An Energy-Efficient Spiking Neural Network Architecture for Predictive Insulin Delivery

• URL: http://arxiv.org/abs/2603.27589v1
• Date: Sun, 29 Mar 2026 09:06:36 GMT
• Title: An Energy-Efficient Spiking Neural Network Architecture for Predictive Insulin Delivery
• Abstract summary: This paper presents an in-silico, software-complete research prototype of an event-driven computational pipeline for predictive insulin dose calculation.<n>Motivated by neuromorphic computing principles for ultra-low-power wearable edge devices, the core contribution is a three-layer Leaky-and-Fire (LIF) Spiking Neural Network trained on 128,025 windows from OhioT1DM and the FDA-accepted UVa/Padova physiological simulator (33.5%), achieving 85.90% validation accuracy.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diabetes mellitus affects over 537 million adults worldwide. Insulin-dependent patients require continuous glucose monitoring and precise dose calculation while operating under strict power budgets on wearable devices. This paper presents PDDS - an in-silico, software-complete research prototype of an event-driven computational pipeline for predictive insulin dose calculation. Motivated by neuromorphic computing principles for ultra-low-power wearable edge devices, the core contribution is a three-layer Leaky Integrate-and-Fire (LIF) Spiking Neural Network trained on 128,025 windows from OhioT1DM (66.5% real patients) and the FDA-accepted UVa/Padova physiological simulator (33.5%), achieving 85.90% validation accuracy. We present three rigorously honest evaluations: (1) a standard test-set comparison against ADA threshold rules, bidirectional LSTM (99.06% accuracy), and MLP (99.00%), where the SNN achieves 85.24% - we demonstrate this gap reflects the stochastic encoding trade-off, not architectural failure; (2) a temporal benchmark on 426 non-obvious clinician-annotated hypoglycemia windows where neither the SNN (9.2% recall) nor the ADA rule (16.7% recall) performs adequately, identifying the system's key limitation and the primary direction for future work; (3) a power-efficiency analysis showing the SNN requires 79,267x less energy per inference than the LSTM (1,551 Femtojoules vs. 122.9 nanojoules), justifying the SNN architecture for continuous wearable deployment. The system is not yet connected to physical hardware; it constitutes the computational middle layer of a five phase roadmap toward clinical validation. Keywords: spiking neural network, glucose severity classification, edge computing, hypoglycemia detection, event-driven architecture, LIF neuron, Poisson encoding, OhioT1DM, in-silico, neuromorphic, power efficiency.

Related papers

• Detecting Neurovascular Instability from Multimodal Physiological Signals Using Wearable-Compatible Edge AI: A Responsible Computational Framework [0.0]
  We propose Melaguard, a multimodal ML framework for detecting neurovascular instability (NVI) from wearable-compatible physiological signals.<n>With 12.2 million incident strokes annually, continuous multimodal physiological monitoring offers a practical path to community-scale screening.
  arXiv  Detail & Related papers  (2026-03-20T19:17:46Z)
• Neuromorphic Eye Tracking for Low-Latency Pupil Detection [37.091037454305024]
  Eye tracking for wearable systems demands low latency and milliwatt-level power.<n>Neuromorphic sensors and spiking neural networks (SNNs) offer a promising alternative.<n>This paper presents a neuromorphic version of top-performing event-based eye-tracking models.
  arXiv  Detail & Related papers  (2025-12-10T11:30:21Z)
• Physics-Informed Neural Networks vs. Physics Models for Non-Invasive Glucose Monitoring: A Comparative Study Under Realistic Synthetic Conditions [0.0]
  Non-invasive glucose monitors often fail outside the lab because existing datasets ignore hardware noise, environmental drift, and person-to-person physiology.<n>We introduce the first ultra-realistic near-infrared (NIR) simulator that injects 12-bit ADC quantisation.
  arXiv  Detail & Related papers  (2025-09-12T12:18:00Z)
• Peptidomic-Based Prediction Model for Coronary Heart Disease Using a Multilayer Perceptron Neural Network [0.0]
  Coronary heart disease (CHD) is a leading cause of death worldwide and contributes significantly to annual healthcare expenditures.<n>To develop a non-invasive diagnostic approach, we designed a model based on a multilayer perceptron (MLP) neural network.<n>The model achieved a precision, sensitivity, and specificity of 95.67 percent, with an F1-score of 0.9565.
  arXiv  Detail & Related papers  (2025-09-04T04:54:02Z)
• Quantization-Aware Neuromorphic Architecture for Efficient Skin Disease Classification on Resource-Constrained Devices [8.61918204555282]
  We introduce QANA, a novel quantization-aware neuromorphic architecture for incremental skin lesion classification on resource-limited hardware.<n>QANA integrates ghost modules, efficient channel attention, and squeeze-and-excitation blocks for robust feature representation.<n>Its quantization-aware head and spike-compatible transformations enable seamless conversion to spiking neural networks (SNNs) and deployment on neuromorphic platforms.
  arXiv  Detail & Related papers  (2025-07-21T18:01:44Z)
• Spiking Neural Networks for Low-Power Vibration-Based Predictive Maintenance [38.09509006669997]
  Spiking Neural Networks (SNNs) offer a promising pathway toward energy-efficient on-device processing.<n>This paper investigates a recurrent SNN for simultaneous regression (flow, pressure, pump speed) and multi-label classification (normal, overpressure, cavitation) for an industrial progressing cavity pump.<n>Results demonstrate high classification accuracy (>97%) with zero False Negative Rates for critical Overpressure and Cavitation faults.
  arXiv  Detail & Related papers  (2025-06-16T12:33:09Z)
• Mamba-based Deep Learning Approach for Sleep Staging on a Wireless Multimodal Wearable System without Electroencephalography [3.7428541180163126]
  We investigate a Mamba-based deep learning approach for sleep staging on signals from ANNE One.<n>We obtained wearable sensor recordings from 357 adults undergoing concurrent polysomnography.<n>We trained a Mamba-based recurrent neural network architecture on these recordings.
  arXiv  Detail & Related papers  (2024-12-20T14:43:02Z)
• Brain Tumor Classification on MRI in Light of Molecular Markers [56.99710477905796]
  Co-deletion of the 1p/19q gene is associated with clinical outcomes in low-grade gliomas.<n>This study aims to utilize a specially MRI-based convolutional neural network for brain cancer detection.
  arXiv  Detail & Related papers  (2024-09-29T07:04:26Z)
• An end-to-end deep learning pipeline to derive blood input with partial volume corrections for automated parametric brain PET mapping [1.3243230917306228]
  A key challenge in the quantitative analysis of dFDG-PET is characterizing a patient-specific blood input function. This research introduces a novel approach employing non-invasive deep learning model-based computations from the internal carotid arteries. We present an end-to-end pipeline incorporating a 3D U-Net based ICA-net for ICA segmentation, alongside a Recurrent Neural Network (RNN) based MCIF-net for the derivation of a model-corrected blood input function.
  arXiv  Detail & Related papers  (2024-02-05T17:02:30Z)
• CIRCA: comprehensible online system in support of chest X-rays-based COVID-19 diagnosis [37.41181188499616]
  Deep learning techniques can help in the faster detection of COVID-19 cases and monitoring of disease progression. Five different datasets were used to construct a representative dataset of 23 799 CXRs for model training. A U-Net-based model was developed to identify a clinically relevant region of the CXR.
  arXiv  Detail & Related papers  (2022-10-11T13:30:34Z)
• SOUL: An Energy-Efficient Unsupervised Online Learning Seizure Detection Classifier [68.8204255655161]
  Implantable devices that record neural activity and detect seizures have been adopted to issue warnings or trigger neurostimulation to suppress seizures. For an implantable seizure detection system, a low power, at-the-edge, online learning algorithm can be employed to dynamically adapt to neural signal drifts. SOUL was fabricated in TSMC's 28 nm process occupying 0.1 mm2 and achieves 1.5 nJ/classification energy efficiency, which is at least 24x more efficient than state-of-the-art.
  arXiv  Detail & Related papers  (2021-10-01T23:01:20Z)
• CovidDeep: SARS-CoV-2/COVID-19 Test Based on Wearable Medical Sensors and Efficient Neural Networks [51.589769497681175]
  The novel coronavirus (SARS-CoV-2) has led to a pandemic. The current testing regime based on Reverse Transcription-Polymerase Chain Reaction for SARS-CoV-2 has been unable to keep up with testing demands. We propose a framework called CovidDeep that combines efficient DNNs with commercially available WMSs for pervasive testing of the virus.
  arXiv  Detail & Related papers  (2020-07-20T21:47:28Z)

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.