Current Issue : July - September Volume : 2017 Issue Number : 3 Articles : 5 Articles
Container traffic forecasting is important for the operations and the design steps of a seaport facility. In this study, performances\nof the novel soft computing models were compared for the container traffic forecasting of principal Turkish seaports (Istanbul,\nIzmir, and Mersin seaports) with excessive container traffic. Four forecasting models were implemented based on Artificial\nNeuralNetwork with Artificial Bee Colony and Levenberg-Marquardt Algorithms (ANN-ABC and ANN-LM),MultipleNonlinear\nRegression with Genetic Algorithm (MNR-GA), and Least Square Support Vector Machine (LSSVM). Forecasts were carried out\nby using the past records of the gross domestic product, exports, and population of the Turkey as indicators of socioeconomic\nand demographic status. Performances of the forecasting models were evaluated with several performance metrics. Considering\nthe testing period, the LSSVM, ANN-ABC, and ANN-LM models performed better than theMNR-GA model considering overall\nfitting and prediction performances of the extreme values in the testing data. The LSSVM model was found to be more reliable\ncompared to the ANN models. Forecasting part of the study suggested that container traffic of the seaports will be increased up to\n60%, 67%, and 95% at the 2023 for the Izmir, Mersin, and Istanbul seaports considering official growth scenarios of Turkey....
Support vector machine (SVM) is one of the top picks in pattern recognition and classification related tasks. It has been used\nsuccessfully to classify linearly separable and nonlinearly separable data with high accuracy. However, in terms of classification\nspeed, SVMs are outperformed by many machine learning algorithms, especially, when massive datasets are involved. SVM\nclassification speed scales linearly with number of support vectors, and support vectors increase with increase in dataset size.\nHence, SVM classification speed can be enormously reduced if it is trained on a reduced dataset. Instance selection techniques\nare one of themost effective techniques suitable for minimizing SVM training time. In this study, two instance selection techniques\nsuitable for identifying relevant training instances are proposed. The techniques are evaluated on a dataset containing 4000 emails\nand results obtained compared to other existing techniques. Result reveals excellent improvement in SVM classification speed....
Recently, the demand for wireless devices that support multiband frequency has increased. The integration of such technology in\nmobile communication system has led to a great demand in developing small size antenna with multiband operation, which is\nable to operate in the required system. In this paper, a novel type planar inverted F antenna (PIFA) with gridded ground plane\nstructure and overlapping cells is presented. By controlling the overlapping size, we improve the characteristics of the proposed\nantenna. This antenna is developed to achieve multiband operation with small size and good performance. The particle swarm\noptimization (PSO) is employed to a PIFA antenna to get rid of the limitations of single band operation by searching the optimal\nlocalization and length of linear slots on the ground plane to give triband operation. This PIFA antenna can be integrated to operate\nfor several mobile applications as Bluetooth/WLAN,WIMAX, and 4G (UMTS2100, LTE). The optimized antenna is simulated by\nboth Ansoft HFSS and computer simulation technology microwave studio (CSTMWS) in terms of ...
Flexible robot system is in general taken into real consideration as most important\nprocess in a number of academic and industrial environments. Due to the fact that the\naforementioned system is so applicable in real domains, the novel ideas with respect\nto state-of-the-art in outperforming its performance are always valuable. With this\npurpose, a number of the soft computing techniques can be preferred with reference\nto the traditional ones to predict and optimize the overall performance of the abovecaptioned\nprocess. The approach proposed here is in fact organized in line with the\nintegration of the fuzzy-based approach in association with the neural networks, in\norder to enable the process under control to be capable of learning and adapting to\nbe matched, in a number of real environments. It can be shown that the outcomes\ntolerate the imprecise circumstances, as one of advantages regarding the fuzzy-based\napproach. In the present investigation, a new hybrid approach is proposed to deal\nwith the arm of flexible robot system through the neural networks, the fuzzy-based\napproach and also the particle swarm optimization. It should be noted that the objective\nof the proposed research is to control the claw of robot system including twodegree-\nof-freedom movable arms. The results indicate that the mean-square error and\nthe root-mean-square error are accurately outperformed with reference to the traditional\nones, tangibly....
Modeling response of structures under seismic loads is an important factor in Civil Engineering as it crucially affects the design\nand management of structures, especially for the high-risk areas. In this study, novel applications of advanced soft computing\ntechniques are utilized for predicting the behavior of centrically braced frame (CBF) buildings with lead-rubber bearing (LRB)\nisolation system under ground motion effects. These techniques include least square support vector machine (LSSVM), wavelet\nneural networks (WNN), and adaptive neurofuzzy inference system (ANFIS) along with wavelet denoising. The simulation of a\n2D frame model and eight ground motions are considered in this study to evaluate the prediction models. The comparison results\nindicate that the least square support vector machine is superior to other techniques in estimating the behavior of smart structures....
Loading....