• ETRI Journal
• /
• v.36 no.1
• /
• pp.99-105
• /
• 2014

This paper presents a new locomotion mode recognition method based on a transformed correlation feature analysis using an electromyography (EMG) pattern. Each movement is recognized using six weighted subcorrelation filters, which are applied to the correlation feature analysis through the use of six time-domain features. The proposed method has a high recognition rate because it reflects the importance of the different features according to the movements and thereby enables one to recognize real-time EMG patterns, owing to the rapid execution of the correlation feature analysis. The experiment results show that the discriminating power of the proposed method is 85.89% (${\pm}2.5$) when walking on a level surface, 96.47% (${\pm}0.9$) when going up stairs, and 96.37% (${\pm}1.3$) when going down stairs for given normal movement data. This makes its accuracy and stability better than that found for the principal component analysis and linear discriminant analysis methods.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.149-152
• /
• 2003

In this paper, we present a performance comparison of feature parameters and classifiers for speech/music discrimination. Experiments were carried out on six feature parameters and three classifiers. It turns out that three classifiers shows similar performance. The feature set that captures the temporal and spectral structure of the signal yields good performance, while the phone-based feature set shows relatively inferior performance.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.43-50
• /
• 2022

Continuous development is the key of development issue in developing nations. Smart city measurement is prevalently carried through in the cities in which the nations have been classified as industrialized countries. In addition, cities in Europe becomes the models of smart city system. Smart city concept used in the cities in Europe applies six predominant features i.e. smart economic, smart mobility, smart environment, smart people, smart living, and smart governance. This paper focuses on figuring out city' development strategy in developing nations particularly Indonesia in regard with European Framework by way of Multi Expert Multi Criterion Decision Making (ME-MCDM). Recommendation is resulted from the tests using the data collected from one of the metropolis cities in Indonesia, whereby issuing recommendation must firstly implement smart education, secondly communication, thirdly smart government, and fourthly smart health, as well as simultaneously implement smart energy and smart mobility.

• MALSORI
• /
• no.46
• /
• pp.37-50
• /
• 2003

In this paper, we evaluate and compare the performance of speech/music discrimination based on various feature parameters and classifiers. As for feature parameters, we consider High Zero Crossing Rate Ratio (HZCRR), Low Short Time Energy Ratio (LSTER), Spectral Flux (SF), Line Spectral Pair (LSP) distance, entropy and dynamism. We also examine three classifiers: k Nearest Neighbor (k-NN), Gaussian Mixure Model (GMM), and Hidden Markov Model (HMM). According to our experiments, LSP distance and phoneme-recognizer-based feature set (entropy and dunamism) show good performance, while performance differences due to different classifiers are not significant. When all the six feature parameters are employed, average speech/music discrimination accuracy up to 96.6% is achieved.

• Journal of architectural history
• /
• v.17 no.4
• /
• pp.25-42
• /
• 2008

The Gyeongbok Palace was completed during the reign of King Taejo and King Sejong in the early Joseon Dynasty. The most remarkable spacious feature of the palace is that it has an inner palace wall without an outer palace wall. The absence of the outer palace wall had its origin in the palace of the late Goryeo Dynasty which did not provide the outer palace wall. Gwanghwamoon was the main gate of the palace, and the office buildings of the Six Ministries were arranged on the right side in front of the main gate. A wide road called Six Ministries Avenue was made between the builidings. The avenue was completed during the reign of the third king of Joseon, Taejong, and it was assumed that this arrangement was influenced by the government office arrangements of Nanjing, the early capital city of the Ming Dynasty. Gwanghwamoon held national rituals as well as the civic and military state examinations nations in front of the gate. The avenue was decorated with flowers and silks when kings and the royal families, or Chinese envoys enter the gate, and the civilians watched the parade, Because there was no outer palace wall, all the events held at Gwanghwamoon and the Six Ministries Avenue ware opened to the public, it was the unique feature of Gyeongbok Palace that the palaces of Goryeo dynasty and China did not have.

• The Journal of Korea Robotics Society
• /
• v.3 no.3
• /
• pp.237-244
• /
• 2008

Nowadays, research on human-robot interaction has been getting increasing attention. In the research field of human-robot interaction, speech signal processing in particular is the source of much interest. In this paper, we report a speaker localization system with six microphones for a humanoid robot called MAHRU from KIST and propose a time delay of arrival (TDOA)-based feature matrix with its algorithm based on the minimum sum of absolute errors (MSAE) for sound source localization. The TDOA-based feature matrix is defined as a simple database matrix calculated from pairs of microphones installed on a humanoid robot. The proposed method, using the TDOA-based feature matrix and its algorithm based on MSAE, effortlessly localizes a sound source without any requirement for calculating approximate nonlinear equations. To verify the solid performance of our speaker localization system for a humanoid robot, we present various experimental results for the speech sources at all directions within 5 m distance and the height divided into three parts.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.3E
• /
• pp.91-97
• /
• 2004

In this paper, we propose a classification system of TV program scenes based on audio information. The system classifies the video scene into six categories of commercials, basketball games, football games, news reports, weather forecasts and music videos. Two type of audio feature set are extracted from each audio frame-timbral features and coefficient domain features which result in 58-dimensional feature vector. In order to reduce the computational complexity of the system, 58-dimensional feature set is further optimized to yield l0-dimensional features through Sequential Forward Selection (SFS) method. This down-sized feature set is finally used to train and classify the given TV program scenes using κ -NN, Gaussian pattern matching algorithm. The classification result of 91.6% reported here shows the promising performance of the video scene classification based on the audio information. Finally, the system stability problem corresponding to different query length is investigated.

• Journal of Korea Multimedia Society
• /
• v.20 no.2
• /
• pp.126-133
• /
• 2017

The conventional hand-crafted features used to track objects have limitations in object representation. Convolutional neural networks, which show good performance results in various areas of computer vision, are emerging as new ways to break through the limitations of feature extraction. CNN extracts the features of the image through layers of multiple layers, and learns the kernel used for feature extraction by itself. In this paper, we use the feature map extracted from the convolution layer of the convolution neural network to create an outline model of the object and use it for tracking. We propose a method to adaptively update the outline model to cope with various environment change factors affecting the tracking performance. The proposed algorithm evaluated the validity test based on the 11 environmental change attributes of the CVPR2013 tracking benchmark and showed excellent results in six attributes.

• Journal of Oral Medicine and Pain
• /
• v.9 no.1
• /
• pp.157-167
• /
• 1984

A human bite-mark shows special feature according to the suspect's dentition. The teeth which most frequently give useful bite-marks are six upper and lower anteriors, while the premolar teeth somtimes give marks it is often difficult to distinguish. The author tried to classify and to analize the anterior dentition which makes the bite-mark directly by means of 672 maxillary and 691 mandibular stone model taken from Korean adult aging from 17 to 40 years old. The results were as follows : 1. There was no particular correlation between the presence of six normal-shaped and correctly positioned upper and lower anteriors and the presence of rotation of teeth. 2. Inter central incisor, inter lateral incisor, inter canine width and angles of adjecent teeth were not identical eath other in studied models. 3. The results of this analysis supported the statement that any bite-mark had no same feature.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.11
• /
• pp.3658-3679
• /
• 2022

Classification of persons wearing and not wearing face masks in images has emerged as a new computer vision problem during the COVID-19 pandemic. In order to address this problem and scale up the research in this domain, in this paper a hybrid technique by employing ResNet-101 and multi-layer perceptron (MLP) classifier has been proposed. The proposed technique is tested and validated on a self-created face masks classification dataset and a standard dataset. On self-created dataset, the proposed technique achieved a classification accuracy of 97.3%. To embrace the proposed technique, six other state-of-the-art CNN feature extractors with six other classical machine learning classifiers have been tested and compared with the proposed technique. The proposed technique achieved better classification accuracy and 1-6% higher precision, recall, and F1 score as compared to other tested deep feature extractors and machine learning classifiers.