• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.3B
• /
• pp.339-348
• /
• 2004

Packet classification is an important factor to support various services such as QoS guarantee and VPN for users in Internet. Packet classification is a searching process for best matching rule on rule tables by employing multi-field such as source address, protocol, and port number as well as destination address in If header. In this paper, we propose hardware based packet classification algorithm by employing tree bitmap of multi-bit trio. We divided prefixes of searching fields and rule into multi-bit stride, and perform a rule searching with multi-bit of fixed size. The proposed scheme can reduce the access times taking for rule search by employing indexing key in a fixed size of upper bits of rule prefixes. We also employ a marker prefixes in order to remove backtracking during searching a rule. In this paper, we generate two dimensional random rule set of source address and destination address using routing tables provided by IPMA Project, and compare its memory usages and performance.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.2
• /
• pp.53-60
• /
• 2012

Nearest-neighbor classification predicts the class of an input data with the most frequent class among the near training data of the input data. Even though nearest-neighbor classification doesn't have a training stage, all of the training data are necessary in a predictive stage and the generalization performance depends on the quality of training data. Therefore, as the training data size increase, a nearest-neighbor classification requires the large amount of memory and the large computation time in prediction. In this paper, we propose a prototype selection algorithm that predicts the class of test data with the new set of prototypes which are near-boundary training data. Based on Tomek links and distance metric, the proposed algorithm selects boundary data and decides whether the selected data is added to the set of prototypes by considering classes and distance relationships. In the experiments, the number of prototypes is much smaller than the size of original training data and we takes advantages of storage reduction and fast prediction in a nearest-neighbor classification.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.6
• /
• pp.433-442
• /
• 2018

The reservoir area is defined as the area surrounded by the planned flood level of the dam or the land under the planned flood level of the dam. In this study, supervised classification based on RF (Random Forest), which is a representative machine learning technique, was performed to detect cropland in the reservoir area. In order to classify the cropland in the reservoir area efficiently, the GLCM (Gray Level Co-occurrence Matrix), which is a representative technique to quantify texture information, NDWI (Normalized Difference Water Index) and NDVI (Normalized Difference Vegetation Index) were utilized as additional features during classification process. In particular, we analyzed the effect of texture information according to window size for generating GLCM, and suggested a methodology for detecting croplands in the reservoir area. In the experimental result, the classification result showed that cropland in the reservoir area could be detected by the multispectral, NDVI, NDWI and GLCM images of UAV, efficiently. Especially, the window size of GLCM was an important parameter to increase the classification accuracy.

• Proceedings of the IEEK Conference
• /
• 2004.06a
• /
• pp.171-174
• /
• 2004

Packet classification is an essential architectural component in implementing the quality-of-service (QoS) in today's Internet which provides a best-effort service to ail of its applications. Multiple header fields of incoming packets are compared against a set of rules in packet classification, the highest priority rule among matched rules is selected, and the packet is treated according to the action of the rule. In this Paper, we proposed a new packet classification scheme based on parallel multiple hashing on tuple spaces. Simulation results using real classifiers show that the proposed scheme provides very good performance on the required number of memory accesses and the memory size compared with previous works.

• Journal of Information Processing Systems
• /
• v.14 no.2
• /
• pp.418-434
• /
• 2018

With the increasing use of the Internet and electronic documents, automatic text categorization becomes imperative. Several machine learning algorithms have been proposed for text categorization. The k-nearest neighbor algorithm (kNN) is known to be one of the best state of the art classifiers when used for text categorization. However, kNN suffers from limitations such as high computation when classifying new instances. Instance selection techniques have emerged as highly competitive methods to improve kNN through data reduction. However previous works have evaluated those approaches only on structured datasets. In addition, their performance has not been examined over the text categorization domain where the dimensionality and size of the dataset is very high. Motivated by these observations, this paper investigates and analyzes the impact of instance selection on kNN-based text categorization in terms of various aspects such as classification accuracy, classification efficiency, and data reduction.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.170-174
• /
• 1997

This paper studies a method for making more efficient classification rules in the ID3 using the rough set theory. Decision tree technique of the ID3 always uses all the attributes in a table of examples for making a new decision tree, but rough set technique can in advance eleminate dispensable attributes. And the former generates only one type of classification rules, but the latter generates all the possibles types of them. The rules generated by the rough set technique are the simplist from as proved by the rough set theory. Therefore, ID3, applying the rough set technique, can reduct the size of the table of examples, generate the simplist form of the classification rules, and also implement an effectie classification system.

• Journal of Advanced Marine Engineering and Technology
• /
• v.28 no.4
• /
• pp.611-617
• /
• 2004

Pixel classification is one of basic image processing issues. The general characteristics of the pixels belonging to various classes are discussed and the radical principles of pixel classification are given. At the same time. a pixel classification scheme based on image direction measure is proposed. As a typical application instance of pixel classification, an adaptive multi-level median filter is presented. An image can be classified into two types of areas by using the direction information measure, that is. smooth area and edge area. Single direction multi-level median filter is used in smooth area. and multi-direction multi-level median filter is taken in the other type of area. What's more. an adaptive mechanism is proposed to adjust the type of the filters and the size of filter window. As a result. we get a better trade-off between preserving details and noise filtering.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.447-450
• /
• 2004

This paper proposes remotely sensed image classification method by fuzzy c-means clustering algorithm using average intra-cluster distance. The average intra-cluster distance acquires an average of the vector set belong to each cluster and proportionates to its size and density. We perform classification according to pixel's membership grade by cluster center of fuzzy c-means clustering using the mean-values of training data about each class. Fuzzy c-means algorithm considered membership degree for inter-cluster of each class. And then, we validate degree of overlap between clusters. A pixel which has a high degree of overlap applies to the maximum likelihood classification method. Finally, we decide category by comparing with fuzzy membership degree and likelihood rate. The proposed method is applied to IKONOS remote sensing satellite image for the verifying test.

• Journal of Korea Society of Industrial Information Systems
• /
• v.5 no.3
• /
• pp.65-70
• /
• 2000

In general, the quality of agricultural products is determined by direct measurement of a weight or a magnitude, and it is determined by indirect or non-destructive method. In this paper, using color image processing, the algorithm to determine its quality and grading is presented. And the algorithm is applied to real-time citrus classifier. In the system, the size and color of orange are measured by not the sight of human but the digital image processing. The citrus classification system has the real-time maximum classification capacity of six quantify per one second. The system can be applied to controller design for the quality classification of agricultural products.

• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.324-330
• /
• 2021

Agriculture is one of the essential needs of human life on planet Earth. It is the source of food and earnings for many individuals around the world. The economy of many countries is associated with the agriculture sector. Lots of diseases exist that attack various fruits and crops. Apple Tree Leaves also suffer different types of pathological conditions that affect their production. These pathological conditions include apple scab, cedar apple rust, or multiple diseases, etc. In this paper, an automatic detection framework based on deep learning is investigated for apple leaves disease classification. Different pre-trained models, VGG16, ResNetV2, InceptionV3, and MobileNetV2, are considered for transfer learning. A combination of parameters like learning rate, batch size, and optimizer is analyzed, and the best combination of ResNetV2 with Adam optimizer provided the best classification accuracy of 94%.