• 말소리와 음성과학
• /
• 제1권2호
• /
• pp.15-22
• /
• 2009

Prominence of speech, which is often called 'accent,' affects the fluency of speaking American English greatly. In this paper, we present an accurate prominence detection method that can be utilized in computer-aided language learning (CALL) systems. We employed pitch movement, overall syllable energy, 300-2200 Hz band energy, syllable duration, and spectral and temporal correlation as features to model the prominence of speech. After the features for vowel syllables of speech were extracted, prominent syllables were classified by SVM (Support Vector Machine). To further improve accuracy, the differences in characteristics of neighboring syllables were added as additional features. We also applied a speech recognizer to extract more precise syllable boundaries. The performance of our prominence detector was measured based on the Intonational Variation in English (IViE) speech corpus. We obtained 84.9% accuracy which is about 10% higher than previous research.

• 제어로봇시스템학회논문지
• /
• 제16권7호
• /
• pp.625-631
• /
• 2010

This paper proposes lane recognition algorithm using lane prominence technique to extract lane candidate. The lane prominence technique is combined with embossing effect, lane thickness check, and lane extraction using mask. The proposed lane recognition algorithm consists of preprocessing, lane candidate extraction and lane recognition. First, preprocessing is executed, which includes gray image acquisition, inverse perspective transform and gaussian blur. Second, lane candidate is extracted by using lane prominence technique. Finally, lane is recognized by using hough transform and least square method. To evaluate the proposed lane recognition algorithm, this algorithm was applied to the detection of lanes in the rainy and night day. The experiment results showed that the proposed algorithm can recognize lane in various environment. It means that the algorithm can be applied to lane recognition to drive unmanned vehicles.

• 대한음성학회지:말소리
• /
• 제60호
• /
• pp.97-108
• /
• 2006

The purpose of this study is to observe how Korean listeners detect a target phoneme with 'Focus' represented by prosodic prominence and question-induced semantic emphasis, and with intonational manipulation. According to the automated phoneme detection task using E-Prime, the Korean listeners detected phoneme targets more rapidly when the target-bearing words were in prominence position and in question-induced position. However, the presence of question-induced semantic emphasis reduced the prominence effect, so two effects interacted: when question-induced emphasis were primarily given as a cue, prominence which was given as secondary cue affected less to fine the new information. Besides, the intonation with manipulation was responded to faster than without manipulation.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2006년도 춘계 학술대회 발표논문집
• /
• pp.71-74
• /
• 2006

The purpose of this study is to observe how Korean listeners detect a target phoneme with 'Focus' represented by prosodic prominence and question-induced semantic emphasis. According to the automated phoneme detection task using E-Prime, Korean listeners detected phoneme targets more rapidly when the target-bearing words were in prominence position and in question-induced position. However, when phoneme targets were in prominence position, response time was much faster than in question-induced position. The results suggest that the prosodic prominence which is explicit method of focus representation be more effective than question-inducing, implicit method of it, in phoneme detecting.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권3호
• /
• pp.1173-1192
• /
• 2015

The Support Vector Data Description (SVDD) has achieved great success in anomaly detection, directly finding the optimal ball with a minimal radius and center, which contains most of the target data. The SVDD has some limited classification capability, because the hyper-sphere, even in feature space, can express only a limited region of the target class. This paper presents an anomaly detection algorithm for mitigating the limitations of the conventional SVDD by finding the minimum volume enclosing ellipsoid in the feature space. To evaluate the performance of the proposed approach, we tested it with intrusion detection applications. Experimental results show the prominence of the proposed approach for anomaly detection compared with the standard SVDD.

• Nuclear Engineering and Technology
• /
• 제55권1호
• /
• pp.100-108
• /
• 2023

In this study, a neural network model inspired by a one-dimensional convolution U-net is developed to automatically accelerate edge localized mode (ELM) detection from big diagnostic data of fusion devices and increase the detection accuracy regardless of the hyperparameter setting. This model recognizes the input signal patterns and overcomes the problems of existing detection algorithms, such as the prominence algorithm and those of differential methods with high sensitivity for the threshold and signal intensity. To train the model, 10 sets of discharge radiation data from the KSTAR are used and sliced into 11091 inputs of length 12 ms, of which 20% are used for validation. According to the receiver operating characteristic curves, our model shows a positive prediction rate and a true prediction rate of approximately 90% each, which is comparable to the best detection performance afforded by other algorithms using their optimized hyperparameters. The accurate and automatic ELM-burst detection methodology used in our model can be beneficial for determining plasma properties, such as the ELM frequency from big data measured in multiple experiments using machines from the KSTAR device and ITER. Additionally, it is applicable to feature detection in the time-series data of other engineering fields.

• 천문학회보
• /
• 제37권1호
• /
• pp.97-97
• /
• 2012

Hinode/XRT has observed coronal mass ejections (CMEs) since it launched on Sep. 2006. Observing programs of Hinode/XRT, called 'CME watch', perform several binned observations to obtain large FOV observations with long exposure time that allows the detection of faint CME plasmas in high temperatures. Using those observations, we determine the upper limit to the mass of hot CME plasma using emission measure by assuming the observed plasma structure. In some events, an associated prominence eruption and CME plasma were observed in EUV observations as absorption or emission features. The absorption feature provides the lower limit to the cold mass while the emission feature provides the upper limit to the mass of observed CME plasma in X-ray and EUV passbands. In addition, some events were observed by coronagraph observations (SOHO/LASCO, STEREO/COR1) that allow the determination of total CME mass. However, some events were not observed by the coronagraphs possibly because of low density of the CME plasma. We present the mass constraints of CME plasma and associated prominence as determined by emission and absorption in EUV and X-ray passbands, then compare this mass to the total CME mass as derived from coronagraphs.

• 한국컴퓨터정보학회논문지
• /
• 제28권10호
• /
• pp.17-25
• /
• 2023

본 논문에서는 의류 디자인 도면 이미지의 글자 검출을 위한 경량화된 딥러닝 네트워크를 제안하였다. 최근 의류 디자인 산업에서 Digital Transformation의 중요성이 대두되면서, 디지털 도구를 활용한 의류 디자인 도면 작성이 강조되고 있으며, 디지털화된 의류 디자인 도면의 활용 가능성을 고려할 때, 도면에서 글자 검출과 인식이 중요한 첫 단계로 간주된다. 이 연구에서는 기존의 글자 검출 딥러닝 모델을 기반으로 의류 도면 이미지의 특수성을 고려하여 경량화된 네트워크를 설계하였으며, 별도로 수집한 의류 도면 데이터 셋을 추가하여 딥러닝 모델을 학습시켰다. 실험 결과, 제안한 딥러닝 모델은 의류 도면 이미지에서 기존 글자 검출 모델보다 약 20% 높은 성능을 보였다. 따라서 이 논문은 딥러닝 모델의 최적화와 특수한 글자 정보 검출 등의 연구를 통해 의류 디자인 분야에서의 Digital Transformation에 기여할 것으로 기대한다.

• The Korean Journal of Physiology and Pharmacology
• /
• 제21권5호
• /
• pp.555-563
• /
• 2017

Electrical stimulation through retinal prosthesis elicits both short and long-latency retinal ganglion cell (RGC) spikes. Because the short-latency RGC spike is usually obscured by electrical stimulus artifact, it is very important to isolate spike from stimulus artifact. Previously, we showed that topographic prominence (TP) discriminator based algorithm is valid and useful for artifact subtraction. In this study, we compared the performance of forward backward (FB) filter only vs. TP-adopted FB filter for artifact subtraction. From the extracted retinae of rd1 mice, we recorded RGC spikes with $8{\times}8$ multielectrode array (MEA). The recorded signals were classified into four groups by distances between the stimulation and recording electrodes on MEA (200-400, 400-600, 600-800, $800-1000{\mu}m$). Fifty cathodic phase-$1^{st}$ biphasic current pulses (duration $500{\mu}s$, intensity 5, 10, 20, 30, 40, 50, $60{\mu}A$) were applied at every 1 sec. We compared false positive error and false negative error in FB filter and TP-adopted FB filter. By implementing TP-adopted FB filter, short-latency spike can be detected better regarding sensitivity and specificity for detecting spikes regardless of the strength of stimulus and the distance between stimulus and recording electrodes.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.237-245
• /
• 2022

The prominence of IoTs (Internet of Things) and exponential advancement of computer networks has resulted in massive essential applications. Recognizing various cyber-attacks or anomalies in networks and establishing effective intrusion recognition systems are becoming increasingly vital to current security. MLTs (Machine Learning Techniques) can be developed for such data-driven intelligent recognition systems. Researchers have employed a TFDNNs (Tensor Flow Deep Neural Networks) and DCNNs (Deep Convolution Neural Networks) to recognize pirated software and malwares efficiently. However, tuning the amount of neurons in multiple layers with activation functions leads to learning error rates, degrading classifier's reliability. HTFDNNs ( Hybrid tensor flow DNNs) and MRNs (Modified Residual Networks) or Resnet CNNs were presented to recognize software piracy and malwares. This study proposes HTFDNNs to identify stolen software starting with plagiarized source codes. This work uses Tokens and weights for filtering noises while focusing on token's for identifying source code thefts. DLTs (Deep learning techniques) are then used to detect plagiarized sources. Data from Google Code Jam is used for finding software piracy. MRNs visualize colour images for identifying harms in networks using IoTs. Malware samples of Maling dataset is used for tests in this work.