Local Prediction Method Research Articles

Conformal prediction with local weights: randomization enables robust guarantees

Abstract In this work, we consider the problem of building distribution-free prediction intervals with finite-sample conditional coverage guarantees. Conformal prediction (CP) is an increasingly popular framework for building such intervals with distribution-free guarantees, but these guarantees only ensure marginal coverage: the probability of coverage is averaged over both the training and test data, meaning that there might be substantial undercoverage within certain subpopulations. Instead, ideally we would want to have local coverage guarantees that hold for each possible value of the test point’s features. While the impossibility of achieving pointwise local coverage is well established in the literature, many variants of conformal prediction algorithm show favourable local coverage properties empirically. Relaxing the definition of local coverage can allow for a theoretical understanding of this empirical phenomenon. We propose randomly localized conformal prediction (RLCP), a method that builds on localized CP and weighted CP techniques to return prediction intervals that are not only marginally valid but also offer relaxed local coverage guarantees and validity under covariate shift. Through a series of simulations and real data experiments, we validate these coverage guarantees of RLCP while comparing it with the other local conformal prediction methods.

Local Scour Mechanisms and Prediction Methods Around Offshore Wind Turbine Foundations: Insights and Future Directions

Local Scour Mechanisms and Prediction Methods Around Offshore Wind Turbine Foundations: Insights and Future Directions

An in-depth investigation of global sea surface temperature behavior utilizing chaotic modeling.

Sea surface temperature (SST), with its complex and dynamic behavior, is a major driver of ocean-atmosphere interactions. The purpose of this study is to investigate the behavior of SST and its prediction using a chaotic approach. Average mutual information (AMI) and Cao methods were used to reconstruct the phase space. The Lyapunov exponent and correlation dimension were used to investigate chaos. The Lyapunov exponent index was used to predict SST with a 5-year average prediction horizon using the local prediction method between 2023 and 2027. The results showed a 3-month delay time for the Pacific and Antarctic Oceans, and a 2-month delay time for the Atlantic, Indian, and Arctic Oceans. The optimal embedding dimension for all oceans is between 6 and 7. Our analysis reveals that the dynamics of SST in all oceans exhibit varying degrees of chaos, as indicated by the correlation dimension. The local prediction method achieves relatively accurate short-term SST predictions due to the clustering of SST points around specific attractors in the phase space. However, in the long term, the accuracy of this method decreases as the points in the phase space of SST can spread randomly. The model performance ranking with a Percent Mean Relative Absolute Error shows that the Indian Ocean has the best performance compared to other oceans, while the Atlantic, Pacific, and Antarctic and Arctic Oceans are in the next ranks. This study contributes to understanding the dynamics of SST and has practical value for use in the development of climate models.

A Nonlinear Local Approximation Approach for Catchment Classification.

Catchment classification plays an important role in many applications associated with water resources and environment. In recent years, several studies have applied the concepts of nonlinear dynamics and chaos for catchment classification, mainly using dimensionality measures. The present study explores prediction as a measure for catchment classification, through application of a nonlinear local approximation prediction method. The method uses the concept of phase-space reconstruction of a time series to represent the underlying system dynamics and identifies nearest neighbors in the phase space for system evolution and prediction. The prediction accuracy measures, as well as the optimum values of the parameters involved in the method (e.g., phase space or embedding dimension, number of neighbors), are used for classification. For implementation, the method is applied to daily streamflow data from 218 catchments in Australia, and predictions are made for different embedding dimensions and number of neighbors. The prediction results suggest that phase-space reconstruction using streamflow alone can provide good predictions. The results also indicate that better predictions are achieved for lower embedding dimensions and smaller numbers of neighbors, suggesting possible low dimensionality of the streamflow dynamics. The classification results based on prediction accuracy are found to be useful for identification of regions/stations with higher predictability, which has important implications for interpolation or extrapolation of streamflow data.

Local Geometry-Based Intra Prediction for Octree-Structured Geometry Coding of Point Clouds

Point cloud compression (PCC) is crucial for efficient and flexible storage as well as feasible transmission of point clouds in practice. For geometry compression, one popular approach is the octree-based solution. The intra prediction mechanism utilizes the spatial correlation in the static point cloud to predict the occupancy bit of the octree node for entropy coding, reducing the spatial redundancy. In this study, two local geometry-based prediction methods are proposed following statistical and theoretical analyses: binary prediction, which outputs the binary state (i.e., occupied or unoccupied), and ternary prediction, which provides a third option other than occupied or unoccupied (i.e., not predicted). In comparison to the state-of-the-art, the proposed binary prediction offers the Bjontegaard delta rate (BD-rate) of −0.8% for lossy compression and the bits per input point (bpip) of 100.09% for lossless compression in average, respectively. The binary prediction reduces the computational complexity in terms of more than 20% decrease in decoding time. In particular, it also provides noticeable reduction of the memory usage during entropy coding. The proposed ternary prediction provides −1.2% BD-rate for lossy compression and 97.19% bpip for lossless compression in average, respectively, in comparison to the state-of-the-art. While achieving performance gain, it is considerably more computational efficient by saving about 18% decoding time. Due to these advantages, part of the proposed ternary prediction has been adopted by the ongoing MPEG standard of geometry-based point cloud compression (G-PCC).

GraphLncLoc: long non-coding RNA subcellular localization prediction using graph convolutional networks based on sequence to graph transformation.

The subcellular localization of long non-coding RNAs (lncRNAs) is crucial for understanding lncRNA functions. Most of existing lncRNA subcellular localization prediction methods use k-mer frequency features to encode lncRNA sequences. However, k-mer frequency features lose sequence order information and fail to capture sequence patterns and motifs of different lengths. In this paper, we proposed GraphLncLoc, a graph convolutional network-based deep learning model, for predicting lncRNA subcellular localization. Unlike previous studies encoding lncRNA sequences by using k-mer frequency features, GraphLncLoc transforms lncRNA sequences into de Bruijn graphs, which transforms the sequence classification problem into a graph classification problem. To extract the high-level features from the de Bruijn graph, GraphLncLoc employs graph convolutional networks to learn latent representations. Then, the high-level feature vectors derived from de Bruijn graph are fed into a fully connected layer to perform the prediction task. Extensive experiments show that GraphLncLoc achieves better performance than traditional machine learning models and existing predictors. In addition, our analyses show that transforming sequences into graphs has more distinguishable features and is more robust than k-mer frequency features. The case study shows that GraphLncLoc can uncover important motifs for nucleus subcellular localization. GraphLncLoc web server is available at http://csuligroup.com:8000/GraphLncLoc/.

Robustness- and Processing-Rate-Improved OFDR Based on Local Search and Kalman Prediction

Distributed optical fiber sensing based on optical frequency domain reflectometers is a promising technology to achieve high-density sensing information in harsh environments. Aiming at the major influence factor on robustness due to degradation of the similarity or correlation degree (SCD) between the reference and measurement spectra, in this letter, high-orders residual sampling error of nonlinearly swept laser source is found to cause random position deviations besides accumulated compensation based on thermal-/elastic-optic effect, and a local search and dynamic prediction method based on Kalman filter is proposed for position matching reference and measurement sensing gauges. Through this method, SCD can be improved when the accumulated compensation is invalid. Experiments indicate that a wide measurement range (highest temperature of ~ 450 °C and largest strain of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\sim 10~000~\mu \varepsilon$ </tex-math></inline-formula> ) under a spatial resolution of 5 mm, as well as high robustness and high accuracy, can be achieved along a 50-meter-long fiber under test. Besides, the computation amount can be reduced to 1/3.5 ~ 1/17.2. The advantages of this method include high robustness, wide measurement range, high processing rate, and excellent applicability with current OFDR systems.

DM3Loc: multi-label mRNA subcellular localization prediction and analysis based on multi-head self-attention mechanism.

Subcellular localization of messenger RNAs (mRNAs), as a prevalent mechanism, gives precise and efficient control for the translation process. There is mounting evidence for the important roles of this process in a variety of cellular events. Computational methods for mRNA subcellular localization prediction provide a useful approach for studying mRNA functions. However, few computational methods were designed for mRNA subcellular localization prediction and their performance have room for improvement. Especially, there is still no available tool to predict for mRNAs that have multiple localization annotations. In this paper, we propose a multi-head self-attention method, DM3Loc, for multi-label mRNA subcellular localization prediction. Evaluation results show that DM3Loc outperforms existing methods and tools in general. Furthermore, DM3Loc has the interpretation ability to analyze RNA-binding protein motifs and key signals on mRNAs for subcellular localization. Our analyses found hundreds of instances of mRNA isoform-specific subcellular localizations and many significantly enriched gene functions for mRNAs in different subcellular localizations.

Path-based extensions of local link prediction methods for complex networks

Link prediction in a complex network is a problem of fundamental interest in network science and has attracted increasing attention in recent years. It aims to predict missing (or future) links between two entities in a complex system that are not already connected. Among existing methods, local similarity indices are most popular that take into account the information of common neighbours to estimate the likelihood of existence of a connection between two nodes. In this paper, we propose global and quasi-local extensions of some commonly used local similarity indices. We have performed extensive numerical simulations on publicly available datasets from diverse domains demonstrating that the proposed extensions not only give superior performance, when compared to their respective local indices, but also outperform some of the current, state-of-the-art, local and global link-prediction methods.

Dynamic behavior of intermittent combustion oscillations in a model rocket engine combustor

We experimentally study the dynamic behavior of intermittent combustion oscillations by time series analysis in terms of nonlinear forecasting, symbolic dynamics, and statistical complexity, including the detection of the change in dynamical state based on symbolic dynamics and graph networks. We observe sudden switching back and forth between irregular small-amplitude and regular large-amplitude pressure fluctuations. The nonlinear local prediction method, permutation spectrum test, and the Rényi complexity–entropy curve clearly identify the possible presence of chaotic dynamics in small-amplitude pressure fluctuations during intermittent combustion oscillations. The network entropy in ordinal partition transition networks allows us to capture a significant change in dynamical state switching between chaotic oscillations and noisy limit cycle oscillations.

PSORTm: a bacterial and archaeal protein subcellular localization prediction tool for metagenomics data

MotivationMany methods for microbial protein subcellular localization (SCL) prediction exist; however, none is readily available for analysis of metagenomic sequence data, despite growing interest from researchers studying microbial communities in humans, agri-food relevant organisms and in other environments (e.g. for identification of cell-surface biomarkers for rapid protein-based diagnostic tests). We wished to also identify new markers of water quality from freshwater samples collected from pristine versus pollution-impacted watersheds.ResultsWe report PSORTm, the first bioinformatics tool designed for prediction of diverse bacterial and archaeal protein SCL from metagenomics data. PSORTm incorporates components of PSORTb, one of the most precise and widely used protein SCL predictors, with an automated classification by cell envelope. An evaluation using 5-fold cross-validation with in silico-fragmented sequences with known localization showed that PSORTm maintains PSORTb’s high precision, while sensitivity increases proportionately with metagenomic sequence fragment length. PSORTm’s read-based analysis was similar to PSORTb-based analysis of metagenome-assembled genomes (MAGs); however, the latter requires non-trivial manual classification of each MAG by cell envelope, and cannot make use of unassembled sequences. Analysis of the watershed samples revealed the importance of normalization and identified potential biomarkers of water quality. This method should be useful for examining a wide range of microbial communities, including human microbiomes, and other microbiomes of medical, environmental or industrial importance.Availability and implementationDocumentation, source code and docker containers are available for running PSORTm locally at https://www.psort.org/psortm/ (freely available, open-source software under GNU General Public License Version 3).Supplementary information Supplementary data are available at Bioinformatics online.

Software Aging Forecast Using Recurrent SOM with Local Model

Studies of software aging problems are important since they are related to QoS. Previous studies have used many methods to guarantee QoS. In this article, a recurrent self-organizing map with multi-layerperceptron is proposed to forecast resource consumption in a web server which suffered from a software aging problem. First, a resource consumption series in a web server is split into p dimensional space vectors. Second, the split series is clustered into local sets by using a recurrent self-organizing map. Last, a local prediction method called multi-layerperceptron is used to predict on each local set. The results indicated that the recurrent self-organizing map with multi-layerperceptron generates a slightly better estimation than multi-layerperceptron and autoregressive integrated moving average in the resource consumption predictions of system and application level of web server.

Comparison of the Global, Local and Semi-Local Chaotic Prediction Methods for Stock Markets: The Case of FTSE-100 Index

Chaotic prediction methods are classified as global, local and semi-local methods. In this paper, unlike the studies in the literature, it is aimed to compare all these methods together for stock markets in terms of prediction performance and to determine the best prediction method for stock markets. For this purpose, Multi-Layer Perceptron (MLP) neural networks from global methods, nearest neighbour method from local methods, radial basis functions from semi-local methods are used. The FTSE-100 index is selected to represent the stock market and applied the all methods to these data. The prediction performance is measured in term of root mean square error (RMSE) and normalized mean square error (NMSE). As a result of the analysis; it has been determined that the best prediction method for the FTSE-100 index is the semi-local method. While it is possible to make a maximum of 5 days prediction with global and local methods, it has been determined that up to 20 days prediction can be made with the semi-local prediction methods. The results show that semi-local prediction methods are successful in predicting the behaviour of stock market.

Chaotic prediction of vibration performance degradation trend of rolling element bearing based on Weibull distribution.

Rolling element bearings are used in all rotating machinery, and the degradation performance of rolling element bearings directly affects the performance of the machine. Therefore, high reliability prediction of the performance degradation trend of rolling element bearings has become an urgent research problem. However, the degradation characteristics of the rolling element bearings vibration time series are difficult to extract, and the mechanism of performance degradation is very complicated. The accurate physical model is difficult to establish. In view of the above reasons, based on the vibration performance data of rolling element bearings, a model of bearing performance degradation trend parameter based on wavelet denoising and Weibull distribution is established. Then, the phase space reconstruction of the series of bearing performance degradation trend parameter is carried out, and the prognosis is obtained by the improved adding weighted first-order local prediction method. The experimental results show that the bearing vibration performance degradation parameter can accurately depict the degradation trend of the bearing, and the reliability level is 91.55%; and the prediction of bearing performance degradation trend parameter is satisfactory: the mean relative error is only 0.0053% and the maximum relative error is less than 0.03%.

Critical evaluation of web-based prediction tools for human protein subcellular localization.

Human protein subcellular localization has an important research value in biological processes, also in elucidating protein functions and identifying drug targets. Over the past decade, a number of protein subcellular localization prediction tools have been designed and made freely available online. The purpose of this paper is to summarize the progress of research on the subcellular localization of human proteins in recent years, including commonly used data sets proposed by the predecessors and the performance of all selected prediction tools against the same benchmark data set. We carry out a systematic evaluation of several publicly available subcellular localization prediction methods on various benchmark data sets. Among them, we find that mLASSO-Hum and pLoc-mHum provide a statistically significant improvement in performance, as measured by the value of accuracy, relative to the other methods. Meanwhile, we build a new data set using the latest version of Uniprot database and construct a new GO-based prediction method HumLoc-LBCI in this paper. Then, we test all selected prediction tools on the new data set. Finally, we discuss the possible development directions of human protein subcellular localization. Availability: The codes and data are available from http://www.lbci.cn/syn/.

Evaluation of Dynamic Uncertainty of Rolling Bearing Vibration Performance

The variation trend, failure trajectory, probability distribution, and other information vary with time and working conditions for rolling bearing vibration performance, which makes the evaluation and prediction of the evolution process difficult for the performance reliability. In view of this, the chaos theory, grey bootstrap method, and maximum entropy method were effectively fused to propose a mathematical model for the dynamic uncertainty evaluation of rolling bearing vibration performance. After reconstructing the phase space of the vibration performance time series, four local prediction methods were applied to predict the vibration values of bearings to verify the effectiveness and validity of chaos theory. The estimated true value and estimated interval were calculated using the grey bootstrap method (GBM) and maximum entropy method. Finally, the validity of the proposed model was verified by comparing the probability that the original data fall into the estimated interval with the given confidence level. The experimental results show that the proposed method can effectively predict the variation trend and failure trajectory of the vibration performance time series so as to realize the dynamic monitoring of the evolution process for rolling bearing vibration performance online.

Deterministic chaotic dynamics in soil moisture across Nebraska

Soil moisture systems generally exhibit complex spatiotemporal patterns due to their nonlinear interactions with surrounding environments. In this paper, the possible existence of chaotic behaviors in soil moisture time series was investigated using the chaos theory, specifically based on the techniques of phase space reconstruction, correlation dimension (CD), largest Lyapunov exponent (LLE), and local approximation prediction (LAP) methods. Daily soil moisture data for six years along with different influencing factors were obtained for 35 Nebraska Mesonet (NM) stations with varying hydroclimatic conditions and soil properties. The results of CDs and LLEs revealed the presence of chaos in soil moisture systems, implying that soil moisture dynamics was controlled by deterministic systems with a limited number of governing variables. The results obtained by the LAP method offered further evidence on the chaotic behavior of soil moisture systems. Specifically, Median of CD values of 4.51, 4.06, 3.23, and 1.40 were obtained for soil moisture time series at the depths of 10, 25, 50, and 100 cm, respectively, indicating that the complexity of soil moisture systems decreased with increasing depth. Moreover, the correlations of CDs with different influencing factors showed that the dominant controls on soil moisture dynamics switched at different depths. At shallower depths (e.g., 10 and 25 cm), CDs were more correlated with meteorological forcings, while stronger correlations emerged between CDs and soil texture in deeper soil layers (e.g., 50 and 100 cm). As the first attempt to analyze the complexity of soil moisture systems from the perspective of the chaos theory, the results of this study offer additional avenues for understanding chaotic behaviors of soil moisture dynamics.

Temporal dynamics of monthly evaporation in Lake Urmia

As a UNESCO biosphere, Lake Urmia is a shallow hypersaline lake which is facing a rapid water surface degradation. Evaporation from the surface of the Lake, as a physical process which accelerates the Lake’s degradation, was evaluated using chaos theory. Seven hydrometeorological stations scattered around the Lake were selected, and a 40-year time span between October 1974 and September 2014 was used at each station. Missing data in time series was removed and the whole time series was tested for consistency, randomness, and presence of trend. Since evaporation at each station was measured by means of class A evaporation pan, time series at each station was multiplied by a pan coefficient to incorporate the effect of saline water and free water surface environment simultaneously. Measurement errors arising from assumption of zero evaporation in winter were removed from the time series using locally weighted scatterplot smoothing method after which unification of time series into a single time series is achieved. Results of the data transformation and information loss were monitored by means of auto-correlation, partial-auto-correlation, mutual information, power spectrum, false nearest neighbor, and correlation dimension. A local prediction method is then used to capture the temporal dynamics of the evaporation with consideration of an appropriate time delay and embedding dimension. Finally, the representative model was projected on a 3-dimensional phase space to evaluate the temporal dynamics of the evaporation. Results indicate that the chaotic approach shows accurate predictions in advance.

Semi-supervised neighborhoods and localized patient outcome prediction.

Robust statistical methods that can provide patients and their healthcare providers with individual predictions are needed to help guide informed medical decisions. Ideally an individual prediction would display the full range of possible outcomes (full predictive distribution), would be obtained with a user-specified level of precision, and would be minimally reliant on statistical model assumptions. We propose a novel method that satisfies each of these criteria via the semi-supervised creation of an axis-parallel covariate neighborhood constructed around a given point defining the patient of interest. We then provide non-parametric estimates of the outcome distribution for the subset of subjects in this neighborhood, which we refer to as a localized prediction. We implement local prediction methods using dynamic graphical methods which allow the user to vary key options such as the choice of the variables defining the neighborhood, and the size of the neighborhood.

Localization Prediction in Vehicular Ad Hoc Networks

Localization systems play a major role in many applications for vehicular ad hoc networks (VANETs). One of the most interesting problems to be solved in vehicular networks is how to provide anywhere and anytime highly accurate and reliable localization information. Unique characteristics of VANETs such as mobility constraints, driver’s behavior, and the high-speed displacement nature of vehicles cause rapid and constant changes in network topology, leading to dissemination of outdated localization information. To circumvent this problem, an alternative is the use of predicted future locations of vehicles. The main idea of this approach is to use the localization prediction as an extension of a data fusion localization system. In such an approach, a future position of a vehicle is predicted for a given future time and used to take advantage of a future time-space window of a vectorial trajectory rather than a static localization point. In this paper, we discuss this subject by studying and analyzing the use of localization prediction as natural way to improve VANET applications. We survey proposed approaches for localization, target tracking, and time series prediction techniques that can be used to estimate the future position of a vehicle. We also highlight their advantages and disadvantages through an analytical discussion visualizing its potential application scenarios in VANETs. We present a set of experiments that show the results of such techniques when applied to a realistic VANET scenario. 1 1 This work extends the original contribution proposed by Balico et al. [1] . The current version includes several new contributions: a more complete description of the localization prediction methods and its application to VANETs; additional comparisons with other algorithms; and an analytical discussion of the localization prediction algorithms.