Estimating impervious surfaces from medium spatial resolution imagery using the self-organizing map and multi-layer perceptron neural networks

In recent years, the urban impervious surface has been recognized as a key quantifiable indicator in assessing urbanization impacts on environmental and ecological conditions. A surge of research interests has resulted in the estimation of urban impervious surface using remote sensing studies. The objective of this paper is to examine and compare the effectiveness of two algorithms for extracting impervious surfaces from Landsat TM imagery; the multilayer perceptron neural network (MLPNN) and the support vector machine (SVM). An accuracy assessment was performed using the high-resolution WorldView images. The root mean square error (RMSE), the mean absolute error (MAE), and the coefficient of determination (R(2)) were calculated to validate the classification performance and accuracies of MLPNN and SVM. For the MLPNN model, the RMSE, MAE, and R(2) were 17.18%, 11.10%, and 0.8474, respectively. The SVM yielded a result with an RMSE of 13.75%, an MAE of 8.92%, and an R2 of 0.9032. The results indicated that SVM performance was superior to that of MLPNN in impervious surface classification. To further evaluate the performance of MLPNN and SVM in handling the mixed-pixels, an accuracy assessment was also conducted for the selected test areas, including commercial, residential, and rural areas. Our results suggested that SVM had better capability in handling the mixed-pixel problem than MLPNN. The superior performance of SVM over MLPNN is mainly attributed to the SVM's capability of deriving the global optimum and handling the over-fitting problem by suitable parameter selection. Overall, SVM provides an efficient and useful method for estimating the impervious surface. (C) 2011 Society of Photo-Optical Instrumentation Engineers (SPIE). [DOI: 10.1117/1.3539767]

The increase of urban impervious surface has significant influence on the urban ecological environment, also contributes to urban waterlogging and urban heat island (UHI). Therefore, the remote sensing extraction of urban impervious surface becomes a hotspot. The widely used sub-pixel approach - Linear Spectral Mixture Analysis (LSMA) estimates the impervious surface by adding the high albedo (the bright impervious surface) and the low albedo (the dark impervious surface) from the solving percentage of different objects from mixed pixels. However for the approach, the selection of end members is difficult and some misclassifications will occur, which causes a large area error, and low accuracy of the impervious surface area. For these issue, in this study, a modified LSMA is explored combining with high-resolution image (Google earth image, 2 meters), the Principal Component Analysis (PCA) and the Normalized Difference Building Index (NDBI) to extract the impervious surface of Guangzhou city with Landsat 8 OLI, October 2015. Based on the PCA, and high resolution image are employed to accurate the selection of end members. The LSMA based on the PCA, the modified LSMA based on the PCA and NDBI are taken to extract the impervious surface of the research area. And the Google earth image is for screening the end members and testing the accuracy estimation by sample area. The result shows that after the accurate topographic correction, the modified LSMA based on the PCA and NDBI is better than the conventional LSMA based on the PCA. The area precision of impervious surface in research area by the modified LSMA is improved with the correlation coefficient is 0.947. The study indicates that taking the high resolution images, the PCA and NDBI to improve the LSMA can raise the un-mix accuracy to a certain degree.

Data-driven models were developed for monitoring the power consumption and wood quality during the lumber manufacturing process. The study proposes hybrid models using vibration signals combined with self-organizing maps (SOMs) for cutting power and waviness prediction in the circular sawing process of Douglas-fir wood under very high feed speed conditions. The acquired vibration signals were fed into SOMs with different topologies for data mapping and automatic sensory feature selection, which were fed into the adaptive neuro-fuzzy inference system (ANFIS) or multilayer perceptron (MLP) neural network (NN) for cutting power and waviness prediction. The monitoring performance of the hybrid SOM-MLP NN and SOM-ANFIS models was compared. The frequency response of vibration signals and its correlation with the cutting parameters as well as the cutting power and waviness were discussed. The study shows that the developed SOM models to select the optimal features from the vibration signals could accurately predict cutting power and waviness when combined with a machine learning model. The prediction performance is highly dependent on the optimal choice of SOM topology. Having a poor choice of SOM topology, fine-tuning the architecture of ANFIS and MLP NN is crucial and greatly impacts the monitoring performance. Based on the obtained results, SOM is recommended for the automatic feature in the machining or tool condition monitoring, where due to process high variability, manual feature selection is a challenging task. SOM combined with an ANN or ANFIS makes a powerful intelligent model for monitoring complex processes such as wood circular sawing.

In this paper we propose an unsupervised neural modeling technique, called Vector-Quantized Temporal Associative Memory (VQTAM). Using VQTAM, the Kohonen's self-organizing map (SOM) becomes capable of approximating dynamical nonlinear mappings from time series of measured input-output data. The SOM produces modeling results as accurate as those produced by multilayer perceptron (MLP) networks, and better than those produced by radial basis functions (RBF) networks, both the MLP and the RBF based on supervised training. In addition, the SOM is less sensitive to weight initialization than MLP networks. The three networks are evaluated through simulations and compared with the linear ARX model in the forward modeling of a hydraulic actuator.

The purpose of this study was to investigate the efficiency of using magnesium oxide nanoparticles, twisted tapes with different and modified twist ratios, and the different rotation velocity of perforated twisted tapes in the evaluation of Nusselt number, overall heat transfer coefficient and pressure drop in a double pipe heat exchanger. Subsequently, the results obtained from the experimental tests of Nusselt number, overall heat transfer coefficient and pressure drop using a modified twisted tape in a double pipe heat exchanger and a back propagation artificial neural network with a multilayered perceptron structure show the existence of a relationship between heat transfer parameters and input data such as cold and hot fluid temperatures, volume fractions of nanofluid, twisted tapes of different twist ratios, the rotation velocity of twisted tapes, Reynolds number of hot and cold fluids, viscosity and thermal conductivity of the nanofluid. Also, the non-monitored artificial neural network selected 33 neurons for use in the multilayered perceptron neural network. The network included the sigmoid function in the hidden layer and the Levenberg–Marquardt training algorithm with a three-layer topology of 9–33-1 with the correlation coefficients of 0.9987, 0.9933 and 0.9944 and the mean squared error of 0.66535, 4547.68 and 0.008768. This network was best for predicting heat transfer parameters such as Nusselt number, overall heat transfer coefficient and pressure drop.

Based on Landsat ETM+ data within the metropolitan area of Lanzhou, China, green vegetation(GV) and impervious surface was extracted by a constrained linear spectral mixture analysis (LSMA),together with single window algorithm to invert land surface temperature ,and the correlation analysis was then conducted to examine the relationship between urban heat island (UHI) effect and impervious surface. Four types of end members with high albedo, GV, soil and low albedo are selected to model complicated urban land cover, estimation accuracy is assessed using Root-Mean-Square (RMS)error and color aerial images, with the help of Mantel and Partial Mantel. Spatial relationship of land surface temperatures (LST), impervious surface and GV were analyzed. Results indicate that impervious surface distribution and GV can be derived from Landsat TM/ETM+ images with satisfactory precision. Impervious surface and GV were positively correlated with UHI, while LST has space dependence, it has high space dependence, and was higher correlated with impervious surface than GV.

This paper examines the subpixel analysis of Landsat ETM/sup +/ data to estimate the percent cover of impervious surface, lawn, and woody tree cover in typical urban/suburban landscapes. By combining Self-Organizing Map (SOM), Learning Vector Quantization (LVQ), and Gaussian Mixture Model (GMM) methods, the posterior probability of the various land cover components were estimated for each pixel as a means of subpixel analysis. The estimation of impervious surface and the differentiation of urban vegetation-grass versus woody tree cover-are the main objectives of this paper. Overall, the output estimates compared favorably with those obtained using higher spatial resolution aerial photograph and IKONOS satellite image and traditional hard classification techniques as independent reference. The SOM-LVQ-GMM model showed a moderate degree of similarity in the estimates of impervious surface [root mean-square errors (RMSEs) of </spl plusmn/12% for the aerial photo reference plots and </spl plusmn/18% for the IKONOS classified results at a 3/spl times/3 pixel scale]. The vegetation components of woody tree and grass cover had an RMSE of </spl plusmn/10% and 11% for the aerial photo reference plots and </spl plusmn/15% and 22% for the IKONOS classified results at a 3/spl times/3 pixel scale, respectively. While further work is needed to improve the partition of grass versus woody tree cover estimation, the SOM-LVQ-GMM approach was sufficient to effectively discriminate between those areas dominated by grass cover versus those with significant woody tree cover. The ability to separate the grass versus woody tree components in urban vegetation analysis provides a more nuanced view of urban ecosystems.

Remote sensing estimation of impervious surface is significant in monitoring urban development and determining the overall environmental health of a watershed, and it has therefore attracted more interest recently in the remote sensing community. The main objective of this paper is to examine and compare the effectiveness of two advanced algorithms for estimating impervious surfaces from medium spatial resolution satellite images, namely, linear spectral mixture analysis (LSMA) and artificial neural network (ANN). Terra's Advanced Spaceborne Thermal Emission and Reflection Radiometer [(ASTER); acquired on June 16,2001] and a Landsat Enhanced Thematic Mapper Plus (ETM+) image (acquired on June 22, 2000) of Indianapolis, IN, were used for the analysis. The LSMA was employed to generate high- and low-albedo, vegetation, and soil fraction images (endmembers), and an image of impervious surfaces was then estimated by adding high- and low-albedo fraction images. Furthermore, an ANN model, specifically the multilayer-perceptron feedforward network with the back-propagation learning algorithm, was employed as a subpixel image classifier to estimate impervious surfaces. Accuracy assessment was performed against a high- resolution digital orthophoto. The results show that ANN was more effective than LSMA in generating impervious surfaces with high statistical accuracy. For the ASTER image, the root-mean-square error (RMSE) of the impervious surface map with the ANN model was 12.3%, and the one that resulted from LSMA was 13.2%. For the ETM+ image, the RMSE with the ANN model was 16.7%, and the one from LSMA was 18.9%. The better performance of ANN over LSMA is mainly attributable to the ANN'S capability of handling the nonlinear mixing of image spectrum. In order to test the seasonal sensitivity of satellite images for estimating impervious surfaces, LSMA was applied to two additional ASTER images of the same area, which are acquired on April 5, 2004, and October 3, 2000, respectively. The results were then compared with the ASTER image acquired in June in terms of RMSE. The June image had the highest accuracy, whereas the October image was better than the one in April. Plant phenology caused changes in the variance partitioning and impacted the mixing-space characterization, leading to a less accurate estimation of impervious surfaces.

Breast cancer is the most common kind of cancer, which is the cause of death among the women worldwide. There is evidence that shows that the early detection and treatment can increase the survival rate of patients who suffered this disease. Therefore, this paper proposes an automatic breast cancer diagnosis technique using a genetic algorithm for simultaneous feature selection and parameter optimization of an Multi Layer Perceptron (MLP) neural network. The aim of this paper is to propose a hybrid classification algorithm based on Multi-stage Weights Adjustment in the MLP (MWAMLP) neural network in two parts to improve the breast cancer diagnosis. In the first part, the three classifiers are trained simultaneously on the learning dataset. The output of the first part classifier together with the learning dataset is placed in a new dataset. This dataset uses a hybrid classifier method to model the mapping between the outputs of each ordinary classifier of the first part with real output labels. The proposed algorithm is implemented with three different variations of the backpropagation (BP) technique, namely the Levenberg–Marquardt, resilient BP and gradient descent with momentum for fine tuning of the weight of MLP neural network and their performances are compared. Interestingly, one of the proposed algorithms titled MWAMLP-RP produces the best and on average, 99.35% and 98.74% correct classification, respectively, on the Wisconsin Breast Cancer Database dataset, which is comparable with the obtained results from the methods titled GP-DLNN, GAANN and CAFS and other works found in the literature.

We applied multilayer perceptron (MLP) and radial basis function (RBF) neural networks using data from two water quality monitoring stations at the Karaj Dam in Iran. Input data were calcium ions (Ca2+), magnesium ions (Mg2+), sodium ions (Na+), chloride ions (Cl−), sulfate ( SO 42−), and pH, and the output data were total dissolved solids (TDS). An MLP with one hidden layer containing eight neurons was selected for the upstream water quality station using normalized input data. We developed a second MLP neural network for the downstream station with one hidden layer containing 10 neurons in the hidden layer using normalized input data. Considering applying normalized input data and one hidden layer, the coefficient of determination (R2) and index of agreement (IA) between the observed and the predicted data for the upstream and downstream monitoring stations using the MLP neural networks were 0.985, 0.84, 0.99, and 0.92, respectively. The RBF neural network with 100 neurons in its hidden layer reached the minimum errors between the observed and the predicted results in upstream and downstream stations. The R2 between observed and predicted data for upstream and downstream monitoring stations for the RBF was 0.999 and 0.998, respectively. Data normalization improved the performance of the MLP neural networks. Sensitivity analysis indicated that magnesium is the most effective water quality parameter for predicting TDS, and sulfate is the second most effective water quality parameter affecting TDS prediction at the Karaj Dam.

Complexity Analysis of Multilayer Perceptron Neural Network Embedded into a Wireless Sensor Network

Application of neural networks to detection of medical fraud

Hydraulic calculations of water distribution systems are currently performed using computer programs. In addition to the basic calculation procedure, modules responsible for evaluating the obtained calculation results are introduced more and more often into the programs. This article presents the results of research on artificial neural networks with a radial base function (RBF) and a multilayer perceptron (MLP), aimed at determining whether they can be used to model the relationship between the variables describing the computational section of the water distribution system and the diameter of the water pipe. The classification capabilities of the RBF and MLP networks were analyzed according to the number of neurons in the hidden layer of the network. A comparative analysis of RBF networks with multilayer perceptron (MLP) networks was performed. The results showed that the MLP networks have much better classification properties and are better suited for the task of assessing the selected diameters of the water pipes.

In this paper a natural texture classification study was developed employing neural network models. The objective of this study was to assess the accuracy of each model for the classifying natural texture problem. Multi-layer Perceptron (MLP) network, Hopfield network, Self-organizing feature map (SOFM) network and a Radial Basis Function (RBF) network were the models studied, analyzed using the Neurosolutions version 5.0 (trial version) software and Weka version 3.4 software, in this work. A file, with more than 700 records of natural texture characteristics, which were obtained by the analysis of digital photographs of real landscapes, was used for the experiments. These natural textures were divided in 9 classes: water, ground-sand, grass, stones, sky, tree, mountain, snow and flowers. The experimental results showed that Multilayer Perceptron network was the best neural network model in the natural texture classification.

Urban heat island (UHI) attenuation is an essential aspect for maintaining environmental sustainability at a local, regional, and global scale. Although impervious surfaces (IS) and green spaces have been confirmed to have a dominant effect on the spatial differentiation of the urban land surface temperature (LST), comprehensive temporal and quantitative analysis of their combined effects on LST and surface urban heat island intensity (SUHII) changes is still partly lacking. This study took the plain area of Beijing, China as an example. Here, rapid urbanization and a large-scale afforestation project have caused distinct IS and vegetation cover changes within a small range of years. Based on 8 scenes of Landsat 5 TM/7ETM/8OLI images (30 m × 30 m spatial resolution), 920 scenes of EOS-Aqua-MODIS LST images (1 km × 1 km spatial resolution), and other data/information collected by different approaches, this study characterized the interrelationship of the impervious surface area (ISA) dynamic, forest cover increase, and LST and SUHII changes in Beijing’s plain area during 2009–2018. An innovative controlled regression analysis and scenario prediction method was used to identify the contribution of ISA change and afforestation to SUHII changes. The results showed that percent ISA and forest cover increased by 6.6 and 10.0, respectively, during 2009–2018. SUHIIs had significant rising tendencies during the decade, according to the time division of warm season days (summer days included) and cold season nights (winter nights included). LST changes during warm season days responded positively to a regionalized ISA increase and negatively to a regionalized forest cover increase. However, during cold season nights, LST changes responded negatively to a slight regionalized ISA increase, but positively to an extensive regionalized ISA increase, and LST variations responded negatively to a regionalized forest cover increase. The effect of vegetation cooling was weaker than ISA warming on warm season days, but the effect of vegetation cooling was similar to that of ISA during cold season nights. When it was assumed that LST variations were only caused by the combined effects of ISA changes and the planting project, it was found that 82.9% of the SUHII rise on warm season days (and 73.6% on summer days) was induced by the planting project, while 80.6% of the SUHII increase during cold season nights (and 78.9% during winter nights) was caused by ISA change. The study presents novel insights on UHI alleviation concerning IS and green space planning, e.g., the importance of the joint planning of IS and green spaces, season-oriented UHI mitigation, and considering the thresholds of regional IS expansion in relation to LST changes.