Full Text Available
Access Full Text at Repository
Search Results - (teaching OR training) algorithm
- Go to Previous Page
- Showing 381 - 382 results of 382
-
Control performance assessment for a high pressure leaching process by means of fault database creation and simulation by Miskin, Jason John
Published 2016Get full text
ThesisFull Text AvailableAccess Full Text at Repository
Search Tools:
Refine Results
Page will reload when a filter is selected or excluded.- General 4 results 4
- Computer Science 3 results 3
- Artificial Neural Networks (ANNs) area prormsmg alternative to conventional tools in modeling and prediction of complex and non-linear parameters. However, the selection of appropriate network parameters for optimum performance pose application challenges. In this study, the modeling and predictive performances of six backpropagation learning algorithms: Levenberg-Marquardt (LM), BFGS Quasi-Newton (BFG), Resilient Backpropagation (RP), Fletcher-Powell Conjugate Gradient (CGF), Variable Learning Rate Backpropagation (GDX) and Bayesian Reglarization (BR) in solar radiation forecast were investigated. Multilayer perceptron (MPL) neural network with five, ten and one neuron(s) in the input, hidden and output layers, respectively was designed with MATLAB® neural network toolkit and trained with the six learning algorithms using the daily global solar radiation data of Ibadan (Lat. 7.4° N; Long. 3.90 E; Alt. 227.2m), Nigeria. The network performance was ranked based on the number of iterations required for convergence, and coefficient of correlation (r-value), mean square error (MSE) and mean absolute percentage error (MAPE) between the actual and predicted values of the training and testing datasets. Results showed that the LM and BR learning algorithms are the two best algorithms to be considered for use in modeling and forecasting of solar radiation data. 2 results 2
- "Face recognition is an attractive field in enhancing both the security and the image retrieval activities in the multimedia world. Its natural basis in verification or identification purposes is a major factor of its wide acceptance in this evolving world of information technology. In this paper, experiments based on black African faces using Principal Component Analysis (OPCA) and Fisher Discriminant Analysis (OFDA) techniques were carried out. The design of the face recognition system was separated into three major sections - image acquisition and standardisation, dimensionality reduction, training and testing for recognition. Under static mode, experiments were performed on single scaled images without rotation, OPCA and OFDA both give recognition accuracies of between 89% and 97%;and) 88% and 98% respectively. These have been achieved at different levels of cropping. Despite the constraint created by the resources available, different results got showed that standard face recognition system could be developed using both algorithms. " 1 results 1
- Artificial Neural Network 1 results 1
- Artificial Neural Networks 1 results 1
- Automation and Robotics 1 results 1
- Built-up 1 results 1
- Cathodic Protection 1 results 1
- Class level 1 results 1
- Conflict 1 results 1
- Conflict is part of human social interaction, which may occur from a mere misunderstanding among groups of settlers. In recent times, advanced Machine Learning (ML) techniques have been applied to conflict prediction. Strategic frameworks for improving ML settings in conflict research are emerging and are being tested with new algorithm-based approaches. These developments have given rise to the need to develop a Deep Neural Network model that predicts conflicts. Hence, in this study, two Artificial Neural Network models were developed, the dataset which was extracted from https://www.data.worlduploaded by the Armed Conflict Location and Event Data Project (ACLED), in four separate CSV files (January 2015 to December 2018). The dataset for the year 2015 has 2697 instances and 28 features, for 2016 was 2233 with the same feature, for 2017 has 2669 instances with the same features, and 2018 has 1651 instances. After the development of the models: the baseline Artificial Neural Network achieved an accuracy of 95% and a loss of 5% on the training data and an accuracy of 90% and 10% loss on the test set. The Deep Neural Network Model achieved 98% accuracy and 2% loss on the training set, with 89% accuracy and 11% loss on the test set. It was concluded that to further improve the prediction of conflict, there is a need to address the issue of the dataset, in developing a better and more robust model. 1 results 1
- Cultivation 1 results 1
- Data over-collection 1 results 1
- Deep Neural Network 1 results 1
- Determination of friction factor is an essential prerequisite in pipe flow calculations. The Darcy-Weisbach equation and other analytical models have been developed for the estimation of friction factor. But these developed models are complex and involve iterative schemes which are time consuming. In this study, a suitable model based on artificial neural network (ANN) technique was proposed for estimation of factor to friction in pipe flow. Multilayered perceptron (MLP) neural networks with feed-forward back-propagation training algorithms were designed using the neural network toolbox for MATLAB®. The input parameters of the networks were pipe relative roughness and Reynold’s number of the flow, while the friction factor was used as the output parameter. The performance of the networks was determined based the mean on absolute percentage error (MAPE), mean squared error (MSE), sum of squared errors (SSE), and correlation coefficient (R-value). Results have shown that the network with 2-20-31-1 configuration trained with the Levenberg-Marquardt 'trainlm' function had the best performance with R-value (0.999), MAPE (0.68%), MSE (5.335xI0-7), and SSE (3.414x10-4). A graphic user interface (GUI) with plotting capabilities was developed for easy application of the model. The proposed model is suitable for modeling and prediction of friction to factor in pipe flow for on-line computer-based computations. 1 results 1
- Entropy generation rate 1 results 1
- Face recognition, 1 results 1
- Firefly algorithm 1 results 1
- Forest 1 results 1
- In this study, an attempt was made using machine learning algorithm with the user data store in the mobile cloud framework to solve the problem of data over-collection. This was achieved by designing a model using the security risk level of the applications and the corresponding class level of the users on the smartphone that will help in preventing smartphone apps from accessing and collecting users’ private data while still within the permission scope. Users can store information in the cloud environment where the huge numbers of users are involved. We develop a mobile agent simulator to generate data, and determine the security risk level of the apps on users’ data with the class level of the data. The permission model was designed to determine whether the app is granted permission to access user’s data or not. The data was trained with the use of Neural Network. The evaluation metrics used were accuracy and comparison. For accuracy, the algorithm was compared with the existing algorithm. The data analysis showed that there was restriction for apps accessing the users’ data. The model if deployed on the smartphone will prevent apps from over collect users’ data even while still within the permission scope. This study proved that neural network with mobile cloud computing can be applied to prevent data over-collection in smart devices. 1 results 1
- In vitro gas production of four different browse plants (Azadirachta indica, Terminalia catappa, Mangifera indica and Vernonia amygdalina) was investigated under different extractions. The relationship between the forage composition parameters (dry matter, organic matter, crude protein, acid detergent fibre, neutral detergent fibre and acid detergent lignin), process parameters (extraction mode and incubation time), and volume of gas production were modelled with artificial neural network (ANN). The ANN model consisted of simple, multi-layered, back-propagation networks with eight input neurons consisting of the composition and process parameters and one output neuron for the gas volume. The networks were trained with different algorithms and varying number of layer and neuron in the hidden layer to determine the optimum network architecture. The network with single hidden layer having 45 ‘tangent sigmoid’ neurons trained with Livenberg-Marquard algorithm combined with ‘early stopping’ technique was found to be the optimum network for the model with R-value: mean = 0.9504; max. = 0.9618; min. = 0.9343; and std. = 0.0059. The influence of each chemical composition and processing parameters on gas production was simulated. The developed ANN model offers a more cost and time efficient strategy in feed evaluation for ruminant animals. 1 results 1
- Model 1 results 1
- Monioring of surface roughness is an essential component in planning of machining processes as it affects the surface quality and dimensional accuracy of machined components. In this study, the development and application of a machine vision system suitable for on-line measurement of surface roughness of machined components using artificial neural network (ANN) is described. The system, which was based on digital image processing of the machined surface, consisted of a CCD camera, PC, Microsoft Windows Video Maker, frame grabber, Video to USB cable, digital image processing software (Photoshop, and MATLAB digital image processing toolbox), and two light sources. The images of the machined surface were captured; analyzed and optical roughness features were estimated using the 2-D fast Fourier transform (FFT) algorithm. A multilayer perceptron (MLP) neural network was used to model and predict the optical roughness values. Tool wear index and five features extracted from the surface images were used as input dataset in training and testing the ANN model. The results showed that the ANN predicted optical roughness values were found to be in close agreement with the calculated values (R2-value = 0.9529). Thus, indicating that the proposed machine vision system and ANN model are adequate for online monitoring and control of surface roughness in machining environment. 1 results 1
- Multi-Class Target Label 1 results 1
- Prediction 1 results 1
- Preheat train 1 results 1
- Privacy 1 results 1
- Private data 1 results 1
- Pumping power 1 results 1
- see all…
- SUNScholar — Stellenbosch University Repository 157 results 157
- UCTD — University of Cape Town Open Access Repository 101 results 101
- UPSpace — University of Pretoria Institutional Repository 83 results 83
- AUC Knowledge Fountain — bepress 20 results 20
- KNUSTSpace — Kwame Nkrumah University of Science & Technology (Ghana) 2 results 2