Five models and methodology are discussed in this paper for constructing classifiers capable of recognizing in real time the type of fuel injected into a diesel engine cylinder to accuracy acceptable in practical technical applications. Experimental research was carried out on the dynamic engine test facility. The signal of in-cylinder and in-injection line pressure in an internal combustion engine powered by mineral fuel, biodiesel or blends of these two fuel types was evaluated using the vibro-acoustic method. Computational intelligence methods such as classification trees, particle swarm optimization and random forest were applied.
Land use/land cover (LULC) maps are important datasets in various environmental projects. Our aim was to demonstrate how GEOBIA framework can be used for integrating different data sources and classification methods in context of LULC mapping.We presented multi-stage semi-automated GEOBIA classification workflow created for LULC mapping of Tuszyma Forestry Management area based on multi-source, multi-temporal and multi-resolution input data, such as 4 bands- aerial orthophoto, LiDAR-derived nDSM, Sentinel-2 multispectral satellite images and ancillary vector data. Various classification methods were applied, i.e. rule-based and Random Forest supervised classification. This approach allowed us to focus on classification of each class ‘individually’ by taking advantage from all useful information from various input data, expert knowledge, and advanced machine-learning tools. In the first step, twelve classes were assigned in two-steps rule-based classification approach either vector-based, ortho- and vector-based or orthoand Lidar-based. Then, supervised classification was performed with use of Random Forest algorithm. Three agriculture-related LULC classes with vegetation alternating conditions were assigned based on aerial orthophoto and Sentinel-2 information. For classification of 15 LULC classes we obtained 81.3% overall accuracy and kappa coefficient of 0.78. The visual evaluation and class coverage comparison showed that the generated LULC layer differs from the existing land cover maps especially in relative cover of agriculture-related classes. Generally, the created map can be considered as superior to the existing data in terms of the level of details and correspondence to actual environmental and vegetation conditions that can be observed in RS images.
In this study, emulsified kerosene was investigated to improve the flotation performance of ultrafine coal. For this purpose, NP-10 surfactant was used to form the emulsified kerosene. Results showed that the emulsified kerosene increased the recovery of ultrafine coal compared to kerosene. This study also revealed the effect of independent variables (emulsified collector dosage (ECD), frother dosage (FD) and impeller speed (IS)) on the responses (concentrate yield (γC %), concentrate ash content ( %) and combustible matter recovery (ε %)) based on Random Forest (RF) model and Genetic Algorithm (GA). The proposed models for γC %, % and ε% showed satisfactory results with R2. The optimal values of three test variables were computed as ECD = 330.39 g/t, FD = 75.50 g/t and IS = 1644 rpm by using GA. Responses at these experimental optimal conditions were γC % = 58.51%, % = 21.7% and ε % = 82.83%. The results indicated that GA was a beneficial method to obtain the best values of the operating parameters. According to results obtained from optimal flotation conditions, kerosene consumption was reduced at the rate of about 20% with using the emulsified kerosene.
Sediment samples and hydrographic conditions were studied at 28 stations around Iceland. At these sites, Conductivity−Temperature−Depth (CTD) casts were conducted to collect hydrographic data and multicorer casts were conducted to collect data on sediment characteristics including grain size distribution, carbon and nitrogen concentration, and chloroplastic pigment concentration. A total of 14 environmental predictors were used to model sediment characteristics around Iceland on regional scale. Two approaches were used: Multivariate Adaptation Regression Splines (MARS) and randomForest regression models. RandomForest outperformed MARS in predicting grain size distribution. MARS models had a greater tendency to over− and underpredict sediment values in areas outside the environmental envelope defined by the training dataset. We provide first GIS layers on sediment characteristics around Iceland, that can be used as predictors in future models. Although models performed well, more samples, especially from the shelf areas, will be needed to improve the models in future.
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.
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.