The research aimed to establish tyre-road noise models by using a Data Mining approach that allowed to build a predictive model and assess the importance of the tested input variables. The data modelling took into account three learning algorithms and three metrics to define the best predictive model. The variables tested included basic properties of pavement surfaces, macrotexture, megatexture, and unevenness and, for the first time, damping. Also, the importance of those variables was measured by using a sensitivity analysis procedure. Two types of models were set: one with basic variables and another with complex variables, such as megatexture and damping, all as a function of vehicles speed. More detailed models were additionally set by the speed level. As a result, several models with very good tyre-road noise predictive capacity were achieved. The most relevant variables were Speed, Temperature, Aggregate size, Mean Profile Depth, and Damping, which had the highest importance, even though influenced by speed. Megatexture and IRI had the lowest importance. The applicability of the models developed in this work is relevant for trucks tyre-noise prediction, represented by the AVON V 4 test tyre, at the early stage of road pavements use. Therefore, the obtained models are highly useful for the design of pavements and for noise prediction by road authorities and contractors.

Power big data contains a lot of information related to equipment fault. The analysis and processing of power big data can realize fault diagnosis. This study mainly analyzed the application of association rules in power big data processing. Firstly, the association rules and the Apriori algorithm were introduced. Then, aiming at the shortage of the Apriori algorithm, an IM-Apriori algorithm was designed, and a simulation experiment was carried out. The results showed that the IM-Apriori algorithm had a significant advantage over the Apriori algorithm in the running time. When the number of transactions was 100 000, the running of the IM-Apriori algorithm was 38.42% faster than that of the Apriori algorithm. The IM-Apriori algorithm was little affected by the value of supportmin. Compared with the Extreme Learning Machine (ELM), the IM-Apriori algorithm had better accuracy. The experimental results show the effectiveness of the IM-Apriori algorithm in fault diagnosis, and it can be further promoted and applied in power grid equipment.

A common observation of everyday life reveals the growing importance of data science methods, which are increasingly more and more important part of the mainstream of knowledge generation process. Digital technologies and their potential for data collection and data processing have initiated the birth of the fourth paradigm of science, based on Big Data. Key to these transformations is datafication and data mining that allow the discovery of knowledge from contaminated data. The main purpose of the considerations presented here is to describe the phenomena that make up these processes and indicate their possible epistemological consequences. It has been assumed that increasing datafication tendencies may result in the formation of a data- centric perception of all aspects of reality, making data and the methods of their processing a kind of higher instance shaping human thinking about the world. This research is theoretical in nature. Such issues as the process of datafication and data science have been analyzed with a focus on the areas that raise doubts about the validity of this form of cognition.

Approximately 30 million tons of tailings are being stored each year at the KGHMs Zelazny Most Tailings Storage Facility (TSF). Covering an area of almost 1.6 thousand hectares, and being surrounded by dams of a total length of 14 km and height of over 70 m in some areas, makes it the largest reservoir of post-flotation tailings in Europe and the second-largest in the world. With approximately 2900 monitoring instruments and measuring points surrounding the facility, Zelazny Most is a subject of round-the-clock monitoring, which for safety and economic reasons is crucial not only for the immediate surroundings of the facility but for the entire region. The monitoring network can be divided into four main groups: (a) geotechnical, consisting mostly of inclinometers and VW pore pressure transducers, (b) hydrological with piezometers and water level gauges, (c) geodetic survey with laser and GPS measurements, as well as surface and in-depth benchmarks, (d) seismic network, consisting primarily of accelerometer stations. Separately a variety of different chemical analyses are conducted, in parallel with spigotting processes and relief wells monitorin. This leads to a large amount of data that is difficult to analyze with conventional methods. In this article, we discuss a machine learning-driven approach which should improve the quality of the monitoring and maintenance of such facilities. Overview of the main algorithms developed to determine the stability parameters or classification of tailings are presented. The concepts described in this article will be further developed in the IlluMINEation project (H2020).

Classification techniques have been widely used in different remote sensing applications and correct classification of mixed pixels is a tedious task. Traditional approaches adopt various statistical parameters, however does not facilitate effective visualisation. Data mining tools are proving very helpful in the classification process. We propose a visual mining based frame work for accuracy assessment of classification techniques using open source tools such as WEKA and PREFUSE. These tools in integration can provide an efficient approach for getting information about improvements in the classification accuracy and helps in refining training data set. We have illustrated framework for investigating the effects of various resampling methods on classification accuracy and found that bilinear (BL) is best suited for preserving radiometric characteristics. We have also investigated the optimal number of folds required for effective analysis of LISS-IV images.

The aim of the study was to evaluate the possibility of applying different methods of data mining to model the inflow of sewage into the municipal sewage treatment plant. Prediction models were elaborated using methods of support vector machines (SVM), random forests (RF), k-nearest neighbour (k-NN) and of Kernel regression (K). Data consisted of the time series of daily rainfalls, water level measurements in the clarified sewage recipient and the wastewater inflow into the Rzeszow city plant. Results indicate that the best models with one input delayed by 1 day were obtained using the k-NN method while the worst with the K method. For the models with two input variables and one explanatory one the smallest errors were obtained if model inputs were sewage inflow and rainfall data delayed by 1 day and the best fit is provided using RF method while the worst with the K method. In the case of models with three inputs and two explanatory variables, the best results were reported for the SVM and the worst for the K method. In the most of the modelling runs the smallest prediction errors are obtained using the SVM method and the biggest ones with the K method. In the case of the simplest model with one input delayed by 1 day the best results are provided using k-NN method and by the models with two inputs in two modelling runs the RF method appeared as the best.

This article presents the methodology for exploratory analysis of data from microstructural studies of compacted graphite iron to gain

knowledge about the factors favouring the formation of ausferrite. The studies led to the development of rules to evaluate the content of

ausferrite based on the chemical composition. Data mining methods have been used to generate regression models such as boosted trees,

random forest, and piecewise regression models. The development of a stepwise regression modelling process on the iteratively limited

sets enabled, on the one hand, the improvement of forecasting precision and, on the other, acquisition of deeper knowledge about the

ausferrite formation. Repeated examination of the significance of the effect of various factors in different regression models has allowed

identification of the most important variables influencing the ausferrite content in different ranges of the parameters variability.

The paper presents an analysis of SPC (Statistical Process Control) procedures usability in foundry engineering. The authors pay particular attention to the processes complexity and necessity of correct preparation of data acquisition procedures. Integration of SPC systems with existing IT solutions in area of aiding and assistance during the manufacturing process is important. For each particular foundry, methodology of selective SPC application needs to prepare for supervision and control of stability of manufacturing conditions, regarding specificity of data in particular “branches” of foundry production (Sands, Pouring, Metallurgy, Quality).

The paper analyses the distorted data of an electronic nose in recognizing the gasoline bio-based additives. Different tools of data mining, such as the methods of data clustering, principal component analysis, wavelet transformation, support vector machine and random forest of decision trees are applied. A special stress is put on the robustness of signal processing systems to the noise distorting the registered sensor signals. A special denoising procedure based on application of discrete wavelet transformation has been proposed. This procedure enables to reduce the error rate of recognition in a significant way. The numerical results of experiments devoted to the recognition of different blends of gasoline have shown the superiority of support vector machine in a noisy environment of measurement.

Decision-making processes, including the ones related to ill-structured problems, are of considerable significance in the area of construction projects. Computer-aided inference under such conditions requires the employment of specific methods and tools (non-algorithmic ones), the best recognized and successfully used in practice represented by expert systems. The knowledge indispensable for such systems to perform inference is most frequently acquired directly from experts (through a dialogue: a domain expert - a knowledge engineer) and from various source documents. Little is known, however, about the possibility of automating knowledge acquisition in this area and as a result, in practice it is scarcely ever used. lt has to be noted that in numerous areas of management more and more attention is paid to the issue of acquiring knowledge from available data. What is known and successfully employed in the practice of aiding the decision-making is the different methods and tools. The paper attempts to select methods for knowledge discovery in data and presents possible ways of representing the acquired knowledge as well as sample tools (including programming ones), allowing for the use of this knowledge in the area under consideration.

The application of the 5S methodology to warehouse management represents an important

step for all manufacturing companies, especially for managing products that consist of

a large number of components. Moreover, from a lean production point of view, inventory

management requires a reduction in inventory wastes in terms of costs, quantities and time

of non-added value tasks. Moving towards an Industry 4.0 environment, a deeper understanding

of data provided by production processes and supply chain operations is needed:

the application of Data Mining techniques can provide valuable support in such an objective.

In this context, a procedure aiming at reducing the number and the duration of picking

processes in an Automated Storage and Retrieval System. Association Rule Mining is applied

for reducing time wasted during the storage and retrieval activities of components

and finished products, pursuing the space and material management philosophy expressed

by the 5S methodology. The first step of the proposed procedure requires the evaluation

of the picking frequency for each component. Historical data are analyzed to extract the

association rules describing the sets of components frequently belonging to the same order.

Then, the allocation of items in the Automated Storage and Retrieval System is performed

considering (a) the association degree, i.e., the confidence of the rule, between the components

under analysis and (b) the spatial availability. The main contribution of this work is

the development of a versatile procedure for eliminating time waste in the picking processes

from an AS/RS. A real-life example of a manufacturing company is also presented to explain

the proposed procedure, as well as further research development worthy of investigation.

The paper presents the key-finding algorithm based on the music signature concept. The proposed music signature is a set of 2-D vectors which can be treated as a compressed form of representation of a musical content in the 2-D space. Each vector represents different pitch class. Its direction is determined by the position of the corresponding major key in the circle of fifths. The length of each vector reflects the multiplicity (i.e. number of occurrences) of the pitch class in a musical piece or its fragment. The paper presents the theoretical background, examples explaining the essence of the idea and the results of the conducted tests which confirm the effectiveness of the proposed algorithm for finding the key based on the analysis of the music signature. The developed method was compared with the key-finding algorithms using Krumhansl-Kessler, Temperley and Albrecht-Shanahan profiles. The experiments were performed on the set of Bach preludes, Bach fugues and Chopin preludes.

Wire electrical discharge machining (WEDM) is a non-conventional material-removal process where a continuously travelling electrically conductive wire is used as an electrode to erode material from a workpiece. To explore its fullest machining potential, there is always a requirement to examine the effects of its varied input parameters on the responses and resolve the best parametric setting. This paper proposes parametric analysis of a WEDM process by applying non-parametric decision tree algorithm, based on a past experimental dataset. Two decision tree-based classification methods, i.e. classification and regression tree (CART) and Chi-squared automatic interaction detection (CHAID) are considered here as the data mining tools to examine the influences of six WEDM process parameters on four responses, and identify the most preferred parametric mix to help in achieving the desired response values. The developed decision trees recognize pulse-on time as the most indicative WEDM process parameter impacting almost all the responses. Furthermore, a comparative analysis on the classification performance of CART and CHAID algorithms demonstrates the superiority of CART with higher overall classification accuracy and lower prediction risk.

The present paper describes a methodological framework developed to select a multi-label dataset transformation method in the context of supervised machine learning techniques. We explore the rectangular 2D strip-packing problem (2D-SPP), widely applied in industrial processes to cut sheet metals and paper rolls, where high-quality solutions can be found for more than one improvement heuristic, generating instances with multi-label behavior. To obtain single-label datasets, a total of five multi-label transformation methods are explored. 1000 instances were generated to represent different 2D-SPP variations found in real-world applications, labels for each instance represented by improvement heuristics were calculated, along with 19 predictors provided by problem characteristics. Finally, classification models were fitted to verify the accuracy of each multi-label transformation method. For the 2D-SPP, the single-label obtained using the exclusion method fit more accurate classification models compared to the other four multi-label transformation methods adopted.

Production problems have a significant impact on the on-time delivery of orders, resulting in deviations from planned scenarios. Therefore, it is crucial to predict interruptions during scheduling and to find optimal production sequencing solutions. This paper introduces a selflearning framework that integrates association rules and optimisation techniques to develop a scheduling algorithm capable of learning from past production experiences and anticipating future problems. Association rules identify factors that hinder the production process, while optimisation techniques use mathematical models to optimise the sequence of tasks and minimise execution time. In addition, association rules establish correlations between production parameters and success rates, allowing corrective factors for production quantity to be calculated based on confidence values and success rates. The proposed solution demonstrates robustness and flexibility, providing efficient solutions for Flow-Shop and Job-Shop scheduling problems with reduced calculation times. The article includes two Flow-Shop and Job-Shop examples where the framework is applied.

The use of quantitative methods, including stochastic and exploratory techniques in environmental studies does not seem to be sufficient in practical aspects. There is no comprehensive analytical system dedicated to this issue, as well as research regarding this subject. The aim of this study is to present the Eco Data Miner system, its idea, construction and implementation possibility to the existing environmental information systems. The methodological emphasis was placed on the one-dimensional data quality assessment issue in terms of using the proposed QAAH1 method - using harmonic model and robust estimators beside the classical tests of outlier values with their iterative expansions. The results received demonstrate both the complementarity of proposed classical methods solution as well as the fact that they allow for extending the range of applications significantly. The practical usefulness is also highly significant due to the high effectiveness and numerical efficiency as well as simplicity of using this new tool.