An Evaluation Method for Multi-Agent Systems

Detecting emotions is very useful in many fields, from health-care to human-computer interaction. In this paper, we propose an iterative user-centered methodology for supporting the development of an emotion detection system based on low-cost sensors. Artificial Intelligence techniques have been adopted for emotion classification. Different kind of Machine Learning classifiers have been experimentally trained on the users’ biometrics data, such as hearth rate, movement and audio. The system has been developed in two iterations and, at the end of each of them, the performance of classifiers (MLP, CNN, LSTM, Bidirectional-LSTM and Decision Tree) has been compared. After the experiment, the SAM questionnaire is proposed to evaluate the user’s affective state when using the system. In the first experiment we gathered data from 47 participants, in the second one an improved version of the system has been trained and validated by 107 people. The emotional analysis conducted at the end of each iteration suggests that reducing the device invasiveness may affect the user perceptions and also improve the classification performance.

show abstract

“…How is the performance of the classifier measured? Accuracy is one of the most adopted metrics [9]. -Invasiveness.…”

Section: Background and Related Workmentioning

confidence: 99%

A user-centered approach for detecting emotions with low-cost sensors

Francese

Risi

Tortora

2020

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…The set of architectures agree on the fact that an agent receives (or perceives) flows (or stimuli) from its environment via sensors (or sensory organs), proceeds to a processing on these data and restores an action on the through its effectors (or organs engines) [1]. These actions are themselves perceived by the agent, this forming a loop: the agent is described as being integrated into its environment (embedded according to (Ferguson, 1992)).…”

Section: The Taxonomy 0f Agentsmentioning

confidence: 99%

The Multi-Agent System A Key Pillar in The Modeling And Engineering of Digital Assessment Platforms For A Real Competency Mapping

Yassir¹

2019

IJATCSE

View full text Add to dashboard Cite

The digital assessment platforms is a subject that has not ceased to arouse the interest of researchers in any field. Our study focuses on the architecture and modeling of eassessment platforms and the impact of the multi-agent system on talent measurement. We define a metamodel describing the operating paradigm of this tool. The peculiarity of our application framework lies in the study of the last four ITEF master classes at Hassan II University. For this study, we used the "Innermetrix" tool, an engineering assessment process platform ranked number 1 worldwide.The objective of this paper is to have real competency mapping by defining a digital student repository associated with a digital study agent able to test and evaluate the skills of students in terms of output. The objective is to evaluate the cognitive-behavioral dimensions of students after spending two years in a training that combines a theoretical component and another practice.

show abstract

“…• Frecuencia de transmisión de datos: La forma de activación de los agentes dentro de un proceso puede ser a través del tiempo [25] o a mediante un evento [26]. • Movilidad: En base al dinamismo de los sistemas multiagente se agrupan en estáticos [27] o dinámicos [28].…”

Section: Introducci óNunclassified