International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 186 - Issue 66 |
Published: February 2025 |
Authors: Surabhi Anand, Sahil Miglani, Royana Anand |
![]() |
Surabhi Anand, Sahil Miglani, Royana Anand . Neuro-Symbolic Signal Processing: A Modular Framework for Adaptive and Transparent Real-Time Cognitive Signal Interpretation. International Journal of Computer Applications. 186, 66 (February 2025), 24-30. DOI=10.5120/ijca2025924351
@article{ 10.5120/ijca2025924351, author = { Surabhi Anand,Sahil Miglani,Royana Anand }, title = { Neuro-Symbolic Signal Processing: A Modular Framework for Adaptive and Transparent Real-Time Cognitive Signal Interpretation }, journal = { International Journal of Computer Applications }, year = { 2025 }, volume = { 186 }, number = { 66 }, pages = { 24-30 }, doi = { 10.5120/ijca2025924351 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2025 %A Surabhi Anand %A Sahil Miglani %A Royana Anand %T Neuro-Symbolic Signal Processing: A Modular Framework for Adaptive and Transparent Real-Time Cognitive Signal Interpretation%T %J International Journal of Computer Applications %V 186 %N 66 %P 24-30 %R 10.5120/ijca2025924351 %I Foundation of Computer Science (FCS), NY, USA
Assistive technologies have revolutionized accessibility for individuals with sensory, motor, and cognitive impairments. However, current cognitive signal processing techniques often face significant trade-offs between the adaptability of deep neural networks (DNNs) and the transparency of symbolic artificial intelligence (AI). These limitations hinder the effectiveness of such technologies in real-time, safety-critical applications. This paper proposes a novel neuro-symbolic architecture, integrating the representational power of DNNs with the logical reasoning capabilities of symbolic AI. The framework features three core modules: a neural feature extraction module for processing complex signals, a symbolic reasoning module for interpretable decision-making, and a hybrid integration layer for dynamic context-sensitive output synthesis. This modular design ensures scalability, transparency, and adaptability, addressing key challenges in cognitive signal processing. Potential applications in assistive technologies, healthcare, and adaptive learning are explored. This paper also provides a roadmap for implementation, emphasizing the framework’s transformative potential in computational intelligence and communication networks.