• Journal of KIISE
• /
• v.43 no.7
• /
• pp.781-785
• /
• 2016

Learning from human behaviors in the real world is essential for human-aware intelligent systems such as smart assistants and autonomous robots. Most of research focuses on correlations between sensory patterns and a label for each activity. However, human activity is a combination of several event contexts and is a narrative story in and of itself. We propose a novel approach of human activity prediction based on event cognition. Egocentric multi-sensor data are collected from an individual's daily life by using a wearable device and smartphone. Event contexts about location, scene and activities are then recognized, and finally the users" daily activities are predicted from a decision rule based on the event contexts. The proposed method has been evaluated on a wearable sensor data collected from the real world over 2 weeks by 2 people. Experimental results showed improved recognition accuracies when using the proposed method comparing to results directly using sensory features.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.3
• /
• pp.31-39
• /
• 2006

This paper presents a novel approach to real-time recognition of 3D environment and objects for various applications such as intelligent robots, intelligent vehicles, intelligent buildings,..etc. First, we establish the three fundamental principles that humans use for recognizing and interacting with the environment. These principles have led to the development of an integrated approach to real-time 3D recognition and modeling, as follows: 1) It starts with a rapid but approximate characterization of the geometric configuration of workspace by identifying global plane features. 2) It quickly recognizes known objects in environment and replaces them by their models in database based on 3D registration. 3) It models the geometric details the geometric details on the fly adaptively to the need of the given task based on a multi-resolution octree representation. SIFT features with their 3D position data, referred to here as stereo-sis SIFT, are used extensively, together with point clouds, for fast extraction of global plane features, for fast recognition of objects, for fast registration of scenes, as well as for overcoming incomplete and noisy nature of point clouds.

• Journal of the Korea Convergence Society
• /
• v.10 no.3
• /
• pp.249-256
• /
• 2019

The purpose of this study was to inquire into the structural relations between teachers' attitudes, academic engagement, task-solving behavior which are perceived in a physical education class. To this end, this study selected a total of 434 copies of questionnaires as final valid samples using the convenience sampling method targeting middle school students at 5 schools located at a metropolitan area. For data processing, this study confirmed the goodness of fit test of the whole model using SPSS 20.0 and AMOS 20.0, and then did hypothesis testing; the study results are as follows: first, teachers' attitudes was to have influence on academic engagement. Second, academic engagement had positive influence on help-seeking, while self-handicapping had significantly negative influence. Third, teachers' attitudes had positive influence on help-seeking, while self-handicapping had significantly negative influence. Lastly, in the relationship between teachers' attitudes and task-solving behavior, academic engagement was found to play an intermediary role.

• Journal of the Korea Convergence Society
• /
• v.9 no.12
• /
• pp.33-38
• /
• 2018

Recently, we are trying to predict the emotion from various information and to convey the emotion information that the supervisor wants to inform the audience. In addition, audiences intend to understand the flow of emotions through various information of non-dialogue parts, such as cinematography, scene background, background sound and so on. In this paper, we propose to extract emotions by mixing not only the context of scripts but also the cinematography information such as color, background sound, composition, arrangement and so on. In other words, we propose an emotional prediction system that learns and distinguishes various emotional expression techniques into dialogue and non-dialogue regions, contributes to the completeness of the movie, and quickly applies them to new changes. The precision of the proposed system is improved by about 5.1% and 0.4%, and the recall is improved by about 4.3% and 1.6%, respectively, when compared with the modified n-gram and morphological analysis.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.83-90
• /
• 2023

Blurred image is an important factor in lowering image recognition rates in Computer vision. This mainly occurs when the camera is unstablely out of focus or the object in the scene moves quickly during the exposure time. Blurred images greatly degrade visual quality, weakening visibility, and this phenomenon occurs frequently despite the continuous development digital camera technology. In this paper, it replace the modified building module based on the Deep multi-patch neural network designed with convolution neural networks to capture details of input images and Attention techniques to focus on objects in blurred images in many ways and strengthen the image. It measures and assigns each weight at different scales to differentiate the blurring of change and restores from rough to fine levels of the image to adjust both global and local region sequentially. Through this method, it show excellent results that recover degraded image quality, extract efficient object detection and features, and complement color constancy.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.87-93
• /
• 2023

In this paper, we propose a system that accurately and efficiently determines forward head posture based on network learning by analyzing the user's skeletal posture. Forward head posture syndrome is a condition in which the forward head posture is changed by keeping the neck in a bent forward position for a long time, causing pain in the back, shoulders, and lower back, and it is known that daily posture habits are more effective than surgery or drug treatment. Existing methods use convolutional neural networks using webcams, and these approaches are affected by the brightness, lighting, skin color, etc. of the image, so there is a problem that they are only performed for a specific person. To alleviate this problem, this paper extracts the skeleton from the image and learns the data corresponding to the side rather than the frontal view to find the forward head posture more efficiently and accurately than the previous method. The results show that the accuracy is improved in various experimental scenes compared to the previous method.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.7
• /
• pp.335-347
• /
• 2024

Open-vocabulary 3D point cloud instance segmentation (OV-3DIS) is a challenging visual task to segment a 3D scene point cloud into object instances of both base and novel classes. In this paper, we propose a novel model Open3DME for OV-3DIS to address important design issues and overcome limitations of the existing approaches. First, in order to improve the quality of class-agnostic 3D masks, our model makes use of T3DIS, an advanced Transformer-based 3D point cloud instance segmentation model, as mask proposal module. Second, in order to obtain semantically text-aligned visual features of each point cloud segment, our model extracts both 2D and 3D features from the point cloud and the corresponding multi-view RGB images by using pretrained CLIP and OpenSeg encoders respectively. Last, to effectively make use of both 2D and 3D visual features of each point cloud segment during label assignment, our model adopts a unique feature ensemble method. To validate our model, we conducted both quantitative and qualitative experiments on ScanNet-V2 benchmark dataset, demonstrating significant performance gains.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.5
• /
• pp.55-68
• /
• 2021

The purpose of this study is to analyze the characters and narratives of series films and to extract corresponding elements of film music to compare and analyze how musical elements were utilized. The scope of the study was analyzing the story structure and characters of the films "Mary Poppins" and "Mary Poppins Returns" and the corresponding film music. After comparing the contents of the film "Mary Poppins" and "Mary Poppins Returns," the film matched the film music equivalent to the similar scenes of the two films. As a result, seven of the 11 songs of "Mary Poppins" overlap with those used in similar narratives of "Mary Poppins Returns", and eight songs overlap in "Mary Poppins Returns". Seven songs from "Mary Poppins" and eight songs from "Mary Poppins Returns" can be divided into nine scenes in total when connected to a common narrative. Among them, "A Spoonful of Sugar" from "Mary Poppins", "Jolly Holiday", "A cover is not the Book" from "Mary Poppins Returns" and "Triple light fantastic" were overlapping songs with narratives. Based on this, it analyzes leitmotiv film music, focusing on characters from the films "Mary Poppins" and "Mary Poppins Returns." The common leitmotivs in the two films are Mary Poppins leitmotiv, Lesson leitmotiv, Lullaby leitmotiv, World leitmotiv, Chimney Sweeper leitmotiv, Up & Down leitmotiv, Chimney Sweeper leitmotiv, and Sky leitmotiv. The characteristic rhythm and pitch used in Mary Poppins leitmotivs were used in the overall song featuring Mary Poppins. Through this, the elements of music symbolizing Mary Poppins, a key figure, were matched to the films "Mary Poppins" and "Mary Poppins Returns" and modified according to the narrative flow. The analysis results of this work have theoretical significance in that it is necessary to analyze the narratives and film music of series films to discover common features and consider how they are matched in theoretical terms.

• Journal of Elementary Mathematics Education in Korea
• /
• v.21 no.2
• /
• pp.263-289
• /
• 2017

New mathematics textbooks for elementary school students are under development according to the 2015 national revised curriculum. Not only contents but also framework of textbooks may be interesting to the mathematics educators and researchers. Considering the high dependency on textbooks in elementary classrooms, the influence of the framework of textbooks in mathematics learning cannot be overlooked. The unit and lesson frameworks of the textbook are important because they are directly related to the quality of mathematic lessons, especially when teachers make a lesson plan based on the unit and lesson frameworks of the textbook. This study is to analyse the unit and lesson frameworks of elementary school mathematics textbooks and to find out elementary school teachers' preference about its analysed key points. For longitudinal analysis, we selected 3rd-grade mathematics textbooks of 5th, 6th, 7th, the 2007, and the 2009 national revised curriculums. For horizontal analysis, we selected 3rd-grade mathematics textbooks of Korea, Japan, United States and Finland. We compared unit and lesson frameworks of various textbooks, and abstracted key elements of the textbook frameworks, and constructed survey questions. Looking at results from survey questions based on analysed key points, we were able to grasp the teachers' preference for unit and lesson frameworks for mathematics textbook. Based on the results of this study, some implications for the development of framework for new mathematics textbooks are suggested.

• Journal of Science Education
• /
• v.35 no.2
• /
• pp.149-158
• /
• 2011

The purpose of this study is to improve education program for Informal Science Education Institution by analyzing education program of Natural History Museum, one of informal science education institution. This research subject is Seodaemun Museum of Natural History, located in Seodaemun-Gu, Seoul. It is Public Natural History Museum, which runs more than 60 education programs every year continuously for recent 6 years. Objects of this study are 32 education programs for 3rd to 6th grade of elementary school. The result of study shows that teaching materials of programs, run by informal science education institution, don't contain enough script and activity for improving creativity and inquiring mind. As the result of the study, it is required that guidance plan of education program be developed with more activities, teaching method and script, to seek quality of class than quantity of that when developing education program of science education institutes. And it is required to develop teaching material using creative technique and to improve medium and long term program for development of feedback.