• Journal of KIISE
• /
• v.43 no.8
• /
• pp.848-856
• /
• 2016

Seeking and recognizing maritime targets are very important tasks for maritime safety. While searching for maritime targets using radar is possible, recognition is conducted without automatic identification system, radio communicator or visibility. If this recognition is not feasible, radar operator must tediously recognize maritime targets using movement features on radar base on know-how and experience. In this paper, to support the radar operator's mission of continuous observation, we propose an algorithm for automatic recognition of an unknown ship using movement features on radar and a method of detecting potential ship related accidents. We extract features from contact range, course and speed of four types of vessels and evaluate the recognition accuracy using SVM and suggest a method of detecting potential ship related accidents through the algorithm. Experimentally, the resulting recognition accuracy is found to be more than 90% and presents the possibility of detecting potential ship related accidents through the algorithm using information of MV Sewol. This method is an effective way to support operator's know-how and experience in various circumstances and assist in detecting potential ship related accidents.

• Journal of KIISE:Computing Practices and Letters
• /
• v.11 no.2
• /
• pp.112-123
• /
• 2005

The latest E-commerce sites provide personalized services to maximize user satisfaction for Internet user The collaborative filtering is an algorithm for personalized item real-time recommendation. Various supplementary methods are provided for improving the accuracy of prediction and performance. It is important to consider these two things simultaneously to implement a useful recommendation system. However, established studies on collaborative filtering technique deal only with the matter of accuracy improvement and overlook the matter of performance. This study considers representative attribute-neighborhood, recommendation textile set, and similarity grouping that are expected to improve performance to the recommendation agent system. Ultimately, this paper suggests empirical applications to verify the adequacy and the validity on this system with the development of Fashion Design Recommendation Agent System (FDRAS ).

• The Journal of the Korea Contents Association
• /
• v.19 no.7
• /
• pp.91-98
• /
• 2019

The purpose of this study was to develop and test an eye tracker focusing on early childhood participants, based on the characteristics of early childhood eye tracking studies. Eye tracking collects eye movement data of the subject, which provides scientific evidence of human cognition and thinking. The researcher built a Do It Yourself eye tracker camera module from general electronic components, and used Viewpoint analysis software from Arrington Research. The researcher compared the eye tracking data between the DIY eye tracker group and Tobii Pro eye tracker group, which provides a professional eye tracking system. Eye tracking data was collected from 52 five-year old children. The average proportion of valid trials between the two groups was compared with t test, and no significant difference was found. This result indicates that the DIY eye tracker can be used to collect valid eye tracking data from young children under certain research environment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1762-1769
• /
• 2021

The final goal of this study is to develop a system that can analyze whether a wanted vehicle is a criminal vehicle from images collected from black boxes, smartphones, CCTVs, and so on. Data collection was collected using a self-developed black box. The used data in this study has used a total of 83,753 cases such as the eight vehicle types(truck, RV, passenger car, van, SUV, bus, sports car, electric vehicle) and 434 vehicle models. As a result of vehicle recognition using YOLO v5, mAP was found to be 80%. As a result of identifying the vehicle model with ReXNet using the self-developed black box, the accuracy was found to be 99%. The result was verified by surveying field police officers. These results suggest that improving the accuracy of data labeling helps to improve vehicle recognition performance.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1307-1312
• /
• 2023

In this paper, we propose a hybrid camera system that combines cameras with different focal lengths and LiDAR (Light Detection and Ranging) sensors to address the core components of autonomous driving perception technology, which include object recognition and distance measurement. We extract objects within the scene and generate precise location and distance information for these objects using the proposed hybrid camera system. Initially, we employ the YOLO7 algorithm, widely utilized in the field of autonomous driving due to its advantages of fast computation, high accuracy, and real-time processing, for object recognition within the scene. Subsequently, we use multi-focal cameras to create depth maps to generate object positions and distance information. To enhance distance accuracy, we integrate the 3D distance information obtained from LiDAR sensors with the generated depth maps. In this paper, we introduce not only an autonomous vehicle platform capable of more accurately perceiving its surroundings during operation based on the proposed hybrid camera system, but also provide precise 3D spatial location and distance information. We anticipate that this will improve the safety and efficiency of autonomous vehicles.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.9
• /
• pp.45-53
• /
• 2014

This paper suggests methods to chronicle and track the history of dialogues exchanged among characters to prevent logical errors of a story. As for stories that are long with many characters, especially in full-length novels and co-written stories, cognitive burden is imposed on a writer. If the writer has confused understanding of a character, then a logical error would enter the story. This would compromise completeness and integrity of writing. Against the backdrop, this paper shows how dialogues among characters are chronicled and tracked by using the aforementioned tracking methods through design of a writer support system that relieves a writer's cognitive burden while supporting the writing and through an analysis of existing novels. In addition, we showed the accuracy results of average 68.5% through the performance evaluation of the query used in the dialogue history tracking.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.3
• /
• pp.1-6
• /
• 2018

With the increase of the elderly population, demand for improvement of quality of life and measurement of mental state has increased. However, much of the self-reported diagnosis does not reflect cognitive impairment. This study aims to measure the dwelling depression by applying K-HTP and verify the validity. 301 persons over 65 years old who live as single and couple households in Daejeon and surrounding districts were surveyed during 22 January to 2 February, 2018. The correlations between the dwelling depression and K-HTP are clarified and the validity was evaluated. The correlations between the geriatric dwelling depression index(GDDI) and the GDDI based on K-HTP(GDDI-K) are clarified and the accuracy was analyzed. The results showed that the K-HTP can be utilized to measure the dwelling depression. We suggested a new measurement tool and provide further benefits for researches on diagnoses using the projective method.

• Korean Journal of Cognitive Science
• /
• v.22 no.2
• /
• pp.103-121
• /
• 2011

This study investigated how spatial dimension information and dimensional consistency between learning and testing phase would influence the target search performance. The participants learned spatial layouts of Lego blocks shown in either two- (2D) or three-dimension (3D) and were tested with the rotated stimuli ($0^{\circ}$, $90^{\circ}$, $180^{\circ}$, or $270^{\circ}$ from the initial view) in consistent or inconsistent dimension. Significantly better performance was observed when initial learning display appeared in 2D than in 3D. Particularly, the participants showed difficulties in flexible usage of spatial information presented in 3D especially if the dimensional information in the testing phase also was 3D and required mental rotation. The present study indicates that spatial map presented in 2D may be more useful than 3D in driving situations in which acquired spatial information from navigating device, such as GPS, and location of driver continuously changes.

• Korean Journal of Cognitive Science
• /
• v.17 no.4
• /
• pp.287-301
• /
• 2006

Two experiments were performed to investigate effects of background depth information on the judgment of two-dimensional shapes, using the Posner et al.'s(1969) physical match task. In both experiments, the focus was on whether the background depth information affects the decisions of physical shape sameness of two letters or figures presented successively. In Experiment 1, artificially constructed rues of linear perspective and texture gradient were used, whereas cues contained in a real road situation were used in Experiment 2. The results of both experiments showed that the depth cues affect the perception of two-dimensional shapes. That is, when two stimuli of the same physical shape were likely to be perceived differently due to the given depth cues, response accuracies('yet' in this case) decreased and reaction tines of physical match increased. And when two stimuli of the different physical shape were likely to be perceived the same due to the given depth cues, response accuracies('no' in this case) decreased and reaction times of physical match increased likewise. These results wert discussed in terms of some conceptual methodological problems of the previous studies on the shape constancy and the directions of future research.

• Korean Journal of Cognitive Science
• /
• v.22 no.4
• /
• pp.347-364
• /
• 2011

In this paper, we propose a automatic image bases extraction method for visual image reconstruction from brain activity using Non-negative Matrix Factorization (NMF). Image bases are basic elements to construct and present a visual image. Previous method used brain activity that evoked by predefined 361 image bases of four different sizes: $1{\times}1$, $2{\times}1$, $1{\times}2$, $2{\times}2$, and $2{\times}2$. Then the visual stimuli were reconstructed by linear combination of all the results from these image bases. While the previous method used 361 predefined image bases, the proposed method automatically extracts image bases which represent the image data efficiently. From the experiments, we found that the proposed method reconstructs the visual stimuli better than the previous method.