• Journal of the Korean Data and Information Science Society
• /
• v.22 no.5
• /
• pp.877-884
• /
• 2011

The decision tree is a representative algorithm of data mining and used in many domains such as retail target marketing, fraud detection, data reduction, variable screening, category merging, etc. This method is most useful in classification problems, and to make predictions for a target group after dividing it into several small groups. When we create a model of decision tree with a large number of input variables, we suffer difficulties in exploration and analysis of the model because of complex trees. And we can often find some association exist between input variables by external variables despite of no intrinsic association. In this paper, we study on the removal method of unnecessary input variables using multiple external association rules. And then we apply the removal method to actual data for its efficiencies.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.8A
• /
• pp.633-639
• /
• 2009

For operation of IEEE 802.22 WRAN system, spectrum sensing is a essential function. However, due to strict sensing requirement of WRAN system, spectrum sensing process of CR nodes require long quiet period. In addition, CR nodes sometimes fail to detect licensed users due to shadowing effect of wireless communication environment. To overcome this problem, CR nodes collaborate with each other for increasing the sensing reliability or mitigating the sensitivity requirement. A general approach for decision fusion, the "k out of N" rule is often taken as the decision fusion rule for its simplicity. However, since k out of N rules can not achieve better performance than the highest SNR node when SNR is largely different among CR nodes, the local SNR of each node should be considered to achieve better performance. In this paper, we propose two novel data fusion methods by utilizing confidence vector which represents the confidence level of individual sensing result. The simulation results show that the proposed schemes improve the signal detection performance than the conventional data fusion algorithms.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.3
• /
• pp.199-208
• /
• 2014

At present, the effect of oriental treatment system is proved in the west and using the data of tongue and pulse of body, the doctor can decide the patient's body state without Xray and CT data of large machines. In this paper, the patient's medical data is transmitted to the doctor and the real time decision algorithm is developed and so the doctor can decide the medical treatments. Using the mobile phone, the pulse data and bio data can be sent to the doctor and therefore the patients, who can't care in real time, can be treated in real time in the impossible medical treatment areas. Therefore in this paper, the oriental medical treatment system algorithm and artificial intelligence electrical needle simulation are processed for real time and checked and treated, so anyone can decide patient's state using mobile phone.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39B no.6
• /
• pp.379-386
• /
• 2014

Recently, middleboxes play a key role in many network settings such as firewalls, VPN gateways, proxies, intrusion detection and prevention systems, and WAN optimizers. However, achieving the performance and security benefits that middleboxes offer is highly complex, and therefore it is essential to manage middleboxes efficiently and dynamically. In this respect, Software-Defined Networking (SDN) offers a promising solution for middlebox policy enforcement by using logically centralized management, decoupling the data and control planes, and providing the ability to programmatically configure forwarding rules. Also, cloud computing and distributed Network Function Virtualization (NFV) can enable to manage middleboxes more easily. We introduce SDN-based middlebox management framework in integrated wired and wireless networks and discuss the further issues.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.7 s.349
• /
• pp.84-92
• /
• 2006

To defeat abnormal traffic driven by DoS (Denial-of-Service) or DDoS (Distributed DoS), there has been a variety of researches or studies in a few decades. In this paper, we present the results of theoretical performance analysis between attack prevention schemes and attack mitigation schemes. The former is a scheme that prevents abnormal incoming traffic from forwarding into a specific network based on filtering rules, and the latter is a scheme that makes some perimeter or intermediate routers, which exist on the traffic forwarding path, prevent abnormal traffic based on their own abnormal traffic information, or that mitigates abnormal traffic by using quality-of-service mechanisms at the gateway of the target network. The aspects of theoretical performance analysis are defined as the transit rates of either normal traffic or false-positive traffic after an attack detection routine processes its job, and we also present the concrete network bandwidth rates to control incoming traffic.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.3
• /
• pp.60-68
• /
• 2007

In this paper, we propose an automatic facial expressions recognition system to analyze facial expressions (happiness, disgust, surprise and neutral) using tree structures based on heuristic rules. The facial region is first obtained using skin-color model and connected-component analysis (CCs). Thereafter the origins of user's eyes are localized using neural network (NN)-based texture classifier, then the facial features using some heuristics are localized. After detection of facial features, the facial expression recognition are performed using decision tree. To assess the validity of the proposed system, we tested the proposed system using 180 facial image in the MMI, JAFFE, VAK DB. The results show that our system have the accuracy of 93%.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.10
• /
• pp.2563-2573
• /
• 1999

In most mail automatic processing centers, after facing and canceling, letter mails are passed through an Optical Character Recognition/Barcode Sorter(OCR/BS) to read the postal code and 3 of 5 fluorescent (luminescent) barcode is applied. Normally, 31%∼35% of this mails are rejected. The main reasons for reading failures are poor printing quality of addresses and barcodes, script printing, writing in a cursive hand, variety fonts, and failure to locate the address. Our goal is to provide mailer with top quality service and customer barcode service as we move toward 100% barcoding automation of letter mail. In this paper, we propose a method of printing 3 of 5 customer barcode, postal code management, and detection of postal code based on postal address for increase the performance of automatic processing system in mail items. Using postal code generating rules, which are automatically extracted from postal addresses and address numbers, creates postal codes. The customer barcode support system is implemented by C++ language and runs on IBM PC under Windows 95.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.434-437
• /
• 2010

NIPS(Network Intrusion Prevention System) is in line at the end of the external and internal networks which performed two kinds of action: Signature-based filtering and anomaly detection and prevention-based on self-learning. Among them, a signature-based filtering is well known to defend against attacks. By using signature-based filtering, intrusion prevention system passing a payload of packets is compared with attack patterns which are signature. If match, the packet is discard. However, when there is packet delay, it will increase the required pattern matching time as the number of signature is increasing whenever there is delay occur. Therefore, to ensure the performance of IPS, we needed more efficient pattern matching algorithm for high-performance ISP. To improve the performance of pattern matching the most important part is to reduce the number of comparisons signature rules and the packet whenever the packets arrive. In this paper, we propose an improve signature hashing-based pattern matching method. We use tuple pruning algorithm with Bloom filters, which effectively remove unnecessary tuples. Unlike other existing signature hashing-based IPS, our proposed method to improve the performance of IPS.

• Journal of the Korean Geosynthetics Society
• /
• v.22 no.1
• /
• pp.67-74
• /
• 2023

In order to monitor the stability of slopes, research on data-based slope failure prediction and early warning is increasing. However, most papers overlook the quality of data. Poor data quality can cause problems such as false alarms. Therefore, this paper proposes a two-step hybrid approach consisting of rules and machine learning models for quality control of data collected from slopes. The rule-based has the advantage of high accuracy and intuitive interpretation, and the machine learning model has the advantage of being able to derive patterns that cannot be explicitly expressed. The hybrid approach was able to take both of these advantages. Through a case study, the performance of using the two methods alone and the case of using the hybrid approach was compared, and the hybrid method was judged to have high performance. Therefore, it is judged that using a hybrid method is more appropriate than using the two methods alone for data quality control.

• Convergence Security Journal
• /
• v.22 no.2
• /
• pp.9-19
• /
• 2022

As the expansion of digital transformation, we are more exposed to the threat of cyber attacks, and many institution or company is operating a signature-based intrusion prevention system at the forefront of the network to prevent the inflow of attacks. However, in order to provide appropriate services to the related ICT system, strict blocking rules cannot be applied, causing many false events and lowering operational efficiency. Therefore, many research projects using artificial intelligence are being performed to improve attack detection accuracy. Most researches were performed using a specific research data set which cannot be seen in real network, so it was impossible to use in the actual system. In this paper, we propose a technique for classifying major attack keywords in the security event log collected from the actual system, assigning a weight to each key keyword, and then performing a similarity check using TF-IDF to determine whether an actual attack has occurred.