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

Sahil Shrivastava

cs.LGMar 29, 2026

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

Authors: Sahil Shrivastava

Organizations: Predictive Drug Delivery System (PDDS) Project, Independent Research

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.

Figures & tables

Fig. 1: PDDS system architecture. The pipeline activates only on threshold crossings. The EmergencyDetector always runs first; its Path A (emergency) completely bypasses the injection pathway.

Metric	ADA Rule	SNN
Overall accuracy	87.63%	85.43%
HIGH recall (safety)	100.0% ∗	90.72%
HIGH precision	95.50%	86.65%
HIGH F1	97.70%	88.45%
LOW recall	82.72%	88.00%
MEDIUM recall	84.81%	81.00%

TABLE I: SNN vs. ADA Rule-Based Baseline (Transparent Comparison)

Feature	Patient A	Patient B
Last glucose	190 mg/dL	190 mg/dL
time_below_70_pct	0.00	0.38 (19 min hypo)
glucose_std_norm	0.05 (stable)	0.41 (volatile)
abs_slope	0.3 mg/dL/min	3.2 mg/dL/min
ADA rule prediction	MEDIUM	MEDIUM
SNN prediction	MEDIUM	HIGH

TABLE II: Same Glucose Reading, Completely Different Risk

Layer	Type	Dim	$\beta$	Temporal Role
Input	Poisson encoder	$10\times T$	—	50-min CGM window
fc1	Linear	$10{\to}128$	—	Weight matrix
lif1	LIF	128 neurons	0.95	Slow trend memory
fc2	Linear	$128{\to}64$	—	Weight matrix
lif2	LIF	64 neurons	0.90	Medium integration
fc3	Linear	$64{\to}3$	—	Output weights

TABLE III: PDDSSpikingNet Architecture (9,859 parameters)

Fig. 2: PDDSSpikingNet architecture. Input features are Poisson-encoded into binary spike trains over $T\!=\!50$ timesteps. Three LIF layers with decreasing $\beta$ values (0.95/0.90/0.80) create a hierarchy of temporal integration timescales. Classification is by spike-count argmax.

Fig. 3: LIF neuron model. Membrane potential dynamics $V[t]=\beta V[t-1]+I[t]$ , showing leakage, accumulation, and threshold crossing (spike). The surrogate gradient fast_sigmoid replaces the non-differentiable Heaviside step function during backpropagation.

Fig. 4: PDDS Medallion data architecture. Bronze sources (OhioT1DM XML and simglucose CSV) are parsed into Silver per-patient CSV files, then feature-engineered into Gold NumPy arrays with ADA 2023 labels.

Source	Records	Role in PDDS
OhioT1DM [ 11 ]	85,105 windows (12 T1D pts, 8 wks)	Primary training (66.5%); gold-standard with clinician hypo_event annotations
simglucose / UVa-Padova [ 12 ]	42,920 windows (30 virtual pts)	Augmentation (33.5%); FDA-validated rare glucose patterns
Pima Indians (NIDDK)	768 patients	Threshold calibration; real patient glucose distributions
DrugBank / openFDA	Drug interaction DB	Dose safety cross-reference
MIMIC-IV [ 17 ]	50,000+ ICU admissions	Pending—severity label clinical validation

TABLE IV: PDDS Training Data Sources

F	Name	Clinical Meaning
1	last_glucose_norm	Most recent CGM reading (current state)
2	mean_glucose_norm	50-min mean (sustained vs. transient)
3	min_glucose_norm	Window minimum (catches hypo dips)
4	max_glucose_norm	Window maximum (catches hyper peaks)
5	abs_slope_norm	Rate-of-change magnitude
6	signed_slope_norm	Signed slope (rising vs. falling)

TABLE V: 10 Gold-Layer Features

Mode	Response to HIGH	Emergency
DIABETIC	Compute dose via DoseCalculator; instruct ArtificialPancreas to inject.	Block injection; fire URGENT alert.
PREDIABETIC	Route severity to NotificationEngine: NUDGE / ALERT / URGENT behavioural message. No injection ever.	Fire URGENT alert (no injection to block).

TABLE VI: Deployed Operation Modes

Metric	Value
Training data	128,025 windows (OhioT1DM + simglucose)
Training time	7,589 s ( $\approx$ 2.1 h, CPU-only)
Epochs	59 (early stopping, patience 15)
Best val accuracy	85.90% (epoch 44, $\eta=8.69\!\times\!10^{-5}$ )
Test accuracy	85.43%
HIGH recall	90.72% [primary safety metric]

TABLE VII: SNN Training Summary

Class	Prec.	Rec.	F1	Supp.
LOW (0)	0.8585	0.9299	0.8928	2,297
MEDIUM (1)	0.8415	0.7338	0.7839	2,047
HIGH (2)	0.8629	0.9072	0.8845	1,380
Macro avg	0.8543	0.8570	0.8537	5,724

TABLE VIII: Per-Class Test-Set Results (5,724 windows)

Metric	Exp. 1	Exp. 2	$\Delta$
Features	2 (volt., slope)	10 (Gold layer)	+8
Architecture	2-layer, 16h	3-layer, 128-64-3	Deeper
Optimizer	Adam	RMaxProp	SNN-tailored
Val acc	57.9%	85.90%	+28.0 pp
HIGH recall	N/A	90.72%	—
Verdict	FAILED	SUCCESS	—

TABLE IX: Experiment 1 (Baseline) vs. Experiment 2 (PDDS)

#	Scenario	Result
1	Threshold exceeded (happy path)	PASS
2	All readings below threshold (no wake)	PASS
3	Re-trigger prevention (epsilon guard)	PASS
4	Second spike after recovery	PASS
5	Steady gradual incline	PASS
6	Rapid spike + 5.0 U safety cap	PASS

TABLE X: 15-Scenario Validation Suite Results

Fig. 5: Sigmoidal dose-response curves for three severity levels. HIGH severity (dashed red) activates earliest—full dose engages at lower excess glucose. All curves are bounded by the 5.0 U safety cap. Inspired by Chou et al. [ 10 ] PBA glucose-responsive insulin.

Metric	ADA Rule	SNN	Interpretation
HIGH recall	16.7%	9.2%	Both fail on temporal edges
HIGH precision	100%	100%	When predict HIGH, correct
Correct / 426	71	39	ADA slightly better
Neither classifier meets clinical safety bar.

TABLE XI: Temporal Benchmark on 426 Non-Obvious Hypo Windows

Metric	SNN	Bi-LSTM	MLP
Accuracy	85.24%	99.06%	99.00%
HIGH recall	88.84%	99.78%	99.49%
HIGH F1	87.23%	99.24%	98.92%
Parameters	9,859	138,627	9,859
Training (CPU)	7,589 s	299 s	145 s
Inference (CPU)	1,094 ms	61 ms	6 ms

TABLE XII: SOTA Baseline Comparison

Fig. 6: SNN vs. ADA Rule vs. Bi-LSTM vs. MLP — Complete Comparison. Panel A : Overall accuracy and HIGH-class recall (safety metric) for all four classifiers on the 5,724-window test set. ADA Rule’s 100% HIGH recall is a circular evaluation artefact. Panel B : Estimated energy per inference on neuromorphic hardware (log scale). The SNN is 79,267 $\times$ more energy efficient than the Bi-LSTM. Energy computed using SynOps (SNN) vs. MAC operations (LSTM/MLP) following Merolla et al. [ 15 ] and Diehl et al. [ 16 ] .

Spiking Neural Networks

Spiking neural networks process information through discrete, time-dependent neural events, aiming for efficient computation and biologically inspired learning.

See all 351 papers

Apr 29, 2026

EdgeSpike: Spiking Neural Networks for Low-Power Autonomous Sensing in Edge IoT Architectures

We propose EdgeSpike, a co-designed spiking neural network (SNN) framework for autonomous low-power sensing in edge Internet of Things (IoT) architectures. EdgeSpike unifies (i) a hybrid surrogate-gradient and direct-encoding training pipeline, (ii) a hardware-aware neural architecture search (NAS) bounded by per-inference energy and memory budgets, (iii) an event-driven runtime targeting Intel Loihi 2, SpiNNaker 2, and commodity ARM Cortex-M microcontrollers with custom spike-sparse SIMD kernels, and (iv) a lightweight local plasticity rule enabling continual on-device adaptation without backpropagation. The framework is evaluated across five sensing tasks (keyword spotting, vibration-based machine fault detection, surface electromyography gesture recognition, 77 GHz radar human-activity classification, and structural-health acoustic-emission monitoring) on three hardware targets. EdgeSpike achieves a mean classification accuracy of 91.4%, within 1.2 percentage points (pp) of strong INT8 convolutional neural network (CNN) baselines (mean 92.6%), while reducing energy per inference by 18x to 47x on neuromorphic hardware (mean 31x) and by 4.6x to 7.9x on Cortex-M (mean 6.1x). End-to-end latency remains at or below 9.4 ms across all 15 task-hardware configurations. A seven-month, 64-node wireless field deployment confirms a 6.3x extension in projected battery lifetime (from 312 to 1978 days at 2 Wh per node) and bounded accuracy degradation under seasonal drift (0.7 pp with on-device adaptation versus 2.1 pp without). Hardware-aware NAS evaluates 8400 candidates and yields a 12-point Pareto front. EdgeSpike will be released as open source with reproducible training pipelines, hardware-portable runtimes, and benchmark suites.

Gustav Olaf Yunus Laitinen-Fredriksson Lundstrom-Imanov, Taner Yilmaz

Department of Economics, Stockholm University, Universitetsvägen 10 A, SE-106 91 Stockholm, Sweden · Department of Computer Engineering, Afyon Kocatepe University, 03200 Afyonkarahisar, Türkiye

Energy-Efficient ML Edge Inference Internet of Things Spiking Neural Networks Neuromorphic Computing

Ask PDF

Apr 4, 2026

L-SPINE: A Low-Precision SIMD Spiking Neural Compute Engine for Resource-efficient Edge Inference

Spiking Neural Networks (SNNs) offer a promising solution for energy-efficient edge intelligence; however, their hardware deployment is constrained by memory overhead, inefficient scaling operations, and limited parallelism. This work proposes L-SPINE, a low-precision SIMD-enabled spiking neural compute engine for efficient edge inference. The architecture features a unified multi-precision datapath supporting 2-bit, 4-bit, and 8-bit operations, leveraging a multiplier-less shift-add model for neuron dynamics and synaptic accumulation. Implemented on an AMD VC707 FPGA, the proposed neuron requires only 459 LUTs and 408 FFs, achieving a critical delay of 0.39 ns and 4.2 mW power. At the system level, L-SPINE achieves 46.37K LUTs, 30.4K FFs, 2.38 ms latency, and 0.54 W power. Compared to CPU and GPU platforms, it reduces inference latency from seconds to milliseconds, achieving an up to three orders-of-magnitude improvement in energy efficiency. Quantisation analysis shows that INT2/INT4 configurations significantly reduce memory footprint with minimal accuracy loss. These results establish L-SPINE as a scalable and efficient solution for real-time edge SNN deployment.

Sonu Kumar, Mukul Lokhande, Santosh Kumar Vishvakarma

Centre for Advanced Electronics, Indian Institute of Technology Indore, Simrol 453552, Indore, India · Dept. of Electrical Engineering, Indian Institute of Technology Indore, Simrol 453552, Indore, India

Efficient Neural Network Inference Spiking Neural Networks FPGA-Based Neural Network Acceleration Edge Inference

Ask PDF

May 29, 2026

Memristor-Based Spiking Neural Network Accelerator for Bio-inspired Interception Task

Spiking neural networks (SNNs) provide event-driven and low-power computation inspired by biological neural systems, but current implementations rely on von Neumann graphics processing units (GPUs) and central processing units (CPUs) platforms, where memory and computation bottlenecks limit energy efficiency. To address this challenge, this paper proposes an analog memristor-based spiking neural network (SNN) accelerator that integrates in-memory synaptic computation with analog integrate-and-fire (IF) neurons, eliminating multi-transistor CMOS synapse circuits and enabling asynchronous event-driven operation at the 45nm technology node. Additionally, a digital SNN accelerator is designed and optimized at the 5 nm technology node for comparison. The proposed architecture is evaluated using a predator-prey tracking task that emulates pursuit behavior. In this task, the analog SNN accelerator's inference closely matches the ideal software inference with a mean squared error (MSE) of 0.004. HSPICE simulation results show that the proposed analog SNN accelerator achieves 12.7 times lower energy consumption and 1.26 times lower delay compared to the digital baseline, demonstrating the potential of memristor-based neuromorphic circuits for energy-efficient real-time edge intelligence.

Qianhou Qu, Sheng Lu, Liuting Shang +4

Department of Electrical Engineering The University of Texas at Arlington Arlington, USA · Department of Electrical Engineering and Computer Science South Dakota State University Brookings, USA

Efficient Neural Network Inference Compute-in-Memory Spiking Neural Networks Neuromorphic Computing

Ask PDF

Abstract

Spiking Neural Networks

Explore similar work

EdgeSpike: Spiking Neural Networks for Low-Power Autonomous Sensing in Edge IoT Architectures

L-SPINE: A Low-Precision SIMD Spiking Neural Compute Engine for Resource-efficient Edge Inference

Memristor-Based Spiking Neural Network Accelerator for Bio-inspired Interception Task