• Journal of Navigation and Port Research
• /
• v.31 no.10
• /
• pp.869-877
• /
• 2007

This paper proposes a realtime scheduling method using local search algorithm for non-crossable yard cranes in automated container terminal. To take into consideration the dynamic property of yard crane operation and satisfy the real time constraint, the proposed method repeatedly builds crane schedule for the jobs in a fixed length look-ahead horizon whenever a new job is requested In addition, the proposed method enables the co-operation between yard cranes through prior re-handling and re-positioning in order to resolve the workload imbalance problem between the two cranes, which is one of the primary causes that lower the performance of yard cranes. Simulation-based experiments have shown that the proposed method outperforms the heuristic based methods, and the cooperation scheme contributes a lot to the performance improvement.

• Journal of Information Science Theory and Practice
• /
• v.7 no.4
• /
• pp.56-64
• /
• 2019

Planting intercropping in rubber plantations is another alternative for generating more income for farmers. However, farmers still lack the knowledge of choosing plants. In addition, information for decision making comes from many sources and is knowledge accumulated by the expert. Therefore, this research aims to create a decision support system for growing rubber trees for individual farmers. It aims to get the highest income and the lowest cost by using semantic web technology so that farmers can access knowledge at all times and reduce the risk of growing crops, and also support the decision supporting system (DSS) to be more intelligent. The integrated intercropping ontology and rule are a part of the decision-making process for selecting plants that is suitable for individual rubber plots. A list of suitable plants is important for decision variables in the allocation of planting areas for each type of plant for multiple purposes. This article presents designing and developing the intercropping ontology for DSS which defines a class based on the principle of intercropping in rubber plantations. It is grouped according to the characteristics and condition of the area of the farmer as a concept of the rubber plantation. It consists of the age of rubber tree, spacing between rows of rubber trees, and water sources for use in agriculture and soil group, including slope, drainage, depth of soil, etc. The use of ontology for recommended plants suitable for individual farmers makes a contribution to the knowledge management field. Besides being useful in DSS by offering options with accuracy, it also reduces the complexity of the problem by reducing decision variables and condition variables in the multi-objective optimization model of DSS.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.197-199
• /
• 2016

In this paper, we investigate a market equilibrium in multi-channel sharing cognitive radio networks (CRNs): it is assumed that every subchannel is orthogonally licensed to a single primary user (PU), and can be shared with multiple secondary users (SUs). We model this sharing as a spectrum market where PUs offer SUs their subchannels with limiting the interference from SUs; the SUs purchase the right to transmit over the subchannels while observing the interference limits set by the PUs and their budget constraints. The utility function of SU is defined as least achievable transmission rate, and that of PU is given by the net profit. We define a market equilibrium in the context of extended Fisher model, and show that the equilibrium is yielded by solving an optimization problem, Eisenberg-Gale convex program.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.43-52
• /
• 2021

In weapon assignment studies to defend against threats such as ballistic missiles and long range artillery, threat assessment was partially lacking in analysis of various threat attributes, and considering the threat characteristics of warheads, which are difficult to judge in the early flight stages, it is very important to apply more reliable optimal solutions than approximate solution using LP model, Meta heuristics Genetic Algorithm, Tabu search and Particle swarm optimization etc. Our studies suggest Generic Rule based threat evaluation and weapon assignment algorithm in the basis of various attributes of threats. First job of studies analyzes information on Various attributes such as the type of target, Flight trajectory and flight time, range and intercept altitude of the intercept system, etc. Second job of studies propose Rule based threat evaluation and weapon assignment algorithm were applied to obtain a more reliable solution by reflection the importance of the interception system. It analyzes ballistic missiles and long-range artillery was assigned to multiple intercept system by real time threat assessment reflecting various threat information. The results of this study are provided reliable solution for Weapon Assignment problem as well as considered to be applicable to establishing a missile and long range artillery defense system.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.47-53
• /
• 2021

In this paper, we propose a quadtree-based optimization technique that enables fast Super-resolution(SR) computation by efficiently classifying and dividing physics-based simulation data required to calculate SR. The proposed method reduces the time required for quadtree computation by downscaling the smoke simulation data used as input data. By binarizing the density of the smoke in this process, a quadtree is constructed while mitigating the problem of numerical loss of density in the downscaling process. The data used for training is the COCO 2017 Dataset, and the artificial neural network uses a VGG19-based network. In order to prevent data loss when passing through the convolutional layer, similar to the residual method, the output value of the previous layer is added and learned. In the case of smoke, the proposed method achieved a speed improvement of about 15 to 18 times compared to the previous approach.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.11 no.1 s.53
• /
• pp.11-19
• /
• 2007

This paper proposes an optimal design method of distribution and capacities of linear viscous dampers for vibration control of two adjacent buildings. The previous researches have dealt with suboptimal design problem under the assumption that linear viscous dampers are distributed uniformly or proportionally to the sensitivity of the modal damping ratio according to floors, whereas this study deals with global optimization problem in which the damping capacities of each floor are independently selected as design parameters. For this purpose, genetic algorithm to effectively search multiple design variables in large searching domains is adopted and objective function leading to the global optimal solutions is established through the comparison of several optimal design values obtained from different objective functions with control performance and damping capacity. The effectiveness of the proposed method is investigated by comparing the control performance and total damping capacity designed by the proposed method with those of the previous method. In addition, the time history analyses are performed by using three historical earthquakes with different frequency contents, and the simulation results demonstrate that the proposed method is an effective seismic design method for the vibration control of the adjacent structures.

• The KIPS Transactions:PartD
• /
• v.11D no.4
• /
• pp.983-990
• /
• 2004

Multiple-count problem is occurred when rectangle objects span across several buckets. The CD histogram is a technique which selves this problem by keeping four sub-histograms corresponding to the four points of rectangle. Although It provides exact results with constant response time, there is still a considerable issue. Since it is based on a query window which aligns with a given grid, a number of errors nay be occurred when it is applied to real applications. In this paper, we propose selectivity estimation techniques using the generalized cumulative density histogram based on two probabilistic models : \circled1 probabilistic model which considers the query window area ratio, \circled2 probabilistic model which considers intersection area between a given grid and objects. Our method has the capability of eliminating an impact of the restriction on query window which the existing cumulative density histogram has. We experimented with real datasets to evaluate the proposed methods. Experimental results show that the proposed technique is superior to the existing selectivity estimation techniques. Furthermore, selectivity estimation technique based on probabilistic model considering the intersection area is very accurate(less than 5% errors) at 20% query window. The proposed techniques can be used to accurately quantify the selectivity of the spatial range query on rectangle objects.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.

• Journal of KIISE:Databases
• /
• v.30 no.3
• /
• pp.336-349
• /
• 2003

Histograms have been getting a lot of attention recently. Histograms are commonly utilized in commercial database systems to capture attribute value distributions for query optimization Recently, in the advent of researches on approximate query answering and stream data, the interests in histograms are widely being spread. The simplest approach assumes that the attributes in relational tables are independent by AVI(Attribute Value Independence) assumption. However, this assumption is not generally valid for real-life datasets. To alleviate the problem of approximation on multi-dimensional data with multiple one-dimensional histograms, several techniques such as wavelet, random sampling and multi-dimensional histograms are proposed. Among them, GENHIST is a multi-dimensional histogram that is designed to approximate the data distribution with real attributes. It uses overlapping buckets that allow more efficient approximation on the data distribution. In this paper, we propose a scheme, OPT that can determine the optimal frequencies of overlapped buckets that minimize the SSE(Sum Squared Error). A histogram with overlapping buckets is first generated by GENHIST and OPT can improve the histogram by calculating the optimal frequency for each bucket. Our experimental result confirms that our technique can improve the accuracy of histograms generated by GENHIST significantly.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.10
• /
• pp.2627-2640
• /
• 1998

In this paper, we analyze the performance of the virtual cell system[1] for the transmission of IP datagrams in mobile computer communications. A virtual cell consistsof a group of physical cells shose base stationsl are implemented b recote bridges and interconnected via high speed datagram packet switched networks. Host mobility is supported at the data link layer using the distributed hierachical location information of mobile hosts. Given mobility and communication ptems among physical cells, the problem of deploying virtual cells is equivalent to the optimization cost for the entire system where interclster communication is more expesive than intracluster communication[2]. Once an iptimal partitionof disjoint clusters is obtained, we deploy the virtual cell system according to the topology of the optimal partition such that each virtual cell correspods to a cluser. To analyze the performance of the virtual cell system, we adopt a BCMP open multipel class queueing network model. In addition to mobility and communication patterns, among physical cells, the topology of the virtual cell system is used to determine service transition probabilities of the queueing network model. With various system parameters, we conduct interesting sensitivity analyses to determine network design tradeoffs. The first application of the proposed model is to determine an adequate network bandwidth for base station networking such that the networks would not become an bottleneck. We also evaluate the network vlilization and system response time due to various types of messages. For instance, when the mobile hosts begin moving fast, the migration rate will be increased. This results of the performance analysis provide a good evidence in demonsratc the sysem effciency under different assumptions of mobility and communication patterns.