• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.2
• /
• pp.123-129
• /
• 2017

This paper proposes a new nonnegative matrix factorization (NMF) based direction-of-arrival (DOA) estimation method for multiple sound sources using a dual microphone array. First of all, sound signals coming from the dual microphone array are segmented into consecutive analysis frames, and a steered-response power phase transform (SRP-PHAT) beamformer is applied to each frame so that stereo signals of each frame are represented in a time-direction domain. The time-direction outputs of SRP-PHAT are stored for a pre-defined number of frames, which is referred to as a time-direction block. Next, In order to estimate DOAs robust to noise, each time-direction block is normalized along the time by using a block subtraction technique. After that, an unsupervised NMF method is applied to the normalized time-direction block in order to cluster the directions of each sound source in a multiple sound source environments. In particular, the activation and basis matrices are used to estimate the number of sound sources and their DOAs, respectively. The DOA estimation performance of the proposed method is evaluated by measuring a mean absolute error (MAE) and the standard deviation of errors between the oracle and estimated DOAs under a three source condition, where the sources are located in [$-35{\circ}$, 5m], [$12{\circ}$, 4m], and [$38{\circ}$, 4.m] from the dual microphone array. It is shown from the experiment that the proposed method could relatively reduce MAE by 56.83%, compared to a conventional SRP-PHAT based DOA estimation method.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.2
• /
• pp.77-85
• /
• 2001

This paper proposes a method of time-scale modification of polyphonic audio signals based on a sinusoidal model. The signals are modeled with sinusoidal component and noise component. A multiresolution filter bank is designed which splits the input signal into six octave-spaced subbands without aliasing and sinusoidal modeling is applied to each subband signal. To alleviate smearing of transients in time-scale modification a dynamic segmentation method is applied to subbands which determines the analysis-synthesis frame size adaptively to fit time-frequency characteristics of the subband signal. For extracting sinusoidal components and calculating their parameters matching pursuit algorithm is applied to each analysis frame of subband signal. In accordance with spectrum analysis a psychoacoustic model implementing the effect of frequency masking is incorporated with matching pursuit to provide a resonable stop condition of iteration and reduce the number of sinusoids. The noise component obtained by subtracting the synthesized signal with sinusoidal components from the original signal is modeled by line-segment model of short time spectrum envelope. For various polyphonic audio signals the result of simulation shows suggested sinusoidal modeling can synthesize original signal without loss of perceptual quality and do more robust and high quality time-scale modification for large scale factor because of representing transients without any perceptual loss.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.11A
• /
• pp.1827-1840
• /
• 2001

In digital data transmission/storage systems, the compensation for channel distortion is conducted normally using a training sequence that is known a priori to both the sender and receiver. The use of the training sequences results in inefficient utilization of channel bandwidth. Sometimes, it is also impossible to send training sequences such as in the burst-mode communication. As such, a great deal of attention has been given to the approach requiring no training sequences, which has been called the blind equalization technique. On the other hand, to utilize the limited bandwidth effectively, the concept of partial response (PR) signaling has widely been adopted in both the high-speed transmission and high-density recording/playback systems such as digital microwave, digital subscriber loops, hard disk drives, digital VCRs and digital versatile recordable disks and so on. This paper is concerned with blind adaptive equalization of partial response channels whose transfer function zeros are located on the unit circle, thereby causing some problems in performance. Specifically we study how the problems of blind channel equalization associated with the PR channels can be improved. In doing so, we first discuss the existing methods and then propose new structures for blind PR channel equalization. Our structures have been extensively tested by computer simulation and found out to be encouraging in performance. The results seem very promising as well in terms of the implementation complexity compared to the previous approach reported in literature.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.11
• /
• pp.2715-2720
• /
• 2014

Median filtering is very effective to remove impulse type noises, so it has been widely used in many signal processing applications. However, due to the time complexity of its non-linearity, median filtering is often used using a small filter window size. A lot of work has been done on devising fast median filtering algorithms, but most of them can be efficiently applied to input data with finite integer values like images. Little work has been carried out on fast 2-d median filtering algorithms that can deal with real-valued 2-d data. In this paper, a fast and simple median 2-d filter is presented, and its performance is compared with the Matlab's 2-d median filter and a heap-based 2-d median filter. The proposed algorithm is shown to be much faster than the Matlab's 2-d median filter and consistently faster than the heap-based algorithm that is much more complicated than the proposed one. Also, a more efficient median filtering scheme for 2-d real valued data with a finite range of values is presented that uses higher-bit integer 2-d median filtering with negligible quantization errors.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.1
• /
• pp.16-23
• /
• 2019

Fine particulate matter known as PM 2.5 refers to the atmospheric particulate matter that has a diameter less than 2.5 micrometer identified as dangerous element for human health and its concentration can provide us a clear picture about air dust concentration. Humans stay indoor almost 90% of their life time and also there is no official indoor dust concentration data, so our study is focused on measuring the indoor air quality. Indoor dust data monitoring is very important in hospital environments beside that other places can also be considered for monitoring like classrooms, cements factories, computer server rooms, petrochemical storage etc. In this paper, visible light communication system is proposed by Manchester encoding technique for electromagnetic interference (EMI)-free indoor dust monitoring. Important indoor environment information like dust concentration is transferred by visible light channel in wide range. An average voltage-tracking technique is utilized for robust light detection to eliminate ambient light and low-frequency noise. The incoming light is recognized by a photo diode and are simultaneously processed by a receiver micro-controller. We can monitor indoor air quality in real-time and can take necessary action according to the result.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.9A
• /
• pp.1290-1298
• /
• 2000

Turbo Code decoder is an iterate decoding technology, which extracts extrinsic information from the bit to be decoded by calculating both forward and backward metrics, and uses the information to the next decoding step Turbo Code shows excellent performance, approaching Shannon Limit at the view of BER, when the size of Interleaver is big and iterate decoding is run enough. But it has the problems which are increased complexity and delay and difficulty of real-time processing due to Interleaver and iterate decoding. In this paper, it is analyzed that MAP(maximum a posteriori) algorithm which is used as one of Turbo Code decoding, and the factor which determines its performance. MAP algorithm proceeds iterate decoding by determining soft decision value through the environment and transition probability between all adjacent bits and received symbols. Therefore, to improve the performance of MAP algorithm, the trust between adjacent received symbols must be ensured. However, MAP algorithm itself, can not do any action for ensuring so the conclusion is that it is needed more algorithm, so to decrease iterate decoding. Consequently, MAP algorithm and Turbo Code performance are analyzed in the nongaussian channel applying Robust equalization technique in order to input more trusted information into MAP algorithm for the received symbols.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2005.11a
• /
• pp.500-506
• /
• 2005

본 논문에서는 자가 생성 지도 학습 알고리즘을 이용한 운송 컨테이너 식별자 인식 시스템을 제안한다. 일반적으로 운송 컨테이너의 식별자들은 글자의 색이 검정색 또는 흰색으로 이루어져 있는 특정이 있다. 이러한 특성을 고려하여 원 컨테이너 영상에 대해 검은색과 흰색을 제외하고는 모든 부분을 잡음으로 처리하기 위해 퍼지 추론 방법을 이용하여 식별자 영역과 바탕영역을 구별한다. 식별자 영역으로 구분 된 영역은 그대로 두고, 바탕 영역으로 구분된 영역 은 전체 영상의 평균 픽셀 값으로 대체시킨다. 그리고 Sobel 마스크를 이용하여 에지를 검출하고, 추출된 에지를 이용하여 수직 블록과 수평 블록을 검출 하여 컨테이너의 식별자 영역을 추출하고 이진화한다. 이진화 된 식별자 영역에 대해 검정색의 빈도수를 이용하여 흰바탕과 민바탕을 구분하고 4 방향 윤곽선 추적 알고리즘을 적용하여 개별 식별자를 추출 한다. 개별 식별자 인식을 위해 자가 생성 지도 학습 알고리즘을 제안하여 개별 식별자 인식에 적용한다. 제안된 자가 생성 지도 학습 알고리즘은 입력층과 은닉층 사이의 구조를 ART-l을 개선하여 적용하고 은닉층과 출력층 사이에는 일반화된 델타 학습 방법과 Delta-bar-Delta 알고리즘을 적용하여 학습 및 인식 성능을 개선한다. 실제 80 개의 컨테이너 영상을 대상으로 실험한 결과, 제안된 식별자 추출 방법이 이전의 개별 추출 방법보다 추출률이 개선되었고 FCM 기반 자가 생성 지도 학습 알고리즘보다 제안된 자가 생성 지도 학습 알고리즘이 컨테이너 식별자의 학습 및 인식에 있어서 개선된 것을 확인하였다.색 문제를 해결하고자 하는 것이 연구의 목적이다. 정보추출은 사용자의 관심사에 적합한 문서들로부터 어떤 구체적인 사실이나 관계를 정확히 추출하는 작업을 가리킨다.앞으로 e-메일, 매신저, 전자결재, 지식관리시스템, 인터넷 방송 시스템의 기반 구조 역할을 할 수 있다. 현재 오픈웨어에 적용하기 위한 P2P 기반의 지능형 BPM(Business Process Management)에 관한 연구와 X인터넷 기술을 이용한 RIA (Rich Internet Application) 기반 웹인터페이스 연구를 진행하고 있다.태도와 유아의 창의성간에는 상관이 없는 것으로 나타났고, 일반 유아의 아버지 양육태도와 유아의 창의성간의 상관에서는 아버지 양육태도의 성취-비성취 요인에서와 창의성제목의 추상성요인에서 상관이 있는 것으로 나타났다. 따라서 창의성이 높은 아동의 아버지의 양육태도는 일반 유아의 아버지와 보다 더 애정적이며 자율성이 높지만 창의성이 높은 아동의 집단내에서 창의성에 특별한 영향을 더 미치는 아버지의 양육방식은 발견되지 않았다. 반면 일반 유아의 경우 아버지의 성취지향성이 낮을 때 자녀의 창의성을 향상시킬 수 있는 것으로 나타났다. 이상에서 자녀의 창의성을 향상시키는 중요한 양육차원은 애정성이나 비성취지향성으로 나타나고 있어 정서적인 측면의 지원인 것으로 밝혀졌다.징에서 나타나는 AD-SR맥락의 반성적 탐구가 자주 나타났다. 반성적 탐구 척도 두 그룹을 비교 했을 때 CON 상호작용의 특징이 낮게 나타나는 N그룹이 양적으로 그리고 내용적으로 더 의미 있는 반성적 탐구를 했다용을 지원하는 홈페이지를 만들어 자료

• Journal of Korea Society of Industrial Information Systems
• /
• v.13 no.2
• /
• pp.69-79
• /
• 2008

Due to popularization of the wireless Internet and mobile devices the infrastructure of the ubiquitous environment, where users can get information whatever they want anytime and anywhere, is created. Therefore, a variety of fields including the education studies methods for efficiency of information transmission using on-line and off-line contents. In this paper, we propose the Mixed Mobile Education system(MME) that improves educational efficiency using on-line and off-line contents on mobile devices. Because it is hard to input new data and cannot use similar off-line contents in systems used additional tags, the proposed system does not use additional tags but recognizes of-line contents as we extract feature points in the input image using the mobile camera. We use the Scale Invariant Feature Transform(SIFT) algorithm to extract feature points which are not affected by noise, color distortion, size and rotation in the input image captured by the low resolution camera. And we use the client-server architecture for solving the limited storage size of the mobile devices and for easily registration and modification of data. Experimental results show that compared with previous work, the proposed system has some advantages and disadvantages and that the proposed system has good efficiency on various environments.

• Journal of Digital Convergence
• /
• v.19 no.12
• /
• pp.347-352
• /
• 2021

In this paper, we propose a method for finding feature subsets that are effective for classification in an input dataset by using a multi-agent reinforcement learning method. In the field of machine learning, it is crucial to find features suitable for classification. A dataset may have numerous features; while some features may be effective for classification or prediction, others may have little or rather negative effects on results. In machine learning problems, feature selection for increasing classification or prediction accuracy is a critical problem. To solve this problem, we proposed a feature selection method based on reinforced learning. Each feature has one agent, which determines whether the feature is selected. After obtaining corresponding rewards for each feature that is selected, but not by the agents, the Q-value of each agent is updated by comparing the rewards. The reward comparison of the two subsets helps agents determine whether their actions were right. These processes are performed as many times as the number of episodes, and finally, features are selected. As a result of applying this method to the Wisconsin Breast Cancer, Spambase, Musk, and Colon Cancer datasets, accuracy improvements of 0.0385, 0.0904, 0.1252 and 0.2055 were shown, respectively, and finally, classification accuracies of 0.9789, 0.9311, 0.9691 and 0.9474 were achieved, respectively. It was proved that our proposed method could properly select features that were effective for classification and increase classification accuracy.

• Journal of Convergence for Information Technology
• /
• v.11 no.11
• /
• pp.57-65
• /
• 2021

We propose a novel method to detect abnormal data of specific symptoms using deep learning in air pollution measurement system. Existing methods generally detect abnomal data by classifying data showing unusual patterns different from the existing time series data. However, these approaches have limitations in detecting specific symptoms. In this paper, we use DeepLab V3+ model mainly used for foreground segmentation of images, whose structure has been changed to handle one-dimensional data. Instead of images, the model receives time-series data from multiple sensors and can detect data showing specific symptoms. In addition, we improve model's performance by reducing the complexity of noisy form time series data by using 'piecewise aggregation approximation'. Through the experimental results, it can be confirmed that anomaly data detection can be performed successfully.