• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.67 no.1
• /
• pp.42-46
• /
• 2018

In this paper, we propose fast object detection method of the cars by applying YOLOv2(You Only Look Once version 2) and UAVs (Unmanned Aerial Vehicles) while on the highway. We operated Darknet, OpenCV, CUDA and Deep Learning Server(SDX-4185) for our simulation environment. YOLOv2 is recently developed fast object detection algorithm that can detect various scale objects as fast speed. YOLOv2 convolution network algorithm allows to calculate probability by one pass evaluation and predicts location of each cars, because object detection process has simple single network. In our result, we could find cars on the highway area as fast speed and we could apply to the real time.

• Korean Journal of Remote Sensing
• /
• v.34 no.5
• /
• pp.811-827
• /
• 2018

The purpose of this study is to compare machine learning algorithm and deep learning algorithm in crop classification using multi-temporal remote sensing data. For this, impacts of machine learning and deep learning algorithms on (a) hyper-parameter and (2) training sample size were compared and analyzed for Haenam-gun, Korea and Illinois State, USA. In the comparison experiment, support vector machine (SVM) was applied as machine learning algorithm and convolutional neural network (CNN) was applied as deep learning algorithm. In particular, 2D-CNN considering 2-dimensional spatial information and 3D-CNN with extended time dimension from 2D-CNN were applied as CNN. As a result of the experiment, it was found that the hyper-parameter values of CNN, considering various hyper-parameter, defined in the two study areas were similar compared with SVM. Based on this result, although it takes much time to optimize the model in CNN, it is considered that it is possible to apply transfer learning that can extend optimized CNN model to other regions. Then, in the experiment results with various training sample size, the impact of that on CNN was larger than SVM. In particular, this impact was exaggerated in Illinois State with heterogeneous spatial patterns. In addition, the lowest classification performance of 3D-CNN was presented in Illinois State, which is considered to be due to over-fitting as complexity of the model. That is, the classification performance was relatively degraded due to heterogeneous patterns and noise effect of input data, although the training accuracy of 3D-CNN model was high. This result simply that a proper classification algorithms should be selected considering spatial characteristics of study areas. Also, a large amount of training samples is necessary to guarantee higher classification performance in CNN, particularly in 3D-CNN.

• IEIE Transactions on Smart Processing and Computing
• /
• v.2 no.6
• /
• pp.323-331
• /
• 2013

An extreme learning machine (ELM) is an efficient learning algorithm that is based on the generalized single, hidden-layer feed-forward networks (SLFNs), which perform well in classification applications. Many studies have demonstrated its superiority over the existing classical algorithms: support vector machine (SVM) and BP neural network. This paper presents a novel face recognition approach based on a multi-class project extreme learning machine (MPELM) classifier and 2D Gabor transform. First, all face image features were extracted using 2D Gabor filters, and the MPELM classifier was used to determine the final face classification. Two well-known face databases (CMU-PIE and ORL) were used to evaluate the performance. The experimental results showed that the MPELM-based method outperformed the ELM-based method as well as other methods.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1033-1036
• /
• 2004

The study on speech recognition and understanding has been done for many years. In this paper, we propose a new type of recurrent neural network architecture for speech recognition, in which each output unit is connected to itself and is also fully connected to other output units and all hidden units [1]. Besides that, we also proposed the new architecture and the learning algorithm of recurrent neural network such as Backpropagation Through Time (BPTT, which well-suited. The aim of the study was to observe the difference of Arabic's alphabet like "alif" until "ya". The purpose of this research is to upgrade the people's knowledge and understanding on Arabic's alphabet or word by using Recurrent Neural Network (RNN) and Backpropagation Through Time (BPTT) learning algorithm. 4 speakers (a mixture of male and female) are trained in quiet environment. Neural network is well-known as a technique that has the ability to classified nonlinear problem. Today, lots of researches have been done in applying Neural Network towards the solution of speech recognition [2] such as Arabic. The Arabic language offers a number of challenges for speech recognition [3]. Even through positive results have been obtained from the continuous study, research on minimizing the error rate is still gaining lots attention. This research utilizes Recurrent Neural Network, one of Neural Network technique to observe the difference of alphabet "alif" until "ya".

• Journal of The Korean Society of Integrative Medicine
• /
• v.12 no.2
• /
• pp.155-166
• /
• 2024

Purpose : This study aims to identify key factors for predicting dropout risk at the university level and to provide a foundation for policy development aimed at dropout prevention. This study explores the optimal machine learning algorithm by comparing the performance of various algorithms using data on college students' dropout risks. Methods : We collected data on factors influencing dropout risk and propensity were collected from N University. The collected data were applied to several machine learning algorithms, including random forest, decision tree, artificial neural network, logistic regression, support vector machine (SVM), k-nearest neighbor (k-NN) classification, and Naive Bayes. The performance of these models was compared and evaluated, with a focus on predictive validity and the identification of significant dropout factors through the information gain index of machine learning. Results : The binary logistic regression analysis showed that the year of the program, department, grades, and year of entry had a statistically significant effect on the dropout risk. The performance of each machine learning algorithm showed that random forest performed the best. The results showed that the relative importance of the predictor variables was highest for department, age, grade, and residence, in the order of whether or not they matched the school location. Conclusion : Machine learning-based prediction of dropout risk focuses on the early identification of students at risk. The types and causes of dropout crises vary significantly among students. It is important to identify the types and causes of dropout crises so that appropriate actions and support can be taken to remove risk factors and increase protective factors. The relative importance of the factors affecting dropout risk found in this study will help guide educational prescriptions for preventing college student dropout.

• Journal of Korea Water Resources Association
• /
• v.33 no.4
• /
• pp.505-515
• /
• 2000

THe purpose of this study is to forecast of runoff hydrographs according to rainfall event in a stream. The neural network theory as a hydrologic blackbox model is used to solve hydrological problems. The Back-Propagation(BP) algorithm by the Levenberg-Marquardt(LM) techniques and Radial Basis Function(RBF) network in Neural Network(NN) models are used. Runoff hydrograph is forecasted in Bocheongstream basin which is a IHP the representative basin. The possibility of a simulation for runoff hydrographs about unlearned stations is considered. The results show that NN models are performed to effective learning for rainfall-runoff process of hydrologic system which involves a complexity and nonliner relationships. The RBF networks consist of 2 learning steps. The first step is an unsupervised learning in hidden layer and the next step is a supervised learning in output layer. Therefore, the RBF networks could provide rather time saved in the learning step than the BP algorithm. The peak discharge both BP algorithm and RBF network model in the estimation of an unlearned are a is trended to observed values.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.38 no.3
• /
• pp.169-180
• /
• 2015

Recently, scheduling problems with position-dependent processing times have received considerable attention in the literature, where the processing times of jobs are dependent on the processing sequences. However, they did not consider cases in which each processed job has different learning or aging ratios. This means that the actual processing time for a job can be determined not only by the processing sequence, but also by the learning/aging ratio, which can reflect the degree of processing difficulties in subsequent jobs. Motivated by these remarks, in this paper, we consider a two-agent single-machine scheduling problem with linear job-dependent position-based learning effects, where two agents compete to use a common single machine and each job has a different learning ratio. Specifically, we take into account two different objective functions for two agents: one agent minimizes the total weighted completion time, and the other restricts the makespan to less than an upper bound. After formally defining the problem by developing a mixed integer non-linear programming formulation, we devise a branch-and-bound (B&B) algorithm to give optimal solutions by developing four dominance properties based on a pairwise interchange comparison and four properties regarding the feasibility of a considered sequence. We suggest a lower bound to speed up the search procedure in the B&B algorithm by fathoming any non-prominent nodes. As this problem is at least NP-hard, we suggest efficient genetic algorithms using different methods to generate the initial population and two crossover operations. Computational results show that the proposed algorithms are efficient to obtain near-optimal solutions.

• Journal of the Korean Society of Industry Convergence
• /
• v.2 no.1
• /
• pp.61-67
• /
• 1999

An active control for the swing of crane systems is very important for increasing the productivity. This article introduces the control for the position and the swing of a crane using the fuzzy learning method. Because the crane is a multi-variable system, learning is done to control both position and swing of the crane. Also the fuzzy control rules are separately acquired with the loading and unloading situation of the crane for more accurate control. And We designed controller by fuzzy learning method, and then compare fuzzy learning method with LQR. The result of simulations shows that the crane is controlled better than LQR for a very large swing angle of 1 radian within nearly one cycle.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.995-998
• /
• 2013

Aerial imaging is one of the most common and versatile ways of obtaining information from the Earth surface. In this paper, we present an approach by SOM(Self Organization Map) algorithm with 2 phase learning to be applied successfully to aerial images clustering due to its signal-to-noise independency. A comparison with other classical method, such as K-means and traditional SOM, of real-world areal image clustering demonstrates the efficacy of our approach.

• KEPCO Journal on Electric Power and Energy
• /
• v.2 no.2
• /
• pp.311-316
• /
• 2016

Network intrusion detection system based on machine learning method such as artificial neural network is quite dependent on the selected features in terms of accuracy and efficiency. Nevertheless, choosing the optimal combination of features, which guarantees accuracy and efficienty, from generally used many features to detect network intrusion requires extensive computing resources. In this paper, we deal with a optimal feature selection problem to determine 6 denial service attacks and normal usage provided by NSL-KDD data. We propose a optimal feature selection algorithm. Proposed algorithm is based on the multi-start local search algorithm, one of representative meta-heuristic algorithm for solving optimization problem. In order to evaluate the performance of our proposed algorithm, comparison with a case of all 41 features used against NSL-KDD data is conducted. In addtion, comparisons between 3 well-known machine learning methods (multi-layer perceptron., Bayes classifier, and Support vector machine) are performed to find a machine learning method which shows the best performance combined with the proposed feature selection method.