As traffic conditions constantly change, adaptive optimisation has proven to be an effective method for adapting traffic signal control systems accordingly. The utilisation of heuristic algorithms in directing traffic light control strategies, both in fixed time and real-time, has shown significant results. In order to improve the optimisation approach's ability to cope with modern traffic scenarios and synchronise with them, we propose a novel self-adapting algorithm to further enhance their capabilities. This work integrates particle swarm optimisation and ant colony optimisation with the novel self-adaptive approach, which enhances the selection of the most appropriate traffic cycle length to reduce traffic congestion based on real-world traffic conditions. The numerical experiments conducted on two traffic scenarios, peak hour and non-peak hour, show that our approach outperforms existing approaches by reducing travel time, traffic congestion, queue length, and pedestrian flow by 34%, 44%, 39%, and 11%, respectively. These results imply that our method can be implemented in real-world scenarios for sophisticated traffic light management.

In recent years, artificial intelligence technologies have been successfully applied in time series prediction and analytic tasks. At the same time, a lot of attention has been paid to financial time series prediction, which targets the development of novel deep learning models or optimize the forecasting results. To optimize the accuracy of stock price prediction, in this paper, we propose a clustering-enhanced deep learning framework to predict stock prices with three matured deep learning forecasting models, such as Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN) and Gated Recurrent Unit (GRU). The proposed framework considers the clustering as the forecasting pre-processing, which can improve the quality of the training models. To achieve the effective clustering, we propose a new similarity measure, called Logistic Weighted Dynamic Time Warping (LWDTW), by extending a Weighted Dynamic Time Warping (WDTW) method to capture the relative importance of return observations when calculating distance matrices. Especially, based on the empirical distributions of stock returns, the cost weight function of WDTW is modified with logistic probability density distribution function. In addition, we further implement the clustering-based forecasting framework with the above three deep learning models. Finally, extensive experiments on daily US stock price data sets show that our framework has achieved excellent forecasting performance with overall best results for the combination of Logistic WDTW clustering and LSTM model using 5 different evaluation metrics.

This paper addresses reliable and efficient calculation of the mode of a multivariate sample, which is a classical fusion function. In particular, we focus on the inputs given on the unit simplex, when aggregating elements of Atanassov intuitionistic fuzzy sets, interval-valued fuzzy sets and their extensions, as well as compositional data. We outline the use of a specially designed 2-additive fuzzy measures and the Choquet integral for the purposes of reducing computational complexity in higher dimensions. We present computational analysis and benchmark four different methods of density-based mode estimation.

The cursive and ligature nature of the Arabic script make the segmentation of words into individual characters a difficult task. Despite attempts to apply methods for cursive Latin and other scripts to Arabic script, it is generally insufficient to segment the Arabic text. This paper proposes a new segmentation algorithm for the handwritten Arabic text and the main idea consists of segmenting the word into sub-words and then computing the baseline of each sub-word. Using the descenders of sub-words and the baseline, candidate points are then calculated using a vertical projection. The algorithm has been tested using 800 handwritten Arabic words taken from the IFN/ENIT database and a comparison made against some existing methods and promising results have been obtained.

UNLABELLED: We present a novel method for finding low-dimensional views of high-dimensional data: Targeted Projection Pursuit. The method proceeds by finding projections of the data that best approximate a target view. Two versions of the method are introduced; one version based on Procrustes analysis and one based on an artificial neural network. These versions are capable of finding orthogonal or non-orthogonal projections, respectively. The method is quantitatively and qualitatively compared with other dimension reduction techniques. It is shown to find 2D views that display the classification of cancers from gene expression data with a visual separation equal to, or better than, existing dimension reduction techniques. AVAILABILITY: source code, additional diagrams, and original data are available from http://computing.unn.ac.uk/staff/CGJF1/tpp/bioinf.html