• Journal of KIISE:Information Networking
• /
• v.30 no.2
• /
• pp.282-292
• /
• 2003

This paper proposes an efficient data structure for forwarding IPv4 and IPv6 packets at the gigabit speed in backbone routers. The LPM(Longest Prefix Matching) search becomes a bottleneck of routers' performance since the LPM complexity grows in proportion to the forwarding table size and the address length. To speed up the forwarding process, this paper introduces a data structure named BMT(Bit-Map Tie) to minimize the frequent main memory accesses. All the necessary search computations in BMT are done over a small index table stored at cache. To build the small index table from the tie representation of the forwarding table, BMT represents a link pointer to the child node and a node pointer to the corresponding entry in the forwarding table with one bit respectively. To improve the poor performance of the conventional tries when their height becomes higher due to the increase of the address length, BMT adopts a binary search algorithm for determining the appropriate level of tries to start. The simulation experiments show that BMT compacts the IPv4 backbone routers' forwarding table into a small one less than 512-kbyte and achieves the average speed of 250ns/packet on Pentium II processors, which is almost the same performance as the fastest conventional lookup algorithms.

• Journal of Korea Water Resources Association
• /
• v.55 no.spc1
• /
• pp.1283-1293
• /
• 2022

The purpose of this study is to predict residual chlorine in order to maintain stable residual chlorine concentration in sedimentation basin by using artificial intelligence algorithms in water treatment process employing pre-chlorination. Available water quantity and quality data are collected and analyzed statistically to apply into mathematical multiple regression and artificial intelligence models including multi-layer perceptron neural network, random forest, long short term memory (LSTM) algorithms. Water temperature, turbidity, pH, conductivity, flow rate, alkalinity and pre-chlorination dosage data are used as the input parameters to develop prediction models. As results, it is presented that the random forest algorithm shows the most moderate prediction result among four cases, which are long short term memory, multi-layer perceptron, multiple regression including random forest. Especially, it is result that the multiple regression model can not represent the residual chlorine with the input parameters which varies independently with seasonal change, numerical scale and dimension difference between quantity and quality. For this reason, random forest model is more appropriate for predict water qualities than other algorithms, which is classified into decision tree type algorithm. Also, it is expected that real time prediction by artificial intelligence models can play role of the stable operation of residual chlorine in water treatment plant including pre-chlorination process.

• The KIPS Transactions:PartA
• /
• v.11A no.7 s.91
• /
• pp.555-562
• /
• 2004

Both global volume reduction and local shape changes of hippocampus within the brain indicate their abnormal neurological states. Hippocampal shape analysis consists of two main steps. First, construct a hippocampal shape representation model ; second, compute a shape similarity from this representation. This paper proposes a novel method for the analysis of hippocampal shape using integrated Octree-based representation, containing meshes, voxels, and skeletons. First of all, we create multi-level meshes by applying the Marching Cube algorithm to the hippocampal region segmented from MR images. This model is converted to intermediate binary voxel representation. And we extract the 3D skeleton from these voxels using the slice-based skeletonization method. Then, in order to acquire multiresolutional shape representation, we store hierarchically the meshes, voxels, skeletons comprised in nodes of the Octree, and we extract the sample meshes using the ray-tracing based mesh sampling technique. Finally, as a similarity measure between the shapes, we compute $L_2$ Norm and Hausdorff distance for each sam-pled mesh pair by shooting the rays fired from the extracted skeleton. As we use a mouse picking interface for analyzing a local shape inter-actively, we provide an interaction and multiresolution based analysis for the local shape changes. In this paper, our experiment shows that our approach is robust to the rotation and the scale, especially effective to discriminate the changes between local shapes of hippocampus and more-over to increase the speed of analysis without degrading accuracy by using a hierarchical level-of-detail approach.

• Journal of the Korea Computer Graphics Society
• /
• v.16 no.1
• /
• pp.1-7
• /
• 2010

With the widespread use of vision-based surveillance systems, the capability for person identification is now an essential component. However, the CCTV cameras used in surveillance systems tend to produce relatively low-resolution images, making it difficult to use face recognition techniques for person identification. Therefore, an algorithm is proposed for person identification in CCTV camera images based on the clothing. Whenever a person is authenticated at the main entrance of a building, the clothing feature of that person is extracted and added to the database. Using a given image, the clothing area is detected using background subtraction and skin color detection techniques. The clothing feature vector is then composed of textural and color features of the clothing region, where the textural feature is extracted based on a local edge histogram, while the color feature is extracted using octree-based quantization of a color map. When given a query image, the person can then be identified by finding the most similar clothing feature from the database, where the Euclidean distance is used as the similarity measure. Experimental results show an 80% success rate for person identification with the proposed algorithm, and only a 43% success rate when using face recognition.

• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.1
• /
• pp.9-20
• /
• 2005

Recently, the MPEG-7 standard a multimedia content description standard is wide]y used for content based image/video retrieval systems. However, since the descriptors standardized in MPEG-7 are usually multidimensional and the problem called 'Curse of dimensionality', previously proposed indexing methods(for example, multidimensional indexing methods, dimensionality reduction methods, filtering methods, and so on) could not be used to effectively index the multimedia database represented in MPEG-7. This paper proposes an efficient multimedia data indexing mechanism reflecting the characteristics of MPEG-7 visual descriptors. In the proposed indexing mechanism, the descriptor is transformed into a histogram of some attributes. By representing the value of each bin as a binary number, the histogram itself that is a visual descriptor for the object in multimedia database could be represented as a bit string. Bit strings for all objects in multimedia database are collected to form an index file, bitmap index, in the proposed indexing mechanism. By XORing them with the descriptors for query object, the candidate solutions for similarity search could be computed easily and they are checked again with query object to precisely compute the similarity with exact metric such as Ll-norm. These indexing and searching mechanisms are efficient because the filtering process is performed by simple bit-operation and it reduces the search space dramatically. Upon experimental results with more than 100,000 real images, the proposed indexing and searching mechanisms are about IS times faster than the sequential searching with more than 90% accuracy.

• The KIPS Transactions:PartA
• /
• v.9A no.2
• /
• pp.241-248
• /
• 2002

With the structure of tilde-area computing system which Is specified by a researching team in Vrije University, Netherlands, lots of researchers and developers have been progressing the studies of global location and interconnection services of distributed objects existing in global sites. Most of them halve focused on binding services of only non-duplicated computational objects existing wide-area computing sites without any consideration of duplication problems. But all of objects existing on the earth rave the duplicated characteristics according to how to categorize their own names or properties. These objects with the same property can define as duplicated computational objects. Up to now, the existing naming or trading mechanism has not supported the binding services of duplicated objects, because of deficiency of independent location service. For this reason, we suggest a new model that can not only manages locations of duplicated objects In wide-area computing environments, but also provide minimum binding time by considering both the optimal selection of one of duplicated objects and load balance among distributed systems. Our model is functionally divided into 2 parts, one part to obtain an unique object handle of duplicated objects with same property as a naming and trading service, and the other to search one or more contact addresses by a node manager using a liven object handle, as a location service For location transparency, these services are independently executing each other. Based on our model, we described structure of wide-area integrated tree and algorithms for searching and updating contact address of distributed object on this tree. finally, we showed a federation structure that can globally bind distributed objects located on different regions from an arbitrary client object.

• Spatial Information Research
• /
• v.19 no.3
• /
• pp.95-106
• /
• 2011

Recently as efficient processing of aggregate queries for fetching desired data from sensors has been recognized as a crucial part, in-network aggregate query processing techniques are studied intensively in wireless sensor networks. Existing representative in-network aggregate query processing techniques propose routing algorithms and data structures for processing aggregate queries. However, these aggregate query processing techniques have problems such as high energy consumption in sensor nodes, low accuracy of query processing results, and long query processing time. In order to solve these problems and to enhance the efficiency of aggregate query processing in wireless sensor networks, this paper proposes Bucket-based Parallel Aggregation(BPA). BPA divides a query region into several cells according to the distribution of sensor nodes and builds a Quad-tree, and then processes aggregate queries in parallel for each cell region according to routing. And it sends data in duplicate by removing redundant data, which, in turn, enhances the accuracy of query processing results. Also, BPA uses a bucket-based data structure in aggregate query processing, and divides and conquers the bucket data structure adaptively according to the number of data in the bucket. In addition, BPA compresses data in order to reduce the size of data in the bucket and performs data transmission filtering when each sensor node sends data. Finally, in this paper, we prove its superiority through various experiments using sensor data.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.161-177
• /
• 2019

In this paper, we study the performance improvement of the answer extraction in Question-Answering system by using sentence dependency parsing result. The Question-Answering (QA) system consists of query analysis, which is a method of analyzing the user's query, and answer extraction, which is a method to extract appropriate answers in the document. And various studies have been conducted on two methods. In order to improve the performance of answer extraction, it is necessary to accurately reflect the grammatical information of sentences. In Korean, because word order structure is free and omission of sentence components is frequent, dependency parsing is a good way to analyze Korean syntax. Therefore, in this study, we improved the performance of the answer extraction by adding the features generated by dependency parsing analysis to the inputs of the answer extraction model (Bidirectional LSTM-CRF). The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. In this study, we compared the performance of the answer extraction model when inputting basic word features generated without the dependency parsing and the performance of the model when inputting the addition of the Eojeol tag feature and dependency graph embedding feature. Since dependency parsing is performed on a basic unit of an Eojeol, which is a component of sentences separated by a space, the tag information of the Eojeol can be obtained as a result of the dependency parsing. The Eojeol tag feature means the tag information of the Eojeol. The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. From the dependency parsing result, a graph is generated from the Eojeol to the node, the dependency between the Eojeol to the edge, and the Eojeol tag to the node label. In this process, an undirected graph is generated or a directed graph is generated according to whether or not the dependency relation direction is considered. To obtain the embedding of the graph, we used Graph2Vec, which is a method of finding the embedding of the graph by the subgraphs constituting a graph. We can specify the maximum path length between nodes in the process of finding subgraphs of a graph. If the maximum path length between nodes is 1, graph embedding is generated only by direct dependency between Eojeol, and graph embedding is generated including indirect dependencies as the maximum path length between nodes becomes larger. In the experiment, the maximum path length between nodes is adjusted differently from 1 to 3 depending on whether direction of dependency is considered or not, and the performance of answer extraction is measured. Experimental results show that both Eojeol tag feature and dependency graph embedding feature improve the performance of answer extraction. In particular, considering the direction of the dependency relation and extracting the dependency graph generated with the maximum path length of 1 in the subgraph extraction process in Graph2Vec as the input of the model, the highest answer extraction performance was shown. As a result of these experiments, we concluded that it is better to take into account the direction of dependence and to consider only the direct connection rather than the indirect dependence between the words. The significance of this study is as follows. First, we improved the performance of answer extraction by adding features using dependency parsing results, taking into account the characteristics of Korean, which is free of word order structure and omission of sentence components. Second, we generated feature of dependency parsing result by learning - based graph embedding method without defining the pattern of dependency between Eojeol. Future research directions are as follows. In this study, the features generated as a result of the dependency parsing are applied only to the answer extraction model in order to grasp the meaning. However, in the future, if the performance is confirmed by applying the features to various natural language processing models such as sentiment analysis or name entity recognition, the validity of the features can be verified more accurately.