Wei-Zhen Lu

Determination of the spread parameter in the Gaussian kernel for classification and regression

Based on statistical learning theory, Support Vector Machine (SVM) is a novel type of learning machine, and it contains polynomial, neural network and radial basis function (RBF) as special cases. In the RBF case, the Gaussian kernel is commonly used, while the spread parameter σ in the Gaussian kernel is essential to generalization performance of SVMs. In this paper, determination of σ is studied based on discussions of the influence of σ on generalization performance. For classification problems, the optimal σ can be computed on the basis of Fisher discrimination. And for regression problems, based on scale space theory, we demonstrate the existence of a certain range of σ, within which the generalization performance is stable. An appropriate σ within the range can be achieved via dynamic evaluation. In addition, the lower bound of iterating step size of σ is given. Simulation results show the effectiveness of the presented method.

Application of evolutionary neural network method in predicting pollutant levels in downtown area of Hong Kong

Air pollution emerges as an imminent issue in metropolitan cities like Hong Kong, and attracts much attention in recent years. Prediction ofpollutant levels and their tendency is an important topic in environmental science today. To achieve such prediction tasks, the use ofneural network (NN), in particular, the multi-layer perceptron, is regarded as a cost-e7ective technique superior to traditional statistical methods. But the training ofthe multi-layer perceptron, normally f with back-propagation (BP) algorithm or other gradient algorithms, still faces certain drawbacks, e.g., very slow convergence, easily getting stuck in a local minimum, etc. In this paper, a newly developed method, particle swarm optimization (PSO) model, is adopted to train the perceptron and to predict the pollutant levels. As a result, a new neural network model, PSO-based approach, is established and completed. The approach is proved to be feasible and e7ective by applying to some real air-quality problems and by comparing with the simple BP algorithm. c � 2002 Elsevier Science B.V. All rights reserved.

Prediction of maximum daily ozone level using combined neural network and statistical characteristics

Analysis and forecasting of air quality parameters are important topics of atmospheric and environmental research today due to the health impact caused by air pollution. As one of major pollutants, ozone, especially ground level ozone, is responsible for various adverse effects on both human being and foliage. Therefore, prediction of ambient ozone levels in certain environment, especially the ground ozone level in densely urban areas, is of great importance to urban air quality and city image. To date, though several ozone prediction models have been established, there is still a need for more accurate models to develop effective warning strategies. The development of such models is difficult because the meteorological variables and the photochemical reactions involved in ozone formation are very complex. The present work aims to develop an improved neural network model, which combines the adaptive radial basis function (ARBF) network with statistical characteristics of ozone in selected specific areas, and is used to predict the daily maximum ozone concentration level. The improved method is trained and testified by hourly time series data collected at three air pollutant-monitoring stations in Hong Kong during 1999 and 2000. The simulation results demonstrate the effectiveness and the reliability of the proposed method.

Online prediction model based on support vector machine

For time-series forecasting problems, there have been several prediction models to data, but the development of a more accurate model is very difficult because of high non-linear and non-stable relations between input and output data. Almost all the models at hand are not applicable online, although online prediction, especially for air quality parameters forecasting, has very important significance for real-world applications. A support vector machine (SVM), as a novel and powerful machine learning tool, can be used for time-series prediction and has been reported to perform well by some promising results. This paper develops an online SVM model to predict air pollutant levels in an advancing time-series based on the monitored air pollutant database in Hong Kong downtown area. The experimental comparison between the online SVM model and the conventional SVM model (non-online SVM model) demonstrates the effectiveness and efficiency in predicting air quality parameters with different time series.

Modelling and measurement of airflow and aerosol particle distribution in a ventilated two-zone chamber

Abstract A CFD analysis of air movement and aerosol particle deposition and distribution in a ventilated two-zone system with a small interzonal opening is presented. The comparisons of average particle concentrations in both zones between computations and experiments are generally satisfactory and acceptable. It is concluded that particle deposition and migration are mainly influenced by the particle properties, the ventilation conditions and the airflow patterns in the two zones. Small particles have a greater influence on the indoor air quality than do the large particles.

ANALYSIS OF POLLUTANT LEVELS IN CENTRAL HONG KONG APPLYING NEURAL NETWORK METHOD WITH PARTICLE SWARM OPTIMIZATION

Air pollution has emerged as an imminent issue in modernsociety. Prediction of pollutant levels is an importantresearch topic in atmospheric environment today. For fulfillingsuch prediction, the use of neural network (NN), and inparticular the multi-layer perceptrons, has presented to be acost-effective technique superior to traditional statisticalmethods. But their training, usually with back-propagation (BP)algorithm or other gradient algorithms, is often with certaindrawbacks, such as: 1) very slow convergence, and 2) easilygetting stuck in a local minimum. In this paper, a newlydeveloped method, particle swarm optimization (PSO) model, isadopted to train perceptrons, to predict pollutant levels, andas a result, a PSO-based neural network approach is presented. The approach is demonstrated to be feasible and effective bypredicting some real air-quality problems.

A preliminary study on potential of developing shower/laundry wastewater reclamation and reuse system

With the ever-increasing urban population and economic activities, water usage and demand are continuously increasing. Hence, finding/re-creating adequate water supply and fully utilizing wastewater become important issues in sustainable urban development and environmental benign aspect. Considering Hong Kongs situation, e.g., lack of natural fresh water, domination of municipal wastewater, etc., developing wastewater reclamation and reuse system is of specific significance to exploit new water resource and save natural fresh water supplied from Mainland China. We propose and have carried out some preliminary studies on the potential of categorizing municipal wastewater, developing grey and storm water recycling system in public housing estate, investigating the feasibility and potential of using reclaimed grey water, etc. Since there is very limited experience in grey water recycling, such initial studies can help to understand and increase knowledge in utilizing grey water, to foresee the feasibility of developing new water resource, to estimate the cost-effectiveness of reclaiming grey water in metropolitan city.

Ground-level ozone prediction by support vector machine approach with a cost-sensitive classification scheme.

For ground-level ozone (O(3)) prediction, a predictive model, with reliable performance not only on non-polluted days but, more importantly, on polluted days, is favored by public authorities to issue alerts, so that concerned citizens and industrial organizations could take precautions to avoid exposure and reduce harmful emissions. However, the class imbalance problem, i.e., in some collected field data, number of O(3) polluted days are much smaller than that of non-polluted days, will deteriorate the model performance on minority class-O(3) polluted days. Despite support vector machine (SVM) obtaining promising results in air quality prediction, in this study, a cost-sensitive classification scheme is proposed for the standard support vector classification model (S-SVC) in order to investigate whether the class imbalance plagues S-SVC. The S-SVC with such scheme is named as CS-SVC. Experiments on imbalanced data sets collected from two air quality monitoring sites in Hong Kong show that 1) S-SVC is still sensitive to class imbalance problem; 2) compared with S-SVC, CS-SVC effectively avoids class imbalance problem with lower percentage of false negative on O(3) polluted days but with higher percentage of false positive on non-polluted days; 3) compared with both S-SVC and CS-SVC, support vector regression model (SVR), after converting its output to binary one, only has similar performance with S-SVC, which indicates class imbalance problem also impairs the regressor model. From point of protecting public health, CS-SVC, which less likely misses to forecast O(3) polluted days, is recommended here.

NUMERICAL ANALYSIS OF INDOOR AEROSOL PARTICLE DEPOSITION AND DISTRIBUTION IN TWO-ZONE VENTILATION SYSTEM

Abstract A numerical model predicting the air movement and aerosol particle deposition and migration in two interconnected ventilated zones is presented. The airflow patterns and particle distributions in the two-zone ventilated area are presented and analysed. It is concluded that particle deposition and migration are mainly influenced by the particle properties, the ventilation conditions and the airflow patterns in the two zones. Small particles have a greater potential for inhalation by building occupants than do larger particles.

A study of ozone variation trend within area of affecting human health in Hong Kong

As far as the impact of air pollutants on human health being concerned, ozone is one of the main pollutants in atmosphere. In particular, the ground level ozone is responsible for a variety of adverse effects on both human being and plant life. To protect the humankind from such adverse health effects, early information and precautions of high ozone level need to be supplied in times. In this study, statistical characteristics of ground level ozone is analyzed according to the field monitoring data in mixed residential, commercial and industrial areas, e.g., Tsuen Wan area in Hong Kong. The study deals with the characteristics of hourly and daily mean ozone levels under different climatic conditions such as temperature, solar radiation, wind speed, and other pollutant concentration levels. The study aims to investigate the importance of meteorological factors and their impact on relevant pollutant concentration levels from chemical aspect. Further, reasons causing the spatial and temporal variations of ozone levels are discussed. All these results will provide a physical basis for accurately predicting ozone concentration in extensive, future research.