SAAQ: A Characterization Method for Distributed Servers in Ubicomp Environments.

The increasing evolution of computing technologies has fostered the new intelligent concept of Ubiquitous computing (Ubicomp). Ubicomp environments encompass the introduction of new paradigms, such as Internet of Things (IoT), Mobile computing, and Wearable computing, into communication networks, which demands more efficient strategies to deliver tasks and services, considering heterogeneity, scalability, reliability, and efficient energy consumption of the connected devices. Middlewares have a crucial role to deal with all these aspects, by implementing efficient load balancing methods based on the hardware characterization and the computational cost of the queries and tasks. However, most existing solutions do not take into account both considerations in conjunction. In this context, we propose a methodology to characterize distributed servers, services, and network delays in Ubicomp environments, based on the Server Ability to Answer a Query (SAAQ). To evaluate our SAAQ-based methodology, we implemented a simple middleware in a museum context, in which different IoT devices (e.g., social robots, mobile devices) and distributed servers with different capabilities can participate, and performed a set of experiments in scenarios with diverse hardware and software characteristics. Results show that the middleware is able to distribute queries to servers with adequate capacity, freeing from service requests to devices with hardware restrictions; thus, our SAAQ-based middleware has a good performance regarding throughput (22.52 ms for web queries), end-to-end delay communications (up to 193.30 ms between San Francisco and Amsterdam), and good management of computing resources (up to 80% of CPU consumption).

Emotion Detection for Social Robots Based on NLP Transformers and an Emotion Ontology.

For social robots, knowledge regarding human emotional states is an essential part of adapting their behavior or associating emotions to other entities. Robots gather the information from which emotion detection is processed via different media, such as text, speech, images, or videos. The multimedia content is then properly processed to recognize emotions/sentiments, for example, by analyzing faces and postures in images/videos based on machine learning techniques or by converting speech into text to perform emotion detection with natural language processing (NLP) techniques. Keeping this information in semantic repositories offers a wide range of possibilities for implementing smart applications. We propose a framework to allow social robots to detect emotions and to store this information in a semantic repository, based on EMONTO (an EMotion ONTOlogy), and in the first figure or table caption. Please define if appropriate. an ontology to represent emotions. As a proof-of-concept, we develop a first version of this framework focused on emotion detection in text, which can be obtained directly as text or by converting speech to text. We tested the implementation with a case study of tour-guide robots for museums that rely on a speech-to-text converter based on the Google Application Programming Interface (API) and a Python library, a neural network to label the emotions in texts based on NLP transformers, and EMONTO integrated with an ontology for museums; thus, it is possible to register the emotions that artworks produce in visitors. We evaluate the classification model, obtaining equivalent results compared with a state-of-the-art transformer-based model and with a clear roadmap for improvement.