Hisham El-Shishiny

An Empirical Comparison of Machine Learning Models for Time Series Forecasting

In this work we present a large scale comparison study for the major machine learning models for time series forecasting. Specifically, we apply the models on the monthly M3 time series competition data (around a thousand time series). There have been very few, if any, large scale comparison studies for machine learning models for the regression or the time series forecasting problems, so we hope this study would fill this gap. The models considered are multilayer perceptron, Bayesian neural networks, radial basis functions, generalized regression neural networks (also called kernel regression), K-nearest neighbor regression, CART regression trees, support vector regression, and Gaussian processes. The study reveals significant differences between the different methods. The best two methods turned out to be the multilayer perceptron and the Gaussian process regression. In addition to model comparisons, we have tested different preprocessing methods and have shown that they have different impacts on the performance.

An integrated framework for advanced hotel revenue management.

Purpose – This paper aims to present an integrated framework for hotel revenue room maximization. The revenue management (RM) model presented in this work treats the shortcomings in existing systems. In particular, it extends existing optimization techniques for hotel revenue management to address group reservations and uses “forecasted demand” arrivals generated from the real data.Design/methodology/approach – The proposed forecasting module attempts to model the hotel reservation process from first principles. In particular, it models hotel arrivals as an interrelated process of stochastic parameters like reservations, cancellations, duration of stay, no shows, seasonality, trend, etc. and simulates forward in time the actual process of reservations to obtain the forecast. On the other hand, the proposed optimization module extends existing optimization techniques for hotel revenue management to address group reservations, while including integrality constraints and using “forecasted demand” arrivals ge...

A goal programming model for planning the development of newly reclaimed lands

Abstract A large-scale, multi-objective single-time-period model for planning the development of reclaimed lands is proposed. The period considered is a typical year at the most developed stage of the agricultural complex. Given specific development goals and a set of resource constraints, the model determines the optimal land allocation for the integrated agricultural development of a region, including agricultural and livestock production as well as agriindustries. Linear Goal Programming is the multi-objective technique used for model formulation. The technique proposed for the solution is a multi-phase simplex algorithm which is based on the IBM-MPSX/370.

Multi-objective traffic light control system based on Bayesian probability interpretation

Traffic light control is a challenging problem in modern societies. This is due to the huge number of vehicles and the high dynamics of the traffic system. Poor traffic management causes a high rate of accidents, time losses, and negative impact on the economy as well as the environment. In this paper, we develop a multiagent traffic light control system based on a multi-objective sequential decision making framework. In order to respond effectively to the changing environment and the non-stationarity of the road network, the proposed traffic light controller is based on the Bayesian interpretation of probability. We use the open source Green Light District (GLD) vehicle traffic simulator as a testbed framework. The change in road conditions is modeled by varying the vehicles generation probability distributions and adapting the Intelligent Driver Model (IDM) parameters to the adverse weather conditions. We have added a set of new performance indices in GLD based on collaborative learning to better evaluate the performance of the proposed multi-objective traffic light controller. The results show that the proposed multi-objective controller outperforms the single-objective controller.

A regional broadcast-centric education system

Argues that a broadcast-centric solution can be enabled to provide educational services, in particular distance learning, to an entire region. This solution can provide equity access to resources for all schools in a large region, or access for undergraduate and postgraduate students to an open regional university. The approach described includes a combination of broadcast delivery and local redistribution of content and/or direct and interactive access to the content over the broadcast infrastructure. It requires that special consideration be given to the organization of content for distribution in this manner, therefore those issues are discussed. Enabling technologies are described.

A formal description of Arabic syntax in Definite Clause Grammar

Arabic has some special syntax features which lead to complex syntax structures. We have developed a formal description of Arabic syntax in Definite Clause Grammar. This grammar is characterized by its high descriptive power due to its dual formulation in terms of functions and in terms of grammatical categories. The developed grammar has a high coverage of Arabic language and has context sensitive capabilities. It is suitable for the advanced applications of natural language processing.

MLP, Gaussian Processes and Negative Correlation Learning for Time Series Prediction

Time series forecasting is a challenging problem, that has a wide variety of application domains such as in engineering, environment, finance and others. When confronted with a time series forecasting application, typically a number of different forecasting models are tested and the best one is considered. Alternatively, instead of choosing the single best method, a wiser action could be to choose a group of the best models and then to combine their forecasts. In this study we propose a combined model consisting of Multi-layer perceptron (MLP), Gaussian Processes Regression (GPR) and a Negative Correlation Learning (NCL) model. The MLP and the GPR were the top performers in a previous large scale comparative study. On the other hand, NCL suggests an alternative way for building accurate and diverse ensembles. No studies have reported on the performance of the NCL in time series prediction. In this work we test the efficiency of NCL in predicting time series data. Results on two real data sets show that the NCL is a good candidate model for forecasting time series. In addition, the study also shows that the combined MLP/GPR/NCL model outperforms all models under consideration.

Mining software aging: A neural network approach

This paper investigates the use of artificial neural networks (ANN) to predict software aging phenomenon. We analyze resource usage data collected on a typical long-running software system: a Web server. A multi-layer perceptron feed forward artificial neural network was trained on an Apache Web server dataset to predict future server resource exhaustion through univariate time series forecasting. The results were benchmarked against those obtained from non-parametric statistical techniques, parametric time series models and empirical modeling techniques reported in the literature.

Mining Software Aging Patterns by Artificial Neural Networks

This paper investigates the use of Artificial Neural Networks (ANN) to mine and predict patterns in software aging phenomenon. We analyze resource usage data collected on a typical long-running software system: a web server. A Multi-Layer Perceptron feed forward Artificial Neural Network was trained on an Apache web server dataset to predict future server swap space and physical free memory resource exhaustion through ANN univariate time series forecasting and ANN nonlinear multivariate time series empirical modeling. The results were benchmarked against those obtained from non-parametric statistical techniques, parametric time series models and other empirical modeling techniques reported in the literature.

Fuzzy clustering of large satellite images using high performance computing

Fuzzy clustering is one of the most frequently used methods for identifying homogeneous regions in remote sensing images. In the case of large images, the computational costs of fuzzy clustering can be prohibitive unless high performance computing is used. Therefore, efficient parallel implementations are highly desirable. This paper presents results on the efficiency of a parallelization strategy for the Fuzzy c-Means (FCM) algorithm. In addition, the parallelization strategy has been extended in the case of two FCM variants, which incorporates spatial information (Spatial FCM and Gaussian Kernel-based FCM with spatial bias correction). The high-level requirements that guided the formulation of the proposed parallel implementations are: (i) find appropriate partitioning of large images in order to ensure a balanced load of processors; (ii) use as much as possible the collective computations; (iii) reduce the cost of communications between processors. The parallel implementations were tested through several test cases including multispectral images and images having a large number of pixels. The experiments were conducted on both a computational cluster and a BlueGene/P supercomputer with up to 1024 processors. Generally, good scalability was obtained both with respect to the number of clusters and the number of spectral bands.