• ETRI Journal
• /
• v.39 no.1
• /
• pp.21-29
• /
• 2017

This paper addresses the problem of unsupervised speech separation based on robust non-negative matrix factorization (RNMF) with ${\beta}$-divergence, when neither speech nor noise training data is available beforehand. We propose a robust version of non-negative matrix factorization, inspired by the recently developed sparse and low-rank decomposition, in which the data matrix is decomposed into the sum of a low-rank matrix and a sparse matrix. Efficient multiplicative update rules to minimize the ${\beta}$-divergence-based cost function are derived. A convolutional extension of the proposed algorithm is also proposed, which considers the time dependency of the non-negative noise bases. Experimental speech separation results show that the proposed convolutional RNMF successfully separates the repeating time-varying spectral structures from the magnitude spectrum of the mixture, and does so without any prior training.

• Journal of the Korean Society for Precision Engineering
• /
• v.22 no.8 s.173
• /
• pp.34-41
• /
• 2005

Generally, it is not easy to get a suitable controller for multi variable systems. If the modeling equation of the system can be found, it is possible to get LQR control as an optimal solution. This paper suggests an LQR learning method to design LQR controller without the modeling equation. The proposed algorithm uses the same cost function with error and input energy as LQR is used, and the LQR controller is trained to reduce the function. In this training process, the Jacobian matrix that informs the converging direction of the controller Is used. Jacobian means the relationship of output variations for input variations and can be approximately found by the simple experiments. In the simulations of a hydrofoil catamaran with multi variables, it can be confirmed that the training of LQR controller is possible by using the approximate Jacobian matrix instead of the modeling equation and this controller is not worse than the traditional LQR controller.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.10
• /
• pp.1902-1910
• /
• 2009

This paper presents a graphical windows-based program for the education and training for novel network reduction. The object of developed simulator is to provide users with a simple and useable tool for gaining an intuitive feel for power system analysis. The developed simulator consists of the main module (MMI,GUI), the location marginal price module (LMP), the clustering module and network reduction module. Each module has a separate graphical and interactive interfacing window. The developed simulator needs with the PSS/E input data format, generator cost function, location information. Line admittances of reduced network was determined by using the power flow method(Newton-Raphson). So line flow of reduced network is almost same to original power system. Results of reduced network are compared on the window in the tabular format. Therefore, the developed simulator can be utilized as a useful tool for effective education and training for power system analysis.

• International Journal of Industrial Entomology and Biomaterials
• /
• v.3 no.2
• /
• pp.117-120
• /
• 2001

In India, mulberry (Morus spp.), the sole food plant of the silkworm, Bombyx mori (Linn.), is prone to infestation by the pink mealybug, Maconellicoccus hirsutus (Green). Infestation by this pest causes apical shoot malformation, popularly known as 'tukra'. Occurrence of tukra causes an appreciable reduction in leaf yield and quality, leading to low silkworm cocoon productivity. For management of M. hirsutus (Tukra), an IPM package comprising mechanical, chemical and biological measures was demonstrated in the mulberry gardens of five Government Silk Farms in Mysore District (Karnataka, India) during 1995-96. A suppression of 76.0% in tukra incidence and 90.19% in mealybug population was recorded by employ the IPM package which led to an estimated 4,000 kg recovery in leaf yield/ha/year. The impact of IPM package in the management of M. hirsutus, the role of biocontrol agent (Cryptolaemus montrouzieri Muls.) in pest suppression and the cost-benefit analysis of the IPM package are discussed.

• Journal of the Institute of Convergence Signal Processing
• /
• v.18 no.1
• /
• pp.1-5
• /
• 2017

It is important to train lower limb muscle strength using a tilting table to recover the lower extremity function of hemiplegia patients. It is known that the foot deformity and poor posture of hemiplegia patients can reduce the effectiveness of lower limb rehabilitation training. In this study, we developed a sensor system that can measure the foot pressure distribution of the patients for the load control of the lower extremity during lower limb rehabilitation training and it can be substituted for conventional high-cost technologies.

• International Journal of Advanced Culture Technology
• /
• v.8 no.4
• /
• pp.299-305
• /
• 2020

With the advancement of the 4th Industrial Revolution(4IR), microprocessor education is on the rise due to the explosive demand for IoT (Internet of Things) and M2M devices. However, it is difficult due to many constraints to efficiently transfer training on hardware assembly and implementation through online training. Thus, we developed a cost-effective online content based on Arduino simulations, Atmel Studio 7, and WinAvr simulator that are required for the utilization of AVR 128. These Camtasia videos overcame the limitation of theory focused on-line education by visually introducing the practical utilization of an actual AVR 128. In this paper, the proposed educational content was provided to university students, and the results of student feedback show that it has a strong effect.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.30 no.3
• /
• pp.109-116
• /
• 2022

A modular platform development technique was proposed to minimize development cost and development period by utilizing the already developed unmanned Aerial target AVT, which has been operated and verified for many years. New Mission Profile was designed and structural analysis was performed through finite element analysis (FEA) by analyzing mission requirements for visual short-range, non-visible mid-range, and long-range targets. The targets are used for guided missile anti-aircraft training. In addition, avionics systems including flight control computers for autonomous flights were developed to verify their conformance by performing launcher take-off tests with rapid acceleration changes and autonomous flight tests at a maximum speed of 300km per hour.

• ETRI Journal
• /
• v.45 no.6
• /
• pp.1007-1021
• /
• 2023

Stroke is the leading cause of permanent disability in adults, and it can cause permanent brain damage. According to the World Health Organization, 795 000 Americans experience a new or recurrent stroke each year. Early detection of medical disorders, for example, strokes, can minimize the disabling effects. Thus, in this paper, we consider various risk factors that contribute to the occurrence of stoke and machine learning algorithms, for example, the decision tree, random forest, and naive Bayes algorithms, on patient characteristics survey data to achieve high prediction accuracy. We also consider the semisupervised self-training technique to predict the risk of stroke. We then consider the near-miss undersampling technique, which can select only instances in larger classes with the smaller class instances. Experimental results demonstrate that the proposed method obtains an accuracy of approximately 98.83% at low cost, which is significantly higher and more reliable compared with the compared techniques.

• Korean Journal of Radiology
• /
• v.25 no.2
• /
• pp.126-133
• /
• 2024

Large language models (LLMs) have revolutionized the global landscape of technology beyond natural language processing. Owing to their extensive pre-training on vast datasets, contemporary LLMs can handle tasks ranging from general functionalities to domain-specific areas, such as radiology, without additional fine-tuning. General-purpose chatbots based on LLMs can optimize the efficiency of radiologists in terms of their professional work and research endeavors. Importantly, these LLMs are on a trajectory of rapid evolution, wherein challenges such as "hallucination," high training cost, and efficiency issues are addressed, along with the inclusion of multimodal inputs. In this review, we aim to offer conceptual knowledge and actionable guidance to radiologists interested in utilizing LLMs through a succinct overview of the topic and a summary of radiology-specific aspects, from the beginning to potential future directions.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.3
• /
• pp.111-121
• /
• 2020

Realistic training contents utilizing intensive immersion of virtual reality are being used in various fields such as industry, education, and medical care. High-risk, high-cost education training, in particular, is difficult to conduct in reality, but it can be applied with the latest virtual reality technology that enhances educational effectiveness by efficiently and safely experiencing it in an environment similar to reality. This study introduces a management system that systematically manages realistic virtual training contents and visualizes training results in schematic pictures based on defined evaluation elements. The management system can store the information generated from the content in the database and manage the training records of each trainee in a practical way. In addition, a content-based scenario can be created in multiple scenarios by setting training goals, number of participants, and methods for applying evaluation elements. This paper describes the management system's production method and the results based on the virtual reality training content as an application example.