• Journal of Korea Technology Innovation Society
• /
• v.14 no.spc
• /
• pp.1171-1186
• /
• 2011

Identifying Emerging Technology Trends is crucial for decision makers of nations and organizations in order to use limited resources, such as time, money, etc., efficiently. Many researchers have proposed emerging trend detection systems based on a popularity analysis of the document, but this still needs to be improved. In this paper, an emerging trend detection classifier is proposed which uses both academic and industrial data, SCOPUS and PATSTAT. Unlike most pre-vious research, our emerging technology trend classifi-er utilizes supervised, semi-automatic, machine learning techniques to improve the precision of the results. In addition, the citation information from among the SCOPUS data is analyzed to identify the early signals of emerging technology trends.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.3
• /
• pp.223-230
• /
• 2001

Since self-organizing map (SOM) preserves the topology of ordering in input spaces and trains itself by unsupervised algorithm, it is Llsed in many areas. However, SOM has a shortcoming: structure cannot be easily detcrmined without many trials-and-errors. Structure-adaptive self-orgnizing map (SASOM) which can adapt its structure as well as its weights overcome the shortcoming of self-organizing map: SASOM makes use of structure adaptation capability to place the nodes of prototype vectors into the pattern space accurately so as to make the decision boundmies as close to the class boundaries as possible. In this scheme, the initialization of weights of newly adapted nodes is important. This paper proposes a method which optimizes SASOM with genetic algorithm (GA) to determines the weight vector of newly split node. The leanling algorithm is a hybrid of unsupervised learning method and supervised learning method using LVQ algorithm. This proposed method not only shows higher performance than SASOM in terms of recognition rate and variation, but also preserves the topological order of input patterns well. Experiments with 2D pattern space data and handwritten digit database show that the proposed method is promising.

• Journal of KIISE:Software and Applications
• /
• v.31 no.7
• /
• pp.849-858
• /
• 2004

Most of supervised teaming algorithms could be applied after that continuous variables are transformed to categorical ones at the preprocessing stage in order to avoid the difficulty of processing continuous variables. This preprocessing stage is called global discretization, uses the class distribution list called bins. But, when data are large and the range of the variable to be discretized is very large, many sorting and merging should be performed to produce a single bin because most of global discretization methods need a single bin. Also, if new data are added, they have to perform discretization from scratch to construct categories influenced by the data because the existing methods perform discretization in batch mode. This paper proposes a method that extracts sample points and performs discretization from these sample points in order to solve these problems. Because the approach in this paper does not require merging for producing a single bin, it is efficient when large data are needed to be discretized. In this study, an experiment using real and synthetic datasets was made to compare the proposed method with an existing one.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.2 no.3
• /
• pp.87-95
• /
• 2009

As information theoretic learning techniques, error entropy minimization criterion (MEE) and maximum cross correntropy criterion (MCC) have been studied in depth for supervised learning. MEE criterion leads to maximization of information potential and MCC criterion leads to maximization of cross correlation between output and input random processes. The weighted combination scheme of these two criteria, namely, minimization of Error Entropy with Fiducial points (MEEF) has been introduced and developed by many researchers. As an approach to unsupervised, blind channel equalization, we investigate the possibility of applying constant modulus error (CME) to MEE criterion and some problems of the method. Also we study on the application of CME to MEEF for blind equalization and find out that MEE-CME loses the information of the constant modulus. This leads MEE-CME and MEEF-CME not to converge or to converge slower than other algorithms dependent on the constant modulus.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.115-119
• /
• 2006

The channel is one of the precious and limited resources in wireless networks. There are many researches on the channel management. Recently, the optimization problem of guard channels has been an important issue. In this paper, we propose an intelligent channel management technique based on the neural networks. An SRN channel alteration model is developed to generate the learning data for the neural networks and the performance analysis of system. In the proposed technique, the neural network is trained to generate optimal guard channel number g, using backpropagation supervised learning algorithm. The optimal g is computed using the neural network and compared to the g computed by the SRN model. The numerical results show that the difference between the value of g by backpropagation and that value by SRN model is ignorable.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.5
• /
• pp.3434-3439
• /
• 2015

As a criterion of information theoretic learning, the Euclidean distance (ED) of two error probability distribution functions (minimum ED of error, MEDE) has been adopted in nonlinear (decision feedback, DF) supervised equalizer algorithms and has shown significantly improved performance in severe channel distortion and impulsive noise environments. However, the MEDE-DF algorithm has the problem of heavy computational complexity. In this paper, the recursive ED for MEDE-DF algorithm is derived first, and then the feed-forward and feedback section gradients for weight update are estimated recursively. To prove the effectiveness of the recursive gradient estimation for the MEDE-DF algorithm, the number of multiplications are compared and MSE performance in impulsive noise and underwater communication environments is compared through computer simulation. The ratio of the number of multiplications between the proposed DF and the conventional MEDE-DF algorithm is revealed to be $2(9N+4):2(3N^2+3N)$ for the sample size N with the same MSE learning performance in the impulsive noise and underwater channel environment.

• Journal of Korean Society for Quality Management
• /
• v.49 no.3
• /
• pp.421-431
• /
• 2021

Purpose: For improving outgoing quality, this study presents a novel sampling framework based on predictive analytics. Methods: The proposed framework is composed of three steps. The first step is the variable selection. The knowledge-based and data-driven approaches are employed to select important variables. The second step is the model learning. In this step, we consider the supervised classification methods, the anomaly detection methods, and the rule-based methods. The applying model is the third step. This step includes the all processes to be enabled on real-time prediction. Each prediction model classifies a product as a target sample or random sample. Thereafter intensive quality inspections are executed on the specified target samples. Results: The inspection data of three Samsung products (mobile, TV, refrigerator) are used to check functional defects in the product by utilizing the proposed method. The results demonstrate that using target sampling is more effective and efficient than random sampling. Conclusion: The results of this paper show that the proposed method can efficiently detect products that have the possibilities of user's defect in the lot. Additionally our study can guide practitioners on how to easily detect defective products using stratified sampling

• Journal of the Korea Convergence Society
• /
• v.13 no.3
• /
• pp.23-31
• /
• 2022

This study analyzed the actual frozen container operation data of Starcool provided by H Shipping. Through interviews with H's field experts, only Critical and Fatal Alarms among the four failure alarms were defined as failures, and it was confirmed that using all variables due to the nature of frozen containers resulted in cost inefficiency. Therefore, this study proposes a method for detecting failure of frozen containers through characteristic importance and PCA techniques. To improve the performance of the model, we select variables based on feature importance through tree series models such as XGBoost and LGBoost, and use PCA to reduce the dimension of the entire variables for each model. The boosting-based XGBoost and LGBoost techniques showed that the results of the model proposed in this study improved the reproduction rate by 0.36 and 0.39 respectively compared to the results of supervised learning using all 62 variables.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.4
• /
• pp.687-697
• /
• 2023

Botnets, whose attack patterns are becoming more sophisticated and diverse, are recognized as one of the most serious cybersecurity threats today. This paper revisits the experimental results of botnet detection using autoencoder, a semi-supervised deep learning model, for UGR and CTU-13 data sets. To prepare the input vectors of autoencoder, we create data points by grouping the NetFlow records into sliding windows based on source IP address and aggregating them to form features. In particular, we discover a simple power-law; that is the number of data points that have some flow-degree is proportional to the number of NetFlow records aggregated in them. Moreover, we show that our power-law fits the real data very well resulting in correlation coefficients of 97% or higher. We also show that this power-law has an impact on the learning of autoencoder and, as a result, influences the performance of botnet detection. Furthermore, we evaluate the performance of autoencoder using the area under the Receiver Operating Characteristic (ROC) curve.

• International Journal of Computer Science & Network Security
• /
• v.23 no.3
• /
• pp.49-56
• /
• 2023

Machine learning methods diversely applied to the Internet of Things (IoT) field have been successful due to the enhancement of computer processing power. They offer an effective way of detecting malicious intrusions in IoT because of their high-level feature extraction capabilities. In this paper, we proposed a novel feature selection method for malicious intrusion detection in IoT by using an evolutionary technique - Genetic Algorithm (GA) and Machine Learning (ML) algorithms. The proposed model is performing the classification of BoT-IoT dataset to evaluate its quality through the training and testing with classifiers. The data is reduced and several preprocessing steps are applied such as: unnecessary information removal, null value checking, label encoding, standard scaling and data balancing. GA has applied over the preprocessed data, to select the most relevant features and maintain model optimization. The selected features from GA are given to ML classifiers such as Logistic Regression (LR) and Support Vector Machine (SVM) and the results are evaluated using performance evaluation measures including recall, precision and f1-score. Two sets of experiments are conducted, and it is concluded that hyperparameter tuning has a significant consequence on the performance of both ML classifiers. Overall, SVM still remained the best model in both cases and overall results increased.