• Journal of Electrical Engineering and Technology
• /
• 제13권5호
• /
• pp.1841-1851
• /
• 2018

For the safe and stable operation of the power system, accurate wind power prediction is of great significance. A wind power prediction method based on empirical mode decomposition and improved extreme learning machine is proposed in this paper. Firstly, wind power time series is decomposed into several components with different frequency by empirical mode decomposition, which can reduce the non-stationary of time series. The components after decomposing remove the long correlation and promote the different local characteristics of original wind power time series. Secondly, an improved extreme learning machine prediction model is introduced to overcome the sample data updating disadvantages of standard extreme learning machine. Different improved extreme learning machine prediction model of each component is established. Finally, the prediction value of each component is superimposed to obtain the final result. Compared with other prediction models, the simulation results demonstrate that the proposed prediction method has better prediction accuracy for wind power.

• Journal of Computing Science and Engineering
• /
• 제10권4호
• /
• pp.118-127
• /
• 2016

An improved sample balanced genetic algorithm and Extreme Learning Machine (iSBGA-ELM) was designed for accurate diagnosis of Alzheimer disease (AD) and identification of biomarkers associated with AD in this paper. The proposed AD diagnosis approach uses a set of magnetic resonance imaging scans in Open Access Series of Imaging Studies (OASIS) public database to build an efficient AD classifier. The approach contains two steps: "voxels selection" based on an iSBGA and "AD classification" based on the ELM. In the first step, the proposed iSBGA searches for a robust subset of voxels with promising properties for further AD diagnosis. The robust subset of voxels chosen by iSBGA is then used to build an AD classifier based on the ELM. A robust subset of voxels keeps a high generalization performance of AD classification in various scenarios and highlights the importance of the chosen voxels for AD research. The AD classifier with maximum classification accuracy is created using an optimal subset of robust voxels. It represents the final AD diagnosis approach. Experiments with the proposed iSBGA-ELM using OASIS data set showed an average testing accuracy of 87%. Experiments clearly indicated the proposed iSBGA-ELM was efficient for AD diagnosis. It showed improvements over existing techniques.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권7호
• /
• pp.1705-1720
• /
• 2013

Human face gender recognition requires fast image processing with high accuracy. Existing face gender recognition methods used traditional local features and machine learning methods have shortcomings of low accuracy or slow speed. In this paper, a new framework for face gender recognition to reach fast face gender recognition is proposed, which is based on Local Ternary Pattern (LTP) and Extreme Learning Machine (ELM). LTP is a generalization of Local Binary Pattern (LBP) that is in the presence of monotonic illumination variations on a face image, and has high discriminative power for texture classification. It is also more discriminate and less sensitive to noise in uniform regions. On the other hand, ELM is a new learning algorithm for generalizing single hidden layer feed forward networks without tuning parameters. The main advantages of ELM are the less stringent optimization constraints, faster operations, easy implementation, and usually improved generalization performance. The experimental results on public databases show that, in comparisons with existing algorithms, the proposed method has higher precision and better generalization performance at extremely fast learning speed.

• International Journal of Computer Science & Network Security
• /
• 제22권2호
• /
• pp.232-240
• /
• 2022

To fulfill user expectations, the rapid evolution of software techniques and approaches has necessitated reliable and flawless software operations. Aging prediction in the software under operation is becoming a basic and unavoidable requirement for ensuring the systems' availability, reliability, and operations. In this paper, an improved evolutionary computing-driven extreme learning scheme (ECD-ELM) has been suggested for object-oriented software aging prediction. To perform aging prediction, we employed a variety of metrics, including program size, McCube complexity metrics, Halstead metrics, runtime failure event metrics, and some unique aging-related metrics (ARM). In our suggested paradigm, extracting OOP software metrics is done after pre-processing, which includes outlier detection and normalization. This technique improved our proposed system's ability to deal with instances with unbalanced biases and metrics. Further, different dimensional reduction and feature selection algorithms such as principal component analysis (PCA), linear discriminant analysis (LDA), and T-Test analysis have been applied. We have suggested a single hidden layer multi-feed forward neural network (SL-MFNN) based ELM, where an adaptive genetic algorithm (AGA) has been applied to estimate the weight and bias parameters for ELM learning. Unlike the traditional neural networks model, the implementation of GA-based ELM with LDA feature selection has outperformed other aging prediction approaches in terms of prediction accuracy, precision, recall, and F-measure. The results affirm that the implementation of outlier detection, normalization of imbalanced metrics, LDA-based feature selection, and GA-based ELM can be the reliable solution for object-oriented software aging prediction.

• Journal of Information Processing Systems
• /
• 제10권3호
• /
• pp.443-458
• /
• 2014

An extreme learning machine (ELM) is a recently proposed learning algorithm for a single-layer feed forward neural network. In this paper we studied the ensemble of ELM by using a bagging algorithm for facial expression recognition (FER). Facial expression analysis is widely used in the behavior interpretation of emotions, for cognitive science, and social interactions. This paper presents a method for FER based on the histogram of orientation gradient (HOG) features using an ELM ensemble. First, the HOG features were extracted from the face image by dividing it into a number of small cells. A bagging algorithm was then used to construct many different bags of training data and each of them was trained by using separate ELMs. To recognize the expression of the input face image, HOG features were fed to each trained ELM and the results were combined by using a majority voting scheme. The ELM ensemble using bagging improves the generalized capability of the network significantly. The two available datasets (JAFFE and CK+) of facial expressions were used to evaluate the performance of the proposed classification system. Even the performance of individual ELM was smaller and the ELM ensemble using a bagging algorithm improved the recognition performance significantly.

• Geomechanics and Engineering
• /
• 제34권5호
• /
• pp.547-559
• /
• 2023

We evaluated the applicability of machine learning techniques and the Kuz-Ram model for predicting the mean fragmentation size in open-pit mines. The characteristics of the in-situ rock considered here were uniaxial compressive strength, tensile strength, rock factor, and mean in-situ block size. Seventy field datasets that included these characteristics were collected to predict the mean fragmentation size. Deep neural network, support vector machine, and extreme gradient boosting (XGBoost) models were trained using the data. The performance was evaluated using the root mean squared error (RMSE) and the coefficient of determination (r²). The XGBoost model had the smallest RMSE and the highest r² value compared with the other models. Additionally, when analyzing the error rate between the measured and predicted values, XGBoost had the lowest error rate. When the Kuz-Ram model was applied, low accuracy was observed owing to the differences in the characteristics of data used for model development. Consequently, the proposed XGBoost model predicted the mean fragmentation size more accurately than other models. If its performance is improved by securing sufficient data in the future, it will be useful for improving the blasting efficiency at the target site.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권7호
• /
• pp.3076-3092
• /
• 2020

An IKPCA-ELM-based intrusion detection method is developed to address the problem of the low accuracy and slow speed of intrusion detection caused by redundancies and high dimensions of data in the network. First, in order to reduce the effects of uneven sample distribution and sample attribute differences on the extraction of KPCA features, the sample attribute mean and mean square error are introduced into the Gaussian radial basis function and polynomial kernel function respectively, and the two improved kernel functions are combined to construct a hybrid kernel function. Second, an improved particle swarm optimization (IPSO) algorithm is proposed to determine the optimal hybrid kernel function for improved kernel principal component analysis (IKPCA). Finally, IKPCA is conducted to complete feature extraction, and an extreme learning machine (ELM) is applied to classify common attack type detection. The experimental results demonstrate the effectiveness of the constructed hybrid kernel function. Compared with other intrusion detection methods, IKPCA-ELM not only ensures high accuracy rates, but also reduces the detection time and false alarm rate, especially reducing the false alarm rate of small sample attacks.

• 경영정보학연구
• /
• 제21권1호
• /
• pp.23-38
• /
• 2019

소셜 네트워크 서비스(이하 SNS)는 회사의 마케팅 채널로 적극 활용되고 있으며, 회사들의 고객층에 적합한 내용과 어조를 활용하여 주기적으로 SNS 메시지를 작성하는 등 활발한 마케팅을 펼치고 있다. 본 논문에서는 이제까지 간과되었던 SNS 메시지에 내포된 심리적 거리에 초점을 맞춰 전통적인 코더를 활용한 내용 분석(content analysis)과 자연어 처리 기법 및 머신 러닝 방법을 혼합하여 심리적 거리를 측정하는 분석 방법을 연구하였다. SNS 메시지의 심리적 거리 분석을 위해 코더들을 활용하여 내용분석을 수행하였으며, 이와 같은 방법으로 레이블링된 데이터를 자연어 처리 방법을 이용하여 워드 임베딩을 수행함으로써 머신 러닝 수행을 위한 입력 데이터를 마련하였다. 머신 러닝 분석법 중 Support Vector Machine(SVM)을 이용하여 SNS 메시지와 심리적 거리 간의 관계를 학습시켰으며, 마지막으로 테스트 데이터를 이용하여 심리적 거리를 예측함으로써 머신 러닝 분석의 성과를 검증하였다. 심리적 거리측정 방법론 수행 결과, 코더들의 내용분석 결과가 특정 값으로 편향되어 SVM 예측의 민감도와 정밀도가 낮은 결과가 도출되었다. 심리적 거리 응답 비율을 보정하고 코더들의 1차 내용분석 결과 중 답변이 일치한 데이터로 한정지어 머신 러닝을 실행한 결과 심리적 거리 예측의 정확도, 민감도, 특이도, 정밀도 모두 향상되어 심리적 거리가 70% 이상 예측되는 성과를 보였다. 본 연구는 SNS 메시지의 심리적 거리를 측정하는 방법을 제시함으로써 독자와의 심리적 거리를 제어 가능한 전략 요소로 활용 가능하게 할 것이라 기대된다.

• 사물인터넷융복합논문지
• /
• 제10권1호
• /
• pp.39-45
• /
• 2024

항만 성능에 대한 정확한 평가는 컨테이너 물동량은 매우 중요한 요소이며, 효과적인 항만 개발 및 운영 전략에 대한 정확한 예측이 필수적이다. 하지만 해양 산업의 급격한 변화로 인해 컨테이너 물동량 예측의 정확성이 향상되기는 어렵다. 이를 해결하기 위해 사물인터넷(IoT)을 이용한 항만 성능에 미치는 영향을 분석하여 부산항의 경쟁력과 효율성을 향상시키기 위해 적용이 필요하다. 이에 본 연구에서는 부산항의 미래 컨테이너 물동량을 예측하기 위한 예측 모델을 개발하는 것을 목표로 이를 통해 항만 관리 기관의 개선된 의사 결정과 항만 생산성을 향상시키는 데 초점을 맞추고 있다. 항만 컨테이너 물동량을 예측하기 위해 본 연구에서는 기계 학습 모델의 Extreme Gradient Boosting (XGBoost) 기법을 도입하였다. XGBoost는 다른 알고리즘에 비해 높은 정확도, 빠른 학습 및 예측 속도,과적합을 방지하고 Feature Importance 제공하는 장점이 돋보인다. 특히 XGBoost는 회귀 예측 모델링에 직접 사용할 수 있어 기존 연구에서 제시된 물동량 예측 모델의 정확도 향상에 도움이 된다. 이를 통해 본 연구는 4.3% MAPE (Mean absolute percenture error) 값으로 제안된 방법이 컨테이너 물동량을 정확하고 신뢰성 있게 예측할 수 있다. 본 연구에서 제시한 방법론을 통해서 부산 컨테이너물동량의 정확성을 높일 수 있을 것으로 판단된다.

• Geomechanics and Engineering
• /
• 제37권5호
• /
• pp.475-498
• /
• 2024

The prediction of the susceptibility of soil to liquefaction using a limited set of parameters, particularly when dealing with highly unbalanced databases is a challenging problem. The current study focuses on different ensemble learning classification algorithms using highly unbalanced databases of results from in-situ tests; standard penetration test (SPT), shear wave velocity (V_s) test, and cone penetration test (CPT). The input parameters for these datasets consist of earthquake intensity parameters, strong ground motion parameters, and in-situ soil testing parameters. liquefaction index serving as the binary output parameter. After a rigorous comparison with existing literature, extreme gradient boosting (XGBoost), bagging, and random forest (RF) emerge as the most efficient models for liquefaction instance classification across different datasets. Notably, for SPT and V_s-based models, XGBoost exhibits superior performance, followed by Light gradient boosting machine (LightGBM) and Bagging, while for CPT-based models, Bagging ranks highest, followed by Gradient boosting and random forest, with CPT-based models demonstrating lower G_mean(error), rendering them preferable for soil liquefaction susceptibility prediction. Key parameters influencing model performance include internal friction angle of soil (ϕ) and percentage of fines less than 75 µ (F₇₅) for SPT and V_s data and normalized average cone tip resistance (q_c) and peak horizontal ground acceleration (a_max) for CPT data. It was also observed that the addition of V_s measurement to SPT data increased the efficiency of the prediction in comparison to only SPT data. Furthermore, to enhance usability, a graphical user interface (GUI) for seamless classification operations based on provided input parameters was proposed.