# TSAK: Two-Stage Semantic-Aware Knowledge Distillation for Efficient Wearable Modality and Model Optimization in Manufacturing Lines arXiv: https://arxiv.org/abs/2408.14146 ยท HTML: https://mlsanity.com/paper/2408.14146/ ## Key facts - Cited by 5 papers in the map (data through 14 Oct 2026). - Placed in Distillation for medical imaging, one of 12 directions in Knowledge distillation. - Builds on 20 of its 36 references that are in the map. - First posted on arXiv 26 Aug 2024. ## Placed in - Knowledge distillation / [Distillation for medical imaging](https://mlsanity.com/distill/distillation-for-medical-imaging/) ## Builds on (most cited first, 20 of 20) - [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015) - [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020) - [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019) - [On the Efficacy of Knowledge Distillation](https://mlsanity.com/paper/1910.01348/) (2019) - [Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks](https://mlsanity.com/paper/2004.05937/) (2020) - [Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation](https://mlsanity.com/paper/2105.08919/) (2021) - [Knowledge Distillation from Internal Representations](https://mlsanity.com/paper/1910.03723/) (2019) - [IndustReal: A Dataset for Procedure Step Recognition Handling Execution Errors in Egocentric Videos in an Industrial-Like Setting](https://mlsanity.com/paper/2310.17323/) (2023) - [QKD: Quantization-aware Knowledge Distillation](https://mlsanity.com/paper/1911.12491/) (2019) - [Semantics-aware Adaptive Knowledge Distillation for Sensor-to-Vision Action Recognition](https://mlsanity.com/paper/2009.00210/) (2020) - [Improving Deep Learning for HAR with shallow LSTMs](https://mlsanity.com/paper/2108.00702/) (2021) - [Cross-modal Knowledge Distillation for Vision-to-Sensor Action Recognition](https://mlsanity.com/paper/2112.01849/) (2021) - [HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding](https://mlsanity.com/paper/2307.05721/) (2023) - [DeepSpeed4Science Initiative: Enabling Large-Scale Scientific Discovery through Sophisticated AI System Technologies](https://mlsanity.com/paper/2310.04610/) (2023) - [Learning from the Best: Contrastive Representations Learning Across Sensor Locations for Wearable Activity Recognition](https://mlsanity.com/paper/2210.01459/) (2022) - [OpenPack: A Large-scale Dataset for Recognizing Packaging Works in IoT-enabled Logistic Environments](https://mlsanity.com/paper/2212.11152/) (2022) - [Progressive Cross-modal Knowledge Distillation for Human Action Recognition](https://mlsanity.com/paper/2208.08090/) (2022) - [CaptAinGlove: Capacitive and Inertial Fusion-Based Glove for Real-Time on Edge Hand Gesture Recognition for Drone Control](https://mlsanity.com/paper/2306.04319/) (2023) - [InMyFace: Inertial and Mechanomyography-Based Sensor Fusion for Wearable Facial Activity Recognition](https://mlsanity.com/paper/2302.04024/) (2023) - [BeSound: Bluetooth-Based Position Estimation Enhancing with Cross-Modality Distillation](https://mlsanity.com/paper/2404.15999/) (2024) ## Built on by (most cited first, 5 of 5) - [Past, Present, and Future of Sensor-Based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task](https://mlsanity.com/paper/2411.14452/) (2024) - [OpenMarcie: Dataset for Multimodal Action Recognition in Industrial Environments](https://mlsanity.com/paper/2603.02390/) (2026) - [PIM: Physics-Informed Multi-task Pre-training for Improving Inertial Sensor-Based Human Activity Recognition](https://mlsanity.com/paper/2503.17978/) (2025) - [LITEWAY: LIghtweight HAR via Temporal Efficient highWAY](https://mlsanity.com/paper/2608.09421/) (2026) - [Dynamic Influence-Weighted Distillation for Single-IMU Activity Recognition](https://mlsanity.com/paper/2608.24904/) (2026) ## Abstract (arXiv) 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).