• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.2
• /
• pp.13-21
• /
• 1996

The necessity and usefulness of higher-order neural networks have been well-known since early days of neurocomputing. However the explosive number of terms has hampered the design and training of such networks. In this paper we present an evolutionary learning method for efficiently constructing problem-specific higher-order neural models. The crux of the method is the neural tree representation employing both sigma and pi units, in combination with the use of an MDL-based fitness function for learning minimal models. We provide experimental results in classification and prediction problems which demonstrate the effectiveness of the method. I. Introduction topology employs one hidden layer with full connectivity between neighboring layers. This structure has One of the most popular neural network models been very successful for many applications. However, used for supervised learning applications has been the they have some weaknesses. For instance, the fully mutilayer feedforward network. A commonly adopted connected structure is not necessarily a good topology unless the task contains a good predictor for the full *d*dWs %BH%W* input space.

• Steel and Composite Structures
• /
• v.42 no.6
• /
• pp.733-745
• /
• 2022

This study proposed a robust artificial intelligence (AI) model based on the social behaviour of the imperialist competitive algorithm (ICA) and artificial neural network (ANN) for modelling the deflection of reinforced concrete beams, abbreviated as ICA-ANN model. Accordingly, the ICA was used to adjust and optimize the parameters of an ANN model (i.e., weights and biases) aiming to improve the accuracy of the ANN model in modelling the deflection reinforced concrete beams. A total of 120 experimental datasets of reinforced concrete beams were employed for this aim. Therein, applied load, tensile reinforcement strength and the reinforcement percentage were used to simulate the deflection of reinforced concrete beams. Besides, five other AI models, such as ANN, SVM (support vector machine), GLMNET (lasso and elastic-net regularized generalized linear models), CART (classification and regression tree) and KNN (k-nearest neighbours), were also used for the comprehensive assessment of the proposed model (i.e., ICA-ANN). The comparison of the derived results with the experimental findings demonstrates that among the developed models the ICA-ANN model is that can approximate the reinforced concrete beams deflection in a more reliable and robust manner.

• Smart Structures and Systems
• /
• v.30 no.2
• /
• pp.195-207
• /
• 2022

Computational drawbacks associated with regular predictive models have motivated engineers to use hybrid techniques in dealing with complex engineering tasks like simulating the compressive strength of concrete (CSC). This study evaluates the efficiency of tree potential metaheuristic schemes, namely shuffled complex evolution (SCE), multi-verse optimizer (MVO), and beetle antennae search (BAS) for optimizing the performance of a multi-layer perceptron (MLP) system. The models are fed by the information of 1030 concrete specimens (where the amount of cement, blast furnace slag (BFS), fly ash (FA1), water, superplasticizer (SP), coarse aggregate (CA), and fine aggregate (FA2) are taken as independent factors). The results of the ensembles are compared to unreinforced MLP to examine improvements resulted from the incorporation of the SCE, MVO, and BAS. It was shown that these algorithms can considerably enhance the training and prediction accuracy of the MLP. Overall, the proposed models are capable of presenting an early, inexpensive, and reliable prediction of the CSC. Due to the higher accuracy of the BAS-based model, a predictive formula is extracted from this algorithm.

• Geomechanics and Engineering
• /
• v.33 no.5
• /
• pp.487-506
• /
• 2023

Looking from the past to the present, the earthquakes can be said to be type of disaster with most casualties among natural disasters. Soil liquefaction, which occurs under repeated loads such as earthquakes, plays a major role in these casualties. In this study, analytical equation models were developed to predict the probability of occurrence of soil liquefaction. In this context, the parameters effective in liquefaction were determined out of 170 data sets taken from the real field conditions of past earthquakes, using WEKA decision tree. Linear, Exponential, Power and Quadratic models have been developed based on the identified earthquake and ground parameters using Krill Herd algorithm. The Exponential model, among the models including the magnitude of the earthquake, fine grain ratio, effective stress, standard penetration test impact number and maximum ground acceleration parameters, gave the most successful results in predicting the fields with and without the occurrence of liquefaction. This proposed model enables the researchers to predict the liquefaction potential of the soil in advance according to different earthquake scenarios. In this context, measures can be realized in regions with the high potential of liquefaction and these measures can significantly reduce the casualties in the event of a new earthquake.

• Earthquakes and Structures
• /
• v.27 no.3
• /
• pp.177-189
• /
• 2024

Accurately predicting the failure modes of reinforced concrete (RC) columns is essential for structural design and assessment. In this study, the challenges of imbalanced datasets and complex feature selection in machine learning (ML) methods were addressed through an optimized ML approach. By combining feature selection and oversampling techniques, the prediction of seismic failure modes in rectangular RC columns was improved. Two feature selection methods were used to identify six input parameters. To tackle class imbalance, the Borderline-SMOTE1 algorithm was employed, enhancing the learning capabilities of the models for minority classes. Eight ML algorithms were trained and fine-tuned using k-fold shuffle split cross-validation and grid search. The results showed that the artificial neural network model achieved 96.77% accuracy, while k-nearest neighbor, support vector machine, and random forest models each achieved 95.16% accuracy. The balanced dataset led to significant improvements, particularly in predicting the flexure-shear failure mode, with accuracy increasing by 6%, recall by 8%, and F1 scores by 7%. The use of the Borderline-SMOTE1 algorithm significantly improved the recognition of samples at failure mode boundaries, enhancing the classification performance of models like k-nearest neighbor and decision tree, which are highly sensitive to data distribution and decision boundaries. This method effectively addressed class imbalance and selected relevant features without requiring complex simulations like traditional methods, proving applicable for discerning failure modes in various concrete members under seismic action.

• Journal of Korea Multimedia Society
• /
• v.8 no.2
• /
• pp.258-268
• /
• 2005

The efficient provision of multicast service to moving hosts in mobile computing environments is not so easy task. Bi-directional tunneling scheme causes overhead about encapsulation and triangular routing. On the other hand, remote subscription scheme need freDuent tree reconstruction, which is inefficient for rapid moving hosts. In this paper we propose Mobility Based Mobile Multicast(MBMOM) scheme which is based on host's mobility information. Ultimately MBMOM try to find the strong points of remote subscription scheme and hi-directional tunneling scheme. If host's mobility speed is considered to be high, multicast packets are forwarded using hi-directional tunneling scheme from home agent continuously. If host's mobility speed is considered to be slow, remote subscription scheme is applied for foreign agent and it try to join multicast tree. We developed analytical models to analyze the performance of proposed scheme and simulated our scheme compared with MOM(Mobile Multicast), RBMOM(Range Based MOM), and TBMOM(Timer Based MOM) schemes. Simulation results show that our scheme has shorter transmission delay than above 3 schemes in the aspect of host's mobility speed and multicast group size.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.4
• /
• pp.580-586
• /
• 2021

The CAT methodology is a numerical analysis technique using CAE. Recently, a methodology of applying artificial intelligence techniques to a simulation has been studied. A previous study compared the deformation results according to the injection molding process using a machine learning technique. Although MLP has excellent prediction performance, it lacks an explanation of the decision process and is like a black box. In this study, data was generated using Autodesk Moldflow 2018, an injection molding analysis software. Several Machine Learning Algorithms models were developed using RapidMiner version 9.5, a machine learning platform software, and the root mean square error was compared. The decision-tree showed better prediction performance than other machine learning techniques with the RMSE values. The classification criterion can be increased according to the Maximal Depth that determines the size of the Decision-tree, but the complexity also increases. The simulation showed that by selecting an intermediate value that satisfies the constraint based on the changed position, there was 7.7% improvement compared to the previous simulation.

• MALSORI
• /
• no.66
• /
• pp.61-72
• /
• 2008

This paper proposes a method to improve pathological and normal voice classification performance by combining multiple features such as auditory-based and higher-order features. Their performances are measured by Gaussian mixture models (GMMs) and linear discriminant analysis (LDA). The combination of multiple features proposed by the frame-based LDA method is shown to be an effective method for pathological and normal voice classification, with a 87.0% classification rate. This is a noticeable improvement of 17.72% compared to the MFCC-based GMM algorithm in terms of error reduction.

• Asia pacific journal of information systems
• /
• v.16 no.2
• /
• pp.69-84
• /
• 2006

Importance of Today's diffusion of integrated hospital information systems is that various and huge amount of data is being accumulated in their database systems. Many researchers have studied utilizing such hospital data. While most researches were conducted mainly for medical diagnosis, there have been insufficient studies to develop medical care cost prediction model, especially using machine learning techniques. In this research, therefore, we built a medical care cost prediction model for cancer patients using CBR (Case-Based Reasoning), one of the machine learning techniques. Its performance was compared with those of Neural Networks and Decision Tree models. As a result of the experiment, the CBR prediction model was shown to be the best in general with respect to error rate and linearity between real values and predicted values. It is believed that the medical care cost prediction model can be utilized for the effective management of limited resources in hospitals.

• International Journal of Computer Science & Network Security
• /
• v.23 no.1
• /
• pp.53-63
• /
• 2023

Many researchers are trying hard to minimize the incidence of cancers, mainly Gastric Cancer (GC). For GC, the five-year survival rate is generally 5-25%, but for Early Gastric Cancer (EGC), it is almost 90%. Predicting the onset of stomach cancer based on risk factors will allow for an early diagnosis and more effective treatment. Although there are several models for predicting stomach cancer, most of these models are based on unbalanced datasets, which favours the majority class. However, it is imperative to correctly identify cancer patients who are in the minority class. This research aims to apply three class-balancing approaches to the NHS dataset before developing supervised learning strategies: Oversampling (Synthetic Minority Oversampling Technique or SMOTE), Undersampling (SpreadSubsample), and Hybrid System (SMOTE + SpreadSubsample). This study uses Naive Bayes, Bayesian Network, Random Forest, and Decision Tree (C4.5) methods. We measured these classifiers' efficacy using their Receiver Operating Characteristics (ROC) curves, sensitivity, and specificity. The validation data was used to test several ways of balancing the classifiers. The final prediction model was built on the one that did the best overall.