Search

Accurate tracing of crude oil origins is essential for thwarting deceptive trade practices, including origin falsification to evade taxes, thereby preventing economic losses and security threats for importing nations. Traditional crude oil origin determination methods require complex sample preparation, expensive instrumentation, and stable testing environments, rendering them impractical for real-time analysis at locations such as ports. This paper introduces a novel approach utilizing near-infrared spectroscopy (NIRS) combined with deep learning algorithms to expedite and enhance the precision of crude oil source identification. To effectively eliminate outliers, an improved Mahalanobis distance is introduced, incorporating regularization principles and global-local concepts. This approach addresses the challenges of inverting covariance matrices in high-dimensional spectra and excludes samples with localized aberrations. Furthermore, the integration of multi-receptive fields perception, Transformer-based global information interaction, and the scSE attention mechanism has led to the development of an MG-Unet model, designed to resolve spectral peak overlap issues and capture long-range feature dependencies. The proposed method achieves state-of-the-art accuracy of 96.92%, demonstrating significant potential for reliable crude oil source tracing. [ABSTRACT FROM AUTHOR]

Outliers can occur in application areas, adversely affecting the prediction method's performance. Outliers can be removed by using robust statistical algorithms. However, statistical methods have limitations in capturing the outlier for high-dimensional data. Approaches using Machine Learning (ML) are offered as they develop rapidly due to their excellent interpretability and strong generalization capabilities. So, ML is popular in detecting or eliminating outliers to increase the accuracy of forecasting methods, such as Isolation Forest (IF), an unsupervised outlier detection strategy using a collective approach to calculate the isolation score for every data point. This research objective is to improve the prediction accuracy of the Decision Tree Regression (DTR) method by proposing an IF as an ML-based outlier removal method. The proposed method was tested by two Air Quality Index (AQI) dataset that contained outliers with Mean Absolute Error (MAE), RSquare, and Root Mean Square Error (RMSE) as the accuracy measurements. The results showed that the proposed method outperforms previous studies. [ABSTRACT FROM AUTHOR]

This paper presents a computer vision-based standalone decision-aid landing system for light fixed-wing aircraft, aiming to enhance safety during emergency landings. Current landing assistance systems in airports, such as Instrument Landing Systems (ILSs) and Precision Approach Path Indicators (PAPIs), often rely on costly and location-specific ground equipment, limiting their utility for low-payload light aircraft. Especially in emergency conditions, the pilot may be forced to land on an arbitrary runway where the road flatness and glide angle cannot be ensured. To address these issues, a stereo vision-based auxiliary landing system is proposed, which is capable of estimating an appropriate glide slope based on the terrain, to assist pilots in safe landing decision-making. Moreover, in real-world scenarios, challenges with visual-based methods arise when attempting emergency landings on complex terrains with diverse objects, such as roads and buildings. This study solves this problem by employing the Gaussian Mixture Model (GMM) to segment the color image and extract ground points, while the iterative weighted plane fitting (IWPF) algorithm is introduced to mitigate the interference of outlier feature points, reaching a highly robust plane normal estimation. With the aid of the proposed system, the pilot is able to evaluate the landing glide angle/speed with respect to the uneven terrain. Simulation results demonstrate that the proposed system can successfully achieve landing guidance in unknown environments by providing glide angle estimations with an average error of less than 1 degree. [ABSTRACT FROM AUTHOR]

The early and accurate detection of Distributed Denial of Service (DDoS) attacks is a fundamental area of research to safeguard the integrity and functionality of organizations' digital ecosystems. Despite the growing importance of neural networks in recent years, the use of classical techniques remains relevant due to their interpretability, speed, resource efficiency, and satisfactory performance. This article presents the results of a comparative analysis of six machine learning techniques, namely, Random Forest (RF), Decision Tree (DT), AdaBoost (ADA), Extreme Gradient Boosting (XGB), Multilayer Perceptron (MLP), and Dense Neural Network (DNN), for classifying DDoS attacks. The CICDDoS2019 dataset was used, which underwent data preprocessing to remove outliers, and 22 features were selected using the Pearson correlation coefficient. The RF classifier achieved the best accuracy rate (99.97%), outperforming other classifiers and even previously published neural network-based techniques. These findings underscore the feasibility and effectiveness of machine learning algorithms in the field of DDoS attack detection, reaffirming their relevance as a valuable tool in advanced cyber defense. [ABSTRACT FROM AUTHOR]

This article describes a non-parametric clustering algorithm with an outlier removal step. Our method is based on tools from topological data analysis: we define a new filtration on metric spaces which is a variant of the Vietoris-Rips filtration that adds information about the points' nearest neighbor to the persistence diagram. We prove a stability theorem for this filtration, and evaluate our method on point cloud and graph datasets, showing that it can compete with state-of-the-art methods while being non-parametric. [ABSTRACT FROM AUTHOR]

Summary: Feature extraction is a fundamental step in the feature matching task. A lot of studies are devoted to feature extraction. Recent researches propose to extract features by pre‐trained neural networks, and the output is used for feature matching. However, the quality and the quantity of the features extracted by these methods are difficult to meet the requirements for the practical applications. In this article, we propose a two‐stage object‐aware‐based feature matching method. Specifically, the proposed object‐aware block predicts a weighted feature map through a mask predictor and a prefeature extractor, so that the subsequent feature extractor pays more attention to the key regions by using the weighted feature map. In addition, we introduce a state‐of‐the‐art model estimation algorithm to align image pair as the input of the object‐aware block. Furthermore, our method also employs an advanced outlier removal algorithm to further improve matching quality. Experimental results show that our object‐aware‐based feature matching method improves the performance of feature matching compared with several state‐of‐the‐art methods. [ABSTRACT FROM AUTHOR]

Vehicle exterior inspection is a critical operation for identifying defects and ensuring the overall safety and integrity of vehicles. Visual-based inspection of moving objects, such as vehicles within dynamic environments abounding with reflections, presents significant challenges, especially when time and accuracy are of paramount importance. Conventional exterior inspections of vehicles require substantial labor, which is both costly and prone to errors. Recent advancements in deep learning have reduced labor work by enabling the use of segmentation algorithms for defect detection and description based on simple RGB camera acquisitions. Nonetheless, these processes struggle with issues of image orientation leading to difficulties in accurately differentiating between detected defects. This results in numerous false positives and additional labor effort. Estimating image poses enables precise localization of vehicle damages within a unified 3D reference system, following initial detections in the 2D imagery. A primary challenge in this field is the extraction of distinctive features and the establishment of accurate correspondences between them, a task that typical image matching techniques struggle to address for highly reflective moving objects. In this study, we introduce an innovative end-to-end pipeline tailored for efficient image matching and stitching, specifically addressing the challenges posed by moving objects in static uncalibrated camera setups. Extracting features from moving objects with strong reflections presents significant difficulties, beyond the capabilities of current image matching algorithms. To tackle this, we introduce a novel filtering scheme that can be applied to every image matching process, provided that the input features are sufficient. A critical aspect of this module involves the exclusion of points located in the background, effectively distinguishing them from points that pertain to the vehicle itself. This is essential for accurate feature extraction and subsequent analysis. Finally, we generate a high-quality image mosaic by employing a series of sequential stereo-rectified pairs. [ABSTRACT FROM AUTHOR]

Recovering three-dimensional structure from images is one of the important researches in computer vision. The quality of feature matching is one of the keys to obtaining more accurate results. However, as different objects or different surfaces of objects have similar images with the same elements and different typography, the camera pose estimation will be wrong and the task will fail. This paper proposes a new mismatch elimination algorithm based on global topology consistency. We first formulate the matching task as a mathematical model based on the global constraints, then convert the feature matching into grid matching, calculate the confidence of the grids according to the changes in the angle and displacement between correspondence grid vectors, and remove the mismatches with low confidence. The experiments have demonstrated that our proposed method performs better than the state-of-the-art feature matching methods to accomplish outlier match rejection in the task of similar image matching and could be helped to obtain the correct camera pose to reconstruct more complete and more accurate object models. [ABSTRACT FROM AUTHOR]

For point cloud registration, the purpose of this article is to propose a novel centralized random sample consensus (RANSAC) (C-RANSAC) registration with fast convergence and high accuracy. In our algorithm, the novel contributions are, first, the proposal of a scale histogram-based outlier removal to delete outliers from the initial line vector set $\mathbf {L}$ for constructing a reduced line vector set $\mathbf {L}_{\text{red}}$; second, the handshake cooperation between the host RANSAC (H-RANSAC) only working on L and the local RANSAC (LCL-RANSAC) only working on $\mathbf {L}_{\text{red}}$; third, in each handshake process, after receiving the global registration solution and the global iteration number $x_{H}$ from H-RANSAC, LCL-RANSAC uses the received global solution as the initial solution of the modified TEASER++ (M-TEASER++) method to calculate its first local registration solution. If the first local registration solution satisfies the global iteration number inheritance condition, LCL-RANSAC directly sends the accumulated iteration number, $x_{H} + 1$, and the first local solution back to H-RANSAC; otherwise, LCL-RANSAC iteratively refines its local solution using the M-TEASER++ method, and then sends the resultant local solution and the required local iteration number $x_{\text{LCL}}$ to H-RANSAC for updating the global solution, the global iteration number to $x_{H} := x_{H} + x_{\text{LCL}}$, and the global confidence level. Due to $|L_{\text{red}}| \ll |L|$ and employing the global iteration number inheritance condition test into our algorithm, we have conducted extensive experiments on testing point cloud pairs to show the registration accuracy and execution time merits of our algorithm relative to the state-of-the-art methods.

Time-of-arrival transmitter localization systems, which use measurements from an array of sensors to estimate the location of a radio or acoustic emitter, are now widely used for tracking wildlife. Outlier measurements can severely corrupt estimated locations. This article describes a new suite of location estimation algorithms for such systems. The new algorithms detect and discard outlier time-of-arrival observations, which can be caused by non-line-of-sight propagation, radio interference, clock glitches, or an overestimation of the signal-to-noise ratio. The new algorithms also detect cases in which two locations are equally consistent with measurements and can usually select the correct one. The new algorithms can also infer approximate altitude information from a digital elevation map to improve location estimates close to one of the sensors. Finally, the new algorithms approximate the covariance matrix of location estimates in a simpler and more reliable way than the baseline algorithm. Extensive testing on real-world data involving mobile transmitters attached to wild animals demonstrates the efficacy of the new algorithms. Performance testing also shows that the new algorithms are fast and that they can easily cope with high-throughput real-time loads. [ABSTRACT FROM AUTHOR]

This article describes a non-parametric clustering algorithm with an outlier removal step. Our method is based on tools from topological data analysis: we define a new filtration on metric spaces which is a variant of the Vietoris–Rips filtration that adds information about the points' nearest neighbor to the persistence diagram. We prove a stability theorem for this filtration, and evaluate our method on point cloud and graph datasets, showing that it can compete with state-of-the-art methods while being non-parametric.

Optical and SAR image registration is the primary procedure to exploit the complementary information from the two different image modal types. Although extensive research has been conducted to narrow down the vast radiometric and geometric gaps so as to extract homogeneous characters for feature point matching, few works have considered the registration issue for non-flat terrains, which will bring in more difficulties for not only sparse feature point matching but also outlier removal and geometric relationship estimation. This article addresses these issues with a novel and effective optical-SAR image registration framework. Firstly, sparse feature points are detected based on the phase congruency moment map of the textureless SAR image (SAR-PC-Moment), which helps to identify salient local regions. Then a template matching process using very large local image patches is conducted, which increases the matching accuracy by a significant margin. Secondly, a mutual verification-based initial outlier removal method is proposed, which takes advantage of the different mechanisms of sparse and dense matching and requires no geometric consistency assumption within the inliers. These two procedures will produce a putative correspondence feature point (CP) set with a low outlier ratio and high reliability. In the third step, the putative CPs are used to segment the large input image of non-flat terrain into dozens of locally flat areas using a recursive random sample consensus (RANSAC) method, with each locally flat area co-registered using an affine transformation. As for the mountainous areas with sharp elevation variations, anchor CPs are first identified, and then optical flow-based pixelwise dense matching is conducted. In the experimental section, ablation studies using four precisely co-registered optical-SAR image pairs of flat terrain quantitatively verify the effectiveness of the proposed SAR-PC-Moment-based feature point detector, big template matching strategy, and mutual verification-based outlier removal method. Registration results on four 1 m-resolution non-flat image pairs prove that the proposed framework is able to produce robust and quite accurate registration results. [ABSTRACT FROM AUTHOR]

With the emergence of digitilization, numeric prediction has become a prominent problem in various fields including finance, engineering, industry, and medicine. Among several machine learning methods, regression tree is a widely preferred method due to its simplicity, interpretability and robustness. Motivated by this, we introduce a novel ensemble regression tree based methodology, namely LOF-BRT+OR. The proposed methodology is an integrated solution approach with outlier removal, regression tree and ensemble learning. First, irregular data points are removed using local outlier factor (LOF), which measures the degree of being an outlier for each point. Next, a novel regression tree with LOF weighted node model is introduced. In the proposed node model, the weights of the points in the nodes are determined according to their surrounding neighborhood, as a function of LOF values and neighbor ranks. Finally, in order to increase the prediction performance, ensemble learning is adopted. In particular, bootstrap aggregation is used to generate multiple regression trees with LOF weighted node model. The experimental study shows that the proposed methodology yields the best root mean squared error (RMSE) values in five out of nine data sets. Also, the non-parametric tests demonstrate the statistical significance of the proposed approach over the benchmark methods. The proposed methodology can be applicable to various prediction problems. [ABSTRACT FROM AUTHOR]

Cluster analysis is the most popular and often the foremost task in big data analytics as it helps in unearthing hidden patterns and trends in data. Traditional single-objective clustering techniques often suffer from accuracy fluctuations especially when applied over data groups of varying densities and imbalanced distribution as well as in the presence of outliers. This paper presents a multi-phase clustering solution that achieves good accuracy measures even in the case of noisy and not- well-separated data (linearly not separable data). The proposed design combines a two-stage Particle Swarm Optimisation (PSO) clustering with K-means logic and a state-of-the-art outlier removal technique. The use of two different optimisation criteria in the two stages of PSO clustering equips the model with the ability to escape local minima traps in the process of convergence. Extensive experiments featuring a wide variety of data have been carried out and the system could achieve accuracy levels as high as 99.9% and an average of 87.4% on notwell-separated data. The model has also been proved to be robust on eight out of the ten datasets of the Fundamental Clustering Problem Suit (FCPS), a benchmark for clustering algorithms. [ABSTRACT FROM AUTHOR]

Ellipse detection has a very wide range of applications in the field of object detection, especially in the geometric size detection of inclined microporous parts. However, due to the processing methods applied to the parts, there are certain defects in the features. The existing ellipse detection methods do not meet the needs of rapid detection due to the problems of false detection and time consumption. This article proposes a method of quickly obtaining defective ellipse parameters based on vision. It mainly uses the approximation principle of circles to repair defective circles, then combines this with morphological processing to obtain effective edge points, and finally uses the least squares method to obtain elliptical parameters. By simulating the computer-generated images, the results demonstrate that the center fitting error of the simulated defect ellipses with major and minor axes of 600 and 400 pixels is less than 1 pixel, the major and minor axis fitting error is less than 3 pixels, and the tilt angle fitting error is less than 0.1°. Further, experimental verification was conducted on the engine injection hole. The measurement results show that the surface size deviation was less than 0.01 mm and the angle error was less than 0.15°, which means the parameters of defective ellipses can obtained quickly and effectively. It is thus suitable for engineering applications, and can provide visual guidance for the precise measurement of fiber probes. [ABSTRACT FROM AUTHOR]

Seismic clustering is a vital technique in seismology for identifying patterns in seismic events and providing insights into geological processes. However, its application to ongoing landslide-induced signals and impact of outliers have not received much research attention. This letter presents a novel consensus clustering strategy with outlier removal for landslide-induced seismic signals. The proposed approach incorporates a parameter setting method to improve clustering accuracy and robustness. Experimental results demonstrate that the proposed approach outperforms the state-of-the-art clustering methods. [ABSTRACT FROM AUTHOR]

The time data series of weather stations are a source of information for floods. The study of the previous wintertime series allows knowing the behavior of the variables and the result that will be applied to analysis and simulation models that feed variables such as flow and level of a study area. One of the most common problems is the acquisition and transmission of data from weather stations due to atypical values and lost data; this generates difficulties in the simulation process. Consequently, it is necessary to propose a numerical strategy to solve this problem. The data source for this study is a real database where these problems are presented with different variables of weather. This study is based on comparing three methods of time series analysis to evaluate a multivariable process offline. For the development of the study, we applied a method based on the discrete Fourier transform (DFT), and we contrasted it with methods such as the average and linear regression without uncertainty parameters to complete missing data. The proposed methodology entails statistical values, outlier detection, and the application of the DFT. The application of DFT allows the time series completion, based on its ability to manage various gap sizes and replace missing values. In sum, DFT led to low error percentages for all the time series (1% average). This percentage reflects what would have likely been the shape or pattern of the time series behavior in the absence of misleading outliers and missing data. [ABSTRACT FROM AUTHOR]

Researchers often remove outliers when comparing groups. It is well documented that the common practice of removing outliers within groups leads to inflated Type I error rates. However, it was recently argued by André (2022) that if outliers are instead removed across groups, Type I error rates are not inflated. The same study discusses that removing outliers across groups is a specific case of the more general concept of hypothesis-blind removal of outliers, which is consequently recommended. In this paper, I demonstrate that, contrary to this advice, hypothesis-blind outlier removal is problematic. Specifically, it almost always invalidates confidence intervals and biases estimates if there are group differences. It moreover inflates Type I error rates in certain situations, for example, when variances are unequal and data nonnormal. Consequently, a data point may not be removed solely because it is deemed an outlier, whether the procedure used is hypothesis-blind or hypothesis-aware. I conclude by recommending valid alternatives. [ABSTRACT FROM AUTHOR]

The statistical assessments needed to establish anti-drug antibody (ADA) assay cut points (CPs) can be challenging for bioanalytical scientists. Poorly established CPs that are too high could potentially miss treatment emergent ADA or, when set too low, result in detection of responses that may have no clinical relevance. We evaluated 16 validation CP datasets generated with ADA assays at Regeneron's bioanalytical laboratory and compared results obtained from different CP calculation tools. We systematically evaluated the impact of various factors on CP determination including biological and analytical variability, number of samples for capturing biological variability, outlier removal methods, and the use of parametric vs. non-parametric CP determination. In every study, biological factors were the major component of assay response variability, far outweighing the contribution from analytical variability. Non-parametric CP estimations resulted in screening positivity in drug-naïve samples closer to the targeted rate (5%) and were less impacted by skewness. Outlier removal using the boxplot method with an interquartile range (IQR) factor of 3.0 resulted in screening positivity close to the 5% targeted rate when applied to entire drug-naïve dataset. In silico analysis of CPs calculated using different sample sizes showed that using larger numbers of individuals resulted in CP estimates closer to the CP of the entire population, indicating a larger sample size (~ 150) for CP determination better represents the diversity of the study population. Finally, simpler CP calculations, such as the boxplot method performed in Excel, resulted in CPs similar to those determined using complex methods, such as random-effects ANOVA. [ABSTRACT FROM AUTHOR]

Long-range surveillance and early warning of space targets are significant factors in space security. Under remote observation conditions, the energy performance of the target is weak and subject to environmental and imaging process contamination. Most detection methods are aimed at targets with a high signal-to-noise ratio (SNR) or local contrast, and the detection performance for dim-weak small targets is poor; therefore, the target signal is often enhanced by energy accumulation. However, owing to the interference caused by the instability of the imaging system, energy accumulation errors occur in the target, resulting in the dispersion of the target energy, making detection a challenge. To solve the above problem, this study proposed a multi-frame superposition detection method for dim-weak point targets based on an optimized clustering algorithm by combining the clustering method with the inherent features of the target and using the difference between the target and noise energy distribution for detection. First, we simulated the multi-frame imaging process of the target post-disturbance and established an optical imaging system model of the dim-weak target. Subsequently, we used data dimension reduction and outlier removal to extract the target potential area. Finally, the data were sent to the clustering model for calculation and judgment. Given that the accuracy rate reaches 87.1% when the SNR is 1 dB, the experimental results show that the detection method proposed in this paper can effectively detect dim-weak targets with low SNR. In addition, there is a significant improvement in the detection performance of the receiver characteristic curve compared with other algorithms in the real scene, which further proves the superiority of the method in this paper. [ABSTRACT FROM AUTHOR]

Due to the advancements in information technologies, massive quantity of data is being produced by social media, smartphones, and sensor devices. The investigation of data stream by the use of machine learning (ML) approaches to address regression, prediction, and classification problems have received considerable interest. At the same time, the detection of anomalies or outliers and feature selection (FS) processes becomes important. This study develops an outlier detection with feature selection technique for streaming data classification, named ODFST-SDC technique. Initially, streaming data is pre-processed in two ways namely categorical encoding and null value removal. In addition, Local Correlation Integral (LOCI) is used which is significant in the detection and removal of outliers. Besides, red deer algorithm (RDA) based FS approach is employed to derive an optimal subset of features. Finally, kernel extreme learning machine (KELM) classifier is used for streaming data classification. The design of LOCI based outlier detection and RDA based FS shows the novelty of the work. In order to assess the classification outcomes of the ODFST-SDC technique, a series of simulations were performed using three benchmark datasets. The experimental results reported the promising outcomes of the ODFST-SDC technique over the recent approaches. [ABSTRACT FROM AUTHOR]

Time-of-arrival transmitter localization systems, which use measurements from an array of sensors to estimate the location of a radio or acoustic emitter, are now widely used for tracking wildlife. Outlier measurements can severely corrupt estimated locations. This article describes a new suite of location estimation algorithms for such systems. The new algorithms detect and discard outlier time-of-arrival observations, which can be caused by non-line-of-sight propagation, radio interference, clock glitches, or an overestimation of the signal-to-noise ratio. The new algorithms also detect cases in which two locations are equally consistent with measurements and can usually select the correct one. The new algorithms can also infer approximate altitude information from a digital elevation map to improve location estimates close to one of the sensors. Finally, the new algorithms approximate the covariance matrix of location estimates in a simpler and more reliable way than the baseline algorithm. Extensive testing on real-world data involving mobile transmitters attached to wild animals demonstrates the efficacy of the new algorithms. Performance testing also shows that the new algorithms are fast and that they can easily cope with high-throughput real-time loads.

Shear wave velocity is an essential elastic rock parameter for reservoir characterization, fluid identification, and rock physics model building. However, S-wave velocity logging data are often missing due to economic reason. Machine learning approaches have been successfully adopted to overcome this limitation. However, they have shortcomings in extracting meaningful spatial and temporal relationships. We propose a supervised data-driven method to predict S-wave velocity using a graph convolutional network with a bidirectional gated recurrent unit (GCN-BiGRU). This method adopts the total information coefficient to capture non-linear dependencies among well-log data and uses graph embeddings to extract spatial dependencies. Additionally, the method employs a bidirectional gated mechanism to map depth relationships in both upward and backward directions. Furthermore, the prediction performance is increased by an unsupervised graph neural network to handle outliers and the generation of additional features by the complete ensemble empirical mode decomposition with additive noise method. Finally, the GCN-BiGRU network is compared with Castagna’s empirical velocity formula, support vector regression, long-short-term memory (LSTM), GRU, and BiGRU methods over the North Sea open dataset. The results show that the proposed method performs better predicting S-wave velocity than the other ML and empirical methods.

Outlier correspondence removal is an important task for feature-based point cloud registration. Given putative correspondences contaminated by outliers between two overlapped scans, we propose a Robust Consensus-Aware Network, which labels the correspondences as inliers or outliers and predicts the rigid transformation to align the point clouds. The proposed method dedicates to mining the global consensus of correct correspondences (inliers). So it can learn distinctive features for each correspondence. Specifically, the proposed network comprises three novel operations. First, by capturing the global consensus information in an attentive manner, the network projects the input correspondences into a discriminative feature space. Next, we exploit the feature similarity among correspondences to establish interactions within inlier or outlier correspondences, and aggregate the features of correct correspondences for outlier removal. Finally, we recover the rigid transformation by mining multi-level context with a motion estimation module. Extensive experiments on real-world datasets demonstrate that our approach achieves high registration accuracy and efficiency. [ABSTRACT FROM AUTHOR]

Establishing high-quality correspondences is a fundamental step for many computer vision tasks. Leveraging the local consistency of correct correspondences (i.e., inliers) has been a prevalent approach to distinguish them from incorrect correspondences (i.e., outliers). However, the random distribution of a significant proportion of outliers complicates the local neighborhood construction of inliers, making it inevitably contain many outliers, which compromises the reliability of the consistency information. In this paper, we propose a Progressive Multi-Stage Adaptive Feature Learning Network (PMA-Net) to solve this problem, which progressively and adaptively learns over multiple stages to remove random outliers embedded in the initial consistency. Specifically, we propose an Adaptive Dynamic Graph Construction (ADGC) module to construct a global topological graph with a high inlier ratio by calculating the affinity between the corresponding neighbors. Additionally, we also design a Feature Mapping Processing (FMP) block and Multi-Stage Prediction (MSP) block to improve the accuracy of subsequent local neighborhood information aggregation, as well as information loss due to channel dimension compression in the prediction phase. Experimental results in camera pose estimation, remote sensing image registration, and homography estimation demonstrate that the proposed PMA-Net performs better than other state-of-the-art methods on various public datasets. Code: https://github.com/XiaojieLi11/PMA-Net [ABSTRACT FROM AUTHOR]

Optical and SAR image registration is the primary procedure to exploit the complementary information from the two different image modal types. Although extensive research has been conducted to narrow down the vast radiometric and geometric gaps so as to extract homogeneous characters for feature point matching, few works have considered the registration issue for non-flat terrains, which will bring in more difficulties for not only sparse feature point matching but also outlier removal and geometric relationship estimation. This article addresses these issues with a novel and effective optical-SAR image registration framework. Firstly, sparse feature points are detected based on the phase congruency moment map of the textureless SAR image (SAR-PC-Moment), which helps to identify salient local regions. Then a template matching process using very large local image patches is conducted, which increases the matching accuracy by a significant margin. Secondly, a mutual verification-based initial outlier removal method is proposed, which takes advantage of the different mechanisms of sparse and dense matching and requires no geometric consistency assumption within the inliers. These two procedures will produce a putative correspondence feature point (CP) set with a low outlier ratio and high reliability. In the third step, the putative CPs are used to segment the large input image of non-flat terrain into dozens of locally flat areas using a recursive random sample consensus (RANSAC) method, with each locally flat area co-registered using an affine transformation. As for the mountainous areas with sharp elevation variations, anchor CPs are first identified, and then optical flow-based pixelwise dense matching is conducted. In the experimental section, ablation studies using four precisely co-registered optical-SAR image pairs of flat terrain quantitatively verify the effectiveness of the proposed SAR-PC-Moment-based feature point detector, big template matching strategy, and mutual verification-based outlier removal method. Registration results on four 1 m-resolution non-flat image pairs prove that the proposed framework is able to produce robust and quite accurate registration results.

Financial crisis prediction (FCP) models are used for predicting or forecasting the financial status of a company or financial firm. It is considered a challenging issue in the financial sector. Statistical and machine learning (ML) models can be employed for the design of accurate FCP models. Though numerous works have existed in the literature, it is needed to design effective FCP models adaptable to different datasets. This study designs a new bird swarm algorithm (BSA) with fuzzy min-max neural network (FMM-NN) model, named BSA-FMMNN for FCP. The major intention of the BSA-FMMNN model is to determine the financial status of a firm or company. The presented BSA-FMMNN model primarily undergoes minmax normalization to transform the data into uniformity range. Besides, k-medoid clustering approach is employed for the outlier removal process. Finally, the classification process is carried out using the FMMNN model, and the parameters involved in it are tuned by the use of BSA. The utilization of proficient parameter selection process using BSA demonstrate the novelty of the study. The experimental result analysis of the BSA-FMMNN model is validated using benchmark dataset and the comparative outcomes highlighted the supremacy of the BSA-FMMNN model over the recent approaches. [ABSTRACT FROM AUTHOR]

In data cleaning, the process of detecting and correcting corrupt, inaccurate or irrelevant records from the record set is a tedious task. Particularly, the process of "outlier detection" occupies a significant role in data cleaning that removes or eliminates the outlier's that exist in data. Traditionally, more efforts have been taken to remove the outliers, and one of the promising ways is customizing clustering models. In this manner, this paper intends to propose a new outlier detection model via enhanced k-means with outlier removal (E-KMOR), which assigns all outliers into a group naturally during the clustering process. For assigning the point to be outliers, a new intra-cluster based distance evaluation is employed. The main contribution of this paper is to select cluster centroid optimally through a newly proposed hybrid optimization algorithm termed particle updated lion algorithm (PU-LA), which hybrids the concepts of LA and particle swarm optimization (PSO), respectively. Thereby, the proposed work is named as E-KMOR-PU-LA. Finally, the efficacy of the proposed E-KMOR-PU-LA model is proved through a comparative analysis over conventional models by concerning runtime and accuracy. [ABSTRACT FROM AUTHOR]

Point cloud registration (PCR) is an important and fundamental problem in 3D computer vision, whose goal is to seek an optimal rigid model to register a point cloud pair. Correspondence-based PCR techniques do not require initial guesses and gain more attentions. However, 3D keypoint techniques are much more difficult than their 2D counterparts, which results in extremely high outlier rates. Current robust techniques suffer from very high computational cost. In this paper, we propose a polynomial time ($O(N^2)$ O (N 2) , where $N$ N is the number of correspondences.) outlier removal method. Its basic idea is to reduce the input set into a smaller one with a lower outlier rate based on bound principle. To seek tight lower and upper bounds, we originally define two concepts, i.e., correspondence matrix (CM) and augmented correspondence matrix (ACM). We propose a cost function to minimize the determinant of CM or ACM, where the cost of CM rises to a tight lower bound and the cost of ACM leads to a tight upper bound. Then, we propose a scale-adaptive Cauchy estimator (SA-Cauchy) for further optimization. Extensive experiments on simulated and real PCR datasets demonstrate that the proposed method is robust at outlier rates above 99 percent and 1 $\sim$ ∼ 2 orders faster than its competitors. The source code will be made publicly available in https://ljy-rs.github.io/web/. [ABSTRACT FROM AUTHOR]

Ellipse detection has a very wide range of applications in the field of object detection, especially in the geometric size detection of inclined microporous parts. However, due to the processing methods applied to the parts, there are certain defects in the features. The existing ellipse detection methods do not meet the needs of rapid detection due to the problems of false detection and time consumption. This article proposes a method of quickly obtaining defective ellipse parameters based on vision. It mainly uses the approximation principle of circles to repair defective circles, then combines this with morphological processing to obtain effective edge points, and finally uses the least squares method to obtain elliptical parameters. By simulating the computer-generated images, the results demonstrate that the center fitting error of the simulated defect ellipses with major and minor axes of 600 and 400 pixels is less than 1 pixel, the major and minor axis fitting error is less than 3 pixels, and the tilt angle fitting error is less than 0.1°. Further, experimental verification was conducted on the engine injection hole. The measurement results show that the surface size deviation was less than 0.01 mm and the angle error was less than 0.15°, which means the parameters of defective ellipses can obtained quickly and effectively. It is thus suitable for engineering applications, and can provide visual guidance for the precise measurement of fiber probes.

Reliable feature matching plays an important role in the fields of computer vision and photogrammetry. Due to the complex transformation model caused by photometric and geometric deformations, and the limited discriminative power of local feature descriptors, initial matches with high outlier ratios cannot be addressed very well. This study proposes a reliable outlier-removal algorithm by combining two affine-invariant geometric constraints. First, a very simple geometric constraint, namely, CAI (collinear affine invariance) has been implemented, which is based on the observation that the collinear property of any two points is invariant under affine transformation. Second, after the first-step outlier removal based on the CAI constraint, the SOV (scale-orientation voting) scheme was then adopted to remove remaining outliers and recover the lost inliers, in which the peaks of both scale and orientation voting define the parameters of the geometric transformation model. Finally, match expansion was executed using the Delaunay triangulation of refined matches. By using close-range (rigid and non-rigid images) and UAV (unmanned aerial vehicle) datasets, comprehensive comparison and analysis are conducted in this study. The results demonstrate that the proposed outlier-removal algorithm achieves the best overall performance when compared with RANSAC-like and local geometric constraint-based methods, and it can also be applied to achieve reliable outlier removal in the workflow of SfM-based UAV image orientation. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel multi-scale attention based network (called MSA-Net) for feature matching problems. Current deep networks based feature matching methods suffer from limited effectiveness and robustness when applied to different scenarios, due to random distributions of outliers and insufficient information learning. To address this issue, we propose a multi-scale attention block to enhance the robustness to outliers, for improving the representational ability of the feature map. In addition, we also design a novel context channel refine block and a context spatial refine block to mine the information context with less parameters along channel and spatial dimensions, respectively. The proposed MSA-Net is able to effectively infer the probability of correspondences being inliers with less parameters. Extensive experiments on outlier removal and relative pose estimation have shown the performance improvements of our network over current state-of-the-art methods with less parameters on both outdoor and indoor datasets. Notably, our proposed network achieves an 11.7% improvement at error threshold 5° without RANSAC than the state-of-the-art method on relative pose estimation task when trained on YFCC100M dataset. [ABSTRACT FROM AUTHOR]

Rating data collected by recommendation systems contain noise caused by human uncertainty and malicious attacks. Existing outlier removal approaches usually aim at detecting noise inserted into ground-truth ratings. However, in real applications, the ground-truth of the training data are unavailable, or even unimportant for the prediction task. In this paper, we propose an efficient and effective outlier removal algorithm to improve the quality of the training data. The noise is modeled by the mixture of Gaussian distribution, which can approximate any continuous distribution. First, we employ the expectation-maximization algorithm to calculate the low-rank matrices, whose product forms the recovered ratings. Second, we compare the original and recovered ratings to solicit suspected outliers. This process is repeated a number of times, and ratings that are suspected enough times will be treated as outliers. To validate the effectiveness of our algorithm, we compared the prediction quality of four popular recommendation algorithms. Results showed that several measures on the algorithms were improved with the new training data. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Jilin University (Science Edition) / Jilin Daxue Xuebao (Lixue Ban) is the property of Zhongguo Xue shu qi Kan (Guang Pan Ban) Dian zi Za zhi She and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Earth observation using remote sensing data is a trending research field across the globe. In this perspective, image registration is a mandatory data processing step for any kind of time series data analytics. Feature-based image registration is one of the prominent categories for superimposing multi-temporal and multi-modal images over each other. The paper provides a comprehensive and comparative survey of feature detection/description techniques for remote sensing images. In addition, outlier removal algorithms are explored in detail to generate putative keypoint correspondences for accurate transformation parameter estimation. The experiments are conducted on multiple remote sensing image pairs comprising visible, Synthetic Aperture Radar (SAR) and infrared images that provide diverse characteristics of the feature target. The co-registration accuracy is quantified for all possible combinations of feature detection/description with outlier removal, and best amalgamation is visually verified to check sub-pixel spatial alignment by swiping multi-temporal or multi-modal images over each other. It has been found that SIFT performs better in optical image registration, whereas A-KAZE feature detection has an upper edge at SAR image registration task. Marginalizing Sample Consensus (MAGSAC) and Mode Guided (MG) based outlier removal techniques achieves better pruning performance for multi-temporal optical and SAR images respectively. The comparative evaluation indicates that Motion Smoothness Constraint (MSC) optimization shows optimal performance for multi-modal remote sensing images. The best possible Root Mean Square Error (RMSE) achieved for multi-temporal optical images is 0.44 pixel whereas for multi-temporal SAR images, it is 0.46 pixels. The RMSE achieved for multi-modal images is 0.48 pixel using combination of SIFT with MSC. [ABSTRACT FROM AUTHOR]

Objective: The interpretation of time series data collected in free-living has gained importance in chronic disease management. Some data are collected objectively from sensors and some are estimated and entered by the individual. In type 1 diabetes (T1D), blood glucose concentration (BGC) data measured by continuous glucose monitoring (CGM) systems and insulin doses administered can be used to detect the occurrences of meals and physical activities and generate the personal daily living patterns for use in automated insulin delivery (AID). Methods: Two challenges in time-series data collected in daily living are addressed: data quality improvement and the detection of unannounced disturbances of BGC. CGM data have missing values for varying periods of time and outliers. People may neglect reporting their meal and physical activity information. In this work, novel methods for preprocessing real-world data collected from people with T1D and the detection of meal and exercise events are presented. Four recurrent neural network (RNN) models are investigated to detect the occurrences of meals and physical activities disjointly or concurrently. Results: RNNs with long short-term memory (LSTM) with 1D convolution layers and bidirectional LSTM with 1D convolution layers have average accuracy scores of 92.32% and 92.29%, and outperform other RNN models. The F1 scores for each individual range from 96.06% to 91.41% for these two RNNs. Conclusions: RNNs with LSTM and 1D convolution layers and bidirectional LSTM with 1D convolution layers provide accurate personalized information about the daily routines of individuals. Significance: Capturing daily behavior patterns enables more accurate future BGC predictions in AID systems and improves BGC regulation. [ABSTRACT FROM AUTHOR]

Finding true correspondences from a set of putative correspondences is a basic task in computer vision. Recent advances have demonstrated that Multi Layer Perceptrons (MLPs) can handle the unordered correspondence learning problem by training a deep classifier. However, MLPs ignore the relationship between correspondences, such as geometric information, spatial information and inlier distribution information, which will lead to difficulties in modeling complex global context. To solve this issue, we propose a Relation-Aware Network (RANet), by capturing rich global information from channel and spatial dimensions, to establish reliable correspondences for feature matching. Specifically, we firstly present a Global Context Attention block by a two-branch attention structure to cooperate with MLPs for contextual information extraction. Then, we design a Relation-Aware Filter block by further exploring the channel and spatial relationship information with different connection manners. Finally, we combine two blocks to obtain an enhanced basic block with strong feature representation capacity due to the acquisition of global contextual information. Our experiments have been conducted over both indoor and outdoor datasets on the tasks of outlier removal and camera pose estimation, which demonstrate the superiority of our network that achieves the best performance compared with the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Existing external relationships for outlier removal in the perspective-n-point problem are generally spatial coherence among the neighbor correspondences. In the situation of high noise or spatially incoherent distributions, pose estimation is relatively inaccurate due to a small number of detected inliers. To address these problems, this paper explores the globally coherent external relationships for outlier removal and pose estimation. To this end, the differential degree graph (DDG) is proposed to employ the intersection angles between rays of correspondences to handle outliers. Firstly, a pair of two degree graphs are constructed to establish the external relationships between 3D-2D correspondences in the world and camera coordinates. Secondly, the DDG is estimated through subtracting the two degree graphs and operating binary operation with a degree threshold. Besides, this paper mathematically proves that the maximum clique of the DDG represents the inliers. Thirdly, a novel vertice degree based method is put forward to extract the maximum clique from DDG for outlier removal. Besides, this paper proposes a novel pipeline of DDG based PnP solution, i.e. DDGPnP, to achieve accurate pose estimation. Experiments demonstrate the superiority and effectiveness of the proposed method in the aspects of outlier removal and pose estimation by comparison with the state of the arts. Especially for the high noise situation, the DDGPnP method can achieve not only accurate pose but also a large number of correct correspondences. • The DDG uses a graph model to represent external and internal relationships of correspondences. • This paper mathematically proves the maximum clique of a DDG represents inliers. • A degree-based method is proposed to extract the maximum clique from the DDG. • The DDGPnP is designed for pose estimation and outlier removal simultaneously. [ABSTRACT FROM AUTHOR]

Non-negative Matrix Factorization (NMF) is an effective way to solve the redundancy of non-negative high-dimensional data. Most of the traditional probability-based NMF methods use Gaussian distribution to model the differences between the matrices before and after decomposition. However, the Gaussian distribution is strongly affected by outliers, and it may not fit all datasets accurately when there are no outliers in the data. In this article, we propose a novel Bayesian NMF with the Student's t-distribution, i.e., TNMF. specifically, in order to reduce the impact of outliers on the algorithm, we use the Student's t-distribution to fit the data points instead of the Gaussian distribution. In addition, it is possible to adjust the Degree of Freedom (DF) to make the Student's t-distribution more flexible than the Gaussian distribution to fit data points when there are no outliers. Next, we combine the Automatic Relevance Determination (ARD) prior in our algorithm to simplify the model and allow for better performance of the algorithm. Finally, the article used 10 datasets to design two kinds of experiments, outlier removal and data clustering. The outlier removal results of this proposed algorithm are significantly better than the other methods, and it performs better in clustering compared to the other methods in the majority of cases. [ABSTRACT FROM AUTHOR]

Deep learning-based (DL) methods have recently come to the forefront among the data-driven models due to their success in capturing the complexities of the battery. Many previous DL-based studies for SoC estimation have almost exclusively focused on improving DL structure by proposing various architectures. Questions regarding the outlier or atypical predictions have yet to be adequately addressed. Furthermore, few works benefit from optimization algorithms to determine the hyperparameters of DL. In this study, we have addressed the problem of how to obtain the hyperparameter of DL and fix the improper DL predictions. To this aim, we used two different optimization algorithms to determine the hyperparameters of DL and proposed a novel algorithm that considers the previous SoC estimations. The algorithm either approves or rejects the DL predictions for the relevant step and offers new values for the rejected ones. The proposed scheme is evaluated using a battery dataset which includes different driving cycles. According to the results, it is observed that the optimized DL outperforms the empirical one by at least 35% in terms of performance indices. Moreover, the proposed novel algorithm successfully integrates into all variations and significantly improves the performance index scores. • Deep learning algorithms were used for SoC estimation. • The hyper-parameters of the deep learning algorithms were determined by bio-inspired algorithms. • A novel algorithm was proposed that improves deep learning predictions. • Optimized DL outperformed the empirically tuned one by at least 35% in terms of performance indices. • The proposed algorithm was successfully integrated into all schemes and significantly improved the performance index scores. [ABSTRACT FROM AUTHOR]

Long-range surveillance and early warning of space targets are significant factors in space security. Under remote observation conditions, the energy performance of the target is weak and subject to environmental and imaging process contamination. Most detection methods are aimed at targets with a high signal-to-noise ratio (SNR) or local contrast, and the detection performance for dim-weak small targets is poor; therefore, the target signal is often enhanced by energy accumulation. However, owing to the interference caused by the instability of the imaging system, energy accumulation errors occur in the target, resulting in the dispersion of the target energy, making detection a challenge. To solve the above problem, this study proposed a multi-frame superposition detection method for dim-weak point targets based on an optimized clustering algorithm by combining the clustering method with the inherent features of the target and using the difference between the target and noise energy distribution for detection. First, we simulated the multi-frame imaging process of the target post-disturbance and established an optical imaging system model of the dim-weak target. Subsequently, we used data dimension reduction and outlier removal to extract the target potential area. Finally, the data were sent to the clustering model for calculation and judgment. Given that the accuracy rate reaches 87.1% when the SNR is 1 dB, the experimental results show that the detection method proposed in this paper can effectively detect dim-weak targets with low SNR. In addition, there is a significant improvement in the detection performance of the receiver characteristic curve compared with other algorithms in the real scene, which further proves the superiority of the method in this paper.

The generation of a very accurate and precise digital elevation model (DEM) is one of the main objectives of remote sensing applications. Synthetic-Aperture Radar (SAR) interferometry is one of the most common methods for DEM generation. Moreover, one of the most recent Sentinel-1 missions is SAR imagery. Sometimes due to a variety of errors such as interferogram phase error, DEMs based on SAR interferometry contain outliers in the elevation of points. Thus, they need to be modified and updated. In this study, a 2-D Kalman filter-based method is applied to remove outliers from DEM generated from Sentinel-1 images. The proposed method is examined over an area in Iran and the results are compared with a high resolution and precision DEM. The results demonstrate that the efficiency of the proposed method in the outlier removal and root mean square error (RMSE) of the DEM is improved from 11% to 17%. [ABSTRACT FROM AUTHOR]

RANSAC (RANdom SAmple Consensus) is a widely used robust estimator for estimating a geometric model from feature matches in an image pair. Unfortunately, it becomes less effective when initial input feature matches (i.e., input data) are corrupted by a large number of outliers. In this paper, we propose a new robust estimator (called TRESAC) for model estimation, where data subsets are sampled with the guidance of the triplet relationships, which involve high relevance and local geometric consistency. Each triplet consists of three data, whose relationships satisfy spatial consistency constraints. Therefore, the triplet relationships can be used to effectively initialize and refine the sampling process. With the advantage of the triplet relationships, TRESAC significantly alleviates the influence of outliers and also improves the computational efficiency of model estimation. Experimental results on four challenging datasets show that TRESAC can achieve superior performance on both estimation accuracy and computational efficiency against several other state-of-the-art methods. [ABSTRACT FROM AUTHOR]