Invited Paper: Feature-to-Classifier Co-Design for Mixed-Signal Smart Flexible Wearables for Healthcare at the Extreme Edge

• URL: http://arxiv.org/abs/2508.19637v2
• Date: Fri, 29 Aug 2025 13:09:45 GMT
• Title: Invited Paper: Feature-to-Classifier Co-Design for Mixed-Signal Smart Flexible Wearables for Healthcare at the Extreme Edge
• Abstract summary: We present a holistic mixed-signal feature-to-classifier co-design framework for flexible smart wearable systems.<n>To the best of our knowledge, we design the first analog feature extractors in FE, significantly reducing feature extraction cost.<n>We propose a hardware-aware NAS-inspired feature selection strategy within ML training, enabling efficient, application-specific designs.
• Score: 2.2604925169016923
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Flexible Electronics (FE) offer a promising alternative to rigid silicon-based hardware for wearable healthcare devices, enabling lightweight, conformable, and low-cost systems. However, their limited integration density and large feature sizes impose strict area and power constraints, making ML-based healthcare systems-integrating analog frontend, feature extraction and classifier-particularly challenging. Existing FE solutions often neglect potential system-wide solutions and focus on the classifier, overlooking the substantial hardware cost of feature extraction and Analog-to-Digital Converters (ADCs)-both major contributors to area and power consumption. In this work, we present a holistic mixed-signal feature-to-classifier co-design framework for flexible smart wearable systems. To the best of our knowledge, we design the first analog feature extractors in FE, significantly reducing feature extraction cost. We further propose an hardware-aware NAS-inspired feature selection strategy within ML training, enabling efficient, application-specific designs. Our evaluation on healthcare benchmarks shows our approach delivers highly accurate, ultra-area-efficient flexible systems-ideal for disposable, low-power wearable monitoring.

Related papers

• MedFG-VQA: Low-Frequency Memory and Graph Attention for Lightweight Medical VQA [55.12170695219291]
  MedFG-VQA is a lightweight framework that augments DCT-based low-frequency features and employs graph-enhanced cross-attention for effective visual-textual alignment.<n>To address data scarcity, we construct SynMed-VQA, a large-scale synthetic dataset comprising over 2 million question-answer pairs across 9 imaging modalities and 10 major organs.
  arXiv  Detail & Related papers  (2026-08-27T09:16:14Z)
• A Hardware-Aware Open-Source Framework for Design Space Exploration of Mixed-Signal Spiking Neural Networks [0.8950195742710184]
  This work presents an open-source hardware-aware simulation framework for mixed-signal SNNs.<n>It enables comparative analysis across neuron, synapse and architecture choices.<n>The framework is evaluated on standard neuromorphic benchmarks.
  arXiv  Detail & Related papers  (2026-07-07T16:15:03Z)
• At the Edge of the Heart: ULP FPGA-Based CNN for On-Device Cardiac Feature Extraction in Smart Health Sensors for Astronauts [0.0]
  We present an ultra-low-power (ULP) Field-Programmable Gate Array (FPGA) based solution for real-time Seismocardiography (SCG) feature classification.<n>Our approach combines quantization-aware training with a systolic-array accelerator to enable efficient integer-only inference on the Lattice iCE40UP5K FPGA.<n>The implementation achieves a validation accuracy of 98% while consuming only 8.55 mW, completing inference in 95.5 ms with minimal hardware resources.
  arXiv  Detail & Related papers  (2026-04-28T16:10:16Z)
• A Lightweight Medical Image Classification Framework via Self-Supervised Contrastive Learning and Quantum-Enhanced Feature Modeling [11.167221101488229]
  MobileNetV2 is employed as a compact backbone and pretrained using a SimCLR-style self-supervised paradigm on unlabeled images.<n>A lightweight parameterized quantum circuit (PQC) is embedded as a quantum feature enhancement module, forming a hybrid classical-quantum architecture.
  arXiv  Detail & Related papers  (2026-01-23T10:08:37Z)
• Bespoke Co-processor for Energy-Efficient Health Monitoring on RISC-V-based Flexible Wearables [2.569738171261988]
  We present a mechanically flexible RISC-V that integrates a bespoke multiply-accumulate co-processor with fixed coefficients to maximize energy efficiency and minimize latency.<n>Results demonstrate near-real-time performance across several healthcare datasets, with our circuits operating within the power budget of existing flexible batteries.
  arXiv  Detail & Related papers  (2025-11-08T12:17:34Z)
• Exploration of Low-Power Flexible Stress Monitoring Classifiers for Conformal Wearables [3.195176634942016]
  State-of-the-art approaches use rigid, silicon-based wearables, which are not optimized for lightweight, flexible wear.<n>FE offer flexibility and low manufacturing costs, enabling real-time stress monitoring circuits.<n>This work presents the first comprehensive design space exploration of low-power, flexible stress classifiers.
  arXiv  Detail & Related papers  (2025-08-27T08:19:52Z)
• A Novel Deep Hybrid Framework with Ensemble-Based Feature Optimization for Robust Real-Time Human Activity Recognition [0.6991281327290525]
  Human Activity Recognition (HAR) plays a pivotal role in various applications, including smart surveillance, healthcare, assistive technologies, sports analytics, etc.<n>An optimized hybrid deep learning framework is introduced that integrates a customized InceptionV3, an LSTM architecture, and a novel ensemble-based feature selection strategy.<n>The proposed approach achieves 99.65% recognition accuracy, reduces features to as few as 7, and enhances inference time.
  arXiv  Detail & Related papers  (2025-08-26T05:42:55Z)
• Deep Learning-based Techniques for Integrated Sensing and Communication Systems: State-of-the-Art, Challenges, and Opportunities [54.12860202362483]
  This article comprehensively reviews recent developments and research on deep learning-based (DL-based) techniques for integrated sensing and communication (ISAC) systems.<n>ISAC is regarded as a key enabler for 6G and beyond networks, as many emerging applications, such as vehicular networks and industrial robotics, necessitate both sensing and communication capabilities.<n>As an alternative to conventional techniques, DL-based techniques offer efficient and near-optimal solutions with reduced computational complexity.
  arXiv  Detail & Related papers  (2025-08-23T22:27:51Z)
• Computer Vision for Real-Time Monkeypox Diagnosis on Embedded Systems [0.0]
  This study presents an AI-driven diagnostic tool developed for deployment on the NVIDIA Jetson Orin Nano.<n>The model was trained on the open-source Monkeypox Skin Lesion dataset, achieving a 93.07% F1-Score.<n>The diagnostic tool is an efficient, scalable, and energy-conscious solution to address diagnosis challenges in underserved regions.
  arXiv  Detail & Related papers  (2025-07-23T01:53:31Z)
• FE-UNet: Frequency Domain Enhanced U-Net for Low-Frequency Information-Rich Image Segmentation [48.034848981295525]
  We address the differences in frequency band sensitivity between CNNs and the human visual system.<n>We propose a wavelet adaptive spectrum fusion (WASF) method inspired by biological vision mechanisms to balance cross-frequency image features.<n>We develop the FE-UNet model, which employs a SAM2 backbone network and incorporates fine-tuned Hiera-Large modules to ensure segmentation accuracy.
  arXiv  Detail & Related papers  (2025-02-06T07:24:34Z)
• OmniBuds: A Sensory Earable Platform for Advanced Bio-Sensing and On-Device Machine Learning [46.3331254985615]
  Sensory earables have evolved from basic audio enhancement devices into sophisticated platforms for clinical-grade health monitoring and wellbeing management. This paper introduces OmniBuds, an advanced sensory earable platform integrating multiple biosensors and onboard computation powered by a machine learning accelerator.
  arXiv  Detail & Related papers  (2024-10-07T06:30:59Z)
• SLIDE: A machine-learning based method for forced dynamic response estimation of multibody systems [42.87502453001109]
  SLiding-window Initially-truncated Dynamic-response Estimator (SLIDE) Deep learning-based method designed to estimate output sequences of mechanical or multibody systems. Results demonstrate significant speedups from the simulation up to several millions, exceeding real-time performance substantially.
  arXiv  Detail & Related papers  (2024-09-26T20:34:07Z)
• EventF2S: Asynchronous and Sparse Spiking AER Framework using Neuromorphic-Friendly Algorithm [2.469315273321826]
  Spiking Neural Network (SNN) has become the inherent choice for AER data processing. We introduce a brain-inspired AER-SNN object recognition solution, which includes a data encoder integrated with a First-To-Spike recognition network.
  arXiv  Detail & Related papers  (2024-01-28T19:42:05Z)
• An Energy-Aware Approach to Design Self-Adaptive AI-based Applications on the Edge [42.462246527457594]
  We present an energy-aware approach for the design and deployment of self-adaptive AI-based applications. We address the problem of determining the set of configurations that can be used to self-adapt the system with a meta-heuristic search procedure. Results show that our self-adaptive application can outperform non-adaptive baseline configurations by saving up to 81% of energy while loosing only between 2% and 6% in accuracy.
  arXiv  Detail & Related papers  (2023-08-31T09:33:44Z)
• LAMBO: Large AI Model Empowered Edge Intelligence [71.56135386994119]
  Next-generation edge intelligence is anticipated to benefit various applications via offloading techniques. Traditional offloading architectures face several issues, including heterogeneous constraints, partial perception, uncertain generalization, and lack of tractability. We propose a Large AI Model-Based Offloading (LAMBO) framework with over one billion parameters for solving these problems.
  arXiv  Detail & Related papers  (2023-08-29T07:25:42Z)
• Modeling and Joint Optimization of Security, Latency, and Computational Cost in Blockchain-based Healthcare Systems [2.54403164787763]
  We formulate a joint optimization model with three metrics, namely latency, security, and computational cost. We propose an algorithm called the Adaptive Discrete Particle Swarm Algorithm (ADPSA) to obtain near-optimal solutions. We demonstrate by extensive numerical experiments that the ADPSA consistently outperforms existing benchmark approaches.
  arXiv  Detail & Related papers  (2023-03-28T09:29:29Z)
• Multi-Point Integrated Sensing and Communication: Fusion Model and Functionality Selection [99.67715229413986]
  This paper presents a multi-point ISAC (MPISAC) system that fuses the outputs from multiple ISAC devices for achieving higher sensing performance. We adopt a fusion model that predicts the fusion accuracy via hypothesis testing and optimal voting analysis.
  arXiv  Detail & Related papers  (2022-08-16T08:09:54Z)
• High-Fidelity Machine Learning Approximations of Large-Scale Optimal Power Flow [49.2540510330407]
  AC-OPF is a key building block in many power system applications. Motivated by increased penetration of renewable sources, this paper explores deep learning to deliver efficient approximations to the AC-OPF.
  arXiv  Detail & Related papers  (2020-06-29T20:22:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.