• Steel and Composite Structures
• /
• v.48 no.2
• /
• pp.179-190
• /
• 2023

Many recent attempts have sought accurate prediction of pile pullout resistance (P_ul) using classical machine learning models. This study offers an improved methodology for this objective. Adaptive neuro-fuzzy inference system (ANFIS), as a popular predictor, is trained by a capable metaheuristic strategy, namely equilibrium optimizer (EO) to predict the P_ul. The used data is collected from laboratory investigations in previous literature. First, two optimal configurations of EO-ANFIS are selected after sensitivity analysis. They are next evaluated and compared with classical ANFIS and two neural-based models using well-accepted accuracy indicators. The results of all five models were in good agreement with laboratory P_uls (all correlations > 0.99). However, it was shown that both EO-ANFISs not only outperform neural benchmarks but also enjoy a higher accuracy compared to the classical version. Therefore, utilizing the EO is recommended for optimizing this predictive tool. Furthermore, a comparison between the selected EO-ANFISs, where one employs a larger population, revealed that the model with the population size of 75 is more efficient than 300. In this relation, root mean square error and the optimization time for the EO-ANFIS (75) were 19.6272 and 1715.8 seconds, respectively, while these values were 23.4038 and 9298.7 seconds for EO-ANFIS (300).

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.4
• /
• pp.39-46
• /
• 2024

Many researchers make efforts to evaluate water quality using various models. Such models require a dataset without missing values, but in real world, most datasets include missing values for various reasons. Simple deletion of samples having missing value(s) could distort distribution of the underlying data and pose a significant risk of biasing the model's inference when the missing mechanism is not MCAR. In this study, to explore the most appropriate technique for handing missing values in water quality data, several imputation techniques were experimented based on existing KNN and MICE imputation with/without the generative neural network model, Autoencoder(AE) and Denoising Autoencoder(DAE). The results shows that KNN and MICE combined imputation without generative networks provides the closest estimated values to the true values. When evaluating binary classification models based on support vector machine and ensemble algorithms after applying the combined imputation technique to the observed water quality dataset with missing values, it shows better performance in terms of Accuracy, F1 score, RoC-AuC score and MCC compared to those evaluated after deleting samples having missing values.

• Journal of Korean Society of Environmental Engineers
• /
• v.32 no.1
• /
• pp.97-104
• /
• 2010

At present, the biological nutrient removal (BNR) process for removal of nitrogen and phosphorus is being constructing to keep pace with the reinforced standard of effluent quality and the traditional activated sludge process of preexistence is being promoting to retrofit. At the most case of retrofitting, processes are subjected to be under consideration as alternative BNR process for retrofitting. However, process evaluation methods are restricted to compare only treatment efficiency. Therefore, when BNR process apply, process evaluation was needed various method for treatment efficiency as well as sludge production and aeration cost, and all. In this study, the evaluation method of alternative process was suggested for the case for retrofitting S wastewater treatment plant which has been operated the standard activated sludge process. Three BNR processes for evaluation of proper alternatative process were selected and evaluated with suggested method. The selected $A^2$/O, VIP and DNR processes were evaluated using the mathematical model which is time and cost effective as well as gathered objective evaluation criteria. The evaluation between 5 individual criteria was possible including sludge production and energy efficiency as well as treatment performance. The objective final decision method for selection of optimal process was established through the fuzzy inference.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.5B
• /
• pp.439-447
• /
• 2011

It is a main concern for sustainable development in water resources management to evaluate adaptation capability of water resources structures under the future climate conditions. This study introduced the Fuzzy Inference System (FIS) to represent the change of release and storage of reservoirs in the Han River basin corresponding to various inflows. Defining the adaptation capability of reservoirs as the change of maximum and/or minimum of storage corresponding to the change of inflow, the study showed that Gangdong Dam has the worst adaptation capability on the variation of inflow, while Soyanggang Dam has the best capability. This study also constructed an Adaptive Neuro-Fuzzy Inference System (ANFIS) for the more accurate and efficient simulation of the adaptation capability of the Soyanggang Dam. Nine Inflow scenarios were generated using historical data from frequency analysis and synthetic data from two general circulation models with different climate change scenarios. The ANFIS showed significantly different consequences of the release and reservoir storage upon inflow scenarios of Soyanggang Dam, whilst it provides stable reservoir operations despite the variability of rainfall pattern.

• Journal of Digital Convergence
• /
• v.17 no.1
• /
• pp.239-247
• /
• 2019

An accurate prediction of emotion is a very important issue for the sake of patient-centered medical device development and emotion-related psychology fields. Although there have been many studies on emotion prediction, no studies have applied the heart rate variability and neuro-fuzzy approach to emotion prediction. We propose ANFEP(Adaptive Neuro Fuzzy System for Emotion Prediction) HRV. The ANFEP bases its core functions on an ANFIS(Adaptive Neuro-Fuzzy Inference System) which integrates neural networks with fuzzy systems as a vehicle for training predictive models. To prove the proposed model, 50 participants were invited to join the experiment and Heart rate variability was obtained and used to input the ANFEP model. The ANFEP model with STDRR and RMSSD as inputs and two membership functions per input variable showed the best results. The result out of applying the ANFEP to the HRV metrics proved to be significantly robust when compared with benchmarking methods like linear regression, support vector regression, neural network, and random forest. The results show that reliable prediction of emotion is possible with less input and it is necessary to develop a more accurate and reliable emotion recognition system.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.10
• /
• pp.323-332
• /
• 2022

As various services using AI technology are being developed, much attention is being paid to AI service production. Recently, AI technology is acknowledged as one of ICT services, a lot of research is being conducted for general-purpose AI service production. In this paper, I describe the research results in terms of systems for AI service production, focusing on the distribution and production of machine learning models, which are the final steps of general machine learning development procedures. Three different Ubuntu systems were built, and experiments were conducted on the system, using data from 2017 validation COCO dataset in combination of different AI models (RFCN, SSD-Mobilenet) and different communication methods (gRPC, REST) to request and perform AI services through Tensorflow serving. Through various experiments, it was found that the type of AI model has a greater influence on AI service inference time than AI machine communication method, and in the case of object detection AI service, the number and complexity of objects in the image are more affected than the file size of the image to be detected. In addition, it was confirmed that if the AI service is performed remotely rather than locally, even if it is a machine with good performance, it takes more time to infer the AI service than if it is performed locally. Through the results of this study, it is expected that system design suitable for service goals, AI model development, and efficient AI service production will be possible.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.3C
• /
• pp.115-125
• /
• 2009

The preconsolidation pressure has been commonly determined by oedometer test. However, it can also be determined by insitu test, such as piezocone test with theoretical and(or) empirical correlations. Recently, Neural Network (NN) theory was applied and some models were proposed to estimate the preconsolidation pressure or OCR. It was already found that NN model can come over the site dependency and prediction accuracy is greatly improved when compared with present theoretical and empirical models. However, since the optimization process of synaptic weights of NN model is dependent on the initial synaptic weights, NN models which are trained with different initial weights can't avoid the variability on prediction result for new database even though they have same structure and use same transfer function. In this study, Committee Neural Network (CNN) model is proposed to improve the initial weight dependency of multi-layered neural network model on the prediction of preconsolidation pressure of soft clay from piezocone test result. Prediction results of CNN model are compared with those of conventional empirical and theoretical models and multi-layered neural network model, which has the optimized structure. It was found that even though the NN model has the optimized structure for given training data set, it still has the initial weight dependency, while the proposed CNN model can improve the initial weight dependency of the NN model and provide a consistent and precise inference result than existing NN models.

• Education of Primary School Mathematics
• /
• v.15 no.1
• /
• pp.31-40
• /
• 2012

In this paper, we developed teaching learning models using a numeral operation for the mathematical gifted focused on the design of a circle using GSP and investigated effects of this models. This model gave gifted-students to be able to produce creative outputs with mathematical principles and practicality and beauty of mathematics. We found following facts. Firstly, a developed teaching-learning model improves a mathematical gifted student's mathematical creativity as analytic thinking and deductive inference. Secondly, a circular design using GSP helps gifted students to understand the abstract rules because mathematical patterns was represented visually by a circular design. Lastly, a circular design using a numeral operation is helpful to gifted students revealing to creativity and beauty of mathematics.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.1
• /
• pp.81-98
• /
• 2013

Since Probabilistic Latent Semantic Analysis (PLSA) and Latent Dirichlet Allocation (LDA) were introduced, many revised or extended topic models have appeared. Due to the intractable likelihood of these models, training any topic model requires to use some approximation algorithm such as variational approximation, Laplace approximation, or Markov chain Monte Carlo (MCMC). Although these approximation algorithms perform well, training a topic model is still computationally expensive given the large amount of data it requires. In this paper, we propose a new method, called non-simultaneous sampling deactivation, for efficient approximation of parameters in a topic model. While each random variable is normally sampled or obtained by a single predefined burn-in period in the traditional approximation algorithms, our new method is based on the observation that the random variable nodes in one topic model have all different periods of convergence. During the iterative approximation process, the proposed method allows each random variable node to be terminated or deactivated when it is converged. Therefore, compared to the traditional approximation ways in which usually every node is deactivated concurrently, the proposed method achieves the inference efficiency in terms of time and memory. We do not propose a new approximation algorithm, but a new process applicable to the existing approximation algorithms. Through experiments, we show the time and memory efficiency of the method, and discuss about the tradeoff between the efficiency of the approximation process and the parameter consistency.

• Journal of Digital Convergence
• /
• v.11 no.12
• /
• pp.319-326
• /
• 2013

There are many software reliability models that are based on the times of occurrences of errors in the debugging of software. Software error detection techniques known in advance, but influencing factors for considering the errors found automatically and learning factors, by prior experience, to find precisely the error factor setting up the testing manager are presented comparing the problem. It is shown that it is possible to do asymptotic likelihood inference for software reliability models based on infinite failure model and non-homogeneous Poisson Processes (NHPP). Statistical process control (SPC) can monitor the forecasting of software failure and thereby contribute significantly to the improvement of software reliability. Control charts are widely used for software process control in the software industry. In this paper, we proposed a control mechanism based on NHPP using mean value function of logarithmic hazard learning effects property.