• 한국멀티미디어학회논문지
• /
• 제17권3호
• /
• pp.312-323
• /
• 2014

음성구간 검출은 음성과 잡음이 섞인 신호에서 음성과 잡음이 섞인 신호에서 음성구간을 찾는 과정으로 잡음제거나 음성 향상을 위한 신호처리에서 매우 중요한 과정이다. 지금까지 음성구간 검출에 관한 많은 연구가 있었지만, 낮은 신호 대 잡음비 환경에서 문장형태의 음성신호에 대해서는 좋은 성능을 보이지 못하였다. 본 논문에서는 신호의 엔트로피를 이용한 초기 VAD과정을 거친 후, 퍼지 소속도 천이 c-means 클러스터링 방법을 이용해 주 VAD과정을 거치는 새로운 VAD알고리즘을 제안한다. 제안한 알고리즘의 성능을 비교 평가하기 위하여 백색잡음의 다양한 신호 대 잡음비 환경에서 실험을 수행하였으며 실험결과, 제안한 방법의 우수한 성능을 확인할 수 있었다.

• 한국멀티미디어학회논문지
• /
• 제17권3호
• /
• pp.294-299
• /
• 2014

본 논문에서는 일반화된 정규-라플라스(generalized normal-Laplace) 분포 기반의 음성 검출기(voice activity detection) 알고리즘을 제안한다. 제안된 알고리즘은, 잡음 섞인 음성 신호의 확률밀도함수를 일반화된 정규-라플라스 분포로 표현한 다음, 일반화된 정규-라플라스 분포의 음성과 잡음의 분산을 고차 모멘트(higher order moments)를 이용하여 추정한다. 제안된 알고리즘은 다양한 조건의 잡음 환경에서 기존의 음성 검출기들과 비교하였으며 향상된 성능을 보였다.

• ETRI Journal
• /
• 제31권4호
• /
• pp.451-453
• /
• 2009

This letter proposes the use of vowel sound detection for voice activity detection. Vowels have distinctive spectral peaks. These are likely to remain higher than their surroundings even after severe corruption. Therefore, by developing a method of detecting the spectral peaks of vowel sounds in corrupted signals, voice activity can be detected as well even in low signal-to-noise ratio (SNR) conditions. Experimental results indicate that the proposed algorithm performs reliably under various noise and low SNR conditions. This method is suitable for mobile environments where the characteristics of noise may not be known in advance.

• International Journal of Computer Science & Network Security
• /
• 제21권4호
• /
• pp.131-139
• /
• 2021

In current time, anomaly detection is the primary concern of the administrative authorities. Suspicious activity identification is shifting from a human operator to a machine-assisted monitoring in order to assist the human operator and react to an unexpected incident quickly. These automatic surveillance systems face many challenges due to the intrinsic complex characteristics of video sequences and foreground human motion patterns. In this paper, we propose a novel approach to detect anomalous human activity using a hybrid approach of statistical model and Genetic Programming. The feature-set of local motion patterns is generated by a statistical model from the video data in an unsupervised way. This features set is inserted to an enhanced Genetic Programming based classifier to classify normal and abnormal patterns. The experiments are performed using publicly available benchmark datasets under different real-life scenarios. Results show that the proposed methodology is capable to detect and locate the anomalous activity in the real time. The accuracy of the proposed scheme exceeds those of the existing state of the art in term of anomalous activity detection.

• BMB Reports
• /
• 제48권6호
• /
• pp.313-318
• /
• 2015

Matrix metalloproteinases (MMPs) are zinc-dependent endopeptidases that degrade the extracellular matrix (ECM) and regulate the extracellular microenvironment. Despite the significant role that MMP activity plays in cell-cell and cell-ECM interactions, migration, and differentiation, analyses of MMPs in vitro and in vivo have relied upon their abundance using conventional immunoassays, rather than their enzymatic activities. To resolve this issue, diverse nanoprobes have emerged and proven useful as effective activity-based detection tools. Here, we review the recent advances in luminescent nanoprobes and their applications in in vitro diagnosis and in vivo imaging of MMP activity. Nanoprobes with the purpose of sensing MMP activity consist of recognition and detection units, which include MMP-specific substrates and luminescent (fluorescent or bioluminescent) nanoparticles, respectively. With further research into improvement of the optical performance, it is anticipated that luminescent nanoprobes will have great potential for the study of the functional roles of proteases in cancer biology and nanomedicine. [BMB Reports 2015; 48(6): 313-318]

• ETRI Journal
• /
• 제34권2호
• /
• pp.184-189
• /
• 2012

In this paper, we propose a novel approach to statistical model-based voice activity detection (VAD) that incorporates a second-order conditional maximum a posteriori (CMAP) criterion. As a technical improvement for the first-order CMAP criterion in [1], we consider both the current observation and the voice activity decision in the previous two frames to take full consideration of the interframe correlation of voice activity. This is clearly different from the previous approach [1] in that we employ the voice activity decisions in the second-order (previous two frames) CMAP, which has quadruple thresholds with an additional degree of freedom, rather than the first-order (previous single frame). Also, a soft-decision scheme is incorporated, resulting in time-varying thresholds for further performance improvement. Experimental results show that the proposed algorithm outperforms the conventional CMAP-based VAD technique under various experimental conditions.

• Journal of Communications and Networks
• /
• 제15권3호
• /
• pp.283-291
• /
• 2013

In this paper, we propose new multiuser detectors (MUDs) based on compressed sensing approaches for the large-scale multiple antenna systems equipped with dozens of low-power antennas. We consider the scenarios where the number of receiver antennas is smaller than the total number of users, but the number of active users is relatively small. This prior information motivates sparsity-embracing MUDs such as sparsity-embracing linear/nonlinear MUDs where the detection of active users and their symbol detection are employed. In addition, sparsity-embracing MUDs with maximum a posteriori probability criterion (MAP-MUDs) are presented. They jointly detect active users and their symbols by exploiting the probability of user activity, and it can be solved efficiently by introducing convex relaxing senses. Furthermore, it is shown that sparsity-embracing MUDs exploiting common users' activity across multiple symbols, i.e., frame-by-frame, can be considered to improve performance. Also, in multiple multiple-input and multiple-output networks with aggressive frequency reuse, we propose the interference cancellation strategy for the proposed sparsity-embracing MUDs. That first cancels out the interference induced by adjacent networks and then recovers the desired users' information by exploiting the low user activity. In simulation studies for binary phase shift keying modulation, numerical evidences establish the effectiveness of our proposed MUDs exploiting low user activity, as compared with the conventional MUD.

• 한국통신학회논문지
• /
• 제22권6호
• /
• pp.1302-1310
• /
• 1997

In this paper, we propose a dynamic code allocation strategy using voice activity detection and evaluate the performance of a dynamic code allocation strategy using voice activeity detection in DS-CDMA system. Proposed method allocates code to mobile terminal according to the residual capacity computed by SIR in the base station. In hot spot traffic loading cell, we find that the performance of proposed method is better than that of a fixed code assignment strategy using voice activity detection. Also, we find that the proposed method provide much improvement in blocking probability against the dynamic code assignment strategy withoug voice activity detection.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2008년도 춘계종합학술대회 A
• /
• pp.666-669
• /
• 2008

A number of intrusion detection systems have been developed to detect intrusive activity on individual hosts and networks. The systems developed rely almost exclusively on a software approach to intrusion detection analysis and response. In addition, the network systems developed apply a centralized approach to the detection of intrusive activity. The problems introduced by this approach are twofold. First the centralization of these functions becomes untenable as the size of the network increases.

• Journal of Information Processing Systems
• /
• 제14권1호
• /
• pp.150-161
• /
• 2018

We propose a novel deep neural network model for detecting human activities in untrimmed videos. The process of human activity detection in a video involves two steps: a step to extract features that are effective in recognizing human activities in a long untrimmed video, followed by a step to detect human activities from those extracted features. To extract the rich features from video segments that could express unique patterns for each activity, we employ two different convolutional neural network models, C3D and I-ResNet. For detecting human activities from the sequence of extracted feature vectors, we use BLSTM, a bi-directional recurrent neural network model. By conducting experiments with ActivityNet 200, a large-scale benchmark dataset, we show the high performance of the proposed DeepAct model.