• Journal of KIISE:Software and Applications
• /
• v.36 no.3
• /
• pp.179-186
• /
• 2009

This paper proposes a target speech extraction which restores speech signal of a target speaker form noisy convolutive mixture of speech and an interference source. We assume that the target speaker is known and his/her utterances are available in the training time. Incorporating the additional information extracted from the training utterances into the separation, we combine convolutive blind source separation(CBSS) and non-negative decomposition techniques, e.g., probabilistic latent variable model. The nonnegative decomposition is used to learn a set of bases from the spectrogram of the training utterances, where the bases represent the spectral information corresponding to the target speaker. Based on the learned spectral bases, our method provides two postprocessing steps for CBSS. Channel selection step finds a desirable output channel from CBSS, which dominantly contains the target speech. Reconstruct step recovers the original spectrogram of the target speech from the selected output channel so that the remained interference source and background noise are suppressed. Experimental results show that our method substantially improves the separation results of CBSS and, as a result, successfully recovers the target speech.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.20 no.44
• /
• pp.463-473
• /
• 1997

In this paper, driver's judgements for the priorities of vehicle devices were studied to establish the standard of design of inside devices. The differences within drivers who have different careers were also studied. For this study, two experiments were conducted. First experiment was peformed in terms of total devices in the vehicle cockpit, and second was peformed in terms of the visual devices that these were the source of visual information. These experiments were analyzed using AHP (Analytic Hierarchy Process) method. The result showed the priorities of devices and little relationship between the career and the judgement. Especially, it was shown that the novice tended to depend on the information from visual devices.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.9 no.3
• /
• pp.39-48
• /
• 2013

Ontology has an important role in semantic web to construct and query semantic data. When system make changes to ontologies, questions arise about versioning of these changes. Applying this changes on a dynamic environment is even more important. To apply these changes, change specification method is needed. Early studies show RDF-based syntax for the operations between old and new ontologies. When several ontology versions can be used for some query, if possible, using possible newest version ontology with prospective use is best way to process the query. Prospective use of ontology means using a newer version of an ontology with a data source that conforms to a more recent ontology. In this paper, for prospective use of ontology version, structure of change specification of class and property through several ontology versions is proposed. From this, efficient adaptive ontology version selection for a query can be possible. Algorithm for structure of version transition representation is proposed and simulation results show possible newest version number for queries.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.4
• /
• pp.1889-1910
• /
• 2017

This paper investigates a protocol so-called Adaptive Harvest Then Transmit (AHTT) for wireless powered communication networks (WPCNs) in multiple-input single-output (MISO) downlink systems, which assists in transmitting signals from a multi-antenna transmitter to a single-antenna receiver. Particularly, the power constrained relay is supplied with power by utilizing radio frequency (RF) signals from the source. In order to take advantage of multiple antennas, two different linear processing schemes, including Maximum Ratio Combining (MRC) and Selection Combination (SC) are studied. The system outage capacity and ergodic capacity are evaluated for performance analysis. Furthermore, the optimal power allocation is also considered. Our numerical and simulation results prove that the implementation of multiple antennas helps boost the energy harvesting capability. Therefore, this paper puts forward a new way to the energy efficiency (EE) enhancement, which contributes to better system performance.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2011.01a
• /
• pp.203-206
• /
• 2011

공개 경쟁에 의한 제안 업체 선정과 객관적이고 공정한 제안서의 평가는 공공IT 부문에 있어서 성공적인 사업 수행을 위한 필수요소이다. '소프트웨어 기술성 평가기준 적용 가이드'에서는 소프트웨어 기술성 평가기준을 적용하는데 필요한 절차와 단계별 적용방법 및 세부내용 해설과 평가척도 예시를 제시하여 활용이 가능하도록 하였다. 그러나 기술성을 평가하기 위한 평가부문별 평가항목 및 평가기준에 대한 부분이 구체적이지 않아 경쟁력 있는 제안 업체의 기술성을 정확하고 공정하게 평가하는데 어려움이 있다. 따라서 본 연구에서는 제안 업체의 기술성을 정확하게 평가하기 위하여 평가요소 중에서 기술 평가요소에 대한 부분을 평가지표로 선정하고 통계 기법으로 평가지표를 검증하는 방법을 제시하고자 한다.

• Journal of Korean Library and Information Science Society
• /
• v.41 no.3
• /
• pp.205-224
• /
• 2010

The purpose of this study aims to present the base for the rational management of printed music as an important primary source of music materials. In this study, therefore, the selection and acquisition, organization, user services for the management of printed music are investigated. Then the present situation for management of printed music of university libraries in Daejeon and Chungnam are surveyed. Finally, the special issues to be considered in the management of printed music are presented.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.6 no.4
• /
• pp.161-170
• /
• 2010

This paper provides a novel approach for a user oriented system for face detection system for application developers. Even though there are many open source or commercial libraries to solve the problem of face detection, they are still hard to use because they require specific knowledge on detail algorithmic techniques. The purpose of this paper is to come up with a high-level system for face detection with which users can develop systems easily and even without specific knowledge on face detection theories and algorithms. Important conditions are firstly considered to categorize the large problem space of face detection. The conditions identified here are then represented as expressions so that application developers can use them to express various problems. Once the conditions are expressed by developers, the interpreter proposed take the role to interpret the conditions, find and organize the optimal algorithms to solve the represented problem with corresponding conditions. A proof-of-concept is implemented and some example problems are tested and analyzed to show the ease of use and usability.

• Phonetics and Speech Sciences
• /
• v.1 no.3
• /
• pp.109-115
• /
• 2009

Many isolated word recognition systems may generate non-similar words for recognition candidates because they use only acoustic information. In this paper, we investigate several techniques which can exclude non-similar words from N-best candidate words by applying Levenstein distance measure. At first, word distance method based on phone and syllable distances are considered. These methods use just Levenstein distance on phones or double Levenstein distance algorithm on syllables of candidates. Next, word similarity approaches are presented that they use characters' position information of word candidates. Each character's position is labeled to inserted, deleted, and correct position after alignment between source and target string. The word similarities are obtained from characters' positional probabilities which mean the frequency ratio of the same characters' observations on the position. From experimental results, we can find that the proposed methods are effective for removing non-similar words without loss of system performance from the N-best recognition candidates of the systems.

• The KIPS Transactions:PartC
• /
• v.14C no.1 s.111
• /
• pp.73-80
• /
• 2007

In conventional on-demand mobile ad hoc routing algorithms, an alternate path is sought only after an active path is broken. It incurs a significant cost in terms of money and time in detecting the disconnection and establishing a new route. In this thesis, we propose proactive route selection and maintenance to conventional mobile ad hoc on-demand routing algorithms. The key idea for this research is to only consider a path break to be likely when the signal power of a received packet drops below an optimal threshold value and to generate a forewarning packet. In other words, if a path is lost with high probability, the neighboring node that may easily be cut off notifies the source node by sending a forewarning packet. Then the source node can initiate route discovery early and switched to a reliable path potentially avoiding the disconnection altogether. For the simulational study, network simulator(NS2) is used. The result of simulation shows that the algorithm significantly improves the performance of networks comparing to conventional on-demand routing protocols based on DSR and AODV in terms of packet delivery ratio, packet latency and routing overhead.

• Journal of Information Processing Systems
• /
• v.16 no.5
• /
• pp.1113-1128
• /
• 2020

Ad hoc networks play an important role in mobile communications, and the performance of nodes has a significant impact on the choice of communication links. To ensure efficient and secure data forwarding and delivery, an intelligent routing protocol (IAODV) based on learning method is constructed. Five attributes of node energy, rate, credit value, computing power and transmission distance are taken as the basis of segmentation. By learning the selected samples and calculating the information gain of each attribute, the decision tree of routing node is constructed, and the rules of routing node selection are determined. IAODV algorithm realizes the adaptive evaluation and classification of network nodes, so as to determine the optimal transmission path from the source node to the destination node. The simulation results verify the feasibility, effectiveness and security of IAODV.