İnsan aktivitesi tanımada derin öğrenme yöntemlerinin uygulanması

Traditional sensor-based human activity recognition (HAR) has been defined as a time-series data classification problem and requires feature extraction. The current HAR systems still lack transparent, interpretable, and explainable approaches that can generate human-understandable information. This thesis proposes an approach, called Human Activity Recognition on Signal Images (HARSI), which defines the HAR problem as an image classification problem to improve both explainability and recognition accuracy. The proposed HARSI approach transforms the smart sensor data into some visual images to take advantage of the strengths of convolutional neural networks (CNN) in handling image data. The experimental results carried out on a real-world dataset showed that a significant improvement was achieved by the proposed HARSI model compared to the traditional machine learning models. The results also showed that our method outperformed the state-of-the-art methods in terms of classification accuracy.