Speech Quality Assessment Over Lossy Transmission Channels Using Deep Belief Networks

et al. 2020

Sensors

Self Cite

Minimizing human intervention in engines, such as traffic lights, through automatic applications and sensors has been the focus of many studies. Thus, Deep Learning (DL) algorithms have been studied for traffic signs and vehicle identification in an urban traffic context. However, there is a lack of priority vehicle classification algorithms with high accuracy, fast processing, and a lightweight solution. For filling those gaps, a vehicle detection system is proposed, which is integrated with an intelligent traffic light. Thus, this work proposes (1) a novel vehicle detection model named Priority Vehicle Image Detection Network (PVIDNet), based on YOLOV3, (2) a lightweight design strategy for the PVIDNet model using an activation function to decrease the execution time of the proposed model, (3) a traffic control algorithm based on the Brazilian Traffic Code, and (4) a database containing Brazilian vehicle images. The effectiveness of the proposed solutions were evaluated using the Simulation of Urban MObility (SUMO) tool. Results show that PVIDNet reached an accuracy higher than 0.95, and the waiting time of priority vehicles was reduced by up to 50%, demonstrating the effectiveness of the proposed solution.

“…In recent years, several architectural models for DL algorithms have been presented for many applications, each one with its particularities and means of use [30][31][32][33][34].…”

Section: Deep Learning Algorithms For Object Detectionmentioning

confidence: 99%

Lightweight PVIDNet: A Priority Vehicles Detection Network Model Based on Deep Learning for Intelligent Traffic Lights

Barbosa

Ayub

et al. 2020

Sensors

Self Cite

“…Thus, the proposed model can be useful in modern communication networks that operate in high frequency bands, such as those used in 5G networks. It is important to note that P.563 is a non-intrusive algorithm which results are not reliable in lossy channel transmissions [55], but there is not another standardized non-intrusive algorithm.…”

Section: B Performance Assessment Of the Proposed Modelmentioning

confidence: 99%

Speech Quality Classifier Model based on DBN that Considers Atmospheric Phenomena

Silva

Carrillo²,

J. commun. softw. syst. (Online)

et al. 2020

Current implementations of 5G networks consider higher frequency range of operation than previous telecommunication networks, and it is possible to offer higher data rates for different applications. On the other hand, atmospheric phenomena could have a more negative impact on the transmission quality. Thus, the study of the transmitted signal quality at high frequencies is relevant to guaranty the user ́s quality of experience. In this research, the recommendations ITU-R P.838-3 and ITU-R P.676-11 are implemented in a network scenario, which are methodologies to estimate the signal degradations originated by rainfall and atmospheric gases, respectively. Thus, speech signals are encoded by the AMR-WB codec, transmitted and the perceptual speech quality is evaluated using the algorithm described in ITU-T Rec. P.863, mostly known as POLQA. The novelty of this work is to propose a non-intrusive speech quality classifier that considers atmospheric phenomena. This classifier is based on Deep Belief Networks (DBN) that uses Support Vector Machine (SVM) with radial basis function kernel (RBF-SVM) as classifier, to identify five predefined speech quality classes. Experimental Results show that the proposed speech quality classifier reached an accuracy between 92% and 95% for each quality class overcoming the results obtained by the sole non-intrusive standard described in ITU-T Recommendation P.563. Furthermore, subjective tests are carried out to validate the proposed classifier performance, and it reached an accuracy of 94.8%.

“…Machine Learning algorithms allow the computer to automatize and improve the performance of some tasks in diverse areas [22], highlighting the RS, pattern recognition, time series prediction, search engines, and others [23], [24]. Machine learning algorithms can be classified in supervised and unsupervised classification.…”

Section: B Machine Learning Algorithms and Hybrid Discriminative Resmentioning

confidence: 99%

A Recommendation System for Shared-Use Mobility Service through Data Extracted from Online Social Networks

Lasmar

Rodríguez

2018

JCOMSS

In recent years, the shared mobility service has increased in many countries across the world because its low cost and several shared-use mobility applications on mobile devices [1]. Commonly, if a ride is shared between people with similar preferences, users likely feel both more comfortable and safe. In this context, the main goal of this article is to classify users with similar preferences, in automatic manner, to improve user's quality of experience in ridesharing service. To obtain initial data, subjective tests are carried out using questionnaires and their results are used to determine ridesharing profiles. Then, some basic user profile information is extracted from Online Social Networks (OSN) to determine an user profile based on preferences in ridesharing service. The user profile classification is performed through different machine learning algorithms, which use as input the data extracted from OSN. Two case studies of shared-mobility are treated, (i) sharing a ride with a passenger with a similar hobby [2], and (ii) sharing a ride with people that support an opposite football teams. The novelty of this work consists in the application of the Hybrid Discriminative Restricted Boltzmann Machines (HDRBM) algorithm for classification whose performance overperforms widely used algorithms such as Random Forest, SVM and DRBM. The experimental results presented a correctly classified instance of 96.9% and 97.3% for the cases of sharing a ride with people with similar hobby and support different football team, respectively. Finally, a Recommendation System (RS) is proposed, which efficiency is compared with a basic RS, obtaining a Pearson correlation coefficient of 0.97 and 0.71, respectively. Index Terms-Recommendation system; ridesharing; mobile applications, online social networks, machine learning, HDRBM, social web analysis tool. I. INTRODUCTION T HE mobile devices and applications have facilitated the manner of people request services. The urban mobility is a kind of service that became very popular, in it is common that people share the rides among others. The advantages of this service are related to benefits for urban traffic, such as reduction of environment pollution, and low cost.