• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권8호
• /
• pp.4043-4060
• /
• 2017

Network Intrusion Detection (NID), an important topic in the field of information security, can be viewed as a pattern recognition problem. The existing pattern recognition methods can achieve a good performance when the number of training samples is large enough. However, modern network attacks are diverse and constantly updated, and the training samples have much smaller size. Furthermore, to improve the learning ability of SVM, the research of kernel functions mainly focus on the selection, construction and improvement of kernel functions. Nonetheless, in practice, there are no theories to solve the problem of the construction of kernel functions perfectly. In this paper, we effectively integrate the advantages of the radial basis function kernel and the polynomial kernel on the notion of the game theory and propose a novel kernel SVM algorithm with game theory for NID, called GTNID-SVM. The basic idea is to exploit the game theory in NID to get a SVM classifier with better learning ability and generalization performance. To the best of our knowledge, GTNID-SVM is the first algorithm that studies ensemble kernel function with game theory in NID. We conduct empirical studies on the DARPA dataset, and the results demonstrate that the proposed approach is feasible and more effective.

• Journal of Information Processing Systems
• /
• 제16권5호
• /
• pp.1145-1157
• /
• 2020

A convolution neural networks (CNNs) has demonstrated outstanding performance compared to other algorithms in the field of face recognition. Regarding the over-fitting problem of CNN, researchers have proposed a residual network to ease the training for recognition accuracy improvement. In this study, a novel face recognition model based on game theory for call-over in the classroom was proposed. In the proposed scheme, an image with multiple faces was used as input, and the residual network identified each face with a confidence score to form a list of student identities. Face tracking of the same identity or low confidence were determined to be the optimisation objective, with the game participants set formed from the student identity list. Game theory optimises the authentication strategy according to the confidence value and identity set to improve recognition accuracy. We observed that there exists an optimal mapping relation between face and identity to avoid multiple faces associated with one identity in the proposed scheme and that the proposed game-based scheme can reduce the error rate, as compared to the existing schemes with deeper neural network.

• 한국실내디자인학회:학술대회논문집
• /
• 한국실내디자인학회 2006년도 추계학술발표대회 논문집
• /
• pp.115-120
• /
• 2006

This study concentrates on a new idea that is formulated as a creative space recognition in contemporary architecture and painting. It is stimulated from Deleuze's philosophy, which is expressed with the philosophical instrument, "Non-Representation". After discussing the concept of non-representation used in Deleuze's philosophy, case example in contemporary architecture are analysed to comparatively Investigate the relationship between the architectures by Rem Koolhaas and painting by Francis Bacon. Therefore, he founds expressions of "diagram" and "movement" in painting of F. Bacon. Diagram meansit is a power that is comprised of various points of wiew with the kind experiences that one has in life. Movement that were extracted form the Instrument in space recognition of Deleuze's panting theory were of topology, insertion of geometry, reiteration of layers, transparency and translucency, reflection effect.

• 감성과학
• /
• 제14권1호
• /
• pp.101-116
• /
• 2011

정서 컴퓨팅 분야는 인간과 컴퓨터 간 상호작용을 효과적이게 하기 위하여 사용자의 정서를 재인하는 컴퓨터 시스템을 개발했다. 본 연구의 목적은 심리학적 이론에 기반한 정서 재인 연구들을 고찰하고 보다 진보된 정서 재인 방법을 제안하고자 하였다. 본 연구의 본론에서는 심리학적 이론에 근거한 대표적인 정서 재인 방법을 고찰하였다. 첫째, Darwin 이론에 근거한 얼굴 표정 기반 정서 재인 방법을 고찰하였다. 둘째, James 이론에 근거한 생리신호기반 정서 재인 방법을 고찰하였다. 셋째, 앞의 두 이론에 통합적으로 근거한 다중 모달리티 기반 정서 재인 방법을 고찰하였다. 세 가지 방법들은 이론적 배경과 현재까지 이루어진 연구 결과들을 중심으로 고찰되었다. 결론에서는 선행 연구의 한계점을 종합하여 보다 진보된 정서 재인 방법을 제안하였다. 본 연구는 첫째, 현재 사용되고 있는 제한된 생리 신호에 대한 대안으로 다양한 생리 반응(예., 뇌 활동, 얼굴온도 등)을 정서 재인에 포함하도록 제안하였다. 둘째, 애매한 정서를 구분할 수 있도록 정서의 차원 개념에 기반한 정서 재인 방법을 제안하였다. 셋째, 정서 유발에 영향을 미치는 인지적 요소를 정서 재인에 포함하도록 제안하였다. 본 연구에서 제안한 정서 재인 방법은 다양한 생리 신호를 포함하고, 정서의 차원적 개념에 기반하며, 인지적 요소를 고려한 통합적인 모델이다.

• 한국IT서비스학회지
• /
• 제21권1호
• /
• pp.21-40
• /
• 2022

Advances in information and communication technology have introduced self-service technologies (SSTs) to service companies, changing the way they serve. In addition, as SSTs are expanding for low cost and high efficiency, opportunities for technology to interact with consumers have increased. Restaurant managers have the advantage of the SSTs win-win strategy, which allows consumers to freely receive the products or services they want, but some consumers have low satisfaction of the SSTs, especially elder people and the blind. This study examines the effect of unmanned order payment technology on service quality evaluation. For this, we interviewed a total of 12 consumers in their 10s to 50s with the experiences of using unmanned order payment technology, applying the Grounded Theory Method(GTM). Through a review of the research participant interview materials, totally 84 concepts were derived and the concepts were analyzed to derive 15 subcategories and 10 upper categories. Finally, a paradigm model of the effect of unmanned order payment technology on service quality assessment was derived. It also found the importance of consumers' sense of obligation to use unmanned order payment technology, recognition of advantages (e.g., time savings), recognition of shadow labor, and recognition of whether the technology usage process is in the service quality assessment stage.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 추계학술대회
• /
• pp.887-890
• /
• 2012

Image recognition is one of the most important research directions of pattern recognition. Image based road automatic identification technology is widely used in current society, the intelligence has become the trend of the times. This paper studied the image segmentation algorithm theory and its application in road signs recognition system. With the help of image processing technique, respectively, on road signs automatic recognition algorithm of three main parts, namely, image segmentation, character segmentation, image and character recognition, made a systematic study and algorithm. The experimental results show that: the image segmentation algorithm to establish road signs recognition model, can make effective use of smart phone system and application.

• 경영과정보연구
• /
• 제8권
• /
• pp.45-60
• /
• 2002

Recognition reactions about business area activities of business ethics measurement before and after business ethics educations are as follows: 1. Relativism average in production ethics after education shows the high rates, and deontological theory average shows the low levels. These facts show that period characteristics to respect value diversities are reflected. 2. The high average of justice theory, utilitarianism, relativism in distribution ethics before and after education reflects that fair competitions and multitude happiness are preferred, and situation adaptations about the environment changes are preferred. The low average of egoism and justice theory shows that value systems of minorities are not preferred. 3. The high average of relativism in advertisement ethics before and after education reflects the period characteristics to respect value diversities, and low egoism average shows that ethics standards of examine objects are high. 4. Egoism average in selling ethics before education is high, but this average after education is low. These reflect the fact that business ethics educations are efficient.

• 음성과학
• /
• 제8권2호
• /
• pp.49-59
• /
• 2001

The phoneme segmentation is a very difficult problem in speech sound processing because it has found out segmental algorithm in many kinds of allophone and coarticulation's trees. Thus system configuration for the speech recognition and voice retrieval processing has a complex system structure. To solve it, we discuss a possibility of new segmental algorithm, which is called the minus a thirds one or plus in tripartitioning(삼분손익) of twelve temporament(12 율려), first proposed by Prof. T. S. Han. It is close to oriental and western musical theory. He also has suggested a 3 consonant and 3 vowel phonemes in Hunminjungum(훈민정음) invented by the King Sejong in the 15th century. In this paper, we suggest to newly name it as ortho-phonic phoneme(OPP/정음소), which carries the meaning of 'the absoluteness and independency'. OPP also is acceptable to any other languages, for example IPA. Lastly we know that this algorithm is constantly applicable to the global language and is very useful to construct a voice recognition and retrieval structuring engineering.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 2005년도 추계학술대회
• /
• pp.493-504
• /
• 2005

Statistical Process Control and Process Adjustment theory is gaining recognition in the process industries where the process frequently experiences a shift mean. This paper aims to study, the theory difference between Statistical Process Control and Process Adjustment in simple terms and presents a case study that demonstrates successful integration of Statistical Process Control and Process Adjustment theory for a product in drifting industry.

• ETRI Journal
• /
• 제18권1호
• /
• pp.29-41
• /
• 1996

This paper describes a method to select a suitable feature for speech recognition using information theoretic measure. Conventional speech recognition systems heuristically choose a portion of frequency components, cepstrum, mel-cepstrum, energy, and their time differences of speech waveforms as their speech features. However, these systems never have good performance if the selected features are not suitable for speech recognition. Since the recognition rate is the only performance measure of speech recognition system, it is hard to judge how suitable the selected feature is. To solve this problem, it is essential to analyze the feature itself, and measure how good the feature itself is. Good speech features should contain all of the class-related information and as small amount of the class-irrelevant variation as possible. In this paper, we suggest a method to measure the class-related information and the amount of the class-irrelevant variation based on the Shannon's information theory. Using this method, we compare the mel-scaled FFT, cepstrum, mel-cepstrum, and wavelet features of the TIMIT speech data. The result shows that, among these features, the mel-scaled FFT is the best feature for speech recognition based on the proposed measure.