• Journal of Korea Game Society
• /
• v.7 no.4
• /
• pp.93-104
• /
• 2007

In the complex real-time multi-agent system such as game environment, dynamic task allocations are repeatedly performed to achieve a goal in terms of system efficiency. In this research, we present a task allocation scheme suitable for the real-time multi-agent environment. The scheme is to optimize the task allocation by complementing existing coordination agent with $A^*$ algorithm. The coordination agent creates a status graph that consists of nodes which represent the combinations of tasks and agents, and refines the graph to remove nodes of non-execution tasks and agents. The coordination agent performs the selective utilization of the $A^*$ algorithm method and the greedy method for real-time re-allocation. Then it finds some paths of the minimum cost as optimized results by using $A^*$ algorithm. Our experiments show that the coordination agent with $A^*$ algorithm improves a task allocation efficiency about 25% highly than the coordination agent only with greedy algorithm.

• Journal of Internet of Things and Convergence
• /
• v.6 no.1
• /
• pp.83-95
• /
• 2020

Being a dense and complex task of precisely detecting the weeds in practical crop field environment, previous approaches lack in terms of speed of processing image frames with accuracy. Although much of the attention has been given to classify the plants diseases but detecting crop weed issue remained in limelight. Previous approaches report to use fast algorithms but inference time is not even closer to real time, making them impractical solutions to be used in uncontrolled conditions. Therefore, we propose a detection model for the complex rice weed detection task. Experimental results show that inference time in our approach is reduced with a significant margin in weed detection task, making it practically deployable application in real conditions. The samples are collected at two different growth stages of rice and annotated manually

• The Journal of the Korea Contents Association
• /
• v.5 no.1
• /
• pp.109-116
• /
• 2005

This paper is to develop the prototype of a decision making for loan granting system at banks and to evaluate the effectiveness of it. The prototype is called at FENET-LG in this paper. The decision to grant a loan is an unstructured and vagueness task because it is required a tremendous amount of data and many complex relationships among them. Evaluating these many data and relationships is a difficult task even for most experienced decision maker of bank. Therefore, where complex judgement is required, the decision maker of bank may benefit from the use of fuzzy expert network to support the evaluation of ability to pay back. Given the characteristics of decision maker of banking facilities judgement task about ability to pay back, the prototype system named FENET-LG is constructed by integration of fuzzy expert system and neural network. The FENET-LG takes advantage of both the deductive approach of fuzzy expert system and the inductive approach of a neural network to provide a decision aid designed to support and facilitate the process of conducting a judgement of ability to pay back.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.751-770
• /
• 2019

Action recognition is an essential task in computer vision due to the variety of prospective applications, such as security surveillance, machine learning, and human-computer interaction. The availability of more video data than ever before and the lofty performance of deep convolutional neural networks also make it essential for action recognition in video. Unfortunately, limited crafted video features and the scarcity of benchmark datasets make it challenging to address the multi-person action recognition task in video data. In this work, we propose a deep convolutional neural network-based Effective Hybrid Learning (EHL) framework for two-person interaction classification in video data. Our approach exploits a pre-trained network model (the VGG16 from the University of Oxford Visual Geometry Group) and extends the Faster R-CNN (region-based convolutional neural network a state-of-the-art detector for image classification). We broaden a semi-supervised learning method combined with an active learning method to improve overall performance. Numerous types of two-person interactions exist in the real world, which makes this a challenging task. In our experiment, we consider a limited number of actions, such as hugging, fighting, linking arms, talking, and kidnapping in two environment such simple and complex. We show that our trained model with an active semi-supervised learning architecture gradually improves the performance. In a simple environment using an Intelligent Technology Laboratory (ITLab) dataset from Inha University, performance increased to 95.6% accuracy, and in a complex environment, performance reached 81% accuracy. Our method reduces data-labeling time, compared to supervised learning methods, for the ITLab dataset. We also conduct extensive experiment on Human Action Recognition benchmarks such as UT-Interaction dataset, HMDB51 dataset and obtain better performance than state-of-the-art approaches.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.26 no.4
• /
• pp.82-90
• /
• 2003

The Systems Engineering, as a methodology for engineering and management of today's ever-growing complex system, is a comprehensive and iterative problem-solving process. The process centers on the analysis and management of the stakeholders' needs throughout the entire life-cycle of a system and searches for an optimized system architecture. There are many essential needs and requirements to be met when a system development task is carried out. Systems Engineering Management Plan(SEMP), as a specification for system development process, must be established to satisfy constraints and requirements of stakeholders successfully and to prevent cost overrun and schedule delay. SEMP defines technical management functions and comprehensive plans for managing and controlling the entire system development process, specialty engineering processes, etc. Especially. in the case of a large-scale complex system development program where various disciplinary engineering such as mechanical; electrical; electronics; control; telecommunication; material; civil engineering etc. must be synthesized, it Is essential to develop SEMP to ensure systematic and continuous process improvements for quality and to prevent cost/schedule overruns. This study will enable the process knowledge management on the subject of SEMP as a core systems engineering management effort, that is, definitely defining and continuously managing specification of development process about requirements, functions, and process realization of it using a computer-aided systems engineering software. The paper suggests a systematic SEMP development process and demonstrates a data model and schema for computer-aided systems engineering software, RDD-100, for use in the development and management of SEMP. These are being applied to the systems engineering technology development task for the next-generation high-speed railway systems in progress.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• autumn
• /
• pp.513-516
• /
• 2003

With the size of construction projects getting larger and more complex, the amount of information is increased exponentially. Although there are a lot of construction companies that try to accumulate as-built information from construction sites. it has not been quite satisfactory. This is due to the lack of task information framework that can measure project performance and collect as-built information. Therefore the objective of the paper is to identify the information that can be derived from daily reports and to suggest a unit task information framework to accumulate as-built information.

• Science of Emotion and Sensibility
• /
• v.17 no.1
• /
• pp.3-12
• /
• 2014

Quick and accurate learning of diverse electronic products has become an important daily task. In particular, software occupies core status in the control and operation of the products. This research tested the effects of learning method, schedule, and task difficulty in the learning of software. Using 2 (learning method: experiential vs. verbal) ${\times}$ 2 (learning schedule: spaced vs. massed) ${\times}$ 2 (difficulty: easy vs. difficult) between-subjects design, Experiment 1 tested participants' learning of file control using Windows Movie Maker. There was no effect of learning schedule on task completion time, but participants in experiential learning were faster in the completion of evaluation task compared with those in verbal learning condition. Importantly, as task difficulty increases participants in verbal condition showed markedly lower performance than those in experiential condition, which suggests that experiential learning is more effective with more difficult learning task. That is, in case of learning simple operation of software verbal learning using linguistic manual or instruction could be sufficient; on the other hand in case of learning complex operation learning from experience or tutorial mode would be more effective. Additional studies which manipulated task difficulty (Expt. 2) and inter-trial learning interval (Expt. 3) did not produce meaningful results.

• Journal of Computational Design and Engineering
• /
• v.3 no.3
• /
• pp.286-294
• /
• 2016

In this paper we present an efficient technique for sketch-based 3D modeling using automatically extracted image features. Creating a 3D model often requires a drawing of irregular shapes composed of curved lines as a starting point but it is difficult to hand-draw such lines without introducing awkward bumps and edges along the lines. We propose an automatic alignment of a user's hand-drawn sketch lines to the contour lines of an image, facilitating a considerable level of ease with which the user can carelessly continue sketching while the system intelligently snaps the sketch lines to a background image contour, no longer requiring the strenuous effort and stress of trying to make a perfect line during the modeling task. This interactive technique seamlessly combines the efficiency and perception of the human user with the accuracy of computational power, applied to the domain of 3D modeling where the utmost precision of on-screen drawing has been one of the hurdles of the task hitherto considered a job requiring a highly skilled and careful manipulation by the user. We provide several examples to demonstrate the accuracy and efficiency of the method with which complex shapes were achieved easily and quickly in the interactive outline drawing task.

• The Journal of Korean Physical Therapy
• /
• v.17 no.2
• /
• pp.67-87
• /
• 2005

Impaired sensorimotor function of the hand ipsilateral to a unilateral brain damage has been reported in a variety of motor task. however, it is still the controversial issue because of the difficulty of detection in clinical situation, patients' variability(time after onset, contralateral upper extremity severity, other cognitive functions including apraxia), and the performed various motor task. The purpose of this study is to determine the presence of ipsilateral motor deficit following unilateral brain damage in three different specific tasks(hand tapping, visual tracking and coin rotation) compared with healthy age-sex matched control group using the same hand and to investigate the lateralized motor control in each hemispheric function. Findings revealed that stroke patients with unilateral brain damage experienced difficulties with rapid-simple repetitive movement, visuomotor coordination, complex sequencing movement on ipsilateral side. Also, Comparison of the left-hemispheric stroke groups and the right-hemispheric stroke groups revealed that patients with a left-hemisphere damage tended to be more variable in performing all of the three tasks. These results show that stroke patient with left hemisphere damage has more ipsilateral motor deficit, and the left hemisphere contributes to the processing of motor control that necessary for the executing actions with ipsilateral hand.

• The Journal of Korean Association of Computer Education
• /
• v.12 no.6
• /
• pp.1-9
• /
• 2009

Programming learning may help to enhance learners' complex problem solving abilities. However, it may cause excessive cognitive loads for learners. Therefore, selection of programming tools and design of teaching and learning strategies to minimize the learners' cognitive loads and to maximize the learning effects. A task centered Scratch programming learning program was developed to enhance problem solving abilities of middle school students. And then, we implemented the developed program in middle school programming classes and analysed the educational effects of the developed program. We found that the developed program was helpful in enhancing learners' problem solving abilities, especially in the element of 'troubleshooting', which explains ability of error detecting and correcting.