• Journal of Digital Contents Society
• /
• v.18 no.6
• /
• pp.1165-1173
• /
• 2017

Deep learning method, which is one of the most famous machine learning algorithms, has proven its applicability in various applications and is widely used in digital signal processing. However, it is difficult to apply deep learning technology to IoT devices with limited CPU performance and memory capacity, because a large number of training samples requires a lot of memory and computation time. In particular, if the Arduino with a very small memory capacity of 2K to 8K, is used, there are many limitations in implementing the algorithm. In this paper, we propose a method to optimize the ELM algorithm, which is proved to be accurate and efficient in various fields, on Arduino board. Experiments have shown that multi-class learning is possible up to 15-dimensional data on Arduino UNO with memory capacity of 2KB and possible up to 42-dimensional data on Arduino MEGA with memory capacity of 8KB. To evaluate the experiment, we proved the effectiveness of the proposed algorithm using the data sets generated using gaussian mixture modeling and the public UCI data sets.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.6
• /
• pp.1477-1484
• /
• 2015

With the growth of financial industry with smartphone, interest on user authentication using smartphone has been arisen in these days. There are various type of biometric user authentication techniques, but gait recognition using accelerometer sensor in smartphone does not seem to develop remarkably. This paper suggests the method of user authentication using accelerometer sensor embedded in smartphone. Specifically, calibrate the sensor data from smartphone with 3D-transformation, extract features from transformed data and do principle component analysis, and learn model with using gaussian mixture model. Next, authenticate user data with confidence interval of GMM model. As result, proposed method is capable of user authentication with accelerometer sensor on smartphone as a high degree of accuracy(about 96%) even in the situation that environment control and limitation are minimum on the research.

• Journal of the Korea Convergence Society
• /
• v.11 no.8
• /
• pp.39-45
• /
• 2020

Recently the terrors have been attempted in the public places of the nations such as United states, England and Japan by explosive things, toxic materials and so on. It is understood that the method in which dangerous objects are put in public places is one of the difficult types in detection. While there are the cameras recording videos for many spots in public places, it is very hard for the security personnel to monitor every videos. Nowadays the smart softwares which can analyzing videos automatically are utilized to detect abandoned objects. The method by Lin et al. shows comparatively high detection rates for abandoned objects but it is not easy to obtain the shape information because there is a tendency that the number of the pixels decreases abruptly along the time goes due to the characteristics of short-term background images. In this research a novel method is proposed to successfully extract the shape of the abandoned object by analysing the characteristics of area variation. The experiment results show that the proposed method has better performance in extracting shape information in comparison with the precedent approach.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.9
• /
• pp.1120-1131
• /
• 2016

In this paper, we propose a smoker recognition algorithm, detecting smokers in a video sequence in order to prevent fire accidents. We use description-based method in hierarchical approaches to recognize smoker's activity, the algorithm consists of background subtraction, object detection, event search, event judgement. Background subtraction generates slow-motion and fast-motion foreground image from input image using Gaussian mixture model with two different learning-rate. Then, it extracts object locations in the slow-motion image using chain-rule based contour detection. For each object, face is detected by using Haar-like feature and smoke is detected by reflecting frequency and direction of smoke in fast-motion foreground. Hand movements are detected by motion estimation. The algorithm examines the features in a certain interval and infers that whether the object is a smoker. It robustly can detect a smoker among different objects while achieving real-time performance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.2C
• /
• pp.181-187
• /
• 2012

Millimeter wave (MMW) readily penetrates fabrics, thus it can be used to detect objects concealed under clothing. A passive MMW imaging system can operate as a stand-off type sensor that scans people in both indoors and outdoors. However, because of the diffraction limit and low signal level, the imaging system often suffers from low image quality. Therefore, suitable statistical analysis and computational processing would be required for automatic analysis of the images. In this paper, a real-time concealed object detection is addressed by means of the multi-level segmentation. The histogram of the image is modeled with a Gaussian mixture distribution, and hidden object areas are segmented by a multi-level scheme involving $k$-means, the expectation-maximization algorithm, and a decision rule. The complete algorithm has been implemented in C++ environments on a standard computer for a real-time process. Experimental and simulation results confirm that the implemented system can achieve the real-time detection of concealed objects.

• The Journal of the Acoustical Society of Korea
• /
• v.35 no.2
• /
• pp.134-142
• /
• 2016

In this paper, a method synthesizing speech signal using the 40 kHz ultrasonic signals reflected from the articulatory muscles was introduced and performance was evaluated. When the ultrasound signals are radiated to articulating face, the Doppler effects caused by movements of lips, jaw, and chin observed. The signals that have different frequencies from that of the transmitted signals are found in the received signals. These ADS (Acoustic-Doppler Signals) were used for estimating of the speech parameters in this study. Prior to synthesizing speech signal, a quantitative correlation analysis between ADS and speech signals was carried out on each frequency bin. According to the results, the feasibility of the ADS-based speech synthesis was validated. ADS-to-speech transformation was achieved by the joint Gaussian mixture model-based conversion rules. The experimental results from the 5 subjects showed that filter bank energy and LPC (Linear Predictive Coefficient) cepstrum coefficients are the optimal features for ADS, and speech, respectively. In the subjective evaluation where synthesized speech signals were obtained using the excitation sources extracted from original speech signals, it was confirmed that the ADS-to-speech conversion method yielded 72.2 % average recognition rates.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.7
• /
• pp.312-318
• /
• 2006

The conventional lip-synch system has a two-step process, speech segmentation and recognition. However, the difficulty of speech segmentation procedure and the inaccuracy of training data set due to the segmentation lead to a significant Performance degradation in the system. To cope with that, the connected vowel recognition method using Head-Body-Tail (HBT) model is proposed. The HBT model which is appropriate for handling relatively small sized vocabulary tasks reflects co-articulation effect efficiently. Moreover the 7 vowels are merged into 3 classes having similar lip shape while the system is optimized by employing a class dependent SCHMM structure. Additionally in both end sides of each word which has large variations, 8 components Gaussian mixture model is directly used to improve the ability of representation. Though the proposed method reveals similar performance with respect to the CHMM based on the HBT structure. the number of parameters is reduced by 33.92%. This reduction makes it a computationally efficient method enabling real time operation.

• Journal of Korea Multimedia Society
• /
• v.12 no.10
• /
• pp.1418-1426
• /
• 2009

There has been a lot of interest in an effective method for background subtraction in an effort to separate foreground objects from a predefined background image. Promising results on background subtraction using statistical methods have recently been reported are robust enough to operate in dynamic environments, but generally require very large computational resources and still have difficulty in obtaining clear segmentation of objects. We use a simple running-average method to model a gradually changing background, instead of using a complicated statistical technique. We employ a single global threshold vector, optimized by a genetic algorithm, instead of pixel-by-pixel thresholds. A new fitness function is defined and trained to evaluate segmentation result. The system has been implemented on a PC with a webcam, and experimental results on real images show that the new method outperforms an existing method based on a mixture of Gaussian.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.1
• /
• pp.291-297
• /
• 2018

In this paper, we present an automatic image object tracking system for Studio cameras on the stage. For object tracking, we use the OpenCV-based Python program using PC, Raspberry Pi 3 and mobile devices. There are many methods of image object tracking such as mean-shift, CAMshift (Continuously Adaptive Mean shift), background modelling using GMM(Gaussian mixture model), template based detection using SURF(Speeded up robust features), CMT(Consensus-based Matching and Tracking) and TLD methods. CAMshift algorithm is very efficient for real-time tracking because of its fast and robust performance. However, in this paper, we implement an image object tracking system for studio cameras based CMT algorithm. This is an optimal image tracking method because of combination of static and adaptive correspondences. The proposed system can be applied to an effective and robust image tracking system for continuous object tracking on the stage in real time.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.6
• /
• pp.259-268
• /
• 2007

This paper contributes to an improvement of the statistical bandwidth extension(BWE) system based on Hidden Markov Model(HMM). First, the existing HMM training method for BWE, which is suggested originally by Jax, is analyzed in comparison with the general Baum-Welch training method. Next, based on this analysis, a new HMM-based BWE method is suggested which adopts the Baum-Welch re-estimation algorithm instead of the Jax's to train HMM model. Conclusionally speaking, the Baum-Welch re-estimation algorithm is a generalized form of the Jax's training method. It is flexible and adaptive in modeling the statistical characteristic of training data. Therefore, it generates a better model to the training data, which results in an enhanced BWE system. According to experimental results, the new method performs much better than the Jax's BWE systemin all cases. Under the given test conditions, the RMS log spectral distortion(LSD) scores were improved ranged from 0.31dB to 0.8dB, and 0.52dB in average.