• Korean Journal of Remote Sensing
• /
• v.27 no.4
• /
• pp.435-444
• /
• 2011

The land cover map derived from spectral features of high resolution optical images has low spectral resolution and heterogeneity in the same land cover class. For this reason, despite the same land cover class, the land cover can be classified into various land cover classes especially in vegetation area. In order to overcome these problems, detailed vegetation classification is applied to optical satellite image and SAR(Synthetic Aperture Radar) integrated data in vegetation area which is the result of pre-classification from optical image. The pre-classification and vegetation classification were performed with MLC(Maximum Likelihood Classification) method. The hierarchical land cover classification was proposed from fusion of detailed vegetation classes and non-vegetation classes of pre-classification. We can verify the facts that the proposed method has higher accuracy than not only general SAR data and GLCM(Gray Level Co-occurrence Matrix) texture integrated methods but also hierarchical GLCM integrated method. Especially the proposed method has high accuracy with respect to both vegetation and non-vegetation classification.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2010.04a
• /
• pp.387-388
• /
• 2010

There is no generalized and systematic method yet to data pre-processing for point cloud data classification even if there have been lots of previous studies such as local maxima filter, morphology filter, slope based filter and so on. Main focus of this study is to present classification method for bare ground information from LiDAR data for the mountainous area.

• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.2905-2907
• /
• 1999

The meaningful speech sound block classification provides very important information in the speech recognition. The following technique of the classification is based on the DWT (discrete wavelet transform), which will provide a more fast algorithm and a useful, compact solution for the pre-processing of speech recognition. The algorithm is implemented to the unvoiced/voiced classification and the denoising.

• Journal of Biomedical Engineering Research
• /
• v.43 no.5
• /
• pp.299-307
• /
• 2022

In this paper, we propose a pre-processing method that converts to Spider Chart image data for classification of gripping movement using EMG (electromyography) sensors and Convolution Neural Networks (CNN) deep learning. First, raw data for six hand gestures are extracted from five test subjects using an 8-channel armband and converted into Spider Chart data of octagonal shapes, which are divided into several sliding windows and are learned. In classifying six hand gestures, the classification performance is compared with the proposed pre-processing method and the existing methods. Deep learning was performed on the dataset by dividing 70% of the total into training, 15% as testing, and 15% as validation. For system performance evaluation, five cross-validations were applied by dividing 80% of the entire dataset by training and 20% by testing. The proposed method generates 97% and 94.54% in cross-validation and general tests, respectively, using the Spider Chart preprocessing, which was better results than the conventional methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.420-437
• /
• 2024

There are some problems in network traffic classification (NTC), such as complicated statistical features and insufficient training samples, which may cause poor classification effect. A NTC architecture based on one-dimensional Convolutional Neural Network (CNN) and transfer learning is proposed to tackle these problems and improve the fine-grained classification performance. The key points of the proposed architecture include: (1) Model classification--by extracting normalized rate feature set from original data, plus existing statistical features to optimize the CNN NTC model. (2) To apply transfer learning in the classification to improve NTC performance. We collect two typical network flows data from Youku and YouTube, and verify the proposed method through extensive experiments. The results show that compared with existing methods, our method could improve the classification accuracy by around 3-5%for Youku, and by about 7 to 27% for YouTube.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.6 s.44
• /
• pp.1-8
• /
• 2006

Many researchers have been studied for the automatic chromosome karyotype classification and analysis. For the automatic classify the each chromosome which is the image in microscope, it is necessary to process the sub-procedure, ie. image pre-processing, implementing karyotype classifier. The image pre-processing proceeded the each chromosome separation, the noise exception and the feature parameter extraction. The extracted morphological feature parameter were the centromeric index(C.I.), the relative length ratio(R.L.), and the relative area ratio(R.A.). In this paper, the fuzzy classifier was implemented for the human chromosome karyotype classification. The extracted morphological feature parameter were used in the input parameter of fuzzy classifier. We studied about the selection of the membership function for the optimal fuzzy classifier in each chromosome groups.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.4
• /
• pp.1442-1462
• /
• 2014

Packet classification is a key technology of the Internet for routers to classify the arriving packets into different flows according to the predefined rulesets. Previous packet classification algorithms have mainly focused on search speed and memory usage, while overlooking update performance. In this paper, we propose PreCuts, which can drastically improve the update speed. According to the characteristics of IP field, we implement three heuristics to build a 3-layer decision tree. In the first layer, we group the rules with the same highest byte of source and destination IP addresses. For the second layer, we cluster the rules which share the same IP prefix length. Finally, we use the heuristic of information entropy-based bit partition to choose some specific bits of IP prefix to split the ruleset into subsets. The heuristics of PreCuts will not introduce rule duplication and incremental update will not reduce the time and space performance. Using ClassBench, it is shown that compared with BRPS and EffiCuts, the proposed algorithm not only improves the time and space performance, but also greatly increases the update speed.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.3
• /
• pp.33-38
• /
• 2021

Recently, transfer learning techniques with a base convolutional neural network (CNN) model have widely gained acceptance in early detection and classification of crop diseases to increase agricultural productivity with reducing disease spread. The transfer learning techniques based classifiers generally achieve over 90% of classification accuracy for crop diseases using dataset of crop leaf images (e.g., PlantVillage dataset), but they have ability to classify only the pre-trained diseases. This paper provides with an evaluation scheme on selecting an effective base CNN model for crop disease transfer learning with regard to the accuracy of trained target crops as well as of untrained target crops. First, we present transfer learning models called CDC (crop disease classification) architecture including widely used base (pre-trained) CNN models. We evaluate each performance of seven base CNN models for four untrained crops. The results of performance evaluation show that the DenseNet201 is one of the best base CNN models.

• Youth Facilities and Environment
• /
• v.17 no.1
• /
• pp.131-141
• /
• 2019

The purpose of this study is to derive and type utilization indexes by comparing public design indicators with preceding studies related to closed school facilities, and to derive preliminary classification systems through a correlation review between indicators. Pre-research was conducted in the scope of academic papers, academic journals, research reports, and special act for promoting the utilization of closed school assets. Public design indicators were set in the scope of domestic design guidelines, the Seoul city public design assessment system, the 'Good Building' designation system, and the UK Design Quality Index (DQI). and the design review of the British architects. First of all, the research method looked at laws, procedures and utilization of closed schools, and reviewed the preceding study and domestic and international public design indicators sequentially. Next, the association was reviewed through a comparison between the preceding study and the public design indicators, and a preliminary classification system for the use of closed schools was derived from this.

• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.673-687
• /
• 2023

Convolutional neural network-based deep learning technology is the most commonly used in image identification, but it requires large-scale data for training. Therefore, application in specific fields in which data acquisition is limited, such as in the military, may be challenging. In particular, the identification of ground weapon systems is a very important mission, and high identification accuracy is required. Accordingly, various studies have been conducted to achieve high performance using small-scale data. Among them, the ensemble method, which achieves excellent performance through the prediction average of the pre-trained models, is the most representative method; however, it requires considerable time and effort to find the optimal combination of ensemble models. In addition, there is a performance limitation in the prediction results obtained by using an ensemble method. Furthermore, it is difficult to obtain the ensemble effect using models with imbalanced classification accuracies. In this paper, we propose a transfer learning-based feature fusion technique for heterogeneous models that extracts and fuses features of pre-trained heterogeneous models and finally, fine-tunes hyperparameters of the fully connected layer to improve the classification accuracy. The experimental results of this study indicate that it is possible to overcome the limitations of the existing ensemble methods by improving the classification accuracy through feature fusion between heterogeneous models based on transfer learning.