Current Issue : January - March Volume : 2015 Issue Number : 1 Articles : 7 Articles
Permeation grouting is a commonly used approach for soil improvement in construction engineering.Thus, predicting the results of\ngrouting activities is a crucial task that needs to be carried out in the planning phase of any grouting project. In this research, a novel\nartificial intelligence approachââ?¬â?auto tuning support vector machineââ?¬â?is proposed to forecast the result of grouting activities that\nemploy micro fine cement grouts. In the new model, the support vector machine (SVM) algorithm is utilized to classify grouting\nactivities into two classes: success and failure. Meanwhile, the differential evolution (DE) optimization algorithm is employed to\nidentify the optimal tuning parameters of the SVM algorithm, namely, the penalty parameter and the kernel function parameter.\nThe integration of the SVM and DE algorithms allows the newly established method to operate automatically without human prior\nknowledge or tedious processes for parameter setting. An experiment using a set of in situ data samples demonstrates that the newly\nestablished method can produce an outstanding prediction performance....
A study has been made to optimise the influential parameters of surface lapping process. Lapping time, lapping speed, downward\npressure, and charging pressure were chosen from the preliminary studies as parameters to determine process performances in\nterms of material removal, lap width, and clamp force.The desirability functions of the-nominal-the-best were used to compromise\nmultiple responses into the overall desirability function level or D response.The conventional modified simplex or Nelder-Mead\nsimplex method and the interactive desirability function are performed to optimise online the parameter levels in order to maximise\nthe D response. In order to determine the lapping process parameters effectively, this research then applies two powerful artificial\nintelligence optimisation mechanisms from harmony search and firefly algorithms. The recommended condition of (lapping time,\nlapping speed, downward pressure, and charging pressure) at (33, 35, 6.0, and 5.0) has been verified by performing confirmation\nexperiments. It showed that the D response level increased to 0.96. When compared with the current operating condition, there\nis a decrease of the material removal and lap width with the improved process performance indices of 2.01 and 1.14, respectively.\nSimilarly, there is an increase of the clamp force with the improved process performance index of 1.58....
Water resources and urban flood management require hydrologic and hydraulic modeling. However, incomplete precipitation data\nis often the issue during hydrological modeling exercise. In this study, gene expression programming (GEP) was utilised to correlate\nmonthly precipitation data from a principal station with its neighbouring station located in Alor Setar, Kedah, Malaysia. GEP is\nan extension to genetic programming (GP), and can provide simple and efficient solution. The study illustrates the applications of\nGEP to determine the most suitable rainfall station to replace the principal rainfall station (station 6103047). This is to ensure that\na reliable rainfall station can be made if the principal station malfunctioned. These were done by comparing principal station data\nwith each individual neighbouring station. Result of the analysis reveals that the station 38 is the most compatible to the principal\nstation where the value of R2 is 0.886....
Steam distillation as one of the important mechanisms has a great role in oil recovery in thermal methods and so it is important to\nsimulate this process experimentally and theoretically. In this work, the simulation of steamdistillation is performed on sixteen sets\nof crude oil data found in the literature. Artificial intelligence (AI) tools such as artificial neural network (ANN) and also adaptive\nneurofuzzy interference system (ANFIS) are used in this study as effective methods to simulate the distillate recoveries of these\nsets of data. Thirteen sets of data were used to train the models and three sets were used to test the models. The developed models\nare highly compatible with respect to input oil properties and can predict the distillate yield with minimum entry. For showing\nthe performance of the proposed models, simulation of steam distillation is also done using modified Peng-Robinson equation of\nstate. Comparison between the calculated distillates by ANFIS and neural network models and also equation of state-based method\nindicates that the errors of the ANFIS model for training data and test data sets are lower than those of other methods...
The aim of this paper was to analyse the different faults occurring in three phase induction motor such as inter-turn short circuit and bearing faults. This paper proposes Parks-Hilbert transformation in combination to detect inter-turn short circuit as well as bearing faults. The net efficiency of this method for 3ø induction motor is more as compared to the previous methods. This method effectively distinguishes inter-turn short circuit condition in stator as well as inner race and outer race defects in the bearing. ANN is used to classify the listed faults. It produces excellent capabilities in fault classification process....
School bullying is a serious problem among teenagers, causing depression, dropping out of school, or even suicide. It is thus\nimportant to develop antibullying methods. This paper proposes a physical bullying detection method based on activity recognition.\nThe architecture of the physical violence detection system is described, and a Fuzzy Multi thres hold classifier is developed to\ndetect physical bullying behaviour, including pushing, hitting, and shaking. Importantly, the application has the capability of\ndistinguishing these types of behaviour from such everyday activities as running, walking, falling, or doing push-ups. To accomplish\nthis, the method uses acceleration and gyro signals. Experimental data were gathered by role playing school bullying scenarios and\nby doing daily-life activities. The simulations achieved an average classification accuracy of 92%, which is a promising result for\nsmartphone-based detection of physical bullying....
Considering the influence of particle shape and the rheological properties of fluid, two artificial intelligence methods (Artificial Neural\nNetwork and Support Vector Machine) were used to predict the wall factor which is widely introduced to deduce the net hydrodynamic\ndrag force of confining boundaries on settling particles. 513 data points were culled from the experimental data of previous\nstudies,which were divided into training set and test set. Particles with various shapes were divided into three kinds: sphere, cylinder,\nand rectangular prism; feature parameters of each kind of particle were extracted; prediction models of sphere and cylinder using\nartificial neural network were established. Due to the little number of rectangular prism sample, support vector machine was used\nto predict the wall factor, which is more suitable for addressing the problem of small samples.The characteristic dimension was presented\nto describe the shape and size of the diverse particles and a comprehensive prediction model of particles with arbitrary shapes\nwas established to cover all types of conditions. Comparisons were conducted between the predicted values and the experimental\nresults....
Loading....