An automated industrial conveyor belt system using image processing and hierarchical clustering for classifying marble slabs

Although there are many industrial machines used in marble industry, classification of marble slabs in terms of quality is generally performed by human experts. Due to economic losses of this rather subjective process, automatic and computerized methods are needed in order to obtain reproducible and objective results in classification. With the aim of remedying this insufficiency in marble industry, a new electro-mechanical system, which automatically classifies marble slabs while they are on a conveyor belt and groups them with the help of a control mechanism, is proposed. The developed system is composed of two parts: the software part acquires digital images of marble slabs, extracts several features using these images, and finally performs the classification using clustering methods. The hardware part is composed of a conveyor belt, a serial port communication system, pneumatic pistons, a programmable logic controller (PLC), and its control circuits, all employed together for grouping the marble slabs mechanically. Although similar studies exist, this paper proposes three novelties over the existing systems. Firstly, a new hierarchical clustering approach is introduced for quality classification without requiring a training set. Secondly, a new feature set based on morphological properties of marble surface images is proposed. Finally, an electro-mechanical system is designed for accomplishing the task of sorting out the classified marble slabs. In the literature, only a system with a labeling mechanism has been presented. Our system, on the other hand, comes with a complete conveyor belt acting as an element that links the production line with the proposed system. This allows the possibility of embedding the proposed system into the production line of a marble factory. It has been observed that although the performance of the developed system is not as high as neural network based systems that use training, it could still be employed in industry when there is no available training set of samples. With this advantage, it provides an increase in the quality control standards of marble slab classification, since marbles are classified with an objective and uniform-through-time criterion.     

Mapping classifiers and datasets

Given the posterior probability estimates of 14 classifiers on 38 datasets, we plot two-dimensional maps of classifiers and datasets using principal component analysis (PCA) and Isomap. The similarity between classifiers indicate correlation (or diversity) between them and can be used in deciding whether to include both in an ensemble. Similarly, datasets which are too similar need not both be used in a general comparison experiment. The results show that (i) most of the datasets (approximately two third) we used are similar to each other, (ii) multilayer perceptrons and k-nearest neighbor variants are more similar to each other than support vector machine and decision tree variants, (iii) the number of classes and the sample size has an effect on similarity.     

Correlates of the length of the relationship between main and specialist trade contractors in the construction industry

Although there is a growing literature on the factors associated with the length of interorganizational relationships, there seem to be few empirical studies related to the subject in project-based industries such as construction. In this study we looked for correlations among the length of the relationship between main and specialist trade contractors, control methods and the number of rival speciality contractors in the Turkish construction industry, drawing on the data provided by a study of 27 specialist trade contractors. Correlation analysis was used to investigate the relationship. The results demonstrate that the length of the relationship between main and speciality contractors is inversely related to the number of rival specialist trade contractors, but directly related to the flexibility of control exercised by the main contractor.     

An Application of Genetic Algorithm Search Techniques to the Future Total Exergy Input/Output Estimation

Since 1975, there has been a great deal of interest, particularly during the past decade, in the promising genetic algorithm (GA) and its application to various disciplines from medicine to cogeneration. However, the studies performed on energy-related GA modeling are relatively low in numbers. The main objective of the present study is to develop the exergy input/output estimation equations in order to estimate the future projections based on the GA notion. In this regard, the GA Future Total EXergy Input/Output Estimation Models (GAFTEXIEM/GAFTEXOEM) are used to estimate total exergy input/output demand of Turkey, which is selected as an application country, based on the economic and social indicators of gross domestic product (GDP), population, import, export and house production figures. The future prediction of Turkey's total exergy input/output values are projected between 2003 and 2023. It may be concluded that the models proposed here can be used as an alternative solution and estimation techniques to available estimation techniques. It is also expected that this study will be helpful in developing highly applicable and productive planning for energy policies.     

Modeling and prediction of Turkey’s electricity consumption using Artificial Neural Networks

Artificial Neural Networks are proposed to model and predict electricity consumption of Turkey. Multi layer perceptron with backpropagation training algorithm is used as the neural network topology. Tangent-sigmoid and pure-linear transfer functions are selected in the hidden and output layer processing elements, respectively. These input–output network models are a result of relationships that exist among electricity consumption and several other socioeconomic variables. Electricity consumption is modeled as a function of economic indicators such as population, gross national product, imports and exports. It is also modeled using export–import ratio and time input only. Performance comparison among different models is made based on absolute and percentage mean square error. Electricity consumption of Turkey is predicted until 2027 using data from 1975 to 2006 along with other economic indicators. The results show that electricity consumption can be modeled using Artificial Neural Networks, and the models can be used to predict future electricity consumption.     

Estimation of welded joint strength using genetic algorithm approach

The genetic algorithm approach is extended to the estimation of mechanical properties of the joining of brass materials. The mechanical properties of joint parts can be improved by selecting suitable parameters. The strength of the joint parts is affected by many factors, such as the gap between the parts, the torch angle, the quantity of the shielding gases, the pulse frequencies and the electrode tip angle during welding operations. Since all these factors affect the mechanical properties of the welded joint parts, the effects of these parameters need to be cautiously investigated. The present paper describes the use of the stochastic search process that is the basis of Genetic Algorithms (GA), in developing the strength value of the welded parts. Non-linear estimation models are developed using GAs. Developed models are validated with experimental data. The Genetic Algorithm Welding Strength Estimation Model (GAWSEM) is developed to estimate the mechanical properties of the welded joint for the brass materials. The effects of five welding design parameters on the strength value using the GAWSEM have been examined. The results indicated that the changes of the gap between the joint parts and the torch angle have an important effect on the welded joint strength value and the optimum quantity of the shielding gas and the pulse frequencies exist in the tensile strength of welded joints.     

Conducting copolymers of polytetrahydrofuran and their electrochromic properties

Living polytetrahydrofuran (PTHF) was terminated with sodium thiophene methonate to yield a polymer with a thiophene group at one end. Copolymerizations of PTHF with pyrrole and thiophene were achieved in water‐p‐toluene sulfonic acid and acetonitrile‐tetrabutylammonium tetrafluoroborate (TBAFB) solvent‐electrolyte couples via constant potential electrolyses. Characterizations of the samples were performed by NMR, cyclic voltammetry, FT‐IR, thermal analyses, and scanning electron microscopy. Electrical conductivities were measured by the four‐probe technique. PTHF/PTh film that was deposited on ITO‐glass in a dichloromethane‐TBAFB solvent‐electrolyte couple was found to exhibit electrochromic behavior and it electrochemically switches between blue oxidized and red reduced states. Optical analyses were carried out to investigate the electronic structure of PTHF/PTh electrochromic copolymer. © 2005 Wiley Periodicals, Inc. J Appl Polym Sci 95: 1014–1023, 2005     

The search for optimal feature set in power quality event classification

The significance of detection and classification of power quality (PQ) events that disturbs the voltage and/or current waveforms in the electrical power distribution networks is well known. Consequently, in spite of a large number of research reports in this area, the problem of PQ event classification remains to be an important engineering problem. Several feature construction, pattern recognition, analysis, and classification methods were proposed for this purpose. In spite of the extensive number of such alternatives, a research on the comparison of “how useful these features with respect to each other using specific classifiers” was omitted. In this work, a thorough analysis is carried out regarding the classification strengths of an ensemble of celebrated features. The feature items were selected from well-known tools such as spectral information, wavelet extrema across several decomposition levels, and local statistical variations of the waveform. The tests are repeated for classification of several types of real-life data acquired during line-to-ground arcing faults and voltage sags due to the induction motor starting under different load conditions. In order to avoid specificity in classifier strength determination, eight different approaches are applied, including the computationally costly “exhaustive search” together with the leave-one-out technique. To further avoid specificity of the feature for a given classifier, two classifiers (Bayes and SVM) are tested. As a result of these analyses, the more useful set among a wider set of features for each classifier is obtained. It is observed that classification accuracy improves by eliminating relatively useless feature items for both classifiers. Furthermore, the feature selection results somewhat change according to the classifier used. This observation shows that when a new analysis tool or a feature is developed and claimed to perform “better” than another, one should always indicate the matching classifier for the feature because that feature may prove comparably inefficient with other classifiers.     

Incremental construction of classifier and discriminant ensembles

We discuss approaches to incrementally construct an ensemble. The first constructs an ensemble of classifiers choosing a subset from a larger set, and the second constructs an ensemble of discriminants, where a classifier is used for some classes only. We investigate criteria including accuracy, significant improvement, diversity, correlation, and the role of search direction. For discriminant ensembles, we test subset selection and trees. Fusion is by voting or by a linear model. Using 14 classifiers on 38 data sets, incremental search finds small, accurate ensembles in polynomial time. The discriminant ensemble uses a subset of discriminants and is simpler, interpretable, and accurate. We see that an incremental ensemble has higher accuracy than bagging and random subspace method; and it has a comparable accuracy to AdaBoost, but fewer classifiers.