The Semantic Web has addressed the development of technologies for efficient data exchange through formats such as RDF and the use of SPARQL as a standard query language. However, users often face difficulties in obtaining unexpected or erroneous results without a clear understanding of the source of the problem, resulting in wasted time. In this context, a method for validating SPARQL queries, divided into five phases executed before processing in RDF engines, is proposed. This method is based on an ontology and considers both syntactic and semantic validations, generating detailed error reports to prevent problems during execution. Experimental results show the efficiency of the approach: when querying a dataset of 16,005 triples, syntactic validation did not exceed 0.4508 ms and semantic validation did not exceed 6.2343 ms. In contrast, queries without validation presented longer response times, with differences of up to 68.2492 ms in syntactic validation and 144.4288 ms in semantic validation. This approach not only improves query accuracy and efficiency, but also significantly reduces time and errors in information retrieval in semantic environments.

The rapid adoption of Internet of Things (IoT) technology has allowed the development of applications where devices such as sensors generate data periodically. These devices are integrated into IoT systems where large volumes of data are managed and whose processing and handling for the proper operation of the IoT system is necessary. One of the main challenges in IoT is the effective data management and real-time communication between heterogeneous devices. Ontologies, which are semantic representations of knowledge, are built to provide semantic interoperability. However, the diversity of applications and the scope of new technologies makes current ontology's proposals incomplete in modeling privacy and security, energy awareness, and ethics at the same time. In this context, we propose an enhanced Ontology, called IoTO++, for improving semantic interoperability in IoT environments. We validated the proposal considering lexical, structural and domain knowledge levels. Results show that even though lite ontologies are more maintainable, compatible and transferable, ontologies with more annotations are better in terms of functional adequacy. This includes but is not limited to characteristics like, knowledge reuse, acquisition and representation. Furthermore, IoTO++ demonstrates superior performance in the domain knowledge level, proving to be a more effective solution for modeling the variety of IoT applications.

Nowadays, the advancement of technology allows the use of social robots for various daily tasks such as therapies, teaching assistants, restaurant services, among others. Human-Robot Interaction (HRI) is under constant study due to the new capabilities that robots acquire thanks to their improved hardware (e.g., more joints). Robots receive information through sensors such as cameras and microphones and can thus modify their behavior and adapt to different situations. However, an exhaustive real-time analysis of data within the robot requires excessive computing power and energy usage, which are limited in social robots. In this context, we propose a lightweight Machine Learning model to balance accuracy and audio processing time to recognize the emotions of happiness, sadness, anger, and neutral in real-time, aiming to improve HRI. Additionally, an empirical analysis to identify the most relevant audio features for emotion recognition is presented. The objective is to generate a lighter and more appropriate model for the robot's hardware. Results show better accuracy by using the RAVDESS, IEMOCAP, and RAVDESS+IEMOCAP datasets and a recognition time around 1 second.

In robotics, object detection in images or videos, obtained in real-time from sensors of robots can be used to support the implementation of service robot tasks (e.g., navigation, model its social behavior, recognize objects in a specific domain), usually accomplished in indoor environments. However, traditional deep learning based object detection techniques present limitations in such indoor environments, specifically related to the detection of small objects and the management of high density of multiple objects. Coupled with these limitations, for specific domains (e.g., hospitals, museums), it is important that the robot, apart from detecting objects, extracts and knows information of the targeted objects. Ontologies, as a part of the Semantic Web, are presented as a feasible option to formally represent the information related to the objects of a particular domain. In this context, this work proposes an object detection and recognition process based on a Deep Learning algorithm, object descriptors, and an ontology. ODROM, an Object Detection and Recognition algorithm supported by Ontologies and applied to Museums, is an implementation to validate the proposal. Experiments show that the usage of ontologies is a good way of desambiguating the detection, obtained with a and$\mathbf{mAP}{@}0.5=0.88$and a$\mathbf{mAP}{@}[0.5:0.95]=61\%$.

Human emotion recognition from visual expressions is an important research area in computer vision and machine learning owing to its significant scientific and commercial potential. Since visual expressions can be captured from different modalities (e.g., face expressions, body posture, hands pose), multi-modal methods are becoming popular for analyzing human reactions. In contexts in which human emotion detection is performed to associate emotions to certain events or objects to support decision making or for further analysis, it is useful to keep this information in semantic repositories, which offers a wide range of possibilities for implementing smart applications. We propose a multi-modal method for human emotion recognition and an ontology-based approach to store the classification results in EMONTO, an extensible ontology to model emotions. The multi-modal method analyzes facial expressions, body gestures, and features from the body and the environment to determine an emotional state; this processes each modality with a specialized deep learning model and applying a fusion method. Our fusion method, called EmbraceNet+, consists of a branched architecture that integrates the EmbraceNet fusion method with other ones. We experimentally evaluate our multi-modal method on an adaptation of the EMOTIC dataset. Results show that our method outperforms the single-modal methods.

Twitter is one of the most popular information source available on the Web. Thus, there exist many studies focused on analyzing the credibility of the shared information. Most proposals use either Twitter API or web scraping to extract the data to perform such analysis. Both extraction techniques have advantages and disadvantages. In this work, we present a study to evaluate their performance and behavior. The motivation for this research comes from the necessity to know ways to extract online information in order to analyze in real-time the credibility of the content posted on the Web. To do so, we develop a framework which offers both alternatives of data extraction and implements a previously proposed credibility model. Our framework is implemented as a Google Chrome extension able to analyze tweets in real-time. Results report that both methods produce identical credibility values, when a robust normalization process is applied to the text (i.e., tweet). Moreover, concerning the time performance, web scraping is faster than Twitter API, and it is more flexible in terms of obtaining data; however, web scraping is very sensitive to website changes.

The Semantic Web and the Linked Open Data (LOD) initiatives promote the integration and combination of RDF data on the Web.In some cases, data need to be analyzed and protected before publication in order to avoid the disclosure of sensitive information.However, existing RDF techniques do not ensure that sensitive information cannot be discovered since all RDF resources are linked in the Semantic Web and the combination of different datasets could produce or disclose unexpected sensitive information.In this context, we propose a framework, called RiAiR, which reduces the complexity of the RDF structure in order to decrease the interaction of the expert user for the classification of RDF data into identifiers, quasi-identifiers, etc.An intersection process suggests disclosure sources that can compromise the data.Moreover, by a generalization method, we decrease the connections among resources to comply with the main objectives of integration and combination of the Semantic Web.Results show a viability and high performance for a scenario where heterogeneous and linked datasets are present.

In the context of RDF document matching/integration, the datatype information, which is related to literal objects, is an important aspect to be analyzed in order to better determine similar RDF documents. In this paper, we present an R DF D atatype in F erring F ramework, called RDF-F, which provides two independent datatype inference processes: 1) a four-step process consisting of (i) a predicate information analysis (i.e., deduce the datatype from existing range property), (ii) an analysis of the object value itself by a pattern-matching process (i.e., recognize the object lexical space), (iii) a semantic analysis of the predicate name and its context, and (iv) generalization of Numeric and Binary datatypes to ensure the integration; and 2) a non-ambiguous lexical-space-matching process, where literal values are inferred by the modification of their representation, following new lexical spaces. We evaluated the performance and the accuracy of both processes with datasets from DBpedia. Results show that the execution time of both indicators is linear and their accuracy can increase up to 97.10 and 99.30%, respectively.

International audience

XML has experimented a rapid growth mostly because of its application on the Web. Application varies from version control management, data storage to clustering and information retrieval. In this context, it is necessary to develop efficient techniques for comparing XML documents. Many method proposed are based only on structural commonalities, ignoring semantics. In this paper, we propose a new method for comparing XML documents based on LevelEdge combining tag structural and semantic similarities.