A review of computational intelligence methods for traffic management systems

One of the most important challenges in modern city life is to enable effective and efficient traffic management system. Recently, computational intelligence methods have become increasingly popular for traffic management system design, application, and monitoring. Computational intelligence methods are often deployed for managing traffic, that is for reducing mileage, congestion, the use of fuels, and environmental impact. The aim of this paper is twofold. First, to present the three main areas in a computational intelligence approach, namely neural networks, fuzzy logic systems, and evolutionary computation. Second, to emphasize their impact on various traffic management domains, including traffic flow forecasting, traffic light control, traffic fatalities prediction, traffic sign detection, and optimization of transportation networks.

A review of computational intelligence methods for traffic management systems

One of the most important challenges in modern city life is to enable effective and efficient traffic management system. Recently, computational intelligence methods have become increasingly popular for traffic management system design, application, and monitoring. Computational intelligence methods are often deployed for managing traffic, that is for reducing mileage, congestion, the use of fuels, and environmental impact. The aim of this paper is twofold. First, to present the three main areas in a computational intelligence approach, namely neural networks, fuzzy logic systems, and evolutionary computation. Second, to emphasize their impact on various traffic management domains, including traffic flow forecasting, traffic light control, traffic fatalities prediction, traffic sign detection, and optimization of transportation networks.

The Power of Computational Intelligence Methods in the Containment of COVID-19 Pandemic from Detection to Recovery

The coronavirus disease (SARS-CoV-2)) pandemic has caused unprecedented economic crises, and changes in our lifestyle to different things that we have not experienced before in this century, which cause by movement restriction order by the authority to halt the spread of the disease around the globe. Researchers around the globe applied computational intelligence methods in numerous fields which exhibits a successful story. The computational intelligence methods play an important role in dealing with coronavirus pandemics. This research will focus on the use of computational intelligence methods in understanding the infection, accelerating drugs and treatments research, detecting, diagnosis, and predicting the virus, surveillance, and contact tracing to prevent or slow the virus from the spread, monitoring the recovery of the infected individuals. This study points out promising CI techniques utilized as an adjunct along with the current methods used in containments of COVID-19. It is imagined that this study will give CI researchers and the wider community an outline of the current status of CI applications and motivate CI researchers in harnessing CI technique possibilities in the battle against COVID-19.

Deep Learning Models for Automatic Makeup Detection

Makeup can disguise facial features, which results in degradation in the performance of many facial-related analysis systems, including face recognition, facial landmark characterisation, aesthetic quantification and automated age estimation methods. Thus, facial makeup is likely to directly affect several real-life applications such as cosmetology and virtual cosmetics recommendation systems, security and access control, and social interaction. In this work, we conduct a comparative study and design automated facial makeup detection systems leveraging multiple learning schemes from a single unconstrained photograph. We have investigated and studied the efficacy of deep learning models for makeup detection incorporating the use of transfer learning strategy with semi-supervised learning using labelled and unlabelled data. First, during the supervised learning, the VGG16 convolution neural network, pre-trained on a large dataset, is fine-tuned on makeup labelled data. Secondly, two unsupervised learning methods, which are self-learning and convolutional auto-encoder, are trained on unlabelled data and then incorporated with supervised learning during semi-supervised learning. Comprehensive experiments and comparative analysis have been conducted on 2479 labelled images and 446 unlabelled images collected from six challenging makeup datasets. The obtained results reveal that the convolutional auto-encoder merged with supervised learning gives the best makeup detection performance achieving an accuracy of 88.33% and area under ROC curve of 95.15%. The promising results obtained from conducted experiments reveal and reflect the efficiency of combining different learning strategies by harnessing labelled and unlabelled data. It would also be advantageous to the beauty industry to develop such computational intelligence methods.

Analyzing Healthcare Data Using Water Wave Optimization-Based Clustering Technique

The medical informatics field gets wide attention among the research community while developing a disease diagnosis expert system for useful and accurate predictions. However, accuracy is one of the major medical informatics concerns, especially for disease diagnosis. Many researchers focused on the disease diagnosis system through computational intelligence methods. Hence, this paper describes a new diagnostic model for analyzing healthcare data. The proposed diagnostic model consists of preprocessing, diagnosis, and performance evaluation phases. This model implements the water wave optimization (WWO) algorithm to analyze the healthcare data. Before integrating the WWO algorithm in the proposed model, two modifications are inculcated in WWO to make it more robust and efficient. These modifications are described as global information component and mutation operator. Several performance indicators are applied to assess the diagnostic model. The proposed model achieves better results than existing models and algorithms.

Investigation of computational intelligence methods in forecasting problems at stock exchanges

In this paper, the forecasting problem of share prices at the New York Stock Exchange (NYSE) was considered and investigated. For its solution the alternative methods of computational intelligence were suggested and investigated: LSTM networks, GRU, simple recurrent neural networks (RNN) and Group Method of Data Handling (GMDH). The experimental investigations of intelligent methods for the problem of CISCO share prices were carried out and the efficiency of forecasting methods was estimated and compared. It was established that method GMDH had the best forecasting accuracy compared to other methods in the problem of share prices forecasting.

The Salience of Traditional Moral Values: Bolsonaro’s Electoral Competition Strategy on Twitter

This article analyzes the electoral competition strategy adopted by the Brazilian presidential candidate Jair Bolsonaro on Twitter, supported by the saliency theory – where candidates compete by emphasizing different topics and selecting issues from a universal agenda to focus the campaign’s attention and efforts. The salience Bolsonaro’s winning campaign attributed to values during the 2018 presidential election. Values are attitudinal guidelines related to different social, religious, economic, and political concepts, covering various topics on views about what is desirable or undesirable in a society. The study used content analysis to explore and categorize a corpus of 809 tweets posted in the account @jairbolsonaro. The data was mined by applying computational intelligence methods and using the public API and the Python Twint library. Four dimensions of cultural variance found in the World Values Survey were used to establish the categories: traditional values, rational-secular values, survival values, and self-expression values. The results show that the content of Bolsonaro’s electoral competition strategy was based on traditional moral values and the campaign’s format was developed primarily via social media.