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.

In Science Fiction (Sci-Fi) movies, filmmakers try to anticipate trends and new forms of interaction. Metaphors are created allowing their characters to interact with futuristic devices and environments. These devices and metaphors should be target of research considering they have proven to be useful before. Moreover, the impact of the new interfaces on the audience may indicate their expectations regarding future gesture interactions. Thus, the first goal of this work is to collect and expose a compilation of gestural interactions in Sci-Fi movies, providing a catalog to researchers as resource to future discussions. The second goal is to classify the collected data according to a series of criteria. The catalog is also open to new content contribution, and fellow researchers are invited to provide additional entries of hand gesture scenes from any Sci-Fi title as well as suggestions about new classification criteria and amendments on the already provided content.