arXiv subjects

Alexandre Silva

Publications and source records attributed to Alexandre Silva.

5 recordsLinked to original sources

arXiv2026

Using the gameplay and user data to predict and identify causes of cybersickness manifestation in virtual reality games

Virtual reality (VR) is an imminent trend in games, education, entertainment, military, and health applications, as the use of head-mounted displays is accessible to everyone. While VR provides immersive experiences, it still does not offer an entirely perfect situation, mainly due to cybersickness (CS) issues. In this work, we propose a novel approach for predicting upcoming CS symptoms. Our solution is able to suggest whether the user of VR is entering into an illness situation. We adopted random forest classifiers and validated our solution using 16 different machine-learning techniques, which presented the best results. For training purposes, we built our own dataset through a CS profile questionnaire that we also propose in the present work. The questionnaire is focused on registering and identifying the user's susceptibility to CS, considering their historical conditions and also their response to the immersive environment developed by us. In this method, 86 individuals are selected and the developed questionnaire was put to them on different days, and the answers are compiled as dataset. Our proposal also identifying attributes responsible (causes and individual's parameters) for the observed stressful and uncomfortable situations.

cs.HC↗

arXiv2022

A deep learning approach to the texture optimization problem for friction control in lubricated contacts

The possibility to control friction through surface micro texturing could offer invaluable advantages in many fields, from wear and pollution reduction in the transportation industry to improved adhesion and grip. Unfortunately, the texture optimization problem is very hard to solve using traditional experimental and numerical methods, due to the complexity of the texture configuration space. In this work, we apply machine learning techniques to perform the texture optimization, by training a deep neural network to predict, with extremely high accuracy and speed, the Stribeck curve of a textured surface in lubricated contact. The deep neural network was used to completely resolve the mapping between textures and Stribeck curves, enabling a simple method to solve the texture optimization problem. This work demonstrates the potential of machine learning techniques in texture optimization for friction control in lubricated contacts.

physics.comp-ph↗

arXiv2020

Automatic Recommendation of Strategies for Minimizing Discomfort in Virtual Environments

Virtual reality (VR) is an imminent trend in games, education, entertainment, military, and health applications, as the use of head-mounted displays is becoming accessible to the mass market. Virtual reality provides immersive experiences but still does not offer an entirely perfect situation, mainly due to Cybersickness (CS) issues. In this work, we first present a detailed review about possible causes of CS. Following, we propose a novel CS prediction solution. Our system is able to suggest if the user may be entering in the next moments of the application into an illness situation. We use Random Forest classifiers, based on a dataset we have produced. The CSPQ (Cybersickness Profile Questionnaire) is also proposed, which is used to identify the player's susceptibility to CS and the dataset construction. In addition, we designed two immersive environments for empirical studies where participants are asked to complete the questionnaire and describe (orally) the degree of discomfort during their gaming experience. Our data was achieved through 84 individuals on different days, using VR devices. Our proposal also allows us to identify which are the most frequent attributes (causes) in the observed discomfort situations.

cs.HC↗

arXiv2020

HPIM-DM: a fast and reliable dense-mode multicast routing protocol (extended version)

This paper proposes the HPIM-DM (Hard-state Protocol Independent Multicast - Dense Mode) multicast routing protocol. HPIM-DM is a hard-state version of PIM-DM that keeps its main characteristics but has faster convergence and better resilience to replay attacks. Like PIM-DM, HPIM-DM is meant for dense networks and supports its operation on a unicast routing protocol and reverse path forwarding checks. However, routers maintain sense of the multicast trees at all times, allowing fast reconfiguration in the presence of network failures or unicast route changes. This is achieved by (i) keeping information on all upstream neighbors from which multicast data can be received, (ii) ensuring the reliable transmission and sequencing of control messages, and (iii) synchronizing the routing information immediately when a new router joins the network. The protocol was fully implemented in Python, and the implementation is publicly available. Finally, the correctness of the protocol was extensively validated using model checking, logical reasoning and tests performed over the protocol implementation.

cs.NI↗

arXiv2018

FPR -- Fast Path Risk Algorithm to Evaluate Collision Probability

As mobile robots and autonomous vehicles become increasingly prevalent in human-centred environments, there is a need to control the risk of collision. Perceptual modules, for example machine vision, provide uncertain estimates of object location. In that context, the frequently made assumption of an exactly known free-space is invalid. Clearly, no paths can be guaranteed to be collision free. Instead, it is necessary to compute the probabilistic risk of collision on any proposed path. The FPR algorithm, proposed here, efficiently calculates an upper bound on the risk of collision for a robot moving on the plane. That computation orders candidate trajectories according to (the bound on) their degree of risk. Then paths within a user-defined threshold of primary risk could be selected according to secondary criteria such as comfort and efficiency. The key contribution of this paper is the FPR algorithm and its `convolution trick' to factor the integrals used to bound the risk of collision. As a consequence of the convolution trick, given $K$ obstacles and $N$ candidate paths, the computational load is reduced from the naive $O(NK)$, to the qualitatively faster $O(N+K)$.

cs.RO↗