Neural network and interval type-2 fuzzy system for stock price forecasting

Stock price forecast has long been received special attention of investors and financial institutions. As stock prices are changeable over time and increasingly uncertain in modern financial markets, their forecasting becomes more important than ever before. A hybrid approach consisting of two components, a neural network and a fuzzy logic system, is proposed in this paper for stock price prediction. The first component of the hybrid, i.e. a feedforward neural network (FFNN), is used to select inputs that are highly relevant to the dependent variables. An interval type-2 fuzzy logic system (IT2 FLS) is employed as the second component of the hybrid forecasting method. The IT2 FLS’s parameters are initialized through deployment of the k-means clustering method and they are adjusted by the genetic algorithm. Experimental results demonstrate the efficiency of the FFNN input selection approach as it reduces the complexity and increase the accuracy of the forecasting models. In addition, IT2 FLS outperforms the widely used type-1 FLS and FFNN models in stock price forecasting. The combination of the FFNN and the IT2 FLS produces dominant forecasting accuracy compared to employing only the IT2 FLSs without the FFNN input selection.

Neural network ensemble : evaluation of aggregation algorithms for electricity demand forecasting

This paper examines and analyzes different aggregation algorithms to improve accuracy of forecasts obtained using neural network (NN) ensembles. These algorithms include equal-weights combination of Best NN models, combination of trimmed forecasts, and Bayesian Model Averaging (BMA). The predictive performance of these algorithms are evaluated using Australian electricity demand data. The output of the aggregation algorithms of NN ensembles are compared with a Naive approach. Mean absolute percentage error is applied as the performance index for assessing the quality of aggregated forecasts. Through comprehensive simulations, it is found that the aggregation algorithms can significantly improve the forecasting accuracies. The BMA algorithm also demonstrates the best performance amongst aggregation algorithms investigated in this study.

Prediction intervals for electricity load forecasting using neural networks

Most of the research in time series is concerned with point forecasting. In this paper we focus on interval forecasting and its application for electricity load prediction. We extend the LUBE method, a neural network-based method for computing prediction intervals. The extended method, called LUBEX, includes an advanced feature selector and an ensemble of neural networks. Its performance is evaluated using Australian electricity load data for one year. The results showed that LUBEX is able to generate high quality prediction intervals, using a very small number of previous lag variables and having acceptable training time requirements. The use of ensemble is shown to be critical for the accuracy of the results.

Analysing building energy use using sub metering and external weather data

The Intergovernmental Panel on Climate Change and the McKinsey Greenhouse Gas abatement studies have highlighted reduction of building energy consumption as a primary cost-effective element in the abatement of Global Warming. Nevertheless, the energy investigation in most of our existing building stock remains at a novice level at best. Building sub-metering, by which we mean any secondary, hourly, metering (after the main) of various circuits, provides substantial information on when and where energy is used in specific buildings. Furthermore, combining this information with external weather data provides information beyond basic metering results. This paper discusses three case studies and explains how sub-metering, augmented by external solar and temperature data, benefits energy management and identified problems. It explains how different methods of analysing energy usage allowed: justifiable sizing of a solar photovoltaic system, with a calculated Cooling Degree Unit, identified the absence of savings from a proprietary chiller controller, and the energy variation due to user schedules and external conditions indicated anomalies in energy use. The advantages of wireless access are noted. Extracting information in graphical formats suggests better strategies to understand and control energy use.

Design with nature : a proposed model for coastal settlements in Australia adapting to climate change and extreme weather events

The Australian coast is rich in history and is scattered with coastal settlements amongst a contrasting landscape with infinite visual and ecological diversity. These attributes provide the opportunity to create sustainable and resilient settlements, linking the wholeness of a place to the foundation of living in harmony with nature. On the contrary the coastal regions of Australia are facing dynamic changes of population growth including the looming impact of a changing climate. Acknowledging these challenges, the Australian Government highlighted that one of the key requirements for a sustainable future is to establish sustainable settlements that are resilient against the impacts of climate change. Recent government studies and reports highlighted various possible impacts to the Australian coast and regional settlements due to sea level rise with associated coastal recession, extreme weather events, flooding, and prolonged heat waves. Various adaptation frameworks are proposed to deal with this issue, but very few consider the relationship between ecological systems and human built environments. The resilience planning of settlements must consider the co-evolution of human and nature under future climate effects. This paper is thus seeking answers to the question: How can the theoretical principles of Design with Nature (McHarg, 1967) and The Nature of Order (Alexander, 1980) provide for input to a adaptation model for settlements along the coast? Reflecting on a literature review of these two well established theories, the author select key principles from both as input to a ecological design based adaptation model for coastal settlements, which establishes a system of unfolding steps to create sustainable communities that connect with the landscape, and are resilient against future impacts of change.

Short-term load and wind power forecasting using neural network-based prediction intervals

Electrical power systems are evolving from today's centralized bulk systems to more decentralized systems. Penetrations of renewable energies, such as wind and solar power, significantly increase the level of uncertainty in power systems. Accurate load forecasting becomes more complex, yet more important for management of power systems. Traditional methods for generating point forecasts of load demands cannot properly handle uncertainties in system operations. To quantify potential uncertainties associated with forecasts, this paper implements a neural network (NN)-based method for the construction of prediction intervals (PIs). A newly introduced method, called lower upper bound estimation (LUBE), is applied and extended to develop PIs using NN models. A new problem formulation is proposed, which translates the primary multiobjective problem into a constrained single-objective problem. Compared with the cost function, this new formulation is closer to the primary problem and has fewer parameters. Particle swarm optimization (PSO) integrated with the mutation operator is used to solve the problem. Electrical demands from Singapore and New South Wales (Australia), as well as wind power generation from Capital Wind Farm, are used to validate the PSO-based LUBE method. Comparative results show that the proposed method can construct higher quality PIs for load and wind power generation forecasts in a short time.