Traversal Method Research Articles

Identification of accident-injury type and bodypart factors from construction accident reports: A graph-based deep learning framework

Accident reports provide information to understand why and how events occur. Learning from past accident reports is critical for preventing accidents or injuries in construction safety management. However, there are two issues: (1) manual analysis of such accident reports is time-consuming and labor-intensive; and (2) previous research mainly focused on analyzing the causal factors of accidents. Not much research concentrates on the injury effect in an accident and the influential relationship between accident cause and injury effect. To tackle this problem, a graph-based deep learning framework is proposed to identify accident-injury type and bodypart factors automatically to enable managers to make timely and better-informed decisions to prevent accidents and injuries for on-site safety. In this framework, a graph-based deep learning approach (specifically, the Graph Convolutional Network) is developed to automatically classify accident reports labeled with accident_type and injury_type, whereas the traversal method is developed to identify the bodypart factors. To further intuitively visualize these safety risk factors (e.g., accident_type, injury_type, and bodypart factors), the co-occurrence networks are drawn to further intuitively reveal the interdependency in accident-injury and injury-bodypart types respectively. From the perspective of theoretical and practical contributions, the framework proposed in this study not only represents a substantial data-driven advancement in construction accident report classification and keyword extraction tasks, but also enables managers to get knowledge of construction safety performance (i.e., accident causes and injury effects) and further formulate corresponding strategies to prevent accidents and injuries in on-site safety management.

Terrain matching positioning method for underwater vehicles based on curvature discrimination

Terrain matching positioning technology is used to locate underwater vehicles by the terrain information. The traditional method uses all real-time bathymetric points to traverse the underwater prior map, which has a large calculation amount and high complexity. To improve computational efficiency while ensuring accuracy, we represent the terrain matching positioning method based on the local terrain features and the global search technology in this paper. Firstly, the Moving Least Square (MLS) method is used to construct the MLS surface of the multi-beam bathymetric terrain. Then, a shape operator related to the principal curvatures is employed to reflect the curvedness of the MLS surface at each bathymetric point. Next, a Local Curvature Binary Discrimination (LCBD) method is proposed to describe the shape of local MLS surface with a LCBD descriptor, and divide the points satisfying the LCBD situations into the sampling point set. Finally, the Genetic Algorithm (GA) is introduced to replace the traditional traversal method (TM) to search the optimal estimated position of vehicle from the underwater prior map. The experimental results show that the proposed method can quickly locate the vehicle without affecting the accuracy, and the efficiency is improved by more than 80% compared with the traditional method.

Disassemble Byte Sequence Using Graph Attention Network

Disassembly is the basis of static analysis of binary code and is used in malicious code detection, vulnerability mining, software optimization, etc. Disassembly of arbitrary suspicious code blocks (e.g., for suspicious traffic packets intercepted by the network) is a difficult task. Traditional disassembly methods require manual specification of the starting address and cannot automate the disassembly of arbitrary code blocks. In this paper, we propose a disassembly method based on code extension selection network by combining traditional linear sweep and recursive traversal methods. First, each byte of a code block is used as the disassembly start address, and all disassembly results (control flow graphs) are combined into a single flow graph. Then a graph attention network is trained to pick the correct subgraph (control flow graph) as the final result. In the experiment, the compiler-generated executable file, as well as the executable file generated by hand-written assembly code, the data file and the byte sequence intercepted by the code segment were tested, and the disassembly accuracy was 93%, which can effectively distinguish the code from the data.

Editorial

Dear Readers Welcome to the seventh issue in 2022. I am very pleased to announce the journal’s improved Scopus CiteScore of 2.7 and the Web of Science impact factor of 1.056 for 2021, indicating another scientifically successful year. On behalf of the J.UCS team, I would like to thank all the authors for their sound research contributions, the reviewers for their very helpful suggestions, and the consortium members for their financial support. Your commitment and dedicated work have contributed significantly to the long-lasting success of our journal. In this regular issue, I am very pleased to introduce four accepted papers from four different countries and 11 involved authors. Daisy Ferreira Brito, Monalessa P. Barcellos and Gleison Santos from Brazil address in their research a pattern language to support software measurement planning for statistical process control. More specifically, they use the Goal-Question-Metric format and organize it in a Measurement Planning Pattern Language. Ajay Kumar from India presents a hybridized neuro-fuzzy approach for software reliability prediction and validates the proposed approach by applying the neuro-fuzzy method to a software failure dataset. Jesus Serrano-Guerrero, Bashar Alshouha, Francisco P. Romero and Jose A. Olivas from Spain conduct a comparative study of affective knowledge-enhanced emotion detection in Arabic language. Jing Qiu, Feng Dong and Guanglu Sun from China propose and discuss a disassembly method based on a code extension selection network by combining traditional linear sweep and recursive traversal methods.

CRCLoc: A Crowdsourcing-Based Radio Map Construction Method for WiFi Fingerprinting Localization

The WiFi-based fingerprint indoor-positioning system has attracted increasing interest from industry and academia, benefiting from the widespread deployment of the wireless local area network (WLAN) infrastructure. However, with the expansion of application scenarios, this system suffers from labor-intensive work for received signal strength (RSS) fingerprint construction. In this article, we propose a crowdsourcing-based radio map construction method and trajectory matching algorithm to solve the time-consuming preliminary fingerprint data collection in the offline phase, where the tedious collection work is replaced by the massive crowdsourcing sensor data. First, the latent information of the map is extracted by using some image processing methods, and all possible routes are obtained simultaneously with the depth-first traversal method. Then, considering the strict restrictions on walking in indoor environments, the crowdsourcing trajectories are produced by matching the result of pedestrian dead reckoning (PDR) with the candidate routes based on the Shape Context algorithm. Further, a crowdsourcing trajectory can be represented by uniformly distributed reference points based on step detection, and each point corresponds to a unique RSS of access points (APs). Since such a fingerprint construction method can be performed while smartphone holders are moving and not aware of their actual positions, it can be referred to the dynamic construction method of the radio map. The real scenario experiments reveal that the proposed solution can significantly reduce the time and manpower consumption to build the radio map. Moreover, compared with traditional schemes, our crowdsourcing-based radio map construction method for the WiFi fingerprinting localization (CRCLoc) system can improve the accuracy and robustness of the indoor-positioning results.

Multithreaded wedge detection method on triangular 3D CAD objects using mesh traversal method

In this study, a multithreaded method for triangular mesh three-dimensional computer aided design objects is proposed to detect and extract wedges. Wedge detection is time consuming process for such objects that have large number of facets. To take the advantage of parallel computing opportunities, the algorithm is refactored in this study. Scope of variables, memory management and stack use are optimized for efficient use of computational resources. The proposed method is focused to calculation efficiency and performance on multicore / multithreaded processors and it is evaluated with benchmark, complex and realistic objects.

The traversal method for user address space in Windows 10 system based on VAD tree

The existing traversal method for user address space in the memory forensic research is only applicable to Windows XP and Windows 7 32-bit system. Windows 10 64-bit system is currently used by most users, which is the main target of network attackers. A method to traverse Windows 10 user address space based on VAD(virtual address descriptor) tree is proposed. The memory kernel and user address space metadata of Windows 10 64-bit system was located. The related metadata such as mapping files, shared memory, heap, stack and reserved system structures were parsed and matched with the information in VAD tree nodes. The starting address, ending address, used size, allocating protection, memory type and details of each memory area were output. The results show that the method is compatible with all versions of Windows 10 64-bit system and can effectively traverse common structures when dealing with processes with different complexity.

Short-circuit calculation method for unbalanced distribution networks with doubly fed induction generators

In an unbalanced distribution network, transforming three-phase unbalanced components into components with positive, negative, and zero sequences is difficult. Moreover, the fault currents of doubly fed induction generators (DFIGs) exhibit a complex nonlinear relationship. The fault characteristics of DFIGs with an activated crowbar differ from those with a non-activated crowbar. Moreover, distinguishing between these two crowbar conditions based on calculations is difficult. Therefore, the traditional symmetric component method is unsuitable for unbalanced distribution networks with DFIGs owing to its low calculation accuracy. In this work, the equivalent calculation phase component models of DFIGs are analyzed using low-voltage control strategies. In particular, the activation criterion of crowbar protection in the time domain is proposed. A novel fault analysis method for unbalanced distribution networks with DFIGs is also proposed. The action condition of crowbar protection is assessed using the traversal method, and the coupling relationship among DFIGs is determined using an iterative calculation method. Finally, the effectiveness of the proposed fault analysis method is verified by simulation.

An improved embedded discrete fracture model and domain connectivity algorithms on 3D unstructured grids

Numerical simulation in 3D complex fractured media is challenging as the geometric discretization of porous media and fracture domains is on multiple scales. In this paper, we present an improved embedded discrete fracture model (EDFM) for 3D unstructured non-matching grids, and correspondingly efficient and robust domain connectivity algorithms are developed. Unlike traditional EDFM, improved EDFM is capable to simulate flows on 3D staggered overlapping unstructured matrix and fracture grids. We illustrate flux exchange patterns and formulas of improved EDFM. Two types of domain connectivity are built to assemble hybrid dimensional overlapping grids of matrix and fracture domains to a coupled linear system using finite volume method. Building domain connectivity is an important challenge for 3D hybrid-dimensional unstructured non-matching grids. We classify all points of domain connectivity into three types. A face indexed octree is employed for spatial binary search. Two types of grid adjacency information are used to accelerate the calculation of grid intersection points. Fracture-matrix intersection information is adopted to accelerate fracture-fracture connectivity generation. The performance of the algorithms is tested by 8 cases in different scales and compared with traversal method. Improved EDFM is validated against discrete fracture model and traditional EDFM using a two-phase flow solver. A case with highly complex fracture network is simulated to demonstrate the capacity of improved EDFM in real complex physical problems. The effects of grid type and resolution are also analyzed in this work.

Reachable domain with a single coplanar impulse considering the target-visit constraint

This paper proposes a simple numerical method to solve the spacecraft reachable domain problem with a single coplanar impulse considering the target-visit constraint and the impulse-magnitude constraint. The target-visit constraint here is considered as the same position vector for the chaser and the target. Three cases are analyzed for either impulse time or visit time being free, or both being free. Firstly, for the impulse-magnitude constraint, the feasible ranges of impulse time and visit time are obtained based on Kepler’s equation. Then, by using the Lambert solution, the extreme-value problems of all three cases are transformed into solving the roots of a single- or two-variable function, which are obtained by numerical methods. Finally, the envelopes of reachable domain are obtained by comparing the extreme values and the boundary values in the feasible ranges. Numerical examples verify the correctness and the effectiveness of the proposed methods by comparing with the traditional Lambert traversal method.

Single-Shot Diffraction Autofocusing: Distance Prediction via an Untrained Physics-Enhanced Network

Deep learning technology has shown excellent performances and successful applications in optical information processing. However, the long-time training, large amount of manually labeled data and generalization capability hinder the application of deep neural network (DNN) under supervised learning. The deep image prior (DIP) opinion promotes the development of untrained neural network, which can learn from one image. Here we propose a DIP-based strategy to nest the DNN into a physical model for finding the optimal solution in a univariate optimization problem. The untrained physics-enhanced network (UPN) is proposed to predict the diffraction distance via only one diffraction pattern of a known phase object. Simulation and experimental results show that the UPN can be used to predict the distance precisely and consistently with different targets, diffraction distances as well as phase ranges, while it only takes a little time for training. In addition, the trained UPN can generalize to the other targets as long as the actual diffraction process keeps the same. Compared with the autofocusing metrics of holographic reconstruction and traversal method, the UPN has advantages in speed and accuracy, and it also has good noise resistance, which are all meaningful for the autofocusing of holographic reconstruction and imaging.

Determination of the key parameters of VOCs emitted from multi-layer leather furniture using a region traversal approach

Volatile organic compounds (VOCs) emitted from indoor materials and products are one of the main factors affecting air quality and human health. Compared with building materials and wooden furniture, leather furniture has a more complex internal structure and uneven emission surfaces. The market share of leather furniture is relatively high, while investigation on this kind of furniture is relatively rare. In this study, we develop a region traversal method to measure the three key parameters of VOC emissions from typical two-layer leather furniture, i.e., the initial emittable concentration, the diffusion coefficient, and the partition coefficient. A series of experiments examining VOC emissions from a leather sofa under different conditions, were carried out in a 1 m3 chamber. This method locks the upper and lower limits of an optimal solution through loop calculation in parameter intervals, and demonstrates high accuracy, efficiency and robustness. The good agreement (R2 > 0.95) between model predictions and experimental data confirms the reliability of this method. In addition, the influence of temperature and air exchange rate on the key parameters is explored. Results indicate that, increasing the temperature leads to an increase in Dm and a decrease in K, and that air exchange rate does not affect the key parameters, which is consistent with physical principles. The region traversal method is further applied to analyze the emission scenarios for other furniture, which is very helpful for indoor air quality pre-evaluation.

Determining the maximal inscribed rectangle of an irregularly shaped stone using machine vision

ABSTRACT This study uses machine vision approaches to develop a rotation histogram method with better area utilization and shorter execution time that automatically determines the maximal inscribed rectangle of an irregularly shaped stone. This image processing procedure is designed to enhance the stone image, reduce the contour noise, determine the stone contour and the calculation range of the computational algorithm, and speed up the determination of the maximal inscribed rectangle of irregularly shaped stones. The rotation histogram method transforms to a histogram the stone image after-image processing, and then uses the stack method to determine the maximal rectangle of the histogram. Finally, the stone image is rotated to determine the maximal inscribed rectangle and angle of the irregularly shaped stone. The rotation histogram method is applicable to irregularly shaped stones with internal voids, and the area utilization of the stone will not be influenced by the placement orientation. The experimental results show that the rotation histogram method, as designed in this study, not only increases the area utilization for achieving the average value of 3.27%, but it also significantly shortens the execution time to achieve an average value of 64.83% compared with the existing traversal center diffusion method.

Two Approaches for Recognizing the Structure of Block Diagrams

Introduction. Working with graphic images is an essential element of almost any modern computer-aided design systems. The result of neural network, including deep image processing, can be recognition of the belonging classes of objects present on them. Objects of the real world require large expenditures for the development and implementation of highly specialized computer vision systems. In recent years, there has been an improvement of the quality characteristics obtained in the field of technical vision. This is made possible by artificial neural networks. The article deals with the recognition of a flat, black and white flowchart image. These are two-dimensional images or their selected parts, which are displayed in an arbitrary graphic format by system means on a computer monitor screen. Basic block diagram shapes: rectangle, rhombus, parallelogram, circle, ellipse (oval), etc. The purpose of the article is to solve the problem of graphic image recognition. The systems for the recognition of graphic images include modern systems of computer-aided design, management and document management. The article has formed a basic set of training and test images of block diagram nodes. Neural network models are proposed to improve the detection accuracy of block diagram nodes based on fully connected and convolutional neural networks. Results. The basic procedures of the block diagram image recognition algorithm were partially tested at the software level, and allow us to conclude the effectiveness of the proposed structural methods. A comparative analysis of neural network and syntactic structural approaches for solving this problem is carried out. Conclusions. Two methods of recognizing flat graphic figures and recognizing connections between figures in flowcharts are proposed: a method of recursive traversal of all branches of the tree of the current union of connections between figures and the figures themselves, and also a study was carried out for the created neural network in PyTorch to solve this problem using trained neural network methods. Keywords: image recognition, convolutional neural networks, syntactic analysis.

Partial transmit sequence based on discrete particle swarm optimization with threshold about PAPR reduction in FBMC/OQAM system

Partial transmit sequence (PTS) is an effective method to reduce the peak-to-average power ratio (PAPR) of orthogonal frequency division multiplexing (OFDM) system, but it is not suitable for the filter bank multi-carrier with offset quadrature amplitude modulation (FBMC/OQAM) system because of the overlapping structure of FBMC/OQAM signals. And PTS needs the traversal method to search for the optimal solution, which will increase the complexity of the system. To overcome this shortcoming, a PTS based on discrete particle swarm optimization with threshold (PTS-DPSO-TH) is proposed and applied to FBMC/OQAM system in this paper. PTS-DPSO-TH uses discrete particle swarm optimization (DPSO) to search for the optimal solution, effectively reducing the excessively high PAPR of the FBMC/OQAM system and avoiding the increase of system complexity. Secondly, the threshold is introduced to decrease the number of iterations and further reduce the system's complexity on the premise of guaranteeing the performance of PAPR reduction. Furthermore, through simulation, the effects of multiple parameters on PAPR reduction performance of PTS-DPSO-TH are compared and analysed.

Fundamentals of a Novel Debugging Mechanism for Orchestrated Cloud Infrastructures with Macrosteps and Active Control

In Infrastructure-as-a-Service (IaaS) clouds, the development process of a ready-to-use and reliable infrastructure might be a complex task due to the interconnected and dependent services that are deployed (and operated later on) in a concurrent way on virtual machines. Different timing conditions may change the overall initialisation method, which can lead to abnormal behaviour or failure in the non-deterministic environment. The overall motivation of our research is to improve the reliability of cloud-based infrastructures with minimal user interactions and significantly accelerate the time-consuming debugging process. This paper focuses on the behaviour of cloud-based infrastructures during their deployment phase and introduces the adaption of a replay, and active control enriched debugging technique, called macrostep, in the field of cloud orchestration in order to provide support for developers troubleshooting deployment-related errors. The fundamental macrostep mechanisms, including the generation of collective breakpoint sets as well as the traversal method for such consistent global states, have been combined with the Occopus cloud orchestrator and the Neo4J graph database. The paper describes the novel approach, the design choices as well as the implementation of the experimental debugger tool with a use case for validation purposes by providing some preliminary numerical results.

A binary discrete particle swarm optimization satellite selection algorithm with a queen informant for Multi-GNSS continuous positioning

Currently, there are more than 130 available navigation satellites, a much larger scale low earth orbit (LEO) satellites will be deployed in the near future. However, limited by computational performance, capacity and receiver channels, a subset of all visible satellites is suggested to be selected with a with better geometric dilution of precision (GDOP). Since a reduced set of used satellite will have little effect on positioning accuracy, in contrast, higher real-time performance will be obtained. In view of the problems of the particle swarm optimization (PSO) algorithm for satellites selection, we adopt an easy binary particle swarm optimization with a queen informant (EPSOq) algorithm. This avoids the concept of “speed” in the discrete PSO algorithm and directly calculates the probability of position value when updating particles, with a queen particle used to accelerate convergence. Further, considering the continuity of positioning, we use a sequence to determine whether satellite re-selection is necessary. If the visible satellite has not changed greatly, the results of the last satellite selection is used instead of selecting new satellites. The observation data collected in the East China Sea is utilized in the experiment. Compared with the traversal method which requires 51.215 s, the average calculation time of EPSOq-C is only 0.0025 s with a population size of 70, and the calculation speed is an order of magnitude faster than the PSO algorithm. Furthermore, the distribution of GDOP bias derived from EPSOq-C is more concentrated than the PSO algorithm.

Improving Ponzi Scheme Contract Detection Using Multi-Channel TextCNN and Transformer.

With the development of blockchain technologies, many Ponzi schemes disguise themselves under the veil of smart contracts. The Ponzi scheme contracts cause serious financial losses, which has a bad effect on the blockchain. Existing Ponzi scheme contract detection studies have mainly focused on extracting hand-crafted features and training a machine learning classifier to detect Ponzi scheme contracts. However, the hand-crafted features cannot capture the structural and semantic feature of the source code. Therefore, in this study, we propose a Ponzi scheme contract detection method called MTCformer (Multi-channel Text Convolutional Neural Networks and Transofrmer). In order to reserve the structural information of the source code, the MTCformer first converts the Syntax Tree (AST) of the smart contract code to the specially formatted code token sequence via the Structure-Based Traversal (SBT) method. Then, the MTCformer uses multi-channel TextCNN (Text Convolutional Neural Networks) to learn local structural and semantic features from the code token sequence. Next, the MTCformer employs the Transformer to capture the long-range dependencies of code tokens. Finally, a fully connected neural network with a cost-sensitive loss function in the MTCformer is used for classification. The experimental results show that the MTCformer is superior to the state-of-the-art methods and its variants in Ponzi scheme contract detection.

Land classification based on high resolution remote sensing images

Land information is an important information related to the timely adjustment of land management policy, which can significantly improve the efficiency of land management. The traditional land information collection completely depends on field survey of grass-roots personnel, which is not only time-consuming and laborious but also can not guarantee the accuracy of information. With the rapid development of remote sensing technology, using remote sensing image to obtain land information is an important means to conduct land investigation and detect whether crop planting area is up to the standard. At present, the method of artificial neural network (ANN) learning classification has achieved great success in the land classification, but there is still room for improvement in the classification accuracy. In this paper, a new Algorithm is introduced-shuffled frog leaping algorithm (SFLA), the important parameters of ANN are optimized. The traditional traversal method is improved to a combination of global optimization and local optimization, which can effectively reduce the search time, increase the generalization ability of the model and improve the classification accuracy. Through the experiment of remote sensing data of Fengqi town, Luochuan county, Yan’an city, Shaanxi province, it is shown that SFLA can effectively increase the accuracy of ANN in land information classification. It has achieved the paper research goal.

Interference-Aware Online Multicomponent Service Placement in Edge Cloud Networks and its AI Application

Edge computing that utilizes ubiquitous edge devices locating in close proximity to users is powerful for providing Quality of Service guaranteed computation offloading services. Toward the limited resources of edge servers and wireless links, large services can be split into multiple interconnected components to be served by multiple edge servers cooperatively. The current works on service placement either assume unsplittable services or ignore the geographically isolated property of edge servers. They also ignore the interference among online services that share the same physical nodes/links in terms of executing delay. Namely, every service adds load to the placed nodes/links and every increment on load of nodes/links risks delay violation of existing services. To overcome above challenges, this article emphasizes on the interference-aware (IA) online multicomponent service placement in edge cloud networks. First, the delay of tree-like services is analyzed considering the dependency among components, based on which the IA residual capacities of physical nodes, links, and paths are defined and formulated theoretically. Furthermore, we reduce the problem of multicomponent service placement to be NP-hard and transform it into an ant colony optimization (ACO) problem to obtain the near-optimal solution. More importantly, a level traversal component ranking method and an IA dynamic pruning method are proposed for ACO to achieve faster convergence, interference awareness, and higher acceptance ratio of services. Simulation results are presented to validate the effectiveness of proposed methods. In addition, the classic artificial intelligence application of image classification is experimented to further strength the motivation of IA investigation in practical.