scholarly journals Robust and Scalable Learning of Complex Intrinsic Dataset Geometry via ElPiGraph

Entropy ◽  
2020 ◽  
Vol 22 (3) ◽  
pp. 296 ◽  
Author(s):  
Luca Albergante ◽  
Evgeny Mirkes ◽  
Jonathan Bac ◽  
Huidong Chen ◽  
Alexis Martin ◽  
...  
Keyword(s):  
Statistical Significance ◽  
Point Clouds ◽  
Large Datasets ◽  
Graph Grammar ◽  
Complex Data ◽  
Learning Approaches ◽  
Topological Graph ◽  
Principal Graph ◽  
Scalable Learning ◽  
Low Dimensional

Multidimensional datapoint clouds representing large datasets are frequently characterized by non-trivial low-dimensional geometry and topology which can be recovered by unsupervised machine learning approaches, in particular, by principal graphs. Principal graphs approximate the multivariate data by a graph injected into the data space with some constraints imposed on the node mapping. Here we present ElPiGraph, a scalable and robust method for constructing principal graphs. ElPiGraph exploits and further develops the concept of elastic energy, the topological graph grammar approach, and a gradient descent-like optimization of the graph topology. The method is able to withstand high levels of noise and is capable of approximating data point clouds via principal graph ensembles. This strategy can be used to estimate the statistical significance of complex data features and to summarize them into a single consensus principal graph. ElPiGraph deals efficiently with large datasets in various fields such as biology, where it can be used for example with single-cell transcriptomic or epigenomic datasets to infer gene expression dynamics and recover differentiation landscapes.

scholarly journals Automated feature-based grading and progression analysis of diabetic retinopathy

Eye ◽  
2021 ◽  
Author(s):  
Lutfiah Al-Turk ◽  
James Wawrzynski ◽  
Su Wang ◽  
Paul Krause ◽  
George M. Saleh ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Diabetic Macular Oedema ◽  
Large Datasets ◽  
Image Analysis System ◽  
Learning Approaches ◽  
External Evaluation ◽  
Severity Scale ◽  
Grading Systems ◽  
Feature Based ◽  
Analysis System

Abstract Background In diabetic retinopathy (DR) screening programmes feature-based grading guidelines are used by human graders. However, recent deep learning approaches have focused on end to end learning, based on labelled data at the whole image level. Most predictions from such software offer a direct grading output without information about the retinal features responsible for the grade. In this work, we demonstrate a feature based retinal image analysis system, which aims to support flexible grading and monitor progression. Methods The system was evaluated against images that had been graded according to two different grading systems; The International Clinical Diabetic Retinopathy and Diabetic Macular Oedema Severity Scale and the UK’s National Screening Committee guidelines. Results External evaluation on large datasets collected from three nations (Kenya, Saudi Arabia and China) was carried out. On a DR referable level, sensitivity did not vary significantly between different DR grading schemes (91.2–94.2.0%) and there were excellent specificity values above 93% in all image sets. More importantly, no cases of severe non-proliferative DR, proliferative DR or DMO were missed. Conclusions We demonstrate the potential of an AI feature-based DR grading system that is not constrained to any specific grading scheme.

scholarly journals EXPLORING ALS AND DIM DATA FOR SEMANTIC SEGMENTATION USING CNNS

2018 ◽  
Vol XLII-1 ◽  
pp. 347-354 ◽  
Author(s):  
F. Politz ◽  
M. Sester
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Good Alternative ◽  
Aerial Images ◽  
Learning Approaches ◽  
Advantages And Disadvantages ◽  
Sensing Applications ◽  
High Level

<p><strong>Abstract.</strong> Over the past years, the algorithms for dense image matching (DIM) to obtain point clouds from aerial images improved significantly. Consequently, DIM point clouds are now a good alternative to the established Airborne Laser Scanning (ALS) point clouds for remote sensing applications. In order to derive high-level applications such as digital terrain models or city models, each point within a point cloud must be assigned a class label. Usually, ALS and DIM are labelled with different classifiers due to their varying characteristics. In this work, we explore both point cloud types in a fully convolutional encoder-decoder network, which learns to classify ALS as well as DIM point clouds. As input, we project the point clouds onto a 2D image raster plane and calculate the minimal, average and maximal height values for each raster cell. The network then differentiates between the classes ground, non-ground, building and no data. We test our network in six training setups using only one point cloud type, both point clouds as well as several transfer-learning approaches. We quantitatively and qualitatively compare all results and discuss the advantages and disadvantages of all setups. The best network achieves an overall accuracy of 96<span class="thinspace"></span>% in an ALS and 83<span class="thinspace"></span>% in a DIM test set.</p>

scholarly journals Enhancing Both Efficiency and Representational Capability of Isomap by Extensive Landmark Selection

2015 ◽  
Vol 2015 ◽  
pp. 1-18 ◽  
Author(s):  
Dong Liang ◽  
Chen Qiao ◽  
Zongben Xu
Keyword(s):  
Manifold Learning ◽  
Computational Efficiency ◽  
New Method ◽  
Data Sets ◽  
Learning Approaches ◽  
Real World Data ◽  
Efficiency Property ◽  
Data Points ◽  
Low Dimensional ◽  
High Computational Efficiency

The problems of improving computational efficiency and extending representational capability are the two hottest topics in approaches of global manifold learning. In this paper, a new method called extensive landmark Isomap (EL-Isomap) is presented, addressing both topics simultaneously. On one hand, originated from landmark Isomap (L-Isomap), which is known for its high computational efficiency property, EL-Isomap also possesses high computational efficiency through utilizing a small set of landmarks to embed all data points. On the other hand, EL-Isomap significantly extends the representational capability of L-Isomap and other global manifold learning approaches by utilizing only an available subset from the whole landmark set instead of all to embed each point. Particularly, compared with other manifold learning approaches, the data manifolds with intrinsic low-dimensional concave topologies and essential loops can be unwrapped by the new method more successfully, which are shown by simulation results on a series of synthetic and real-world data sets. Moreover, the accuracy, robustness, and computational complexity of EL-Isomap are analyzed in this paper, and the relation between EL-Isomap and L-Isomap is also discussed theoretically.

scholarly journals On the Road: Route Proposal from Radar Self-Supervised by Fuzzy LiDAR Traversability

AI ◽  
2020 ◽  
Vol 1 (4) ◽  
pp. 558-585
Author(s):  
Michael Broome ◽  
Matthew Gadd ◽  
Daniele De Martini ◽  
Paul Newman
Keyword(s):  
Autonomous Vehicle ◽  
Optimal Path ◽  
Extreme Environments ◽  
Point Clouds ◽  
Learning Approaches ◽  
Weak Supervision ◽  
The Road ◽  
Optimal Path Planning ◽  
Rule Set ◽  
On The Road

This is motivated by a requirement for robust, autonomy-enabling scene understanding in unknown environments. In the method proposed in this paper, discriminative machine-learning approaches are applied to infer traversability and predict routes from Frequency-Modulated Contunuous-Wave (FMCV) radar frames. Firstly, using geometric features extracted from LiDAR point clouds as inputs to a fuzzy-logic rule set, traversability pseudo-labels are assigned to radar frames from which weak supervision is applied to learn traversability from radar. Secondly, routes through the scanned environment can be predicted after they are learned from the odometry traces arising from traversals demonstrated by the autonomous vehicle (AV). In conjunction, therefore, a model pretrained for traversability prediction is used to enhance the performance of the route proposal architecture. Experiments are conducted on the most extensive radar-focused urban autonomy dataset available to the community. Our key finding is that joint learning of traversability and demonstrated routes lends itself best to a model which understands where the vehicle should feasibly drive. We show that the traversability characteristics can be recovered satisfactorily, so that this recovered representation can be used in optimal path planning, and that an end-to-end formulation including both traversability feature extraction and routes learned by expert demonstration recovers smooth, drivable paths that are comprehensive in their coverage of the underlying road network. We conclude that the proposed system will find use in enabling mapless vehicle autonomy in extreme environments.

scholarly journals Combining K-Means and XGBoost Models for Anomaly Detection Using Log Datasets

Electronics ◽  
2020 ◽  
Vol 9 (7) ◽  
pp. 1164
Author(s):  
João Henriques ◽  
Filipe Caldeira ◽  
Tiago Cruz ◽  
Paulo Simões
Keyword(s):  
Data Analysis ◽  
Anomaly Detection ◽  
Capacity Planning ◽  
Domain Knowledge ◽  
Large Data ◽  
Large Datasets ◽  
Complex Data ◽  
Security Breaches ◽  
Log Files ◽  
Clustering And Classification

Computing and networking systems traditionally record their activity in log files, which have been used for multiple purposes, such as troubleshooting, accounting, post-incident analysis of security breaches, capacity planning and anomaly detection. In earlier systems those log files were processed manually by system administrators, or with the support of basic applications for filtering, compiling and pre-processing the logs for specific purposes. However, as the volume of these log files continues to grow (more logs per system, more systems per domain), it is becoming increasingly difficult to process those logs using traditional tools, especially for less straightforward purposes such as anomaly detection. On the other hand, as systems continue to become more complex, the potential of using large datasets built of logs from heterogeneous sources for detecting anomalies without prior domain knowledge becomes higher. Anomaly detection tools for such scenarios face two challenges. First, devising appropriate data analysis solutions for effectively detecting anomalies from large data sources, possibly without prior domain knowledge. Second, adopting data processing platforms able to cope with the large datasets and complex data analysis algorithms required for such purposes. In this paper we address those challenges by proposing an integrated scalable framework that aims at efficiently detecting anomalous events on large amounts of unlabeled data logs. Detection is supported by clustering and classification methods that take advantage of parallel computing environments. We validate our approach using the the well known NASA Hypertext Transfer Protocol (HTTP) logs datasets. Fourteen features were extracted in order to train a k-means model for separating anomalous and normal events in highly coherent clusters. A second model, making use of the XGBoost system implementing a gradient tree boosting algorithm, uses the previous binary clustered data for producing a set of simple interpretable rules. These rules represent the rationale for generalizing its application over a massive number of unseen events in a distributed computing environment. The classified anomaly events produced by our framework can be used, for instance, as candidates for further forensic and compliance auditing analysis in security management.

scholarly journals Progress in Biomedical Knowledge Discovery: A 25-year Retrospective

2016 ◽  
Vol 25 (S 01) ◽  
pp. S117-S29 ◽  
Author(s):  
L. Sacchi ◽  
J. H. Holmes
Keyword(s):  
Machine Learning ◽  
Knowledge Discovery ◽  
Latent Dirichlet Allocation ◽  
Heterogeneous Data ◽  
Machine Learning Algorithms ◽  
Search Term ◽  
Complex Data ◽  
Learning Approaches ◽  
Biomedical Knowledge ◽  
Observation Period

Summary Objectives: We sought to explore, via a systematic review of the literature, the state of the art of knowledge discovery in biomedical databases as it existed in 1992, and then now, 25 years later, mainly focused on supervised learning. Methods: We performed a rigorous systematic search of PubMed and latent Dirichlet allocation to identify themes in the literature and trends in the science of knowledge discovery in and between time periods and compare these trends. We restricted the result set using a bracket of five years previous, such that the 1992 result set was restricted to articles published between 1987 and 1992, and the 2015 set between 2011 and 2015. This was to reflect the current literature available at the time to researchers and others at the target dates of 1992 and 2015. The search term was framed as: Knowledge Discovery OR Data Mining OR Pattern Discovery OR Pattern Recognition, Automated. Results: A total 538 and 18,172 documents were retrieved for 1992 and 2015, respectively. The number and type of data sources increased dramatically over the observation period, primarily due to the advent of electronic clinical systems. The period 1992-2015 saw the emergence of new areas of research in knowledge discovery, and the refinement and application of machine learning approaches that were nascent or unknown in 1992. Conclusions: Over the 25 years of the observation period, we identified numerous developments that impacted the science of knowledge discovery, including the availability of new forms of data, new machine learning algorithms, and new application domains.Through a bibliometric analysis we examine the striking changes in the availability of highly heterogeneous data resources, the evolution of new algorithmic approaches to knowledge discovery, and we consider from legal, social, and political perspectives possible explanations of the growth of the field. Finally, we reflect on the achievements of the past 25 years to consider what the next 25 years will bring with regard to the availability of even more complex data and to the methods that could be, and are being now developed for the discovery of new knowledge in biomedical data.

Self-Organizing Map Learning Nonlinearly Embedded Manifolds

2005 ◽  
Vol 4 (1) ◽  
pp. 22-31 ◽  
Author(s):  
Timo Similä
Keyword(s):  
Learning Algorithm ◽  
Image Data ◽  
High Dimensional ◽  
Locally Linear Embedding ◽  
Complex Data ◽  
Dimensional Manifold ◽  
Self Organizing Map ◽  
Training Strategy ◽  
Low Dimensional ◽  
Self Organizing

One of the main tasks in exploratory data analysis is to create an appropriate representation for complex data. In this paper, the problem of creating a representation for observations lying on a low-dimensional manifold embedded in high-dimensional coordinates is considered. We propose a modification of the Self-organizing map (SOM) algorithm that is able to learn the manifold structure in the high-dimensional observation coordinates. Any manifold learning algorithm may be incorporated to the proposed training strategy to guide the map onto the manifold surface instead of becoming trapped in local minima. In this paper, the Locally linear embedding algorithm is adopted. We use the proposed method successfully on several data sets with manifold geometry including an illustrative example of a surface as well as image data. We also show with other experiments that the advantage of the method over the basic SOM is restricted to this specific type of data.

scholarly journals Hypergraph Induced Convolutional Manifold Networks

2019 ◽  
Author(s):  
Taisong Jin ◽  
Liujuan Cao ◽  
Baochang Zhang ◽  
Xiaoshuai Sun ◽  
Cheng Deng ◽  
...  
Keyword(s):  
State Of The Art ◽  
Noisy Data ◽  
Large Datasets ◽  
Complex Data ◽  
Deep Convolutional Neural Networks ◽  
Multiple Features ◽  
Performance Loss ◽  
Graph Modeling ◽  
Manifold Embedding ◽  
Two Samples

Deep convolutional neural networks (DCNN) with manifold embedding have achieved considerable attention in computer vision. However, prior arts are usually based on the neighborhood-based graph modeling only the pairwise relationship between two samples, which fail to fully capture intra-class variations and thus suffer from severe performance loss for noisy data. While such intra-class variations can be well captured via sophisticated hypergraph structure, we are motivated and lead a hypergraph induced Convolutional Manifold Network (H-CMN) to significantly improve the representation capacity of DCNN for the complex data. Specifically, two innovative designs are provides: 1) our manifold preserving method is implemented based on a mini-batch, which can be efficiently plugged into the existing DCNN training pipelines and be scalable for large datasets; 2) a robust hypergraph is built for each mini-batch, which not only offers a strong robustness against typical noise, but also captures the variances from multiple features. Extensive experiments on the image classification task on large benchmarking datasets demonstrate that our model achieves much better performance than the state-of-the-art  

Sign in / Sign up

Export Citation Format

Share Document