Probability Graphs Research Articles

Probability of maximum values of stress concentration factors in tubular DKT-joints reinforced with FRP under axial loads

In the paper, the most suitable probability distributions for SCFmax in DKT-Joints stiffened with FRP under axial loading conditions are studied. To this end, 1296 models were generated and then analyzed in the ANSYS to provide five reliable samples. Created FE models were validated using previous laboratory and FE data. Afterward, to predict the appropriate probability distribution models, 12 different kinds of distributions were utilized to check the fit distribution curve to the samples. Next, the accuracy and reliability of the distribution curves were assessed with the help of goodness-of-fit tests, such as the Kolmogorov-Smirnov (KS) and the Chi-squared (CS). The results of the analysis reveal that the Birnbaum-Saunders distribution is the best option. Furthermore, based on the probability graphs, it was concluded that the developed distribution is suitable enough for the given data sets.

Mathematical model of single-channel search for signals of mobile radio communications with one degree of detection in the frequency-time domain.

In the context of a full-scale invasion and military operations for Ukraine's independence, the issues of radio monitoring of radio emission sources of telecommunication networks and systems are gaining special attention and require fundamentally new approaches to the level of informatization, technical implementation and increase of their efficiency. Today, the technical means of radio interception, monitoring and direction finding in the networks of mobile radio communication systems are realized in the form of software and hardware complexes, the most important performance indicators of which are considered to be speed, accuracy of detection and probability of recognition of mobile radio communication means with their information content. At the same time, these issues still remain problematic and require further development of methods and techniques for searching and detecting signals of mobile radio communications in both frequency and time telecommunication channels and their information processing. To solve this issue, the authors propose a mathematical model for searching for mobile radio signals in the frequency-time domain with one degree of detection. The description of the mathematical model for determining the spectral components of signals in the frequency and time domains is carried out using the basic provisions of the theory of directed probability graphs, geometric probabilities with its well-known problem of meeting in a given time interval, and the theoretical foundations of statistical information processing. The analysis of the proposed model shows that the probability of successful completion of the search for a signal with one degree of detection in the frequency-time domain for a given time depends on the value of the signal duration, the number of analyzed frequency channels, the time of signal analysis in each channel, and the probabilities of errors of the first and second kinds The article presents the results of calculations of the value of the probability of successful completion of the signal search as a function of the search time at different values of the analysis time. It is shown that the application of the mathematical model of single-channel search for signals of mobile radio communication means with one degree of detection in the frequency-time domain in practice will make it possible to determine the quality of the radio monitoring process and increase the efficiency of evaluating the spectral components of radio signals in terms of speed, detection accuracy and probability of recognition of mobile radio communication means with further determination of their information content.

A Joint Communication and Computation Design for Probabilistic Semantic Communications.

In this paper, the problem of joint transmission and computation resource allocation for a multi-user probabilistic semantic communication (PSC) network is investigated. In the considered model, users employ semantic information extraction techniques to compress their large-sized data before transmitting them to a multi-antenna base station (BS). Our model represents large-sized data through substantial knowledge graphs, utilizing shared probability graphs between the users and the BS for efficient semantic compression. The resource allocation problem is formulated as an optimization problem with the objective of maximizing the sum of the equivalent rate of all users, considering the total power budget and semantic resource limit constraints. The computation load considered in the PSC network is formulated as a non-smooth piecewise function with respect to the semantic compression ratio. To tackle this non-convex non-smooth optimization challenge, a three-stage algorithm is proposed, where the solutions for the received beamforming matrix of the BS, the transmit power of each user, and the semantic compression ratio of each user are obtained stage by stage. The numerical results validate the effectiveness of our proposed scheme.

Измерение транспортабельности и стандартного геометрического отклонения транспортабельности радиоактивных аэрозолей с помощью каскадного импактора

An approach is proposed for the operational measurement of transportability and standard geometric deviation of transportability of radioactive aerosols in industrial conditions. The cascade impactor is preliminarily calibrated (graduated) in transportability units - this is a preliminary single measurement of transportability at each impactor cascade. After calibrating the impactor in transportability units, the transportability and standard geometric deviation of the transportability of radioactive aerosols can be repeatedly measured periodically and/or as needed. To do this, it is enough to measure the activity of the radionuclide at each impactor cascade using any available method. Based on measurements of radionuclide activity at each impactor cascade,an integral transportability distribution function is constructed for all cascades in percentage, then on paper. for lognormal probability graphs, the logarithms of the transportability of the cascade elements are plotted along the ordinate axis (but transportability values are indicated), and the total amount of the fraction activity is plotted along the abscissa axis. The obtained points determine the straight line f(S), the required transportability is S50, where f(S50) = 50%, the desired standard geometric deviation is bg = S84/S50, where f(S84) = 84%. A patent for the invention RU 2801822 C2 was issued for the presented means of measuring transportability and standard geometric deviation of transportability of radioactive aerosols.

Effective Application of Artificial Intelligence Techniques in Security Risk Assessment and Dependency Analysis of Open Source Components

Abstract With the wide application of open source software, the security of open source components has become a non-negligible problem in software development. In this paper, based on the research on deep learning algorithms, the deep reinforcement learning algorithm DQN is proposed, and the DQN-LightGBM model is constructed by combining LightGBM classifiers to achieve better mining performance. This model introduces the attention mechanism and BiLSTM network, and the TextACBL vulnerability identification algorithm is proposed. In the end, the performance of the open source component vulnerability mining model is evaluated to investigate its impact on vulnerability identification, risk assessment, and dependency analysis of open source components. The results show that the performance of DQN-LightGBM model is above 0.9 in accuracy, checking accuracy, checking completeness, AUC value, and F1, and the mining completion time is only 54s, which is the best. The accuracy of TextACBL model in identifying the types of vulnerabilities is above 94%, and the vulnerability danger levels on the seven items measured are high, low, high, high, and high risk, respectively, medium risk, high risk, and medium risk. The differences in the global graph features of the identified normal and vulnerability samples are obvious, and there are frequent dependencies in the probability graphs of the opcodes of the vulnerability samples. This study allows for the assessment of security risks of open source components and the comprehensive, accurate, and efficient conduct of dependency analysis.

Investigation of The Role of The Quality of Servıces Offered at Fitness Centers on Customer Satısfactıon in Terms of Some Variables (Bayburt Example)

In this research, “The Analysis of the Role of Quality of Services Offered at Fitness Centers on Customer Satisfaction in Terms of Some Variables” is discussed. The intense pace of work in today's world has greatly worn people out physically and psychologically. This has led people to search for an environment where they can feel better socially, mentally, and physically. As a result, there has been an increase in the number of sports businesses and fitness centres, leading to competition among them. In this rapidly developing sector, service quality has become prominent, and the importance of customer satisfaction has been clearly demonstrated. Within this scope, the purpose of this thesis is to examine the role of service quality offered in fitness centers on customer satisfaction in terms of some variables. This research was carried out with volunteer participants who received service from fitness centers operating in the province of Bayburt. The study group consisted of a total of 304 people, including 166 men and 138 women. A personal information form and the "Perceived Service Quality Scale for Sports-Fitness Centers," developed by Uçan (2007), were used to collect the data. The scale consists of 31 items and 6 subscales. The obtained data and statistical analyses were evaluated using SPSS version 26 software. The pertinence of the variables to the normal distribution was examined using visual (histogram and probability graphs) and analytical methods. Descriptive analyses were submitted using the average and standard deviation. A one-way analysis of variance(ANOVA) test was used to compare the change in the process of time in the data with the normal distribution of the variables. The statistical significance level was accepted as p<0.05. In conclusion, service quality offered in fitness centers has a significant impact on customer satisfaction. Therefore, fitness centers should strive to provide quality service to increase customer satisfaction.Keywords: Fitness center, service quality, customer satisfaction

A framework for recalibrating pedotransfer functions using nonlinear least squares and estimating uncertainty using quantile regression

Pedotransfer functions (PTFs) have been developed for many regions to estimate values missing from soil profile databases. However, globally there are many areas without existing PTFs, and it is not advisable to use PTFs outside their domain of development due to poor performance. Further, developed PTFs often lack accompanying uncertainty estimations. To address these issues, a framework is proposed where existing equation-based PTFs are recalibrated using a nonlinear least squares (NLS) approach and validated on two regions of Canada; this process is coupled with the use of quantile regression (QR) to generate uncertainty estimates. Many PTFs have been developed to predict soil bulk density, so this variable is used as a case study to evaluate the outcome of recalibration. New coefficients are generated for existing soil bulk density PTFs, and the performance of these PTFs is validated using three case study datasets, one from the Ottawa region of Ontario and two from the province of British Columbia, Canada. The improvement of the performance of the recalibrated PTFs is evaluated using root mean square error (RMSE) and the concordance correlation coefficient (CCC). Uncertainty estimates produced using QR are communicated through the mean prediction interval (MPI) and prediction interval coverage probability (PICP) graphs. This framework produces dataset-specific PTFs with improved accuracy and minimized uncertainty, and the method can be applied to other regional datasets to improve the estimations of existing PTF model forms. The methods are most successful with large datasets and PTFs with fewer variables and minimal transformations; further, PTFs with organic carbon (OC) as one of or the sole input variable resulted in the highest accuracy.

Influence of twin-screw elements on dispersion of nano-clay in vinyl ester polymer composites using Taguchi’s orthogonal array technique

This work aims to experimentally investigate the influence of screw elements on the dispersion of Cloisite-15A in vinyl ester based on the design of experiments using MINITAB-V16 software. Experiments were designed considering two main factors such as Cloisite-15A loading (1, 2, 3, and 4 wt%) and type of screw elements with a varying number of kneading elements (type 1 with 55 mm, kneading elements and type 2 with 90 mm, kneading elements). The dispersion procedure of Cloisite-15A in vinyl ester was carried out by a combination of both ultrasonication and then twin-screw extrusion. The influence of these factors on the tensile strength and hardness was studied using an experimental layout possessing Taguchi’s L8 Orthogonal Array technique. ANOVA of the experimental results revealed the dispersion of Cloisite-15A with vinyl ester proved to be better when processed with type 2 screw elements having more kneading screws. The S/N ratio study showed that the Cloisite-15A loading had the greatest impact on the type 2 screw's tensile and hardness values for the Cloisite-15A/vinyl ester gel coats when treated at 230 rpm with 10 passes. The probability graphs led to the conclusion that, with a 95% confidence interval, all response values were distributed equally along the normal probability plot's trend. In order to achieve the best response in terms of mechanical strength, the Grey Relational Analysis (GRA) helped identify the best combination of process variables. This combination was known to be 4 wt% Cloisite-15A loading, with type 2 screw processed at 230 rpm with 10 passes. The SEM and XRD showed the absence of agglomeration and better exfoliation of Cloisite-15A in the gel coats with 4 wt% of clay loading.

Performance Assessment of Hybrid Fibre-Reinforced Concrete (FRC) under Low-Speed Impact: Experimental Analysis and Optimized Mixture

Fibre-reinforced concrete (FRC) has gained tremendous attention in many disciplines due to its high initial strength, favorable mechanical properties, structural lightness, and energy-absorbing properties. In this research, Barchip fibres, Forta, and Basalt are utilized to reinforce concrete under penetration effect loading to examine the energy absorption and impact strength characteristics. To determine the parameters of the percentage of fibres on the impact resistance properties, the Box–Behnken method as a subset of the response surface method (RSM) was used. A diagram of RSM is adopted to determine the optimal percentage of fibres for higher initial strength and energy absorption. Results obtained using Design-Expert software revealed an initial strength of 886.127 N and an optimal energy absorption of 4.9865 J. In addition, the calculated R2 values and normal probability graphs showed a fairy accurate correlation between the results of the experimental and mathematical approaches. Finally, this study evaluated the fracture surface, adhesion of the fibres to the concrete, and degradation modes of the fibres to pave the way for optimal utilization of these hybrid FRCs.

Effects of halloysite clay nanotubes on the energy absorption and failure mechanisms of glass/epoxy composite tubes subjected to quasi‐static axial crushing

AbstractThe capability of a structure to absorb enormous amount of energy is a crucial issue, particularly for structural components of vehicles, in decreasing the injury in case of collision. The current study investigates the impact of the presence of halloysite clay nanotubes (HNTs) on crashworthiness performance of glass/epoxy energy absorbent composite tubes. Specimens filled with 0, 1, 2, 3, and 4 wt% of HNTs were manufactured via wet‐wrapping process and tested under quasi‐static axial crushing. The crush load–displacement response, initial crushing load , average crushing load (), crushing force efficiency (CFE), absorbed energy (U), specific absorbed energy (SEA) for the proposed composite tubes were determined and discussed. The crushing behaviors for all specimens were traced. Results indicated that the specimens' failure mechanisms and the energy absorption capacities of nanofilled glass reinforced epoxy composites are controlled by wt% of HNTs. The presence of HNTs improves the energy absorbing capacities of glass/epoxy composites during the crushing process. Composite tubes filled with 4 wt% of HNTs are recommended as energy dissipating elements in vehicles. Weibull distribution was applied to show the failure probabilities and the scatter in the output data. The obtained failure probability graphs are important tools for helping the designers to understand and chose the suitable material for the required design.

0082 External Validation of an Enhanced Machine Learning Algorithm: Polysomnography-Based Narcolepsy-Like Feature Assessment and Clinician Notification in Routine Sleep Medicine Clinics

Abstract Introduction Polysomnography (PSG) contains quantitative information that, using machine learning (ML) algorithms, may aid the identification of type 1 narcolepsy. This study aimed to evaluate the utility of a previously developed quantitative tool (ML evaluation of PSG data) for detecting narcolepsy (types 1 and 2) in a “real-world” sleep clinic population. Methods Nocturnal PSG studies from a random sample of sleep clinic patients (narcolepsy, n=302; controls, n=21,535) were randomly split (1:1) into a training set and a validation set for algorithm testing. A separate, external PSG dataset was used for additional testing of the final model. Sleep stage probability graphs (hypnodensities) were estimated from PSGs on 15-second epochs using a previously developed convolutional neural network. Feature engineering was applied to hypnodensities to create a feature vector that was used to train a Gaussian process (GP) model to identify patients with a high probability of having narcolepsy. Features could be scaled to the 85th percentile, zero-mean and unit-variance, or unscaled. A recursive feature-elimination scheme was compared with training the GP kernel’s length scale for determining the subset of features that best discriminate narcolepsy and controls. A synthetic minority oversampling technique was applied in combination with random undersampling to balance the distribution of cases and controls in the training set. Several kernels and relevant hyperparameters were evaluated. Model performance (specificity and sensitivity) was examined using receiver operating characteristics with the goal of achieving an area under the curve (AUC) ≥0.80. Results The final GP model used a Matérn 5/2 covariance kernel with the length scale hyperparameter trained to determine the feature subset selection. Input features were normalized to zero-mean and unit-variance. The model had AUC=0.9960 and AUC=0.8014 for classifying narcolepsy in the training and validation sets, respectively. Sensitivity ranged from 73% to 65% when specificity was between 75% and 80%. Final performance evaluation of the model for classifying narcolepsy in an external PSG dataset is ongoing; results will be presented at the congress. Conclusion An ML-based algorithm can offer an objective, sensitive, and specific tool for alerting sleep clinicians about patients at risk for narcolepsy, using nocturnal PSG in general sleep medicine clinics. Support (If Any) Jazz Pharmaceuticals.

О МОДЕЛИРОВАНИИ СЛУЧАЙНЫХ ПРОЦЕССОВ В АГРОПРОМЫШЛЕННОМ КОМПЛЕКСЕ

Research was carried out with the aim of mathematical description of random deviations of the incoming flow of raw materials, to justify the necessary rational modes of operation of continuously operating units in the agro-industrial complex. The incoming flow is given by the average value and random deviations in different directions. The intensity of the deviation from the average value up or down can be different. The numerical characteristics of the incoming stream are determined by processing statistical observations. Two tasks are considered separately. In the first, in order to determine the time or cyclicity of response to changes in the incoming flow, their total number is studied. For this, a pure reproduction model was used. On the basis of the constructed model, the numerical values of the probability that by the time t there will be n deviations are calculated. Such a function Pn(t) has its maximum for any value of n. When solving the second problem, it is assumed that deviations of the average value of the incoming flow in different directions can partially or completely compensate for one another. To take into account such features of a random flow, a model of reproduction and death was used. The calculation of the corresponding probabilities is reduced to solving a system of differential equations, taking into account the normalization condition P0+P1+P2+ … Pn=1. Calculations have shown that if the deflection intensities in different directions are equal, the probability graphs Pn(t) have a common time asymptote. Consequently, deviations with the same intensity, having different signs, compensate for one another. If the intensities are not equal, then the probabilities Pn(t) go to their individual asymptotes. This means that the input stream with random deviations takes its stationary state with some reduced rate. The considered mathematical models make it possible to calculate the probabilistic values of the incoming flow parameters and their changes over time. This makes it possible to justify the necessary rational mode of operation of continuously operating units, taking into account random deviations of the incoming flow

О МОДЕЛИРОВАНИИ СЛУЧАЙНЫХ ПРОЦЕССОВ В АГРОПРОМЫШЛЕННОМ КОМПЛЕКСЕ

Research was carried out with the aim of mathematical description of random deviations of the incoming flow of raw materials, to justify the necessary rational modes of operation of continuously operating units in the agro-industrial complex. The incoming flow is given by the average value and random deviations in different directions. The intensity of the deviation from the average value up or down can be different. The numerical characteristics of the incoming stream are determined by processing statistical observations. Two tasks are considered separately. In the first, in order to determine the time or cyclicity of response to changes in the incoming flow, their total number is studied. For this, a pure reproduction model was used. On the basis of the constructed model, the numerical values of the probability that by the time t there will be n deviations are calculated. Such a function Pn(t) has its maximum for any value of n. When solving the second problem, it is assumed that deviations of the average value of the incoming flow in different directions can partially or completely compensate for one another. To take into account such features of a random flow, a model of reproduction and death was used. The calculation of the corresponding probabilities is reduced to solving a system of differential equations, taking into account the normalization condition P0+P1+P2+ … Pn=1. Calculations have shown that if the deflection intensities in different directions are equal, the probability graphs Pn(t) have a common time asymptote. Consequently, deviations with the same intensity, having different signs, compensate for one another. If the intensities are not equal, then the probabilities Pn(t) go to their individual asymptotes. This means that the input stream with random deviations takes its stationary state with some reduced rate. The considered mathematical models make it possible to calculate the probabilistic values of the incoming flow parameters and their changes over time. This makes it possible to justify the necessary rational mode of operation of continuously operating units, taking into account random deviations of the incoming flow

Probability fatigue life prediction of pin-loaded laminated composites by continuum damage mechanics-based Monte Carlo simulation

Predicting the failure probability of composite laminates under fatigue loading has many uncertainties, such as material properties, loading, boundary conditions, etc. In this paper, the failure probability of pin-loaded composite laminates is investigated. For this purpose, the continuum damage mechanics (CDM) theory has been combined with Monte Carlo Simulation (MCS) as a physics of failure tool to predict the failure of composite laminates in different directions (fibers, matrix, and shear) to calculate the probability of failure of the composite laminates under fatigue loading. Therefore, the failure function will be formed using the CDM theory and random variables identified. Finally, using the MCS, the failure probability will be obtained and the failure probability graphs extracted.

Multiple factors predict longer and shorter time-to-ulcer-free in people with diabetes-related foot ulcers: Survival analyses of a large prospective cohort followed-up for 24-months

AimsTo investigate factors independently associated with time-to-(being)-ulcer-free, time-varying effects and predict adjusted ulcer-free probabilities, in a large prospective cohort with diabetes-related foot ulcers (DFU) followed-up for 24 months. MethodsPatients presenting with DFU(s) to 65 Diabetic Foot Services across Queensland, Australia, between July-2011 and December-2017 were included. Demographic, comorbidity, limb, ulcer, and treatment factors were captured at presentation. Patients were followed-up until ulcer-free (all DFU(s) healed), amputation, death or two years. Factors associated with time-to-ulcer-free were investigated using both Cox proportional hazards and flexible parametric survival models to explore time-varying effects and plot predicted adjusted ulcer-free probability graphs. ResultsOf 4,709 included patients (median age 63 years, 69.5% male), median time-to-ulcer-free was 112 days (IQR:40->730), with 68.4% ulcer-free within two years. Factors independently associated with longer time-to-ulcer-free were each year of age younger than 60 years, living in a regional or remote area, smoking, neuropathy, peripheral artery disease (PAD), ulcer size >1 cm2, deep ulcer and mild infection (all p < 0.05). Time-varying effects were found for PAD and ulcer size limiting their association to six months only. Shorter time-to-ulcer-free was associated with recent DFU treatment by a podiatrist and receiving knee-high offloading treatment (both p < 0.05). Predicted adjusted ulcer-free probability graphs reported largest differences in time-to-ulcer-free over 24-months for geographical remoteness and PAD factors. ConclusionsMultiple factors predicted longer and shorter time-to-ulcer-free in people presenting with DFUs. Considering these factors, their time-varying effects and adjusted ulcer-free probability graphs, should aid the prediction of the likely time-to-(being)-ulcer-free for DFU patients.

Modeling and multiple optimization in face milling of hardfacing welding applied steel: Force, roughness, power

The coating performance for indexable inserts is very important for the main machinability indicators such as energy consumption, cutting force, and surface quality, especially in milling operations. The present study intend to the comprehensive analysis of machining conditions for above mentioned machinability indicators that can be considered most important for sustainability in hard milling of a worn machine part. First, the worn zone of the shearing blade made of X40CrMoV5-1 hot work tool steel was filled with electric arc welding. Then, hard milling experiments were carried out to analyze the performance of different coated carbide inserts in the machining of the hardfacing welded part. Experiments were performed by applying L18 experimental design for invariable cutting depth, three different cutting speed, and feed rate with PVD-AlTiCrN and CVD-TiCN/Al2O3/TiN coated inserts. Machining parameters for the responses namely the resultant force (Fr), surface roughness (Ra), and cutting power (Pc) were simultaneously optimized via applying Taguchi-based grey relationship analysis. Finally, predictive models for the responses were developed by RSM. The results obtained by both coatings shown that the Fr and Ra are mainly influenced by the feed rate, while cutting speed is the parameter that most influenced the Pc. The optimum results with regards to the responses were obtained with the PVD-AlTiCrN coated tool. In the current study, the developed quadratic models and probability graphs indicated that the responses were highly predictable.

Rockfall and Rainfall Correlation in the Anaga Nature Reserve in Tenerife (Canary Islands, Spain)

AbstractRockfalls are frequent and damaging phenomena that occur on steep or vertical slopes, in coastal areas, mountains and along coastal cliff. Water, in different forms, is the most common triggered factor of rockfalls. Consequently, we can consider that precipitation is the most influential factor for slope instabilities and it influences almost all other water parameters. Besides, the specific geology of the Anaga nature reserve in the volcanic island of Tenerife, together with its steep landscape, contributes to the instability of the slopes and frequent rockfalls. Recently, due to climate change and global warming, the annual precipitation/rainfall has declined but the number of heavy storms, associated with intense rainfall and strong winds, events that exceed precipitation thresholds in a brief period has increased which triggers slope movements. This paper describes the analysis of information on rainfall-induced rockfalls in Anaga, Tenerife (Canary Islands), to forecast rock failures of social significance and to improve the capability to respond and emergency decision making. To define reliable thresholds for a certain area, we analized information during the period 2010–2016, reconstructed the rockfall events, and statistically analyzed the historical rainfall conditions that led to landslides. The summary graph correlating precipitation to the probability of occurrence of an event was plotted. Statistical and probability graphs were made with the direct relationship between the number of rockfall events and total rainfall in that period by examining the maximum daily precipitation, not only on the day of the event but up to 3 days before. Hence, the results of this study would serve as a guide for the possible forecasting of rainfall-induced rockfalls, especially for road maintenance services, so that they can be on alert or mobilize the necessary resources in advance depending on the intensity of the expected rainfall.

Dynamic graph convolutional network for long-term traffic flow prediction with reinforcement learning

Exploiting deep learning techniques for traffic flow prediction has become increasingly widespread. Most existing studies combine CNN or GCN with recurrent neural network to extract the spatio-temporal features in traffic networks. The traffic networks can be naturally modeled as graphs which are effective to capture the topology and spatial correlations among road links. The issue is that the traffic network is dynamic due to the continuous changing of the traffic environment. Compared with the static graph, the dynamic graph can better reflect the spatio-temporal features of the traffic network. However, in practical applications, due to the limited accuracy and timeliness of data, it is hard to generate graph structures through frequent statistical data. Therefore, it is necessary to design a method to overcome data defects in traffic flow prediction. In this paper, we propose a long-term traffic flow prediction method based on dynamic graphs. The traffic network is modeled by dynamic traffic flow probability graphs, and graph convolution is performed on the dynamic graphs to learn spatial features, which are then combined with LSTM units to learn temporal features. In particular, we further propose to use graph convolutional policy network based on reinforcement learning to generate dynamic graphs when the dynamic graphs are incomplete due to the data sparsity i sue. By testing our method on city-bike data in New York City, it demonstrates that our model can achieve stable and effective long-term predictions of traffic flow, and can reduce the impact of data defects on prediction results.

Time-variant reliability-based prediction of COVID-19 spread using extended SEIVR model and Monte Carlo sampling

A probabilistic method is proposed in this study to predict the spreading profile of the coronavirus disease 2019 (COVID-19) in the United State (US) via time-variant reliability analysis. To this end, an extended susceptible-exposed-infected-vaccinated-recovered (SEIVR) epidemic model is first established deterministically, considering the quarantine and vaccination effects, and then applied to the available COVID-19 data from US. Afterwards, the prediction results are described as a time-series of the number of people infected, recovered, and dead. Upon introducing the extended SEIVR model into a limit-state function and defining the model parameters including transmission, recovery, and mortality rates as random variables, the problem is transformed into a reliability model and analyzed by the Monte Carlo sampling. The findings are subsequently given in the form of exceedance probabilities (EPs) of the three main outputs, namely, the maximum number of infected cases, the total number of recovered cases, and the total number of fatal cases. Afterwards, by incorporating time into the formulation of the reliability problem, the EPs are calculated over time and presented as 3D probability graphs, illustrating the relationship between the number of cases affected (i.e., infected, recovered, or dead), exceedance probability, and time. The results for the US demonstrate that, by the end of 2021, the number of the infected (active) cases decreases to 0.8 million and number of cases recovered and fatalities increases to 41.3 million and 0.6 million, respectively.

Analysis of Sanda action based on CCNN model of IBS distance measurement

IBS is a similarity measurement method of symbol sequences based on order statistics, and CCNN is a method based on CNN feature extraction and IBS distance measurement, which can construct crossover probability graph through image crossover comparison. IBS distance and Noribs distance are used to define the similarity between crossover probability graphs. For Sanda movement, it is difficult to carry out big data analysis with a small number of samples and the movement style of athletes will change greatly. In this paper, a CCNN model based on IBS distance measurement is proposed to analyze the action of Sanda. Firstly, the motion pictures obtained were de-noised and then simplified into a sequence diagram of human skeleton nodes by Delaunay triangulation. Then, 80% of the samples were input into the CCNN network for training and 20% for algorithm verification. The experiment found that in the case of a small number of samples, the accuracy of the simplified image analysis was 10% higher than that of the unsimplified image. In addition, compared with the accuracy of K-distance classification, Bayesian network classification and decision tree classification, it is found that the model can improve the accuracy by 2%-11.75% due to the small number of samples, and has higher accuracy and applicability.