical constraints. The proposed local feature extraction method generates two sets of high-level local features consisting of cropped pressure mapping and numerical features such as angular orientation, location on the mat, and pressure area. In addition, we adopt a knowledge distillation for regularization to preserve the knowledge of the global feature extraction and improve the performance of the exercise recognition. Our experimental results demonstrate a notable 11 percent improvement in F1 score for exercise recognition while preserving label-specific features.