• Korean Management Science Review
• /
• v.15 no.2
• /
• pp.109-124
• /
• 1998

Recently, as the importance placed on the design phase of system development has increased, the use of diagrams to design the overall system before implementing the actual program code has seen a proportionate increase. This study focuses on the diverse diagrams depicting organizational processes when integrating multiple processes of individual organizations to form an Inter-Organizational System(IOS). In this study, we attempt to identify the critical representation features of process diagrams that enable the effective integration of Inter-Organizational processes. In particular, the effect of the mapping relationship between the representation features of different diagrams to be integrated was tested empirically in a laboratory setting. The experimental task consisted of integrating the processes of two organization based upon the given process diagrams. Actual business processes were selected from real world cases and process diagrams were formulated based upon existing object-oriented notation. An analysis of the errors committed by the subjects during the integration process indicated that the mapping relationship between the diagram features representing the respective organizational processes had a significant impact upon the final integration outcome. Based upon these results, the present study provides a guideline for process diagrams that are crucial to effective Inter-Organizational process implementation and maintenance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.3
• /
• pp.1477-1491
• /
• 2017

Inspired by the multi-scale nature of hippocampal place cells, a biologically inspired model based on a multi-scale spatial representation for goal-directed navigation is proposed in order to achieve robotic spatial cognition and autonomous navigation. First, a map of the place cells is constructed in different scales, which is used for encoding the spatial environment. Then, the firing rate of the place cells in each layer is calculated by the Gaussian function as the input of the Q-learning process. The robot decides on its next direction for movement through several candidate actions according to the rules of action selection. After several training trials, the robot can accumulate experiential knowledge and thus learn an appropriate navigation policy to find its goal. The results in simulation show that, in contrast to the other two methods(G-Q, S-Q), the multi-scale model presented in this paper is not only in line with the multi-scale nature of place cells, but also has a faster learning potential to find the optimized path to the goal. Additionally, this method also has a good ability to complete the goal-directed navigation task in large space and in the environments with obstacles.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.35 no.12
• /
• pp.1613-1618
• /
• 2011

Analysis method for mechanism has been fully developed and relatively easy work compared to mechanism synthesis. Developing or creating a new mechanism for a given task is a creative job. In this case, a few theories are developed such as type synthesis. However, these methods are not sufficient for mechanism designers to sufficientely take into account alternative mechanism models during the initial phase of the mechanism design process. This paper presents the configuration design of mechanisms using graphical representation in the conceptual design stage. In this stage of kinematic synthesis, one needs to select mechanisms and configure appropriately to realize the desired motion of a machine. Graphical representation of mechanisms is proposed in this paper to help a designer to be highly creative and efficient in the initial design process. It is possible to easily design and analyze the mechanism of a machine by using this method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.1
• /
• pp.54-61
• /
• 2008

This paper proposes a new algorithm for detecting and recognizing overlapped objects among a stack of arbitrarily located objects using a signature representation scheme. The proposed algorithm consists of two processes of detecting overlap of objects and of determining the boundary between overlapping objects. To determine overlap of objects, in the first step, the edge image of object region is extracted and those areas in the object region are considered as the object areas if an area is surrounded by a closed edge. For each object, its signature image is constructed by measuring the distances of those edge points from the center of the object, along the angle axis, which are located at every angle with reference to the center of the object. When an object is not overlapped, its features which consist of the positions and angles of outstanding points in the signature are searched in the database to find its corresponding model. When an object is overlapped, its features are partially matched with those object models among which the best matching model is selected as the corresponding model. The boundary among the overlapping objects is determined by projecting the signature to the original image. The performance of the proposed algorithm has been tested with the task of picking the top or non-overlapped object from a stack of arbitrarily located objects. In the experiment, a recognition rate of 98% has been achieved.

• Proceedings of the KIEE Conference
• /
• 1997.11a
• /
• pp.600-602
• /
• 1997

In this study, a hybrid neural net consisting of an Adaptive LVQ(ALVQ) algorithm and MLP is proposed to perform speaker identification task. ALVQ is a new learning procedure using adaptively feature vector sequence instead of only one feature vector in training codebooks initialized by LBG algorithm and the optimization criterion of this method is consistent with the speaker classification decision rule. ALVQ aims at providing a compressed, geometrically consistent data representation. It is fit to cover irregular data distributions and computes the distance of the input vector sequence from its nodes. On the other hand, MLP aim at a data representation to fit to discriminate patterns belonging to different classes. It has been shown that MLP nets can approximate Bayesian "optimal" classifiers with high precision, and their output values can be related a-posteriori class probabilities. The different characteristics of these neural models make it possible to devise hybrid neural net systems, consisting of classification modules based on these two different philosophies. The proposed method is compared with LBG algorithm, LVQ algorithm and MLP for performance.

• Industrial Engineering and Management Systems
• /
• v.11 no.4
• /
• pp.397-405
• /
• 2012

This research proposes a framework of buffer management for multi-project systems in the critical chain project management (CCPM) method, expressed in the form of max-plus linear (MPL) representation. Since time buffers are inserted in the projects for absorbing uncertainties in task durations and protecting the completion times, the proposed method provides a procedure for frequently surveying the rates of consumed buffers and the rate of elapsed times. Their relation expresses the performance of the projects which is plotted on a chart through the completed processes. The chart presents the current performance of the projects and their interaction, which alerts managers to make necessary decisions at the right time for managing each project and the entire multi-project system. The proposed framework can analyze the complex system readily, and it enables managers to make an effective decision on scheduling. The effectiveness of the framework is demonstrated through a numerical example.

• Korean Institute of Interior Design Journal
• /
• v.15 no.3 s.56
• /
• pp.193-200
• /
• 2006

Any design process is interwoven with numerous intermediate design representations and information. On the other hand, designers proceed the design through various activities. It has always been a difficult task to model the design process, yet there are many significant research outputs that explain the design process through the cognitive approaches. This research started from the necessity of an interactive system which externalize the elements of design process in a visual or tangible manner. In order to do so, a design model, specifically a design process representation model was necessary to capture and represent design process. Several concepts such as design issue, design concept, and design form were defined through the empirical studies of design practices. The assumption is that the design process can be effectively captured by the presented system and it can help both designers and tutors review and analyze the design process. It should also help novice designers learn from expert designer's design process patterns. The system represents design process pattern in a interactive graphic environment. It also provides various useful features to enhance the analysis of design process. This paper presents theoretical groundwork and development process of the design process visualizer. The representation model is presented, and the application of the system is reviewed. Discussions on the further development directions include critical evaluation of the system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4275-4291
• /
• 2021

With the unprecedented growth of textual information on the Internet, an efficient automatic summarization system has become an urgent need. Recently, the neural network models based on the encoder-decoder with an attention mechanism have demonstrated powerful capabilities in the sentence summarization task. However, for paragraphs or longer document summarization, these models fail to mine the core information in the input text, which leads to information loss and repetitions. In this paper, we propose an abstractive document summarization method by applying guidance signals of key sentences to the encoder based on the hierarchical encoder-decoder architecture, denoted as KI-HABS. Specifically, we first train an extractor to extract key sentences in the input document by the hierarchical bidirectional GRU. Then, we encode the key sentences to the key information representation in the sentence level. Finally, we adopt key information representation guided selective encoding strategies to filter source information, which establishes a connection between the key sentences and the document. We use the CNN/Daily Mail and Gigaword datasets to evaluate our model. The experimental results demonstrate that our method generates more informative and concise summaries, achieving better performance than the competitive models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.670-684
• /
• 2024

3D Cross-Modal Retrieval (3DCMR) is a task that retrieves 3D objects regardless of modalities, such as images, meshes, and point clouds. One of the most prominent methods used for 3DCMR is the Cross-Modal Center Loss Function (CLF) which applies the conventional center loss strategy for 3D cross-modal search and retrieval. Since CLF is based on center loss, the center features in CLF are also susceptible to subtle changes in hyperparameters and external inferences. For instance, performance degradation is observed when the batch size is too small. Furthermore, the Mean Squared Error (MSE) used in CLF is unable to adapt to changes in batch size and is vulnerable to data variations that occur during actual inference due to the use of simple Euclidean distance between multi-modal features. To address the problems that arise from small batch training, we propose a Noisy Center Loss (NCL) method to estimate the optimal center features. In addition, we apply the simple Siamese representation learning method (SimSiam) during optimal center feature estimation to compare projected features, making the proposed method robust to changes in batch size and variations in data. As a result, the proposed approach demonstrates improved performance in ModelNet40 dataset compared to the conventional methods.

• Journal of the Korean Institute of Gas
• /
• v.21 no.4
• /
• pp.47-61
• /
• 2017

The preconditions of the usefulness of an operator safety training model in large plants are the versatility and accuracy of operational procedures, obtained by detailed analysis of the various types of risks associated with the operation, and the systematic representation of knowledge. In this study, we consider the artificial intelligence planning method for the generation of operation procedures; classify them into general actions, actions and technical terms of the operator; and take into account the sharing and reuse of knowledge, defining a knowledge expression ontology. In order to expand and extend the general operations of the operation, we apply a Hierarchical Task Network (HTN). Actual boiler plant case studies are classified according to operating conditions, states and operating objectives between the units, and general emergency shutdown procedures are created to confirm the applicability of the proposed method. These results based on systematic knowledge representation can be easily applied to general plant operation procedures and operator safety training scenarios and will be used for automatic generation of safety training scenarios.