• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.4
• /
• pp.482-486
• /
• 2010

Recently, gesture recognition methods based on dynamic time warping (DTW) have been actively investigated as more mobile devices have equipped the accelerometer. DTW has no additional training step since it uses given samples as the matching templates. However, it is difficult to apply the DTW on mobile environments because of its computational complexity of matching step where the input pattern has to be compared with every templates. In order to address the problem, this paper proposes a gesture recognition method based on DTW that uses localized subset of templates. Here, the k-means clustering algorithm is used to divide each class into subclasses in which the most centered sample in each subclass is employed as the localized template. It increases the recognition speed by reducing the number of matches while it minimizes the errors by preserving the diversities of the training patterns. Experimental results showed that the proposed method was about five times faster than the DTW with all training samples, and more stable than the randomly selected templates.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.6
• /
• pp.201-208
• /
• 2014

In this paper, we propose the classifier structure design algorithm using DTW. Proposed algorithm uses DTW result to design the binary tree architecture based on the SVM which classify the multi-class data. Design the binary tree architecture for Support Vector Machine(SVM-BTA) using the threshold criterion calculated by the sum columns in square matrix which components are the reference data from each class. For comparison the performance of the proposed algorithm, compare the results of classifiers which binary tree structure are designed based on database and k-means algorithm. The data used for classification is 333 signals from 18 classes of underwater transient noise. The proposed classifier has been improved classification performance compared with classifier designed by database system, and probability of detection for non-biological transient signal has improved compare with classifiers using k-means algorithm. The proposed SVM-BTA classified 68.77% of biological sound(BO), 92.86% chain(CHAN) the mechanical sound, and 100% of the 6 kinds of the other classes.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.10
• /
• pp.1746-1754
• /
• 2016

In this paper, we provide a development and evaluation method for an archery posture analyzing system, using an inertial sensor. The system was developed using LabVIEW2014 by National Instruments and evaluated using the DTW algorithm. To convert the voltage value of the inertial sensor into a physical value, a coordinate transformation matrix bias was applied. To evaluate the similarity of movement in archery shooting, the DTW distance was calculated and similarity was confirmed based on simple mechanical movement, the same person's shooting movement, shooting movement with another person, and the noise signal. The average similarity comparison results were as follows: simple mechanical movement was 17.05%, the same person's shooting movement was 26.48%, shooting movement with another person was 62.8%, and the noise signal was 328.5%; a smaller value indicates a higher level of similarity. We confirmed the possibility of analyzing the archery posture using 3-axis acceleration of the inertial sensor. We inferred that the proposed method might be important means for assessing shooting skills, evaluation of archer's progress, and finding talented archers in advance.

• The Journal of Bigdata
• /
• v.9 no.1
• /
• pp.31-47
• /
• 2024

With the advancement of artificial intelligence, the travel and hospitality industry is also adopting AI and machine learning technologies for various purposes. In the tourism industry, demand forecasting is recognized as a very important factor, as it directly impacts service efficiency and revenue maximization. Demand forecasting requires the consideration of time-varying data flows, which is why statistical techniques and machine learning models are used. In recent years, variations and integration of existing models have been studied to account for the diversity of demand forecasting data and the complexity of the natural world, which have been reported to improve forecasting performance concerning uncertainty and variability. This study also proposes a new model that integrates various machine-learning approaches to improve the accuracy of hotel sales demand forecasting. Specifically, this study proposes a new time series forecasting model based on XGBoost that selectively utilizes a local model by clustering with DTW K-means and a global model using the entire data to improve forecasting performance. The hotel demand forecasting model that selectively utilizes global and regional models proposed in this study is expected to impact the growth of the hotel and travel industry positively and can be applied to forecasting in other business fields in the future.

• Journal of Korea Multimedia Society
• /
• v.16 no.3
• /
• pp.302-308
• /
• 2013

In this research, we have explored personal authentication system through multimodal biometrics for mobile computing environment. We have selected face and speaker recognition for the implementation of multimodal biometrics system. For face recognition part, we detect the face with Modified Census Transform (MCT). Detected face is pre-processed through eye detection module based on k-means algorithm. Then we recognize the face with Principal Component Analysis (PCA) algorithm. For speaker recognition part, we extract features using the end-point of voice and the Mel Frequency Cepstral Coefficient (MFCC). Then we verify the speaker through Dynamic Time Warping (DTW) algorithm. Our proposed multimodal biometrics system shows improved verification rate through combining two different biometrics described above. We implement our proposed system based on Android environment using Galaxy S hoppin. Proposed system presents reduced false acceptance ratio (FAR) of 1.8% which shows improvement from single biometrics system using the face and the voice (presents 4.6% and 6.7% respectively).

• MALSORI
• /
• no.47
• /
• pp.131-140
• /
• 2003

We propose a new method of generating client models for HMM based text-dependent speaker verification system with only a small amount of training data. To make a client model, statistical methods such as segmental K-means algorithm are widely used, but they do not guarantee the quality or reliability of a model when only limited data are avaliable. In this paper, we propose a blind speech segmentation based on level building DTW algorithm as an alternative method to make a client model with limited data. In addition, considering the fact that voiced sounds have much more speaker-specific information than unvoiced sounds and energy of the former is higher than that of the latter, we also propose a new score evaluation method using the observation probability raised to the power of weighting factor estimated from the normalized log energy. Our experiment shows that the proposed methods are superior to conventional HMM based speaker verification system.

• 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.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.10
• /
• pp.723-730
• /
• 2013

This paper presents the design of an arm gesture recognition system using Kinect sensor. A variety of methods have been proposed for gesture recognition, ranging from the use of Dynamic Time Warping(DTW) to Hidden Markov Models(HMM). Our system learns a unique HMM corresponding to each arm gesture from a set of sequential skeleton data. Whenever the same gesture is performed, the trajectory of each joint captured by Kinect sensor may much differ from the previous, depending on the length and/or the orientation of the subject's arm. In order to obtain the robust performance independent of these conditions, the proposed system executes the feature transformation, in which the feature vectors of joint positions are transformed into those of angles between joints. To improve the computational efficiency for learning and using HMMs, our system also performs the k-means clustering to get one-dimensional integer sequences as inputs for discrete HMMs from high-dimensional real-number observation vectors. The dimension reduction and discretization can help our system use HMMs efficiently to recognize gestures in real-time environments. Finally, we demonstrate the recognition performance of our system through some experiments using two different datasets.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.1
• /
• pp.149-160
• /
• 1997

This paper is concerned with the problem of speaker-adaptive speech synthes is method using a mapped codebook designed by fuzzy mapping on FLVQ (Fuzzy Learning Vector Quantization). The FLVQ is used to design both input and reference speaker's codebook. This algorithm is incorporated fuzzy membership function into the LVQ(learning vector quantization) networks. Unlike the LVQ algorithm, this algorithm minimizes the network output errors which are the differences of clas s membership target and actual membership values, and results to minimize the distances between training patterns and competing neurons. Speaker Adaptation in speech synthesis is performed as follow;input speaker's codebook is mapped a reference speaker's codebook in fuzzy concepts. The Fuzzy VQ mapping replaces a codevector preserving its fuzzy membership function. The codevector correspondence histogram is obtained by accumulating the vector correspondence along the DTW optimal path. We use the Fuzzy VQ mapping to design a mapped codebook. The mapped codebook is defined as a linear combination of reference speaker's vectors using each fuzzy histogram as a weighting function with membership values. In adaptive-speech synthesis stage, input speech is fuzzy vector-quantized by the mapped codcbook, and then FCM arithmetic is used to synthesize speech adapted to input speaker. The speaker adaption experiments are carried out using speech of males in their thirties as input speaker's speech, and a female in her twenties as reference speaker's speech. Speeches used in experiments are sentences /anyoung hasim nika/ and /good morning/. As a results of experiments, we obtained a synthesized speech adapted to input speaker.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.1
• /
• pp.358-377
• /
• 2015

In this paper, we propose a novel approach for trajectory recovery. Our system uses a triangulation procedure for skeletonization and graph theory to extract the trajectory. Skeletonization extracts the polyline skeleton according to the polygonal contours of the handwritten characters, and as a result, the junction becomes clear and the characters that are touching each other are separated. The approach for the trajectory recovery is based on graph theory to find the optimal path in the graph that has the best representation of the trajectory. An undirected graph model consisting of one or more strokes is constructed from a polyline skeleton. By using the polyline skeleton, our approach accelerates the process to search for an optimal path. In order to evaluate the performance, we built our own dataset, which includes testing and ground-truth. The dataset consist of thousands of handwritten characters and word images, which are extracted from five handwritten documents. To show the relative advantage of our skeletonization method, we first compare the results against those from Zhang-Suen, a state-of-the-art skeletonization method. For the trajectory recovery, we conduct a comparison using the Root Means Square Error (RMSE) and Dynamic Time Warping (DTW) in order to measure the error between the ground truth and the real output. The comparison reveals that our approach has better performance for both the skeletonization stage and the trajectory recovery stage. Moreover, the processing time comparison proves that our system is faster than the existing systems.