No abstract

No abstract

No abstract

SUMMARYNowadays, the use of wireless sensor networks (WSNs) is increasing in many fields of application, such as industrial monitoring, home automation, and intensive agriculture. However, this technology presents an important shortcoming, which has not been solved yet: the energy efficiency. This factor involves a critical economic disadvantage, affecting quality of service. This situation led us to tackle the relay node placement problem, that is, the addition of relay nodes to traditional WSNs as a way to optimize such networks, assuming two important factors: energy consumption and average coverage. To achieve this goal, three multi-objective (MO) evolutionary algorithms are considered (non-dominated sorting genetic algoritm II, strength Pareto evolutionary algorithm 2, and MO gravitational search algorithm), assuming a freely available data set and different stop criteria to analyze the behavior of the algorithms. All the results obtained are studied through a widely accepted statistical methodology and two MO metrics (hypervolume and set coverage), concluding that the novel swarm intelligence algorithm MO gravitational search algorithm provides the best performance on average. Moreover, we study the advantages provided by the addition of relay nodes to traditional WSNs. Finally, we compare our proposal with another author approach, assuming a heuristic.

Emotion recognition is benefitting from the latest research into physiological monitoring and wireless communications, among other remarkable achievements. These technologies can indeed provide solutions to protect vulnerable people in scenarios such as personal assaults, the abuse of children or the elderly, gender violence or sexual aggression. Cyberphysical systems using smart sensors, artificial intelligence and wearable and inconspicuous devices can serve as bodyguards to detect these risky situations (through fear-related emotion detection) and automatically trigger a protection protocol. As expected, these systems should be trained and customized for each user to ensure the best possible performance, which undoubtedly requires a gender perspective. This paper presents a specialized fear recognition system for women based on a reduced set of physiological signals. The architecture proposed is characterized by the usage of three physiological sensors, lightweight binary classification and the conjunction of linear (temporal and frequency) and non-linear features. Moreover, a binary fear mapping strategy between dimensional and discrete emotional information based on emotional self-report data is implemented to avoid emotional bias. The architecture is evaluated using a public multi-modal physiological dataset with two approaches (subject-dependent and subject-independent models) focusing on the female participants. As a result, the proposal outperforms the state-of-the-art in fear recognition, achieving a recognition rate of up to 96.33% for the subject-dependent model.