scholarly journals Detecting Ordinal Subcascades

2020 ◽  
Vol 52 (3) ◽  
pp. 2583-2605
Author(s):  
Ludwig Lausser ◽  
Lisa M. Schäfer ◽  
Silke D. Kühlwein ◽  
Angelika M. R. Kestler ◽  
Hans A. Kestler
Keyword(s):  
Data Analysis ◽  
Feature Space ◽  
Screening Procedure ◽  
Potential Candidate ◽  
Classifier Systems ◽  
Correct Order ◽  
Semantic Class ◽  
Class Labels ◽  
Total Orders

AbstractOrdinal classifier cascades are constrained by a hypothesised order of the semantic class labels of a dataset. This order determines the overall structure of the decision regions in feature space. Assuming the correct order on these class labels will allow a high generalisation performance, while an incorrect one will lead to diminished results. In this way ordinal classifier systems can facilitate explorative data analysis allowing to screen for potential candidate orders of the class labels. Previously, we have shown that screening is possible for total orders of all class labels. However, as datasets might comprise samples of ordinal as well as non-ordinal classes, the assumption of a total ordering might be not appropriate. An analysis of subsets of classes is required to detect such hidden ordinal substructures. In this work, we devise a novel screening procedure for exhaustive evaluations of all order permutations of all subsets of classes by bounding the number of enumerations we have to examine. Experiments with multi-class data from diverse applications revealed ordinal substructures that generate new and support known relations.

scholarly journals Weakly Supervised Conditional Random Fields Model for Semantic Segmentation with Image Patches

2020 ◽  
Vol 10 (5) ◽  
pp. 1679
Author(s):  
Xinying Xu ◽  
Yujing Xue ◽  
Xiaoxia Han ◽  
Zhe Zhang ◽  
Jun Xie ◽  
...  
Keyword(s):  
Random Fields ◽  
Conditional Random Fields ◽  
Semantic Category ◽  
Semantic Segmentation ◽  
Potential Energy Function ◽  
Semantic Class ◽  
Image Patches ◽  
Benchmark Datasets ◽  
Weakly Supervised ◽  
Class Labels

Image semantic segmentation (ISS) is used to segment an image into regions with differently labeled semantic category. Most of the existing ISS methods are based on fully supervised learning, which requires pixel-level labeling for training the model. As a result, it is often very time-consuming and labor-intensive, yet still subject to manual errors and subjective inconsistency. To tackle such difficulties, a weakly supervised ISS approach is proposed, in which the challenging problem of label inference from image-level to pixel-level will be particularly addressed, using image patches and conditional random fields (CRF). An improved simple linear iterative cluster (SLIC) algorithm is employed to extract superpixels. for image segmentation. Specifically, it generates various numbers of superpixels according to different images, which can be used to guide the process of image patch extraction based on the image-level labeled information. Based on the extracted image patches, the CRF model is constructed for inferring semantic class labels, which uses the potential energy function to map from the image-level to pixel-level image labels. Finally, patch based CRF (PBCRF) model is used to accomplish the weakly supervised ISS. Experiments conducted on two publicly available benchmark datasets, MSRC and PASCAL VOC 2012, have demonstrated that our proposed algorithm can yield very promising results compared to quite a few state-of-the-art ISS methods, including some deep learning-based models.

scholarly journals NON-TRIVIAL FEATURE DERIVATION FOR INTENSIFYING FEATURE DETECTION USING LIDAR DATASETS THROUGH ALLOMETRIC AGGREGATION DATA ANALYSIS APPLYING DIFFUSED HIERARCHICAL CLUSTERING FOR DISCRIMINATING AGRICULTURAL LAND COVER IN PORTIONS OF NORTHERN MINDANAO, PHILIPPINES

2016 ◽  
Vol XLI-B8 ◽  
pp. 1009-1016
Author(s):  
Ricardo G. Villar ◽  
Jigg L. Pelayo ◽  
Ray Mari N. Mozo ◽  
James B. Salig Jr. ◽  
Jojemar Bantugan
Keyword(s):  
Data Analysis ◽  
Hierarchical Clustering ◽  
Feature Detection ◽  
Agricultural Land ◽  
Feature Space ◽  
Machine Learning Algorithms ◽  
Kappa Index ◽  
Cloud Data ◽  
Allometric Relations ◽  
Novel Approach

Leaning on the derived results conducted by Central Mindanao University Phil-LiDAR 2.B.11 Image Processing Component, the paper attempts to provides the application of the Light Detection and Ranging (LiDAR) derived products in arriving quality Landcover classification considering the theoretical approach of data analysis principles to minimize the common problems in image classification. These are misclassification of objects and the non-distinguishable interpretation of pixelated features that results to confusion of class objects due to their closely-related spectral resemblance, unbalance saturation of RGB information is a challenged at the same time. Only low density LiDAR point cloud data is exploited in the research denotes as 2 pts/m<sup>2</sup> of accuracy which bring forth essential derived information such as textures and matrices (number of returns, intensity textures, nDSM, etc.) in the intention of pursuing the conditions for selection characteristic. A novel approach that takes gain of the idea of object-based image analysis and the principle of allometric relation of two or more observables which are aggregated for each acquisition of datasets for establishing a proportionality function for data-partioning. In separating two or more data sets in distinct regions in a feature space of distributions, non-trivial computations for fitting distribution were employed to formulate the ideal hyperplane. Achieving the distribution computations, allometric relations were evaluated and match with the necessary rotation, scaling and transformation techniques to find applicable border conditions. Thus, a customized hybrid feature was developed and embedded in every object class feature to be used as classifier with employed hierarchical clustering strategy for cross-examining and filtering features. This features are boost using machine learning algorithms as trainable sets of information for a more competent feature detection. The product classification in this investigation was compared to a classification based on conventional object-oriented approach promoting straight-forward functionalities of the software eCognition. A compelling rise of efficiency in the overall accuracy (74.4% to 93.4%) and kappa index of agreement (70.5% to 91.7%) is noticeable based on the initial process. Nevertheless, having low-dense LiDAR dataset could be enough in generating exponential increase of performance in accuracy.

scholarly journals Deep Coupling Recurrent Auto-Encoder with Multi-Modal EEG and EOG for Vigilance Estimation

Entropy ◽  
2021 ◽  
Vol 23 (10) ◽  
pp. 1316
Author(s):  
Kuiyong Song ◽  
Lianke Zhou ◽  
Hongbin Wang
Keyword(s):  
Data Analysis ◽  
Traffic Safety ◽  
Feature Fusion ◽  
Pearson Correlation ◽  
Metric Learning ◽  
Feature Space ◽  
Research Field ◽  
Function Optimization ◽  
Analysis Model ◽  
New Feature

Vigilance estimation of drivers is a hot research field of current traffic safety. Wearable devices can monitor information regarding the driver’s state in real time, which is then analyzed by a data analysis model to provide an estimation of vigilance. The accuracy of the data analysis model directly affects the effect of vigilance estimation. In this paper, we propose a deep coupling recurrent auto-encoder (DCRA) that combines electroencephalography (EEG) and electrooculography (EOG). This model uses a coupling layer to connect two single-modal auto-encoders to construct a joint objective loss function optimization model, which consists of single-modal loss and multi-modal loss. The single-modal loss is measured by Euclidean distance, and the multi-modal loss is measured by a Mahalanobis distance of metric learning, which can effectively reflect the distance between different modal data so that the distance between different modes can be described more accurately in the new feature space based on the metric matrix. In order to ensure gradient stability in the long sequence learning process, a multi-layer gated recurrent unit (GRU) auto-encoder model was adopted. The DCRA integrates data feature extraction and feature fusion. Relevant comparative experiments show that the DCRA is better than the single-modal method and the latest multi-modal fusion. The DCRA has a lower root mean square error (RMSE) and a higher Pearson correlation coefficient (PCC).

scholarly journals Relative Weighted Feature Space for Dimensionality Reduction and Classification of Hyperspectral Images

2017 ◽  
Author(s):  
Seyyed Ali Ahmadi ◽  
Nasser Mehrshad ◽  
Seyyed Mohammad Razavi
Keyword(s):  
Data Analysis ◽  
Dimension Reduction ◽  
Arbitrary Dimension ◽  
Feature Space ◽  
Hyperspectral Images ◽  
Low Rank ◽  
Similarity Function ◽  
Data Set ◽  
Weighting Matrix ◽  
Spectral Bands

Containing hundreds of spectral bands (features), hyperspectral images (HSIs) have high ability in discrimination of land cover classes. Traditional HSIs data processing methods consider the same importance for all bands in the original feature space (OFS), while different spectral bands play different roles in identification of samples of different classes. In order to explore the relative importance of each feature, we learn a weighting matrix and obtain the relative weighted feature space (RWFS) as an enriched feature space for HSIs data analysis in this paper. To overcome the difficulty of limited labeled samples which is common case in HSIs data analysis, we extend our method to semisupervised framework. To transfer available knowledge to unlabeled samples, we employ graph based clustering where low rank representation (LRR) is used to define the similarity function for graph. After construction the RWFS, any arbitrary dimension reduction method and classification algorithm can be employed in RWFS. The experimental results on two well-known HSIs data set show that some dimension reduction algorithms have better performance in the new weighted feature space.

scholarly journals Semantic image annotation using convolutional neural network and wordnet ontology

2018 ◽  
Vol 7 (2.27) ◽  
pp. 56
Author(s):  
Jaison Saji Chacko ◽  
Tulasi B
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Image Annotation ◽  
Digital Cameras ◽  
Semantic Class ◽  
Semantic Labeling ◽  
Textual Data ◽  
Semantic Concepts ◽  
Class Labels ◽  
Semantic Image Annotation

Images are a major source of content on the web. The increase in mobile phones and digital cameras have led to huge amount of non-textual data being generated which is mostly images. Accurate annotation is critical for efficient image search and retrieval. Semantic image annotation refers to adding meaningful meta-data to an image which can be used to infer additional knowledge from an image. It enables users to perform complex queries and retrieve accurate image results. This paper proposes an image annotation technique that uses deep learning and semantic labeling. A convolutional neural network is used to classify images and the predicted class labels are mapped to semantic concepts. The results shows that combining semantic class labeling with image classification can help in polishing the results and finding common concepts and themes.

Data Classification

2017 ◽  
pp. 34-51 ◽  
Author(s):  
A. Sheik Abdullah ◽  
R. Suganya ◽  
S. Selvakumar ◽  
S. Rajaram
Keyword(s):  
Big Data ◽  
Data Analysis ◽  
Data Classification ◽  
Large Data ◽  
Classification Problem ◽  
Data Sets ◽  
Credit Risk Analysis ◽  
Predicted Values ◽  
Class Labels ◽  
The One

Classification is considered to be the one of the data analysis technique which can be used over many applications. Classification model predicts categorical continuous class labels. Clustering mainly deals with grouping of variables based upon similar characteristics. Classification models are experienced by comparing the predicted values to that of the known target values in a set of test data. Data classification has many applications in business modeling, marketing analysis, credit risk analysis; biomedical engineering and drug retort modeling. The extension of data analysis and classification makes the insight into big data with an exploration to processing and managing large data sets. This chapter deals with various techniques, methodologies that correspond to the classification problem in data analysis process and its methodological impacts to big data.

AoP-LSE: Antioxidant Proteins Classification Using Deep Latent Space Encoding of Sequence Features

2021 ◽  
Vol 43 (3) ◽  
pp. 1489-1501
Author(s):  
Muhammad Usman ◽  
Shujaat Khan ◽  
Seongyong Park ◽  
Jeong-A Lee
Keyword(s):  
Feature Space ◽  
Vital Role ◽  
Computational Method ◽  
The Novel ◽  
Novel Proteins ◽  
Discriminating Power ◽  
Latent Space ◽  
Antioxidant Proteins ◽  
Class Labels ◽  
Space Encoding

It is of utmost importance to develop a computational method for accurate prediction of antioxidants, as they play a vital role in the prevention of several diseases caused by oxidative stress. In this correspondence, we present an effective computational methodology based on the notion of deep latent space encoding. A deep neural network classifier fused with an auto-encoder learns class labels in a pruned latent space. This strategy has eliminated the need to separately develop classifier and the feature selection model, allowing the standalone model to effectively harness discriminating feature space and perform improved predictions. A thorough analytical study has been presented alongwith the PCA/tSNE visualization and PCA-GCNR scores to show the discriminating power of the proposed method. The proposed method showed a high MCC value of 0.43 and a balanced accuracy of 76.2%, which is superior to the existing models. The model has been evaluated on an independent dataset during which it outperformed the contemporary methods by correctly identifying the novel proteins with an accuracy of 95%.

scholarly journals Feature Learning for SAR Target Recognition with Unknown Classes by Using CVAE-GAN

2021 ◽  
Vol 13 (18) ◽  
pp. 3554
Author(s):  
Xiaowei Hu ◽  
Weike Feng ◽  
Yiduo Guo ◽  
Qiang Wang
Keyword(s):  
Target Recognition ◽  
Feature Learning ◽  
Feature Space ◽  
Automatic Target Recognition ◽  
Data Sets ◽  
Generative Adversarial Network ◽  
Data Set ◽  
Adversarial Network ◽  
Public Data ◽  
Class Labels

Even though deep learning (DL) has achieved excellent results on some public data sets for synthetic aperture radar (SAR) automatic target recognition(ATR), several problems exist at present. One is the lack of transparency and interpretability for most of the existing DL networks. Another is the neglect of unknown target classes which are often present in practice. To solve the above problems, a deep generation as well as recognition model is derived based on Conditional Variational Auto-encoder (CVAE) and Generative Adversarial Network (GAN). A feature space for SAR-ATR is built based on the proposed CVAE-GAN model. By using the feature space, clear SAR images can be generated with given class labels and observation angles. Besides, the feature of the SAR image is continuous in the feature space and can represent some attributes of the target. Furthermore, it is possible to classify the known classes and reject the unknown target classes by using the feature space. Experiments on the MSTAR data set validate the advantages of the proposed method.

scholarly journals Prediction of Crime Occurrence using Multinomial Logistic Regression

2020 ◽  
Vol 9 (3) ◽  
pp. 1432-1435
Keyword(s):  
Logistic Regression ◽  
Data Analysis ◽  
Systematic Approach ◽  
Multinomial Logistic Regression ◽  
Heat Map ◽  
Criminal Offender ◽  
Logistic Regression Method ◽  
Hidden Patterns ◽  
Class Labels ◽  
Causes Of Crime

In order to uncover hidden patterns and correlations, data analysis examines large amounts of data. Analysis of crime isa systematic approach to the identification and analysis of crime patterns and itstrends. This plays a role in the planning of problems with crime and in formulating strategies for crime prevention. Instead of focusing on causes of crime such as criminal offender background, this work focuses primarily crime factors happened on every day. This work can predict the category of crime that has a higher likelihood of occurrence in those areas and can visualize in the form of histogram and heat map by category of crime, crime by day of week and month. The study depends on a lot of variables like class, latitude, longitude, etc. For forecast, the multinomial logistic regression method is used. For weekdays, the district and the hour of the accident are used as predictors.This algorithm is used because its target variable has more than two values and no ordering in the response variable.This provides greater efficiency for handling datasets with multi class labels. This forecast can be helpful in predicting the occurrence of crime in vulnerable areas, which in turn minimizes the crime rate by providing the patrol in those areas.

Sign in / Sign up

Export Citation Format

Share Document