Lilly Suriani Affendey

Intrusion detection using data mining techniques

As the network dramatically extended, security considered as major issue in networks. Internet attacks are increasing, and there have been various attack methods, consequently. Intrusion detection systems have been used along with the data mining techniques to detect intrusions. In this work we aim to use data mining techniques including classification tree and support vector machines for intrusion detection. As results indicate, C4.5 algorithm is better than SVM in detecting network intrusions and false alarm rate in KDD CUP 99 dataset.

An integrated semantic-based approach in concept based video retrieval

Multimedia content has been growing quickly and video retrieval is regarded as one of the most famous issues in multimedia research. In order to retrieve a desirable video, users express their needs in terms of queries. Queries can be on object, motion, texture, color, audio, etc. Low-level representations of video are different from the higher level concepts which a user associates with video. Therefore, query based on semantics is more realistic and tangible for end user. Comprehending the semantics of query has opened a new insight in video retrieval and bridging the semantic gap. However, the problem is that the video needs to be manually annotated in order to support queries expressed in terms of semantic concepts. Annotating semantic concepts which appear in video shots is a challenging and time-consuming task. Moreover, it is not possible to provide annotation for every concept in the real world. In this study, an integrated semantic-based approach for similarity computation is proposed with respect to enhance the retrieval effectiveness in concept-based video retrieval. The proposed method is based on the integration of knowledge-based and corpus-based semantic word similarity measures in order to retrieve video shots for concepts whose annotations are not available for the system. The TRECVID 2005 dataset is used for evaluation purpose, and the results of applying proposed method are then compared against the individual knowledge-based and corpus-based semantic word similarity measures which were utilized in previous studies in the same domain. The superiority of integrated similarity method is shown and evaluated in terms of Mean Average Precision (MAP).

Instance based Matching using Regular Expression

Instance based matching is the process of comparing data from different heterogeneous data sources in determining the correspondence of schema elements. It is a useful alternative choice when schema information (element name, description, constraint) is unavailable or unable to determine the match between schema elements. Instance based matching is a non trivial problem and is applied in many application areas such as data integration, data cleaning, query mediations, and warehousing. Many instance based solutions to the schema matching problem have been proposed and most of them utilized similarity metrics. In this paper, we present a fully automatic approach that contributes to the solution of instance based matching in identifying the correspondences of attributes which is one of the elements in the schema by utilizing regular expression. Several experiments using real-world data set have been conducted to evaluate the performance of our proposed approach. The results showed that our proposed approach achieved better accuracy compared to previous approaches using similarity metrics.

3-L Model: A Model for Checking the Integrity Constraints of Mobile Databases

In this paper we propose a model for checking integrity constraints of mobile databases called Three-Level (3-L) model, wherein the process of constraint checking to maintain the consistent state of mobile databases is realized at three different levels. Sufficient and complete tests proposed in the previous works together with the idea of caching relevant data items for checking the integrity constraints are adopted. This has improved the checking mechanism by preventing delays during the process of checking constraints and performing the update. Also, the 3-L model reduces the amount of data accessed given that much of the tasks are performed at the mobile host, and hence speeds up the checking process.

A study on surveillance video abstraction techniques

The goal of surveillance video abstraction is to generate a video abstract that includes important events and object by eliminating the redundant frames, lacking from activity in original video. Although many research and progresses have been done in video abstraction, the developed approaches either fail to accurately and effectively cover the overall visual content of video or they are computationally expensive in term of time or process. In this paper, firstly we critically review the applicable video abstraction techniques in surveillance domain based on our hierarchical classification, and then briefly introduce a new approach for generating a static surveillance video abstraction, which mitigate the drawbacks of reviewed approaches.

Effective mining on large databases for intrusion detection

Data mining is a common automated way of generating normal patterns for intrusion detection systems. In this work a large dataset is customized to be suitable for both sequence mining and association rule learning. These two different mining methods are then tested and compared to find out which one produces more accurate valid patterns for the intrusion detection system.Results show that higher detection rate is achieved when using apriori algorithm on the proposed dataset. The main contribution of this work is the evaluation of the association rule learning that can be used for further studies in the field of database intrusion detection systems.

Data quality comparative model for data warehouse

The growth of daily data and complexity in data warehouse with enhanced the information technology has created new challenges for information user. The demand for quality data has increase an awareness of the quality, reliable and accuracy of information in making fast and reliable decision-making. Nowadays, many organizations are depending on their resources in data warehouse. As that matter of fact, the qualities of data warehouse are greatly concern. The poor and error data will cause more trouble in data warehouse as data accessed from the same resources by the user. Here we present the systematic review comparative model to determine the data quality model as further research in our studies.

Mobile Plant Tagging System for Urban Forest Eco-Tourism Using QR Code

The transformation of mobile devices from being a communication devices to be important information resources has changed the way of how activities being implemented including in tourism industry. This is very important for the tourists especially when they visit remote location such as forests. For these tourists, information regarding plants is very important to them and most of the time the tour guides or books will be their source of references. The traditional way of forest tourism lacks the facility for these tourists to obtain information regarding the plants. This paper proposes a system that uses QR codes as tag for tagging the plants that can be scanned by tourists to get further information of the plants. Through this system the visitors only need to use their mobile devices to scan on the plant tag to get its information on their devices. The QR codes used representing the plant ID. Based on these QR codes, the application will query a remote database and retrieved the information of the scanned plant and will be displayed in the visitors mobile devices. Using this system, tourists can get accurate information regarding the plants in the forest through their devices. Also, through this system, they can get information during their visit in the forest quickly without having to depend on tour guides or reference books.

Conceptual Database Design for Smart Medical Clinical System

Hospitals are known for having separate information systems across various departments, which are usually heterogeneous in nature. Medical experts could benefit greatly from the integration of these islands, but the heterogeneity of the sources/databases often impedes this. Most cardiothoracic units use isolated heterogeneous systems to keep patients records as well as to support the experts when deciding for cardiothoracic surgery. These include patients information system, lab results for x-ray, angiography, echocardiogram, blood etc. All these information are stored in heterogeneous systems and as such, a user would have to log-in and log-out from one system to another, to monitor/trace a patients medical record. As the solution, we proposed a clinical database system in which the system incorporates the overall patients management, from ward admission through Operation Theatre, Coronary Intensive Care Unit (CICU), recovery and discharge in which is divided into several modules. The purpose of this paper is to presents the conceptual database design for the Smart Medical Clinical System which include features that could alert the healthcare personnel regarding any abnormal trend in the data, so that medical experts need not have to repeat the same investigations.

Analyzing Integrity Tests for Data Caching in Mobile Databases

In a mobile environment, due to the various constraints inherited from limitations of wireless communication and mobile devices, checking for integrity constraints to maintain the consistent state of mobile databases is an important issue that needs to be addressed. Hence, in this paper we propose a strategy for caching relevant data items needed during the process of checking integrity constraints of mobile databases. This is achieved by analyzing the relationships among the integrity tests (simplified form of integrity constraints) to be evaluated for a given update operation. Our strategy improves the checking mechanism by not only preventing delays during the process of checking constraints and performing the update but also by minimizing the amount of data items to be cached. Hence, our strategy speeds up the checking process.