• Nuclear Engineering and Technology
• /
• v.53 no.7
• /
• pp.2334-2340
• /
• 2021

Radioactive particle tracking (RPT) is a minimally invasive nuclear technique that tracks a radioactive particle inside a volume of interest by means of a mathematical location algorithm. During the past decades, many algorithms have been developed including ones based on artificial intelligence techniques. In this study, RPT technique is applied in a simulated test section that employs a simplified mixer filled with concrete, six scintillator detectors and a¹³⁷Cs radioactive particle emitting gamma rays of 662 keV. The test section was developed using MCNPX code, which is a mathematical code based on Monte Carlo simulation, and 3516 different radioactive particle positions (x,y,z) were simulated. Novelty of this paper is the use of a location algorithm based on a deep learning model, more specifically a 6-layers deep rectifier neural network (DRNN), in which hyperparameters were defined using a Bayesian optimization method. DRNN is a type of deep feedforward neural network that substitutes the usual sigmoid based activation functions, traditionally used in vanilla Multilayer Perceptron Networks, for rectified activation functions. Results show the great accuracy of the DRNN in a RPT tracking system. Root mean squared error for x, y and coordinates of the radioactive particle is, respectively, 0.03064, 0.02523 and 0.07653.

• Bulletin of the Korean Chemical Society
• /
• v.26 no.12
• /
• pp.2007-2016
• /
• 2005

An artificial neural network (ANN) is successfully presented for prediction acidity constant (pKa) of various benzoic acids and phenols with diverse chemical structures using a nonlinear quantitative structure-property relationship. A three-layered feed forward ANN with back-propagation of error was generated using six molecular descriptors appearing in the multi-parameter linear regression (MLR) model. The polarizability term $(\pi_1)$, most positive charge of acidic hydrogen atom $(q^+)$, molecular weight (MW), most negative charge of the acidic oxygen atom $(q^-)$, the hydrogen-bond accepting ability $(\epsilon_B)$ and partial charge weighted topological electronic (PCWTE) descriptors are inputs and its output is pKa. It was found that properly selected and trained neural network with 205 compounds could fairly represent dependence of the acidity constant on molecular descriptors. For evaluation of the predictive power of the generated ANN, an optimized network was applied for prediction pKa values of 37 compounds in the prediction set, which were not used in the optimization procedure. Squared correlation coefficient $(R^2)$ and root mean square error (RMSE) of 0.9147 and 0.9388 for prediction set by the MLR model should be compared with the values of 0.9939 and 0.2575 by the ANN model. These improvements are due to the fact that acidity constant of benzoic acids and phenols in water shows nonlinear correlations with the molecular descriptors.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2005.11a
• /
• pp.516-525
• /
• 2005

Case-based reasoning (CBR) has been widely used in various areas due to its convenience and strength in complex problem solving. Generally, in order to obtain successful results from CBR, effective retrieval of useful prior cases for the given problem is essential. However, designing a good matching and retrieval mechanism for CBR systems is still a controversial research issue. Most prior studies have tried to optimize the weights of the features or selection process of appropriate instances. But, these approaches have been performed independently until now. Simultaneous optimization of these components may lead to better performance than in naive models. In particular, there have been few attempts to simultaneously optimize the weight of the features and selection of the instances for CBR. Here we suggest a simultaneous optimization model of these components using a genetic algorithm (GA). We apply it to a customer classification model which utilizes demographic characteristics of customers as inputs to predict their buying behavior for a specific product. Experimental results show that simultaneously optimized CBR may improve the classification accuracy and outperform various optimized models of CBR as well as other classification models including logistic regression, multiple discriminant analysis, artificial neural networks and support vector machines.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1916-1934
• /
• 2023

The phishing attack is a malicious emerging threat on the internet where the hackers try to access the user credentials such as login information or Internet banking details through pirated websites. Using that information, they get into the original website and try to modify or steal the information. The problem with traditional defense systems like firewalls is that they can only stop certain types of attacks because they rely on a fixed set of principles to do so. As a result, the model needs a client-side defense mechanism that can learn potential attack vectors to detect and prevent not only the known but also unknown types of assault. Feature selection plays a key role in machine learning by selecting only the required features by eliminating the irrelevant ones from the real-time dataset. The proposed model uses Hyperparameter Optimized Artificial Neural Networks (H-ANN) combined with a Hybrid Firefly and Grey Wolf Optimization algorithm (H-FFGWO) to detect and block phishing websites in Internet of Things(IoT) Applications. In this paper, the H-FFGWO is used for the feature selection from phishing datasets ISCX-URL, Open Phish, UCI machine-learning repository, Mendeley website dataset and Phish tank. The results showed that the proposed model had an accuracy of 98.07%, a recall of 98.04%, a precision of 98.43%, and an F1-Score of 98.24%.

• Computers and Concrete
• /
• v.27 no.5
• /
• pp.489-512
• /
• 2021

In this study, two powerful techniques, namely particle swarm optimization (PSO) and imperialist competitive algorithm (ICA) were selected and combined with a pre-developed ANN model aiming at improving its performance prediction of the compressive strength of concrete modified with fly ash. To achieve this study's aims, a comprehensive database with 379 data samples was collected from the available literature. The output of the database is the compressive strength (CS) of concrete samples, which are influenced by 9 parameters as model inputs, namely those related to mix composition. The modeling steps related to ICA-ANN (or neuro-imperialism) and PSO-ANN (or neuro-swarm) were conducted through the use of several parametric studies to design the most influential parameters on these hybrid models. A comparison of the CS values predicted by hybrid intelligence techniques with the experimental CS values confirmed that the neuro-swarm model could provide a higher degree of accuracy than another proposed hybrid model (i.e., neuro-imperialism). The train and test correlation coefficient values of (0.9042 and 0.9137) and (0.8383 and 0.8777) for neuro-swarm and neuro-imperialism models, respectively revealed that although both techniques are capable enough in prediction tasks, the developed neuro-swarm model can be considered as a better alternative technique in mapping the concrete strength behavior.

• Composites Research
• /
• v.36 no.1
• /
• pp.59-67
• /
• 2023

Damage caused by impact on a vehicle composed of CFRP(carbon fiber reinforced plastic) composite to reduce weight in the aerospace industries is related to the safety of passengers. Therefore, it is important to understand the damage behavior of materials that is invisible in impact situations, and research through the FEM(finite element model) is needed to simulate this. In this study, FEM suitable for predicting damage behavior was constructed for impact analysis of unidirectional laminated composite. The calibration parameters of the MAT_54 Enhanced Composite Damage material model in LS-DYNA were acquired by inverse estimation through ANN(artificial neural network) model. The reliability was verified by comparing the result of experiment with the results of the ANN model for the obtained parameter. It was confirmed that accuracy of FEM can be improved through optimization of calibration parameters.

• Wind and Structures
• /
• v.36 no.6
• /
• pp.393-404
• /
• 2023

Skewness and kurtosis are important higher-order statistics for simulating non-Gaussian wind pressure series on low-rise buildings, but their predictions are less studied in comparison with those of the low order statistics as mean and rms. The distribution gradients of skewness and kurtosis on roofs are evidently higher than those of mean and rms, which increases their prediction difficulty. The conventional artificial neural networks (ANNs) used for predicting mean and rms show unsatisfactory accuracy in predicting skewness and kurtosis owing to the limited capacity of shallow learning of ANNs. In this work, the deep neural networks (DNNs) model with the ability of deep learning is introduced to predict the skewness and kurtosis on a low-rise building. For obtaining the optimal generalization of the DNNs model, the hyper parameters are automatically determined by Bayesian Optimization (BO). Moreover, for providing a benchmark for future studies on predicting higher order statistics, the data sets for training and testing the DNNs model are extracted from the internationally open NIST-UWO database, and the prediction errors of all taps are comprehensively quantified by various error metrices. The results show that the prediction accuracy in this study is apparently better than that in the literature, since the correlation coefficient between the predicted and experimental results is 0.99 and 0.75 in this paper and the literature respectively. In the untrained cornering wind direction, the distributions of skewness and kurtosis are well captured by DNNs on the whole building including the roof corner with strong non-normality, and the correlation coefficients between the predicted and experimental results are 0.99 and 0.95 for skewness and kurtosis respectively.

• International Journal of Heart Failure
• /
• v.6 no.1
• /
• pp.11-19
• /
• 2024

The prevalence of heart failure (HF) is increasing, necessitating accurate diagnosis and tailored treatment. The accumulation of clinical information from patients with HF generates big data, which poses challenges for traditional analytical methods. To address this, big data approaches and artificial intelligence (AI) have been developed that can effectively predict future observations and outcomes, enabling precise diagnoses and personalized treatments of patients with HF. Machine learning (ML) is a subfield of AI that allows computers to analyze data, find patterns, and make predictions without explicit instructions. ML can be supervised, unsupervised, or semi-supervised. Deep learning is a branch of ML that uses artificial neural networks with multiple layers to find complex patterns. These AI technologies have shown significant potential in various aspects of HF research, including diagnosis, outcome prediction, classification of HF phenotypes, and optimization of treatment strategies. In addition, integrating multiple data sources, such as electrocardiography, electronic health records, and imaging data, can enhance the diagnostic accuracy of AI algorithms. Currently, wearable devices and remote monitoring aided by AI enable the earlier detection of HF and improved patient care. This review focuses on the rationale behind utilizing AI in HF and explores its various applications.

• The KIPS Transactions:PartB
• /
• v.14B no.2
• /
• pp.127-134
• /
• 2007

There are many researches about the intelligent stock trading systems with the help of the advance of the artificial intelligence such as machine learning techniques, Though the establishment of the reasonable trading policy plays an important role in the performance of the trading systems most researches focused on the improvement of the predictability. Also some previous works, which treated the trading policy, treated the simplified versions dependent on the predictors in less systematic ways. In this paper, we propose the integrated multiple simulation' as a method of optimizing trading performance of stock trading systems. The propose method is adopted in the NXShell a development environment for neural network based stock trading systems. Under the proposed integrated multiple simulation', we simulate the multiple tradings for all combinations of the neural network's outputs and the trading policy parameters, evaluate the learning performance according to the various metrics and establish the optimal policy for a given prediction module based on the resulting performance. In the experiment, we present the trading policy comparison results using the stock value data from the KOSPI and KOSDAQ.

• Journal of Korean Association for Spatial Structures
• /
• v.24 no.2
• /
• pp.83-90
• /
• 2024

Machine learning is widely applied to various engineering fields. In structural engineering area, machine learning is generally used to predict structural responses of building structures. The aging deterioration of reinforced concrete structure affects its structural behavior. Therefore, the aging deterioration of R.C. structure should be consider to exactly predict seismic responses of the structure. In this study, the machine learning based seismic response prediction model was developed. To this end, four machine learning algorithms were employed and prediction performance of each algorithm was compared. A 3-story coupled shear wall structure was selected as an example structure for numerical simulation. Artificial ground motions were generated based on domestic site characteristics. Elastic modulus, damping ratio and density were changed to considering concrete degradation due to chloride penetration and carbonation, etc. Various intensity measures were used input parameters of the training database. Performance evaluation was performed using metrics like root mean square error, mean square error, mean absolute error, and coefficient of determination. The optimization of hyperparameters was achieved through k-fold cross-validation and grid search techniques. The analysis results show that neural networks and extreme gradient boosting algorithms present good prediction performance.