BioniChaos Logo
  • Home
  • About
  • Contact
⚡ DEMO MODE ACTIVE - Tap here or any control to resume

Simulation Diagnostics

Diagnostic Score
N/A
Status Index
NORMAL
Explainable AI & Diagnostics

Fuzzy Logic Matrix

This diagnostic block determines state risk parameters. Modulating the noise and amplitude directly adjusts these criteria:

  • • IF [Amplitude] is HIGH AND [Irregularity] is HIGH → Status: CRITICAL
  • • IF [Noise] is HIGH AND [Spectral Power] is DEGRADED → Status: BAD GAIN
  • • IF [Rhythmic Spiking] is HIGH → Status: SEIZURE RISK

Model Explanations (XAI)

Features contributing to classification confidence:

Voltage Amplitude weight: 0.00
Signal Irregularity weight: 0.00
Electrode Impedance weight: 0.00

Overview: Virtual Lab for Neurological & Cardiac Disorders

In biomedical engineering and clinical diagnostics, analyzing physiological signals is critical for mapping organ functionality and identifying pathology. Electrophysiology encompasses multiple measurement methods designed to trace bioelectric potential shifts. This portal simulates three primary modalities: Electroencephalography (EEG) for cortical brain rhythm tracking, Intracranial Electroencephalography (iEEG) for local field potentials directly recorded from the cerebral tissue matrix, and Electrocardiography (ECG) for monitoring cardiac depolarization and repolarization sequences.

This diagnostic environment functions as an interactive educational workspace where students analyze synthetic waveforms in real time, matching open-source datasets (such as those from PhysioNet and BioniChaos). Biological signals are naturally affected by electrode contact impedance, patient motion, and power line noise. To simulate these conditions, this platform embeds a real-time broadband white-noise generator. Additionally, a dynamic fuzzy logic inference engine classifies the output wave signals. By analyzing spectral amplitude, temporal variance, and spike frequency, the engine determines health parameters and presents explainable AI (XAI) feature weight matrices for clinical transparency.

How to Use the Interactive Workspace

This visualizer represents diagnostic instrument environments. Follow these instructions to explore signal dynamics:

  • Select the Core Archetype: Toggle between EEG, ECG, and iEEG using the dropdown selection box to load specific physiological configurations onto the high-contrast digital oscilloscope screen.
  • Select a Pathology: Apply different clinical disorders, such as an epileptic spike-and-wave seizure discharge, cardiac arrhythmia with premature ventricular contractions, or burst suppression patterns seen in deep anesthesia.
  • Modulate System Parameters: Adjust the sliders to scale parameters like overall Signal Amplitude and Temporal Resolution. This affects the frequency spectrum and simulation speed, immediately updating the real-time analyzer.
  • Simulate Electrode Noise: Move the Broadband Electrode Noise slider to introduce thermal white noise into the biosignal stream. This simulates poor contact impedance or movement artifacts, testing the robustness of the diagnostic model.
  • Explore Explainable AI: Expand the "Explainable AI & Diagnostics" tab. This pane showcases real-time feature extraction weight parameters and illustrates how fuzzy set constraints classify the underlying signal condition.
  • Start Demo Mode: Click "Start Demo Mode" to initiate an automated, high-yield diagnostic scan. Click anywhere on the dashboard to immediately stop the demo and restore your previous settings.

Technical Details & Engineering Logic

The signal processing architecture uses a mathematical framework optimized for smooth real-time performance. High-frequency synthesis algorithms model specialized components of human cardiac and cortical rhythms:

The ECG signal is modeled as a sum of individual Gaussian waveforms, where each wave representing standard cardiac pacing (the P wave, QRS complex, and T wave) is mapped via the equation:
V(t) = Σ a_i * exp( -((t - θ_i) / b_i)^2 ) where a_i represents amplitude, θ_i represents phase offset, and b_i represents duration width of the constituent waves.

For brain rhythm simulations, we generate a multi-band EEG wave composed of specific cortical frequencies, including Alpha waves (8-12 Hz) to simulate posterior resting states, Beta waves (13-30 Hz) representing alert active cognitive states, and high-voltage spike-and-wave patterns around 3 Hz to simulate generalized absence epilepsy.

This simulator is designed to run efficiently on mobile platforms, conforming to responsive viewport limitations and minimizing layout shifts. Our custom canvas element relies on lightweight execution loops linked directly to requestAnimationFrame. We use boundary validation systems to protect calculations from numeric errors, avoiding thread stalls during rapid manual adjustments. Sound generation relies on the Web Audio API, which maps signal voltage peaks directly to audio pitch frequencies when sound output is enabled.

Future Research Directions & Engineering Roadmap

This platform serves as a foundation for testing cloud-based educational and diagnostic software. Future development will focus on the following features:

  • Real-Time Fast Fourier Transforms (FFT): Adding a split-screen spectral power visualizer to show signal frequency distributions alongside the time-domain waveform.
  • Importing External Files: Providing file-upload support for PhysioNet European Data Format (.edf) and raw text files, enabling direct visualization and analysis of patient data in the browser.
  • Expanded Explainable AI (XAI) Models: Integrating WebNN or lightweight TensorFlow.js models to replace the fuzzy rules with deep learning-based arrhythmia and seizure classification.
  • Dynamic 3D Source Localization: Adding an interactive WebGL skull and cortex model to estimate EEG source locations on a virtual cortical mesh using signal amplitudes.

Context-Aware Cross-Linking Engine

Explore related simulation environments and diagnostic interfaces from the BioniChaos project collection:

  • Neurofeedback Mapping Interface

    Live cortical region mapping and biofeedback visualization designed to demonstrate neurological self-regulation training protocols.

  • SeizureSim Interactive Engine

    Detailed epileptic seizure propagation modeling with dynamic 3D electroencephalographic electrode array outputs.

  • EEG Signal Source Mixer (ICA/PCA)

    Interactive tool to decompose multi-channel EEG signals using Independent Component Analysis and Principal Component Analysis.

  • Artificial Pacemaker Simulator

    Dynamic cardiac pacing model and lead synchronization interface designed to demonstrate electrical conduction management.