• Journal of information and communication convergence engineering
• /
• v.11 no.4
• /
• pp.258-267
• /
• 2013

New incremental learning algorithm using extended data expression, based on probabilistic compounding, is presented in this paper. Incremental learning algorithm generates an ensemble of weak classifiers and compounds these classifiers to a strong classifier, using a weighted majority voting, to improve classification performance. We introduce new probabilistic weighted majority voting founded on extended data expression. In this case class distribution of the output is used to compound classifiers. UChoo, a decision tree classifier for extended data expression, is used as a base classifier, as it allows obtaining extended output expression that defines class distribution of the output. Extended data expression and UChoo classifier are powerful techniques in classification and rule refinement problem. In this paper extended data expression is applied to obtain probabilistic results with probabilistic majority voting. To show performance advantages, new algorithm is compared with Learn++, an incremental ensemble-based algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3657-3682
• /
• 2018

This paper presents a Bluetooth and pedestrian dead reckoning (PDR)-based indoor fusion localization approach (BtPDR) using smartphones. A Bluetooth and PDR-based indoor fusion localization approach can localize the initial position of a smartphone with the received signal strength (RSS) of Bluetooth. While a smartphone is moving, BtPDR can track its position by fusing the localization results of PDR and Bluetooth RSS. In addition, BtPDR can adaptively modify the parameters of PDR. The contributions of BtPDR include: a Bluetooth RSS-based Probabilistic Voting (BRPV) localization mechanism, a probabilistic voting-based Bluetooth RSS and PDR fusion method, and a heuristic search approach for reducing the complexity of BRPV. The experiment results in a real scene show that the average positioning error is < 2m, which is considered adequate for indoor location-based service applications. Moreover, compared to the traditional PDR method, BtPDR improves the location accuracy by 42.6%, on average. Compared to state-of-the-art Wireless Local Area Network (WLAN) fingerprint + PDR-based fusion indoor localization approaches, BtPDR has better positioning accuracy and does not need the same offline workload as a fingerprint algorithm.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.01a
• /
• pp.271-272
• /
• 2015

센서 네트워크에서 센서는 제한적인 자원 때문에 다양한 공격으로부터 취약하다. 이러한 공격 중 하나인 허위 보고서 삽입 공격은 불필요한 에너지 소모와 허위 알람을 유발한다. 이 공격의 피해를 줄이기 위한 확률적 투표 여과 기법은 검증 노드를 통해 보고서의 맥들을 검증한다. 그러나 허위 보고서가 검증 노드까지 도달하는 데 불필요한 에너지가 소비된다. 본 논문에서, 우리의 제안 기법은 소스의 다음 노드에 키를 배포하여 허위 보고서 삽입 공격을 효율적으로 감지한다. 따라서 제안 기법은 기존 기법보다 에너지 효율성 향상을 기대할 수 있다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.07a
• /
• pp.11-13
• /
• 2013

무선 센서 네트워크는 개방된 환경에서 무작위로 배치되어 악의적인 공격자들에게 쉽게 노출된다. 센서 노드는 한정된 에너지 자원과 손쉽게 훼손된다는 단점을 통해 허위 보고서와 투표 삽입 공격이 발생한다. Li와 Wu는 두 공격을 대응하기 위해 확률적 투표기반 여과기법을 제안하였다. 확률적 투표기반 여과기법은 고정적인 검증 경로를 결정하기 때문에 특정 노드의 에너지 자원고갈 위험이 있다. 본 논문에서는 센서 네트워크에서 보고서 여과 확률 향상을 위하여 퍼지 시스템을 기반으로 다음 노드 선택을 약 6% 효율적인 경로 선택 방법을 제안한다. 제안 기법은 전달 경로 상의 노드 중 상태정보가 높은 노드를 검증 노드로 선택하고, 선택된 검증 노드는 허용 범위 경계 값을 기준으로 공격 유형을 판별하고 여과한다. 실험결과를 통해 제안기법은 기존기법과 비교하였을 때 에너지 효율이 향상되었다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.16 no.4
• /
• pp.119-126
• /
• 2006

In order to improve voters' reliability in electronic voting system, voter verifiable receipt technique is being actively researched. Since the receipt should be verifiable not only inside but also outside a polling place, it satisfies the requirements, individual verifiability and receipt-freeness. In the previous researches, there are some problems that special paper and printer is necessary or frequent monitoring is needed to confirm the voting machine's trustworthiness. In this paper, we propose a new receipt issuing scheme. Our scheme does not require any special equipments such as special paper and printer or optical scanner. In addition to that it does not require voters to trust any devices in the polling station and there is no need of frequent observations to the voting machines.

• Journal of the Korea Society for Simulation
• /
• v.16 no.1
• /
• pp.59-68
• /
• 2007

IT (Intrusion Tolerant) technology is for guaranteeing the availability of service for certain amount time against the attacks which couldn't be prevented by the currently deployed information security countermeasures. IT (Intrusion Tolerant) technology mainly makes use of the replication of service and system fur enhancing availability, and voting scheme and GMP (Croup Management Protocol) are used for the correctness of service. This paper presents a scheme to analyze dependability of IT (Intrusion Tolerant) technology through probabilistic and simulation method. Using suggested analysis scheme, we can analyze the robustness and make a sensible trade-offs in of IT (Intrusion Tolerant) technology.

• Journal of Information Processing Systems
• /
• v.16 no.2
• /
• pp.360-376
• /
• 2020

Many heuristic attribute reduction algorithms have been proposed to find a single reduct that functions as the entire set of original attributes without loss of classification capability; however, the proposed reducts are not always perfect for these multiclass datasets. In this study, based on a probabilistic rough set model, we propose the class-oriented attribute reduction (COAR) algorithm, which separately finds a reduct for each target class. Thus, there is a strong dependence between a reduct and its target class. Consequently, we propose a type of ensemble constructed on a group of classifiers based on class-oriented reducts with a customized weighted majority voting strategy. We evaluated the performance of our proposed algorithm based on five real multiclass datasets. Experimental results confirm the superiority of the proposed method in terms of four general evaluation metrics.

• The Journal of Korea Robotics Society
• /
• v.10 no.1
• /
• pp.9-15
• /
• 2015

We present a robust power transmission lines detection method based on vanishing point estimation. Vanishing point estimation can be helpful to detect power transmission lines because parallel lines converge on the vanishing point in a projected 2D image. However, it is not easy to estimate the vanishing point correctly in an image with complex background. Thus, we first propose a vanishing point estimation method on power transmission lines by using a probabilistic voting procedure based on intersection points of line segments. In images obtained by our system, power transmission lines are located in a fan-shaped area centered on this estimated vanishing point, and therefore we select the line segments that converge to the estimated vanishing point as candidate line segments for power transmission lines only in this fan-shaped area. Finally, we detect the power transmission lines from these candidate line segments. Experimental results show that the proposed method is robust to noise and efficient to detect power transmission lines.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.2
• /
• pp.87-94
• /
• 2016

In this paper, we discuss a gait representation based on the width of silhouette in terms of discriminative power and robustness against the noise in silhouette image for gait recognition. Its sensitivity to the noise in silhouette image are rigorously analyzed using probabilistic noisy silhouette model. In addition, we develop a gait recognition system using width representation and identify subjects using the decision level fusion based on majority voting. Experiments on CASIA gait dataset A and the SOTON gait database demonstrate the recognition performance with respect to the noise level added to the silhouette image.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.07a
• /
• pp.81-82
• /
• 2013

무센 센서 네트워크는 개방된 환경에서 운영되기 때문에 허위 보고서와 허위 투표 삽입 공격으로부터 쉽게 노출되어 있다. 두 공격을 감지하기 위해 확률적 투표-기반 여과 기법은 보고서가 전달되는 동안 그 보고서의 투표 검증을 이용하여 허위 범위 경계 값을 통해 두 공격을 감지한다. 본 논문에서 제안 기법은 네트워크의 상황을 고려하여 센서 노드의 에너지 잔여량, 홉 수, 전달된 보고서의 수를 통해 퍼지 시스템의 입력 요소로 결정하고 나온 결과를 허위 범위 경계 값을 결정을 통해 기존 기법보다 에너지 효율을 증가시킨다. 그러므로 우리의 제안 기법은 기본 기법보다 비교했을 때 전체 네트워크 수명 연장을 기대한다.