Feature Outlier Research Articles

Rapid and Non-Destructive Geographical Origin Identification of Chuanxiong Slices Using Near-Infrared Spectroscopy and Convolutional Neural Networks

Ligusticum Chuanxiong, a perennial herb of considerable medicinal value commonly known as Chuanxiong, holds pivotal importance in sliced form for ensuring quality and regulating markets through geographical origin identification. This study introduces an integrated approach utilizing Near-Infrared Spectroscopy (NIRS) and Convolutional Neural Networks (CNNs) to establish an efficient method for rapidly determining the geographical origin of Chuanxiong slices. A dataset comprising 300 samples from 6 distinct origins was analyzed using a 1D-CNN model. In this study, we initially established a traditional classification model. By utilizing the Spectrum Outlier feature in TQ-Analyst 9 software to exclude outliers, we have enhanced the performance of the model. After evaluating various spectral preprocessing techniques, we selected Savitzky–Golay filtering combined with Multiplicative Scatter Correction (S-G + MSC) to process the raw spectral data. This approach significantly improved the predictive accuracy of the model. After 2000 iterations of training, the CNN model achieved a prediction accuracy of 92.22%, marking a 12.09% improvement over traditional methods. The application of the Class Activation Mapping algorithm not only visualized the feature extraction process but also enhanced the traditional model’s classification accuracy by an additional 7.41% when integrated with features extracted from the CNN model. This research provides a powerful tool for the quality control of Chuanxiong slices and presents a novel perspective on the quality inspection of other agricultural products.

Partial label learning via identifying outlier features

Partial label learning (PLL) is a classification problem where each training instance is ambiguously annotated with a set of candidate labels, among which only one is the ground truth label. The topological structure in the feature space is frequently used by existing PLL approaches to clarify if a candidate label is the ground truth label for a training example. However, these techniques frequently experience cumulative errors brought on by the error-prone labeling confidence estimate throughout the topological structure because of the redundant and noisy features occurring naturally in the feature space. In this paper, we propose a novel approach through Identifying Outlier Features (PL-IOF) to address this challenge. The feature space is decomposed into class prototype features and outlier features, where the former captures the discriminative features of each class prototype, and the latter captures the outlier features in each training instance. A unified framework is specifically suggested to simultaneously optimize class prototypes and outlier features, as well as to estimate labeling confidences over incomplete label training instances. This framework ensures the high quality of the extracted class prototypes by recognizing the outliers. Experiments on both synthetic and real-world datasets demonstrate the out-performance of PL-IOF over the state-of-the-art.

Autonomous and reliable fingerprint map maintenance for indoor positioning system

In WiFi-based crowdsourced fingerprinting indoor positioning systems (IPS), the signal space of WiFi APs changes over time. To autonomously maintain a highly reliable localization accuracy, the fingerprint database needs regular maintenance and updates. However, this process is labor-intensive and time-consuming due to the appearance of faulty access points (APs) in crowdsourced samples received from target clients, which are mainly used for autonomous maintenance and updates. Additionally, if some APs are relocated, removed, or replaced in the indoor environment after fingerprint map construction, it can severely impact IPS accuracy. In this paper, we present Dynamic Online Fingerprint Learning with Altered APs status-aware and updating (DOFLAAU) for IPS. Our systematic methodology involves several key steps. First, we employ the Modified Group Method of Data Handling (GMDH) neural network regression for autonomous AP status monitoring and alteration detection. Next, we perform autonomous APs subset sample selection using a modified Thomson model, followed by outlier feature detection and removal based on the weighted sample density rate. Thirdly, we propose a dynamic online fingerprint map updating model using the cosine similarity distance metric. Lastly, we adopted an effective signal distance-based weighted k-nearest neighbor algorithm to improve IPS accuracy. The experiment results validate the efficiency and effectiveness of our proposed algorithms in terms of better localization accuracy compared to peer algorithms.

Development of an Uneven Terrain Decision-Aid Landing System for Fixed-Wing Aircraft Based on Computer Vision

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.

Particle sizes in Saturn’s rings from UVIS stellar occultations 2. Outlier Populations in the C ring and Cassini Division

The Cassini Ultraviolet Imaging Spectrograph (UVIS) included a High-Speed Photometer (HSP), which observed hundreds of stellar occultations by Saturn’s ring system across a range of viewing geometries (Colwell et al. 2010). The unocculted time series data from the HSP follow Poisson counting statistics, such that the second and third central moments of the unocculted data should be equal to the mean photon rate of the star. When the star is occulted by the rings, the presence of ring particles introduces a correlation in the previously uncorrelated photons. This causes each of the central moments to deviate from their expected value. In particular, the second central moment, μ2, commonly known as the variance, becomes greater than the mean (Colwell et al. 2018). The third central moment, μ3, also deviates from this expectation upon occultation, but the nature of the deviation varies with optical depth. In particular, μ3 is less than its Poisson expectation for τ<0.33 and greater than this expectation for τ>0.33. The introduction of outlier features, namely small gaps (‘ghosts’, Baillié et al. (2013)) and clumps produce variable effects on the behavior of both μ2 and μ3, which is also dependent on optical depth.We compare the higher-order moments from Monte Carlo Simulations of a simplified ring system to those from the UVIS data to gain insight into the nature of such outliers in the C ring and Cassini Division. The behavior of the data in the C ring plateaus indicates that a small population of ∼ 10-m ghosts exists in this region, with a frequency of about 1 ghost per km of radial extent. In the background C ring, we find that particle sizes are positively correlated with optical depth and the data cannot be explained with a simple power-law size distribution. Instead, we are able to describe the behavior of the higher-order moments using a bent-power law size distribution of particles. We find similar behavior in the C ring ramp and Cassini Division ramp. However, we cannot rule out nor confirm the presence of either ghosts or clumps in the background Cassini Division. In the Triple Band, the local ∼ 10-m ghost frequency oscillates between about 1 and 4 ghosts per km.

Fault Diagnosis and Detection for Battery System in Real-World Electric Vehicles Based on Long-Term Feature Outlier Analysis

Accurate detection and diagnosis battery faults are increasingly important to guarantee safety and reliability of battery systems. Developed methods for battery early fault diagnosis concentrate on short-term data to analyze the deviation of external features without considering the long-term latent period of faults. This work proposes a novel data-driven method to detect long-term latent fault and abnormality for electric vehicles based on real-world operation data. Specifically, the battery fault features are extracted from the incremental capacity curves, which are smoothed by advanced filter algorithms. Secondly, principal component analysis algorithm is utilized to reduce dimensionality and the cumulative percent variance is to determine the number of significant features. Based on the features, a cluster algorithm is employed to capture the battery potential failure information. Moreover, the cumulative root-mean-square-deviation is introduced to quantificationally analyze the degree of the battery failures using large-scale battery data to avoid the missing fault reports using short-term data. In addition, a battery system failure index is proposed to evaluate battery fault conditions. The results indicate that the proposed long-term feature analysis method can effectively detect and diagnose faults.

Statement of Retraction: Incremental Outlier Feature Clustering Algorithm in Blockchain Networks Based on Big Data Analysis

Statement of Retraction: Incremental Outlier Feature Clustering Algorithm in Blockchain Networks Based on Big Data Analysis

Saliency-Induced Moving Object Detection for Robust RGB-D Vision Navigation Under Complex Dynamic Environments

Localization in unknown environments is an essential requirement for vision navigation of robotic vehicles in intelligent transportation systems. However, moving objects in dynamic scenarios usually bring about great difficulty for robot localization, because motion estimation of robotic vehicles is disturbed by increasing feature outliers caused by moving objects. In order to improve the accuracy and robustness of robot localization, a novel saliency-induced moving object detection (SMOD) approach is proposed to filter out feature outliers for RGB-D-based simultaneous localization and mapping (SLAM) in complex dynamic workspaces. Firstly, three complementary motion saliency potentials, including motion energy (ME), spatiotemporal objectness (STO), and dynamic superpixels (DS), are modeled by fully analyzing spatial, temporal, appearance and depth cues in RGB-D inputs. They can be used to identify the dynamic objects effectively from diversely changing backgrounds. Then, a superpixel-level graph-based motion saliency (MS) measure is proposed to generate the MS map for reliable localization of the moving objects. The edge weights and background nodes on the graph are determined reasonably by fusing ME, STO, and DS, which is not vulnerable to background interferences. Furthermore, the SMOD approach is embedded into the front-end of ORB-SLAM3 as a pre-processing stage, in order to filter out feature outliers associated with the moving objects. Finally, the extensive experiments are performed to verify the accuracy and robustness of the proposed approach on the public dynamic datasets. The experimental results show that the SMOD method can detect the moving objects effectively in a variety of challenging dynamic environments, and separate the dynamic regions reliably from the irrelevant background. The data comparison demonstrates that the SMOD-SLAM navigation system can outperform other state-of-the-art dynamic visual SLAM (vSLAM) systems.

Tracking by segmentation with future motion estimation applied to person-following robots.

Person-following is a crucial capability for service robots, and the employment of vision technology is a leading trend in building environmental understanding. While most existing methodologies rely on a tracking-by-detection strategy, which necessitates extensive datasets for training and yet remains susceptible to environmental noise, we propose a novel approach: real-time tracking-by-segmentation with a future motion estimation framework. This framework facilitates pixel-level tracking of a target individual and predicts their future motion. Our strategy leverages a single-shot segmentation tracking neural network for precise foreground segmentation to track the target, overcoming the limitations of using a rectangular region of interest (ROI). Here we clarify that, while the ROI provides a broad context, the segmentation within this bounding box offers a detailed and more accurate position of the human subject. To further improve our approach, a classification-lock pre-trained layer is utilized to form a constraint that curbs feature outliers originating from the person being tracked. A discriminative correlation filter estimates the potential target region in the scene to prevent foreground misrecognition, while a motion estimation neural network anticipates the target's future motion for use in the control module. We validated our proposed methodology using the VOT, LaSot, YouTube-VOS, and Davis tracking datasets, demonstrating its effectiveness. Notably, our framework supports long-term person-following tasks in indoor environments, showing promise for practical implementation in service robots.

Intelligent fault diagnosis of partial deep transfer based on multi-representation structural intraclass compact and double-aligned domain adaptation

The main challenge of fault diagnosis models based on partial domain adaptation (PDA) is to promote positive transfer in the shared label space and avoid negative transfer caused by the mismatch between the outlier and the target label spaces. To address the above challenges and enhance the diagnosis performance in the PDA scenario, this paper proposes a partial deep transfer diagnosis model (MICDDA) based on multi-representation structure intraclass compact and double-aligned domain adaptation. First, the Gabor feature extractor and multi-representation structure network are constructed to enhance the representation ability of deep features and enrich feature information. Then, the information entropy and class diversity loss of the target domain are introduced to improve the loss of the classification network, and the source class-level weight and the target instance-level weight are used to reduce the outlier features participating in the alignment of the target features. Next, an intraclass compact constraint is proposed to enhance the agglomeration of features with the same label by minimizing the distance between the feature and the centroid. Finally, a double-aligned domain adaptation strategy is designed to enhance the alignment between the source and target domains' shared features by minimizing the inter- and intra-domain alignment. Experimental results in two case studies show that the MICDDA can effectively weaken the transfer of source outlier knowledge to the target domain, capture rich and homogeneous compact fault features in PDA diagnosis scenarios, and effectively improve diagnostic performance.

Design and Experiment of an Automatic Row-Oriented Spraying System Based on Machine Vision for Early-Stage Maize Corps

Spraying pesticides using row alignment in the maize seedling stage can effectively improve pesticide utilization and protect the ecological environment. Therefore, this study extracts a guidance line for maize crops using machine vision and develops an automatic row-oriented control system based on a high-clearance sprayer. First, the feature points of crop rows are extracted using a vertical projection method. Second, the candidate crop rows are obtained using a Hough transform, and two auxiliary line extraction methods for crop rows based on the slope feature outlier algorithm are proposed. Then, the guidance line of the crop rows is fitted using a tangent formula. To greatly improve the robustness of the vision algorithm, a Kalman filter is used to estimate and optimize the guidance line to obtain the guidance parameters. Finally, a visual row-oriented spraying platform based on autonomous navigation is built, and the row alignment accuracy and spraying performance are tested. The experimental results showed that, when autonomous navigation is turned on, the average algorithm time consumption of guidance line detection is 42 ms, the optimal recognition accuracy is 93.3%, the average deviation error of simulated crop rows is 3.2 cm and that of field crop rows is 4.36 cm. The test results meet the requirements of an automatic row-oriented control system, and it was found that the accuracy of row alignment decreased with increasing vehicle speed. The innovative spray performance test found that compared with the traditional spray, the inter-row pesticide savings were 20.4% and 11.4% overall, and the application performance was significantly improved.

Prototype-guided multi-scale domain adaptation for Alzheimer's disease detection

Alzheimer's disease (AD) is the most common form of dementia and there is no effective treatment currently. Using artificial intelligence technology to assist the diagnosis and intervention as early as possible is of great significance to delay the development of AD. Structural Magnetic Resonance Imaging (sMRI) has shown great practical values on computer-aided AD diagnosis. Affected by data from different sources or acquisition domains in realistic scenarios, MRI data often suffer from domain shift problem. In this paper, we propose a deep Prototype-Guided Multi-Scale Domain Adaptation (PMDA) framework to handle MRI data with domain shift problem, and realize automatic auxiliary diagnosis of AD, Mild Cognitive Impairment (MCI) and Cognitively Normal (CN). PMDA is composed of three modules: (1) MRI multi-scale feature extraction module combines the advantages of 3D convolution and self-attention to effectively extract multi-scale features in high-dimensional space, (2) Prototype Maximum Density Divergence (Pro-MDD) module adopts prototype learning to constrain the feature outlier samples in a mini-batch when MDD is used to align source domain and target domain, and (3) Adversarial Domain Adaptation module is applied to achieve global feature alignment of the source domain and target domain and co-training two distinctive discriminators to mitigate the over-fitting issue. Experiments have been performed on 3T and 1.5T sMRI with domain shift in ADNI dataset. The experimental results demonstrated that the proposed framework PMDA outperforms supervised learning methods and several state-of-the-art domain adaptation methods and achieves a superior accuracy of 92.11%, 76.01% and 82.37% on AD vs. CN, AD vs. MCI, and MCI vs. CN tasks, respectively.

An outlier detection algorithm based on segmentation and pruning of competitive network for glioma identification using Raman spectroscopy.

Raman spectroscopy is a promising diagnostic tool for brain gliomas, owing to its non-invasive and high information density properties. However, identifying patterns in glioma cancer tissue and healthy tissue in the brain is challenging, and outlier spectra resulting from operator error or changes in external conditions can compromise the model's robustness and generalizability to new data. Given the heterogeneity of glioma tissue, the within-group variance of data obtained by a portable Raman spectrometer is relatively high, and inconsistencies in instrument repeatability and experimental conditions can lead to an incompact distribution of non-outlier points, complicating outlier detection. Strict outlier criteria may result in the deletion of non-outlier points, leading to reduced sample utilization. To address these issues, we propose the SPCN outlier detection algorithm, which segments and prunes a competitive network to extract global outlier features, identifies topological errors, and divides initial outlier domains using the α-β region segmentation method. The algorithm also proposes a two-stage pruning method based on the characteristics of the manifold map and visualizes the outlier measure using a normalized histogram. Compared to traditional methods, SPCN is label-free and does not require an estimation of outlier distance threshold or data distribution density. We compared the accuracy of six outlier detection algorithms using Raman spectra collected from brain glioma tissues of 113 patients and examined changes in pattern recognition accuracy after removing the outliers, confirming the precision and robustness of SPCN. This method has the potential to enhance the accuracy and reliability of glioma diagnosis via Raman spectroscopy and can also be applied to outlier detection in other spectra such as near infrared and middle infrared.

Indoor–Outdoor Point Cloud Alignment Using Semantic–Geometric Descriptor

Aligning indoor and outdoor point clouds is a challenging problem since the overlapping area is usually limited, thus resulting in a lack of correspondence features. The windows and doors can be observed from both sides and are usually utilized as shared features to make connections between indoor and outdoor models. However, the registration performance using the geometric features of windows and doors is limited due to the considerable number of extracted features and the mismatch of similar features. This paper proposed an indoor/outdoor alignment framework with a semantic feature matching method to solve the problem. After identifying the 3D window and door instances from the point clouds, a novel semantic–geometric descriptor (SGD) is proposed to describe the semantic information and the spatial distribution pattern of the instances. The best object match is identified with an improved Hungarian algorithm using indoor and outdoor SGDs. The matching method is effective even when the numbers of objects are not equal in the indoor and outdoor models, which is robust to measurement occlusions and feature outliers. The experimental results conducted in the collected dataset and the public dataset demonstrated that the proposed method could identify accurate object matches under complicated conditions, and the alignment accuracy reached the centimeter level.

Robust discriminative projection with dynamic graph regularization for feature extraction and classification

Learning an efficient discriminative projection to extract meaningful features from high-dimensional data is a challenging task in machine learning. However, most of the existing discriminative projection literatures have the following two issues: (1) the performance of projection would largely degenerate when handling the data corrupted by complex outlier, e.g., noisy and outlier mixed data; and (2) fixed graph in graph regularization can be negatively affected by outliers or noisy features. To deal with above issues, we design a new feature extraction method called robust discriminative projection with dynamic graph regularization (RDPDG) to handle above problems. Specifically, RDPDG simulates complex outlier features, i.e., low rank and sparse structured outlier features, using two matrices constrained by the nuclear and adaptive loss norm. RDPDG is able to boost the performance of classification, which primarily due to two key factors: (1) learns reliable projection through a unified framework that integrates discriminant analysis, reconstituted data and manifold learning; and (2) can exploit the local intrinsic structure among data effectively by dynamic graph regularization. Furthermore, an alternating iteration algorithm is designed to solve the proposed nonconvex model, which seamlessly connects the update process of all components in the RDPDG framework, offering a powerful discriminative capability for projection. Comprehensive experiments on a synthetic and several real-world data sets demonstrate that the RDPDG outperforms the precious related methods for classification.

RETRACTED ARTICLE: Incremental Outlier Feature Clustering Algorithm in Blockchain Networks Based on Big Data Analysis

Outlier detection in data mining aims at identifying anomalous observations known as outliers. The standard communication network incremental outlier feature clustering technique has a low clustering impact, requires several iterations, and takes a long clustering time. A novel incremental outlier based on big data analysis is proposed to overcome these problems for communicating networks in a Blockchain environment. Through big data analysis, the Point feature clustering algorithm uses the kernel density estimation technique with Gaussian kernel function to estimate the incremental outlier density of the communication network in the Blockchain framework. It mines the incremental outlier and applies the empirical mode based on the outlier mined for optimal outcome. The decomposition technique is used to extract outlier features, give weights to the features, and calculate the outlier degree and clusters. According to the results, the communication network, based on the Blockchain environment, may be clustered for incremental outlier features, and then outliers are ideally detected optimally. The simulation of the proposed technique is performed on three types of datasets. The simulation to form a cluster with the proposed method takes around 10 s of clustering time. The simulation results reveal that the proposed incremental outlier feature clustering (OFC) technique has a better outlier feature clustering impact on Blockchain-based networks, and requires a fewer iterations due to low computational and space complexity than other existing clustering techniques.

Feature matching for texture-less endoscopy images via superpixel vector field consistency.

Feature matching is an important technology to obtain the surface morphology of soft tissues in intraoperative endoscopy images. The extraction of features from clinical endoscopy images is a difficult problem, especially for texture-less images. The reduction of surface details makes the problem more challenging. We proposed an adaptive gradient-preserving method to improve the visual feature of texture-less images. For feature matching, we first constructed a spatial motion field by using the superpixel blocks and estimated its information entropy matching with the motion consistency algorithm to obtain the initial outlier feature screening. Second, we extended the superpixel spatial motion field to the vector field and constrained it with the vector feature to optimize the confidence of the initial matching set. Evaluations were implemented on public and undisclosed datasets. Our method increased by an order of magnitude in the three feature point extraction methods than the original image. In the public dataset, the accuracy and F1-score increased to 92.6% and 91.5%. The matching score was improved by 1.92%. In the undisclosed dataset, the reconstructed surface integrity of the proposed method was improved from 30% to 85%. Furthermore, we also presented the surface reconstruction result of differently sized images to validate the robustness of our method, which showed high-quality feature matching results. Overall, the experiment results proved the effectiveness of the proposed matching method. This demonstrates its capability to extract sufficient visual feature points and generate reliable feature matches for 3D reconstruction and meaningful applications in clinical.

An Outlier Detection and Feature Ranking based Ensemble Learning for ECG Analysis

An Outlier Detection and Feature Ranking based Ensemble Learning for ECG Analysis

An accurate and robust registration framework based on outlier removal and feature point adjustment for remote sensing images

ABSTRACT The reliability of feature matching can decide the accuracy and robustness of the feature-based registration result. Aiming at the problem that the number of final feature matches preserved by many popular outlier removal methods is small, and the position accuracy of final feature matches is not high enough, we propose an accurate and robust image registration framework based on outlier removal and feature point adjustment in this paper. This framework increases the number and improves the position accuracy of inliers while eliminating most outliers. The increased number of inliers improves the robustness of image registration, and high accurate inliers improves the accuracy of image registration. Firstly, the initial feature matches are extracted by a commonly used feature-based registration method, such as the scale-invariant feature transform (SIFT)-based method. Then, outliers of the initial feature matches are eliminated by a frequency domain similarity measure, called PHase-based Structural SIMilarity (PH-SSIM) proposed in this paper. Considering the inherent error of the feature matches that still exist after the outlier elimination, a PH-SSIM-based feature point adjustment strategy is designed to fine-adjust the position of the preserved feature points in the reference image. Finally, the registration parameters are calculated by the fine-adjusted feature matches. The proposed framework has been evaluated by several remote sensing images with different resolution, grey-scale, texture, and scene, and compared with four state-of-the-art image registration methods. Experimental result demonstrates the high accuracy and robustness of the proposed method.

ARIC: accurate and robust inference of cell type proportions from bulk gene expression or DNA methylation data.

Quantifying cell proportions, especially for rare cell types in some scenarios, is of great value in tracking signals associated with certain phenotypes or diseases. Although some methods have been proposed to infer cell proportions from multicomponent bulk data, they are substantially less effective for estimating the proportions of rare cell types which are highly sensitive to feature outliers and collinearity. Here we proposed a new deconvolution algorithm named ARIC to estimate cell type proportions from gene expression or DNA methylation data. ARIC employs a novel two-step marker selection strategy, including collinear feature elimination based on the component-wise condition number and adaptive removal of outlier markers. This strategy can systematically obtain effective markers for weighted $\upsilon$-support vector regression to ensure a robust and precise rare proportion prediction. We showed that ARIC can accurately estimate fractions in both DNA methylation and gene expression data from different experiments. We further applied ARIC to the survival prediction of ovarian cancer and the condition monitoring of chronic kidney disease, and the results demonstrate the high accuracy and robustness as well as clinical potentials of ARIC. Taken together, ARIC is a promising tool to solve the deconvolution problem of bulk data where rare components are of vital importance.