• Geomechanics and Engineering
• /
• v.33 no.6
• /
• pp.567-581
• /
• 2023

The prediction and achievement of a proper rock fragmentation size is the main challenge of blasting operations in surface mines. This is because an optimum size distribution can optimize the overall mine/plant economics. To this end, this study attempts to develop four improved artificial intelligence models to predict rock fragmentation through cascaded forward neural network (CFNN) and radial basis function neural network (RBFNN) models. In this regards, the CFNN was trained by the Levenberg-Marquardt algorithm (LMA) and Conjugate gradient backpropagation (CGP). Further, the RBFNN was optimized by the Dragonfly Algorithm (DA) and teaching-learning-based optimization (TLBO). For developing the models, the database required was collected from the Midouk copper mine, Iran. After modeling, the statistical functions were computed to check the accuracy of the models, and the root mean square errors (RMSEs) of CFNN-LMA, CFNN-CGP, RBFNN-DA, and RBFNN-TLBO were obtained as 1.0656, 1.9698, 2.2235, and 1.6216, respectively. Accordingly, CFNN-LMA, with the lowest RMSE, was determined as the model with the best prediction results among the four examined in this study.

• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.21-31
• /
• 2023

In this paper, we focused on the problem of evaluating multi-class classification accuracy and simulation of multiple classifier performance metrics. Multi-class classifiers for sentiment analysis involved many challenges, whereas previous research narrowed to the binary classification model since it provides higher accuracy when dealing with text data. Thus, we take inspiration from the non-linear Support Vector Machine to modify the algorithm by embedding dynamic hyperplanes representing multiple class labels. Then we analyzed the performance of multi-class classifiers using macro-accuracy, micro-accuracy and several other metrics to justify the significance of our algorithm enhancement. Furthermore, we hybridized Enhanced Convolution Neural Network (ECNN) with Dynamic Support Vector Machine (DSVM) to demonstrate the effectiveness and efficiency of the classifier towards multi-class text data. We performed experiments on three hybrid classifiers, which are ECNN with Binary SVM (ECNN-BSVM), and ECNN with linear Multi-Class SVM (ECNN-MCSVM) and our proposed algorithm (ECNNDSVM). Comparative experiments of hybrid algorithms yielded 85.12 % for single metric accuracy; 86.95 % for multiple metrics on average. As for our modified algorithm of the ECNN-DSVM classifier, we reached 98.29 % micro-accuracy results with an f-score value of 98 % at most. For the future direction of this research, we are aiming for hyperplane optimization analysis.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.105-114
• /
• 2023

In this paper, we propose a deployment and operation scheme of UxNB network toward mobile IAB. By operating a UxNB network based on SDN(Software Defined Network), UxNBs are deployed in areas where mobile communication services are desired. After deploying UxNB in the service area, IAB can be set up to perform mobile communication services. For this purpose, this paper first proposes a UxNB Network Controller consisting of a UAV Controller and an SDN Controller, and proposes the necessary functions. Next, we present a scenario in which a UxNB network can be deployed and operated in detail step by step. We also discuss the location of the UxNB network controller, how to deliver control commands from the UAV controller to the UxNB, how to apply IAB for UxNB networks, optimization of UxNB networks, RLF(radio link failure) recovery in UxNB networks, and future research on security in UxNB networks. It is expected that the proposed UxNB Network Controller architecture and UxNB network deployment and operation will enable seamless integration of UxNB networks into Mobile IAB.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.1A
• /
• pp.67-72
• /
• 2011

There are lots of researches for mobility of MS(mobile station) in All IP based network. Specially, NEMO(NEwork MObility) is not supporting mobility of each MS but supporting mobility of network that include group of MS. Some research try to overcome limitation of wireless with the protocol in wired state and it maintains the performance such as wire environment. There are no researches about multicast with reliability in NEMO. Therefore, this paper suggests efficient algorithm to solve problems when RMTP(Reliable Multicast Transport Protocol) apply to NEMO environment to support high reliability with multicast. And this paper shows the better performance of proposed algorithm for delay and transmission rate between AR and TLMR comparing with RMTP in NEMO.

• Journal of KIISE
• /
• v.43 no.12
• /
• pp.1412-1419
• /
• 2016

In cognitive radio sensor networks (CRSNs), secondary users (SUs) can occupy licensed bands opportunistically without causing interferences to primary users (PUs). SUs perform spectrum sensing to detect the presence of PUs. Sensing time is a critical parameter for spectrum sensing that can yield a tradeoff between sensing performance and secondary throughput. In this study, we investigate new approaches for spectrum sensing by exploring the tradeoff from a) spectrum sensing for PU detection (SSPD) and b) spectrum sensing for secondary throughput (SSST). In the proposed scheme, the first sensing result of the current frame determines the dynamic performance of the second spectrum sensing. Energy constraint in CRSNs leads to maximized network energy efficiency via optimization of sensing time. Simulation results show that the proposed scheme of SSPD and SSST improves network performance in terms of energy efficiency and secondary throughput, respectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.9
• /
• pp.4145-4164
• /
• 2016

Energy harvesting is an increasingly attractive source of power for cellular networks, and can be a promising solution for green networks. In this paper, we consider a cellular network with power beacons powering multiple mobile terminals with microwave power transfer in energy beamforming. In this network, the power beacons are powered by grid and renewable energy jointly. We adopt a dual-level control architecture, in which controllers collect information for a core controller, and the core controller has a real-time global view of the network. By implementing the water filling optimized power allocation strategy, the core controller optimizes the energy allocation among mobile terminals within the same cluster. In the proposed green energy cooperation paradigm, power beacons dynamically share their renewable energy by locally injecting/drawing renewable energy into/from other power beacons via the core controller. Then, we propose a new water filling optimized green energy cooperation management strategy, which jointly exploits water filling optimized power allocation strategy and green energy cooperation in cellular networks. Finally, we validate our works by simulations and show that the proposed water filling optimized green energy cooperation management strategy can achieve about 10% gains of MT's average rate and about 20% reduction of on-grid energy consumption.

• Journal of Intelligence and Information Systems
• /
• v.13 no.3
• /
• pp.101-117
• /
• 2007

In this paper, we propose a customized genetic algorithm (GA) to find the minimum-cost guideway network (GN) of personal rapid transit (PRT) subject to connectivity, reliability, and traffic capacity constraints. PRT is a novel transportation concept, where a number of automated taxi-sized vehicles run on an elevated GN. One of the most important problems regarding PRT is how to design its GN topology for given station locations and the associated inter-station traffic demands. We model the GN as a directed graph, where its cost, connectivity, reliability, and node traffics are formulated. Based on this formulation, we develop the GA with special genetic operators well suited for the GN design problem. Such operators include steady state selection, repair algorithm, and directed mutation. We perform numerical experiments to determine the adequate GA parameters and compare its performance to other optimization algorithms previously reported. The experimental results verify the effectiveness and efficiency of the proposed approach for the GN design problem having up to 210 links.

• Journal of Korean Society of Transportation
• /
• v.26 no.2
• /
• pp.89-100
• /
• 2008

In an urban network controlled by traffic signals, there is an interaction between the signal timing and the routes chosen by individual road users. This study develops a bi level programming model for traffic signal optimization in networks with path based traffic assignment. In the bi level programming model, genetic algorithm approach has been proposed to solve upper level problem for a signalized road network. Path based traffic assignment using column generation technique which is proposed by M.H. Xu, is applied at the lower-level. Genetic Algorithm provieds a feasible set of signal timings within specified lower and upper bounds signal timing variables and feeds into lower level problem. The performance of this model is investigated in numerical experiment in a sample network. In result, optimal signal settings and user equilibrium flows are made.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.8
• /
• pp.1504-1511
• /
• 2009

By development of renewable energies and high-efficient facilities and deregulated electricity market, the operation cost of distributed generation(DG) becomes more competitive. The amount of distributed resource is considerably increasing in the distribution network consequently. Also, international environmental regulations of the leaking carbon become effective to keep pace with the global efforts for low-carbon paradigm. It contributes to spread out the business of DG. Therefore, the operator of DG is able to supply electric power to customers who are connected directly to DG as well as loads that are connected to entire network. In this situation, community energy system(CES) having DGs is recently a new participant in the energy market. DG's purchase price from the market is different from the DG's sales price to the market due to the transmission service charges and etc. Therefore, CES who owns DGs has to control the produced electric power per hourly period in order to maximize the profit. If there is no regulation for carbon emission(CE), the generators which get higher production than generation cost will hold a prominent position in a competitive price. However, considering the international environment regulation, CE newly will be an important element to decide the marginal cost of generators as well as the classified fuel unit cost and unit's efficiency. This paper will introduce the optimal operation of CES's DG connected to the distribution network considering CE. The purpose of optimization is to maximize the profit of CES and Particle Swarm Optimization (PSO) will be used to solve this problem. The optimal operation of DG represented in this paper is to be resource to CES and system operator for determining the decision making criteria.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.1
• /
• pp.69-74
• /
• 2005

In this paper, we suggested user assistant soft computing method for 3D effect optimization. In order to maximize 3D effect of image, intervals among cameras have to be set up properly according to distance between cameras and an object. Two data such as interval and distance was obtained to use in neural network as the data for learning. However, if the data for learning was obtained by only human's subjective views, it could be that the obtained data was not optimal for learning because the data had an accidental ewer To obtain optimal data lot learning, we added candidature data to obtained data through data analysis, and then selected the most proper data between the candidature data and the obtained data for learning in neural network. Usually, 3D effect of image was affected by both distance from an object to cameras and an object size. Therefore, we suggested fuzzy inference model which was able to represent two factors like distance and size. Candidature data was added by fuzzy model. In the simulation result, we verified that the mote the obtained data was affected by human's subjective views, the more effective the suggested system was.