Flood Forecasting for Klang River at Kuala Lumpur using Artificial Neural Networks

Jer Lang Hong,KeeAn Hong 보안공학연구지원센터 2016 International Journal of Hybrid Information Techno Vol.9 No.3

This study evaluates the use of Multi-Layer Perceptron (MLP) neural network models to forecast water levels of a gauging station located at the Kuala Lumpur city centre in Malaysia using records of upstream multiple stations. Cross correlation analysis of water level data was performed to determine the input vectors which include the current and antecedent water level data of the upstream stations to ensure that of the data available, the most influential values corresponding to different lags are selected for analysis. Twelve well recorded storm events were used to train, test and validate the MLP models. The best performance based on MSE, MAE and R² was achieved with a model of 15 input vectors of upstream current and antecedent water levels, 7 hidden nodes and an output vector for the station at Kuala Lumpur centre. The R² values for training, testing and validation datasets are 0.81,0.85 and 0.85 respectively.

Flow Forecasting For Selangor River Using Artificial Neural Network Models to Improve Reservoir Operation Efficiency

Jer Lang Hong,Kee An Hong 보안공학연구지원센터 2016 International Journal of Hybrid Information Techno Vol.9 No.7

Selangor is an important river basin in adjacent to the city of Kuala Lumpur, the federal capital of Malaysia and it supplies about 70% of the water required for domestic and industrial use for the city. Selangor river basin is presently regulated by two water supply dams, namely the Tinggi dam and the Selangor dam. Water is abstracted at an intake located 21 and 42 km downstream of the Tinggi and Selangor dam respectively. In the wet season, when unregulated flows downstream of the dams are sufficient for abstraction, no releases from the dams are required. However, releases are required in the dry season when flows downstream fall below the normal level. The present practice in dam operation is to use recession analysis in low flow forecasting during prolonged dry periods. Recession constants were derived using stream flow data and future flows were forecasted using the current flow and the recession constants assuming that there is no rain for the coming period where forecasts were made. Decisions were then made for releases from the dams. The disadvantage of recession analysis in forecasting low flow is that the forecast is not accurate if rain falls during the period and over release will occur. This study reports the use of Artificial Neural Network (ANN) models to forecast one and two time steps ahead river flows at the Rantau Panjang gauging station near the water supply intake for different travel times from the dams to the intake point to help in determining the regulating releases from the dams for more efficient reservoir operation. Two different ANN models, the Multi -Layer Perceptron (MLP) and the General Regression Neural Network (GRNN), were developed and their performances were compared. Endogenous and exogenous input variables such as stream flow and rainfall with various lags were used and compared for their ability to make future flow predictions. The input variables required are decided considering statistical properties of the recorded rainfall and flow such as cross-correlation between flow and rainfall, auto and partial autocorrelation of the flows which are best in representing the catchment response. Results show that both methods perform well in terms of R² but GRNN models generally give lower RME and MAE values indicating their superiority compared to MLP models.

WordNet in Malay Language

Jer Lang Hong 보안공학연구지원센터 2016 International Journal of Database Theory and Appli Vol.9 No.6

World Wide Web contains huge amount of data available in different languages across the world. Web browsers are tools used to display the data in graphical forms. With the evolution of Web 3.0, data has become an important part of human daily tasks, where it is used to process information, and formulate important decision rules for many organizations. Current tools used to conceptualize data are catered for some of the world well known languages such as English. However, these tools may not be able to support other languages as there are a wide range of languages with different syntax and representation. In this paper, we present a novel lexical semantic based database tool called MalayWordNet, specifically written for Malay language. Our tool is helpful for high end semantic based applications which use Malay language as part of their data presentation.

Automated Data Extraction with Multiple Ontologies

Jer Lang Hong 보안공학연구지원센터 2016 International Journal of Grid and Distributed Comp Vol.9 No.6

Current search engines require an accurate yet fast automated extractor to extract relevant information from deep web for the users. Human users usually enter search queries and the search engines will then locate the desire information of interest by disambiguate the search query accordingly. The queries will then be passed on to multiple search engines for further processing. These search engines will then return the search results to the main search engine. However, data returned from these search engines are usually varied and presented in numerous formats and layouts. To extract them, we need automated extractor to filter out irrelevant information and locate the correct information. Current trends focused on using ontologies to automatically extract this information with high accuracy. To the best of our knowledge, no works have been made on using multiple ontologies (using many ontology techniques) to automatically extract information from deep webs. In this paper, we demonstrate that multiple ontologies technique can achieve higher accuracy when extracting data from the deep web. Our method outperforms existing state of the art systems and is able to robustly extract data from deep web.

Regional Drought Rainfall for Selangor River Basin in Malaysia Estimated Using L-Moments

Jer Lang Hong,Kee An Hong 보안공학연구지원센터 2016 International Journal of Hybrid Information Techno Vol.9 No.6

Water from the Selangor river basin is the main source of supply for the federal capital of Kuala Lumpur and the various districts of Selangor State located in the centre of Peninsular Malaysia since 2000. As this region is the most populated area in the country, its rapid economic development and population growth have caused concern over the adequacy of the quantity and quality of water abstracted from the Selangor basin, both at present and in the future. A recent prolonged drought has caused a one-month water rationing in the Kuala Lumpur and adjacent areas which basically has seriously affected the everyday life of the people and the industrial and agricultural sectors. A rainfall drought analysis is therefore required for assessing the severity of the drought events in the study area. In this study, L-moments have been used to compute the rainfall quantile values for 9 probabilities, 6 durations, 12 starting months for the 2 regions across the Selangor basin. The choice of the Pearson Type III and Wakeby distributions for fitting the Selangor rainfall data is presented. Quantile values are expressed as a percentage of mean rainfall of the particular duration and presented as drought indication maps. Rainfall of specific return period can be calculated easily using these maps and the mean rainfall for the particular station. The return period (severity) of a historical rainfall event from the station can be known when the magnitude of the historical event is compared with that of the rainfall event of a particular return period. This helps in monitoring and management of droughts.

Search Ranking Utilizing User’s Opinion

Jun Jin Choong,Jer Lang Hong 보안공학연구지원센터 2016 International Journal of Database Theory and Appli Vol.9 No.7

The Internet is one of the most widely available services in the world today. With the Internet, people are now looking for reviews on the Internet; more specifically, the social networking services. Within the social network medium, we can identify a suitable service that describes more about a person’s personality as the subject. The growth of social networking popularity has contributed to the in-crease in information available on social networking services. The flexibility of these services allows writing individual thoughts without restrictions. With the vast information available on social networking sites today, how is it possible to look all of these opinions? How do we know which opinion holds truth? How do we know if someone is not bias based on his writing? Hence, it is seen necessary to filter opinions. In this paper we look at the possibility of using search ranking as a medium of filter opinions by exploring opinion mining methods, social net-working candidates and search ranking methods. With existing sentiment analysis techniques, we can obtain opinions that are then ranked against a set of key-words.

Automatic Social Media Data Extraction

Estelle Xin Ying Kee,Jer Lang Hong 보안공학연구지원센터 2016 International Journal of Database Theory and Appli Vol.9 No.8

Opinions, the key influencer of human behavior and activity is ranked as of one of the strong factors that determine the effectiveness of one’s strategy and approach in terms of influential power and trend setting capabilities. This highlights the importance of sentiment analysis done upon the extracted data. Today, statistics have shown significantly that most opinions can be obtained via many social media platforms. Social media has provided a convenient platform for web users to comfortably share their thoughts and to boldly voice up. Having to process such huge amount of data, it is proposed that automated sentiment analysis is done when extracting social media data. Using an effective algorithm which produces meaningful information from raw data, the possibilities of venturing deeper into areas like decision making and influential thinking are simply limitless.

Mobile Security and its Application

Jun Hou Chan,Jer Lang Hong 보안공학연구지원센터 2016 International Journal of Security and Its Applicat Vol.10 No.10

Ownership of a smartphone has never been easier nowadays, and it is supported by the fact that most of the people around us have a smartphone or an equivalent smart device. What is smartphone and why is it a smart? A smartphone by definition is as the name suggests, it is a phone is smart enough to not only be limited to the features and capabilities of a traditional cellular phone but also perform what a “smart” device can. And in recent years, the device that is deemed as the most intelligent device is the computer as it is the most advance piece of technology that is commercially available to the general public. Why this is so, is because in our opinion it has revolutionized how most if not all of the societies of today work. Hence what makes a smartphone is the mobile operating system that it is built upon, which is similar to a computer. It is becoming more and more of a common sight nowadays and this is because they are being offered at a price where more people are able to afford, hence they are reaching the hands of ceiling of the lower income families, all the way up to the higher income families. Back then, pure play devices were mostly simple in terms of how it function and works, hence if possible, we could suggest that the security aspect was never or rather has never been an issue other than the alteration of data after operation such as the tape of video recorders or images captured but never in the process, in the sense that there were no interruptions during operation, most likely is because it was clear and visible, but nowadays when you combine all of those devices into a complex entity, we tend to leave a hole in the cloth somewhere that we did not or rather can’t see due to the overwhelming amount of other things that we have. In this paper we discuss the current state of the commercially available operating systems of the two biggest names in smart devices, namely iOS and Android; and measure how secure and/or vulnerable (susceptible) are they to malwares and the nature of the mobile ad hoc network. We first analyze the integrity of the core of a smart device, the operating system and then use it to evaluate the effectiveness of their techniques and defenses of preventing and identifying malwares.

Data Cleaning Utilizing Ontology Tool

Jing Ting Wong,Jer Lang Hong 보안공학연구지원센터 2016 International Journal of Grid and Distributed Comp Vol.9 No.7

Recent advancement in Internet Technologies has made web browsing increasingly easy and user friendly. From the traditional method of desktop web browsing and the birth of dial up modem connection, users nowadays are able to enjoy a fast and reliable web browsing via high speed wireless Internet connection and portable mobile devices. Browsing a web has become much easier with the state of the art search engines such as Google, which provide much functionalities which could make browsing easier such as improved crawler, easy to use search interface, web personlization, Web 3.0 support and integration and many more. In order to build a robust and reliable search engine, the developer needs to integrate all the data and present them in a meaningful format for user’s viewing convenience. Integrating these data is a tedious task as data usually occur in numerous format, and layout. Furthermore, web developers usually present the data content in various languages of their choice, which made the processing of these data increasingly difficult. There is also no standard convention to represent the data format and even a standardize rule to process this data has not been developed. To resolve this issue, researchers develop data extractor which could effectively extract data from web sources, tabulate them, and used it for further processing. However, not all data are correctly extracted, they may either missed certain valuable information or contain additional unnecessary information. In the case of unnecessary information, researchers use a cleaning method to remove them such that the data extracted are free of errors. Removing these data is important as unnecessary information may affect the accuracy of subsequent extractor tools, hence may eventually prevent the tool from performing its task efficiently. In this research proposal, we embark on a data cleaning tool to clean data using ontology tools. Experimental results show that our tool is highly efficient in data cleaning and is able to outperform existing state of the art tools.