• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.278-284
• /
• 2003

Speech act is the speaker's intentions indicated through utterances. It is important for understanding natural language dialogues and generating responses. This paper proposes the method of two stage that increases the performance of the korean speech act decision. The first stage is to select features from the part of speech results in sentence and from the context that uses previous speech acts. We use x$^2$ statistics(CHI) for selecting features that have showed high performance in text categorization. The second stage is to determine speech act with selected features and Neural Network. The proposed method shows the possibility of automatic speech act decision using only POS results, makes good performance by using the higher informative features and speed up by decreasing the number of features. We tested the system using our proposed method in Korean dialogue corpus transcribed from recording in real fields, and this corpus consists of 10,285 utterances and 17 speech acts. We trained it with 8,349 utterances and have test it with 1,936 utterances, obtained the correct speech act for 1,709 utterances(88.3%). This result is about 8% higher accuracy than without selecting features.

• Journal of KIISE:Computing Practices and Letters
• /
• v.8 no.2
• /
• pp.174-182
• /
• 2002

The object-oriented design methods and their CASE tools are widely used in practice by many real-time software developers. However, object-oriented CASE tools require an additional step of identifying tasks from a given design model. Unfortunately, it is difficult to automate this step for a couple of reasons: (1) there are inherent discrepancies between objects and tasks; and (2) it is hard to derive tasks while maximizing real-time schedulability since this problem makes a non-trivial optimization problem. As a result, in practical object-oriented CASE tools, task identification is usually performed in an ad-hoc manner using hints provided by human designers. In this paper, we present a systematic, schedulability-aware approach that can help mapping real-time object-oriented models to multi-threaded implementations. In our approach, a task contains a group of mutually exclusive transactions that may possess different periods and deadline. For this new task model, we provide a new schedulability analysis algorithm. We also show how the run-time system is implemented and how executable code is generated in our frame work. We have performed a case study. It shows the difficulty of task derivation problem and the utility of the automated synthesis of implementations as well as the Inappropriateness of the single-threaded implementations.

• Journal of Distribution Science
• /
• v.10 no.10
• /
• pp.17-24
• /
• 2012

Purpose - This study aimed to (a) investigate the effects of emotional intelligence on customer orientation, (b) examine the impact of customer orientation on customer relationship management (CRM) performance (including CRM-related variables such as 'relationship commitment,' 'image of corporation,' and 'customer loyalty'), and (c) identify the conceptual framework of emotional intelligence. Research design, data, and methodology - The data were collected using a questionnaire given to a sample of employees of luxury hotels in the metropolitan area. To test the hypotheses, AMOS were conducted for the 271 respondents of the sample using the SPSS Win 17.0 software. The concept of emotional intelligence (EI) has been on the radar of many leaders and managers over the past few decades. Emotional intelligence is generally accepted to be a combination of emotional and interpersonal competencies that influence behavior, thoughts, and interactions with others. Emotional intelligence consists of four factors: understanding the self's emotion, understanding other people's emotions, emotion utilization, and emotion control. Understanding the self's emotion means to understand of my own emotions. Understanding other people's emotions is to understand of the emotions of the people around me and to know how my friends feel based on their behavior. The concept of emotion utilization means to set goals for myself and then try to achieve them, encouraging myself to do my best. The concept of emotion control means I can control my temper, handle difficult situations rationally, and calm down quickly when I am very angry. Results - As a result of the analysis, three factors (understanding the self's emotion, understanding of other people's emotions, and emotion utilization) were shown to have a significant effect on customer orientation. Emotion control had an insignificant effect on customer orientation. Only emotion control makes it difficult to solve customers' problems because it is a passive behavior. In order to solve the customers' problems, hotel employees have to show a positive attitude. Second, customer orientation had a significant effect on customer relationship management performance (customer relationship commitment, corporate image, and customer loyalty). In other words, customer orientation increases commitment to customer relationships. For example, employees who have a customer-orientated perspective provide good service to their customers, while employees who don't have a customer-orientated perspective can't satisfy their customers. Customer orientation can also generate a good image among customers, because they evaluate the image of a hotel through the behavior of hotel employees. So it is very important for employees to show excellent customer orientation. Conclusions - It is very important for hotel CEOs to manage their employees' emotional intelligence. In order to increase their employees' emotional intelligence abilities, CEOs have to manage the overall corporate culture and reward programs to achieve what they want. This is because the system can lead to a customer-orientated mind-set and CRM performance among employees. As a result, the hotel CEO has to pay attention to the emotional intelligence of employees to achieve strong CRM performance. The sentence as originally written was a bit unclear. If this edit does not retain your intended meaning please consider: "Only emotion control does not have a significant impact on customer orientation, and therefore on the ability of an employee to solve customer problems, because it is a passive behavior." Please use the version of the sentence that best captures your original meaning.

• Korean Chemical Engineering Research
• /
• v.58 no.4
• /
• pp.565-572
• /
• 2020

This study developed a software platform using machine learning of artificial intelligence to optimize the distillation column system. The distillation column is representative and core process in the petrochemical industry. Process stabilization is difficult due to various operating conditions and continuous process characteristics, and differences in process efficiency occur depending on operator skill. The process control based on the theoretical simulation was used to overcome this problem, but it has a limitation which it can't apply to complex processes and real-time systems. This study aims to develop an empirical simulation model based on machine learning and to suggest an optimal process operation method. The development of empirical simulations involves collecting big data from the actual process, feature extraction through data mining, and representative algorithm for the chemical process. Finally, the platform for the distillation column was developed with verification through a developed model and field tests. Through the developed platform, it is possible to predict the operating parameters and provided optimal operating conditions to achieve efficient process control. This study is the basic study applying the artificial intelligence machine learning technique for the chemical process. After application on a wide variety of processes and it can be utilized to the cornerstone of the smart factory of the industry 4.0.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.11
• /
• pp.208-213
• /
• 2016

In the fourth industrial revolution, customization is becoming a conversation topic in various domains. Industry 4.0 applies cyber-physical systems (CPS), the Internet of Things (IoT), and cloud computing to manufacturing businesses. One of the main phrases in Industry 4.0 is mass customization. Optimized products or services are developed and provided through customization. Therefore, the competitiveness of a product can be enhanced, and satisfaction is improved. In particular, as IoT technology spreads, customization is an essential aspect of smooth service connections between various devices or things. Customized services in mobile applications are assembled and operate in various mobile devices in the mobile environment. Therefore, this paper proposes a method for improving customized cloud server-based mobile architectures, processes, and metrics, and for measuring the performance improvement of the customized architectures operating in various mobile devices based on the Android or IOS platforms. We reduce the total time required for customization in half as a result of applying the proposed customized architectures, processes, and metrics in various devices.

• Journal of KIISE:Software and Applications
• /
• v.35 no.12
• /
• pp.780-788
• /
• 2008

Modeling hand poses and tracking its movement are one of the challenging problems in computer vision. There are two typical approaches for the reconstruction of hand poses in 3D, depending on the number of cameras from which images are captured. One is to capture images from multiple cameras or a stereo camera. The other is to capture images from a single camera. The former approach is relatively limited, because of the environmental constraints for setting up multiple cameras. In this paper we propose a method of reconstructing 3D hand poses from a 2D input image sequence captured from a single camera by means of Belief Propagation in a graphical model and recognizing a finger clicking motion using a hidden Markov model. We define a graphical model with hidden nodes representing joints of a hand, and observable nodes with the features extracted from a 2D input image sequence. To track hand poses in 3D, we use a Belief Propagation algorithm, which provides a robust and unified framework for inference in a graphical model. From the estimated 3D hand pose we extract the information for each finger's motion, which is then fed into a hidden Markov model. To recognize natural finger actions, we consider the movements of all the fingers to recognize a single finger's action. We applied the proposed method to a virtual keypad system and the result showed a high recognition rate of 94.66% with 300 test data.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.4
• /
• pp.103-110
• /
• 2018

Infrared signatures emitted from naval ships are mainly classified into internal signatures generated by the internal combustion engine of the ship and external signatures generated from the surface of the ship heated by solar heat. The internal signatures are also affected by the chemical components ($CO_2$, $H_2O$, CO and soot) of the exhaust plumes generated by the gas turbine and diesel engine, which constitute the main propulsion system. Therefore, in this study, the chemical composition ratios of the exhaust plumes generated by the gas turbines and diesel engines installed in domestic naval ships were examined to identify the chemical components and their levels. The influence of the chemical components of the exhaust plumes and their ratios on the infrared signatures of a naval ship was investigated using orthogonal arrays. The infrared signature intensity of the exhaust plumes calculated using infrared signature analysis software was converted to the signal-to-noise ratio to facilitate the analysis. The signature analysis showed that $CO_2$, soot and $H_2O$ are the major components influencing the mid-wave infrared signatures of both the gas turbine and diesel engine. In addition, it was confirmed that $H_2O$ and $CO_2$ are the major components influencing the long-wave infrared signatures.

• Journal of KIISE:Software and Applications
• /
• v.36 no.4
• /
• pp.253-260
• /
• 2009

Many algorithms for computer vision and pattern recognition have recently been implemented on GPU (graphic processing unit) for faster computational times. However, the implementation has two problems. First, the programmer should master the fundamentals of the graphics shading languages that require the prior knowledge on computer graphics. Second, in a job that needs much cooperation between CPU and GPU, which is usual in image processing and pattern recognition contrary to the graphic area, CPU should generate raw feature data for GPU processing as much as possible to effectively utilize GPU performance. This paper proposes more quick and efficient implementation of neural networks on both GPU and multi-core CPU. We use CUDA (compute unified device architecture) that can be easily programmed due to its simple C language-like style instead of GPU to solve the first problem. Moreover, OpenMP (Open Multi-Processing) is used to concurrently process multiple data with single instruction on multi-core CPU, which results in effectively utilizing the memories of GPU. In the experiments, we implemented neural networks-based text extraction system using the proposed architecture, and the computational times showed about 15 times faster than implementation on only GPU without OpenMP.

• KIPS Transactions on Software and Data Engineering
• /
• v.1 no.3
• /
• pp.159-168
• /
• 2012

Relation in the new IT environment, such as the SNS, Cloud, Web3.0, has become an important factor. And these relations generate a transaction. However, existing relational database and graph database does not processe graph structure representing the relationships and transactions. This paper, we propose the technique that can be processed concurrently graph structures and transactions in a scalable complex network system. The proposed technique simultaneously save and navigate graph structures and transactions using the Topic Maps data model. Topic Maps is one of ontology language to implement the semantic web(Web 3.0). It has been used as the navigator of the information through the association of the information resources. In this paper, the architecture of the proposed technique was implemented and design using Cassandra - one of column type NoSQL. It is to ensure that can handle up to Big Data-level data using distributed processing. Finally, the experiments showed about the process of storage and query about typical RDBMS Oracle and the proposed technique to the same data source and the same questions. It can show that is expressed by the relationship without the 'join' enough alternative to the role of the RDBMS.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.6
• /
• pp.315-320
• /
• 2017

Estimating the correct pose of augmented objects on the real camera view efficiently is one of the most important questions in image tracking area. In computer vision, Homography is used for camera pose estimation in augmented reality system with markerless. To estimating Homography, several algorithm like SURF features which extracted from images are used. Based on extracted features, Homography is estimated. For this purpose, RANSAC algorithm is well used to estimate homography and DCS-RANSAC algorithm is researched which apply constraints dynamically based on Constraint Satisfaction Problem to improve performance. In DCS-RANSAC, however, the dataset is based on pattern of feature distribution of images manually, so this algorithm cannot classify the input image, pattern of feature distribution is not recognized in DCS-RANSAC algorithm, which lead to reduce it's performance. To improve this problem, we suggest the KCS-RANSAC algorithm using K-means clustering in CS-RANSAC to cluster the images automatically based on pattern of feature distribution and apply constraints to each image groups. The suggested algorithm cluster the images automatically and apply the constraints to each clustered image groups. The experiment result shows that our KCS-RANSAC algorithm outperformed the DCS-RANSAC algorithm in terms of speed, accuracy, and inlier rate.