A Proposal for Multimodal Emotion Recognition Using Aural Transformers and Action Units on RAVDESS Dataset

Emotion recognition is attracting the attention of the research community due to its multiple applications in different fields, such as medicine or autonomous driving. In this paper, we proposed an automatic emotion recognizer system that consisted of a speech emotion recognizer (SER) and a facial emotion recognizer (FER). For the SER, we evaluated a pre-trained xlsr-Wav2Vec2.0 transformer using two transfer-learning techniques: embedding extraction and fine-tuning. The best accuracy results were achieved when we fine-tuned the whole model by appending a multilayer perceptron on top of it, confirming that the training was more robust when it did not start from scratch and the previous knowledge of the network was similar to the task to adapt. Regarding the facial emotion recognizer, we extracted the Action Units of the videos and compared the performance between employing static models against sequential models. Results showed that sequential models beat static models by a narrow difference. Error analysis reported that the visual systems could improve with a detector of high-emotional load frames, which opened a new line of research to discover new ways to learn from videos. Finally, combining these two modalities with a late fusion strategy, we achieved 86.70% accuracy on the RAVDESS dataset on a subject-wise 5-CV evaluation, classifying eight emotions. Results demonstrated that these modalities carried relevant information to detect users’ emotional state and their combination allowed to improve the final system performance.

Introduction

This chapter serves as an introduction to the book Practical Microsimulation Modelling. It provides as context a description of microsimulation modelling, a simulation-based tool with a micro-unit of analysis that can be used for ex-ante analysis. The methodology is motivated as a mechanism of abstracting from reality to help us understand complexity better. It describes the main analytical objectives of users of microsimulation models in the field of income distribution analysis. The chapter then describes in turn the main methods of microsimulation considered in the book: hypothetical models, static models, behavioural models (labour supply and consumption), environmental models, decomposing inequality, dynamic microsimulation models, and spatial microsimulation models. The chapter concludes by providing an outline of the book.

ANALYSIS AND COMPARATIVE RESEARCH OF THE MAIN APPROACHES TO THE MATHEMATICAL FORMALIZATION OF THE PENETRATION TESTING PROCESS

In dynamic models, threats (vulnerabilities) can be viewed as a flow of temporary events. If the intervals of realized cyber threats are recorded, then a continuous log-list of events related to software security can be formed. In some cases and models, only the number of realized cyber threats for an arbitrary time interval can be recorded. In this case, the software response to threats can be represented only at discrete points. In static models, the implementation of cyber threats is not related to time, but the dependence of the number of errors or the number of implemented test cases (models by error area) on the characteristics of the input data (models by data area) is taken into account. The article analyzes the methods of mathematical formalization of the software penetration testing process. This software testing method is one of many approaches to testing the security of computer systems. The article substantiates the importance of the processes of preliminary prototyping and mathematical formalization. The classification is carried out and the advantages and disadvantages of the main approaches of mathematical modeling are highlighted. The list and main characteristics of dynamic and static models are presented. One of the negative factors of formalization is indicated - the neglect of the factors of a priori uncertainty in the safety parameters in static models.

Design of Contact-aided Compliant Flexure Hinge Mechanism Using Superelastic Nitinol

This paper presents a novel miniature contact-aided compliant mechanism (CCM) that includes flexure hinges and contact-aided structures. This continuum mechanism comprises a nickel–titanium alloy (Nitinol) tube with CCM cut via laser micromachining and actuated using wires bending from −80° to +80° in four directions. The proposed CCM has the following merits: perfect capacity for deflection around the centroid, a self-backbone, and improved torsional as well as tensile strengths. Further, it is pre-assembled. First, kinematic and static models are used to predict the bending behaviour of the mechanism. Thereafter, the maximum strain is evaluated using finite element analysis (FEA) then compared with the static models. Finally, the performances of the mechanism are characterized by experiments. The results validate the proposed models and demonstrate that the torsional and tensile strengths of the proposed CCM increased by more than 100% and 30%, respectively, compared with those of conventional non-CCMs with a similar fatigue life. Moreover, with the integrated forceps and probe, the proposed mechanism can achieve object transfer and square trajectory scanning of the targeted location. These experimental results demonstrate the potential clinical value of the proposed mechanism and provide important insights into the design of long and flexible instruments for endoscopic surgery.