• Phonetics and Speech Sciences
• /
• v.15 no.2
• /
• pp.53-59
• /
• 2023

Detection of children with autism spectrum disorder (ASD) based on speech has relied on predefined feature sets due to their ease of use and the capabilities of speech analysis. However, clinical impressions may not be adequately captured due to the broad range and the large number of features included. This paper demonstrates that the knowledge-driven speech features (KDSFs) specifically tailored to the speech traits of ASD are more effective and efficient for detecting speech of ASD children from that of children with typical development (TD) than a predefined feature set, extended Geneva Minimalistic Acoustic Standard Parameter Set (eGeMAPS). The KDSFs encompass various speech characteristics related to frequency, voice quality, speech rate, and spectral features, that have been identified as corresponding to certain of their distinctive attributes of them. The speech dataset used for the experiments consists of 63 ASD children and 9 TD children. To alleviate the imbalance in the number of training utterances, a data augmentation technique was applied to TD children's utterances. The support vector machine (SVM) classifier trained with the KDSFs achieved an accuracy of 91.25%, surpassing the 88.08% obtained using the predefined set. This result underscores the importance of incorporating domain knowledge in the development of speech technologies for individuals with disorders.

• IE interfaces
• /
• v.7 no.1
• /
• pp.59-66
• /
• 1994

In scheduling open-field type FMS, process planning of decision making between alternate machines is taken into consideration. This idea is validated via implementing two experimental systems; One is a knowledge-based system and the other is to solve a Constraint Satisfaction Problem. The former generates some promising schedules in view of improving machine utilization, makespan and meanflow time, and the latter does in view of meeting due date.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.719-724
• /
• 1998

This paper presents a systematic developement of a formal approach to inference in approximate reasoning. We introduce some measures of similarity and discuss their properties. Using the concept of similarity index we formulate two methods for inferring from vague knowledge. In order to illustrate the effectiveness of the proposed technique we use it to develop a vowel recognition system.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.944-947
• /
• 1996

Realization of autonomous agents that organize their own internal structure in order to behave adequately with respect to their goals and the world is the ultimate goal of AI and Robotics. Reinforcement learning gas recently been receiving increased attention as a method for robot learning with little or no a priori knowledge and higher capability of reactive and adaptive behaviors. In this paper, we present a method of reinforcement learning by which a multi robots learn to move to goal. The results of computer simulations are given.

• The Journal of Information Systems
• /
• v.3
• /
• pp.171-201
• /
• 1994

I wish to acknowledge the people who inspired me to believe that a machine can have intelligence. They are the ones who envisioned the future of mankind. I specially appreciate to my advisor Dr. Srivasan raghunathan, who was always supportive and encouraged to finish this research. I also sincerely thank for my parents who are always concerned of my well-being. Without them, what I achived here cannot be possible.

• Journal of Radiation Protection and Research
• /
• v.11 no.1
• /
• pp.83-89
• /
• 1986

High energy radiation therapy using accelerator or radioioisotope teletherapy unit is now one of the most important modality in the field dealing with human malignant tumor. It's successful technology overcomes incurable disease to change into curable disease not only by the improvement of clinical technique but also by the development of radiation physics and biology. The author presented the principles of radiation therapy by means of basic knowledge of medicine. physics and biology, described the various ways to improve the result of radiation therapy, and reviewed recent status of radiotherapy field in Korea.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.18 no.1
• /
• pp.1-6
• /
• 1981

The knowledge of the characteristics of the control input of polymachine has been highly emphasized. Several transform processes of different types of polymachines are illustrated. It is proved that control inputs fed to the polymachines have machine-dependent structure which are closely associated with the interior structure of the machines.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.887-891
• /
• 1992

In this study, it is developed the interactive DNC(Direct Numerical Control) system, in using RS-232C cable and auxiliary computer, through the diagnosis of planning process and information evaluation. this DNC system recognize the Manufacturing planning and control it. This DNC system has a different notation. It can be done by an operator who hasn't knowledge about personnel computer. It is operated with automatic planning and measurement tec. by operator, using part program on the NC(Numerical Control).

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 1999.03b
• /
• pp.39-44
• /
• 1999

Hydroforming is a forming process enabling circular metal tubes to be produced in complex cross sections along curved axial paths With the availability of advanced machine design and control They offer advantages over stamped sheet metal in lower tooling cost and structural mass The technology is relatively new so that there is no large knowledge base to assist the fundamentals of tube hydroforming technology. The purpose of this paper is found that adaptive bending condition and contact condition for bended part has uniform thickness distribution.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.366-368
• /
• 2000

규칙기반 기계번역 시스템의 문제점을 보완하고자 제시된 예제기반 기계번역 시스템은 대량의 고품질 대역 코퍼스가 필요하다. 그리고, 빠른 N-best 예제 검색, 유사 예제 계산, 번역결과의 평가 등이 중요한 문제들이다. 또한, 무엇보다도 기본적인 것은 대역 예문들을 표현하고 기술하는 방법이다. 본 논문에서는 자연어 대역 예문들을 수집하여 기계번역 시스템에서 사용하는 고정 표현 지식을 기술하는 방법에 대해서 논의한다. 대역 패턴의 기술 방법을 CFG 형태로 정의하고 실제 용례를 통하여 기술 방법을 설명한다.