The recognition of human activities (HAR) using wearable device data, such as smartwatches, has gained significant attention in the field of computer science due to its potential to provide insights into individuals’ daily activities. This article aims to conduct a comparative study of deep learning techniques for recognizing activities of daily living (ADL). A mapping of HAR techniques was performed, and three techniques were selected for evaluation, along with a dataset. Experiments were conducted using the selected techniques to assess their performance in ADL recognition, employing standardized evaluation metrics, such as accuracy, precision, recall, and F1-score. Among the evaluated techniques, the DeepConvLSTM architecture, consisting of recurrent convolutional layers and a single LSTM layer, achieved the most promising results. These findings suggest that software applications utilizing this architecture can assist smartwatch users in understanding their movement routines more quickly and accurately.

Given the growing interest in immersive gaming experiences, particularly within the horror genre, there is a rising demand for sophisticated and engaging game mechanics. However, creating a truly immersive horror experience requires a balance between fear-inducing elements and player engagement. In this work, we present Eyes of Fear, a horror game that explores human emotions and eye movement as interactive mechanisms in virtual reality. We used a state-of-the-art emotion recognition algorithm and Tobii Eye Tracker for our game prototype and evaluated their effectiveness through player feedback. Our findings show that emotion-sensitive enemy behavior elevates unpredictability and intense emotions while amusing players.