• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.05a
• /
• pp.175-178
• /
• 2008

본 논문은 생체 신호들 중 데이터 획득이 간편한 심전도와 맥파를 실시간으로 취득하여 기계학습 기법인 SVM (Support Vector Machine)알고리즘과 클러스터링 기법인 k-NN (Nearest Neighbor)알고리즘을 적용한 인간의 감정을 분석하는 시스템에 대한 연구결과를 제시한다.

• Journal of Korea Multimedia Society
• /
• v.4 no.1
• /
• pp.46-55
• /
• 2001

In this paper, a new voice activity detection method estimating SNR of enhanced speech with extended spectral subtraction (ESS) is proposed. Voice activity detection is performed by putting an second Wiener filter behind an Wiener filter used in the ESS to estimate speech and noise power of output signal of first Wiener filter. The proposed voice activity detection method does not require many computational loads and performs well under severe input SNR. Boll's spectral substraction algorithm with proposed voice activity detection was compared to ESS under several noise environment having different time-frequency distributions. During speech and non-speech activity, performance of Boll's spectral substraction algorithm with proposed voice activity detection is superior to that of ESS.

• Journal of IKEEE
• /
• v.23 no.3
• /
• pp.978-983
• /
• 2019

Under the influence of Autonomous Driving and AI, it is important to accurately recognize and judge objects through cameras. In particular, since a method of recognizing an object using a camera can obtain a large amount of information visually compared to other methods, many image signal processing methods have been studied to extract an accurate image. In addition, a lot of research is being carried out to implementation about hardware. In this work, we compare the principles and characteristics of the sorting algorithms that are frequently used in image signal processing and summarize the performance evaluation. Based on this, we define an efficient algorithm when implemented in hardware among efficient sorting algorithms.

• The KIPS Transactions:PartB
• /
• v.19B no.1
• /
• pp.19-26
• /
• 2012

The rapid increase of information imposes new demands of content management. The purpose of automatic audio segmentation and classification is to meet the rising need for efficient content management. With this reason, this paper proposes a high-accuracy algorithm that segments audio signals and classifies them into different classes such as speech, music, silence, and environment sounds. The proposed algorithm utilizes support vector machine (SVM) to detect audio-cuts, which are boundaries between different kinds of sounds using the parameter sequence. We then extract feature vectors that are composed of statistical data and they are used as an input of fuzzy c-means (FCM) classifier to partition audio-segments into different classes. To evaluate segmentation and classification performance of the proposed SVM-FCM based algorithm, we consider precision and recall rates for segmentation and classification accuracy for classification. Furthermore, we compare the proposed algorithm with other methods including binary and FCM classifiers in terms of segmentation performance. Experimental results show that the proposed algorithm outperforms other methods in both precision and recall rates.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.6
• /
• pp.9-16
• /
• 2011

Due to the development and proliferation of ubiquitous technologies and services, various sensor network applications are being appeared on the stage. The needs for algorithms requiring sensor data fusion and complex signal processing with a high-performance processor such as a digital signal processor are also increased. However, it is difficult to use such processor for the low-power sensor network operating with a battery because of power consumption. This paper proposes a hybrid-type sensor module architecture supporting wakeup/sleep software framework for the wireless sensor node and shows the implemented sensor node platform and performances focused on the energy consumption and wakeup time.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.3
• /
• pp.1-6
• /
• 2003

It is difficult to detect and to track the moving targets like tanks and diesel vehicles due to the variety of terrain and moving of targets. It is possible to be happened the aliasing conditions as the difficulty of antenna deployment in the complex environment like the battle fields. In this paper, we study the problem of detecting and tracking of moving targets which are emitting wideband signals under severe spatial aliasing conditions because of the sparse arrays. We developed a direction of arrival(DOA) estimation algorithm based on subband MUSIC(Multiple Signal Classification) method which produces high-resolution estimation. In this algorithm, the true bearings are invariant regardless of changes of frequency bands while the aliased false bearings vary. As a result, the proposed algorithm overcomes the aliasing effects and improves the localization performance in sparse passive arrays.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.3
• /
• pp.203-208
• /
• 2010

In this paper, we convert underwater acoustic signal made by sonar system into digital image. We propose the algorithm that detects target candidate and emphasizes information of target introducing image processing technique for the digital image. The process detecting underwater target estimates background noise in underwater acoustic signal changing irregularly, recomposes it. and eliminates background from original image. Therefore, it generates initial target group. Also, it generates weighted map through proceeding doppler information, ensures information for target candidate through filtering using weighted map for image eliminated background noise, and decides the target candidate area in the single frame. In this paper, we verified that proposed algorithm almost had eliminated the noise generated irregularly in underwater acoustic signal made by simulation, targets had been displayed more surely in the image of underwater acoustic signal through filtering and process of target detection.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.15 no.9
• /
• pp.764-774
• /
• 1990

In this paper, make a study on comparison of adaptive filters for predictor characteristics that transversal, lattice, and joint process lattice filter is using the LMS algorithm that is simple structure and pracotical application is easy. The theoical background and structure of each adaptive filters exhibit for practical design. Adaptive convergence condition for optimal weight vector and optimal reflection coefficient make clear, and it is also shown through computer simulation. The error signals and noise characteristics of these filters make a comparative study. In view of the results, joint process lattice filter is shown that most superior characteristic in these adaptie filters.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2001.06a
• /
• pp.69-72
• /
• 2001

High-level synthesis generates a structural design that implements the given behavior and satisfies design constraints for area, performance, power consumption, packaging, testing and other criteria. Thus, high-level synthesis generates that register-transfer(RT) level structure from algorithm level description. High-level syntehsis consist of compiling, partitioning, scheduling This paper we study the partitioning process, and analysis the min-cut algorithm and simulated annealing algorithm.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.2
• /
• pp.15-22
• /
• 2002

In this paper, we proposed the face recognition algorithm which can be used for a security system. The distance and angle of the face features are used in the conventional method, but the proposed method used the genetic algorithm which selects image to best fit the input image in the database images. The performance of proposed algorithm is verified through the simulation. The results of proposed method show good performance.