• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.49 no.7
• /
• pp.23-31
• /
• 2012

Resource allocation, such as joint rate control and scheduling, is an important issue in cognitive radio networks. However, it is difficult to jointly consider the rate control and scheduling problem due to the stochastic behavior of channel availability in cognitive radio networks. In this paper, we propose an asymmetric joint rate control and scheduling technique under reliability constraints in cognitive radio networks. The joint rate control and scheduling problem is formulated as a convex optimization problem and substantially decomposed into several sub-problems using a dual decomposition method. An algorithm for secondary users to locally update their rate that maximizes the utility of the overall system is also proposed. The results of simulations revealed that the proposed algorithm converges to a globally optimal solution.

• Korean Journal of Remote Sensing
• /
• v.33 no.4
• /
• pp.423-436
• /
• 2017

This paper presents a deep learning-based road segmentation framework from very high-resolution orthophotos. The proposed method uses Deep Convolutional Autoencoders for end-to-end mapping of orthophotos to road segmentations. In addition, a set of post-processing steps were applied to make the model outputs GIS-ready data that could be useful for various applications. The optimization of the model's parameters is explained which was conducted via grid search method. The model was trained and implemented in Keras, a high-level deep learning framework run on top of Tensorflow. The results show that the proposed model with the best-obtained hyperparameters could segment road objects from orthophotos at an average accuracy of 88.5%. The results of optimization revealed that the best optimization algorithm and activation function for the studied task are Stochastic Gradient Descent (SGD) and Exponential Linear Unit (ELU), respectively. In addition, the best numbers of convolutional filters were found to be 8 for the first and second layers and 128 for the third and fourth layers of the proposed network architecture. Moreover, the analysis on the time complexity of the model showed that the model could be trained in 4 hours and 50 minutes on 1024 high-resolution images of size $106{\times}106pixels$, and segment road objects from similar size and resolution images in around 14 minutes. The results show that the deep learning models such as Convolutional Autoencoders could be a best alternative to traditional machine learning models for road segmentation from aerial photographs.

• Steel and Composite Structures
• /
• v.51 no.6
• /
• pp.679-695
• /
• 2024

This paper presents a novel technique that combines machine learning (ML) with moth-flame optimization (MFO) methods to predict the axial compressive strength (ACS) of concrete filled double skin steel tubes (CFDST) columns. The proposed model is trained and tested with a dataset containing 125 tests of the CFDST column subjected to compressive loading. Five ML models, including extreme gradient boosting (XGBoost), gradient tree boosting (GBT), categorical gradient boosting (CAT), support vector machines (SVM), and decision tree (DT) algorithms, are utilized in this work. The MFO algorithm is applied to find optimal hyperparameters of these ML models and to determine the most effective model in predicting the ACS of CFDST columns. Predictive results given by some performance metrics reveal that the MFO-CAT model provides superior accuracy compared to other considered models. The accuracy of the MFO-CAT model is validated by comparing its predictive results with existing design codes and formulae. Moreover, the significance and contribution of each feature in the dataset are examined by employing the SHapley Additive exPlanations (SHAP) method. A comprehensive uncertainty quantification on probabilistic characteristics of the ACS of CFDST columns is conducted for the first time to examine the models' responses to variations of input variables in the stochastic environments. Finally, a web-based application is developed to predict ACS of the CFDST column, enabling rapid practical utilization without requesting any programing or machine learning expertise.

• Journal of the Korea Society for Simulation
• /
• v.19 no.1
• /
• pp.143-151
• /
• 2010

Fingerprint classification is a step to increase the efficiency of an 1:N fingerprint recognition system and plays a role to reduce the matching time of fingerprint and to increase accuracy of recognition. It is difficult to classify fingerprints, because the ridge pattern of each fingerprint class has an overlapping characteristic with more than one class, fingerprint images may include a lot of noise and an input condition is an exceptional case. In this paper, we propose a novel approach to design a stochastic model and to accomplish fingerprint classification using a directional characteristic of fingerprints for an effective classification of various qualities. We compute the directional value by searching a fingerprint ridge pixel by pixel and extract a directional characteristic by merging a computed directional value by fixed pixels unit. The modified Markov model of each fingerprint class is generated using Markov model which is a stochastic information extraction and a recognition method by extracted directional characteristic. The weight list of classification model of each class is decided by analyzing the state transition matrixes of the generated Markov model of each class and the optimized value which improves the performance of fingerprint classification using GA (Genetic Algorithm) is estimated. The performance of the optimized classification model by GA is superior to the model before the optimization by the experiment result of applying the fingerprint database of various qualities to the optimized model by GA. And the proposed method effectively achieved fingerprint classification to exceptional input conditions because this approach is independent of the existence and nonexistence of singular points by the result of analyzing the fingerprint database which is used to the experiments.

• Journal of KIISE:Software and Applications
• /
• v.30 no.9
• /
• pp.862-866
• /
• 2003

Traveling Salesman Problem(TSP) is a combinational optimization problem, Genetic Algorithm(GA) and Lin-Kernighan(LK) Heuristic［1］that is Local Search Heuristic are one of the most commonly used methods to resolve TSP. In this paper, we introduce ACS(Ant Colony System) Algorithm as another approach to solve TSP and propose a new pheromone updating method. ACS uses pheromone information between cities in the Process where many ants make a tour, and is a method to find a optimal solution through recursive tour creation process. At the stage of Global Updating of ACS method, it updates pheromone of edges belonging to global best tour of created all edge. But we perform once more pheromone update about created all edges before global updating rule of original ACS is applied. At this process, we use the frequency of occurrence of each edges to update pheromone. We could offer stochastic value by pheromone about each edges, giving all edges' occurrence frequency as weight about Pheromone. This finds an optimal solution faster than existing ACS algorithm and prevent a local optima using more edges in next time search.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.1A
• /
• pp.76-83
• /
• 2009

In this paper, we provide opportunistic scheduling schemes for elastic services in OFDMA systems with fairness constraints for each user. We adopt the network utility maximization framework in which a utility function is defined for each user to represent its level of satisfaction to the service. Since we consider elastic services whose degree of satisfaction depends on its average data rate, we define the utility function of each user as a function of its average data rate. In addition, for fair resource allocation among users, we define fairness requirements of each user by using utility functions. We first formulate an optimization problem for each fairness requirement that aim at maximizing network utility, which is defined as the sum of utilities of users. We then develop an opportunistic scheduling scheme for each fairness requirement by solving the problem using a dual approach and a stochastic sub-gradient algorithm.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.115-119
• /
• 2006

The channel is one of the precious and limited resources in wireless networks. There are many researches on the channel management. Recently, the optimization problem of guard channels has been an important issue. In this paper, we propose an intelligent channel management technique based on the neural networks. An SRN channel alteration model is developed to generate the learning data for the neural networks and the performance analysis of system. In the proposed technique, the neural network is trained to generate optimal guard channel number g, using backpropagation supervised learning algorithm. The optimal g is computed using the neural network and compared to the g computed by the SRN model. The numerical results show that the difference between the value of g by backpropagation and that value by SRN model is ignorable.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.647-654
• /
• 2023

Deep Learning is a useful method for classifying and recognizing complex data such as images and text, and the accuracy of the deep learning method is the basis for making artificial intelligence-based services on the Internet useful. However, the vast amount of user da vita used for training in deep learning has led to privacy violation problems, and it is worried that companies that have collected personal and sensitive data of users, such as photographs and voices, own the data indefinitely. Users cannot delete their data and cannot limit the purpose of use. For example, data owners such as medical institutions that want to apply deep learning technology to patients' medical records cannot share patient data because of privacy and confidentiality issues, making it difficult to benefit from deep learning technology. In this paper, we have designed a privacy preservation technique-applied deep learning technique that allows multiple workers to use a neural network model jointly, without sharing input datasets, in multi-party system. We proposed a method that can selectively share small subsets using an optimization algorithm based on modified stochastic gradient descent, confirming that it could facilitate training with increased learning accuracy while protecting private information.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.1A
• /
• pp.45-52
• /
• 2009

In conventional structural design, deterministic optimization which satisfies codified constraints is performed to ensure safety and maximize economical efficiency. However, uncertainties are inevitable due to the stochastic nature of structural materials and applied loads. Thus, deterministic optimization without considering these uncertainties could lead to unreliable design. Recently, there has been much research in reliability-based design optimization (RBDO) taking into consideration both the reliability and optimization. RBDO involves the evaluation of probabilistic constraint that can be estimated using the RIA (Reliability Index Approach) and the PMA(Performance Measure Approach). It is generally known that PMA is more stable and efficient than RIA. Despite the significant advancement in PMA, RBDO still requires large computation time for large-scale applications. In this paper, A new reliability-based design optimization (RBDO) method is presented to achieve the more stable and efficient algorithm. The idea of the new method is to integrate a response surface method (RSM) with PMA. For the approximation of a limit state equation, the moving least squares (MLS) method is used. Through a mathematical example and ten-bar truss problem, the proposed method shows better convergence and efficiency than other approaches.

• Smart Structures and Systems
• /
• v.17 no.3
• /
• pp.523-539
• /
• 2016

The ambient vibration measurement is an output-data-only dynamic testing where natural excitations are represented, for instance, by winds and typhoons. The modal identification involving output-only measurements requires the use of specific modal identification techniques. This paper presents the application of a reliable method (the Stochastic Subspace Identification - SSI) implemented in a general purpose software. As a criterion toward the robustness of identified modes, a bio-inspired optimization algorithm, with a highly nonlinear objective function, is introduced in order to find the optimal deployment of a reduced number of sensors across a large civil engineering structure for the validation of its modal identification. The Ting Kau Bridge (TKB), one of the longest cable-stayed bridges situated in Hong Kong, is chosen as a case study. The results show that the proposed method catches eigenvalues and eigenvectors even for a reduced number of sensors, without any significant loss of accuracy.