Groundwater is a vital water source in the rural and urban areas of developing and developed nations. In this study, a novel hybrid integration approach of Fisher’s linear discriminant function (FLDA) with rotation forest (RFLDA) and bagging (BFLDA) ensembles was used for groundwater potential assessment at the Ningtiaota area in Shaanxi, China. A spatial database with 66 groundwater spring locations and 14 groundwater spring contributing factors was prepared; these factors were elevation, aspect, slope, plan and profile curvatures, sediment transport index, stream power index, topographic wetness index, distance to roads and streams, land use, lithology, soil and normalized difference vegetation index. The classifier attribute evaluation method based on the FLDA model was implemented to test the predictive competence of the mentioned contributing factors. The area under curve, confidence interval at 95%, standard error, Friedman test and Wilcoxon signed-rank test were used to compare and validate the success and prediction competence of the three applied models. According to the achieved results, the BFLDA model showed the most prediction competence, followed by the RFLDA and FLDA models, respectively. The resulting groundwater spring potential maps can be used for groundwater development plans and land use planning.

/pdf/novel-hybrid-integration-approach-of-bagging-based-fisher-s-4pqbgejc27.pdf

Novel Hybrid Integration Approach of Bagging-Based Fisher’s Linear Discriminant Function for Groundwater Potential Analysis

This analysis aims to generate landslide susceptibility maps (LSMs) using various machine learning methods, namely random forest (RF), alternative decision tree (ADTree) and Fisher’s Linear Discriminant Function (FLDA). The results of the FLDA, RF and ADTree models were compared with regard to their applicability for creating an LSM of the Gallicash river watershed in the northern part of Iran close to the Caspian Sea. A landslide inventory map was created using GPS points obtained in a field analysis, high-resolution satellite images, topographic maps and historical records. A total of 249 landslide sites have been identified to date and were used in this study to model and validate the LSMs of the study region. Of the 249 landslide locations, 70% were used as training data and 30% for the validation of the resulting LSMs. Sixteen factors related to topographical, hydrological, soil type, geological and environmental conditions were used and a multi-collinearity test of the landslide conditioning factors (LCFs) was performed. Using the natural break method (NBM) in a geographic information system (GIS), the LSMs generated by the RF, FLDA, and ADTree models were categorized into five classes, namely very low, low, medium, high and very high landslide susceptibility (LS) zones. The very high susceptibility zones cover 15.37% (ADTree), 16.10% (FLDA) and 11.36% (RF) of the total catchment area. The results of the different models (FLDA, RF, and ADTree) were explained and compared using the area under receiver operating characteristics (AUROC) curve, seed cell area index (SCAI), efficiency and true skill statistic (TSS). The accuracy of models was calculated considering both the training and validation data. The results revealed that the AUROC success rates are 0.89 (ADTree), 0.92 (FLDA) and 0.97 (RF) and predication rates are 0.82 (ADTree), 0.79 (FLDA) and 0.98 (RF), which justifies the approach and indicates a reasonably good landslide prediction. The results of the SCAI, efficiency and TSS methods showed that all models have an excellent modeling capability. In a comparison of the models, the RF model outperforms the boosted regression tree (BRT) and ADTree models. The results of the landslide susceptibility modeling could be useful for land-use planning and decision-makers, for managing and controlling the current and future landslides, as well as for the protection of society and the ecosystem.

Landslide Susceptibility Evaluation and Management Using Different Machine Learning Methods in The Gallicash River Watershed, Iran

A new solution to one sample problem in face recognition using FLDA

Survey: Subspace methods for face recognition

Since the manual inspection of analog instruments is inefficient, many computer vision-based automatic reading systems have been proposed recently. However, most of them use fixed cameras that are costly due to a large number of used cameras. Although some other systems adopting the pan–tilt–zoom camera and the movable inspection robot can avoid using many cameras, they have to overcome high computational cost in aligning the camera to the tested instrument. Meanwhile, most existing systems are instrument type-dependent and, hence, cannot handle multiple types of instruments simultaneously. In this article, first, based on an inspection robot, an automatic reading system equipped with a pan–tilt–zoom camera is designed for different types of round-shape analog instruments. Then, a fast camera alignment algorithm based on visual servo is proposed, in which YOLOv3 is applied and improved to locate the instrument and guide the camera to iteratively align with the instrument. Finally, a monocular-vision pointer reconstruction algorithm is proposed to accurately read the instrument. Experimental results demonstrated that our proposed system is fast and reliable in the camera-alignment process and is effective in reading different types of analog instruments during the robot-based inspection.

An Automatic Analog Instrument Reading System Using Computer Vision and Inspection Robot

Sampled FLDA for face recognition with single training image per person

A face recognition method based on the discrete cosine transform (DCT) and two dimensional linear discriminant analysis (2DLDA) is presented. First, in this paper, the dimensionality of the original face image is reduced by using the DCT and the upper-left corner of the DCT matrix is selected to be the features of face image. Next, the proper feature are abstracted from the truncated DCT coefficient matrix by 2DLDA. The proposed algorithms are compared with both the DCT-based algorithm and the DCT+LDA algorithm which are proposed for face recognition. Experimental results on the ORL face database show that the proposed approach is feasible and has higher recognition performance than the other two algorithms.

/pdf/face-recognition-based-on-dct-and-2dlda-3cwthgqulv.pdf

Face Recognition Based on DCT and 2DLDA

To effectively resolve the automatic recognition of analog pointer measuring instruments, a reading recognition method based on Hough transform is proposed. In order to simplify the following procedure, image graying and binary, mathematical morphology, including dilation and thinning, edge recognition was applied to the system. We proposed the recognition principle for reading recognition of the pointer's angle by using Hough transform. And the reading of the pointer is decided by the linear relationship between the panel's scale and the angle of the instrument's dial revolutionary. Considering that in most practical cases, the panel cannot be horizontal, so the procedure of tilt correction is employed in this paper. Finally, the software is written in MATLAB. The recognition system is achieved in LabVIEW, where the front panel of the reading system is developed. The experimental results demonstrate that our method is feasible for pointer instrument recognition.

Development of an automatic reading method and software for pointer instruments

IEEE 1588 defines a precision time protocol, which is widely used in distributed test and measurement systems. It is very important to capture the timestamps of the location that can affect the synchronization accuracy seriously in the synchronization process. In this paper, we proposed a method to capture the timestamps based on specialized hardware Field Programmable Gate Array (FPGA) between the physical layer and MAC layer. We designed IEEE 1588 message detection module and frequency compensation clock to detect IEEE 1588 message and record the timestamps, respectively. This method can eliminate the delay jitter which is caused by the network protocol stack to improve the synchronization accuracy. The test experiments results show that 97.76% of the synchronization deviation is located within ±40nS.

The implementation of IEEE 1588 clock synchronization protocol based on FPGA

The advanced deep convolution neural networks (CNNs) based salient object detection (SOD) models still suffer from the coarse object edge. The traditional graph-based SOD models can preserve the object edge well benefitting from the superpixels, but they perform weaker in highlighting the whole object compared to recent deep learning models. To tackle this problem, we attempt to find a new way to address this issue under the framework of graph convolution networks (GCNs). Specifically, we first model the image as a set of superpixels and construct the graph structure by connecting the k nearest neighbors for each node. For the connected nodes, rather than only leveraging on the predefined edges, we propose a multi-relations edge convolution operation, expecting to learn multiple implicit relations in the pair-wise nodes and aggregate the information from their neighbors relying on the learned edges. Then, a channel-wise attention operation is also proposed to boost the intra-node massage propagation across channels within the same node. In order to optimize the graph structure from layer to layer, we learn a new metric to re-measure the distance between any pair of nodes, and the graph structure evolves dynamically by recomputing the k nearest neighbors in the saliency feature space at different layers. Finally, a residual structure is applied to enable our graph network to go as deep as CNNs models. The graph nodes (superpixels) inherently belonging to the same class will be ideally clustered together in the learned embedding space. Experiments show that this work is a good practice for designing GCNs for image SOD and achieves the comparable performance with the recent state-of-the-art deep CNNs-based models.

Hongtao Yin

Papers

Sampled FLDA for face recognition with single training image per person

Face Recognition Based on DCT and 2DLDA

Development of an automatic reading method and software for pointer instruments

The implementation of IEEE 1588 clock synchronization protocol based on FPGA

A novel dynamic graph evolution network for salient object detection