• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.12
• /
• pp.1791-1800
• /
• 2012

This paper presents effective design schemes for a photovoltaic (PV) and battery hybrid system that includes state-of-the-art technologies such as maximum power point tracking scheme for PV arrays, an effective charging/discharging circuit for batteries, and grid-interfacing power inverters. Compared to commonly-used PV systems, the proposed configuration has more flexibility and autonomy in controlling individual components of the PV-battery hybrid system. This paper also proposes an intelligent coordination scheme for the components of the PV-battery hybrid system to improve the efficiency of renewable energy resources and peak-load management. The proposed algorithm is based on a rule-based expert system that has excellent capability to optimize multi-objective functions. The proposed configuration and algorithms are investigated via switching-level simulation studies of the PV-battery hybrid system.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.2
• /
• pp.123-131
• /
• 2020

The text ranking algorithm is a representative method for keyword extraction, and its importance is emphasized highly. In this paper, we compare the performance of recent research and experiments with TF-IDF, SMART, INQUERY and CCA algorithms, which are used in text ranking algorithm.. After explaining each algorithm, we compare the performance of each algorithm based on the data collected from news and Twitter. Experimental results show that all of four algorithms can extract specific words from news data equally. However, in the case of Twitter, CCA has the best performance to extract specific words, and INQUERY shows the worst performance. We also analyze the accuracy of the algorithm through six comparison metrics. The experimental results present that CCA shows the best accuracy in the news data. In case of Twitter, TF-IDF and CCA show similar performance and demonstrate good performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.1
• /
• pp.232-248
• /
• 2014

A series of kernel regression (KR) algorithms, such as the classic kernel regression (CKR), the 2- and 3-D steering kernel regression (SKR), have been proposed for image and video super-resolution. In existing KR frameworks, a single algorithm is usually adopted and applied for a whole image/video, regardless of region characteristics. However, their performances and computational efficiencies can differ in regions of different characteristics. To take full advantage of the KR algorithms and avoid their disadvantage, this paper proposes a kernel regression framework for video super-resolution. In this framework, each video frame is first analyzed and divided into three types of regions: flat, non-flat-stationary, and non-flat-moving regions. Then different KR algorithm is selected according to the region type. The CKR and 2-D SKR algorithms are applied to flat and non-flat-stationary regions, respectively. For non-flat-moving regions, this paper proposes a similarity-assisted steering kernel regression (SASKR) algorithm, which can give better performance and higher computational efficiency than the 3-D SKR algorithm. Experimental results demonstrate that the computational efficiency of the proposed framework is greatly improved without apparent degradation in performance.

• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.350-358
• /
• 2021

In modern years, the performance of the students is analysed with lot of difficulties, which is a very important problem in all the academic institutions. The main idea of this paper is to analyze and evaluate the academic performance of the college students with bipolar disorder by applying data mining classification algorithms using Jupiter Notebook, python tool. This tool has been generally used as a decision-making tool in terms of academic performance of the students. The various classifiers could be logistic regression, random forest classifier gini, random forest classifier entropy, decision tree classifier, K-Neighbours classifier, Ada Boost classifier, Extra Tree Classifier, GaussianNB, BernoulliNB are used. The results of such classification model deals with 13 measures like Accuracy, Precision, Recall, F1 Measure, Sensitivity, Specificity, R Squared, Mean Absolute Error, Mean Squared Error, Root Mean Squared Error, TPR, TNR, FPR and FNR. Therefore, conclusion could be reached that the Decision Tree Classifier is better than that of different algorithms.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.31-33
• /
• 2007

Devising an efficient one-pass frequent pattern mining algorithm has been an issue in data mining research in recent past. Pattern growth algorithms like FP-Growth which are found more efficient than candidate generation and test algorithms still require two database scans. Moreover, FP-growth approach requires rebuilding the base-tree while mining with different support counts. In this paper we propose an item-based tree, called I-Tree that not only efficiently mines frequent patterns with single database scan but also provides multiple mining scopes with multiple support thresholds. The 'build-once-mine-many' property of I-Tree allows it to construct the tree only once and perform mining operation several times with the variation of support count values.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.7
• /
• pp.598-602
• /
• 2001

Recently, due to the widely use of personal computers and internet, many computer users requested intelligent system that can cope with various types of requirements and user-friendly interfaces. Based on this background, researches on the intelligent agent are now activating in various fields. In this paper, we modeled, designed and implemented an intelligent agent system for pattern classification by adopting intelligent agent concepts. We also investigated the pattern classification method by utilizing some pattern classification algorithms for the common data. As a result, we identified that 300 3-dimensional data are applied to three pattern classification algorithms and returned correct results. Our system showed a distinguished user-friendly interface feature by adopting various agents including graphic agent.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.255-258
• /
• 2008

For rapidly increasing amount of medical images, it is difficult for radiologist to interpretate the medical images fastly and for sufficient time. We investigated whether liver CT image has good features to be analyzed by computer algorithm, We examed the CT images of liver tumors (Hepetocellular carcinomas; HCCs) and searched any potential morphologic characteristics to be analyzed by computer algorithms. On unenhanced CT, HCCs appeared hypodense After enhancement, most HCCs were hyperdense, and then. as a consequence of rapid washout, HCCS became hypodense compared with the liver parenchyma. Most CT images of HCCs showed synchronous phase-specific.morphologic features. We applied various edge detection filters to these images and some filters showed favorable performance in the detection of tile edge of liver and HCC. Therefore, theses features seems to be analyzed by computer algorithms effectively.Further studies may be warranted.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.10
• /
• pp.23-31
• /
• 2018

Recently, there have been many studies on machine learning. Among them, studies on reinforcement learning are actively worked. In this study, we propose a controller to control bicycle using DDPG (Deep Deterministic Policy Gradient) algorithm which is the latest deep reinforcement learning method. In this paper, we redefine the compensation function of bicycle dynamics and neural network to learn agents. When using the proposed method for data learning and control, it is possible to perform the function of not allowing the bicycle to fall over and reach the further given destination unlike the existing method. For the performance evaluation, we have experimented that the proposed algorithm works in various environments such as fixed speed, random, target point, and not determined. Finally, as a result, it is confirmed that the proposed algorithm shows better performance than the conventional neural network algorithms NAF and PPO.

• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.56-62
• /
• 2021

The surge in generic attacks execution against cipher text on the computer network has led to the continuous advancement of the mechanisms to protect information integrity and confidentiality. The implementation of explicit decision tree machine learning algorithm is reported to accurately classifier generic attacks better than some multi-classification algorithms as the multi-classification method suffers from detection oversight. However, there is a need to improve the accuracy and reduce the false alarm rate. Therefore, this study aims to improve generic attack classification by implementing two hybridized decision tree algorithms namely Naïve Bayes Decision tree (NBTree) and Logistic Model tree (LMT). The proposed hybridized methods were developed using the 10-fold cross-validation technique to avoid overfitting. The generic attack detector produced a 99.8% accuracy, an FPR score of 0.002 and an MCC score of 0.995. The performances of the proposed methods were better than the existing decision tree method. Similarly, the proposed method outperformed multi-classification methods for detecting generic attacks. Hence, it is recommended to implement hybridized decision tree method for detecting generic attacks on a computer network.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.8
• /
• pp.95-103
• /
• 2019

According to the Statistics Korea in 2017, the 10 leading causes of death contain a cardiac disorder disease, self-injury. In terms of these diseases, urgent assistance is highly required when people do not move for certain period of time. We propose an unusual event detection algorithm to identify abnormal user behaviors using dust, vision and activity sensors in their houses. Vision sensors can detect personalized activity behaviors within the CCTV range in the house in their lives. The pattern algorithm using the dust sensors classifies user movements or dust-generated daily behaviors in indoor areas. The accelerometer sensor in the smartphone is suitable to identify activity behaviors of the mobile users. We evaluated the proposed pattern algorithms and the fusion method in the scenarios.