• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1435-1438
• /
• 2015

본 논문에서는 대용량의 K-POP 모션캡처 데이터베이스에서 특정 안무구간을 검색하는 방법을 제안한다. 제안 기술은 저가형 3D 카메라를 이용하여 사용자가 직접 검색하고자 하는 동작을 생성하고 이를 질의동작으로 입력하여 원하는 안무동작을 검색하는 직관적인 검색 기술로서 구간 동작의 명칭이 존재하지 않는 K-POP 댄스를 검색하기 위한 핵심기술이다. 역동적인 댄스 자세를 표현하고 매칭하는 방법으로 관절 및 바디파트 간의 상대적인 각도 정보를 추출하고 비교하는 방법을 설명한다. 대용량의 모션캡쳐 데이터베이스를 고속으로 검색하기 위해서 안무동작의 핵심 자세를 분석하여 후보구간 집합을 빠르게 생성하고, 이들 집합에서 Dynamic Time Warping(DTW) 알고리즘으로 안무동작 간의 매칭거리를 보다 정밀하게 산출한다. 약 358분의 K-POP 댄스 곡 100곡에 대한 성능평가에서 92%의 검색정확도를 보였으며, 이는 K-POP 댄스 동작의 복잡성을 고려할 때 경쟁력 있는 성능치이다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.385-388
• /
• 2012

본 논문에서는 스마트 폰에 내장된 3축 가속도 센서를 이용해 제스처 훈련 및 테스터 데이터를 수집하고, DTW(Dynamic Time Warping) 알고리즘을 근간으로 하는 효과적인 제스처 인식 방법을 제안한다. 본 논문에서 제안하는 제스처 인식 방법의 성능을 분석하기 위해 안드로이드 스마트 폰에서 동작하는 제스처 인식 프로그램을 개발하였고, 이것을 이용해 수행한 성능실험 결과를 소개한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.342-345
• /
• 2013

본 논문은 모바일 환경에서의 다중생체인식을 통한 개인인증 시스템을 제안한다. 다중생체인식을 위하여 얼굴인식과 화자인식을 선택하였으며, 시스템의 인식 시나리오는 다음을 따른다. 얼굴인식을 위하여 Modified census transform (MCT) 기반의 얼굴검출과 k-means 클러스터 분석 (cluster analysis) 알고리즘 기반의 눈 검출을 통해 얼굴영역 전처리를 수행하고, principal component analysis (PCA) 기반의 얼굴인증 시스템을 구현한다. 화자인식을 위하여 음성의 끝점 추출과 Mel frequency cepstral coefficient(MFCC) 특징을 추출하고, dynamic time warping (DTW) 기반의 화자 인증 시스템을 구현한다. 그리고 각각의 생체인식을 본 논문에서 제안된 방법을 기반으로 융합하여 인식률을 향상시킨다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.732-735
• /
• 2010

본 연구에서는 음악 데이터 베이스에서 노래의 특정 구간과 가장 유사한 구간을 검색하는 시스템을 제안한다. 제안된 시스템에서는 음악을 다차원 시계열 데이터로 간주하고, 음악의 조성 차이 및 템포(tempo) 차이를 고려한 음악의 유사도 계산 방법을 사용한다. 유사도 계산의 전처리 단계에서 조성 차이를 보정하고, 비트(beat)를 검출하며, 추출된 크로마그램(chromagram)을 검출된 비트와 동기화 하여 평균한다. 이후, 동적 시간 왜곡(DTW; dynamic time warping)을 사용하여 두 구간사이의 유사도를 계산한 후 계산된 유사도 순서로 정렬된 검색 결과를 출력한다. 사용자는 제안된 시스템을 사용하여 선택 구간 유사도 검색과 자동 유사 검색 결과로 도출된 구간 쌍을 검토하여 유사 구간을 보다 쉽게 찾을 수 있다.

• Journal of Internet Computing and Services
• /
• v.6 no.1
• /
• pp.105-114
• /
• 2005

This paper describes a new measuring technique by analysing multiple time-series patterns. This paper's goal is that extracts a really measured value having a sample pattern which is the best matched with an inputted time-series, and calculates a difference ratio with the value. Therefore, the proposed technique is not a recognition but a measurement. and not a hardware but a software. The proposed technique is consisted of three stages, initialization, learning and measurement. In the initialization stage, it decides weights of all parameters using importance given by an operator. In the learning stage, it classifies sample patterns using LBG and DTW algorithm, and then creates code sequences for all the patterns. In the measurement stage, it creates a code sequence for an inputted time-series pattern, finds samples having the same code sequence by hashing, and then selects the best matched sample. Finally it outputs the really measured value with the sample and the difference ratio. For the purpose of performance evaluation, we tested on multiple time-series patterns obtained from etching machine which is a semiconductor manufacturing.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.538-561
• /
• 2020

Recommender Systems (RecSys) have a major role in e-commerce for recommending products, which they may like for every user and thus improve their business aspects. Although many types of RecSyss are there in the research field, the state of the art RecSys has focused on finding the user similarity based on sequence (e.g. purchase history, movie-watching history) analyzing and prediction techniques like Recurrent Neural Network in Deep learning. That is RecSys has considered as a sequence prediction problem. However, evaluation of similarities among the customers is challenging while considering temporal aspects, context and multi-component ratings of the item-records in the customer sequences. For addressing this issue, we are proposing a Deep Learning based model which learns customer similarity directly from the sequence to sequence similarity as well as item to item similarity by considering all features of the item, contexts, and rating components using Dynamic Temporal Warping(DTW) distance measure for dynamic temporal matching and 2D-GRU (Two Dimensional-Gated Recurrent Unit) architecture. This will overcome the limitation of non-linearity in the time dimension while measuring the similarity, and the find patterns more accurately and speedily from temporal and spatial contexts. Experiment on the real world movie data set LDOS-CoMoDa demonstrates the efficacy and promising utility of the proposed personalized RecSys architecture.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.1
• /
• pp.78-85
• /
• 1999

In this paper we propose a method to improve the performance of the mel-cepstrum that is widely used in speech recognition. Typically, the met-cepstrum is obtained by critical band filters that have fixed center spacing and bandwidth. However different filter characteristics produce a different mel-cepstrum, resulting in a different performance. In this paper we analyze triangular-shaped and rectangular-shaped filters. By changing the characteristics of filters such as center frequency and bandwidth, we analyze the performance of the met-cepstrum. Then utilizing the simplex method, we propose a method to optimize the critical band filters. Using the dynamic time warping, we performed speaker independent recognition experiments with Korean digit words pronounced by 10 males and 10 females. Experiments show that the rectangular-shaped filters show good performance and the mel-cepstrum obtained by the optimized filters shows better performance than filters that have fixed center spacing and bandwidth.

• Journal of Korean Society of Environmental Engineers
• /
• v.29 no.8
• /
• pp.944-949
• /
• 2007

The profiles of on-line sensors such as DO, ORP and pH can provide useful information about pollutant removal reaction in sequencing batch reactor. For detection of denitrification completion, the nitrate hee point from ORP profile has been considered as a main indicator of denitrification completion. However, many researchers pointed out that the nitrate knee usually disappeared been the progress of denitrification is so fast and it makes the fault at detection of denitrification completion. In this paper, dynamic time warping(DTW) method and discriminant analysis were used to detect and isolate the profiles of two cases, denitrification completed and uncompleted. As the results, proposed methods can detect state of denitrification successfully.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.1
• /
• pp.49-54
• /
• 2006

The recent fingerprint recognition system has unstable factors, such as copy of fingerprint patterns and hacking of fingerprint feature point, which mali cause significant system error. Thus, in this research, we used the fingerprint as the main recognition device and then implemented the multi-biometric recognition system in serial using the speech recognition which has been widely used recently. As a multi-biometric recognition system, once the speech is successfully recognized, the fingerprint recognition process is run. In addition, speaker-dependent DTW(Dynamic Time Warping) algorithm is used among existing speech recognition algorithms (VQ, DTW, HMM, NN) for effective real-time process while KSOM (Kohonen Self-Organizing feature Map) algorithm, which is the artificial intelligence method, is applied for the fingerprint recognition system because of its calculation amount. The experiment of multi-biometric recognition system implemented in this research showed 2 to $7\%$ lower FRR (False Rejection Ratio) than single recognition systems using each fingerprints or voice, but zero FAR (False Acceptance Ratio), which is the most important factor in the recognition system. Moreover, there is almost no difference in the recognition time(average 1.5 seconds) comparing with other existing single biometric recognition systems; therefore, it is proved that the multi-biometric recognition system implemented is more efficient security system than single recognition systems based on various experiments.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2012.02a
• /
• pp.239-240
• /
• 2012

With advancements in semiconductor device technologies, manufacturing processes are getting more complex and it became more difficult to maintain tighter process control. As the number of processing step increased for fabricating complex chip structure, potential fault inducing factors are prevail and their allowable margins are continuously reduced. Therefore, one of the key to success in semiconductor manufacturing is highly accurate and fast fault detection and classification at each stage to reduce any undesired variation and identify the cause of the fault. Sensors in the equipment are used to monitor the state of the process. The idea is that whenever there is a fault in the process, it appears as some variation in the output from any of the sensors monitoring the process. These sensors may refer to information about pressure, RF power or gas flow and etc. in the equipment. By relating the data from these sensors to the process condition, any abnormality in the process can be identified, but it still holds some degree of certainty. Our hypothesis in this research is to capture the features of equipment condition data from healthy process library. We can use the health data as a reference for upcoming processes and this is made possible by mathematically modeling of the acquired data. In this work we demonstrate the use of recurrent neural network (RNN) has been used. RNN is a dynamic neural network that makes the output as a function of previous inputs. In our case we have etch equipment tool set data, consisting of 22 parameters and 9 runs. This data was first synchronized using the Dynamic Time Warping (DTW) algorithm. The synchronized data from the sensors in the form of time series is then provided to RNN which trains and restructures itself according to the input and then predicts a value, one step ahead in time, which depends on the past values of data. Eight runs of process data were used to train the network, while in order to check the performance of the network, one run was used as a test input. Next, a mean squared error based probability generating function was used to assign probability of fault in each parameter by comparing the predicted and actual values of the data. In the future we will make use of the Bayesian Networks to classify the detected faults. Bayesian Networks use directed acyclic graphs that relate different parameters through their conditional dependencies in order to find inference among them. The relationships between parameters from the data will be used to generate the structure of Bayesian Network and then posterior probability of different faults will be calculated using inference algorithms.