Search

Many complex physical systems exhibit a rich variety of discrete behavioural modes. Often, the system complexity limits the applicability of standard modelling tools. Hence, understanding the underlying physics of different behaviours and distinguishing between them is challenging. Although traditional machine learning techniques could predict and classify behaviour well, typically they do not provide any meaningful insight into the underlying physics of the system. In this paper we present a novel method for extracting physically meaningful clusters of discrete behaviour from limited experimental observations. This method obtains a set of physically plausible functions that both facilitate behavioural clustering and aid in system understanding. We demonstrate the approach on the V-shaped falling paper system, a new falling paper type system that exhibits four distinct behavioural modes depending on a few morphological parameters. Using just 49 experimental observations, the method discovered a set of candidate functions that distinguish behaviours with an error of 2.04%, while also aiding insight into the physical phenomena driving each behaviour. © 2019 Howison et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Research paper recommenders emerged over the last decade to ease finding publications relating to researchers' area of interest. The challenge was not just to provide researchers with very rich publications at any time, any place and in any form but to also offer the right publication to the right researcher in the right way. Several approaches exist in handling paper recommender systems. However, these approaches assumed the availability of the whole contents of the recommending papers to be freely accessible, which is not always true due to factors such as copyright restrictions. This paper presents a collaborative approach for research paper recommender system. By leveraging the advantages of collaborative filtering approach, we utilize the publicly available contextual metadata to infer the hidden associations that exist between research papers in order to personalize recommendations. The novelty of our proposed approach is that it provides personalized recommendations regardless of the research field and regardless of the user's expertise. Using a publicly available dataset, our proposed approach has recorded a significant improvement over other baseline methods in measuring both the overall performance and the ability to return relevant and useful publications at the top of the recommendation list.

Many results have been obtained when studying scientific papers citations databases in a network perspective. Articles can be ranked according to their current in-degree and their future popularity or citation counts can even be predicted. The dynamical properties of such networks and the observation of the time evolution of their nodes started more recently. This work adopts an evolutionary perspective and proposes an original algorithm for the construction of genealogical trees of scientific papers on the basis of their citation count evolution in time. The fitness of a paper now amounts to its in-degree growing trend and a "dying" paper will suddenly see this trend declining in time. It will give birth and be taken over by some of its most prevalent citing "offspring". Practically, this might be used to trace the successive published milestones of a research field., SCOPUS: ar.j, info:eu-repo/semantics/published

We implemented three recently proposed approaches to the identification of overlapping and hierarchical substructures in graphs and applied the corresponding algorithms to a network of 492 information-science papers coupled via their cited sources. The thematic substructures obtained and overlaps produced by the three hierarchical cluster algorithms were compared to a content-based categorisation, which we based on the interpretation of titles and keywords. We defined sets of papers dealing with three topics located on different levels of aggregation: h-index, webometrics, and bibliometrics. We identified these topics with branches in the dendrograms produced by the three cluster algorithms and compared the overlapping topics they detected with one another and with the three pre-defined paper sets. We discuss the advantages and drawbacks of applying the three approaches to paper networks in research fields., Comment: 18 pages, 9 figures

Environmentally Degradable Parameter ((Ed)K) is of importance in the describing of biodegradability of environmentally biodegradable polymers (BDPs). In this study, a concept (Ed)K was introduced. A test procedure of using the ISO 14852 method and detecting the evolved carbon dioxide as an analytical parameter was developed, and the calculated (Ed)K was used as an indicator for the ultimate biodegradability of materials. Starch and polyethylene used as reference materials were defined as the (Ed)K values of 100 and 0, respectively. Natural soil samples were inoculated into bioreactors, followed by determining the rates of biodegradation of the reference materials and 15 commercial BDPs over a 2-week test period. Finally, a formula was deduced to calculate the value of (Ed)K for each material. The (Ed)K values of the tested materials have a positive correlation to their biodegradation rates in the simulated soil environment, and they indicated the relative biodegradation rate of each material among all the tested materials. Therefore, the (Ed)K was shown to be a reliable indicator for quantitatively evaluating the potential biodegradability of BDPs in the natural environment.

Choice tests are a standard method to determine preferences in bio-assays, e.g. for food types and food additives such as bait attractants and toxicants. Choice between food additives can be determined only when the food substrate is sufficiently homogeneous. This is difficult to achieve for wood eating organisms as wood is a highly variable biological material, even within a tree species due to the age of the tree (e.g. sapwood vs. heartwood), and components therein (sugar, starch, cellulose and lignin). The current practice to minimise variation is to use wood from the same tree, yet the variation can still be large and the quantity of wood from one tree may be insufficient. We used wood samples of identical volume from multiple sources, measured three physical properties (dry weight, moisture absorption and reflected light intensity), then ranked and clustered the samples using fuzzy c-means clustering. A reverse analysis of the clustered samples found a high correlation between their physical properties and their source of origin. This suggested approach allows a quantifiable, consistent, repeatable, simple and quick method to maximize control over similarity of wood used in choice tests. © 2014 Oberst et al.

The COVID-19 pandemic has exposed the vulnerability of healthcare services worldwide, raising the need to develop novel tools to provide rapid and cost-effective screening and diagnosis. Clinical reports indicated that COVID-19 infection may cause cardiac injury, and electrocardiograms (ECG) may serve as a diagnostic biomarker for COVID-19. This study aims to utilize ECG signals to detect COVID-19 automatically. We propose a novel method to extract ECG signals from ECG paper records, which are then fed into a one-dimensional convolution neural network (1D-CNN) to learn and diagnose the disease. To evaluate the quality of digitized signals, R peaks in the paper-based ECG images are labeled. Afterward, RR intervals calculated from each image are compared to RR intervals of the corresponding digitized signal. Experiments on the COVID-19 ECG images dataset demonstrate that the proposed digitization method is able to capture correctly the original signals, with a mean absolute error of 28.11 ms. Our proposed 1D-CNN model, which is trained on the digitized ECG signals, allows identifying individuals with COVID-19 and other subjects accurately, with classification accuracies of 98.42%, 95.63%, and 98.50% for classifying COVID-19 vs. Normal, COVID-19 vs. Abnormal Heartbeats, and COVID-19 vs. other classes, respectively. Furthermore, the proposed method also achieves a high-level of performance for the multi-classification task. Our findings indicate that a deep learning system trained on digitized ECG signals can serve as a potential tool for diagnosing COVID-19., Accepted with minor revision by Plos One

Recommendation algorithms save a lot of valuable time for people to get the information they are interested in. However, the feature calculation and extraction process of each machine learning or deep learning recommendation algorithm are different, so how to obtain various features with different dimensions, i.e., how to integrate the advantages of each model and improve the model inference efficiency, becomes the focus of this paper. In this paper, a better deep learning model is obtained by integrating several cutting-edge deep learning models. Meanwhile, to make the integrated learning model converge better and faster, the parameters of the integrated module are initialized, constraints are imposed, and a new activation function is designed for better integration of the sub-models. Finally, the integrated large model is distilled for knowledge distillation, which greatly reduces the number of model parameters and improves the model inference efficiency.

Resource allocation problem is one of key issues in the field of revenue management. The traditional models usually rely on some restrictive assumptions about demand information or arrival process, which is sometimes out of line with reality. To overcome this shortcoming, the method of competitive analysis of online algorithms, which eliminates the need for the assumptions on demand and arrivals, is adopted to deal with the quantity-based revenue management problem. The current model in this paper considers two downgrade compatible levels of resources. Given the capacities and fares of both levels of resources, the objective is to accept appropriate customers and assign them to appropriate resources so as to maximize revenues. Compared with the existing literature, this paper generalizes the concerned resource allocation problem by considering multiple fares for each level of resources. From the perspective of online algorithms and competitive analysis, both an upper bound and an optimal online strategy are derived in this paper.

When aerial cameras get aerial remote sensing images, the defocus will occur because of reasons such as air pressure, temperature and ground elevation changes, resulting in different image sharpness of continual aerial remote sensing images. Nowadays, the rapidly developing feature matching algorithm will rapidly reduce the registration rate between images with different image sharpness. Therefore, in order to enable aerial cameras to get image sharpness parameters according to the locations of aerial image feature points with inconsistent sharpness, this paper proposes a feature matching algorithm between aerial images with different sharpness by using DEM data and multiple constraints. In this paper, the feature matching range is extended according to the modified aerial imaging model and the nonlinear soft margin support vector machine. Then the relative moving speed and its variation of the feature points in the image are obtained by using the extended L-k optical flow, and finally the epipolar geometric constraint is introduced. To locate the feature points is obtained under multiple constraints, there is no need to calculate the feature point descriptors, and some mismatched point pairs are corrected, which improves the matching efficiency and precision. The experimental results show the feature matching precision of this algorithm is more than 90%, and the running time and matching precision can meet various application needs of aerial cameras.

In the field of surface electromyography (sEMG) gesture recognition, how to improve recognition accuracy has been a research hotspot. The rapid development of deep learning provides a new solution to this problem. At present, the main applications of deep learning for sEMG gesture feature extraction are based on convolutional neural network (CNN) structures to capture spatial morphological information of the multichannel sEMG or based on long short-term memory network (LSTM) to extract time-dependent information of the single-channel sEMG. However, there are few methods to comprehensively consider the distribution area of the sEMG signal acquisition electrode sensor and the arrangement of the sEMG signal morphological features and electrode spatial features. In this paper, a novel multi-stream feature fusion network (MSFF-Net) model is proposed for sEMG gesture recognition. The model adopts a divide-and-conquer strategy to learn the relationship between different muscle regions and specific gestures. Firstly, a multi-stream convolutional neural network (Multi-stream CNN) and a convolutional block attention module integrated with a resblock (ResCBAM) are used to extract multi-dimensional spatial features from signal morphology, electrode space, and feature map space. Then the learned multi-view depth features are fused by a view aggregation network consisting of an early fusion network and a late fusion network. The results of all subjects and gesture movement validation experiments in the sEMG signal acquired from 12 sensors provided by NinaPro’s DB2 and DB4 sub-databases show that the proposed model in this paper has better performance in terms of gesture recognition accuracy compared with the existing models.

Immersive projection display system is widely adopted in virtual reality and various exhibition halls. How to maintain high display quality in an immersive projection environment with uneven illumination and the color deviation caused by the inter-reflection of light is still a challenging task. In this paper, we innovatively propose a deep learning-based radiation compensation for an L-shaped projector-camera system. This method employs complex reflection phenomena to simulate the light transport processing in an L-shaped environment, we also designed a Dark-Channel Enhanced-Compensation Net (DECNet) which composed of a convolutional neural network called Compensation Net, a DarkChannelNet and another subnet (such as sensing network) aiming at achieving high-quality reproduction of projected display images. The final output of DECNet is the compensation image to be projected. It is always a critical problem to establish appropriate evaluation and analysis indexes throughout the research of light pollution compensation algorithms. In this paper, PSNR, SSIM, and RMSE are proposed to quantitatively analyze the image quality. The experimental results show that this method has certain advantages in reducing the inter-reflection of the projection plane. And our method could also well replace the traditional process using the backlight transmission matrix. It can be concluded to a certain that this method can be extended to other more complex projection environments with strong scalability and inclusiveness.

This paper offers a comprehensive analysis model for android malware. The model presents the essential factors affecting the analysis results of android malware that are vision-based. Current android malware analysis and solutions might consider one or some of these factors while building their malware predictive systems. However, this paper comprehensively highlights these factors and their impacts through a deep empirical study. The study comprises 22 CNN (Convolutional Neural Network) algorithms, 21 of them are well-known, and one proposed algorithm. Additionally, several types of files are considered before converting them to images, and two benchmark android malware datasets are utilized. Finally, comprehensive evaluation metrics are measured to assess the produced predictive models from the security and complexity perspectives. Consequently, guiding researchers and developers to plan and build efficient malware analysis systems that meet their requirements and resources. The results reveal that some factors might significantly impact the performance of the malware analysis solution. For example, from a security perspective, the accuracy, F1-score, precision, and recall are improved by 131.29%, 236.44%, 192%, and 131.29%, respectively, when changing one factor and fixing all other factors under study. Similar results are observed in the case of complexity assessment, including testing time, CPU usage, storage size, and pre-processing speed, proving the importance of the proposed android malware analysis model.

An electronic transition-based bare bones particle swarm optimization (ETBBPSO) algorithm is proposed in this paper. The ETBBPSO is designed to present high precision results for high dimensional single-objective optimization problems. Particles in the ETBBPSO are divided into different orbits. A transition operator is proposed to enhance the global search ability of ETBBPSO. The transition behavior of particles gives the swarm more chance to escape from local minimums. In addition, an orbit merge operator is proposed in this paper. An orbit with low search ability will be merged by an orbit with high search ability. Extensive experiments with CEC2014 and CEC2020 are evaluated with ETBBPSO. Four famous population-based algorithms are also selected in the control group. Experimental results prove that ETBBPSO can present high precision results for high dimensional single-objective optimization problems.

Global warming has seriously affected the local climate characteristics of cities, resulting in the frequent occurrence of urban waterlogging with severe economic losses and casualties. Aiming to improve the effectiveness of disaster emergency management, we propose a novel emergency decision model embedding similarity algorithms of heterogeneous multi-attribute based on case-based reasoning. First, this paper establishes a multi-dimensional attribute system of urban waterlogging catastrophes cases based on the Wuli-Shili-Renli theory. Due to the heterogeneity of attributes of waterlogging cases, different algorithms to measure the attribute similarity are designed for crisp symbols, crisp numbers, interval numbers, fuzzy linguistic variables, and hesitant fuzzy linguistic term sets. Then, this paper combines the best-worst method with the maximal deviation method for a more reasonable weight allocation of attributes. Finally, the hybrid similarity between the historical and the target cases is obtained by aggregating attribute similarities via the weighted method. According to the given threshold value, a similar historical case set is built whose emergency measures are used to provide the reference for the target case. Additionally, a case of urban waterlogging emergency is conducted to demonstrate the applicability and effectiveness of the proposed model, which exploits historical experiences and retrieves the optimal scheme for the current disaster emergency with heterogeneous multi attributes. Consequently, the proposed model solves the problem of diverse data types to satisfy the needs of case presentation and retrieval. Compared with the existing model, it can better realize the multi-dimensional expression and fast matching of the cases.

In this paper, we discuss a multi-period portfolio optimization problem based on uncertainty theory and prospect theory. We propose an uncertain multi-period portfolio selection model, in which the return utility and risk of investment are measured by prospect theory utility function and uncertain semivariance. More realistically, the influence of transaction costs and bankruptcy of investor are also considered. Moreover, to solve the portfolio model, this paper designs a new artificial bee colony algorithm by combining sine cosine search method. Finally, a numerical experiment is presented to demonstrate the proposed model and the effectiveness of the designed algorithm.

The deep neural network is used to establish a neural network model to solve the problems of low accuracy and poor accuracy of traditional algorithms in screening differentially expressed genes and function prediction during the walnut endocarp hardening stage. The paper walnut is used as the research object to analyze the biological information of paper walnut. The changes of lignin deposition during endocarp hardening from 50 days to 90 days are observed by microscope. Then, the Convolutional Neural Network (CNN) and Long and Short-term Memory (LSTM) network model are adopted to construct an expression gene screening and function prediction model. Then, the transcriptome and proteome sequencing and biological information of walnut endocarp samples at 50, 57, 78, and 90 days after flowering are analyzed and taken as the training data set of the CNN + LSTM model. The experimental results demonstrate that the endocarp of paper walnut began to harden at 57 days, and the endocarp tissue on the hardened inner side also began to stain. This indicates that the endocarp hardened laterally from outside to inside. The screening and prediction results show that the CNN + LSTM model’s highest accuracy can reach 0.9264. The Accuracy, Precision, Recall, and F1-score of the CNN + LSTM model are better than the traditional machine learning algorithm. Moreover, the Receiver Operating Curve (ROC) area enclosed by the CNN + LSTM model and coordinate axis is the largest, and the Area Under Curve (AUC) value is 0.9796. The comparison of ROC and AUC proves that the CNN + LSTM model is better than the traditional algorithm for screening differentially expressed genes and function prediction in the walnut endocarp hardening stage. Using deep learning to predict expressed genes’ function accurately can reduce the breeding cost and significantly improve the yield and quality of crops. This research provides scientific guidance for the scientific breeding of paper walnut.

Pathological examination is the gold standard for breast cancer diagnosis. The recognition of histopathological images of breast cancer has attracted a lot of attention in the field of medical image processing. In this paper, on the base of the Bioimaging 2015 dataset, a two-stage nuclei segmentation strategy, that is, a method of watershed segmentation based on histopathological images after stain separation, is proposed to make the dataset recognized to be the carcinoma and non-carcinoma recognition. Firstly, stain separation is performed on breast cancer histopathological images. Then the marker-based watershed segmentation method is used for images obtained from stain separation to achieve the nuclei segmentation target. Next, the completed local binary pattern is used to extract texture features from the nuclei regions (images after nuclei segmentation), and color features were extracted by using the color auto-correlation method on the stain-separated images. Finally, the two kinds of features were fused and the support vector machine was used for carcinoma and non-carcinoma recognition. The experimental results show that the two-stage nuclei segmentation strategy proposed in this paper has significant advantages in the recognition of carcinoma and non-carcinoma on breast cancer histopathological images, and the recognition accuracy arrives at 91.67%. The proposed method is also applied to the ICIAR 2018 dataset to realize the automatic recognition of carcinoma and non-carcinoma, and the recognition accuracy arrives at 92.50%.

The present work aims to find the optimal solution of Nash Equilibrium (NE) in the traditional Game Theory (GT) applied to water resources allocation. Innovatively, this paper introduces Particle Swarm Optimization (PSO) into GT to propose a cooperative game model to solve the NE problem. Firstly, the basic theory of the PSO algorithm and cooperative game model is described. Secondly, the PSO-based cooperative game model is explained. Finally, the PSO-based cooperative game model is compared with the Genetic Algorithm (GA) to test the performance. Besides taking the countries in Lancang Mekong River Basin as the research object, this paper discusses each country’s water consumption and economic benefits under different cooperation patterns. Then, a series of improvement measures and suggestions are put forward accordingly. The results show that the average server occupancy time of the PSO-based cooperative game model is 78.46% lower than that of GA, and the average waiting time is 79.24% lower than that of the GA. Thus, the model reported here has higher computational efficiency and excellent performance than the GA and is more suitable for the current study. In addition, the multi-country cooperation mode can obtain more economic benefits than the independent water resource development mode. This model can quickly find the optimal combination of 16 cooperation modes and has guiding significance for maximizing the benefits of cross-border water Resource Utilization. This research can provide necessary technical support to solve the possible contradictions and conflicts between cross-border river basin countries and build harmonious international relations.

Software Test Case Prioritization (TCP) is an effective approach for regression testing to tackle time and budget constraints. The major benefit of TCP is to save time through the prioritization of important test cases first. Existing TCP techniques can be categorized as value-neutral and value-based approaches. In a value-based fashion, the cost of test cases and severity of faults are considered whereas, in a value-neutral fashion these are not considered. The value-neutral fashion is dominant over value-based fashion, and it assumes that all test cases have equal cost and all software faults have equal severity. But this assumption rarely holds in practice. Therefore, value-neutral TCP techniques are prone to produce unsatisfactory results. To overcome this research gap, a paradigm shift is required from value-neutral to value-based TCP techniques. Currently, very limited work is done in a value-based fashion and to the best of the authors’ knowledge, no comprehensive review of value-based cost-cognizant TCP techniques is available in the literature. To address this problem, a systematic literature review (SLR) of value-based cost-cognizant TCP techniques is presented in this paper. The core objective of this study is to combine the overall knowledge related to value-based cost-cognizant TCP techniques and to highlight some open research problems of this domain. Initially, 165 papers were reviewed from the prominent research repositories. Among these 165 papers, 21 papers were selected by using defined inclusion/exclusion criteria and quality assessment procedures. The established questions are answered through a thorough analysis of the selected papers by comparing their research contributions in terms of the algorithm used, the performance evaluation metric, and the results validation method used. Total 12 papers used an algorithm for their technique but 9 papers didn’t use any algorithm. Particle Swarm Optimization (PSO) Algorithm is dominantly used. For results validation, 4 methods are used including, Empirical study, Experiment, Case study, and Industrial case study. The experiment method is dominantly used. Total 6 performance evaluation metrics are used and the APFDc metric is dominantly used. This SLR yields that value-orientation and cost cognition are vital in the TCP process to achieve its intended goals and there is great research potential in this research domain.

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.

Transmission lines are most prone to faults in the transmission system, so high-precision fault diagnosis is very important for quick troubleshooting. There are some problems in current intelligent fault diagnosis research methods, such as difficulty in extracting fault features accurately, low fault recognition accuracy and poor fault tolerance. In order to solve these problems, this paper proposes an intelligent fault diagnosis method for high voltage direct current transmission lines (HVDC) based on Gramian angular difference field (GADF) domain and improved convolutional neural network (VGG16). This method first performs variational modal decomposition (VMD) on the original fault voltage signal, and then uses the correlation coefficient method to select the appropriate intrinsic mode function (IMF) component, and converts it into a two-dimensional image using the Gramian Angular Difference Field(GADF). Finally, the improved VGG16 network is used to extract and classify fault features adaptively to realize fault diagnosis. In order to improve the performance of the VGG16 fault diagnosis model, batch normalization, dense connection and global average pooling techniques are introduced. The comparative experimental results show that the model proposed in this paper can further identify fault features and has a high fault diagnosis accuracy. In addition, the method is not affected by fault type, transitional resistance and fault distance, has good anti-interference ability, strong fault tolerance, and has great potential in practical applications.

In order to further improve the accuracy of the video-based behavior recognition method, an effective behavior recognition method in the video session using convolutional neural network is proposed. Specifically, by adding the target detection phase before the behavior recognition algorithm, the body region in the video can be accurately extracted to reduce the interference of redundant and unnecessary background noises, and at the same time, the inappropriate images can be replaced, which has reached the role of balance background trade-off, and finally, the neural network can learn the human behavior information with emphasis. By adding fragmentation and stochastic sampling, the long-time time-domain modeling of the whole video session can be established, so that the model can obtain video-level expression ability. Finally, the improved loss function is used for behavior recognition to solve the problem of classification difficulty and possible sample imbalance. In addition, we conducted the hyperparametric experiment, the ablation experiment and the contrast experiment on different open source and benchmark datasets. Compared with other commonly used behavior recognition algorithms, the experimental results verify the effectiveness of the proposed method. In addition, the related deep learning-based methods used in behavior recognition are reviewed at the beginning of this paper, and the challenges in behavior recognition and future research directions are prospected at the end of this paper, which will undoubtedly play a double role in the work of later researchers.

Varieties of raisins are diverse, and different varieties have different nutritional properties and commercial value. In this paper, we propose a method to identify different varieties of raisins by combining near-infrared (NIR) spectroscopy and machine learning algorithms. The direct averaging of the spectra taken for each sample may reduce the experimental data and affect the extraction of spectral features, thus limiting the classification results, due to the different substances of grape skins and flesh. Therefore, this experiment proposes a method to fuse the spectral features of pulp and peel. In this experiment, principal component analysis (PCA) was used to extract baseline corrected features, and linear models of k-nearest neighbor (KNN) and linear discriminant analysis (LDA) and nonlinear models of back propagation (BP), support vector machine with genetic algorithm (GA-SVM), grid search-support vector machine (GS-SVM) and particle swarm optimization with support vector machine (PSO- SVM) coupling were used to classify. This paper compared the results of four experiments using only skin spectrum, only flesh spectrum, average spectrum of skin and flesh, and their spectral feature fusion. The experimental results showed that the accuracy and Macro-F1 score after spectral feature fusion were higher than the other three experiments, and GS-SVM had the highest accuracy and Macro-F1 score of 94.44%. The results showed that feature fusion can improve the performance of both linear and nonlinear models. This may provide a new strategy for acquiring spectral data and improving model performance in the future. The code is available at https://github.com/L-ain/Source.

In this paper, a dynamic update algorithm of double scrambling-DNA row and column closed loop based on chaotic system is proposed. The classical scrambling and diffusion structure are used in the whole process. In the scrambling stage, a new pixel reconstruction method is proposed by combining the Hilbert curve with Knuth-Durstenfeld shuffle algorithm to overcome the shortcoming of nearby storage of Hilbert curve. This method reconstructs the pixel matrix of one-dimensional vector according to the Hilbert curve coding method, and achieves good scrambling effect, while reducing its time complexity and space complexity. In the diffusion stage, combining the plaintext row, the ciphertext row and the key row, and taking advantage of the parallel computing power and high storage density of the DNA encoding, the existing block diffusion operation is improved, and the two-round diffusion of the DNA encoding is proposed. When the last line of ciphertext is generated, the first line of ciphertext is updated and the closed-loop dynamic update of the encryption system is realized. Finally, SHA-256 is used to give the secret key and calculate the initial value of the chaotic system. The simulation results show that the “double scrambling-DNA row and column closed loop dynamic” update algorithm proposed in this paper can effectively improve the efficiency of information transmission and have high security.

This paper proposes a new method for low-light image enhancement with balancing image brightness and preserving image details, this method can improve the brightness and contrast of low-light images while maintaining image details. Traditional histogram equalization methods often lead to excessive enhancement and loss of details, thereby resulting in an unclear and unnatural appearance. In this method, the image is processed bidirectionally. On the one hand, the image is processed by double histogram equalization with double automatic platform method based on improved cuckoo search (CS) algorithm, where the image histogram is segmented firstly, and the platform limit is selected according to the histogram statistics and improved CS technology. Then, the sub-histograms are clipped by two platforms and carried out the histogram equalization respectively. Finally, an image with balanced brightness and good contrast can be obtained. On the other hand, the main structure of the image is extracted based on the total variation model, and the image mask with all the texture details is made by removing the main structure of the image. Eventually, the final enhanced image is obtained by adding the mask with texture details to the image with balanced brightness and good contrast. Compared with the existing methods, the proposed algorithm significantly enhances the visual effect of the low-light images, based on human subjective evaluation and objective evaluation indices. Experimental results show that the proposed method in this paper is better than the existing methods.

Cosegmentation is a newly emerging computer vision technique used to segment an object from the background by processing multiple images at the same time. Traditional plant phenotyping analysis uses thresholding segmentation methods which result in high segmentation accuracy. Although there are proposed machine learning and deep learning algorithms for plant segmentation, predictions rely on the specific features being present in the training set. The need for a multi-featured dataset and analytics for cosegmentation becomes critical to better understand and predict plants’ responses to the environment. High-throughput phenotyping produces an abundance of data that can be leveraged to improve segmentation accuracy and plant phenotyping. This paper introduces four datasets consisting of two plant species, Buckwheat and Sunflower, each split into control and drought conditions. Each dataset has three modalities (Fluorescence, Infrared, and Visible) with 7 to 14 temporal images that are collected in a high-throughput facility at the University of Nebraska-Lincoln. The four datasets (which will be collected under the CosegPP data repository in this paper) are evaluated using three cosegmentation algorithms: Markov random fields-based, Clustering-based, and Deep learning-based cosegmentation, and one commonly used segmentation approach in plant phenotyping. The integration of CosegPP with advanced cosegmentation methods will be the latest benchmark in comparing segmentation accuracy and finding areas of improvement for cosegmentation methodology.

Sleep staging is the basis of sleep evaluation and a key step in the diagnosis of sleep-related diseases. Despite being useful, the existing sleep staging methods have several disadvantages, such as relying on artificial feature extraction, failing to recognize temporal sequence patterns in the long-term associated data, and reaching the accuracy upper limit of sleep staging. Hence, this paper proposes an automatic Electroencephalogram (EEG) sleep signal staging model, which based on Multi-scale Attention Residual Nets (MAResnet) and Bidirectional Gated Recurrent Unit (BiGRU). The proposed model is based on the residual neural network in deep learning. Compared with the traditional residual learning module, the proposed model additionally uses the improved channel and spatial feature attention units and convolution kernels of different sizes in parallel at the same position. Thus, multiscale feature extraction of the EEG sleep signals and residual learning of the neural networks is performed to avoid network degradation. Finally, BiGRU is used to determine the dependence between the sleep stages and to realize the automatic learning of sleep data staging features and sleep cycle extraction. According to the experiment, the classification accuracy and kappa coefficient of the proposed method on sleep-EDF data set are 84.24% and 0.78, which are respectively 0.24% and 0.21 higher than the traditional residual net. At the same time, this paper also verified the proposed method on UCD and SHHS data sets, and the figure of classification accuracy is 79.34% and 81.6%, respectively. Compared to related existing studies, the recognition accuracy is significantly improved, which validates the effectiveness and generalization performance of the proposed method.

The bin packing problem has a wide range of applications in industry. With the upgrade of the task difficulty, the traditional 2d rectangular layout algorithm can no longer meet the needs of modern industry, such as express packing task and exoplanet ore collection task. The express or ore samples come in heterogeneous shapes so they cannot all be treated as rectangular pieces. In this paper, we propose a three-stage method called covering, corner-searching and occupying (C,S&O) to solve the two-dimensional multishape part packing problem. The objective of the packing problem variant is to ensure maximum use of the raw material and minimize the trim loss. The algorithm cannot make use of information about the sequence of future objects that are going to arrive, only knowing the shape and size of the coming one, and the coming part must be packed into the bin immediately after its arrival without buffering or readjusting. The method of C,S&O hybridizes the idea of “gold corners, silver edges and grass belly” in the Chinese game Go and the method of finding picture corners in machine vision. In the first stage, the rectangular bin and the coming part are transformed into matrix representation, and generating the position matrix that indicates possible ways of packing the part into the bin. In the second stage, the suitable layout position of the coming part is obtained using machine vision image processing technology for reference. The third stage is calculating the environment matching degree to determine the current optimal placement orientation. In order to facilitate the display of the simulation results, only three shapes of parts are considered in the simulation, rectangle, circle and triangle. The experimental results show the effectiveness of this method. Consulting the literature, it is found that this paper is the first to propose a layout method for multishape manufacturing parts.

In the paper, we proposed a deep learning-based industrial equipment detection algorithm ROMS R-CNN (Rotation Occlusion Multi-Scale Region-CNN). It can solve the problem of inaccurate detection of industrial equipment under complex working conditions such as multi-scale ratio, rotation tilt, occlusion and overlap. The method proposed in this paper first is to construct the MobileNetV2 as the feature pyramid network, and then to combine high semantic information with high resolution information solved industrial equipment detection of different scales. Secondly, a specific rotation anchor scheme is proposed, and the data set is clustered through the k-means algorithm to obtain a specific aspect ratio. Combined with the rotation angle, a rotation anchor of any direction and size is generated to solve the problem of easy tilting of industrial equipment. Finally, a Non-Maximum Suppression algorithm with penalty factors is introduced to solve the overlapping in industrial equipment detection. The experimental results in common industrial equipment detection show that this method is better than other algorithms, significantly improves the missed detection and false detection, and the mAP reaches 0.939.

In this paper, we propose methods for functional predictor selection and the estimation of smooth functional coefficients simultaneously in a scalar-on-function regression problem under high-dimensional multivariate functional data setting. In particular, we develop two methods for functional group-sparse regression under a generic Hilbert space of infinite dimension. We show the convergence of algorithms and the consistency of the estimation and the selection (oracle property) under infinite-dimensional Hilbert spaces. Simulation studies show the effectiveness of the methods in both the selection and the estimation of functional coefficients. The applications to the functional magnetic resonance imaging (fMRI) reveal the regions of the human brain related to ADHD and IQ., The R package that is developed for this paper is available at GitHub. See https://github.com/Ali-Mahzarnia/MFSGrp

Segmentation of retinal vessels is important for doctors to diagnose some diseases. The segmentation accuracy of retinal vessels can be effectively improved by using deep learning methods. However, most of the existing methods are incomplete for shallow feature extraction, and some superficial features are lost, resulting in blurred vessel boundaries and inaccurate segmentation of capillaries in the segmentation results. At the same time, the “layer-by-layer” information fusion between encoder and decoder makes the feature information extracted from the shallow layer of the network cannot be smoothly transferred to the deep layer of the network, resulting in noise in the segmentation features. In this paper, we propose the MFI-Net (Multi-resolution fusion input network) network model to alleviate the above problem to a certain extent. The multi-resolution input module in MFI-Net avoids the loss of coarse-grained feature information in the shallow layer by extracting local and global feature information in different resolutions. We have reconsidered the information fusion method between the encoder and the decoder, and used the information aggregation method to alleviate the information isolation between the shallow and deep layers of the network. MFI-Net is verified on three datasets, DRIVE, CHASE_DB1 and STARE. The experimental results show that our network is at a high level in several metrics, with F1 higher than U-Net by 2.42%, 2.46% and 1.61%, higher than R2U-Net by 1.47%, 2.22% and 0.08%, respectively. Finally, this paper proves the robustness of MFI-Net through experiments and discussions on the stability and generalization ability of MFI-Net.

Reconstruction of network is to infer the relationship among nodes using observation data, which is helpful to reveal properties and functions of complex systems. In view of the low reconstruction accuracy based on small data and the subjectivity of threshold to infer adjacency matrix, the paper proposes two models: the quadratic compressive sensing (QCS) and integer compressive sensing (ICS). Then a combined method (CCS) is given based on QCS and ICS, which can be used on binary-state and multi-state dynamics. It is found that CCS is usually a superior method comparing with compressive sensing, LASSO on several networks with different structures and scales. And it can infer larger node correctly than the other two methods. The paper is conducive to reveal the hidden relationship with small data so that to understand, predicate and control a vast intricate system.

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.

Blockchain has been applied to quality control in manufacturing, but the problems of false defect detections and lack of data transparency remain. This paper proposes a framework, Blockchain Quality Controller (BCQC), to overcome these limitations while fortifying data security. BCQC utilizes blockchain and Internet-of-Things to form a peer-to-peer supervision network. This paper also proposes a consensus algorithm, Quality Defect Tolerance (QDT), to adopt blockchain for during-production quality control. Simulation results show that BCQC enhances data security and improves defect detections. Although the time taken for the quality control process increases with the number of nodes in blockchain, the application of QDT allows multiple inspections on a workpiece to be consolidated at a faster pace, effectively speeding up the entire quality control process. The BCQC and QDT can improve the quality of parts produced for mass personalization manufacturing.

In this paper, we investigate the outage probability and ergodic sum capacity of the downlink of the integrated satellite-terrestrial networks (ISTN) with a cooperative non-orthogonal multiple access (CNOMA) scheme, in which a user with better channel condition acts as a relay node and forwards information to the other users. In this paper, a pilot-based channel estimation method is considered which can verify the performance of this scheme with the imperfect channel state information. In this model, all these users are equipped with multi-antennas, and all of them are both in the coverage of a same beam of the satellite. Specifically, the exact analytical expression for the outage probability and ergodic sum capacity of the system is derived. The result shows that this coordinated non-orthogonal multiple access (CNOMA) scheme performs better than that of OMA (TDMA) in this model. Finally, the future research directions are given to further enhance the system capacity.

Political redistricting is the redrawing of electoral district boundaries. It is normally undertaken to reflect population changes. The process can be abused, in what is called gerrymandering, to favor one party or interest group over another, resulting thereby in broadly undemocratic outcomes that misrepresent the views of the voters. Gerrymandering is especially vexing in the United States. This paper introduces an algorithm, with an implementation, for creating districting plans (whether for political redistricting or for other districting applications). The algorithm, Seed-Fill-Shift-Repair (SFSR), is demonstrated for Congressional redistricting in American states. SFSR is able to create thousands of valid redistricting plans, which may then be used as points of departure for public deliberation regarding how best to redistrict a given polity. The main objectives of this paper are: (i) to present SFSR in a broadly accessible form, including code that implements it and test data, so that it may be used for both civic deliberations by the public and for research purposes. (ii) to make the case for what SFSR essays to do, which is to approach redistricting, and districting generally, from a constraint satisfaction perspective and from the perspective of producing a plurality of feasible solutions that may then serve in subsequent deliberations. To further these goals, we make the code publicly available. The paper presents, for illustration purposes, a corpus of 11,206 valid redistricting plans for the Commonwealth of Pennsylvania (produced by SFSR), using the 2017 American Community Survey, along with descriptive statistics. Also, the paper presents 1,000 plans for each of the states of Arizona, Michigan, North Carolina, Pennsylvania, and Wisconsin, using the 2018 American Community Survey, along with descriptive statistics on these plans and the computations involved in their creation.

Cloud computing has evolved the big data technologies to a consolidated paradigm with SPaaS (Streaming processing-as-a-service). With a number of enterprises offering cloud-based solutions to end-users and other small enterprises, there has been a boom in the volume of data, creating interest of both industry and academia in big data analytics, streaming applications, and social networking applications. With the companies shifting to cloud-based solutions as a service paradigm, the competition grows in the market. Good quality of service (QoS) is a must for the enterprises, as they strive to survive in a competitive environment. However, achieving reasonable QoS goals to meet SLA agreement cost-effectively is challenging due to variation in workload over time. This problem can be solved if the system has the ability to predict the workload for the near future. In this paper, we present a novel topology-refining scheme based on a workload prediction mechanism. Predictions are made through a model based on a combination of SVR, autoregressive, and moving average model with a feedback mechanism. Our streaming system is designed to increase the overall performance by making the topology refining robust to the incoming workload on the fly, while still being able to achieve QoS goals of SLA constraints. Apache Flink distributed processing engine is used as a testbed in the paper. The result shows that the prediction scheme works well for both workloads, i.e., synthetic as well as real traces of data.

Surveys are commonly used to quantify public opinions of climate change and to inform sustainability policies. However, conducting large-scale population-based surveys is often a difficult task due to time and resource constraints. This paper outlines a machine learning framework—grounded in statistical learning theory and natural language processing—to augment climate change opinion surveys with social media data. The proposed framework maps social media discourse to climate opinion surveys, allowing for discerning the regionally distinct topics and themes that contribute to climate opinions. The analysis reveals significant regional variation in the emergent social media topics associated with climate opinions. Furthermore, significant correlation is identified between social media discourse and climate attitude. However, the dependencies between topic discussion and climate opinion are not always intuitive and often require augmenting the analysis with a topic’s most frequent n-grams and most representative tweets to effectively interpret the relationship. Finally, the paper concludes with a discussion of how these results can be used in the policy framing process to quickly and effectively understand constituents’ opinions on critical issues.

GOKASAR, ILGIN/0000-0001-9896-9220; Aydin, Omer Faruk/0000-0001-9345-3997 WOS:000535264000042 PubMed: 32130273 Increasing traffic congestion and the advancements in technology have fostered the growth of alternative transportation modes such as dynamic ride-sharing. Smartphone technologies have enabled dynamic ride-sharing to thrive, as this type of transportation aims to establish ride matches between people with similar routes and schedules on short notice. Many automated matching methods are designed to improve system performance; such methods include minimizing process time, minimizing total system cost or maximizing total distance savings. However, the results may not provide the maximum benefits for the participants. This paper intends to develop an algorithm for optimizing matches when considering participants' gender, age, employment status and social tendencies. The proposed matching algorithm also splits unmatched parts of drivers' routes and creates new travel requests to find additional matches using these unmatched parts. Accordingly, this paper performs an extensive simulation study to assess the performance of the proposed algorithm. The simulation results indicate that route splits may increase the number of matches significantly when there is a shortage of drivers. Furthermore, the paper demonstrates the effects and potential benefits of utilizing a social compatibility score in the objective function.

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.

In the case of a fire, the choice of exit in the highway tunnel is strictly limited by fire location, which seriously affects the evacuation time. A spontaneous or disorderly exit choice might result in a decreased evacuation efficiency and utilization rate of exits. In this paper, we propose a strategy to obtain the optimal exit choice based on fire location during highway tunnel evacuations. In our strategy, first, the vehicle distributions and locations of evacuating occupants are determined in the traffic simulation program VISSIM. The evacuation simulation software BuildingEXODUS is employed to obtain the corresponding parameters of the evacuation process and analyze the impacts of different fire locations on the evacuation time. During the analysis, the optimal productivity statistics (OPS) is selected as the evaluation index. Then, the feature points of the crowding occupants are captured by the fuzzy c-means (FCM) cluster algorithm. Next, based on the feature points, the relationship between the location of the fire and boundary of the optimal exit choice under the optimal OPS is obtained through the polynomial regression model. It is found that the R-squared(R2) and sum of squares for error (SSE) of the polynomial regression model, reflecting the accuracy estimation, are 98.02% and 2.79×10−4, respectively. Moreover, different fire locations impact the evacuation time of tunnel entrance and evacuation passageway. This paper shows that the location of the fire and boundary of optimal exit choice have a negative linear correlation. Taking the fire 110 m away from the evacuation passageway as an example, the OPS of our strategy can be decreased by 35.6% when compared with no strategies. Our proposed strategy could be applied to determine the location of variable evacuation signs to help evacuating occupants make optimal exit choices.

In this paper, we propose a hierarchical statistical model for a single repairable system subject to several failure modes (competing risks). The paper describes how complex engineered systems may be modelled hierarchically by use of Bayesian methods. It is also assumed that repairs are minimal and each failure mode has a power-law intensity. Our proposed model generalizes another one already presented in the literature and continues the study initiated by us in another published paper. Some properties of the new model are discussed. We conduct statistical inference under an objective Bayesian framework. A simulation study is carried out to investigate the efficiency of the proposed methods. Finally, our methodology is illustrated by two practical situations currently addressed in a project under development arising from a partnership between Petrobras and six research institutes.

Peer-to-Peer (P2P) lending provides convenient and efficient financing channels for small and medium-sized enterprises and individuals, and therefore it has developed rapidly since entering the market. However, due to the imperfection of the credit system and the influence of cyberspace restrictions, P2P network lending faces frequent borrower credit risk crises during the transaction process, with a high proportion of borrowers default. This paper first analyzes the basic development of China’s P2P online lending and the credit risks of borrowers in the industry. Then according to the characteristics of P2P network lending and previous studies, a credit risk assessment indicators system for borrowers in P2P lending is formulated with 29 indicators. Finally, on the basis of the credit risk assessment indicators system constructed in this paper, BP neural network is built based on the BP algorithm, which is trained by the LM algorithm (Levenberg-Marquardt), Scaled Conjugate Gradient, and Bayesian Regularization respectively, to complete the credit risk assessment model. By comparing the results of three mentioned training methodologies, the BP neural network trained by the LM algorithm is finally adopted to construct the credit risk assessment model of borrowers in P2P lending, in which the input layer node is 9, the hidden layer node is 11 and output layer node is 1. The model can provide practical guidance for China and other countries’ P2P lending platforms, and therefore to establish and improve an accurate and effective borrower credit risk management system.

In this paper, we describe a novel approach to the development of a reference standard for the quality control of complex natural products, which will assist in the assessment of their authenticity and purity. The proposed method provides a template for the selection of samples, which can be pooled to obtain a reference standard. A shortfall of such an approach is, however, that the pooled sample is static in nature and therefore unable to capture difference in processing conditions or natural variations triggered by geographical or climatic impacts over time. To address this, the paper also outlines the development of a dynamic reference standard, which allows for ongoing adjustments to future variations. The method employs High-Performance Thin Layer Chromatography (HPTLC) derived extract profiles processed by multivariate analysis. The development of the dynamic reference standard is illustrated using honey, a complex natural matrix, as an example.

Objective Some researchers have studied about early prediction and diagnosis of major adverse cardiovascular events (MACE), but their accuracies were not high. Therefore, this paper proposes a soft voting ensemble classifier (SVE) using machine learning (ML) algorithms. Methods We used the Korea Acute Myocardial Infarction Registry dataset and selected 11,189 subjects among 13,104 with the 2-year follow-up. It was subdivided into two groups (ST-segment elevation myocardial infarction (STEMI), non ST-segment elevation myocardial infarction NSTEMI), and then subdivided into training (70%) and test dataset (30%). Third, we selected the ranges of hyper-parameters to find the best prediction model from random forest (RF), extra tree (ET), gradient boosting machine (GBM), and SVE. We generated each ML-based model with the best hyper-parameters, evaluated by 5-fold stratified cross-validation, and then verified by test dataset. Lastly, we compared the performance in the area under the ROC curve (AUC), accuracy, precision, recall, and F-score. Results The accuracies for RF, ET, GBM, and SVE were (88.85%, 88.94%, 87.84%, 90.93%) for complete dataset, (84.81%, 85.00%, 83.70%, 89.07%) STEMI, (88.81%, 88.05%, 91.23%, 91.38%) NSTEMI. The AUC values in RF were (98.96%, 98.15%, 98.81%), ET (99.54%, 99.02%, 99.00%), GBM (98.92%, 99.33%, 99.41%), and SVE (99.61%, 99.49%, 99.42%) for complete dataset, STEMI, and NSTEMI, respectively. Consequently, the accuracy and AUC in SVE outperformed other ML models. Conclusions The performance of our SVE was significantly higher than other machine learning models (RF, ET, GBM) and its major prognostic factors were different. This paper will lead to the development of early risk prediction and diagnosis tool of MACE in ACS patients.