• The Journal of the Acoustical Society of Korea
• /
• v.22 no.5
• /
• pp.360-366
• /
• 2003

Although multilayer perceptrons (MLPs) present several advantages against other pattern recognition methods, MLP-based speaker verification systems suffer from slow enrollment speed caused by many background speakers to achieve a low verification error. To solve this problem, the quantitative discriminative cohort speakers (QnDCS) method, by introducing the cohort speakers method into the systems, reduced the number of background speakers required to enroll speakers. Although the QnDCS achieved the goal to some extent, the improvement rate for the enrolling speed was still unsatisfactory. To improve the enrolling speed, this paper proposes the qualitative DCS (QlDCS) by introducing a qualitative criterion to select less background speakers. An experiment for both methods is conducted to use the speaker verification system based on MLPs and continuants, and speech database. The results of the experiment show that the proposed QlDCS method enrolls speakers in two times shorter time than the QnDCS does over the online error backpropagation(EBP) method.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.19-22
• /
• 2021

기존 영상 콘텐츠에 새로운 물체를 삽입하는 등의 영상 재구성 기술은 새로운 게임, 가상현실, 증강현실 콘텐츠를 생성하거나 인공신경망 학습을 위한 데이터 증대를 위해 사용될 수 있다. 하지만, 기존 기술은 컴퓨터 그래픽스, 사람에 의한 수동적인 영상 편집에 의존하고 있어 금전적/시간적 비용이 높다. 이에 본 연구에서는 인공지능 신경망을 활용하여 낮은 비용으로 영상을 재구성하는 기술을 소개하고자 한다. 제안하는 방법은 기존 콘텐츠와 삽입하고자 하는 객체를 포함하는 영상이 주어졌을 때, 객체 세그먼테이션 네트워크를 활용하여 입력 영상에서 객체를 분리하고, 스타일 변환 네트워크를 활용하여 입력 영상을 스타일 변환한 후, 사용자 입력과 두 네트워크의 결과를 활용하여 기존 콘텐츠에 새로운 객체를 삽입하는 것이다. 실험에서는 기존 콘텐츠는 온라인 영상을 활용하였으며 삽입 객체를 포함한 영상은 ImageNet 영상 분류 데이터 세트를 활용하였다. 실험을 통해 제안한 방법을 활용하면 기존 콘텐츠와 잘 어우러지게끔 객체를 삽입할 수 있음을 보인다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.6
• /
• pp.69-80
• /
• 2004

This paper proposes a method to learn action patterns of opponent characters for intelligent characters. For learning action patterns, intelligent characters learn the past actions as well as the current actions of opponent characters. Therefore, intelligent characters react more properly than ones without the knowledge on action patterns. In addition, this paper proposes a method to learn moving actions whose fitness is hard to evaluate. To evaluate the performance of the proposed algorithm, we experiment with four repeated action patterns in a game similar to real games. The results show that intelligent characters learn the optimal actions for action patterns and react properly against to random action opponent characters. The proposed method can be applied to various games in which characters confront each other, e.g. massively multiple of line games.

• Journal of Intelligence and Information Systems
• /
• v.7 no.2
• /
• pp.143-151
• /
• 2001

This paper investigates the development of a neural network based system for automated signature authentication that relies on an autoregressive characterization for the segments of a signature. The primary contributions of this work are tow-fold: a) the development of the neural network architecture and the modalities of training it, b) adaptation of the dynamic time warping algorithm to fomulate a new method for enabling consistent segmentation of multiple signatures from the same writer. The performance of the signature verification system has been tested using a sizable database that includes a comprehensive set of simulated and realistic forgeries. False Acceptance and False Rejection error rates of 0.78% and 1.6% respectively were obtained in tests conducted using 1920 skilled forgeries.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.39 no.2
• /
• pp.157-165
• /
• 2002

This paper presents the implementation of the speed control system for 3 phase induction motor using PD controller and neural networks. The PD controller is used to control the motor and to train neural networks at the first time. And neural networks are widely used as controllers because of a nonlinear mapping capability, we used feedforward neural networks(FNN) in order to simply design the speed control system of the 3 phase induction motor. Neural networks are tuned online using the speed reference, actual speed measured from an encoder and control input current to motor. PD controller and neural networks are applied to the speed control system for 3 phase induction motor, are compared with PI controller through computer simulation and experiment respectively. The results are illustrated that the output of the PD controller is decreased and feedforward neural networks act main controller, and the proposed hybrid controllers show better performance than the PI controller in abrupt load variation and the precise control is possible because the steady state error can be minimized by training neural networks.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.347-364
• /
• 2022

Fraudulent companies or sellers strategically manipulate reviews to influence customers' purchase decisions; therefore, the reliability of reviews has become crucial for customer decision-making. Since customers increasingly rely on online reviews to search for more detailed information about products or services before purchasing, many researchers focus on detecting manipulated reviews. However, the main problem in detecting manipulated reviews is the difficulties with obtaining data with manipulated reviews to utilize machine learning techniques with sufficient data. Also, the number of manipulated reviews is insufficient compared with the number of non-manipulated reviews, so the class imbalance problem occurs. The class with fewer examples is under-represented and can hamper a model's accuracy, so machine learning methods suffer from the class imbalance problem and solving the class imbalance problem is important to build an accurate model for detecting manipulated reviews. Thus, we propose an OpenAI-based reviews generation model to solve the manipulated reviews imbalance problem, thereby enhancing the accuracy of manipulated reviews detection. In this research, we applied the novel autoregressive language model - GPT-3 to generate reviews based on manipulated reviews. Moreover, we found that applying GPT-3 model for oversampling manipulated reviews can recover a satisfactory portion of performance losses and shows better performance in classification (logit, decision tree, neural networks) than traditional oversampling models such as random oversampling and SMOTE.

• Journal of Broadcast Engineering
• /
• v.23 no.5
• /
• pp.642-655
• /
• 2018

Occupancy sensors installed in buildings and households turn off the light if the space is vacant. Currently PIR(pyroelectric infra-red) motion sensors have been utilized. Recently, the researches using camera sensors have been carried out in order to overcome the demerit of PIR that cannot detect stationary people. The detection of moving and stationary people is a main functionality of the occupancy sensors. In this paper, we propose an on-line human occupancy tracking method using convolutional neural network (CNN) and self-organizing map. It is well known that a large number of training samples are needed to train the model offline. To solve this problem, we use an untrained model and update the model by collecting training samples online directly from the test sequences. Using videos capurted from an overhead camera, experiments have validated that the proposed method effectively tracks human.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.205-208
• /
• 2010

We introduce a novel feature extraction scheme for online handwritten digit based on utilizing Zernike moment and angulation feature. The time sequential signal from mouse movement on the writing pad is described as a sequence of consecutive points on the x-y plane. So, we can create data-set which are successive and time-sequential pixel position data by preprocessing. Data preprocessed is used for Zernike moment and angulation feature extraction. this feature is scale-, translation-, and rotation-invariant. The extracted specific feature is fed to a BP(backpropagation) neural network, which in turn classifies it as one of the nine digits. In this paper, proposed method not noly show high recognition rate but also need less learning data for 200 handwritten digit data.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.99-105
• /
• 2021

In addition to the OTT video production service represented by Nexflix and YouTube, a personalized recommendation system for content with artificial intelligence has become common. YouTube's personalized recommendation service system consists of two neural networks, one neural network consisting of a recommendation candidate generation model and the other consisting of a ranking network. Netflix's video recommendation system consists of two data classification systems, divided into content-based filtering and collaborative filtering. As the online platform-led content production is activated by the Corona Pandemic, the field of virtual influencers using artificial intelligence is emerging. Virtual influencers are produced with GAN (Generative Adversarial Networks) artificial intelligence, and are unsupervised learning algorithms in which two opposing systems compete with each other. This study also researched the possibility of developing AI platform based on individual recommendation and virtual influencer (metabus) as a core content of OTT in the future.

• Cement Symposium
• /
• no.29
• /
• pp.245-252
• /
• 2002

소성 영역(Sintering zone)에서 클링커(Clinker)의 형상 형성은 시멘트 생산 공정에서 가장 중요한 생산 공정중의 하나이다. 소성공정의 진단 및 최적 제어의 핵심은 써모그래프(Thermo graph), 즉 적외선 카메라를 이용한 온도 분포의 측정이다. 여기에서 다룰 ''PIT Indicator'' 시스템은 분진이 많은 열악한 산업 현장의 연소 시스템에 적용할 수 있도록 특별히 설계한 공냉식의 2개 채널을 가진 광학 장비에 기초하고 있다. 비디오 영상과 써모그래프 이미지 그리고 다양한 연소 특성이 카메라를 통하여 얻어지고 자기 학습 기능을 가진 소프트웨어에서 기록되고 분석된다. 이때 얻은 데이터는 수학적 모델에서 온라인으로 Free Lime 함유율을 예측하는데 이용된다. 열분포의 써모그래프 표시와 공정상의 다양한 운전 특성을 분석하여 주는 ''PIT Indicator'' 소프트웨어를 통하여 다른 공정 제어 시스템과 연결이 가능하다. 이와 같은 하드웨어와 소프트웨어를 이용하여 최적화가 필요한 여러요소들의 최적화를 동시에 그리고 온라인으로 수행할 수가 있다. Free Lime 함유율의 연속적인 온라인 연산을 통해 생산 설비 및 공정에 맞는 최소한의 에너지를 Kiln 에 공급함으로써 근본적으로 1차 연료의 절감이 가능하고 NOx와 같은 유해 가스의 배출량도 제어할 수 있다. 또한 별도로 NOx에 대한 모델을 개발하여 NOx를 정확하게 예측하는 것도 가능하다.