Search

To better prevent the potential risks in Internet-based Supply Chain Financing (SCF) products, this paper optimizes and evaluates the Internet-based SCF-oriented Credit Risk Evaluation (CRE) method. Firstly, this paper summarizes 12 risk factors of SCF business, establishes a Risk Assessment Index System (RAIS) with good consistency and stability; then, the principles of Backpropagation (BP) Neural Network (NN) is expounded together with Support Vector Machines (SVM) and Genetic Algorithm (GA) model. Consequently, a CRE model is implemented by the NN tools in MATLAB based on the collection of multiple groups of SCF-oriented risk assessment samples. Subsequently, the assessment samples are trained and tested. Finally, the SCF-oriented CRE model is proposed and verified. The results show that the BP-GA model has presented high prediction consistency with the actual classification. According to the comparison of classification results of SVM, BP model, and BP-GA model, the classification accuracy of test samples of the proposed Internet-based SCF-oriented CRE system using BP-GA model reaches 97.19%; the Type I and Type II error rate of the CRE system based on BP-GA model is 7.2% and 14.21%, respectively. Therefore, a suitable SCF-oriented CRE method is put forward for China’s commercial banks along with scientific and feasible suggestions to manage SCF-oriented credit risks more reasonably and effectively.

PurposeThe aim of the paper is to identify management practices that are characteristic for SMEs that achieve market success measured by their business performance in last their years of their operation analyze the relationships between management practices applied in small and medium-sized enterprises and their success measured by their business performance drawing on the data from 2710 SMEs operating on the Polish market.Approach/Methodology/DesignA cluster analysis was used to distinguish homogenous SME groups in view of their management practices. We examined differences between groups in terms of their business performance. The HINoV algorithm allowed six variables to be selected out of 32 management practices chosen initially for testing, with these variables providing the basis for grouping. Modal values and medians were calculated for 17 business performance measures in the three clusters produced. The subsequent analysis of those findings was focused on capturing significant differences.FindingsIn the group of 2710 Polish SMEs, it was possible to verify that there existed an association between management practices in the field of modern HRM, computer systems supporting management and the company’s economic performance, as measured by an increase in net revenue and number of customers over the last three years. In clusters where the above mentioned practices were appreciated, modal and median values of the increase reported in net revenue and number of customers were significantly higher.Practical implicationsThe research has shown that at a time marked by a shortage of highly skilled personnel one should pay particular attention to building an integrated and committed team of workers and to employee empowerment. The research has also shown that SME managers monitor only a fraction of basic business performance measures, which may prove to be a major risk to SMEs.Originality/ValuePrevious studies have been largely conducted in a fragmentary manner, i.e. they were concerned with the relationships between the application of some practices (strategic management, BPR, entrepreneurial orientation, monitoring, etc.) and selected business effectiveness measures. In this paper, the research covered SME management practices from a variety of areas which were then compared with the entrepreneurs’ assessment as to whether the company’s economic condition changed over the last three years. It is also the first attempt in post-socialist economies to identify those SME management practices that are related to better economic results.

When keystroke dynamics are used for authentication, users tend to get different levels of security due to differences in the quality of their templates. This paper addresses this issue by proposing a metric to quantify the quality of keystroke dynamic templates. That is, in behavioral biometric verification, the user’s templates are generally constructed using multiple enrolled samples to capture intra-user variation. This variation is then used to normalize the distance between a set of enrolled samples and a test sample. Then a normalized distance is compared against a predefined threshold value to derive a verification decision. As a result, the coverage area for accepted samples in the original space of vector representation is discrete. Therefore, users with the higher intra-user variation suffer higher false acceptance rates (FAR). This paper proposes a metric that can be used to reflect the verification performance of individual keystroke dynamic templates in terms of FAR. Specifically, the metric is derived from statistical information of user-specific feature variations, and it has a non-decreasing property when a new feature is added to a template. The experiments are performed based on two public keystroke dynamic datasets comprising of two main types of keystroke dynamics: constrained-text and free-text, namely the CMU keystroke dynamics dataset and the Web-Based Benchmark for keystroke dynamics dataset. Experimental results based on multiple classifiers demonstrate that the proposed metric can be a good indicator of the template’s false acceptance rate. Thus, it can be used to enhance the security of the user authentication system based on keystroke dynamics.

Grounding systems are critical in safeguarding people and equipment from power system failures. A grounding system’s principal goal is to offer the lowest impedance path for undesired fault current. Optimization of the grounding grid designs is important in satisfying the minimum cost of the grounding system and safeguarding those people who work in the surrounding area of the grounded installations. Currently, there is no systematic guidance or standard for grounding grid designs that include two-layer soil and its effects on grounding grid systems, particularly vertically layered soil. Furthermore, while numerous studies have been conducted on optimization, relatively limited study has been done on the problem of optimizing the grounding grid in two-layer soil, particularly in vertical soil structures. This paper presents the results of optimization for substation grounding systems using the Simulated Annealing (SA) algorithm in different soil conditions which conforms to the safety requirements of the grounding system. Practical features of grounding grids in various soil conditions discussed in this paper (uniform soil, two-layer horizontal soil, and two-layer vertical soil) are considered during problem formulation and solution algorithm. The proposed algorithm’s results show that the number of grid conductors in the X and Y directions (Nx and Ny), as well as vertical rods (Nr), can be optimized from initial numbers of 35% for uniform soil, 57% for horizontal two-layer soil for ρ1> ρ2, and 33% for horizontal two-layer soil for ρ1< ρ2, and 29% for vertical two-layer soil structure. In other words, the proposed technique would be able to utilize square and rectangle-shaped grounding grids with a number of grid conductors and vertical rods to be implemented in uniform, two-layer horizontal and vertical soil structure, depending on the resistivity of the soil layer.

At present, the rapier loom has gradually become the mainstream equipment in the manufacturing industry. In order to make the rapier loom realize automated production and further improve the production efficiency of the rapier loom, improve the programmability of the system, and reduce the cost of system maintenance. The thesis developed a rapier loom control system based on embedded soft PLC, and carried out experiments and applications in the field. The contribution and innovation of this paper is to develop a complete low-cost control system, and through a genetic algorithm optimized PID algorithm to complete the more effective control of the loom tension system. The embedded soft PLC system proposed in this paper reduces the overall maintenance cost of the system and improves the programmability of the system. This text carries on the systematic scheme design to the embedded soft PLC from the hardware system and the software system respectively. First, according to the actual requirements, this article designs the overall scheme of the embedded software PLC hardware system with STM32F407ZGT6 as the core. Then this article is based on the embedded soft PLC hardware platform, according to the international standard of industrial control programming, writes the embedded soft PLC low-level driver software. Secondly, this article analyzes the factors that affect the warp tension during the operation of the rapier loom, and proposes the use of genetic algorithm to optimize the warp tension control method of the traditional PID algorithm. Finally, we conducted verification tests and on-site application debugging for the entire set of rapier loom embedded soft PLC control system. We controlled the warp tension as the main experimental object. The results show that this control system effectively improves the control accuracy of the warp tension of the rapier loom and meets the actual needs of industrial applications. The whole system has a good application prospect in the warp tension control of rapier looms.

Background As the world’s largest coal producer, China was accounted for about 46% of global coal production. Among present coal mining risks, methane gas (called gas in this paper) explosion or ignition in an underground mine remains ever-present. Although many techniques have been used, gas accidents associated with the complex elements of underground gassy mines need more robust monitoring or warning systems to identify risks. This paper aimed to determine which single method between the PCA and Entropy methods better establishes a responsive weighted indexing measurement to improve coal mining safety. Methods Qualitative and quantitative mixed research methodologies were adopted for this research, including analysis of two case studies, correlation analysis, and comparative analysis. The literature reviewed the most-used multi-criteria decision making (MCDM) methods, including subjective methods and objective methods. The advantages and disadvantages of each MCDM method were briefly discussed. One more round literature review was conducted to search publications between 2017 and 2019 in CNKI. Followed two case studies, correlation analysis and comparative analysis were then conducted. Research ethics was approved by the Shanxi Coking Coal Group Research Committee. Results The literature searched a total of 25,831publications and found that the PCA method was the predominant method adopted, and the Entropy method was the second most widely adopted method. Two weighting methods were compared using two case studies. For the comparative analysis of Case Study 1, the PCA method appeared to be more responsive than the Entropy. For Case Study 2, the Entropy method is more responsive than the PCA. As a result, both methods were adopted for different cases in the case study mine and finally deployed for user acceptance testing on 5 November 2020. Conclusions The findings and suggestions were provided as further scopes for further research. This research indicated that no single method could be adopted as the better option for establishing indexing measurement in all cases. The practical implication suggests that comparative analysis should always be conducted on each case and determine the appropriate weighting method to the relevant case. This research recommended that the PCA method was a dimension reduction technique that could be handy for identifying the critical variables or factors and effectively used in hazard, risk, and emergency assessment. The PCA method might also be well-applied for developing predicting and forecasting systems as it was sensitive to outliers. The Entropy method might be suitable for all the cases requiring the MCDM. There is also a need to conduct further research to probe the causal reasons why the PCA and Entropy methods were applied to each case and not the other way round. This research found that the Entropy method provides higher accuracy than the PCA method. This research also found that the Entropy method demonstrated to assess the weights of the higher dimension dataset was higher sensitivity than the lower dimensions. Finally, the comprehensive analysis indicates a need to explore a more responsive method for establishing a weighted indexing measurement for warning applications in hazard, risk, and emergency assessments.

With the increase of patients with retinopathy, retinopathy recognition has become a research hotspot. In this article, we describe the etiology and symptoms of three kinds of retinal diseases, including drusen(DRUSEN), choroidal neovascularization(CNV) and diabetic macular edema(DME). In addition, we also propose a hybrid attention mechanism to classify and recognize different types of retinopathy images. In particular, the hybrid attention mechanism proposed in this paper includes parallel spatial attention mechanism and channel attention mechanism. It can extract the key features in the channel dimension and spatial dimension of retinopathy images, and reduce the negative impact of background information on classification results. The experimental results show that the hybrid attention mechanism proposed in this paper can better assist the network to focus on extracting thr fetures of the retinopathy area and enhance the adaptability to the differences of different data sets. Finally, the hybrid attention mechanism achieved 96.5% and 99.76% classification accuracy on two public OCT data sets of retinopathy, respectively.

In this paper, the algebraic topological characteristics of brain networks composed of electroencephalogram(EEG) signals induced by different quality images were studied, and on that basis, a neurophysiological image quality assessment approach was proposed. Our approach acquired quality perception-related neural information via integrating the EEG collection with conventional image assessment procedures, and the physiologically meaningful brain responses to different distortion-level images were obtained by topological data analysis. According to the validation experiment results, statistically significant discrepancies of the algebraic topological characteristics of EEG data evoked by a clear image compared to that of an unclear image are observed in several frequency bands, especially in the beta band. Furthermore, the phase transition difference of brain network caused by JPEG compression is more significant, indicating that humans are more sensitive to JPEG compression other than Gaussian blur. In general, the algebraic topological characteristics of EEG signals evoked by distorted images were investigated in this paper, which contributes to the study of neurophysiological assessment of image quality.

E-documents are carriers of sensitive data, and their security in the open network environment has always been a common problem with the field of data security. Based on the use of encryption schemes to construct secure access control, this paper proposes a fusion data security protection scheme. This scheme realizes the safe storage of data and keys by designing a hybrid symmetric encryption algorithm, a data security deletion algorithm, and a key separation storage method. The scheme also uses file filter driver technology to design a user operation state monitoring method to realize real-time monitoring of user access behavior. In addition, this paper designs and implements a prototype system. Through the verification and analysis of its usability and security, it is proved that the solution can meet the data security protection requirements of sensitive E-documents in the open network environment.

A query optimizer attempts to predict a performance metric based on the amount of time elapsed. Theoretically, this would necessitate the creation of a significant overhead on the core engine to provide the necessary query optimizing statistics. Machine learning is increasingly being used to improve query performance by incorporating regression models. To predict the response time for a query, most query performance approaches rely on DBMS optimizing statistics and the cost estimation of each operator in the query execution plan, which also focuses on resource utilization (CPU, I/O). Modeling query features is thus a critical step in developing a robust query performance prediction model. In this paper, we propose a new framework based on query feature modeling and ensemble learning to predict query performance and use this framework as a query performance predictor simulator to optimize the query features that influence query performance. In query feature modeling, we propose five dimensions used to model query features. The query features dimensions are syntax, hardware, software, data architecture, and historical performance logs. These features will be based on developing training datasets for the performance prediction model that employs the ensemble learning model. As a result, ensemble learning leverages the query performance prediction problem to deal with missing values. Handling overfitting via regularization. The section on experimental work will go over how to use the proposed framework in experimental work. The training dataset in this paper is made up of performance data logs from various real-world environments. The outcomes were compared to show the difference between the actual and expected performance of the proposed prediction model. Empirical work shows the effectiveness of the proposed approach compared to related work.

Fake news is a complex problem that leads to different approaches used to identify them. In our paper, we focus on identifying fake news using its content. The used dataset containing fake and real news was pre-processed using syntactic analysis. Dependency grammar methods were used for the sentences of the dataset and based on them the importance of each word within the sentence was determined. This information about the importance of words in sentences was utilized to create the input vectors for classifications. The paper aims to find out whether it is possible to use the dependency grammar to improve the classification of fake news. We compared these methods with the TfIdf method. The results show that it is possible to use the dependency grammar information with acceptable accuracy for the classification of fake news. An important finding is that the dependency grammar can improve existing techniques. We have improved the traditional TfIdf technique in our experiment.

Improving travel time prediction for public transit effectively enhances service reliability, optimizes travel structure, and alleviates traffic problems. Its greater time-variance and uncertainty make predictions for short travel times (≤35min) more subject to be influenced by random factors. It requires higher precision and is more complicated than long-term predictions. Effectively extracting and mining real-time, accurate, reliable, and low-cost multi-source data such as GPS, AFC, and IC can provide data support for travel time prediction. Kalman filter model has high accuracy in one-step prediction and can be used to calculate a large amount of data. This paper adopts the Kalman filter as a travel time prediction model for a single bus based on single-line detection: including the travel time prediction model of route (RTM) and the stop dwell time prediction model (DTM); the evaluation criteria and indexes of the models are given. The error analysis of the prediction results is carried out based on AVL data by case study. Results show that under the precondition of multi-source data, the public transportation prediction model can meet the accuracy requirement for travel time prediction and the prediction effect of the whole route is superior to that of the route segment between stops.

Transport layer security (TLS) protocol is the most widely used security protocol in modern network communications. However, protocol vulnerabilities caused by the design of the network protocol or its implementation by programmers emerge one after another. Meanwhile, various versions of TLS protocol implementations exhibit different behavioral characteristics. Researchers are attempting to find the differences in protocol implementations based on differential testing, which is conducive to discovering the vulnerabilities. This paper provides a solution to find the differences more efficiently by targeting the TLS protocol handshake process. The differences of different implementations during the fuzzing process, such as code coverage and response data, are taken to guide the mutation of test cases, and the seeds are mutated based on the TLS protocol syntax. In addition, the definition of duplicate discrepancies is theoretically explored to investigate the root cause of the discrepancies and to reduce the number of duplicate cases that are caused by the same reason. Besides, the necessary conditions for excluding duplicate cases are further analyzed to develop the deduplication strategy. The proposed method is developed based on open-source tools, i.e., NEZHA and TLS-diff. Three types of widely used TLS protocol implementations, i.e., OpenSSL, BoringSSL, and LibreSSL, are taken for experimental testing. The experimental results show that the proposed method can effectively improve the ability to find differences between different implementations. Under the same test scale or the same time, the amount of discrepancies increases by about 20% compared to TLS-diff, indicating the effectiveness of the deduplication strategy.

In this paper, a Markovian model is constructed to test a flexible manufacturing cell’s (FMC) performance. The considered FMC includes a conveyer belt, robot, and n machines. The conveyer belt delivers the working part to the robot, and the robot picks it up and loads it onto the machines. The movement of a working part from one step to the next depends on the availability of the tool in the next step (i.e., conveyer belt, robot, and machine). Any machine is assumed to potentially fail during the processing time as a result of high loading stresses. First, a Markovian model is constructed for single-machine and double-machine FMCs. Then, a generalized FMC with an n-machine is constructed. The introduced model is illustrated with two numerical examples for both the single- and triple-machine. The Markov chain model can be used to estimate the FMC performance measures (i.e., overall utilization of machines and production rate). It is used to analyze the response of these measures under varying parameters (i.e., conveyor belt delivery rate, robot loading rate, processing rate of a machine, failure rate of a machine, and down machines’ repairing rate). Moreover, an economic model based on the Markov chain model is introduced to analyze the FMC’s net profit under these varying parameters.

Real-time ride-sharing has become popular in recent years. However, the underlying optimization problem for this service is highly complex. One of the most critical challenges when solving the problem is solution quality and computation time, especially in large-scale problems where the number of received requests is huge. In this paper, we rely on an exact solving method to ensure the quality of the solution, while using AI-based techniques to limit the number of requests that we feed to the solver. More precisely, we propose a clustering method based on a new shareability function to put the most shareable trips inside separate clusters. Previous studies only consider Spatio-temporal dependencies to do clustering on the mobility service requests, which is not efficient in finding the shareable trips. Here, we define the shareability function to consider all the different sharing states for each pair of trips. Each cluster is then managed with a proposed heuristic framework in order to solve the matching problem inside each cluster. As the method favors sharing, we present the number of sharing constraints to allow the service to choose the number of shared trips. To validate our proposal, we employ the proposed method on the network of Lyon city in France, with half-million requests in the morning peak from 6 to 10 AM. The results demonstrate that the algorithm can provide high-quality solutions in a short time for large-scale problems. The proposed clustering method can also be used for different mobility service problems such as car-sharing, bike-sharing, etc.

Instance segmentation is more challenging and difficult than object detection and semantic segmentation. It paves the way for the realization of a complete scene understanding, and has been widely used in robotics, automatic driving, medical care, and other aspects. However, there are some problems in instance segmentation methods, such as the low detection efficiency for low-resolution objects and the slow detection speed of images with complex backgrounds. To solve these problems, this paper proposes an instance segmentation method with multi-scale attention, which is called a Hybrid Kernel Mask R-CNN. Firstly, the hybrid convolution kernel is constructed by combining different kernels and groups, which can complement each other to extract rich information. Secondly, a multi-scale attention mechanism is designed by assign weights to different convolution kernels, which can retain more important information. After the introduction of our strategy, the network is more inclined to focus on the low-resolution objects in the image. The proposed method achieves the best accuracy over the anchor-based method. To verify the universality of the model, we test Hybrid Kernel Mask R-CNN on Balloon, xBD and COCO datasets. The test results exceed the state of art methods. And the visualization results show our method can extract low-resolution objects effectively.

To undertake a reliable analysis of injury severity in road traffic accidents, a complete understanding of important attributes is essential. As a result of the shift from traditional statistical parametric procedures to computer-aided methods, machine learning approaches have become an important aspect in predicting the severity of road traffic injuries. The paper presents a hybrid feature selection-based machine learning classification approach for detecting significant attributes and predicting injury severity in single and multiple-vehicle accidents. To begin, we employed a Random Forests (RF) classifier in conjunction with an intrinsic wrapper-based feature selection approach called the Boruta Algorithm (BA) to find the relevant important attributes that determine injury severity. The influential attributes were then fed into a set of four classifiers to accurately predict injury severity (Naive Bayes (NB), K-Nearest Neighbor (K-NN), Binary Logistic Regression (BLR), and Extreme Gradient Boosting (XGBoost)). According to BA’s experimental investigation, the vehicle type was the most influential factor, followed by the month of the year, the driver’s age, and the alignment of the road segment. The driver’s gender, the presence of a median, and the presence of a shoulder were all found to be unimportant. According to classifier performance measures, XGBoost surpasses the other classifiers in terms of prediction performance. Using the specified attributes, the accuracy, Cohen’s Kappa, F1-Measure, and AUC-ROC values of the XGBoost were 82.10%, 0.607, 0.776, and 0.880 for single vehicle accidents and 79.52%, 0.569, 0.752, and 0.86 for multiple-vehicle accidents, respectively.

Made available in DSpace on 2022-04-28T19:49:42Z (GMT). No. of bitstreams: 0 Previous issue date: 2022-01-01 Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) Several studies have reported the relationship of deforestation with increased incidence of infectious diseases, mainly due to the deregulation caused in these environments. The purpose of this study was to answer the following questions: a) is increased loss of vegetation related to dengue cases in the Brazilian Cerrado? b) how do different regions of the tropical savanna biome present distinct patterns for total dengue cases and vegetation loss? c) what is the projection of a future scenario of deforestation and an increased number of dengue cases in 2030? Thus, this study aimed to assess the relationship between loss of native vegetation in the Cerrado and dengue infection. In this paper, we quantify the entire deforested area and dengue infection cases from 2001 to 2019. For data analyses, we used Poisson generalized linear model, descriptive statistics, cluster analysis, non-parametric statistics, and autoregressive integrated moving average (ARIMA) models to predict loss of vegetation and fever dengue cases for the next decade. Cluster analysis revealed the formation of four clusters among the states. Our results showed significant increases in loss of native vegetation in all states, with the exception of Piauí. As for dengue cases, there were increases in the states of Minas Gerais, São Paulo, and Mato Grosso. Based on projections for 2030, Minas Gerais will register about 4,000 dengue cases per 100,000 inhabitants, São Paulo 750 dengue cases per 100,000 inhabitants, and Mato Grosso 500 dengue cases per 100,000 inhabitants. To reduce these projections, Brazil will need to control deforestation and implement public health, environmental and social policies, requiring a joint effort from all spheres of society. Graduate Program in Agronomy–Cropping Systems São Paulo State University (Unesp), SP Graduate Program in Geography São Paulo State University (Unesp) School of Technology and Sciences, SP Federal University of Mato Grosso do Sul (UFMS), Chapadão do Sul, MS Federal University of Acre (UFAC) Graduate Program in Agronomy State University of Londrina (Uel), PR Graduate Program in Sciences—Nuclear Energy in Agriculture Centro de Energia Nuclear na Agricultura São Paulo University São Paulo State University (Unesp) Engineering School, SP Graduate Program in Geography Federal University of Mato Grosso do Sul (UFMS), Três Lagoas, MS Graduate Program in Agronomy–Cropping Systems São Paulo State University (Unesp), SP Graduate Program in Geography São Paulo State University (Unesp) School of Technology and Sciences, SP São Paulo State University (Unesp) Engineering School, SP CNPq: 303767/2020-0

Active Queue Management (AQM) is recommended by Internet Engineering Task Force to mitigate the bufferbloat phenomenon in the Internet. In this paper, we show the results of comprehensive measurements carried out in our university network, in which a device with an AQM algorithm, designed and programmed for this purpose, was running. The implemented AQM algorithm was based on the dropping function, i.e. arriving packets were dropped randomly, with the probability being a function of the queue length. Several different dropping function forms, proposed in the networking literature, were used, in addition to the classic FIFO queue (no AQM). The experiment lasted over a month, during which the state of the network was measured and recorded several thousand times. This made the results independent of the natural fluctuations of the users’ behavior and the network load. Conclusions on the general performance improvement offered by the implemented AQM, as well as the differences in the performance between particular forms of the dropping function, were reached. Some of these conclusions differ from those drawn previously from simulations. This underlines the need for carrying measurements of new AQMs in real, operating networks, with complex, natural traffic.

The Monitoring and Analysis Centre for the fight against money laundering is a valid financial information body which is responsible for collecting, analysing and providing financial information and conducting international exchanges of financial information for relevant undertakings. By constructing the analysis of the monitoring of the local and foreign currency and of the data transmission subsystem in the plan for the transitional period against In the light of the above, the Commission will continue to monitor the implementation of the acquis in the light of the progress made in implementing the acquis future new systems. The purpose of this paper is to study the research and implementation of the security control of the anti-money laundering monitoring and analysis system. This article studies the application of decision tree analysis technology in the anti-money laundering monitoring system of insurance companies to achieve the purpose of improving the anti-money laundering monitoring technology and capabilities of insurance companies. The emergence of data mining technology provides a new system solution for anti-money laundering monitoring. For insurance anti-money laundering, how to find potential money laundering cases in suspicious and large surrender transactions is key. The experimental data show that the decision tree method is the best predictor of the customer category between the insurance application and the surrender days. The decision tree analysis technology has greatly improved the security monitoring capabilities of the insurance in the anti-money laundering monitoring system. Experimental data shows that the security control capabilities of the anti-money laundering monitoring and analysis system make the accuracy of the entire model reach 95%, the accuracy of large and suspicious transactions reaches 88.6%, and the correct classification of customers is about 99.6%.

In this work, we proposed a hybrid pointer network (HPN), an end-to-end deep reinforcement learning architecture is provided to tackle the travelling salesman problem (TSP). HPN builds upon graph pointer networks, an extension of pointer networks with an additional graph embedding layer. HPN combines the graph embedding layer with the transformer’s encoder to produce multiple embeddings for the feature context. We conducted extensive experimental work to compare HPN and Graph pointer network (GPN). For the sack of fairness, we used the same setting as proposed in GPN paper. The experimental results show that our network significantly outperforms the original graph pointer network for small and large-scale problems. For example, it reduced the cost for travelling salesman problems with 50 cities/nodes (TSP50) from 5.959 to 5.706 without utilizing 2opt. Moreover, we solved benchmark instances of variable sizes using HPN and GPN. The cost of the solutions and the testing times are compared using Linear mixed effect models. We found that our model yields statistically significant better solutions in terms of the total trip cost. We make our data, models, and code publicly available https://github.com/AhmedStohy/Hybrid-Pointer-Networks.

There is a growing interest in the application of artificial intelligence (AI) to orthopaedic surgery. This review aims to identify and characterise research in this field, in order to understand the extent, range and nature of this work, and act as springboard to stimulate future studies. A scoping review, a form of structured evidence synthesis, was conducted to summarise the use of AI in orthopaedics. A literature search (1946–2019) identified 222 studies eligible for inclusion. These studies were predominantly small and retrospective. There has been significant growth in the number of papers published in the last three years, mainly from the USA (37%). The majority of research used AI for image interpretation (45%) or as a clinical decision tool (25%). Spine (43%), knee (23%) and hip (14%) were the regions of the body most commonly studied. The application of artificial intelligence to orthopaedics is growing. However, the scope of its use so far remains limited, both in terms of its possible clinical applications, and the sub-specialty areas of the body which have been studied. A standardized method of reporting AI studies would allow direct assessment and comparison. Prospective studies are required to validate AI tools for clinical use.

Light fidelity (LiFi) uses different forms of orthogonal frequency division multiplexing (OFDM), including DC biased optical OFDM (DCO-OFDM). In DCO-OFDM, the use of a large DC bias causes optical power inefficiency, while a small bias leads to higher clipping noise. Hence, finding an appropriate DC bias level for DCO-OFDM is important. This paper applies machine learning (ML) algorithms to find optimum DC-bias value for DCO-OFDM based LiFi systems. For this, a dataset is generated for DCO-OFDM using MATLAB tool. Next, ML algorithms are applied using Python programming language. ML is used to find the important attributes of DCO-OFDM that influence the optimum DC bias. It is shown here that the optimum DC bias is a function of several factors including, the minimum, the standard deviation, and the maximum value of the bipolar OFDM signal, and the constellation size. Next, linear and polynomial regression algorithms are successfully applied to predict the optimum DC bias value. Results show that polynomial regression of order 2 can predict the optimum DC bias value with a coefficient of determination of 96.77% which confirms the effectiveness of the prediction.

Quantum signature is the use of the principles of quantum computing to establish a trusted communication between two parties. In this paper, a quantum signature scheme using amplitude amplification techniques will be proposed. To secure the signature, the proposed scheme uses a partial diffusion operator and a diffusion operator to hide/unhide certain quantum states during communication. The proposed scheme consists of three phases, preparation phase, signature phase and verification phase. To confuse the eavesdropper, the quantum states representing the signature might be hidden, not hidden or encoded in Bell states. It will be shown that the proposed scheme is more secure against eavesdropping when compared with relevant quantum signature schemes.

Particle swarm optimization and genetic algorithms are two classes of popular heuristic algorithms that are frequently used for solving complex multi-dimensional mathematical optimization problems, each one with its one advantages and shortcomings. Particle swarm optimization is known to favor exploitation over exploration, and as a result it often converges rapidly to local optima other than the global optimum. The genetic algorithm has the ability to overcome local extrema throughout the optimization process, but it often suffers from slow convergence rates. This paper proposes a new hybrid algorithm that nests particle swarm optimization operations in the genetic algorithm, providing the general population with the exploitation prowess of the genetic algorithm and a sub-population with the high exploitation capabilities of particle swarm optimization. The effectiveness of the proposed algorithm is demonstrated through solutions of several continuous optimization problems, as well as discrete (traveling salesman) problems. It is found that the new hybrid algorithm provides a better balance between exploration and exploitation compared to both parent algorithms, as well as existing hybrid algorithms, achieving consistently accurate results with relatively small computational cost.

The Coronavirus (COVID-19) pandemic has led to a rapidly growing ‘infodemic’ of health information online. This has motivated the need for accurate semantic search and retrieval of reliable COVID-19 information across millions of documents, in multiple languages. To address this challenge, this paper proposes a novel high precision and high recall neural Multistage BiCross encoder approach. It is a sequential three-stage ranking pipeline which uses the Okapi BM25 retrieval algorithm and transformer-based bi-encoder and cross-encoder to effectively rank the documents with respect to the given query. We present experimental results from our participation in the Multilingual Information Access (MLIA) shared task on COVID-19 multilingual semantic search. The independently evaluated MLIA results validate our approach and demonstrate that it outperforms other state-of-the-art approaches according to nearly all evaluation metrics in cases of both monolingual and bilingual runs.

This paper uses newly available data from Web of Science on publications matched to researchers in Survey of Doctorate Recipients to compare the quality of scientific publication data collected by surveys versus algorithmic approaches. We illustrate the different types of measurement errors in self-reported and machine-generated data by estimating how publication measures from the two approaches are related to career outcomes (e.g., salaries and faculty rankings). We find that the potential biases in the self-reports are smaller relative to the algorithmic data. Moreover, the errors in the two approaches are quite intuitive: the measurement errors in algorithmic data are mainly due to the accuracy of matching, which primarily depends on the frequency of names and the data that was available to make matches, while the noise in self reports increases over the career as researchers’ publication records become more complex, harder to recall, and less immediately relevant for career progress. At a methodological level, we show how the approaches can be evaluated using accepted statistical methods without gold standard data. We also provide guidance on how to use the new linked data.

With the development of recent years, the field of deep learning has made great progress. Compared with the traditional machine learning algorithm, deep learning can better find the rules in the data and achieve better fitting effect. In this paper, we propose a hybrid stock forecasting model based on Feature Selection, Convolutional Neural Network and Bidirectional Gated Recurrent Unit (FS-CNN-BGRU). Feature Selection (FS) can select the data with better performance for the results as the input data after data normalization. Convolutional Neural Network (CNN) is responsible for feature extraction. It can extract the local features of the data, pay attention to more local information, and reduce the amount of calculation. The Bidirectional Gated Recurrent Unit (BGRU) can process the data with time series, so that it can have better performance for the data with time series attributes. In the experiment, we used single CNN, LSTM and GRU models and mixed models CNN-LSTM, CNN-GRU and FS-CNN-BGRU (the model used in this manuscript). The results show that the performance of the hybrid model (FS-CNN-BGRU) is better than other single models, which has a certain reference value.

The reformations of the electrical power sector have resulted in very dynamic and competitive market that has changed many elements of the power industry. Excessive demand of energy, depleting the fossil fuel reserves of planet and releasing the toxic air pollutant, has been causing harm to earth habitats. In this new situation, insufficiency of energy supplies, rising power generating costs, high capital cost of renewable energy equipment, environmental concerns of wind power turbines, and ever-increasing demand for electrical energy need efficient economic dispatch. The objective function in practical economic dispatch (ED) problem is nonlinear and non-convex, with restricted equality and inequality constraints, and traditional optimization methods are incapable of resolving such non-convex problems. Over the recent decade, meta-heuristic optimization approaches have acquired enormous reputation for obtaining a solution strategy for such types of ED issues. In this paper, a novel soft computing optimization technique is proposed for solving the dynamic economic dispatch problem (DEDP) of complex non-convex machines with several constraints. Our premeditated framework employs the genetic algorithm (GA) as an initial optimizer and sequential quadratic programming (SQP) for the fine tuning of the pre-optimized run of GA. The simulation analysis of GA-SQP performs well by acquiring less computational cost and finite time of execution, while providing optimal generation of powers according to the targeted power demand and load, whereas subject to valve point loading effect (VPLE) and multiple fueling option (MFO) constraints. The adequacy of the presented strategy concerning accuracy, convergence as well as reliability is verified by employing it on ten benchmark case studies, including non-convex IEEE bus system at the same time also considering VPLE of thermal power plants. The potency of designed optimization seems more robust with fast convergence rate while evaluating the hard bounded DEDP. Our suggested hybrid method GA-SQP converges to achieve the best optimal solution in a confined environment in a limited number of simulations. The simulation results demonstrate applicability and adequacy of the given hybrid schemes over conventional methods.

Considering the issue of noise reduction associated with Laser Doppler Interference (LDI) signal, the paper presented a correlation coefficient local capping robust empirical mode decomposition (REMD) filter algorithm for LDI laser sensor that enables more robust reconstruction of the displacement information from an LDI signal. The performance of the algorithm is studied, and it is shown that the algorithm is capable of removing high-frequency noise. Useful information can be extracted more easily by this method, and the Hilbert phase unwrapping displacement reconstructions method based on this algorithm has been experimentally validated. The experimental results show that the proposed method can improve the frequency separation performance in experiments, and is robust against noise interference.

In quantum computing, the variational quantum algorithms (VQAs) are well suited for finding optimal combinations of things in specific applications ranging from chemistry all the way to finance. The training of VQAs with gradient descent optimization algorithm has shown a good convergence. At an early stage, the simulation of variational quantum circuits on noisy intermediate-scale quantum (NISQ) devices suffers from noisy outputs. Just like classical deep learning, it also suffers from vanishing gradient problems. It is a realistic goal to study the topology of loss landscape, to visualize the curvature information and trainability of these circuits in the existence of vanishing gradients. In this paper, we calculate the Hessian and visualize the loss landscape of variational quantum classifiers at different points in parameter space. The curvature information of variational quantum classifiers (VQC) is interpreted and the loss function's convergence is shown. It helps us better understand the behavior of variational quantum circuits to tackle optimization problems efficiently. We investigated the variational quantum classifiers via Hessian on quantum computers, starting with a simple 4-bit parity problem to gain insight into the practical behavior of Hessian, then thoroughly analyzed the behavior of Hessian's eigenvalues on training the variational quantum classifier for the Diabetes dataset. Finally, we show how the adaptive Hessian learning rate can influence the convergence while training the variational circuits., Comment: 13 pages, 9 figures

Containers have emerged as a more portable and efficient solution than virtual machines for cloud infrastructure providing both a flexible way to build and deploy applications. The quality of service, security, performance, energy consumption, among others, are essential aspects of their deployment, management, and orchestration. Inappropriate resource allocation can lead to resource contention, entailing reduced performance, poor energy efficiency, and other potentially damaging effects. In this paper, we present a set of online job allocation strategies to optimize quality of service, energy savings, and completion time, considering contention for shared on-chip resources. We consider the job allocation as the multilevel dynamic bin-packing problem that provides a lightweight runtime solution that minimizes contention and energy consumption while maximizing utilization. The proposed strategies are based on two and three levels of scheduling policies with container selection, capacity distribution, and contention-aware allocation. The energy model considers joint execution of applications of different types on shared resources generalized by the job concentration paradigm. We provide an experimental analysis of eighty-six scheduling heuristics with scientific workloads of memory and CPU-intensive jobs. The proposed techniques outperform classical solutions in terms of quality of service, energy savings, and completion time by 21.73–43.44%, 44.06–92.11%, and 16.38–24.17%, respectively, leading to a cost-efficient resource allocation for cloud infrastructures.

The electrical control system of rapier weaving machines is susceptible to various disturbances during operation and is prone to failures. This will seriously affect the production and a fault diagnosis system is needed to reduce this effect. However, the existing popular fault diagnosis systems and methods need to be improved due to the limitations of rapier weaving machine process and electrical characteristics. Based on this, this paper presents an in-depth study of rapier loom fault diagnosis system and proposes a rapier loom fault diagnosis method combining edge expert system and cloud-based rough set and Bayesian network. By analyzing the process and fault characteristics of rapier loom, the electrical faults of rapier loom are classified into common faults and other faults according to the frequency of occurrence. An expert system is built in the field for edge computing based on knowledge fault diagnosis experience to diagnose common loom faults and reduce the computing pressure in the cloud. Collect loom fault data in the cloud, train loom fault diagnosis algorithms to diagnose other faults, and handle other faults diagnosed by the expert system. The effectiveness of loom fault diagnosis is verified by on-site operation and remote monitoring of the loom human-machine interaction system. Technical examples are provided for the research of loom fault diagnosis system.

Regional collaboration and the division of economic zones have been widely discussed for sustainable development. This paper aims at building a framework for analyzing the provincial division of economic zone (DEZ) via considering spatial interaction among regions based on the improved gravity model and clustering approaches. The proposed framework of province DEZ is applied in the case study of Hunan Province, China. The results reveal that Chenzhou city in the south of Hunan Province is always excluded from the DEZ due to its larger external gravity from other cities in neighboring provinces. It also shows that the city components of economic zones (EZs) have experienced a fluctuation at a higher degree from 2002 to 2006 to 2009 while it reached to a stable phase in 2013. Furthermore, cross-provincial regional integration and the highway construction have a significant impact on the change of city components of EZ. The findings are of great potential in regional planning that should be incorporated to the toolkit of regional policy and sustainable development for local governments.

Low count PET (positron emission tomography) imaging is often desirable in clinical diagnosis and biomedical research, but its images are generally very noisy, due to the very weak signals in the sinograms used in image reconstruction. To address this issue, this paper presents a novel kernel graph filtering method for dynamic PET sinogram denoising. This method is derived from treating the dynamic sinograms as the signals on a graph, and learning the graph adaptively from the kernel principal components of the sinograms to construct a lowpass kernel graph spectrum filter. The kernel graph filter thus obtained is then used to filter the original sinogram time frames to obtain the denoised sinograms for PET image reconstruction. Extensive tests and comparisons on the simulated and real life in-vivo dynamic PET datasets show that the proposed method outperforms the existing methods in sinogram denoising and image enhancement of dynamic PET at all count levels, especially at low count, with a great potential in real life applications of dynamic PET imaging.

The recent uptake in popularity in vehicles with zero tailpipe emissions is a welcome development in the fight against traffic induced airborne pollutants. As vehicle fleets become electrified, and tailpipe emissions become less prevalent, non-tailpipe emissions (from tires and brake disks) will become the dominant source of traffic related emissions, and will in all likelihood become a major concern for human health. This trend is likely to be exacerbated by the heavier weight of electric vehicles, their increased power, and their increased torque capabilities, when compared with traditional vehicles. While the problem of emissions from tire wear is well-known, issues around the process of tire abrasion, its impact on the environment, and modelling and mitigation measures, remain relatively unexplored. Work on this topic has proceeded in several discrete directions including: on-vehicle collection methods; vehicle tire-wear abatement algorithms and controlling the ride characteristics of a vehicle, all with a view to abating tire emissions. Additional approaches include access control mechanisms to manage aggregate tire emissions in a geofenced area with other notable work focussing on understanding the particle size distribution of tire generated PM, the degree to which particles become airborne, and the health impacts of tire emissions. While such efforts are already underway, the problem of developing models to predict the aggregate picture of a network of vehicles at the scale of a city, has yet to be considered. Our objective in this paper is to present one such model, built using ideas from Markov chains. Applications of our modelling approach are given toward the end of this note, both to illustrate the utility of the proposed method, and to illustrate its application as part of a method to collect tire dust particles.

Aiming at these problems of image colorization algorithms based on deep learning, such as color bleeding and insufficient color, this paper converts the study of image colorization to the optimization of image semantic segmentation, and proposes a fully automatic image colorization model based on semantic segmentation technology. Firstly, we use the encoder as the local feature extraction network and use VGG-16 as the global feature extraction network. These two parts do not interfere with each other, but they share the low-level feature. Then, the first fusion module is constructed to merge local features and global features, and the fusion results are input into semantic segmentation network and color prediction network respectively. Finally, the color prediction network obtains the semantic segmentation information of the image through the second fusion module, and predicts the chrominance of the image based on it. Through several sets of experiments, it is proved that the performance of our model becomes stronger and stronger under the nourishment of the data. Even in some complex scenes, our model can predict reasonable colors and color correctly, and the output effect is very real and natural.

Focusing on the problem incurred during particle swarm optimization (PSO) that tends to fall into local optimization when solving Nash equilibrium solutions of games, as well as the problem of slow convergence when solving higher order game pay off matrices, this paper proposes an improved Predator-Prey particle swarm optimization (IPP-PSO) algorithm based on a Predator-Prey particle swarm optimization (PP-PSO) algorithm. First, the convergence of the algorithm is advanced by improving the distribution of the initial predator and prey. By improving the inertia weight of both predator and prey, the problem of “precocity” of the algorithm is improved. By improving the formula used to represent particle velocity, the problems of local optimizations and slowed convergence rates are solved. By increasing pathfinder weight, the diversity of the population is increased, and the global search ability of the algorithm is improved. Then, by solving the Nash equilibrium solution of both a zero-sum game and a non-zero-sum game, the convergence speed and global optimal performance of the original PSO, the PP-PSO and the IPP-PSO are compared. Simulation results demonstrated that the improved Predator-Prey algorithm is convergent and effective. The convergence speed of the IPP-PSO is significantly higher than that of the other two algorithms. In the simulation, the PSO does not converge to the global optimal solution, and PP-PSO approximately converges to the global optimal solution after about 40 iterations, while IPP-PSO approximately converges to the global optimal solution after about 20 iterations. Furthermore, the IPP-PSO is superior to the other two algorithms in terms of global optimization and accuracy.

With the continuing increase in online communications, virtual proximity as well as physical proximity has become a common way to connect individuals. Virtual proximity refers to the psychological closeness felt by people based on their participation in a virtual space. Hence, augmenting physical proximity with virtual types is believed to enhance connectivity within social networks, and applications that consider both types have the capability to provide new forms of interaction. However, despite the importance of their coexistence, these proximity concepts have been studied separately or are being integrated using diverse terminologies that often lead to misunderstandings. Furthermore, although some applications reflect the two proximity types (e.g., location-based services), there is no metric of comparison. This paper proposes the concept of augmented proximity (AP), which combines physical and virtual forms into a network analogous to one of mixed reality (MR). The concept provides a clear distinction between physical and virtual proximity using a single quantitative value. Using this concept, a formal taxonomy is established to compare and evaluate AP-based networks. The taxonomy consists of three dimensions that can be analyzed using graph theory, including the extent of connectivity degree, diffusion effect, and extent of perceived closeness. Furthermore, using the services underlying AP-based network, the proposed taxonomy can be applied to evaluate the suitability of the services as an indicator for comparison. The results show that one of the two services has a higher taxonomy-based value, and a reasonable basis for selecting one based on proximity is established. This study suggests that AP will play an important role as a quantitative indicator in developing and comparing applications that consider proximity in both virtual and physical modes.

This paper proposes a cutting head optimization method based on meshing the spatial position of the picks. According to the expanded shape of the spatial mesh composed of four adjacent picks on the plane, a standard mesh shape analysis method can be established with mesh skewness, mesh symmetry, and mesh area ratio as the indicators. The traversal algorithm is used to calculate the theoretical meshing rate, pick rotation coefficient, and the variation of cutting load for the longitudinal cutting head with 2, 3, and 4 helices. The results show that the 3-helix longitudinal cutting head has better performance. By using the traversal result with maximum theoretical meshing rate as the design parameter, the longitudinal cutting head CH51 with 51 picks was designed and analyzed. The prediction model of pick consumption is established based on cutting speed, direct rock cutting volume of each pick, pick rotation coefficient, uniaxial compressive strength, and CERCHAR abrasivity index. And the rock with normal distribution characteristics of Uniaxial Compressive Strength is used for the specific energy calculating. The artificial rock wall cutting test results show that the reduction in height loss suppresses the increase in pick equivalent loss caused by the increase in mass loss, and the pick consumption in this test is only 0.037–0.054 picks/m3. In addition, the correlation between the actual pick consumption and the prediction model, and the correlation between the actual cutting specific energy and the theoretical calculation value are also analyzed. The research results show that the pick arrangement design method based on meshing pick tip spatial position can effectively reduce pick consumption and improve the rock cutting performance.

Searching similar pictures for a given picture is an important task in numerous applications, including image recommendation system, image classification and image retrieval. Previous studies mainly focused on the similarities of content, which measures similarities based on visual features, such as color and shape, and few of them pay enough attention to semantics. In this paper, we propose a link-based semantic similarity search method, namely PictureSim, for effectively searching similar pictures by building a picture-tag network. The picture-tag network is built by “description” relationships between pictures and tags, in which tags and pictures are treated as nodes, and relationships between pictures and tags are regarded as edges. Then we design a TF-IDF-based model to removes the noisy links, so the traverses of these links can be reduced. We observe that “similar pictures contain similar tags, and similar tags describe similar pictures”, which is consistent with the intuition of the SimRank. Consequently, we utilize the SimRank algorithm to compute the similarity scores between pictures. Compared with content-based methods, PictureSim could effectively search similar pictures semantically. Extensive experiments on real datasets to demonstrate the effectiveness and efficiency of the PictureSim.

In this paper, we propose a framework for CT image segmentation of oil rock core. According to the characteristics of CT image of oil rock core, the existing level set segmentation algorithm is improved. Firstly, an algorithm of Chan-Vese (C-V) model is carried out to segment rock core from image background. Secondly the gray level of image background region is replaced by the average gray level of rock core, so that image background does not affect the binary segmentation. Next, median filtering processing is carried out. Finally, an algorithm of local binary fitting (LBF) model is executed to obtain the crack region. The proposed algorithm has been applied to oil rock core CT images with promising results.

The Internet of Things (IoT) technology is widely used and has been improved in research. However, due to the extensiveness of IoT technology, the heterogeneity and diversity of the device structure, the number of attacks against IoT has increased dramatically, so we need a method that can effectively and actively determine safety. Considering the diversity of the terminal structure of IoT, a security method for the IoT terminal based on structural balance, method objectivity, and reliability is currently a challenging task. This paper introduces the idea of rate of change in mathematics into trust analysis, and forms three attribute sets based on trust interval and rate of change: discrete interval, change range, and change frequency. By calculating the above attributes of the entity’s trust value, the entity’s trust situation is obtained, and an overall assessment of the terminal entity’s trust situation is made from the three levels of completeness, accuracy and objectivity. Under the premise of reducing encryption and other means, the above method can evaluate the trust state of the IoT terminal from the perspective of the data, and this evaluation method can provide a basis for the judgment of the IoT terminal more objectively and accurately.