Smoothing Algorithm Research Articles

Ensemble transport smoothing. Part I: Unified framework

Smoothers are algorithms for Bayesian time series re-analysis. Most operational smoothers rely either on affine Kalman-type transformations or on sequential importance sampling. These strategies occupy opposite ends of a spectrum that trades computational efficiency and scalability for statistical generality and consistency: non-Gaussianity renders affine Kalman updates inconsistent with the true Bayesian solution, while the ensemble size required for successful importance sampling can be prohibitive. This paper revisits the smoothing problem from the perspective of measure transport, which offers the prospect of consistent prior-to-posterior transformations for Bayesian inference. We leverage this capacity by proposing a general ensemble framework for transport-based smoothing. Within this framework, we derive a comprehensive set of smoothing recursions based on nonlinear transport maps and detail how they exploit the structure of state-space models in fully non-Gaussian settings. We also describe how many standard Kalman-type smoothing algorithms emerge as special cases of our framework. A companion paper [35] explores the implementation of nonlinear ensemble transport smoothers in greater depth.

Smooth particle mesh Ewald-integrated stochastic Lanczos many-body dispersion algorithm.

We derive and implement an alternative formulation of the Stochastic Lanczos algorithm to be employed in connection with the Many-Body Dispersion model (MBD). Indeed, this formulation, which is only possible due to the Stochastic Lanczos' reliance on matrix-vector products, introduces generalized dipoles and fields. These key quantities allow for a state-of-the-art treatment of periodic boundary conditions via the O(Nlog(N)) Smooth Particle Mesh Ewald (SPME) approach which uses efficient fast Fourier transforms. This SPME-Lanczos algorithm drastically outperforms the standard replica method which is affected by a slow and conditionally convergence rate that limits an efficient and reliable inclusion of long-range periodic boundary conditions interactions in many-body dispersion modelling. The proposed algorithm inherits the embarrassingly parallelism of the original Stochastic Lanczos scheme, thus opening up for a fully converged and efficient periodic boundary conditions treatment of MBD approaches.

Convergence of a smoothing algorithm for horizontal linear complementarity problem with a nonmonotone line search

In this paper, we present a nonmonotone smoothing Newton type algorithm for solving the horizontal linear complementarity problem. We show that the proposed algorithm is globally convergent under an assumption that has the column -property. Such an assumption is weaker than those required by most other smoothing Newton algorithms. The preliminary numerical results are reported.

Assessing the security status and future scenarios of the Mediterranean region through the water-energy-food nexus

Over the past decades, the Mediterranean region has faced significant challenges due to the impacts of climate change and ongoing conflicts. This study proposes an assessment of the region's security status and potential future scenarios through the lens of the water-energy-food nexus, utilising indicators that align with the Sustainable Development Goals (SDGs). These indicators include agricultural yields, value-added, and land variations, water and sanitation services, income and inequality, use of renewable energy, carbon footprints, and political stability. To evaluate the situation, this analysis applies Ward's hierarchical clustering algorithm to group countries based on these indicators, examining the average terms and the years 2006 and 2015 for comparative analysis. Additionally, an exponential smoothing algorithm forecasts future trends and generates clusters for the years 2030 and 2050. By computing an index of convergence for each cluster and indicator, this contribution identifies areas of particular interest from a security perspective. The findings of this analysis reveal a growing polarisation within the Mediterranean region, with European countries and Israel forming one distinct group, and African and Eastern countries (excluding Israel) forming another. Notably, recurring disparities exist in variables such as agricultural land, political stability, violence, income per capita, and agricultural value added. Conversely, certain variables, including the Gini coefficient, prevalence of overweight population, and access to drinking water services, show signs of convergence. These results shed light on potential areas of both conflict and cooperation in the Mediterranean region, highlighting the importance of addressing the challenges posed by climate change. By understanding the geopolitical dynamics and identifying key areas of concern, policymakers can develop informed strategies to promote stability and sustainable development in the region.

Inference and forecasting phase shift regime of COVID-19 sub-lineages with a Markov-switching model.

The occurrences and domination of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) variants are still crucial factors for determining the coronavirus disease 19 (COVID-19) policies. We collected weekly Phylogenetic Assignment of Named Global Outbreak sub-lineages, naming genetically distinct lineages of SARS-CoV-2, including variants of concern, in the United Kingdom, South Africa, South Korea, Denmark, Germany, the United States, and worldwide. This study included 12,296,756 samples of the max share of the sub-lineages from the 33rd week of 2020 to the 40th week of 2022. This study conducted a two-state Markov-switching model to estimate the probability of the phase shift state and predicted the probability of each regime with the Hamilton filter and Kim's smoothing algorithm. We discovered different weekly patterns based on dominant SARS-CoV-2 variants in target area. Due to differences in containment policies and outbreak waves, we observed a time lag in dominant variants in these countries. Using the inferred probability of the phase shift regime for forecasting, it showed significant probabilities that the stable phase will still be stable in the next week. It also showed significant probabilities that the unstable phase will still be unstable in the next week. Our findings present the probability of observing the phase shift regime each week. Until a new SARS-CoV-2 variant occurs, the regime tended to stay with a low probability of phase shift regime. When a new SARS-CoV-2 variant would occur, the regime would immediately react and change the probability. We propose the Markov-switching model to determine COVID-19 policies and predict SARS-CoV-2 variants. IMPORTANCE Using regime-switching models, we attempted to determine whether there is a link between changes in severe acute respiratory syndrome coronavirus 2 (SARS-Cov-2) variants and infection waves, as well as forecasting new SARS-Cov-2 variants. We believe that our study makes a significant contribution to the field because it proposes a new approach for forecasting the ongoing pandemic, and the spread of other infectious diseases, using a statistical model which incorporates unpredictable factors such as human behavior, political factors, and cultural beliefs.

Bone mineral density saturation as influenced by the visceral adiposity index in adults older than 20 years: a population-based study

ObjectiveThe goal of this research was to determine whether or not there is a saturation effect and whether or not the visceral adiposity index (VAI) correlates with bone mineral density (BMD) in adult Americans.MethodsThis study used multivariate logistic regression models to examine the association between VAI and total femur BMD, drawing on the most up-to-date data from the National Health and Nutrition Examination Survey (NHANES) between 2007 and 2018. Saturation levels and non-linear connections were calculated using a smooth curve-fitting algorithm and an investigation of saturation effects. Subgroup analyses and interaction tests were also conducted.ResultsThis study ultimately recruited 6257 individuals aged 20 years or older. According to multivariate regression analysis, those with high VAI scores exhibited higher total femur BMD. Total femur BMD was greater in the highest VAI quartile (Q4: 0.060 g/cm2) after adjustment than in the lowest VAI quartile (Q1) (P < 0.05). After controlling for variables, subgroup analysis failed to reveal any significant interaction effects. Furthermore, the study determined that VAI and BMD exhibited a specific saturation effect through the investigation of the saturation effect and the fitting of smooth curves. Saturation effect investigation of total femur BMD using VAI revealed a saturation value of 3.3.ConclusionThe present study uncovered a non-linear relationship between VAI and total femur BMD, which exhibited a saturation effect.

Pseudo-ground Truth Trajectory From Contaminated Data of Object Tracking Using Smoothing Algorithms

Pseudo-ground Truth Trajectory From Contaminated Data of Object Tracking Using Smoothing Algorithms

A user-friendly guide to using distance measures to compare time series in ecology.

Time series are a critical component of ecological analysis, used to track changes in biotic and abiotic variables. Information can be extracted from the properties of time series for tasks such as classification (e.g., assigning species to individual bird calls); clustering (e.g., clustering similar responses in population dynamics to abrupt changes in the environment or management interventions); prediction (e.g., accuracy of model predictions to original time series data); and anomaly detection (e.g., detecting possible catastrophic events from population time series). These common tasks in ecological research all rely on the notion of (dis-) similarity, which can be determined using distance measures. A plethora of distance measures have been described, predominantly in the computer and information sciences, but many have not been introduced to ecologists. Furthermore, little is known about how to select appropriate distance measures for time-series-related tasks. Therefore, many potential applications remain unexplored. Here, we describe 16 properties of distance measures that are likely to be of importance to a variety of ecological questions involving time series. We then test 42 distance measures for each property and use the results to develop an objective method to select appropriate distance measures for any task and ecological dataset. We demonstrate our selection method by applying it to a set of real-world data on breeding bird populations in the UK and discuss other potential applications for distance measures, along with associated technical issues common in ecology. Our real-world population trends exhibit a common challenge for time series comparisons: a high level of stochasticity. We demonstrate two different ways of overcoming this challenge, first by selecting distance measures with properties that make them well suited to comparing noisy time series and second by applying a smoothing algorithm before selecting appropriate distance measures. In both cases, the distance measures chosen through our selection method are not only fit-for-purpose but are consistent in their rankings of the population trends. The results of our study should lead to an improved understanding of, and greater scope for, the use of distance measures for comparing ecological time series and help us answer new ecological questions.

A New Smoothing Algorithm to Solve a System of Nonlinear Inequalities

In this study, the system of nonlinear inequalities (SNI) problem is investigated. First, a SNI is reformulated as a system of nonsmooth and nonlinear equations (SNNE). Second, a new smoothing technique for the "$\max$" function is proposed and the smoothing technique is employed for each element of the SNNE. Then, a new smoothing algorithm is developed in order to solve SNNE by combining the smoothing technique with the iterative method. The new algorithm is applied to some numerical examples to show the efficiency of our algorithm.

Comparison of Triple Exponential Smoothing and Support Vector Regression Algorithms in Predicting Drug Usage at Puskesmas

Comparison of Triple Exponential Smoothing and Support Vector Regression Algorithms in Predicting Drug Usage at Puskesmas

Penerapan Algoritma Adaptive Response Rate Exponential Smoothing Terhadap Business Intelligence System

PT. XYZ is one of the companies in the field of furniture sales by offering its flagship product, namely spring bed. The company's business continues to grow every year, of course, the company must be able to complete its work quickly and precisely. One of the main problems of the company is that the increase in company sales is still not able to cover the company's expenses and sometimes the company still suffers losses. This happens because companies often make mistakes in purchasing product inventory stock. Not all types of spring beds sell well, so sometimes purchases are made of the type of spring bed that is not selling well, which results in stock accumulation and instability of the company's cash inflow and outflow. In this study, a Business Intelligence System was built, which is a form of information technology implementation to store, collect and analyze data into knowledge so that it can be used as prediction results. The prediction algorithm used in this research is the Adaptive Response Rate Exponential algorithm. The expected goal of this research is to build a Business Intelligence System that can calculate product sales predictions in the following month using the Adaptive Response Rate Exponential Smoothing (ARRES) algorithm. Based on the results of the MAPE test, it can be concluded that the percentage of prediction accuracy from the ARRES algorithm on the sales transaction data of PT. XYZ is 53.33% which is categorized as quite accurate and the percentage of prediction error from the ARRES method is 46.67% which is categorized as reasonable

LE-YOLOv5: A Lightweight and Efficient Road Damage Detection Algorithm Based on Improved YOLOv5

Road damage detection is very important for road safety and timely repair. The previous detection methods mainly rely on humans or large machines, which are costly and inefficient. Existing algorithms are computationally expensive and difficult to arrange in edge detection devices. To solve this problem, we propose a lightweight and efficient road damage detection algorithm LE-YOLOv5 based on YOLOv5. We propose a global shuffle attention module to improve the shortcomings of the SE attention module in MobileNetV3, which in turn builds a better backbone feature extraction network. It greatly reduces the parameters and GFLOPS of the model while increasing the computational speed. To construct a simple and efficient neck network, a lightweight hybrid convolution is introduced into the neck network to replace the standard convolution. Meanwhile, we introduce the lightweight coordinate attention module into the cross-stage partial network module that was designed using the one-time aggregation method. Specifically, we propose a parameter-free attentional feature fusion (PAFF) module, which significantly enhances the model’s ability to capture contextual information at a long distance by guiding and enhancing correlation learning between the channel direction and spatial direction without introducing additional parameters. The K-means clustering algorithm is used to make the anchor boxes more suitable for the dataset. Finally, we use a label smoothing algorithm to improve the generalization ability of the model. The experimental results show that the LE-YOLOv5 proposed in this document can stably and effectively detect road damage. Compared to YOLOv5s, LE-YOLOv5 reduces the parameters by 52.6% and reduces the GFLOPS by 57.0%. However, notably, the mean average precision (mAP) of our model improves by 5.3%. This means that LE-YOLOv5 is much more lightweight while still providing excellent performance. We set up visualization experiments for multialgorithm comparative detection in a variety of complex road environments. The experimental results show that LE-YOLOv5 exhibits excellent robustness and reliability in complex road environments.

Gravity modulation, thermal radiation and viscous dissipation impact on heat transfer and magnetic flux across gravity-driven magnetized circular cylinder

Heat transfer in burners, combustion engines and energy consumption through nuclear explosions is significantly influenced by radiations. In missile nozzles, nuclear power plants for aerospace uses, and gaseous-core nuclear rocket systems, the radiations are considered for evaluating heating significance. The significance of present study is to compute heat and magnetic flux behavior across various angles π/6, π/4, π/3, π/2, π and 3π/2 of gravity-driven magnetized cylinder under gravity modulation, thermal radiation and viscous dissipation. The aim of this research is to examine wave oscillations in heat and current density along magnetic-driven circular cylinder. The computational and mathematical model is evaluated in terms of coupled periodic partial differential equations (PDE). The appropriate dimensionless variables are used to convert governing periodic model into non-dimensional form. The dimensionless formulations are transformed into steady and oscillatory form. To explore physical and numerical findings, the finite difference method with primitive formulations is applied for smooth algorithm in FORTRAN language. The significant results are explored for various pertinent parameters. The oscillatory magnetic flux and heat transmission are plotted by using steady state temperature and magnetic boundary layers. It is found that the prominent amplitude in velocity increases as reduced gravity increases at each angle. The maximum oscillating amplitude in heat transfer enhances at each angle as viscous dissipations and solar radiation increases.

An Accelerated Algorithm for 3D Inversion of Gravity Data Based on Improved Conjugate Gradient Method

The 3D inversion algorithm for gravity data based on a smooth model constraint has been proven to yield a reasonable density distribution. However, as the amount of observed data and model parameters increases, the algorithm experiences issues with high memory consumption and prolonged computation time. Therefore, the corresponding problem in interpreting gravity inversion lies in developing a fast inversion algorithm. The conventional smooth model constraint inversion algorithm, based on regularization theory, requires the introduction of a model weighting function with a large matrix, and involves storage and operation of a large matrix with intermediate variables during inversion iteration, contributing significantly to the prolonged computation time. In this paper, a diagonal weight matrix is represented by vectorization, and the intermediate variable of the large matrix type in the iteration is replaced with the combination of a small matrix and a vector. Additionally, the algorithm flow of the conjugate gradient method is further optimized to minimize the number of vectors that need to be stored during iteration. As a result of these optimizations, the memory consumption of the algorithm during the operation process is successfully reduced. Finally, the experiments demonstrate the successful development of a fast 3D inversion algorithm for gravity data. Specifically, for a 80 × 80 × 20 mesh number inversion, our accelerated algorithm achieves an average speed of ~0.5 s per iteration, and the iterative process speeds up by a factor of 1000, providing an effective strategy for the fast inversion of large-scale data.

Dynamic robust analysis of IoV link delay in cellular Telematics and smart edge networking base on deep reinforcement learning

Applications for the Internet of Vehicles (IoV) are progressing from more fundamental ones like those for traffic efficiency, road safety, and information services to more sophisticated ones like autonomous driving and intelligent mobility that have a variety of connectivity requirements. Therefore, IoV communication systems must overcome various obstacles in order to enable a variety of IoV applications. Attacks on TSP servers are the major target of telematics attack threat events. This article analyses data security monitoring from the vehicle end to the TSP platform, as well as gathering and analysing the status and intelligence of linked vehicles, in order to develop a Telematics TSP server attack monitoring system. Experiments show that the error detection rate of the benchmark algorithms decreases significantly as the error rate of vehicle speed data increases, with the exponential smoothing algorithm showing the largest decrease in the error detection rate. However, the proposed combined model is very close to the error detection rate of the benchmark algorithm at the later stages when the error rate is high, with an error detection rate of more than 80%.It provides great assistance for anomaly detection and data recovery, especially in researching key technologies for remote information processing data security and reliability, greatly improving their performance.

Detection and evolution of disaster sources in high slopes of open-pit mines based on time-lapse high-density electricity method

High and steep slopes in open pit mines used for ore production require careful monitoring to ensure stability and safeguard lives, property, and social welfare. Understanding the evolutionary characteristics of hazard sources within these slopes is crucial for effective slope management. This article presents a novel approach to identify the evolution of hazard sources within slopes by utilizing the derivative of normalized inversion data versus time as a characteristic feature. To analyze the evolution of hazard sources, raw apparent resistivity data collected at different times are processed using smoothing and wavelet denoising algorithms to reduce noise. Geological constraints are then applied to the collected data through the parametric region method. The least squares method is employed for independent inversion, and the inversion results are standardized. Subsequently, the standardized inversion results are used to derive the derivative of resistivity versus time equation, which reveals the evolution of hazard sources within the slope. A case study is conducted on a large open pit rocky slope to analyze the effectiveness of the proposed approach. The results demonstrate the successful reduction of noise through the smoothing and wavelet threshold denoising algorithms, effectively suppressing interference caused by acquisition equipment and environmental electromagnetic noise. The application of the parametric region method with geological constraints highlights the spatial and temporal evolution characteristics of hazard sources within the slope. The findings indicate varying degrees of evolution of hazard sources within the slope, with significant changes observed mainly in the shallow part influenced by water erosion and blasting vibration. Areas with lithological stability show minimal changes, while original hazard source areas have evolved to different extents, distinguishable based on the size and sparsity of contour values. By combining inversion data analysis, noise reduction techniques, and geological constraints, the proposed approach provides valuable insights into the evolution of hazard sources within slopes. This information can aid in the development of effective slope management strategies in open pit mines, contributing to enhanced safety and protection of valuable assets.

Global contextual feature aggregation networks with multiscale attention mechanism for mechanical fault diagnosis under non-stationary conditions

In recent years, the rapid development of convolutional neural networks (CNNs) has significantly advanced the progress of intelligent fault diagnosis. Most currently-available CNN-based diagnostic models are built on the premise that the monitored machine operates under stable conditions. However, in real-world scenarios, rotary machinery usually operates at varying speeds, making the fault-related pulse features susceptible to noise oversaturation. To extract discriminative features from mechanical signals under non-stationary conditions, a global contextual feature aggregation network (GCFAN) is developed in this paper. To begin with, a global contextual module (GCM) is embedded in the CNN architecture to explore multimodal features. Then, a multiscale attention module (MSAM) is introduced to guide the model to focus on global and local discriminative information. Further, a multiscale feature enhancement module (MFEM) is established to enlarge the receptive field and eliminate useless features. Finally, the GCFAN architecture is constructed based on these improvements. To achieve favourable diagnostic results under fluctuating variable speed conditions, we apply the label smoothing algorithm and the AMSGrad algorithm to assist the training of the model. Two case studies using the benchmark variable speed bearing dataset and the HF-MS variable speed gearbox dataset were carried out to test the practicality of the developed approach. Experimental results demonstrated that the developed GCFAN performs better than seven state-of-the-art approaches.

Effects of data smoothing and recurrent neural network (RNN) algorithms for real-time forecasting of tunnel boring machine (TBM) performance

Tunnel boring machines (TBMs) have been widely utilised in tunnel construction due to their high efficiency and reliability. Accurately predicting TBM performance can improve project time management, cost control, and risk management. This study aims to use deep learning to develop real-time models for predicting the penetration rate (PR). The models are built using data from the Changsha metro project, and their performances are evaluated using unseen data from the Zhengzhou Metro project. In one-step forecast, the predicted penetration rate follows the trend of the measured penetration rate in both training and testing. The autoregressive integrated moving average (ARIMA) model is compared with the recurrent neural network (RNN) model. The results show that univariate models, which only consider historical penetration rate itself, perform better than multivariate models that take into account multiple geological and operational parameters (GEO and OP). Next, an RNN variant combining time series of penetration rate with the last-step geological and operational parameters is developed, and it performs better than other models. A sensitivity analysis shows that the penetration rate is the most important parameter, while other parameters have a smaller impact on time series forecasting. It is also found that smoothed data are easier to predict with high accuracy. Nevertheless, over-simplified data can lose real characteristics in time series. In conclusion, the RNN variant can accurately predict the next-step penetration rate, and data smoothing is crucial in time series forecasting. This study provides practical guidance for TBM performance forecasting in practical engineering.

Graph Machine Learning for Improved Imputation of Missing Tropospheric Ozone Data.

Gaps in the measurement series of atmospheric pollutants can impede the reliable assessment of their impacts and trends. We propose a new method for missing data imputation of the air pollutant tropospheric ozone by using the graph machine learning algorithm "correct and smooth". This algorithm uses auxiliary data that characterize the measurement location and, in addition, ozone observations at neighboring sites to improve the imputations of simple statistical and machine learning models. We apply our method to data from 278 stations of the year 2011 of the German Environment Agency (Umweltbundesamt - UBA) monitoring network. The preliminary version of these data exhibits three gap patterns: shorter gaps in the range of hours, longer gaps of up to several months in length, and gaps occurring at multiple stations at once. For short gaps of up to 5 h, linear interpolation is most accurate. Longer gaps at single stations are most effectively imputed by a random forest in connection with the correct and smooth. For longer gaps at multiple stations, the correct and smooth algorithm improved the random forest despite a lack of data in the neighborhood of the missing values. We therefore suggest a hybrid of linear interpolation and graph machine learning for the imputation of tropospheric ozone time series.

Novel Paradigm for Steel Joints in Gridshell Structures: from Structural Optimization to Advanced Construction

AbstractNovel integrated computer‐aided paradigm/workflow for the topology optimization (TO) and additive manufacturing (AM) of steel joints in gridshell structures is proposed. The architecture scheme of gridshell structure was first established and numerically analyzed through Grasshopper parametric platform. Based on the extracted joint geometric parameters and the corresponding loading conditions, the initial joint structures were parametrically modelled using the subdivision surface method. Further parametric TO design was accomplished by the bi‐directional evolutionary structural optimization (BESO) method on the basis of cloud computing server. A series of mesh smoothing and reverse modelling algorithms were applied to the optimized joint to obtain a closed smooth surface in the NURBS form, which was then output as STL file for additive manufacturing. One typical optimized joint was additively manufactured using selective laser melting. The proposed workflow can be extended to a much wider range of spatial structures with various joint types.