• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.7-9
• /
• 2021

본 논문은 Detectron2 [1]에서 지원하는 객체 검출 임무 수행 네트워크의 과정 중에서 추출한 피쳐 맵을 신경망 기반으로 압축하는 방법을 제안한다. 이를 위해, 신경 망 기반 영상 압축을 지원하는 공개 소프트웨어인 CompressAI [2] 모델 중 하나인 bmshj2018-hyperprior 의 압축 네트워크를 활용하여 임무 수행 네트워크의 과정 중 스탬 레이어(stem layer)에서 추출된 피쳐 맵을 압축하도록 학습시켰다. 또한, 압축 네트워크의 입력 피쳐 맵의 너비와 높이 크기가 64 의 배수가 되도록 객체 검출 네트워크의 입력 영상 보간 값을 조정하는 방법도 제안한다. 제안하는 신경망 기반 피쳐 맵 압축 방법은 피쳐 맵을 최근 표준이 완료된 차세대 압축 표준 방법인 VVC(Versatile Video Coding, [3])로 압축한 결과에 비해 큰 성능 향상을 보이고, VCM 앵커와 유사한 성능을 보인다.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.7
• /
• pp.23-35
• /
• 2013

This paper proposes an effective technique that is used to automatically extract feature vectors from vibration signals for fault classification systems. Conventional mel-frequency cepstral coefficients (MFCCs) are sensitive to noise of vibration signals, degrading classification accuracy. To solve this problem, this paper proposes spectral envelope cepstral coefficients (SECC) analysis, where a 4-step filter bank based on spectral envelopes of vibration signals is used: (1) a linear predictive coding (LPC) algorithm is used to specify spectral envelopes of all faulty vibration signals, (2) all envelopes are averaged to get general spectral shape, (3) a gradient descent method is used to find extremes of the average envelope and its frequencies, (4) a non-overlapped filter is used to have centers calculated from distances between valley frequencies of the envelope. This 4-step filter bank is then used in cepstral coefficients computation to extract feature vectors. Finally, a multi-layer support vector machine (MLSVM) with various sigma values uses these special parameters to identify faulty types of induction motors. Experimental results indicate that the proposed extraction method outperforms other feature extraction algorithms, yielding more than about 99.65% of classification accuracy.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.1
• /
• pp.29-37
• /
• 2005

This paper proposes an automatic genre classification system for Korean traditional music. The Proposed system accepts and classifies queried input music as one of the six musical genres such as Royal Shrine Music, Classcal Chamber Music, Folk Song, Folk Music, Buddhist Music, Shamanist Music based on music contents. In general, content-based music genre classification consists of two stages - music feature vector extraction and Pattern classification. For feature extraction. the system extracts 58 dimensional feature vectors including spectral centroid, spectral rolloff and spectral flux based on STFT and also the coefficient domain features such as LPC, MFCC, and then these features are further optimized using SFS method. For Pattern or genre classification, k-NN, Gaussian, GMM and SVM algorithms are considered. In addition, the proposed system adopts MFC method to settle down the uncertainty problem of the system performance due to the different query Patterns (or portions). From the experimental results. we verify the successful genre classification performance over $97{\%}$ for both the k-NN and SVM classifier, however SVM classifier provides almost three times faster classification performance than the k-NN.

• Journal of Korea Spatial Information System Society
• /
• v.6 no.1 s.11
• /
• pp.101-117
• /
• 2004

Standards are essential to facilitate the efficient use of GIS data. International Standards such as ISO TC211's 19100 series and various technical specifications from OpenGIS Consortium are some of the examples of efforts to maintain the interoperability among GIS applications. Marine GIS is no exception to this rule and in this context. developing standards for marine GIS is also in urgent needs. Using the same meaning and definition for the features commonly found in marine GIS applications is one of the ways to increase the interoperability among systems. One of the key requirements for maintaining the standard meanings for features is to build a common feature catalogue. This paper examines the concept of feature catalogue and describe the ways in which the feature catalogue can be organized. To identify the common features found in various marine GIS applications, a comprehensive search has been made to collect and analyze the features used in various applications. To maintain the interoperability with the National GIS (NGIS) system, the features used in various NGIS applications have been analyzed as well. The result of these analyses are used to create a comprehensive list of common features for marine GIS. This paper then explains the common feature catalogue for marine GIS and the provides the appropriate classification and coding systems for the common features. In addition, a registration tool for registering the common features into the standard registry has been developed in this study. This Web-based tool can be used to input features into the feature catalogue by various applications and also to maintain a standard-compliant feature catalogue by standard agencies.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.10
• /
• pp.887-895
• /
• 2014

Drowsy driving is a large proportion of the total car accidents. For this reason, drowsiness detection and warning system for drivers has recently become a very important issue. Monitoring physiological signals provides the possibility of detecting features of drowsiness and fatigue of drivers. Many researches have been published that to measure electroencephalogram(EEG) signals is the effective way in order to be aware of fatigue and drowsiness of drivers. The aim of this study is to extract drowsiness-related features from a set of EEG signals and to classify the features into three states: alertness, transition, and drowsiness. This paper proposes a drowsiness detection system using errors-in-variables(EIV) for extraction of feature vectors and multilayer perceptron (MLP) for classification. The proposed method evaluates robustness for noise and compares to the previous one using linear predictive coding (LPC) combined with MLP. From evaluation results, we conclude that the proposed scheme outperforms the previous one in the low signal-to-noise ratio regime.

• The Journal of the Korea Contents Association
• /
• v.12 no.4
• /
• pp.10-19
• /
• 2012

Seamless streaming of multimedia content that ensures Quality of Service over heterogeneous networks has been a desire for many multimedia services, for which the multimedia contents should be adapted to usage environments such as network characteristics, terminal capabilities, and user preferences. Scalability in video coding is a good feature to meet the requirement of heterogeneous networks. In this paper, we propose a dynamic adaptation scheme of H.264/AVC SVC bit-stream using the MPEG-21 Digital Item Adaptation (DIA) tool. MPEG-21 DIA framework provides systematic solutions in choosing an adaptation operation to given conditions and supports interoperable video adaptation. The experiment results show that the proposed adaptation scheme provides QoS-enabled delivery and consumption of SVC with time-varying constraints of network, terminal, and user preference, in a robust and efficient way. In particular, the proposed adaptation scheme is proved to work well with very low delay under the condition that the variation rate of the given network bandwidth is upto 62%.

• Journal of Broadcast Engineering
• /
• v.11 no.4 s.33
• /
• pp.458-470
• /
• 2006

This paper describes issues and consideration on authoring of interactive multi-view visual content based on MPEG-4. The issues include types of multi-view visual content; scene composition for rendering; functionalities for user-interaction; and multi-view visual content file format. The MPEG-4 standard, which aims to provide an object based audiovisual coding tool, has been developed to address the emerging needs from communications, interactive broadcasting as well as from mixed service models resulting from technological convergence. Due to the feature of object based coding, the use of MPEG-4 can resolve the format diversity problem of multi-view visual contents while providing high interactivity to users. Throughout this paper, we will present which issues need to be determined and how they can be realized by means of MPEG-4 Systems.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.5 no.2
• /
• pp.269-279
• /
• 1998

In nursing research that the data is collected through clinical observation, analysis of clinical recording or coding of interpersonal interaction in clinical areas, testing and reporting interrater reliability is very important to assure reliable results. Procedures for interrater reliability in these studies should follow two steps. The first step is to determine unitizing reliability, which is defined as consistency in the identification of same data elements in the record by two or more raters reviewing the same record. Unitizing reliability have been rarely reported in previous studies. Unitizing reliability should be tested before progressing to the next step as precondition. Next step is to determine interpretive reliability. Cohen's kappa is a preferable method of calculating the extent of agreement between observer or judges because it provides beyond-chance agreement. Despite its usefulness, kappa can sometimes present paradoxical conclusions and can be difficult to interpret. These difficulties result from the feature of kappa which is affected in complex ways by the presence of bias between observers and by true prevalence of certain categories. Therefore, percentage agreement should be reported with kappa for adequate interpretation of kappa. The presence of bias should be assessed using the bias index and the effect of prevalence should be assessed using the prevalence index. Researchers have been reported only global reliability reflecting the extent to which coders can consistently use the whole coding system across all categories. Category-by-category reliability also need to be reported to inform the possibility that some categories are harder to use than others.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.12
• /
• pp.3056-3068
• /
• 1996

This papre presents the RDM algorithm for composition of bit. After this, we propose a digital signature scheme for facsimile document using RDM algorithm. We modify the even-odd feature in distance of changing pel between coding line and multiple reference line which have been scanned before, and run-length in coding line. The time to take in signature is reduced by spreading of signature. Non-repudiation in origin, the 3rd condition of digital signature is realized by proposed digital signature scheme. The transmitter embeds the signature secretly and tensfers it, and the receiver makes a check of any forgery on the signature and the document. This scheme is compatible with the ITU-T.4(G3 or G4 facsimile standard). The total amount of data transmitted and the quality of image are about the same to that of the original document, thus a third party does not notics signature embeded on the document.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.4
• /
• pp.491-508
• /
• 2010

In peer-to-peer (P2P) on-demand streaming networks, the alleviation of server load depends on reciprocal stream sharing among peers. In general, on-demand video services enable clients to watch videos from beginning to end. As long as clients are able to buffer the initial part of the video they are watching, on-demand service can provide access to the video to the next clients who request to watch it. Therefore, the key challenge is how to keep the initial part of a video in a peer's buffer for as long as possible, and thus maximize the availability of a video for stream relay. In addition, to address the issues of delivering data on lossy network and providing scalable quality of services for clients, the adoption of multiple description coding (MDC) has been proven as a feasible resolution by much research work. In this paper, we propose a novel caching scheme for P2P on-demand streaming, called Dynamic Buffering. The proposed Dynamic Buffering relies on the feature of MDC to gradually reduce the number of cached descriptions held in a client's buffers, once the buffer is full. Preserving as many initial parts of descriptions in the buffer as possible, instead of losing them all at one time, effectively extends peers’ service time. In addition, this study proposes a description distribution balancing scheme to further improve the use of resources. Simulation experiments show that Dynamic Buffering can make efficient use of cache space, reduce server bandwidth consumption, and increase the number of peers being served.