Leveraging Metaheuristic Approaches to Improve Deep Learning Systems for Anxiety Disorder Detection

TL;DR

This paper presents a hybrid approach combining deep learning and swarm intelligence optimization to improve the accuracy and generalization of anxiety disorder detection using multimodal sensor data.

Contribution

It introduces a novel integrated framework that leverages metaheuristic algorithms to optimize deep learning models for anxiety detection, enhancing performance over traditional methods.

Findings

Significant accuracy improvements over standalone deep learning models

Enhanced generalization across diverse individuals

Effective feature space refinement using genetic algorithms and particle swarm optimization

Abstract

Despite being among the most common psychological disorders, anxiety-related conditions are still primarily identified through subjective assessments, such as clinical interviews and self-evaluation questionnaires. These conventional methods often require significant time and may vary depending on the evaluator. However, the emergence of advanced artificial intelligence techniques has created new opportunities for detecting anxiety in a more consistent and automated manner. To address the limitations of traditional approaches, this study introduces a comprehensive model that integrates deep learning architectures with optimization strategies inspired by swarm intelligence. Using multimodal and wearable-sensor datasets, the framework analyzes physiological, emotional, and behavioral signals. Swarm intelligence techniques including genetic algorithms and particle swarm optimization are incorporated to refine the feature space and optimize hyperparameters. Meanwhile, deep learning components are tasked with deriving layered and discriminative representations from sequential, multi-source inputs. Our evaluation shows that the fusion of these two computational paradigms significantly enhances detection performance compared with using deep networks alone. The hybrid model achieves notable improvements in accuracy and demonstrates stronger generalization across various individuals. Overall, the results highlight the potential of combining metaheuristic optimization with deep learning to develop scalable, objective, and clinically meaningful solutions for assessing anxiety disorders