scholarly journals On Supervised Classification of Feature Vectors with Independent and Non-Identically Distributed Elements

Entropy ◽  
2021 ◽  
Vol 23 (8) ◽  
pp. 1045
Author(s):  
Farzad Shahrivari ◽  
Nikola Zlatanov
Keyword(s):  
Error Probability ◽  
Supervised Classification ◽  
Feature Vector ◽  
Training Data ◽  
Finite Alphabet ◽  
Feature Vectors ◽  
Optimal Classifier ◽  
Mutually Independent ◽  
Distributed Elements

In this paper, we investigate the problem of classifying feature vectors with mutually independent but non-identically distributed elements that take values from a finite alphabet set. First, we show the importance of this problem. Next, we propose a classifier and derive an analytical upper bound on its error probability. We show that the error probability moves to zero as the length of the feature vectors grows, even when there is only one training feature vector per label available. Thereby, we show that for this important problem at least one asymptotically optimal classifier exists. Finally, we provide numerical examples where we show that the performance of the proposed classifier outperforms conventional classification algorithms when the number of training data is small and the length of the feature vectors is sufficiently high.

scholarly journals Walsh Transform based Feature vector generation for Image Database Classification

2016 ◽  
Vol 6 (3) ◽  
pp. 1176
Author(s):  
Jagruti Ketan Save
Keyword(s):  
Nearest Neighbor ◽  
Feature Vector ◽  
Similarity Measures ◽  
Image Database ◽  
Training Data ◽  
Walsh Transform ◽  
Test Image ◽  
Feature Vectors ◽  
Vector Generation ◽  
Automated Classifier

Thousands of images are generated everyday, which implies the need to build an easy, faster, automated classifier to classify and organize these images. Classification means selecting an appropriate class for a given image from a set of pre-defined classes. The main objective of this work is to explore feature vector generation using Walsh transform for classification. In the first method, we applied Walsh transform on the columns of an image to generate feature vectors. In second method, Walsh wavelet matrix is used for feature vector generation. In third method we proposed to apply vector quantization (VQ) on feature vectors generated by earlier methods. It gives better accuracy, fast computation and less storage space as compared with the earlier methods. Nearest neighbor and nearest mean classification algorithms are used to classify input test image. Image database used for the experimentation contains 2000 images. All these methods generate large number of outputs for single test image by considering four similarity measures, six sizes of feature vector, two ways of classification, four VQ techniques, three sizes of codebook, and five combinations of wavelet transform matrix generation. We observed improvement in accuracy from 63.22% to 74% (55% training data) through the series of techniques.

Quantifying forest loss and forest degradation in Myanmar’s “home of teak”

2020 ◽  
Vol 50 (2) ◽  
pp. 89-101
Author(s):  
Thu Ya Kyaw ◽  
René H. Germain ◽  
Stephen V. Stehman ◽  
Lindi J. Quackenbush
Keyword(s):  
Supervised Classification ◽  
Landsat Imagery ◽  
Reference Sample ◽  
Tectona Grandis ◽  
Forest Degradation ◽  
Training Data ◽  
Forest Loss ◽  
Mountain Range ◽  
And Training

The Bago Mountain Range in Myanmar is known as the “home of teak” (Tectona grandis L. f.) because of its bountiful, naturally growing teak-bearing forests. Accelerating forest loss and degradation are threatening the sustainable production of teak in the region. Changes in land cover between 2000 and 2017 in four reserved forests of the Bago Mountain Range were mapped using supervised classification of Landsat imagery and training data collected in the field. A stratified random sample was used to collect reference data to assess accuracy of the maps and estimate area. Based on the reference sample, it was estimated that the forest area declined from 71 240 ha (standard error (SE) = 1524 ha) in 2000 to 40 891 ha (SE = 4404 ha) in 2017, whereas the area of degraded forests increased from 88 797 ha (SE = 1694 ha) to 97 013 ha (SE = 5395 ha). The annualized rates of gross forest loss and gross forest degradation were 1.03% and 0.97%, respectively, indicating that forest degradation paralleled forest loss. In many degraded areas, there is an opportunity to ameliorate the situation through silviculture. The 2017 map identifies bamboo-dominated degraded forests where enrichment planting or reforestation is recommended.

scholarly journals An Automatic Modulation Classification Network for IoT Terminal Spectrum Monitoring under Zero-sample Situations

2021 ◽  
Author(s):  
Quan Zhou ◽  
Ronghui Zhang ◽  
Fangpei Zhang ◽  
Xiaojun Jing
Keyword(s):  
Cooperative Communication ◽  
Feature Vector ◽  
Recognition Accuracy ◽  
Original Data ◽  
Training Data ◽  
Modulation Classification ◽  
Spectrum Monitoring ◽  
Automatic Modulation Classification ◽  
Feature Vectors ◽  
Wireless Signal

Abstract Rely on powerful computing resources, a large number of internet of things (IoT) sensors are placed in various locations to sense the environment around where we live and improve the service. The proliferation of IoT end devices has led to the misuse of spectrum resources, making spectrum regulation an important task. Automatic modulation classification (AMC) is a task in spectrum monitoring, which senses the electromagnetic space and is carried out under non-cooperative communication. However, DL-based methods are data-driven and require large amounts of training data. In fact, under some non-cooperative communication scenarios, it is challenging to collect the wireless signal data directly. How can the DL-based algorithm complete the inference task under zero-sample conditions? In this paper, a signal zero-shot learning network (SigZSLNet) is proposed for AMC under the zero-sample situations firstly. Specifically, for the complexity of the original signal data, SigZSLNet generates the convolutional layer output feature vector instead of directly generating the original data of the signal. The semantic descriptions and the corresponding semantic vectors are designed to generate the feature vectors of the modulated signals. The generated feature vectors act as the training data of zero-sample classes, and the recognition accuracy of AMC is greatly improved in zero-sample cases as a consequence. The experimental results demonstrate the effectiveness of the proposed SigZSLNet. Simultaneously, we show the generated feature vectors and the intermediate layer output of the model.

Automated image classification of outlet glaciers in Greenland using deep learning

2020 ◽  
Author(s):  
Melanie Marochov ◽  
Patrice Carbonneau ◽  
Chris Stokes
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Image Classification ◽  
Supervised Classification ◽  
Greenland Ice Sheet ◽  
Training Data ◽  
Glacier Change ◽  
Outlet Glacier ◽  
Glacial Environments

<p>In recent decades, a wealth of research has focused on elucidating the key controls on the mass loss of the Greenland Ice Sheet and its response to climate forcing, specifically in relation to the drivers of spatio-temporally variable outlet glacier change. Despite the increasing availability of high-resolution satellite data, the time-consuming nature of the manual methods traditionally used to analyse satellite imagery has resulted in a significant bottleneck in the monitoring of outlet glacier change. Recent advances in deep learning applied to image processing have opened up a new frontier in the area of automated delineation of glacier termini. However, at this stage, there remains a paucity of research on the use of deep learning for image classification of outlet glacier landscapes. In this contribution, we apply a deep learning approach based on transfer learning to automatically classify satellite images of Helheim glacier, the fastest flowing outlet glacier in eastern Greenland. The method uses the well-established VGG16 convolutional neural network (CNN), and is trained on 224x224 pixel tiles derived from Sentinel-2 RGB bands, which have a spatial resolution of 10 metres. Based on features learned from ImageNet and limited training data, our deep learning model can classify glacial environments with >85% accuracy. In future stages of this research, we will use a new method originally developed for fluvial settings, dubbed ‘CNN-Supervised Classification’ (CSC). CSC uses a pre-trained CNN (in this case our VGG16 model) to replace the human operator’s role in traditional supervised classification by automatically producing new label data to train a pixel-level neural network classifier for any new image. This transferable approach to image classification of outlet glacier landscapes permits not only automated terminus delineation, but also facilitates the efficient analysis of numerous processes controlling outlet glacier behaviour, such as fjord geometry, subglacial plumes, and supra-glacial lakes.</p>

A Caption Text Detection Method from Images/Videos for Efficient Indexing and Retrieval of Multimedia Data

2015 ◽  
Vol 29 (01) ◽  
pp. 1555003 ◽  
Author(s):  
Samabia Tehsin ◽  
Asif Masood ◽  
Sumaira Kausar ◽  
Yunous Javed
Keyword(s):  
Feature Vector ◽  
Extraction Process ◽  
Text Detection ◽  
Multimedia Data ◽  
Support Vector ◽  
Feature Vectors ◽  
Text Extraction ◽  
Indexing And Retrieval ◽  
Detection And Localization

Textual information embedded in multimedia can provide a vital tool for indexing and retrieval. Text extraction process has many inherent problems due to the variation in font sizes, color, backgrounds and resolution. Text detection and localization are the most challenging phases of text extraction process whereas text extraction results are highly dependent upon these phases. This paper focuses on the text localization because of its very fundamental importance. Two effective feature vectors are introduced for the classification of the text and nontext objects. First feature vector is represented by the Radon transform of text candidate objects. Second feature vector is derived from the detailed geometrical analysis of text contents. Union of two feature vectors is used for the classification of text and nontext objects using support vector machine (SVM). Text detection and localization results are evaluated on two publicly available datasets namely ICDAR 2013 and IPC-Artificial text. Moreover, results are compared with state-of-the-art techniques and the Comparison demonstrates the superiority of the presented research.

scholarly journals Technical Note: Semi-automated classification of time-lapse RGB imagery for a remote Greenlandic river

2015 ◽  
Vol 12 (1) ◽  
pp. 1311-1327
Author(s):  
C. J. Gleason ◽  
L. C. Smith ◽  
D. C. Finnegan ◽  
A. L. LeWinter ◽  
L. H. Pitcher ◽  
...  
Keyword(s):  
Supervised Classification ◽  
Field Measurements ◽  
Time Lapse ◽  
Technical Note ◽  
Training Data ◽  
Hydraulic Parameters ◽  
Automated Classification ◽  
Braided Rivers ◽  
Highly Correlated

Abstract. River systems in remote environments are often challenging to monitor and understand where traditional gauging apparatus are difficult to install or where safety concerns prohibit field measurements. In such cases, remote sensing, especially terrestrial time lapse imaging platforms, offer a means to better understand these fluvial systems. One such environment is found at the proglacial Isortoq River in southwest Greenland, a river with a constantly shifting floodplain and remote Arctic location that make gauging and in situ measurements all but impossible. In order to derive relevant hydraulic parameters for this river, two RGB cameras were installed in July of 2011, and these cameras collected over 10 000 half hourly time-lapse images of the river by September of 2012. Existing approaches for extracting hydraulic parameters from RGB imagery require manual or supervised classification of images into water and non-water areas, a task that was impractical for the volume of data in this study. As such, automated image filters were developed that removed images with environmental obstacles (e.g. shadows, sun glint, snow) from the processing stream. Further image filtering was accomplished via a novel automated histogram similarity filtering process. This similarity filtering allowed successful (mean accuracy 79.6%) supervised classification of filtered images from training data collected from just 10% of those images. Effective width, a hydraulic parameter highly correlated with discharge in braided rivers, was extracted from these classified images, producing a hydrograph proxy for the Isortoq River between 2011 and 2012. This hydrograph proxy shows agreement with historic flooding observed in other parts of Greenland in July 2012 and offers promise that the imaging platform and processing methodology presented here will be useful for future monitoring studies of remote rivers.

scholarly journals Predictive Modeling of Future Forest Cover Change Patterns in Southern Belize

2019 ◽  
Vol 11 (7) ◽  
pp. 823 ◽  
Author(s):  
Carly Voight ◽  
Karla Hernandez-Aguilar ◽  
Christina Garcia ◽  
Said Gutierrez
Keyword(s):  
Supervised Classification ◽  
Forest Cover ◽  
Agricultural Practices ◽  
Google Earth ◽  
Training Data ◽  
Forest Loss ◽  
Landsat 8 ◽  
Forest Cover Change ◽  
Change Analysis

Tropical forests and the biodiversity they contain are declining at an alarming rate throughout the world. Although southern Belize is generally recognized as a highly forested landscape, it is becoming increasingly threatened by unsustainable agricultural practices. Deforestation data allow forest managers to efficiently allocate resources and inform decisions for proper conservation and management. This study utilized satellite imagery to analyze recent forest cover and deforestation in southern Belize to model vulnerability and identify the areas that are the most susceptible to future forest loss. A forest cover change analysis was conducted in Google Earth Engine using a supervised classification of Landsat 8 imagery with ground-truthed land cover points as training data. A multi-layer perceptron neural network model was performed to predict the potential spatial patterns and magnitude of forest loss based on the regional drivers of deforestation. The assessment indicates that the agricultural frontier will continue to expand into recently untouched forests, predicting a decrease from 75.0% mature forest cover in 2016 to 71.9% in 2026. This study represents the most up-to-date assessment of forest cover and the first vulnerability and prediction assessment in southern Belize with immediate applications in conservation planning, monitoring, and management.

scholarly journals Heartbeat type classification with optimized feature vectors

2018 ◽  
Vol 8 (2) ◽  
pp. 170-175 ◽  
Author(s):  
Özal Yildirim ◽  
Ulas Baran Baloglu
Keyword(s):  
Particle Swarm Optimization ◽  
Feature Vector ◽  
Swarm Optimization ◽  
Genetic Search ◽  
Ecg Signals ◽  
Feature Vectors ◽  
Electrocardiogram Ecg ◽  
Type Classification

In this study, a feature vector optimization based method has been proposed for classification of the heartbeat types. Electrocardiogram (ECG) signals of five different heartbeat type were used for this aim. Firstly, wavelet transform (WT) method were applied on these ECG signals to generate all feature vectors. Optimizing these feature vectors is provided by performing particle swarm optimization (PSO), genetic search, best first, greedy stepwise and multi objective evoluationary algorithms on these vectors. These optimized feature vectors are later applied to the classifier inputs for performance evaluation. A comprehensive assessment was presented for the determination of optimized feature vectors for ECG signals and best-performing classifier for these optimized feature vectors was determined.

Sign in / Sign up

Export Citation Format

Share Document