Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 232 for “"Nearest neighbours"”.
-
Algorithms and techniques for efficient and effective nearest neighbours classification
Although the k-NN classifier is considered to be an effective classification algorithm, it has some major weaknesses that may render its use inappropriate for some application domains and / or datasets. The first one is the high computational cost involved (all distances between each unclassified …
-
k-Nearest Neighbours, a Novel Machine Learning Method for Retail Promotional Forecasting
Forecasting accuracy remains a persistent challenge in competitive markets with widespread use of promotions. Machine learning algorithms have emerged as an alternative to traditional (statistical) ones to improve forecast accuracy; however, they frequently present an obscure prediction logic when …
-
Catalogue Retail Forecasting – An Empirical Evaluation of Linear Regression and K-Nearest Neighbours sensitivity to preprocessing
… forecasting approaches—linear regression and k-nearest neighbours (k-NN)—with a particular focus on their sensitivity to different data preprocessing techniques. Using a real-world dataset from a multinational cosmetics company, comprising 1,765 product-level observations across three catalogue …
-
Comparative Classification of Prostate Cancer Data using the Support Vector Machine, Random Forest, Dualks and k-Nearest Neighbours
… (SVM), Random Forest (RF), DualKS and the k-Nearest Neighbors (kNN) that are based on different statistical learning theories. The dataset used is a microarray gene expression of 596 male patients with prostate cancer. After treatment, the patients were classified into one group of phenotype …
-
MOLECULAR DYNAMICS STUDY OF PRESSURE-INDUCED STRUCTURAL PHASE TRANSISTION OF IONIC CRYSTALS
… for this kind of transformation. Two first nearest neighbours and the other two nearest neighbours, of a Mg2+ ion, form a parallelogram with the cation at the centre and anions at the corners. The next nearest neighbours will move towards the first nearest neighbours along the longer sides …
-
Numerical Solutions of Laplace's Equation for Various Physical Situations
… of nodes. On the regular lattices the number of nearest neighbours was a constant at all lattice sites. For a random distribution of nodes there was variation in the number of nearest neighbours at different nodes. Some percentage of the nodes were isolated from the rest of the distribution, …
-
Network Kriging - Predicting the Attributes of Nodes in a Network
… and compares results to those using the K-Nearest Neighbours algorithm. We found that for important roles, such as Emir (Leadership), Network Kriging performs better than K-Nearest Neighbours.
-
Statistical avalanche forecating using meteorological data from Bear Pass, British Columbia, Canada
… set is then used in a Mahalanobis-metric nearest neighbours model to determine the observations in the historical database that most closely represent conditions of the forecast period. The information about these neighbours can be used by the forecaster to aid in making an avalanche …
-
Spin-Spin Correlations in the CuAlCr₄S₈ Breathing Pyrochlore
… , the Heisenberg model that goes up to third nearest neighbours (up-to-3rd-NN), and Heisenberg model that goes up to fifth-nearest neighbours (up-to-5th-NN). Both models have exchange couplings obtained from our collaborators using density-functional theory (DFT). Both Heisenberg models for …
-
Crystallisation kinetics and optical properties of Ge₂Sb₂Te₅
… these parameters from the co-ordination of nearest neighbours in the structure. The model was found to work for a simplified silicon Hamiltonian and it is described how the model could be extended to include more realistic systems. Ep, Δ and Γ were determined before and after crystallisation …
-
Investigating fuzzy methods for multilingual speaker identification
… adopted four classifiers: Fuzzy C-Means, Fuzzy k-Nearest Neighbours, k-Nearest Neighbours, and Support Vector Machines. Initial tests indicated the systems have certain robustness on multiple languages. Where results with more languages decreases our accuracy; however our investigation suggests …
-
A Comparative Study of Machine Learning Algorithms
… data. The algorithms that were tested are k-nearest neighbours, decision trees, random forests, gradient tree boosting, logistic regression, naive bayes, support vector machines, and artificial neural net- works. These algorithms were compared in terms of accuracy, training time, and …
-
N.M.R. study on single crystals of lead and thallium
… that the contribution from the second-nearest neighbours is very small, and values are obtained for the pseudoexchange and pseudodipolar coefficients for the first-nearest neighbours, which are in good agreement with the theoretical values of Tterlikkis, Mahanti, and Das. A small …
-
Exploring social dynamics in cattle using a social networks approach
… and the focal cattle preferred related nearest-neighbours over unrelated nearest-neighbours (p<0.00). The social network of a related group of cattle remained stable over time as the weaning period approached (p=0.007), and there was no difference between the cow-calf associations before …
-
Implementation of a Cellular Computing Memory Array
… so that each cell can communicate with the four nearest neighbours. In addition to the ordinary communication between cells to perform operations on data in adjacent cells, data can be transferred in the memory plane on a mass basis.</p>
-
Machine Learning Methods for Autonomous Object Recognition and Restoration in Images
… are often used for image recognition such as K-nearest neighbours, however, K-nearest neighbours are vulnerable to noise and high dimensional features. This thesis proposes a non-parametric classifier based on Bayesian compressive sensing; the developed classifier is robust and it does not need …
-
Space-Time Block Codes for Multi-Input Single-Output Channels and Simple Maximum Likelihood Detection
… due to the increase of the number of the nearest neighbours per symbol.</p> <p>To correct such a deficiency of the code, in this thesis, we propose to include the number of nearest neighbors in the design criterion. We show that for the current optimal rotated quasi-orthogonal code, the …
-
Spatial price competition in german retail gasoline markets /
… thus examine the nature of spatial competition: nearest neighbours, border neighbours and Euclidean distance neighbours. The results strongly point to local competition as local models describe the reaction functions most accurately. Furthermore, temporal reaction functions (containing lagged …
-
An application of cell-cluster theory to a rare gas crystal /|n[by] K. Westera. - 260 St. Catharines [Ont.] : Dept. of Physics, Brock University,
… a Lennard-Jones (6-12) pair interaction between nearest neighbours only for the f.c.c. lattice. The thermodynamic properties predicted by this model agree well with experimental results for solid Xenon.
Page 1 of 12