Gu-Min Jeong

Kookmin University, Sŏul, Seoul, South Korea

Are you Gu-Min Jeong?

Claim your profile

Publications (62)19.43 Total impact

  • Source
    Gu-Min Jeong · Nguyen Trong Nghia · Sang-Il Choi
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we present a pseudo optimization method for electronic nose (e-nose) data using region selection with feature feedback based on regularized linear discriminant analysis (R-LDA) to enhance the performance and cost functions of an e-nose system. To implement cost- and performance-effective e-nose systems, the number of channels, sampling time and sensing time of the e-nose must be considered. We propose a method to select both important channels and an important time-horizon by analyzing e-nose sensor data. By extending previous feature feedback results, we obtain a two-dimensional discriminant information map consisting of channels and time units by reverse mapping the feature space to the data space based on R-LDA. The discriminant information map enables optimal channels and time units to be heuristically selected to improve the performance and cost functions. The efficacy of the proposed method is demonstrated experimentally for different volatile organic compounds. In particular, our method is both cost and performance effective for the real implementation of e-nose systems.
    Preview · Article · Dec 2014 · Sensors
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a 3D facial model reconstruction from a single frontal face image for mobile devices using cloud. In this approach, we design a cloud to receive frontal facial images to reconstruct a corresponding 3D depth map from clients that can be smartphones, computers or any other Wi-Fi supported handsets through Wi-Fi connection. The depth map and texture are then transferred back to the sending client through the configured Wi-Fi connection. This setting makes applications light-weight, portable and fast-executive to be able to install on limited specification devices. The experimental results show the advantage and accuracy of the designed system.
    No preview · Conference Paper · Oct 2014
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents case studies of robust algorithm of multi-parametric model predictive control (mpMPC). For discrete-time linear parameter-varying (LPV) systems, the robust algorithm is investigated based on the solution of the mpMPC problem for discrete-time linear time-invariant (LTI) systems. The algorithm provides a controller design method, adaptable to parameter changes of a LPV system. By this controller the performance of the controller LPV system is improved in terms of robustness particularly for slowly varying parameters in the system. Thus the design method is applicable to systems suffering from slow parameter variations due, for example, to aging or degradation. The paper illustrates two control problems, one of which is disturbance rejection problem while the other is reference tracking problem. Each control problem is studied by computer simulation. Particularly for the reference tracking problem the robust mpMPC technique not only reduces the tracking error but renders a system stable while the nominal mpMPC could not.
    No preview · Article · Aug 2014 · International Journal of Control and Automation
  • Gu-Min Jeong · Chang-Woo Park · Sujeong You · Sang-Hoon Ji
    [Show abstract] [Hide abstract]
    ABSTRACT: Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Abstract In this paper, we propose a new education assistant system model using both smartphones and service robots for children's learning. Through the interaction between a smartphone and a robot, various use cases can be derived. For example, we can control the movement of the robot remotely, watch the status of the children using real-time streaming, or read the answer on the smartphone while only the question is displayed on the robot. Considering these facts, we present three use cases, namely 'remote control', 'streaming' and 'N-screen' for robot-based learning with smartphones. The proposed learning model is implemented in Android-based smartphones and a service robot using the OPRoS platform, and we show that the proposed model works well.1
    No preview · Article · Apr 2014 · International Journal of Advanced Robotic Systems
  • Source
    Sang-Il Choi · Gu-Min Jeong
    [Show abstract] [Hide abstract]
    ABSTRACT: We present a composite vector selection method for an effective electronic nose system that performs well even in noisy environments. Each composite vector generated from a electronic nose data sample is evaluated by computing the discriminant distance. By quantitatively measuring the amount of discriminative information in each composite vector, composite vectors containing informative variables can be distinguished and the final composite features for odor classification are extracted using the selected composite vectors. Using the only informative composite vectors can be also helpful to extract better composite features instead of using all the generated composite vectors. Experimental results with different volatile organic compound data show that the proposed system has good classification performance even in a noisy environment compared to other methods.
    Preview · Article · Apr 2014 · Sensors
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a capacity modeling method for Bluetooth based LBSs (Location Based Services) between Bluetooth APs(Access Points) and mobile phones. In order to do this, we consider the entrance and exit of the users to and from the AP. Using parameters such as the connection time, data transmission time and number of users in the AP zone, we analyze the capacity of a Bluetooth AP using an appropriate queuing model. The required number of APs in a certain zone is estimated from the number of users in the zone using the proposed queuing model. By performing simulations and experiments, the validity and applicability of the proposed method are verified.
    No preview · Article · Jan 2013 · Journal of Electrical Engineering and Technology
  • Gu-Min Jeong · Sang-Hoon Ji

    No preview · Article · Jan 2013 · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences
  • Source
    Sang-Il Choi · Gu-Min Jeong · Chunghoon Kim
    [Show abstract] [Hide abstract]
    ABSTRACT: We present an effective portable e-nose system that performs well even in noisy environments. Considering the characteristics of the e-nose data, we use an image covariance matrix-based method for extracting discriminant features for vapor classification. To construct composite vectors, primitive variables of the data measured by a sensor array are rearranged. Then, composite features are extracted by utilizing the information about the statistical dependency among multiple primitive variables, and a classifier for vapor classification is designed with these composite features. Experimental results with different volatile organic compounds data show that the proposed system has better classification performance than other methods in a noisy environment.
    Full-text · Article · Dec 2012 · Sensors
  • Gu-Min Jeong · Dong-Byeong Kang · Sung-Soo Lim · Nikil Dutt
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we present the design of an advanced course on mobile embedded software, especially focused on Android programming for various embedded system applications. With the popularity of smartphone applications, there are numerous books and classes for smartphone programming. However, fast growing mobile technologies have led to a huge gap between advances in industry and university educational programs. Furthermore, trends in device convergence based on smartphones necessitate a broadened and diversified treatment of application domains such as automotive embedded systems and smart robots. Consequently, an advanced project course in mobile embedded software requires a complete redesign of its contents to meet these multiple goals. We describe our experience in redesigning an Android programming course to satisfy both the fundamental educational needs and industry trends. Based on the proposed design, we offered a successful course, "CS 190: Mobile Embedded SW with Android" at UC Irvine in Spring Quarter 2012, and describe our experience with the offering.
    No preview · Conference Paper · Oct 2012
  • Gu-Min Jeong · Chanwoo Moon · Hyun-Sik Ahn
    [Show abstract] [Hide abstract]
    ABSTRACT: This letter investigates an iterative learning control with advanced output data (ADILC) scheme for non-minimum phase (NMP) systems when the number of NMP zeros is unknown. ADILC has a simple learning structure that can be applied to both minimum phase and NMP systems. However, in the latter case, it is assumed that the number of NMP zeros is already known. In this paper, we propose an ADILC scheme in which the number of NMP zeros is unknown. Based on input-to-output mapping, the learning starts from the relative degree. When the input becomes larger than a certain upper bound, we redesign the input update law which consists of the relative degree and the estimated value for the number of NMP zeros.
    No preview · Article · Aug 2012 · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences
  • Sang-Il Choi · Chong-Ho Choi · Gu-Min Jeong · Nojun Kwak
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a pixel selection method in a face image based on discriminant features for face recognition. By analyzing the relationship between the pixels in face images and features extracted from them, the pixels that contain a large amount of discriminative information are selected, while the pixels with less discriminative information are discarded. The experimental results obtained with various face databases show that the proposed pixel selection method results in improved recognition performance, especially in the presence of illumination or facial expression variations. Additionally, the proposed method greatly reduces the memory size and computational load in the face recognition process.
    No preview · Article · Jul 2012 · Pattern Recognition Letters
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a WPAN (Wireless Personal Area Net-work) platform for converged network services integrating a cellular network and a WPAN. We mainly focus on an easy-to-develop and easy-to-use WPAN platform for wireless communication services using both networks. The pro-posed WPAN platform consists of a WPAN handset platform, a WPAN con-nection scheme, and a WPAN server platform. The WPAN handset platform provides abstract WPAN API (Application Programming Interface) set and ap-plication management module. Using the WPAN connection scheme, the user can enjoy converged network services in a convenient way. The WPAN server platform manages the overall services and digital devices that are connected to the handset. Compared to the existing WPAN related platform, we consider the need for the integrated service components allowing for the development of WPAN applications in the handset and their convenience for the user. Also, illustrative services and devices are implemented using the proposed method, which show the applicability of the proposed WPAN platform.
    Full-text · Article · Apr 2012
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents the paradigm shift and the state of the art of LBS(Location Based Service) in the recent mobile environment. The advent of smartphone, especially, HW(Hardware) for localization, the middleware for LBS and map DB(Database), leads a big step towards LBS as a killer application. The LBS grows very fast with various smartphone applications. In feature phone, the service area of LBS was limited and the main usage was finding buddy. However, in smartphone, LBS merges other killer applications such as SNS(Social Network Service), AR(Augmented Reality), game, mobile commerce and so on. The abrupt evolution of technology and service requires appropriate laws and systems for the future development. KeywordsLBS–Smartphone–Platform–Applications
    No preview · Chapter · Oct 2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we present a control system allowing users to control R-Learning robot using Android smart phone. The presented control system consists of an application for Android smartphone and an application embedded in R-Learning robot. Two important roles of this system are assuring safety and working as an assistant. Therefore, if smartphone is used with R-Leaning, we can provide more functions to teachers and students and it will be helpful to the learning. Technically, when robot using smartphone, the program embedded in robot will receive related information and control values from smart phone and move robot to desired position. Also, the smartphone displays the related information to the teacher different from that of robot.
    No preview · Conference Paper · Sep 2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we introduce a control algorithm for robot simulator in educational platform. This platform is used to execute and check contents which are used for English education, making it more convenient for content developers. When the educational contents are executed, control values in contents are sent to the robot simulator to control its motion. In addition, robot motion can be controlled directly from the platform manually. Also, a PID controller is used to improve the performance of robot simulator.
    No preview · Conference Paper · Sep 2011
  • Sung-Hun Shin · Jong-Yun Yeo · Sang-Hoon Ji · Gu-Min Jeong
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a method of analyzing vibration sensor data for smartphone camera applications and apply it to the smartphone. Vibration is one of the main features influencing the quality of camera image. Based on these facts, we need a method to prevent the image-blurring phenomenon on a smart phone. In this paper, we have performed an analysis and reconstruction the data from installed sensor on the smart phone in order to compute accurate vibration values. An implementation of smartphone application shows the validity and applicability of the proposed method for assisting smartphone camera function.
    No preview · Conference Paper · Sep 2011
  • Jong-Yun Yeo · Yong Dae Lee · Sang-Hoon Ji · Gu-Min Jeong
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a hand-writing message system for smartphone using digital pen. Existing messaging systems can only send a message through MMS and cannot utilize various SNS (Social Network Service) because it uses feature phone environment. A proposed messaging system based on smartphone can utilize SNS and can create new systems. We verify usefulness of it by implementation.
    No preview · Conference Paper · Jan 2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper improves the performance of Feature Feedback and presents its application to face recognition. Feature Feedback has been introduced as a method which focuses on preprocessing the input data before classification. After extracting the features from original, Feature Feedback identifies the important part of the original data through the reverse mapping from the extracted features to the original space. In the feature extraction step, original feature feedback used PCA before LDA to avoid the small sample size problem but it has been shown that this may cause loss of significant discriminatory information. To overcome that problem, in the proposed method, we introduce feature feedback using regularized Fisher's separability criterion to extract the features and apply it to face recognition using the Yale data. The experimental results show that the proposed method works well.
    No preview · Conference Paper · Jan 2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we improve the performance of Feature Feedback and present its application for vapor classification in a portable E-Nose system. Feature Feedback is a preprocessing method which detects and removes unimportant information from input data so that classification performance is improved. In our original Feature Feedback algorithm, PCA is used before LDA in order to avoid the small sample size (SSS) problem but it is said that this may cause loss of significant discriminant information for classification. To overcome this, in the proposed method, we improve Feature Feedback using regularized Fisher's separability criterion to extract the features and apply it to E-Nose system. The experimental result shows that the proposed method works well.
    No preview · Conference Paper · Jan 2011
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose and implement the automated brightness control system using distance measuring sensor for reducing the power consumption of emotional lighting device. In order to reduce the power consumption of emotional lighting devices which express continuous color changes, the proposed device measures the distance continuously using ultrasonic sensor and by using this, it also performs PWM Dimming control. The lighting device is composed of micro controller, LED driver, ultrasonic sensor, communication module and so on. And the device performs the real time brightness control by adapting the measured distance information from ultrasonic sensor to PWM signals. From this experiment, we implement the active lighting system which minimizes unnecessary power consumption during user's absence by adapting existing energy reducing techniques.
    Preview · Article · Jan 2011