Intelligent sensing systems are increasingly used in wearable devices, enabling advanced tasks across various application domains including robotics and human–machine interaction. Ensuring these systems are energy autonomous is highly demanded, despite strict constraints on power, memory and processing resources. To meet these requirements, embedded neural networks must be optimized to achieve a balance between accuracy and efficiency. This paper presents an integrated approach that combines Hardware-Aware Neural Architecture Search (HW-NAS) with optimization techniques—weight reshaping, quantization, and their combination—to develop efficient classifiers for a multisensory glove. HW-NAS automatically derives 1D-CNN models tailored to the NUCLEO-F401RE board, while the additional optimization further reduces model size, memory usage, and latency. Across three datasets, the optimized models not only improve classification accuracy but also deliver an average reduction of 75% in inference time, 69% in flash memory, and more than 45% in RAM compared to NAS-only baselines. These results highlight the effectiveness of integrating NAS with optimization techniques, paving the way towards energy-autonomous wearable systems.

Deploying neural networks on embedded tactile sensing systems is constrained by limited computational and memory resources. This work presents a Knowledge Distillation (KD)–based optimization framework to improve deployment efficiency on such platforms. A pretrained baseline model serves as the teacher, transferring knowledge to a lightweight student model. Experiments on a texture dataset collected with a multisensory glove show that the KD student preserves the teacher’s accuracy while substantially reducing computation and memory requirements. Compared with an optimized teacher variant, the KD student achieves slightly lower accuracy with 53% lower inference time, 79% less flash usage, and 90% fewer multiply–accumulate operations (MACs), demonstrating the framework’s effectiveness for real-time embedded deployment.