• Steel and Composite Structures
• /
• v.47 no.2
• /
• pp.167-184
• /
• 2023

In this study, a new recentering friction device (RFD) to retrofit steel moment frame structures is introduced. The device provides both self-centering and energy dissipation capabilities for the retrofitted structure. A hybrid performance-based seismic design procedure considering multiple limit states is proposed for designing the device and the retrofitted structure. The design of the RFD is achieved by modifying the conventional performance-based seismic design (PBSD) procedure using computational intelligence techniques, namely, genetic algorithm (GA) and artificial neural network (ANN). Numerous nonlinear time-history response analyses (NLTHAs) are conducted on multi-degree of freedom (MDOF) and single-degree of freedom (SDOF) systems to train and validate the ANN to achieve high prediction accuracy. The proposed procedure and the new RFD are assessed using 2D and 3D models globally and locally. Globally, the effectiveness of the proposed device is assessed by conducting NLTHAs to check the maximum inter-story drift ratio (MIDR). Seismic fragilities of the retrofitted models are investigated by constructing fragility curves of the models for different limit states. After that, seismic life cycle cost (LCC) is estimated for the models with and without the retrofit. Locally, the stress concentration at the contact point of the RFD and the existing steel frame is checked being within acceptable limits using finite element modeling (FEM). The RFD showed its effectiveness in minimizing MIDR and eliminating residual drift for low to mid-rise steel frames models tested. GA and ANN proved to be crucial integrated parts in the modified PBSD to achieve the required seismic performance at different limit states with reasonable computational cost. ANN showed a very high prediction accuracy for transformation between MDOF and SDOF systems. Also, the proposed retrofit showed its efficiency in enhancing the seismic fragility and reducing the LCC significantly compared to the un-retrofitted models.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.125-140
• /
• 2013

We call a data set in which the number of records belonging to a certain class far outnumbers the number of records belonging to the other class, 'imbalanced data set'. Most of the classification techniques perform poorly on imbalanced data sets. When we evaluate the performance of a certain classification technique, we need to measure not only 'accuracy' but also 'sensitivity' and 'specificity'. In a customer churn prediction problem, 'retention' records account for the majority class, and 'churn' records account for the minority class. Sensitivity measures the proportion of actual retentions which are correctly identified as such. Specificity measures the proportion of churns which are correctly identified as such. The poor performance of the classification techniques on imbalanced data sets is due to the low value of specificity. Many previous researches on imbalanced data sets employed 'oversampling' technique where members of the minority class are sampled more than those of the majority class in order to make a relatively balanced data set. When a classification model is constructed using this oversampled balanced data set, specificity can be improved but sensitivity will be decreased. In this research, we developed a hybrid model of support vector machine (SVM), artificial neural network (ANN) and decision tree, that improves specificity while maintaining sensitivity. We named this hybrid model 'hybrid SVM model.' The process of construction and prediction of our hybrid SVM model is as follows. By oversampling from the original imbalanced data set, a balanced data set is prepared. SVM_I model and ANN_I model are constructed using the imbalanced data set, and SVM_B model is constructed using the balanced data set. SVM_I model is superior in sensitivity and SVM_B model is superior in specificity. For a record on which both SVM_I model and SVM_B model make the same prediction, that prediction becomes the final solution. If they make different prediction, the final solution is determined by the discrimination rules obtained by ANN and decision tree. For a record on which SVM_I model and SVM_B model make different predictions, a decision tree model is constructed using ANN_I output value as input and actual retention or churn as target. We obtained the following two discrimination rules: 'IF ANN_I output value <0.285, THEN Final Solution = Retention' and 'IF ANN_I output value ${\geq}0.285$, THEN Final Solution = Churn.' The threshold 0.285 is the value optimized for the data used in this research. The result we present in this research is the structure or framework of our hybrid SVM model, not a specific threshold value such as 0.285. Therefore, the threshold value in the above discrimination rules can be changed to any value depending on the data. In order to evaluate the performance of our hybrid SVM model, we used the 'churn data set' in UCI Machine Learning Repository, that consists of 85% retention customers and 15% churn customers. Accuracy of the hybrid SVM model is 91.08% that is better than that of SVM_I model or SVM_B model. The points worth noticing here are its sensitivity, 95.02%, and specificity, 69.24%. The sensitivity of SVM_I model is 94.65%, and the specificity of SVM_B model is 67.00%. Therefore the hybrid SVM model developed in this research improves the specificity of SVM_B model while maintaining the sensitivity of SVM_I model.

• Geomechanics and Engineering
• /
• v.15 no.1
• /
• pp.631-643
• /
• 2018

The estimation of the strength and other mechanical parameters characterizing the tensile behavior of granites can play an important role in civil engineering tasks such as design, construction, rehabilitation and repair of existing structures. The purpose of this paper is to apply data mining techniques, such as multiple regression (MR), artificial neural networks (ANN) and support vector machines (SVM) to estimate the mechanical properties of granites. In a first phase, the mechanical parameters defining the complete tensile behavior are estimated based on the tensile strength. In a second phase, the estimation of the mechanical properties is carried out from different combination of the physical properties (ultrasonic pulse velocity, porosity and density). It was observed that the estimation of the mechanical properties can be optimized by combining different physical properties. Besides, it was seen that artificial neural networks and support vector machines performed better than multiple regression model.

• Journal of Intelligence and Information Systems
• /
• v.16 no.4
• /
• pp.159-172
• /
• 2010

The recommender system is one of the possible solutions to assist customers in finding the items they would like to purchase. To date, a variety of recommendation techniques have been developed. One of the most successful recommendation techniques is Collaborative Filtering (CF) that has been used in a number of different applications such as recommending Web pages, movies, music, articles and products. CF identifies customers whose tastes are similar to those of a given customer, and recommends items those customers have liked in the past. Numerous CF algorithms have been developed to increase the performance of recommender systems. Broadly, there are memory-based CF algorithms, model-based CF algorithms, and hybrid CF algorithms which combine CF with content-based techniques or other recommender systems. While many researchers have focused their efforts in improving CF performance, the theoretical justification of CF algorithms is lacking. That is, we do not know many things about how CF is done. Furthermore, the relative performances of CF algorithms are known to be domain and data dependent. It is very time-consuming and expensive to implement and launce a CF recommender system, and also the system unsuited for the given domain provides customers with poor quality recommendations that make them easily annoyed. Therefore, predicting the performances of CF algorithms in advance is practically important and needed. In this study, we propose an efficient approach to predict the performance of CF. Social Network Analysis (SNA) and Artificial Neural Network (ANN) are applied to develop our prediction model. CF can be modeled as a social network in which customers are nodes and purchase relationships between customers are links. SNA facilitates an exploration of the topological properties of the network structure that are implicit in data for CF recommendations. An ANN model is developed through an analysis of network topology, such as network density, inclusiveness, clustering coefficient, network centralization, and Krackhardt's efficiency. While network density, expressed as a proportion of the maximum possible number of links, captures the density of the whole network, the clustering coefficient captures the degree to which the overall network contains localized pockets of dense connectivity. Inclusiveness refers to the number of nodes which are included within the various connected parts of the social network. Centralization reflects the extent to which connections are concentrated in a small number of nodes rather than distributed equally among all nodes. Krackhardt's efficiency characterizes how dense the social network is beyond that barely needed to keep the social group even indirectly connected to one another. We use these social network measures as input variables of the ANN model. As an output variable, we use the recommendation accuracy measured by F1-measure. In order to evaluate the effectiveness of the ANN model, sales transaction data from H department store, one of the well-known department stores in Korea, was used. Total 396 experimental samples were gathered, and we used 40%, 40%, and 20% of them, for training, test, and validation, respectively. The 5-fold cross validation was also conducted to enhance the reliability of our experiments. The input variable measuring process consists of following three steps; analysis of customer similarities, construction of a social network, and analysis of social network patterns. We used Net Miner 3 and UCINET 6.0 for SNA, and Clementine 11.1 for ANN modeling. The experiments reported that the ANN model has 92.61% estimated accuracy and 0.0049 RMSE. Thus, we can know that our prediction model helps decide whether CF is useful for a given application with certain data characteristics.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.4
• /
• pp.129-134
• /
• 2018

Recently, the artificial neural network (ANN) model is a promising technique in the prediction, numerical control, robot control and pattern recognition. We predicted the outside temperature of greenhouse using ANN and utilized the model in greenhouse control. The performance of ANN model was evaluated and compared with multiple regression model(MRM) and support vector machine (SVM) model. The 10-fold cross validation was used as the evaluation method. In order to improve the prediction performance, the data reduction was performed by correlation analysis and new factor were extracted from measured data to improve the reliability of training data. The backpropagation algorithm was used for constructing ANN, multiple regression model was constructed by M5 method. And SVM model was constructed by epsilon-SVM method. As the result showed that the RMSE (Root Mean Squared Error) value of ANN, MRM and SVM were 0.9256, 1.8503 and 7.5521 respectively. In addition, by applying the prediction model to greenhouse heating load calculation, it can increase the income by reducing the energy cost in the greenhouse. The heating load of the experimented greenhouse was 3326.4kcal/h and the fuel consumption was estimated to be 453.8L as the total heating time is $10000^{\circ}C/h$. Therefore, data mining technology of ANN can be applied to various agricultural fields such as precise greenhouse control, cultivation techniques, and harvest prediction, thereby contributing to the development of smart agriculture.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.3-6
• /
• 2000

In this paper, ‘gesture’ is discussed as a means of human-friendly communication between man and machine. We classify various gestures into two Categories: ‘contact based’ and ‘non-contact based’ Each method is reviewed and some real applications are introduced. Also, key design issues of the method are addressed and some contributions of soft-computing techniques, such as fuzzy logic, artificial neural networks (ANN), rough set theory and evolutionary computation, are discussed.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.551-552
• /
• 2007

Increasingly nonlinear dynamic loads have been connected into power systems. This adds to the harmonics in the power system. In traditional load modeling techniques, the harmonics has not been considered. Thus, the harmonics problems in load modeling are considered and ANN load modeling is proposed.

• Journal of Soil and Groundwater Environment
• /
• v.21 no.3
• /
• pp.21-34
• /
• 2016

In the present study, we applied various machine learning techniques comparatively for prediction of subsurface structures based on multiple secondary information (i.e., well-logging data). The machine learning techniques employed in this study are Naive Bayes classification (NB), artificial neural network (ANN), support vector machine (SVM) and logistic regression classification (LR). As an alternative model, conventional hidden Markov model (HMM) and modified hidden Markov model (mHMM) are used where additional information of transition probability between primary properties is incorporated in the predictions. In the comparisons, 16 boreholes consisted with four different materials are synthesized, which show directional non-stationarity in upward and downward directions. Futhermore, two types of the secondary information that is statistically related to each material are generated. From the comparative analysis with various case studies, the accuracies of the techniques become degenerated with inclusion of additive errors and small amount of the training data. For HMM predictions, the conventional HMM shows the similar accuracies with the models that does not relies on transition probability. However, the mHMM consistently shows the highest prediction accuracy among the test cases, which can be attributed to the consideration of geological nature in the training of the model.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06a
• /
• pp.893-898
• /
• 1994

In this paper, the influence of voice source estimation and modeling on speech synthesis and coding is examined and then their new estimation and modeling techniques are proposed and verified by computer simulation. It is known that the existing speech synthesizer produced the speech which is dull and inanimated. These problems are arised from the fact that existing estimation and modeling techniques can not give more accurate voice parameters. Therefore, in this paper we propose a new voice source estimation algorithm and modeling techniques which can not give more accurate voice parameters. Therefore, in this paper we propose a new voice source estimation algorithm and modeling techniques which can represent a variety of source characteristics. First, we divide speech samples in one pitch region into four parts having different characteristics. Second, the vocal-tract parameters and voice source waveforms are estimated in each regions differently using sequential SVD. Third, we propose composite source model as a new voice source model which is represented by weighted sum of pre-defined basis functions. And finally, the weights and time-shift parameters of the proposed composite source model are estimeted uning EM(estimate maximize) algorithm. Experimental results indicate that the proposed estimation and modeling methods can estimate more accurate voice source waveforms and represent various source characteristics.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.73-78
• /
• 2022

The aim of this paper is to investigate the prevalence of Deep Learning in the literature on Fire & Rescue Service. It is found that deep learning techniques are only beginning to benefit the firefighters. The popular areas where deep learning techniques are making an impact are situational awareness, decision making, mental stress, injuries, well-being of the firefighter such as his sudden fall, inability to move and breathlessness, path planning by the firefighters while getting to an fire scene, wayfinding, tracking firefighters, firefighter physical fitness, employment, prediction of firefighter intervention, firefighter operations such as object recognition in smoky areas, firefighter efficacy, smart firefighting using edge computing, firefighting in teams, and firefighter clothing and safety. The techniques that were found applied in firefighting were Deep learning, Traditional K-Means clustering with engineered time and frequency domain features, Convolutional autoencoders, Long Short-Term Memory (LSTM), Deep Neural Networks, Simulation, VR, ANN, Deep Q Learning, Deep learning based on conditional generative adversarial networks, Decision Trees, Kalman Filters, Computational models, Partial Least Squares, Logistic Regression, Random Forest, Edge computing, C5 Decision Tree, Restricted Boltzmann Machine, Reinforcement Learning, and Recurrent LSTM. The literature review is centered on Firefighters/firemen not involved in wildland fires. The focus was also not on the fire itself. It must also be noted that several deep learning techniques such as CNN were mostly used in fire behavior, fire imaging and identification as well. Those papers that deal with fire behavior were also not part of this literature review.