Search

Traditionally, temperature control for massive concrete structures during the construction phase is based on experience instead of using advanced methods such as predictive control method. In this paper, a predictive control method with a hybrid data-based artificial neural network (ANN) model is proposed. The main parameters of the numerical model are identified based on the data measured from the site. Since the limitation of the measured data, a rich dataset is generated by the numerical model with the identified parameters. Finally, a hybrid data-based ANN model for predicting the temperature indicator of massive concrete is developed. A case study in which the temperature control of concrete in a real bridge anchorage foundation construction in Southwestern China is conducted. Results show that the maximum temperature of concrete can be controlled around the target temperature by the proposed method. The average temperature decline rate decreases from 0.19 °C/h to 0.14 °C/h in the period of 120 h (i.e., from 60 h to 180 h after the concrete pouring) at a sudden decrease of 8 °C in environmental temperature, thereby enabling a significant reduction in the risk of concrete cracking. [ABSTRACT FROM AUTHOR]

Timely and accurate survey of construction and demolition waste (C&DW) distribution is of significance for managing C&DW and enhancing the quality of the urban environment, especially in rapidly urbanizing country of China. Automatic C&DW recognition using high-resolution remote sensing images is an extremely important surveying method. Existing C&DW recognition methods can only obtain a rough spatial distribution of C&DW. Mapping precise C&DW distribution on large-scale remote sensing images is still challenging. In this paper, to solve the problem of precise C&DW recognition, a novel deep learning algorithm based on high-resolution remote sensing images is proposed, which we refer to as the cross-channel multi-scale gated fusion network (CCMGNet). CCMGNet extracts depth features of C&DW from RGB and NIR bands by using two independent encoding streams. A gated fusion layer and a multi-scale attention module are designed to effectively fuse the features from two encoding streams. We manually labelled the sample set used for training and testing on 26 remote sensing images captured by the Gaofen-2 (GF-2) satellite. These images were taken in nine typical cities in China over the time period from 2019 to 2021. The results showed that the proposed method is effective in recognizing C&DW, realizing 89.42% and 84.52% in precision and IoU, and is superior to other state-of-the-art deep learning algorithms and existing C&DW recognition methods. The effectiveness of all significant components in CCMGNet was confirmed by ablation experiments. The proposed method was applied to extract C&DW regions in large-scale remote sensing images, with an example of a GF-2 image of Beijing. The high extraction efficiency and satisfactory visual effect demonstrate the potential of the proposed method for surveying the spatial distribution of C&DW. The novel method will play a crucial role in automatically surveying the spatial distribution and size of C&DW across the country. [ABSTRACT FROM AUTHOR]

In machine learning driven surface inspection one often faces the issue that defects to be detected are difficult to make available for training, especially when pixel-wise labeling is required. Therefore, supervised approaches are not feasible in many cases. In this paper, this issue is circumvented by injecting synthetized defects into fault-free surface images. In this way, a fully convolutional neural network was trained for pixel-accurate defect detection on decorated plastic parts, reaching a pixel-wise PRC score of 78% compared to 8% that was reached by a state-of-the-art unsupervised anomaly detection method. In addition, it is demonstrated that a similarly good performance can be reached even when the network is trained on only five fault-free parts. [ABSTRACT FROM AUTHOR]

Artificial neural network–cellular automata model has been applied successfully in land use change simulation. However, it has rarely been integrated with landscape pattern indices (LPIs), the embodiment of the spatial heterogeneity of land use. This paper proposed to integrate LPIs as the parameters of artificial neural network–cellular automata model. Subsequent to a description of the principles and implementation of the model, a case study was presented in Changping district. In the case study, two LPIs, the landscape similarity index and patch density, along with 10 other spatial variables, were selected as the influencing factors of land use change. Based on land use maps in years 1988 and 1998, a land use map in 2008 was simulated by the proposed model. Comparing with the actual land use map in 2008 and the simulated result of artificial neural network–cellular automata model, the results showed that the proposed model is more applicable for simulating land use change in the study area; the limitation of this model is the spatial scale and calculation method of LPIs. [ABSTRACT FROM PUBLISHER]

Research indicates that the worldwide shortage of qualified seafarers has been due to the rapidly increasing world merchant fleet on the one hand and the difficulty of attracting and retaining people in the industry on the other. The paper argues that in the context of the Chinese shipping industry, the high “wastage” is one of the major contributors to the shortage. The aims of the research are to examine the motives of students studying nautical courses; identify the key factors affecting nautical students to choose seafaring career, and to predict students’ career choice behavior. The research finds that (a) those who had a clear sense of their future career when enrolled in the nautical studies tend to choose a seafaring career and remain active for a longer period of time; (b) high wage is the most important factor affecting students’ decisions to choose seafaring as a career; (c) prolonged separation from family, job opportunities ashore, and concern about children’s growth and education are among the top three factors for students not to choose a seafaring career or to quit it early; and (d) nautical students’ career choice behaviors can be predicted through the use of artificial neural network (ANN) and genetic programming (GP) with five rules being generated. This novel methodological approach, a combination of ANN and GP, has been proven to be effective in analyzing complex variables and in generating rules. [ABSTRACT FROM AUTHOR]

Primary fine particulate matters with a diameter of less than 10µm(PM10) are important air emissions causing human health damage. PM10concentration forecast is important and necessary to perform in order to assess the impact of air on the health of living beings. To better understand the PM10pollution health risk in Taiyuan City, China, this paper forecasted the temporal and spatial distribution of PM10yearly average concentration, using Back Propagation Artificial Neural Network (BPANN) model with various air quality parameters. The predicted results of the models were consistent with the observations with a correlation coefficient of 0.72. The PM10yearly average concentrations combined with the population data from 2002 to 2008 were given into the Intake Fraction (IF) model to calculate the IFs, which are defined as the integrated incremental intake of a pollutant released from a source category or a region over all exposed individuals. The results in this study are only for main stationary sources of the research area, and the traffic sources have not been included. The computed IFs results are therefore under-estimations. The IFs of PM10from Taiyuan with a mean of 8.5 per million were relatively high compared with other IFs of the United States, Northern Europe and other cities in China. The results of this study indicate that the artificial neural network is an effective method for PM10pollution modeling, and the Intake Fraction model provides a rapid population risk estimate for pollutant emission reduction strategies and policies. [ABSTRACT FROM AUTHOR]

A remote sensing approach is proposed in this paper for monitoring instantaneous underwater light climate in Dahuchi Lake, China. Water constituents that are optically significant to the lake water can be retrieved through this method based on an artificial neural network (ANN) algorithm with a satisfactory accuracy. In this study, the ANN was trained by spectral simulations which were generated by a water colour simulation model (WASI). An underwater light attenuation model has been built by fitting the field measurements and applied to calculate photosynthetically available radiation (PAR) at the bottom of the lake from the inputs of hyperspectral reflectance above the water surface and the water depth. Results show that this method can predict the concentration of suspended particle matter (SPM) with a high accuracy and explain more than half of the underwater PAR variation with a standard deviation of 94.8 μmol s-1 m-2. In order to test the portability of the algorithm, it has also been extended to three bands of Landsat TM image. Compared with hyperspectral inputs, ANN with broadband inputs has lower but still acceptable accuracy on SPM retrieval. The advantage of this method lies in its time-efficient and cost-efficient monitoring of underwater light climate, i.e. the simulations generated by a semi-physical model can be used for ANN training, instead of using a large number of field measurements. [ABSTRACT FROM AUTHOR]

The giant panda is an obligate bamboo grazer. Therefore, the availability and abundance of understorey bamboo determines the quantity and quality of panda habitat. However, there is little or no information about the spatial distribution or abundance of bamboo underneath the forest canopy, due to the limitations of traditional remote sensing classification techniques. In this paper, a new method combines an artificial neural network and a GIS expert system in order to map understorey bamboo in the Qinling Mountains of south-western China. Results from leaf-off ASTER imagery, using a neural network and an expert system, were evaluated for their suitability to quantify understorey bamboo. Three density classes of understorey bamboo were mapped, first using a neural network (overall accuracy 64.7%, Kappa 0.45) and then using an expert system (overall accuracy 62.1%, Kappa 0.43). However, when using the results of the neural network classification as input into the expert system, a significantly improved mapping accuracy was achieved with an overall accuracy of 73.8% and Kappa of 0.60 (average z-value = 3.35, p = 0.001). Our study suggests that combining a neural network with an expert system makes it possible to successfully map the cover of understorey species such as bamboo in complex forested landscapes (e.g. coniferous-dominated and dense canopy forests), and with higher accuracy than when using either a neural network or an expert system. [ABSTRACT FROM AUTHOR]

A high-dimensional dataset was built with time-series data of vegetation indexes derived from a Terra-Moderate Resolution Imaging Spectroradiometer (MODIS) sensor used for land use/cover classification. The self-organizing map (SOM) neural network technique can reduce the dimensionality of high-dimensional data, yet keep the same topological characters in the low-dimension space after dimension reduction. In this paper, we first employed the SOM neural network technique to classify land cover types using a 17-dimensional dataset that was generated from 16-day interval MODIS Enhanced Vegetation Index (EVI) data with a spatial resolution of 500 m in eastern China during the growing period of plants. Then, we defined an unlabelled class of neuron. Pixels matched to this type of neuron were regarded as unclassified land cover types, so that we could remove the poorly classified areas. Finally, the classification results were compared with those of the maximum likelihood classification (MLC) method. Comparison showed that the accuracy of the former exceeded that of the latter in classifying a high-dimensional dataset. [ABSTRACT FROM AUTHOR]

Using the measured data on no-flow events in the Lower Yellow River since 1972, this paper presents an approach to describe the no-flow status in terms of a comprehensive indicator. The severity levels of no-flow events are identified by cluster analysis. Furthermore, the relation between severity levels and incoming water from upstream and its variance is well established with a BP-typed Artificial Neural Network (ANN), which is helpful to identify the complex response of the severity level to flow characteristics. The availability of the approach for quantitative description and prediction of no-flow events is discussed through comparisons between predicted and measured results in the Lower Yellow River. [ABSTRACT FROM AUTHOR]