Design and Validation of a Lightweight 1D CNN for Affective Touch Classification in Soft Plush Companions
Quick Answer
This study introduces a lightweight 1D CNN model for affective touch classification in soft companions, achieving 75% test accuracy with only 13.2k parameters.
Quick Take
A new dataset of 1326 labeled gestures from 25 participants is also released, enhancing future research in this domain.
Key Points
- The model achieved 85% mean leave-one-subject-out cross-validation accuracy.
- Quantized deployment requires only 3.2 MMAC per window for real-time operation.
- The study provides an open-source MATLAB framework for model development.
- Hybrid inference combines heuristic filtering with CNN-based gesture classification.
- A diverse dataset includes gestures from children, teenagers, and adults.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Soft, sensorized companions offer a physically safe and emotionally intuitive interface for socially assistive technologies, yet their deformability and multichannel tactile sensing complicate the robust interpretation of human affect. This study presents a complete open-source MATLAB-based framework for the development and validation of compact deep learning models for affective touch recognition in soft interactive companions. As a primary contribution, a diverse FAIR-compliant dataset of 1326 labelled gesture sequences collected from 25 participants spanning children, teenagers, and adults is made publicly available, providing a reusable resource for future research in affective touch recognition. Through systematic architecture and hyperparameter exploration across 468 CNN models, the study identifies compact dilated one-dimensional convolutional neural networks (1D CNNs) as the most effective solution, with a 13.2k-parameter model achieving 75% test accuracy and 85% mean leave-one-subject-out cross-validation accuracy. Theoretical inference-time analysis shows that quantized deployment requires 3.2 MMAC per window, compatible with 20 Hz real-time operation on the target microcontroller. PC-based real-time simulation with the physical toy streaming sensor data demonstrates that the CNN resolves subtle social touches that the previous heuristic system failed to detect, whereas high-force negative interactions are captured more reliably by trivial threshold-based logic. The resulting hybrid inference pipeline - instantaneous heuristic filtering followed by CNN-based nuanced gesture classification - is proposed as the embedded deployment strategy. The study demonstrates that emotionally meaningful, privacy-preserving touch interpretation is computationally feasible for direct embedding within soft therapeutic companions, with hardware integration addressed in a forthcoming study.
| Comments: | 28 pages, 11 figures |
| Subjects: | Artificial Intelligence (cs.AI) |
| ACM classes: | I.5.1; I.5.4; J.4 |
| Cite as: | arXiv:2607.16196 [cs.AI] |
| (or arXiv:2607.16196v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.16196 arXiv-issued DOI via DataCite |
Submission history
From: Aleksandrs Vališevskis [view email]
[v1]
Thu, 16 Apr 2026 10:20:05 UTC (1,133 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.