• Journal of KIISE
• /
• v.42 no.11
• /
• pp.1372-1379
• /
• 2015

This paper presents an analysis of feature extraction methods used for distinguishing the speech of patients with cleft palates and people with normal palates. This research is a basic study on the development of a software system for automatic recognition and restoration of speech disorders, in pursuit of improving the welfare of speech disabled persons. Monosyllable voice data for experiments were collected for three groups: normal speech, cleft palate speech, and simulated clef palate speech. The data consists of 14 basic Korean consonants, 5 complex consonants, and 7 vowels. Feature extractions are performed using three well-known methods: LPC, MFCC, and PLP. The pattern recognition process is executed using the acoustic model GMM. From our experiments, we concluded that the MFCC method is generally the most effective way to identify speech distortions. These results may contribute to the automatic detection and correction of the distorted speech of cleft palate patients, along with the development of an identification tool for levels of speech distortion.

• Journal of Ocean Engineering and Technology
• /
• v.22 no.1
• /
• pp.75-82
• /
• 2008

A vibration-based damage-monitoring scheme is proposed that would generate an alarm showing the occurrence and location of damage under temperature-induced uncertainty conditions. Experiments on a model plate-girder bridge are described, for which a set of modal parameters was measured under uncertain temperature conditions. A damage-alarming model is formulated to statistically identify the occurrence of damage by recognizing the patterns of damage-driven changes in the natural frequencies of the test structure and by distinguishing temperature-induced off-limits. A damage index method based on the concept of modal strain energy is implemented in the test structure to predict the location of damage. In order to adjust for the temperature-induced changes in the natural frequencies that are used for damage detection, a set of empirical frequency correction formulas is analyzed from the relationship between the temperature and frequency ratio.

• Asia pacific journal of information systems
• /
• v.26 no.1
• /
• pp.1-21
• /
• 2016

Social media is increasingly being used as a source of information during crises, such as natural disasters and civil unrests. However, the quality and truthfulness of user-generated information on social media have been a cause of concern. Many users find distinguishing between true and false information on social media difficult. Basing on the elaboration likelihood model and the motivation, opportunity, and ability framework, this study proposes and empirically tests a model that identifies the information processing routes through which users develop trust, as well as the factors that influence the use of these routes. The findings from a survey of Twitter users seeking information about the Fukushima Daiichi nuclear crisis indicate that individuals evaluate information quality more when the crisis information has strong personal relevance or when individuals have low anxiety about the crisis. By contrast, they rely on majority influence more when the crisis information has less personal relevance or when these individuals have high anxiety about the crisis. Prior knowledge does not have significant moderating effects on the use of information quality and majority influence in forming trust. This study extends the theorization of trust in user-generated information by focusing on the process through which users form trust. The findings also highlight the need to alleviate anxiety and manage non-victims in controlling the spread of false information on social media during crises.

• Journal of information and communication convergence engineering
• /
• v.9 no.4
• /
• pp.379-384
• /
• 2011

The scope of the problems that could be solved by monitoring and the improvement of the recognition time is directly correlated to the performance of the management function of the business process. However, the current monitoring process of business activities decides whether to apply warnings or not by assuming a fixed environment and showing expressions based on the design rules. Also, warnings are applied by carrying out the measuring process when the event attribute values are inserted at every point. Therefore, there is a limit for distinguishing the range of occurrence and the level of severity in regard to the new external problems occurring in a complicated environment. Such problems cannot be ed. Also, since it is difficult to expand the range of problems which can be possibly evaluated, it is impossible to evaluate any unexpected situation which could occur in the execution period. In this paper, a process-evaluating model based on the goal scenario is suggested to provide constant services through the current monitoring process in regard to the service demands of the new scenario which occurs outside. The new demands based on the outside situation are analyzed according to the goal scenario for the process activities. Also, by using the meta-heuristic algorithm, a similar process model is found and identified by combining similarity and interrelationship. The process can be stopped in advance or adjusted to the wanted direction.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.467-479
• /
• 2022

Working memory (WM), which plays a vital role in daily activities, is a memory system that temporarily stores and processes information when people are engaged in complex cognitive activities. The influence of music on WM has been widely studied. In this work, we conducted a series of n-back memory experiments with different task difficulties and multiple trials on 14 subjects under the condition of no music and Alpha wave leading music. The analysis of behavioral data show that the change of music condition has significant effect on the accuracy and time of memory reaction (p<0.01), both of which are improved after the stimulation of Alpha wave music. Behavioral results also suggest that short-term training has no significant impact on working memory. In the further analysis of electrophysiology (EEG) data recorded in the experiment, auto-regressive (AR) model is employed to extract features, after which an average classification accuracy of 82.9% is achieved with support vector machine (SVM) classifier in distinguishing between before and after WM enhancement. The above findings indicate that Alpha wave leading music can improve WM, and the combination of AR model and SVM classifier is effective in detecting the brain activity changes resulting from music stimulation.

• Smart Structures and Systems
• /
• v.22 no.1
• /
• pp.57-70
• /
• 2018

For the long-term structural health monitoring of civil structures, the effect of ambient temperature variation has been regarded as one of the critical issues. In this study, a principal component analysis (PCA)-based algorithm is proposed to filter out temperature effects on electromechanical impedance (EMI) monitoring of prestressed tendon anchorages. Firstly, the EMI monitoring via a piezoelectric interface device is described for prestress-loss detection in the tendon anchorage system. Secondly, the PCA-based temperature filtering algorithm tailored to the EMI monitoring of the prestressed tendon anchorage is outlined. The proposed algorithm utilizes the damage-sensitive features obtained from sub-ranges of the EMI data to establish the PCA-based filter model. Finally, the feasibility of the PCA-based algorithm is experimentally evaluated by distinguishing temperature changes from prestress-loss events in a prestressed concrete girder. The accuracy of the prestress-loss detection results is discussed with respect to the EMI features before and after the temperature filtering.

• Journal of the Korean Geophysical Society
• /
• v.9 no.1
• /
• pp.7-19
• /
• 2006

Laser scanning is a new technology for obtaining Digital Surface Models(DSM) of the earth surface.It is a fast method for sampling the earth surface with high density and high point accuracy. This paper is for buildings extraction from LiDAR points data. The core part of building construction is based on a parameters filter for distinguishing between terrain and non-terrain laser points. The 3D geometrical properties of the building facades are obtained based on plane fitting using least-squares adjustment. The reconstruction part of the procedure is based on the adjacency among the roof facades. Primitive extraction and facade intersections are used for building reconstruction. For overcome the difficulty just reconstruct of laser points data used with digital camera images. Also, 3D buildings of city area reconstructed using digital map. Finally, In this paper show 3D building Modeling using digital map and LiDAR data.

• Architectural research
• /
• v.22 no.4
• /
• pp.145-154
• /
• 2020

Zoning has long been criticized for its negative effects and has been taken for granted that zoning works as a hurdle to urban diversity. Responses in the US have emphasized more fine-grained zoning approaches that plan mixed use. This paper introduces and evaluates Seoul's zoning system as a possible alternative. While US zoning regulations have relied on distinguishing ever larger numbers of land use zoning categories, Seoul has opted to integrate new land uses into existing classifications, allowing for greater flexibility of use in each zone. Using municipal building records to evaluate land use in three mid-density residential districts, this paper demonstrates that Seoul's flexible zoning is capable of producing diverse mixed use neighborhoods. It then highlights the potential downside of this approach, showing that flexibility allows for the commercialization and sectoral gentrification of residential districts. It concludes by suggesting that a combination of flexible zones and more fine-grained plans would capture the advantages of both US and Korean planning.

• Advances in aircraft and spacecraft science
• /
• v.8 no.4
• /
• pp.331-344
• /
• 2021

Airframe internal and external specifications are the product of intensive intellectual efforts and technological breakthroughs distinguishing each aircraft manufacturer. Therefore, geometrical information characterizing aircraft primary aerodynamic surfaces remain classified. When attempting to model real aircraft, many members of the aeronautical community depend on their personal expertise and generic design principles to bypass the confidentiality obstacles and sketch real aircraft airfoils, which therefore vary for the same aircraft due to the different designers' initial assumptions. This paper presents a photogrammetric shape prediction method for deriving geometrical properties of real aircraft airframe by utilizing their publicly accessible static and dynamic visual content. The method is based on extracting the visually distinguishable curves at the fairing regions between aerodynamic surfaces and fuselage. Two case studies on B-29 and B-737 are presented showing how to approximate the sectional coordinates of their wing inboard airfoils and proving the good agreement between the geometrical and aerodynamic properties of the replicated airfoils to their original versions. Therefore, the paper provides a systematic reverse engineering approach that will enhance aircraft conceptual design and flight performance optimization studies.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.90-91
• /
• 2023

대기오염에 대한 사회적 관심이 증가함에 따라 미세먼지 관련 IoT 가전제품의 수요가 증가하였다. 이에 따라 IoT 제품에서 수집되는 실내 데이터의 정확성을 높이기 위해 미세먼지 센서 외의 추가적인 센서를 사용하여 관측치를 예측하는 연구가 진행되고 있다. 하지만 기존 연구에서는 센서의 물리적 한계를 인공지능을 통하여 극복하려는 시도는 존재하지 않는다. 본 논문에서는 추가적인 센서를 사용하지 않고 단일 센서만을 사용하여 미세먼지 종류의 구분 가능성을 판단하고자 하며 이를 정확도 기반으로 비교 실험을 진행하여 가장 좋은 성능을 나타낸 딥러닝 기반 분류모델을 선정한다.