• The Journal of the Korea Contents Association
• /
• v.18 no.1
• /
• pp.465-475
• /
• 2018

Recently, as the use of social media and IoT has increased, large graph streams has been generating and studies on real-time processing for them have been actively carrying out. In this paper we propose a incremental graph stream processing scheme that reuses previous result data when the graph changes continuously. We also propose a cost model to selectively perform incremental processing and static processing. The proposed cost model computes the predicted value of the detection cost and the processing cost of the recalculation area based on the actually processed history and performs the incremental processing when the incremental processing is more profit than the static processing. The proposed incremental processing increases the efficiency by processing only the part that changes when the graph update occurs. Also, by collecting only the previous result data of the changed part and performing the incremental processing, the disk I/O costs are reduced. It is shown through various performance evaluations that the proposed scheme outperforms the existing schemes.

• Journal of KIISE
• /
• v.45 no.1
• /
• pp.69-75
• /
• 2018

In the streaming data where data samples arrive sequentially in time, it is difficult to apply the dimension reduction method based on batch learning. Therefore an incremental dimension reduction method for the application to streaming data has been studied. In this paper, we propose an incremental linear discriminant analysis method using the least squared error solution. Instead of computing scatter matrices directly, the proposed method incrementally updates the projective direction for dimension reduction by using the information of a new incoming sample. The experimental results demonstrate that the proposed method is more efficient compared with previously proposed incremental dimension reduction methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.10
• /
• pp.3378-3393
• /
• 2014

We have witnessed the rapid development of information technology in recent years. One of the key phenomena is the fast, near-exponential increase of data. Consequently, most of the traditional data classification methods fail to meet the dynamic and real-time demands of today's data processing and analyzing needs--especially for continuous data streams. This paper proposes an improved incremental learning algorithm for a large-scale data stream, which is based on SVM (Support Vector Machine) and is named DS-IILS. The DS-IILS takes the load condition of the entire system and the node performance into consideration to improve efficiency. The threshold of the distance to the optimal separating hyperplane is given in the DS-IILS algorithm. The samples of the history sample set and the incremental sample set that are within the scope of the threshold are all reserved. These reserved samples are treated as the training sample set. To design a more accurate classifier, the effects of the data volumes of the history sample set and the incremental sample set are handled by weighted processing. Finally, the algorithm is implemented in a cloud computing system and is applied to study user behaviors. The results of the experiment are provided and compared with other incremental learning algorithms. The results show that the DS-IILS can improve training efficiency and guarantee relatively high classification accuracy at the same time, which is consistent with the theoretical analysis.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.301-304
• /
• 2014

비정형 게임 Big Data에서 고효율 정보를 추출하고, 신뢰 할 수 있는 클러스터 게임서버 환경을 위한 병렬 처리를 위해 MapReduce를 사용한다. 본 논문에서는 빈번하게 입력되는 신규 게임데이터 처리를 위해 함수 Demap을 사용하는 Incremental MapReduce를 적용하여 불필요한 중간 값 저장과 재계산 없이 점차적으로 MapReduce 함수를 실행한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.07a
• /
• pp.135-137
• /
• 2012

A existing recommedation system using association rules has the problem, which is suffered from inefficiency by reprocessing of the data which have already been processed in the incremental data environment in which new data are added persistently. We propose the recommendation technique using incremental frequent pattern mining based on RFM in e-commerce. The proposed can extract frequent items and create association rules using frequent patterns mining rapidly when new data are added persistently.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.32 no.2
• /
• pp.147-157
• /
• 2009

This paper is to test the modulating effect of organizational culture on the relationship between personality and incremental innovation, and study of the relationship between incremental innovation and service Quality in service industry. Based on 507 data gathered in service companies in Korea, analysis results and showed that procedural, interactional, and innovative culture have affirmative relation with incremental innovation. Therefore innovative culture appeared to have some modulating effect on the relationship between personality and incremental innovation. And ana-lysis results of relationship between incremental innovation and service quality are followed; service innovation and process innovations showed positive effects except some operation innovations.

• Journal of KIISE
• /
• v.43 no.12
• /
• pp.1396-1403
• /
• 2016

In streaming data analysis where underlying data distribution may be changed or the concept of interest can drift with the progress of time, the ability to adapt to concept drift can be very powerful especially in the process of incremental learning. In this paper, we develop a general framework for an adaptive incremental classifier on data stream with concept drift. A distribution, representing the performance pattern of a classifier, is constructed by utilizing the distance between the confidence score of a classifier and a class indicator vector. A hypothesis test is then performed for concept drift detection. Based on the estimated p-value, the weight of outdated data is set automatically in updating the classifier. We apply our proposed method for two types of linear discriminant classifiers. The experimental results on streaming data with concept drift demonstrate that the proposed adaptive incremental learning method improves the prediction accuracy of an incremental classifier highly.

• Journal of KIISE:Databases
• /
• v.34 no.4
• /
• pp.343-356
• /
• 2007

Due to advances in position monitoring technologies such as global positioning systems and sensor networks, recent position information of moving objects has the form of streaming data which are updated continuously and rapidly. In this paper we propose an efficient trajectory maintenance method that stores the streaming position data of moving objects in the limited size of storage space and estimates past positions based on the stored data. For this, we first propose a new concept of incremental extraction of position information. The incremental extraction means that, whenever a new position is added into the system, we incrementally re-compute the new version of past position data maintained in the system using the current version of past position data and the newly added position. Next, based on the incremental extraction, we present an overall framework that stores position information and estimates past positions in the stream environment. We then propose two polynomial-based methods, line-based and curve-based methods, as the method of estimating the past positions on the framework. We also propose three incremental extraction methods: equi-width, slope-based, and recent-emphasis extraction methods. Experimental results show that the proposed incremental extraction provides the relatively high accuracy (error rate is less than 3%) even though we maintain only a little portion (only 0.1%) of past position information. In particular, the curve-based incremental extraction provides very low error rate of 1.5% even storing 0.1% of total position data. These results indicate that our incremental extraction methods provide an efficient framework for storing the position information of moving objects and estimating the past positions in the stream environment.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.5
• /
• pp.576-581
• /
• 2003

Speech signal has the features of speakers. In this paper, we propose the speaker identification system which use the incremental learning based on neural network. Recorded speech signal through the Mic is passed the end detection and is divided voiced signal and unvoiced signal. The extracted 12 order cpestrum are used the input data for neural network. Incremental learning is the learning algorithm that the learned weights are remembered and only the new weights, that is created as adding new speaker, are trained. The architecture of neural network is extended with the number of speakers. So, this system can learn without the restricted number of speakers.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.716-718
• /
• 2004

The false alarm data in intrusion detection systems are divided into false positive and false negative. The false positive makes bad effects on the performance of intrusion detection system. And the false negative makes bad effects on the efficiency of intrusion detection system. Recently, the most of works have been studied the data mining technique for analysis of alert data. However, the false alarm data not only increase data volume but also change patterns of alert data along the time line. Therefore, we need a tool that can analyze patterns that change characteristics when we look for new patterns. In this paper, we focus on the false positives and present a framework for analysis of false alarm pattern from the alert data. In this work, we also apply incremental data mining techniques to analyze patterns of false alarms among alert data that are incremental over the time. Finally, we achieved flexibility by using dynamic support threshold, because the volume of alert data as well as included false alarms increases irregular.