• Proceedings of the KIEE Conference
• /
• 2002.11c
• /
• pp.163-168
• /
• 2002

The voting algorithm for action selection performs self-improvement by Reinforcement learning algorithm in the dynamic environment. The proposed voting algorithm improves the navigation of the robot by adapting the eligibility of the behaviors and determining the Command Set Generator (CGS). The Navigator that using a proposed voting algorithm corresponds to the CGS for giving the weight values and taking the reward values. It is necessary to decide which Command Set control the mobile robot at given time and to select among the candidate actions. The Command Set was learnt online by means as Q-learning. Action Selector compares Q-values of Navigator with Heterogeneous behaviors. Finally, real-world experimentation was carried out. Results show the good performance for the selection on command set as well as the convergence of Q-value.

• Journal of Information Processing Systems
• /
• v.16 no.2
• /
• pp.435-446
• /
• 2020

With the ability to learn rules from training data, the machine learning model can classify unknown objects. At the same time, the dimension of hyperspectral data is usually large, which may cause an over-fitting problem. In this research, an identification methodology of tea diseases was proposed based on spectral reflectance and machine learning, including the feature selector based on the decision tree and the tea disease recognizer based on random forest. The proposed identification methodology was evaluated through experiments. The experimental results showed that the recall rate and the F1 score were significantly improved by the proposed methodology in the identification accuracy of tea disease, with average values of 15%, 7%, and 11%, respectively. Therefore, the proposed identification methodology could make relatively better feature selection and learn from high dimensional data so as to achieve the non-destructive and efficient identification of different tea diseases. This research provides a new idea for the feature selection of high dimensional data and the non-destructive identification of crop diseases.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.1 no.3
• /
• pp.83-94
• /
• 1993

Design and production of wiring for automobile systems provide the background for the development of concurrent engineering framwork. Key issues include with different parts of the wiring design process and the development of hierarchical representations that capture the different characteristics(e.g., connectivity, geometry) of the harnesses. The abstraction of design information results in features, while the abstraction of operations leads to the development of agents. These abstracts are essential for efficient transactions among people and computer tools in a domain that involves numerous interacting constraints. We have decomposed the wiring design process into four basic categories of tasks that are each addressed by an "agent" : the Environment Editor(EE), the Free Space Manager(FSM), the Wiring Editor(WE), and the Part Selector(PS). In this paper the strategy for the problem decomposition, the definition of features, and the ways in which features are used by various agents, are discussed. We conclude with a discussion of some of the issues raised by the project and the steps underway to address them.

• Bulletin of the Korean Chemical Society
• /
• v.25 no.3
• /
• pp.377-381
• /
• 2004

Chiral separation of aryalcohols such as 1-phenyl-propanol, 1-phenyl-2-proanol, and 2-phenyl-1-propanol by capillary electrophoresis has been optimized using the overlapping resolution mapping (ORM) scheme. Three critical parameters of the electrophoretic media, i.e. phosphate concentration, sulfated ${\beta}$-cyclodextrin (CD) concentration and pH, were chosen for optimization. The working ranges were initially presumed by 7 preexperiments. Further optimization was carried out by another seven experiments within the narrow working ranges. From the final overlapping resolution mapping all peak pairs, the area of maximum separations were located. Using the conditions of a point in this area, we found that the target compounds were a baseline separated within 30 min. The maximum separation conditions of arylalcohols were a chiral selector concentration of 5.4%, a phosphate concentration of 28 mM, and a pH of 5.0.

• The KIPS Transactions:PartD
• /
• v.10D no.6
• /
• pp.1041-1048
• /
• 2003

This paper implements a remote image based metering(IBM) system which capture meter image, recognizes number automatically, and send the data wirelessly through PCS data network. We use existing gas/water meter and get NTSC camera image by installing small monochrome CMOS camera on the meter closely. For remote data transfer, we use SMS (short message service) that is provided by commercial PCS network. We developed DVR(digital video recorder) for capturing meter image and character recognition algorithm. In addition, hardware and software for SMS and meter selector were developed.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.2A
• /
• pp.96-101
• /
• 2003

This paper is on the user equipment (UE) side time tracker design and implementation of the wideband code division multiple access (WCDMA) system. The time tracker is constructed as a second order closed loop including time error detector (TED), loop filter (LP), numerically controlled oscillator (NCO), and sample selector (SS). Through the simulation, we found the gain of the TED as a function of the CPICH power contribution to the total transmission power of the base station. Also we derived the transfer function of the loop and the BER versus DPCH power relationships where timing offsets and loop noise bandwidths are used as parameters. In the curve, we can conclude that there are appropriate loop noise bandwidths according to the given environments for the better performance.

• Genomics & Informatics
• /
• v.12 no.2
• /
• pp.50-57
• /
• 2014

We present a new next-generation sequencing-based method to identify somatic mutations of lung cancer. It is a comprehensive mutation profiling protocol to detect somatic mutations in 30 genes found frequently in lung adenocarcinoma. The total length of the target regions is 107 kb, and a capture assay was designed to cover 99% of it. This method exhibited about 97% mean coverage at $30{\times}$ sequencing depth and 42% average specificity when sequencing of more than 3.25 Gb was carried out for the normal sample. We discovered 513 variations from targeted exome sequencing of lung cancer cells, which is 3.9-fold higher than in the normal sample. The variations in cancer cells included previously reported somatic mutations in the COSMIC database, such as variations in TP53, KRAS, and STK11 of sample H-23 and in EGFR of sample H-1650, especially with more than $1,000{\times}$ coverage. Among the somatic mutations, up to 91% of single nucleotide polymorphisms from the two cancer samples were validated by DNA microarray-based genotyping. Our results demonstrated the feasibility of high-throughput mutation profiling with lung adenocarcinoma samples, and the profiling method can be used as a robust and effective protocol for somatic variant screening.

• ETRI Journal
• /
• v.33 no.2
• /
• pp.210-218
• /
• 2011

Battiti's mutual information feature selector (MIFS) and its variant algorithms are used for many classification applications. Since they ignore feature synergy, MIFS and its variants may cause a big bias when features are combined to cooperate together. Besides, MIFS and its variants estimate feature redundancy regardless of the corresponding classification task. In this paper, we propose an automated greedy feature selection algorithm called conditional mutual information-based feature selection (CMIFS). Based on the link between interaction information and conditional mutual information, CMIFS takes account of both redundancy and synergy interactions of features and identifies discriminative features. In addition, CMIFS combines feature redundancy evaluation with classification tasks. It can decrease the probability of mistaking important features as redundant features in searching process. The experimental results show that CMIFS can achieve higher best-classification-accuracy than MIFS and its variants, with the same or less (nearly 50%) number of features.

• Archives of Pharmacal Research
• /
• v.24 no.4
• /
• pp.281-285
• /
• 2001

Enantiomers of five racemic ${\beta}_2$-agonists were investigated by capillary electrophoresis employing a hydroxypropyl-${\beta}$-cyclodextrin (HP-${\beta}$-CD). The effects of the concentration of HP-${\beta}$-CD added to the background electrolyte and of the pH of the buffer on the effective mobility and resolution of the studied compounds were examined. Very good resolution was achieved for terbutaline and clenbuterol; salbutamol and bambuterol was able to be partially resolved. Enantioselectivity and resolution were influenced by the concentration of the HP-7-CD, buffer composition and pH.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.9
• /
• pp.982-992
• /
• 1992

We developed the interface system between D-SCAN TV system and the Teletext system to reduce the effect of interline flick. At first, horizontal and vertical signal is separated from the composite signal. The stable vertical sync and horizontal sync is applied to the conventional Teletext system and the its output has R.G.B signal form and the output of the Teletext system. This signal is converted into composite signal and is switched at the video selector system in TV to process the signal by progressive method.