• Phonetics and Speech Sciences
• /
• v.7 no.1
• /
• pp.89-95
• /
• 2015

We explored Dutch listeners' perception of Korean three-way contrast of fortis, lenis, and aspirated stops. The three Korean stops are all voiceless word-initially, whereas Dutch distinguishes between voiced and voiceless stops, so Korean voiceless stops were expected to be difficult for the Dutch listeners. Among the three Korean stops, fortis stops are phonetically most similar to Dutch voiceless stops, thus they were expected to be the easiest to distinguish for the Dutch listeners. Dutch and Korean listeners carried out a discrimination task using three crucial comparisons, i.e., fortis-lenis, fortis-aspirated, and lenis-aspirated stops. Results showed that discrimination between lenis and aspirated stops was the most difficult among the three comparisons for both Dutch and Korean listeners. As expected, Dutch listeners discriminated fortis from the other stops relatively accurately. It seems likely that Dutch listeners relied heavily on VOT but less on F0 when discriminating between the three Korean stops.

• Phonetics and Speech Sciences
• /
• v.6 no.4
• /
• pp.47-52
• /
• 2014

This study investigated how the degree of attention modulates English learners' perception of Korean stop contrasts. The contributions of VOT and F0 in perceiving Korean stops were examined while availability of attentional resources was manipulated using a dual-task paradigm. Results demonstrated the attentional modulation in the use of VOT, but not in F0: under less attention, the contribution of VOT to the perception of aspirated stops decreased, whereas that of lenis stops increased, which suggests more native-like performance. This implies that the role of attention in perceiving non-native contrasts might differ depending on how equivalent the acoustic and perceptual cues are between L1 and target L2 contrasts.

• ETRI Journal
• /
• v.43 no.6
• /
• pp.1004-1012
• /
• 2021

The collaboration productively interacting between multi-agents has become an emerging issue in real-world applications. In reinforcement learning, multi-agent environments present challenges beyond tractable issues in single-agent settings. This collaborative environment has the following highly complex attributes: sparse rewards for task completion, limited communications between each other, and only partial observations. In particular, adjustments in an agent's action policy result in a nonstationary environment from the other agent's perspective, which causes high variance in the learned policies and prevents the direct use of reinforcement learning approaches. Unexpected social loafing caused by high dispersion makes it difficult for all agents to succeed in collaborative tasks. Therefore, we address a paradox caused by the social loafing to significantly reduce total returns after a certain timestep of multi-agent reinforcement learning. We further demonstrate that the collaborative paradox in multi-agent environments can be avoided by our proposed effective early stop method leveraging a metric for social loafing.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.203-214
• /
• 2023

The Korea Customs Service is efficiently handling business with an electronic customs system that can effectively handle one-stop business. This is the case and a more effective method is needed. Import and export require HS Code (Harmonized System Code) for classification and tax rate application for all goods, and item classification that classifies the HS Code is a highly difficult task that requires specialized knowledge and experience and is an important part of customs clearance procedures. Therefore, this study uses various types of data information such as product name, product description, and product image in the item classification request form to learn and develop a deep learning model to reflect information well based on Multimodal representation learning. It is expected to reduce the burden of customs duties by classifying and recommending HS Codes and help with customs procedures by promptly classifying items.

• Phonetics and Speech Sciences
• /
• v.12 no.4
• /
• pp.1-8
• /
• 2020

Traditionally it has been understood that the aspirated and lenis stops in Seoul Korean are distinguished primarily by voice onset time (VOT) and secondarily by other cues such as the fundamental frequency (F0) of the following vowel. However, recent studies on stop production have shown that the aspirated and lenis stops are currently merging in VOT and that they are now differentiated primarily by F0. In the present study, we examined whether the currently reported change in the production domain would be also found in the perception domain. To this end, an auditory identification task was conducted using speech materials of varying VOT and F0 values with young and older male and female Seoul listeners. Results revealed that all listener groups used both VOT and F0 to distinguish the lenis vs. aspirated stops but they used the F0 cue more reliably than the VOT cue in discriminating the stop contrast. The effects of gender and age were found only in the VOT cue (i.e., not in the F0 cue), with the greatest VOT cue weight in older males and the smallest in young females, which is in line with recent production studies.

• Speech Sciences
• /
• v.12 no.3
• /
• pp.139-151
• /
• 2005

Previous studies have shown that Korean students have difficulty identifying some English consonants which are not in the Korean sound inventory. The aim of this study was to examine the accuracy rate of English consonants correctly identified by 130 college students in order to find out which English consonants were difficult for the students to perceive. The subject's task was to identify one of the minimal pairs played in a quiet laboratory classroom. 100 minimal pairs consisted of syllables with various onsets or codas: stops, fricatives, affricates, liquids and nasals. Results were as follows: First, the average score of the English major group was significantly higher than that of the non-English major group. Second, there was a similar distribution in the rank order of minimal pairs sorted by the accuracy rate between the two groups. Third, the accuracy rate systematically decreased as each score range decreased. Fourth, the students showed higher accuracy in the perception of liquids than that of the stop-fricative contrast. Fifth, the accuracy score in onset position was higher than in coda position. Finally, the students still had problem telling voiced consonants from voiceless ones, especially in coda position. It would be desirable to extend the present research to middle or high school students to fundamentally resolve those listening problems.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.32 no.2
• /
• pp.45-56
• /
• 2009

The use of national R&D reports becomes a difficult task due to the different level of service being provided and the different way used for its construction by the institute in management. One-stop service of its contents is impossible and there is a lack of specialized service such as a system to satisfy the various needs of the researchers. This study analyzes the laws related to the national R&D reports and the evaluation system of the R&D outputs for the design and construction of the DB and system for the management of the national R&D reports. We also perform an analysis of the economic effect of the system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.131-134
• /
• 2013

최근 클라우드 컴퓨팅의 발전과 상업적인 성공과 함께 클라우드 자원의 이용률을 최대로 유지하면서 에너지를 효율적으로 사용하기 위한 연구에 대한 관심이 커지고 있다. 자원의 사용률이 최대로 높아지게 되면 에너지 소비량이 급격하게 증가하여 많은 에너지를 사용하게 되므로 자원의 사용율과 에너지 사용은 트레이드오프 관계를 가지게 된다. 따라서 본 논문에서는 자원의 최대 사용 및 효율적인 에너지 사용을 위해 에너지 소비가 최적이 되는 자원 이용률의 임계값을 찾기 위한 연구를 수행하였다. 실험을 위해 자원 중 가장 많은 에너지를 소비하는 CPU를 이용하였고, 전력 측정을 위해 KEM2500 전력계와 ThrottleStop_500 프로그램을 사용하였다. 실험 결과 CPU 사용률이 약 90%일 때 에너지 사용량이 급격하게 증가하였으며, 기존의 평균 자원 이용률과 비교했을 때 12.3% 정도의 전기량이 더 소모됨을 확인하였다. 따라서 클라우드 컴퓨팅에서 CPU 자원의 이용률이 90%일 때 에너지가 최적이라고 할 수 있다.

• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.842-857
• /
• 2023

Currently, most sentiment classification models on microblogging platforms analyze sentence parts of speech and emoticons without comprehending users' emotional inclinations and grasping moral nuances. This study proposes a hybrid sentiment analysis model. Given the distinct nature of microblog comments, the model employs a combined stop-word list and word2vec for word vectorization. To mitigate local information loss, the TextCNN model, devoid of pooling layers, is employed for local feature extraction, while BiLSTM is utilized for contextual feature extraction in deep learning. Subsequently, microblog comment sentiments are categorized using a classification layer. Given the binary classification task at the output layer and the numerous hidden layers within BiLSTM, the Tanh activation function is adopted in this model. Experimental findings demonstrate that the enhanced TextCNN-BiLSTM model attains a precision of 94.75%. This represents a 1.21%, 1.25%, and 1.25% enhancement in precision, recall, and F1 values, respectively, in comparison to the individual deep learning models TextCNN. Furthermore, it outperforms BiLSTM by 0.78%, 0.9%, and 0.9% in precision, recall, and F1 values.

• Journal of the Korea Convergence Society
• /
• v.12 no.3
• /
• pp.325-339
• /
• 2021

The purpose of the study is to examine sports-related cognitive functions through a systematic review and to suggest effective instruments to measure the cognitive functions. The present study was conducted based on the systematic review and meta-analysis protocol-the PRISMA. Of 429 articles searched through keywords from 2008 to 2020, 45 articles that met the selection criteria were analyzed. It was revealed that athletes had better cognitive functions than non-athletes, that the higher the sports expertise was, the higher the cognitive functions, and that there were differences in cognitive functions according to the sport types. The primary cognitive functions related to sports performance summarized as executive functions (inhibition ability, cognitive flexibility), information processing speed, spatial ability, and attention. As tasks for measuring each cognitive function, a stop signal task for inhibition ability, a design flexibility task for cognitive flexibility, a simple and choice reaction time test for information processing, a mental rotation task for spatial ability, and an attention network test for attention are appropriate.