Proposed Generation Algorithm Research Articles

Generation of 1D channel networks for overland flow simulations on 2D complex domains

Conventionally two-dimensional (2D) models are used to simulate 2D overland flow with a non-overlapping 2D computational mesh. However, 2D models are not computationally efficient when applied to large domains. Due to their computing efficiency, one-dimensional (1D) models can be used to simulate 2D overland flows by replacing 2D computational meshes with 1D computational channel networks with topography described by closely-spaced transverse cross sections that fully cover the whole domain. Channel networks must enforce the basic physical laws of gravity-driven flows ensuring water flow paths converge and connect from high to low elevations. This manuscript presents a novel algorithm to generate channel networks following two principles, a geometric principle and a hydrologic principle. The geometric principle requires that the generated channel network covers the whole study domain without overlaps or intersections, while the hydrologic principle requires that the generated channel network follows the local steepest slope. Correspondingly, the proposed generation algorithm includes two main processes: (1) the extraction of channel network using a terrain slope-calculation-based delineation algorithm; and, (2) the generation of cross sections with varying channel widths determined by considering topographic complexity, the hydrological correctness, and computational requirements. The proposed cross section generation algorithm is described using several 2D geometrically complex domains at the laboratory scale, and is also applied to a natural watershed. An overflow simulation on a 2D domain with obliques walls using a 1D model demonstrated the effectiveness of the proposed generation algorithm for 1D channel networks of 1D model.

Generation of random directions from the generalized von Mises–Fisher distribution

We introduce two algorithms for generating from the bimodal generalized von Mises-Fisher distribution on the sphere. This generalization of the von Mises-Fisher distribution is more flexible, in particular by allowing for multimodality, and it preserves many of the theoretical properties of the von Mises-Fisher. The first proposed generation algorithm is obtained from conditional simulation and acceptance-rejection. The second one is the Metropolis-Hastings with mixture of von Mises-Fisher as jumping or instrumental distribution. These two algorithms are compared through density estimations of generated polar angles.

Detection with fast feature pyramids and lightweight convolutional neural network: a practical aircraft detector for optical remote images

Aircraft detection in optical remote sensing images has important practical value and attracts great attention in recent years. Due to some clustered backgrounds and various deformations like variability in viewpoints, scales, and directions, it is still a big challenge. In recent years, deep learning, especially convolutional neural networks (CNNs), has achieved remarkable success not only in natural image object detection tasks but also in remote sensing image object detection tasks. However, due to the limitations of the actual application deployment environment only limited processing units and storage space can be used, and most deep learning-based aircraft detection algorithms cannot work well. To this end, a unique aircraft detection framework in optical remote sensing images is proposed, which is based on fast feature pyramids and a specialized lightweight CNN. The algorithm can be summarized into two steps. In the first step, a highly reliable region proposal generation algorithm is designed to predict region proposals. In this phase, a prior square sliding window method and an efficient linear search algorithm are proposed. In the next step, a lightweight CNN is designed to achieve fast and accurate aircraft classification. The proposed model only requires about 237 KB of parameter storage and can infer in a poor central processing unit platform. Comprehensive experiments on three publicly optical remote sensing aircraft datasets demonstrate the superiority and effectiveness of the proposed method. It is also shown that the proposed method is light and fast in comparison with some state-of-the-art methods.

Deep learning of rock images for intelligent lithology identification

An intelligent lithology identification method is proposed based on the deep learning of rock images. The lithology information and position information in rock images can be predicted using the Faster R–CNN architecture through the RPN proposal generation algorithm and the Fast R–CNN detector. To obtain more rock features, the rock detection model is built on the ResNet structure, and the residual learning is used to retain as much as possible detailed information in the original input image. The four-step alternating training is used to fine-tuned end-to-end, and the prediction results are optimized by the cross-entropy loss and the regression loss. To speed up the model and improve the identification accuracy, data augmentation and pre-training are used to train the model. The mAP, P, R and F1 score are used as evaluation indexes of the accuracy, and the Faster R–CNN model is compared with the YOLO v4 model. Results indicate that the mAP of the rock detection model based on the Faster R–CNN is 99.19% and the F1 score is 96.6%. Compared with the YOLO v4 model, the accuracy is higher and the identification ability is more stable. The proposed rock detection model has good identification ability for different rocks in rock images, and the model is of good robustness and generalization performance, which is suitable for rapid intelligent lithology identification in practical geological and logging engineering.

Fine-Grained Action Recognition by Motion Saliency and Mid-Level Patches

Effective extraction of human body parts and operated objects participating in action is the key issue of fine-grained action recognition. However, most of the existing methods require intensive manual annotation to train the detectors of these interaction components. In this paper, we represent videos by mid-level patches to avoid the manual annotation, where each patch corresponds to an action-related interaction component. In order to capture mid-level patches more exactly and rapidly, candidate motion regions are extracted by motion saliency. Firstly, the motion regions containing interaction components are segmented by a threshold adaptively calculated according to the saliency histogram of the motion saliency map. Secondly, we introduce a mid-level patch mining algorithm for interaction component detection, with object proposal generation and mid-level patch detection. The object proposal generation algorithm is used to obtain multi-granularity object proposals inspired by the idea of the Huffman algorithm. Based on these object proposals, the mid-level patch detectors are trained by K-means clustering and SVM. Finally, we build a fine-grained action recognition model using a graph structure to describe relationships between the mid-level patches. To recognize actions, the proposed model calculates the appearance and motion features of mid-level patches and the binary motion cooperation relationships between adjacent patches in the graph. Extensive experiments on the MPII cooking database demonstrate that the proposed method gains better results on fine-grained action recognition.

Weakly-supervised large-scale image modeling for sport scenes and its applications

Image modeling towards sport scenes plays an important role in sport image classification and analysis. Traditional algorithms for sport image modeling required carefully hand-crafted features, which cannot be popularized in practical application, especially with the emergence of massive-scale data. Weakly-supervised learning algorithms have shown effectiveness in modeling data with image-level labels. Thus, in this paper, we propose a weakly-supervised learning based method for sport image modeling without utilizing bounding box annotations, which can be used for various sport image applications. More specifically, we first collect large-scale sport images from existing datasets and Internet, and we annotate them at image-level labels. Subsequently, we leverage region proposal generation algorithm to select discriminative regions that can effectively represent the category of images. Each region is fed into a pre-trained CNN architecture to extract deep representation. Afterwards, we design an improved multiple discriminant analysis (MDA) algorithm to project these datapoints to a subspace that can more easily to distinguish different sport categories. Comprehensive experiments have shown the effectiveness and robustness of our proposed method.

Multi-Scale CNN Based Garbage Detection of Airborne Hyperspectral Data

Garbage detection is important for environmental monitoring in large areas. However, the manual patrol is time-consuming and labor-intensive. This paper proposes a method for monitoring garbage distribution in large areas with airborne hyperspectral data. Since there is no public hyperspectral garbage dataset, a hyperspectral garbage dataset Shandong Suburb Garbage is labeled and published. For garbage detection, a new hyperspectral image (HSI) classification network MSCNN (Multi-Scale Convolutional Neural Network) is proposed to classify the pixels of HSI data and generate binary garbage segmentation map. Unsupervised region proposal generation algorithm Selective Search and None Maximum Suppression (NMS) are used to extract the location and the size of garbage areas based on the garbage segmentation map. The experiment results show that the proposed algorithm has a good performance on garbage detection in large areas. In addition, the MSCNN has achieved better performance in comparison with other HSI classification methods in the public HSI datasets Indian Pines and Pavia University.

An Efficient Method of Generating Deterministic Small-World and Scale-Free Graphs for Simulating Real-World Networks

We propose a novel mechanism to generate a family of deterministic small-world and scale-free networks by inserting new nodes into old nodes. These models can characterize the distinguishing properties of many real-world networks because this novel class of networks incorporates some key properties characterizing a majority of real-world networked systems, namely a high clustering coefficient and a short characteristic path length. We also obtain some accurate results for their properties, including degree distribution, clustering coefficient and network diameter, exactly according to the proposed generation algorithm of the networks considered, and discuss them. The network representation approach provided here can be used to investigate the complexity of many real-world systems from the perspective of complex networks.

Sequential Optimization for Efficient High-Quality Object Proposal Generation.

We are motivated by the need for a generic object proposal generation algorithm which achieves good balance between object detection recall, proposal localization quality and computational efficiency. We propose a novel object proposal algorithm, BING++, which inherits the virtue of good computational efficiency of BING [1] but significantly improves its proposal localization quality. At high level we formulate the problem of object proposal generation from a novel probabilistic perspective, based on which our BING++ manages to improve the localization quality by employing edges and segments to estimate object boundaries and update the proposals sequentially. We propose learning the parameters efficiently by searching for approximate solutions in a quantized parameter space for complexity reduction. We demonstrate the generalization of BING++ with the same fixed parameters across different object classes and datasets. Empirically our BING++ can run at half speed of BING on CPU, but significantly improve the localization quality by 18.5 and 16.7 percent on both VOC2007 and Microhsoft COCO datasets, respectively. Compared with other state-of-the-art approaches, BING++ can achieve comparable performance, but run significantly faster.

Reconfigurable Custom Functional Unit Generation and Exploitation for Multiple-Issue Processors

Next-generation digital entertainment and mobile communication devices are anticipated to require greater processor performance. To meet these demands, several researchers have attached a reconfigurable hardware accelerator to the base processor core. The reconfigurable hardware accelerator, termed a reconfigurable customized functional unit (RCFU), is usually realized by multiple processing elements (PE) organized in matrix form. The structure of the RCFU is generated from hot operation patterns of specific applications. Other than the RCFU, 'multiple-issue' is another microarchitectural technique to increase the performance. However, the impact of combining both of these approaches in the same design is not yet well understood. This problem motivates us to design RCFU generation and exploitation algorithms for a multiple-issue processor. To allow more operations to execute on the RCFU simultaneously, the proposed generation algorithm merges several data-independent operation patterns to construct the RCFU architecture. To schedule operations on both the RCFU and functional units (FU) of the base processor core simultaneously, the proposed exploitation algorithm presents a model to represent all available computing resources from both the FUs of the base processor and the PEs in the RCFU. Using this model, the RCFU exploitation problem can be considered as an instruction-scheduling problem. Our experiment achieves an average improvement in execution performance of 50% compared with previous efforts.

Generating combinatorial test cases using Simplified Swarm Optimization (SSO) algorithm for automated GUI functional testing

Graphical User Interface (GUI) is the outer skin of programs that facilitate the interaction between the user and different type of computing devices. It is been used in different aspects ranging from normal computers, mobile device, to even very small device nowadays like watches. This interaction uses different tools and programming objects like images, text, buttons, checkboxes, etc. With this emergence of different types of GUIs, they become an essential component to be tested (if available in the software) to ensure that the software meets the required quality by the user. In contrast to non-functional testing, function testing of GUI insures a proper interaction between the user and the application interface without dealing with the coding internals. In this paper, a strategy for GUI functional testing using Simplified Swarm Optimization (SSO) is proposed. The SSO is used to generate an optimized test suite with the help of Event-Interaction Graph (EIG). The proposed strategy also manages and repairs the test suites by deleting the unnecessary event sequences that are not applicable. The proposed generation algorithm based on SSO has proved its effectiveness by evaluating it against other algorithms. In addition, the strategy is applied on a standard case study and proved its applicability in reality.

Algorithm for Smooth S-curve Feedrate Profiling Generation

The algorithms for feedrate profile generation,such as linear and S-curve profiles,have been widely used in machinery controllers,and these algorithms can greatly improve the smoothness of motion.However,most of the algorithms lead to the discontinuous acceleration/deceleration and jerk,or high jerk levels,which is very harmful to machine tool or robot in most occasions. This paper presents a smooth S-curve feedrate profiling generation algorithm that produces continuous feedrate,acceleration,and jerk profiles.Smooth jerk is obtained by imposing limits on the first and second time derivatives of acceleration,resulting in trapezoidal jerk profiles along the tool path.The discretization of smooth S-curve feedrate is realized with a novel approach that improves the efficiency without calculating the deceleration point in each sampled time.To ensure that the interpolation time is a multiple of the value of sampled time,the feedrate,acceleration,jerk,and jerk derivative are recalculated.Meantime,to improve the efficiency,the interpolation steps of all regions are computed before interpolation.According to the distance of trajectory,the smooth S-curve acceleration and decelerations are divided into three blocks:normal block,short block type-Ⅰ,and short block type-Ⅱ.Finally feedrate discretization of short block type-Ⅰand type-Ⅱis obtained with considering the efficiency.The proposed generation algorithm is tested in machining a part on a five axis milling machine,which is controlled with the CNC system for newly developed high-speed machine tools.The test result shows that the smooth S-curve approach has the smoother feedrate,acceleration,deceleration,and jerk profiles than S-curve.The proposed algorithm ensures the automated machinery motion smoothness,and improves the quality and efficiency of the automated machinery motion planning.

Mapping Koch curves into scale-free small-world networks

The class of Koch fractals is one of the most interesting families of fractals, and the study of complex networks is a central issue in the scientific community. In this paper, inspired by the famous Koch fractals, we propose a mapping technique converting Koch fractals into a family of deterministic networks called Koch networks. This novel class of networks incorporates some key properties characterizing a majority of real-life networked systems—a power-law distribution with exponent in the range between 2 and 3, a high clustering coefficient, a small diameter and average path length and degree correlations. Besides, we enumerate the exact numbers of spanning trees, spanning forests and connected spanning subgraphs in the networks. All these features are obtained exactly according to the proposed generation algorithm of the networks considered. The network representation approach could be used to investigate the complexity of some real-world systems from the perspective of complex networks.

Generation of Regrasping Motion for Multi-Fingered Robot Hand by Evolutionary Programming.

The control of multi-fingered robot hands has been the subject of recent interest. To manipulate some object with rerasping motion, there are many parameters to be determined ; the grasping points, grasping forces, regrasping phases, finger allocation and so on. It is difficult to optimize such manipulation parameters for achieving effective manipulation. In this paper, we propose a generation algorithm of regrasping motion for a four-fingered robot hand using Evolutionary Programming (EP). Evolutionary optimization method is generally able to find optimal solutions without supervisor after much iteration, which makes it almost impractical to apply a real robot in online learning process. Therefore we apply the controller generated in numerical simulations to the real robot hand. We show effectiveness of the proposed generation algorithm for the regrasping motion with experimental results.

An algorithm for generating low autocorrelation‐sidelobe skew symmetric binary sequences based on complex exponential functions

AbstractIn the smearing process to suppress impulse noises and the pulse compression in long‐range radar, it is crucial to employ the finite binary sequence which minimizes the sidelobe of the autocorrelation function.This paper proposes a new generation algorithm for the finite binary sequence with a sharp autocorrelation function. The method is based on the fact that the autocorrelation function θ(n) of skew‐symmetric sequence is always zero when n is odd, and the Fourier expansion coefficient sequence of the complex exponential function is an uncorrelated sequence.First, the generating function is derived for the skew‐symmetric real‐valued sequence, for which the Fourier expansion coefficient sequence is an uncorrelated sequence. An algorithm is presented in detail, where the foregoing real‐valued sequence is quantized into a binary sequence, and the binary sequence minimizing the autocorrelation is derived with the finite delay coefficients of the generating function as the variables.In the past, no generation algorithm has been found which can derive the optimal skew‐symmetric binary sequence. It is shown that the proposed generation algorithm can derive all of the optimal skew‐symmetric binary sequence derived by Golay using the exhaustive method. It is shown also that all Barker sequences with off length can be derived.