• 산업경영시스템학회지
• /
• 제20권42호
• /
• pp.161-169
• /
• 1997

A variety of learning methods are used for neural networks. Among them, the backpropagation algorithm is most widely used in such image processing, speech recognition, and pattern recognition. Despite its popularity for these application, its main problem is associated with the running time, namely, too much time is spent for the learning. This paper suggests a method which maximize the convergence speed of the learning. Such reduction in e learning time of the backpropagation algorithm is possible through an adaptive adjusting of the slope of the activation function depending on total errors, which is named as the variable slope algorithm. Moreover experimental results using this variable slope algorithm is compared against conventional backpropagation algorithm and other variations; which shows an improvement in the performance over pervious algorithms.

• ETRI Journal
• /
• 제42권1호
• /
• pp.78-89
• /
• 2020

Human activity recognition (HAR) has become effective as a computer vision tool for video surveillance systems. In this paper, a novel biometric system that can detect human activities in 3D space is proposed. In order to implement HAR, joint angles obtained using an RGB-depth sensor are used as features. Because HAR is operated in the time domain, angle information is stored using the sliding kernel method. Haar-wavelet transform (HWT) is applied to preserve the information of the features before reducing the data dimension. Dimension reduction using an averaging algorithm is also applied to decrease the computational cost, which provides faster performance while maintaining high accuracy. Before the classification, a proposed thresholding method with inverse HWT is conducted to extract the final feature set. Finally, the K-nearest neighbor (k-NN) algorithm is used to recognize the activity with respect to the given data. The method compares favorably with the results using other machine learning algorithms.

• 인터넷정보학회논문지
• /
• 제22권3호
• /
• pp.9-16
• /
• 2021

This study aims to develop a human activity recognition (HAR) system as a Deep-Learning (DL) classification model, distinguishing various human activities. We solely rely on the signals from a wristband accelerometer worn by a person for the user's convenience. 3-axis sequential acceleration signal data are gathered within a predefined time-window-slice, and they are used as input to the classification system. We are particularly interested in developing a Deep-Learning model that can outperform conventional machine learning classification performance. A total of 13 activities based on the laboratory experiments' data are used for the initial performance comparison. We have improved classification performance using the Convolutional Neural Network (CNN) combined with an auto-encoder feature reduction and parameter tuning. With various publically available HAR datasets, we could also achieve significant improvement in HAR classification. Our CNN model is also compared against Recurrent-Neural-Network(RNN) with Long Short-Term Memory(LSTM) to demonstrate its superiority. Noticeably, our model could distinguish both general activities and near-identical activities such as sitting down on the chair and floor, with almost perfect classification accuracy.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제22권11호
• /
• pp.583-590
• /
• 2016

최근 일상적인 인간 생활의 거의 모든 영역에서 사물 인터넷에 대한 관심이 급속히 증대되면서, 음성 인식은 중요한 HCI 수단으로 자리 잡고 있다. 더불어, 모바일 환경에서의 음성 인식 시스템에 대한 수요 또한 급속히 증대되고 있다. 모바일 환경을 위한 서버 기반의 음성 인식 시스템은 대체로 빠른 속도와 높은 인식률을 보이고 있지만, 데이터베이스에 저장되어 있는 단어를 단위로 하여 인식을 수행하므로, 인터넷이 연결되어 있어야 하고 서버에서의 많은 계산량을 필요로 한다. 본 논문은 음소 기반 한국어 음성 인식 시스템의 일부로서, 한국어 모음 'ㅗ'에 대한 새로운 인식 방식을 제안한다. 제안하는 방식은 주파수 영역에서의 분석 대신, 시간 영역에서의 파형 패턴에 기반하여 동작하므로, 계산 비용을 현저히 절감할 수 있다. 모음 'ㅗ'의 전형적인 파형 패턴들을 탐지하기 위한 요소 알고리즘들을 제시하며, 이를 결합하여 최종 판별을 수행한다. 실험 결과를 통해, 제안하는 방식이 89.9%의 인식 정확도를 달성할 수 있음을 확인하였다.

• 한국건축시공학회지
• /
• 제10권5호
• /
• pp.87-94
• /
• 2010

건설공사는 현장을 중심으로 이루어지고 있어 공사계획초기 수립된 공기가 공기지연요인에 의하여 지연 또는 연장이 발생하게 되면 건설사는 클레임 등의 위험부담을 안고 있어 공기단축을 통해 공사 준공일 내에 목적물을 완공한다. 이에 광주광역시 내 공동주택 현장의 기술자들을 대상으로 공정관리 실태 및 공기단축의 필요성, 목적, 방법에 관한 인식을 파악해보았고 그 결과 타 지역에 비하여 공정관리전담부서 편성이 미흡하고 전문 인력이 부족함을 알았고, 공기단축의 필요성은 높게 인식된 반면 공사비 절감과의 관계는 낮게 인식되었다. 단축목적으로는 공기연장에 대비, 각종 클레임에 대처를 높게 인식하였으며 단축방법으로는 작업시간연장 및 작업원 증가를 통해 단축하겠다고 하였다. 이에 본 연구는 기술자들로 하여금 공기단축은 단순히 공기지연을 만회하기 위한 것이 아니라 원가절감을 통한 생산성 향상 및 대외 경쟁력 확보와 밀접한 관련성이 있다고 인식되어지길 기대한다.

• 제어로봇시스템학회논문지
• /
• 제13권4호
• /
• pp.371-376
• /
• 2007

This paper presents an emotion recognition and its expression system of an intelligent robot like a home robot or a service robot. Emotion recognition method in the robot is used by a facial image. We use a motion and a position of many facial features. apply a tracking algorithm to recognize a moving user in the mobile robot and eliminate a skin color of a hand and a background without a facial region by using the facial region detecting algorithm in objecting user image. After normalizer operations are the image enlarge or reduction by distance of the detecting facial region and the image revolution transformation by an angel of a face, the mobile robot can object the facial image of a fixing size. And materialize a multi feature selection algorithm to enable robot to recognize an emotion of user. In this paper, used a multi layer perceptron of Artificial Neural Network(ANN) as a pattern recognition art, and a Back Propagation(BP) algorithm as a learning algorithm. Emotion of user that robot recognized is expressed as a graphic LCD. At this time, change two coordinates as the number of times of emotion expressed in ANN, and change a parameter of facial elements(eyes, eyebrows, mouth) as the change of two coordinates. By materializing the system, expressed the complex emotion of human as the avatar of LCD.

• 대한음성학회지:말소리
• /
• 제59호
• /
• pp.53-68
• /
• 2006

We report the evaluation results of the Korean speech recognition platform called ECHOS. The platform has an object-oriented and reusable architecture so that researchers can easily evaluate their own algorithms. The platform has all intrinsic modules to build a large vocabulary speech recognizer: Noise reduction, end-point detection, feature extraction, hidden Markov model (HMM)-based acoustic modeling, cross-word modeling, n-gram language modeling, n-best search, word graph generation, and Korean-specific language processing. The platform supports both lexical search trees and finite-state networks. It performs word-dependent n-best search with bigram in the forward search stage, and rescores the lattice with trigram in the backward stage. In an 8000-word continuous speech recognition task, the platform with a lexical tree increases 40% of word errors but decreases 50% of recognition time compared to the HTK platform with flat lexicon. ECHOS reduces 40% of recognition errors through incorporation of cross-word modeling. With the number of Gaussian mixtures increasing to 16, it yields word accuracy comparable to the previous lexical tree-based platform, Julius.

• 산업기술연구
• /
• 제26권B호
• /
• pp.233-242
• /
• 2006

Continuous, discrete and semi continuous HMM systems are used for the speech recognition. Discrete systems have the advantage of low run-time computation. However, vector quantization reduces accuracy and this can lead to poor performance. Continuous systems let us get good correctness but they need much calculation so that occasionally they are unable to be used for practice. Although there are semi-continuous systems which apply advantage of continuous and discrete systems, they also require much computation. In this paper, we proposed the way which reduces calculation for continuous systems. The proposed method has the same computational load as discrete systems but can give better recognition accuracy than discrete systems.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(4)
• /
• pp.37-40
• /
• 2001

The most important issues in gesture recognition are the simplification of algorithm and the reduction of processing time. The mathematical morphology based on geometrical set theory is best used to perform the real-time processing. A key idea of the algorithm proposed in this paper is to apply morphological shape decomposition. The primitive elements extracted from a hand gesture have very important information including the directivity of the hand gestures. Based on this algorithm, we proposed the morphological hand-gesture recognition algorithm using feature vectors extracted from lines connecting the center points of a main-primitive element and sub-primitive elements. Through the experiments, we applied to the video contents browsing system with natural interactions and demonstrated the efficiency of this algorithm.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• pp.195-198
• /
• 2002

We propose an efficient mixture Gaussian synthesis method for decision tree based state tying that produces better context-dependent models in a short period of training time. This method makes it possible to handle mixture Gaussian HMMs in decision tree based state tying algorithm, and provides higher recognition performance compared to the conventional HMM training procedure using decision tree based state tying on single Gaussian GMMs. This method also reduces the steps of HMM training procedure. We applied this method to training of PBS, and we expect to achieve a little point improvement in phoneme accuarcy and reduction in training time.