• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06c
• /
• pp.407-410
• /
• 1994

In this paper, we describe the new unsuperivised learning algorithm, SASOM. It can solve the defects of the conventional SOM that the state of network can't converge to the minimum point. The proposed algorithm uses the object function which can evaluate the state of network in learning and adjusts the learning rate flexibly according to the evaluation of the object function. We implement the simulated annealing which is applied to the conventional network using the object function and the learning rate. Finally, the proposed algorithm can make the state of network converged to the global minimum. Using the two-dimensional input vectors with uniform distribution, we graphically compared the ordering ability of SOM with that of SASOM. We carried out the recognitioin on the new algorithm for all Korean phonemes and some continuous speech.

• The Transactions of the Korean Institute of Electrical Engineers C
• /
• v.50 no.7
• /
• pp.324-325
• /
• 2001

In this study, the characteristics of ultrasonic sensor fabricated with PZT-Polymer 1-3 type composites are investigated. The 3-D Underwater object recognition using the self-made ultrasonic sensor and SOFM neural network is presented. The ultrasonic sensor is satisfied with the required condition of commercial ultrasonic sensor in underwater. The 3-D underwater object recognition for the training data and the testing data are 100[100%], respectively. The experimental results have shown that the ultrasonic sensor fabricated with PZT-Polymer 1-3 type composites can be applied for sonar system.

• Journal of Korean Institute of Industrial Engineers
• /
• v.28 no.2
• /
• pp.162-170
• /
• 2002

Detecting straight lines in an image is frequently required for various machine vision applications such as restoring CAD drawings from scanned images and object recognition. The standard Hough transform has been dominantly used to that purpose. However, massive storage requirement and low precision in estimating line parameters due to the quantization of parameter space are the major drawbacks of the Hough transform technique. In this paper, to overcome the drawbacks, an iterative algorithm based on a self-organizing map is presented. The self-organizing map can be adaptively learned such that image points are clustered by prominent lines. Through the procedure of the algorithm, a set of lines are sequentially detected one at a time. The algorithm can produce highly precised estimates of line parameters using very small amount of storage memory. Computational results for synthetically generated images are given. The promise of the algorithm is also demonstrated with its application to two natural images of inserts.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.11
• /
• pp.1954-1960
• /
• 2008

Modem Robot is used in all industries. Previous Robot was used by simplicity work, at recent times, robot is developed in form that can do action such as a person. Robot's action runs according to command repeat or in the every moment according to sensor's output value, achieve other action. In this raper, we studied about self-regulation transfer robot that follow Object autonomously. This robot can be used by purpose that carry heavy burden instead of human. Robot's composition is drive part which run object's position awareness Sensor, Processor that control action and Motor part. After robot is connects with Network, we did robot remote control and monitor the action situation of robot. For the methode to reduce drive error, we developed algorithm for outside environment. For an experiment we made the self-regulation robot. We showed the directivity of sensor, error of directivity and soft moving of robot. We showed the monitoring system and the execution screen for communication between robot and PC.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.20 no.3
• /
• pp.13-23
• /
• 2024

For the purpose of predicting credit card customer churn accurately through data analysis Detecting and tracking objects in continuous video is essential in self-driving cars, security and surveillance systems, sports analytics, medical image processing, and more. Correlation tracking methods such as Normalized Cross Correlation(NCC) and Sum of Absolute Differences(SAD) are used as an effective way to measure the similarity between two images. NCC, a representative correlation tracking method, has been useful in real-time environments because it is relatively simple to compute and effective. However, correlation tracking methods are sensitive to rotation and size changes of objects, making them difficult to apply to real-time changing videos. To overcome these limitations, this paper proposes an object tracking method using the Histogram of Oriented Gradients(HOG) feature to effectively obtain object data and the Convolution Neural Network(CNN) algorithm. By using the two algorithms, the shape and structure of the object can be effectively represented and learned, resulting in more reliable and accurate object tracking. In this paper, the performance of the proposed method is verified through experiments and its superiority is demonstrated.

• Journal of Fashion Business
• /
• v.2 no.4
• /
• pp.112-125
• /
• 1998

This study is to grasp the variousness of clothing worn by elderly women with the ideal self-image by group and by finding out the characteristics of higher-image groups and lower-image group. The object of this study was a total of 488 elderly women above full 55 from an elderly women and who lived in downtown Pusan ionnaire. For statistical disposition, the analysis of factors and frequency was carried out. The results of this study are as follows : 1. As a result of the analysis of realistic self-image and ideal self-image, the realistic self-image was derived as 5 factors-voguishness, loftiness, freshness, feminality, activeness and the ideal self-image as 4 factors-activeness, loftiness, feminality, voguishness. 2. The perceptive age according to age in the realistic self -image reflects that though the 50' s percept the 50' s, the 60' s percept the 50' s and the 70' s the 60' s and also in the ideal self-image, it shows the same result. 3. The degree of satisfaction of build in the realistic self-image appeared that the 50's unsatisfied, the 60's and the 70's felt so, and in the ideal self-image, the 50's and 60's unstisfied, the 70's so. 4. The ideal image according to age in both the realistic self-image and the ideal self-image of clothing appeared that all the 50' sand 60' s wanted a good impression and the 70' s wanted a gentle impression. 5. The frequency of doing a make-up by age in all elder women according of the realistic self-image of clothing showed that the case of doing a make-up when going out only was the greatest number and also in the ideal self-image, it agrees to the same.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.10
• /
• pp.1981-1986
• /
• 2009

This paper presents new matting techniques. The matting is an alpha estimation technique of object in an image. We can extract the object in an image naturally using the matting technique. The proposed algorithms begin by segmenting an image into three regions: definitely foreground, definitely background, and unknown. Then we estimate foreground, background, and alpha for all pixels in the unknown region. The proposed algorithms learn the definitely foreground and definitely background using self-organizing map(SOM), and estimate an alpha value of each pixel in the unknown region using SOM learning result. SOM matting is distinguished between global SOM matting and local SOM matting by learning method. Experiment results show the proposed algorithms can extract the object in an image.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.2
• /
• pp.513-522
• /
• 2021

The current research aims to explore which type of identity-based message can be more persuasive for Chinese consumers to form positive restaurant brand attitude based on their cultural orientation, and to examine the roles of brand objective relevance and psychological power state in the persuasive process. The study employs a 2(identity expression focus: warmth vs. competence) × 2(message description manner: identity-defining vs. identity-referencing) × 2(experienced power state: high vs. low) between-subjects design, and conducts an online survey where 240 Chinese participants in total has responded to the questionnaires. SPSS and AMOS programs have been used to examine the hypotheses. The findings suggest that, first, the warmth-focused messages (identity-defining messages) more positively affected Chinese consumers' object relevance than the competence-focused messages (identity-referencing messages); Second, high power-experienced Chinese consumers rather than low power consumers tend to perceive more object relevance at the warmth self-defining messages; Third, brand object relevance revealed a mediation effect in the process of the warmth-focused messages (identity-defining messages) affecting brand attitude. This research offers new insight into the relationships between consumers' cultural orientation, understandings of power, and identity-based consumer behavior, suggesting marketers should take those social influences and consumer diversities into account when developing the message to persuade consumers.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.10 no.2
• /
• pp.101-106
• /
• 2010

We propose an approach to estimate the real-time moving trajectory of an object in this paper. The object's position is obtained from the image data of a CCD camera, while a state estimator predicts the linear and angular velocities of the moving object. To overcome the uncertainties and noises residing in the input data, a Extended Kalman Filter(EKF) and neural networks are utilized cooperatively. Since the EKF needs to approximate a nonlinear system into a linear model in order to estimate the states, there still exist errors as well as uncertainties. To resolve this problem, in this approach the Kohonen networks, which have a high adaptability to the memory of the inputoutput relationship, are utilized for the nonlinear region. In addition to this, the Kohonen network, as a sort of neural network, can effectively adapt to the dynamic variations and become robust against noises. This approach is derived from the observation that the Kohonen network is a type of self-organized map and is spatially oriented, which makes it suitable for determining the trajectories of moving objects. The superiority of the proposed algorithm compared with the EKF is demonstrated through real experiments.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.8 no.1
• /
• pp.157-178
• /
• 1997

1. Only 6 libraries(23.1%) among 26 surveyed libraries have a person or part in charge of continuing education. It means that the method to select education program and education object is systemless. The 19 libraries (73.1%) encourage continuing education of librarian. 2. Compared with the group who didn't receive a formal education, the group who received have a high degree in the grade of confidence, self-satisfaction and ability for job in Internet education case. And the group that received a formal education have also a high degree in the grade of ability for job in OA education case. Confidence, self-satisfaction for job in the carreer is significantly different according to the formal education in Internet education case and OA education case. Confidence, self-satisfaction and ability for Sob in the scholarship are significantly different according to the formal education in internet and computer OA education case 3. Compared with the group that didn't receive periodical education the group that received periodical education have a high degree in the grade of confidence, self-satisfaction for Job in internet education case. Confidence, self-satisfaction and ability for job in the carreer are significantly different according to the periodical education in OA education case. Confidence, self-satisfaction and ability for businessin in the scholarship are significantly different according to the periodical education in internet and OA education case. 4. Compared with the group that didn't receive self-education the group that received self-education have a high degree in the grade of confidence, self-satisfaction and ability for job in internet and OA education case. Confidence, self-satisfaction and ability for Job in the carreer are significantly different according to the self education in internet and OA education case. Confidence, self-satisfaction and ability for Job in the scholarship are significantly different according to the self-education in internet and OA education case.