mlsanityData to 14 Oct 2026

DCentNet: Decentralized Multistage Biomedical Signal Classification using Early Exits

arXiv 2502.17446 ↗First posted 31 Jan 2025eess.SP cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

DCentNet is a novel decentralized multistage signal classification approach designed for biomedical data from IoT wearable sensors, integrating early exit points (EEP) to enhance energy efficiency and processing speed. Unlike traditional centralized processing methods, which result in high energy consumption and latency, DCentNet partitions a single CNN model into multiple sub-networks using EEPs. By introducing encoder-decoder pairs at EEPs, the system compresses large feature maps before transmission, significantly reducing wireless data transfer and power usage. If an input is confidently classified at an EEP, processing stops early, optimizing efficiency. Initial sub-networks can be deployed on fog or edge devices to further minimize energy consumption. A genetic algorithm is used to optimize EEP placement, balancing performance and complexity. Experimental results on ECG classification show that with one EEP, DCentNet reduces wireless data transmission by 94.54% and complexity by 21%, while maintaining original accuracy and sensitivity. With two EEPs, sensitivity reaches 98.36%, accuracy 97.74%, wireless data transmission decreases by 91.86%, and complexity is reduced by 22%. Implemented on an ARM Cortex-M4 MCU, DCentNet achieves an average power saving of 73.6% compared to continuous wireless ECG transmission.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 43 references that are in the map. First posted on arXiv 31 Jan 2025.

Builds on

8 of 43 references.

References · 8

  1. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  2. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 676
  3. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 596
  4. 2019Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computingcited by 152
  5. 2018Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edgecited by 20
  6. 2019Distributed Deep Convolutional Neural Networks for the Internet-of-Thingscited by 13
  7. 2020Inference Time Optimization Using BranchyNet Partitioningcited by 5
  8. 2021Multistage Pruning of CNN Based ECG Classifiers for Edge Devicescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021An adaptive cognitive sensor node for ECG monitoring in the Internet of Medical Things
  2. 2024SparrowSNN: A Hardware/software Co-design for Energy Efficient ECG Classification
  3. 2026Reducing the Complexity of Deep Learning Models for EEG Analysis on Wearable Devices
  4. 2025SleepLiteCNN: Energy-Efficient Sleep Apnea Subtype Classification with 1-Second Resolution Using Single-Lead ECG
  5. 2022Many-to-One Knowledge Distillation of Real-Time Epileptic Seizure Detection for Low-Power Wearable Internet of Things Systems
  6. 2024EEG_RL-Net: Enhancing EEG MI Classification through Reinforcement Learning-Optimised Graph Neural Networks
  7. 2021Sub-100uW Multispectral Riemannian Classification for EEG-based Brain--Machine Interfaces ↗
  8. 2022MI-BMInet: An Efficient Convolutional Neural Network for Motor Imagery Brain--Machine Interfaces with EEG Channel Selection