Lokman Hakim Ismail

Jordan Pi-Sigma Neural Network for Temperature Prediction

This study examines and analyses the use of a new recurrent neural network model: Jordan Pi-Sigma Network (JPSN) as a forecasting tool. JPSN’s ability to predict future trends of temperature was tested and compared to that of Multilayer Perceptron (MLP) and the standard Pi-Sigma Neural Network (PSNN); trained with the standard gradient descent algorithm. A set of historical temperature measurement for five years from Malaysian Meteorological Department was used as input data to train the networks for the next-day prediction. Simulation results show that JPSN forecast comparatively superior to MLP and PSNN models, with lower prediction error, thus revealing a great potential in predicting the temperature measurement.

An Application of Jordan Pi-Sigma Neural Network for the Prediction of Temperature Time Series Signal

Temperature forecasting is mainly issued in qualitative terms with the use of conventional methods, assisted by the data projected images taken by meteorological satellites to assess future trends (Paras et al., 2007). Several criteria that need to be considered when choosing a forecasting method include the accuracy, the cost and the properties of the series being forecast. Considering those criteria, it is noted that such empirical approaches that has been conducted for temperature forecasting is intrinsically costlier and only proficient of providing certain information, which is usually generalized over a larger geographical area (Paras et al., 2007). Despite of involving sophisticated mathematical models to justify the use of empirical rules, it also requires a prior knowledge of the characteristics of the input time-series to predict future events. Not only that, most temperature forecasts today have limited information about uncertainty. Yet, meteorologists often find it challenging to communicate uncertainty effectively. Regardless of the extensive use of the numerical weather method, they are still restricted by the availability of numerical weather prediction products, leading to various studies being conducted for temperature forecasting (Barry & Chorley, 1982; Paras et al., 2007)

A Jordan Pi-Sigma Neural Network for Temperature Forecasting in Batu Pahat Region

This paper disposes towards an idea to develop a new network model called a Jordan Pi Sigma Neural Network (JPSN) to overcome the drawbacks of ordinary Multilayer Perceptron (MLP) whilst taking the advantages of Pi-Sigma Neural Network (PSNN). JPSN, a network model with a single layer of tuneable weights with a recurrent term added in the network, is trained using the standard backpropagation algorithm. The network was used to learn a set of historical temperature data of Batu Pahat region for five years (2005-2009), obtained from Malaysian Meteorological Department (MMD). JPSN’s ability to predict the future trends of temperature was tested and compared to that of MLP and the standard PSNN. Simulation results proved that JPSN’s forecast comparatively superior to MLP and PSNN models, with the combination of learning rate 0.1, momentum 0.2 and network architecture 4-2-1 andlower prediction error. Thus, revealing a great potential for JPSN as an alternative mechanism to both PSNN and MLP in predicting the temperature measurement for one-step-ahead.

The performance of a Recurrent HONN for temperature time series prediction

This paper presents a novel application of Recurrent HONN to forecast the future index of temperature time series data. The prediction capability of Recurrent HONN, namely the Recurrent Pi-Sigma Neural Network was tested on a five-year temperature data taken from Batu Pahat, Malaysia. The performance of the network is benchmarked against the performance of Multilayer Perceptron, and the standard Pi-Sigma Neural Network. The predictions demonstrated that Recurrent Pi-Sigma Neural Network is capable in predicting the future index of temperature series in comparison to other models. It is observed that the network is able to find an appropriate input output mapping of the chaotic temperature signals with a good performance in learning speed and generalization capability.

Implementation of Modified Cuckoo Search Algorithm on Functional Link Neural Network for Climate Change Prediction via Temperature and Ozone Data

The effect of climate change presents a huge impact on the development of a country. Furthermore, it is one of the causes in determining planning activities for the advancement of a country. Also, this change will have an adverse effect on the environment such as flooding, drought, acid rain and extreme temperature changes. To be able to avert these dangerous and hazardous developments, early predictions regarding changes in temperature and ozone is of utmost importance. Thus, neural network algorithm namely the Multilayer Perceptron (MLP) which applies Back Propagation algorithm (BP) as their supervised learning method, was adopted for use based on its success in predicting various meteorological jobs. Nevertheless, the convergence velocity still faces problem of multi layering of the network architecture. As consequence, this paper proposed a Functional Link Neural Network (FLNN) model which only has a single layer of tunable weight trained with the Modified Cuckoo Search algorithm (MCS) and it is called FLNN-MCS. The FLNN-MCS is used to predict the daily temperatures and ozone. Comprehensive simulation results have been compared with standard MLP and FLNN trained with the BP. Based on the extensive output, FLNN-MCS was proven to be effective compared to other network models by reducing prediction error and fast convergence rate.

Pi-Sigma Neural Network for Temperature Forecasting in Batu Pahat

In this study, two artificial neural network (ANN) models, a Pi-Sigma Neural Network (PSNN) and a three-layer multilayer perceptron (MLP), are applied for temperature forecasting. PSNN is use to overcome the limitation of widely used MLP, which can easily get stuck into local minima and prone to overfitting. Therefore, good generalisation may not be obtained. The models were trained with backpropagation algorithm on historical temperature data of Batu Pahat region. Through 810 experiments, we found that PSNN performs considerably better results compared to MLP for daily temperature forecasting and can be suitably adapted to forecasts a particular region using the historical data over larger geographical areas.

Implementation of Modified Cuckoo Search Algorithm on Functional Link Neural Network for Temperature and Relative Humidity Prediction

The impact of temperature and relative humidity changes bringing a sharp warming climate. These changes can cause extreme consequences such as floods, hurricanes, heat waves and droughts. Therefore, prediction of temperature and relative humidity is an important factor to measure environmental changes. Neural network, especially the Multilayer Perceptron (MLP) which uses Back Propagation algorithm (BP) as a supervised learning method, has been successfully applied in various problem for meteorological prediction tasks. However, this architecture still facing problem where the convergence rate is very low due to the multilayering topology of the network. Thus, this study proposes an implementation of Functional Link Neural Network (FLNN) which composes of a single layer of tunable weight trained with the Modified Cuckoo Search algorithm (MCS). The FLNN is used to predict the daily temperatures and relative humidity of Batu Pahat region. Extensive simulation results have been compared with standard MLP trained with the BP, and FLNN with that of BP. Promising results have shown that FLNN when trained with the MCS has successfully outperformed other network models with reduced prediction error and fast convergence rate.

Potential Of Light Pipes System In Malaysian Climate

Light-pipes system are simple structures that allow the transmission of daylight from the outside to the inside of a room. It is a practical application in many buildings where daylight cannot reach due to building design and limited facade to placing windows. Since roof is the element directly exposed to the sunlight, light pipes system could be introduced. This paper examines the illumination levels obtained using light pipes system under Malaysia climate conditions. A light-pipe system that was installed in a test room located in Batu Pahat. Indoor illuminance distributions and concurrent outdoor illuminance were monitored at a 30 minutes interval for 5 days. The results indicated that the amount of daylight penetrated into the building are varied with less than 150lux in the early morning and late evening, and maximum at over 350lux in the noon and early afternoon. The average internal illuminance levels offer by light pipe system met the MS 1525:2007 recommendation for application in Malaysian buildings. These findings indicated that the light pipe system has a potential as a tool for introducing daylight indoors in Malaysia.

PI-SIGMA NEURAL NETWORK FOR A ONE-STEP-AHEAD TEMPERATURE FORECASTING

The main purpose of this study is to employ Pi-Sigma Neural Network (PSNN) for one-step-ahead temperature forecasting. In this paper, we evaluate the performances of PSNN by comparing the network model with widely used Multilayer Perceptron (MLP). PSNN which is a class of Higher Order Neural Networks (HONN), has a highly regular structure, needs much smaller number of weights and less training time. The PSNN is use to overcome the drawbacks of MLP, which can easily trapped into local minima and prone to overfit. Both network models were trained with standard backpropagation algorithm. Through 1012 experiments, it has been demonstrated that the PSNN has a high practicability and better temperature forecasting for one-step-ahead using historical temperature data of Batu Pahat region.

THE EFFECT OF NETWORK PARAMETERS ON PI-SIGMA NEURAL NETWORK FOR TEMPERATURE FORECASTING

In this paper, we present the effect of network parameters to forecast temperature of a suburban area in Batu Pahat, Johor. The common ways of predicting the temperature using Neural Network has been applied for most meteorological parameters. However, researchers frequently neglected the network parameters which might affect the Neural Networks performance. Therefore, this study tends to explore the effect of network parameters by using Pi Sigma Neural Network (PSNN) with backpropagation algorithm. The networks performance is evaluated using the historical dataset of temperature in Batu Pahat for one step-ahead and benchmarked against Multilayer Perceptron (MLP) for comparison. We found out that, network parameters have significantly affected the performance of PSNN for temperature forecasting. Towards the end of this paper, we concluded the best forecasting model to predict the temperature based on the comparison of our study.