Accurate classification of tree-species is essential for sustainably managing forest resources and effectively monitoring species diversity. In this study, we used simultaneously acquired hyperspectral and LiDAR data from LiCHy (Hyperspectral, LiDAR and CCD) airborne system to classify tree-species in subtropical forests of southeast China. First, each individual tree crown was extracted using the LiDAR data by a point cloud segmentation algorithm (PCS) and the sunlit portion of each crown was selected using the hyperspectral data. Second, different suites of hyperspectral and LiDAR metrics were extracted and selected by the indices of Principal Component Analysis (PCA) and the mean decrease in Gini index (MDG) from Random Forest (RF). Finally, both hyperspectral metrics (based on whole crown and sunlit crown) and LiDAR metrics were assessed and used as inputs to Random Forest classifier to discriminate five tree-species at two levels of classification. The results showed that the tree delineation approach (point cloud segmentation algorithm) was suitable for detecting individual tree in this study (overall accuracy = 82.9%). The classification approach provided a relatively high accuracy (overall accuracy > 85.4%) for classifying five tree-species in the study site. The classification using both hyperspectral and LiDAR metrics resulted in higher accuracies than only hyperspectral metrics (the improvement of overall accuracies = 0.4–5.6%). In addition, compared with the classification using whole crown metrics (overall accuracies = 85.4–89.3%), using sunlit crown metrics (overall accuracies = 87.1–91.5%) improved the overall accuracies of 2.3%. The results also suggested that fewer of the most important metrics can be used to classify tree-species effectively (overall accuracies = 85.8–91.0%).

/pdf/tree-species-classification-in-subtropical-forests-using-2t7lhs2fqd.pdf

Tree-species classification in subtropical forests using airborne hyperspectral and LiDAR data.

This paper focuses on the application of machine learning algorithms for predicting spinal abnormalities. As a data preprocessing step, univariate feature selection as a filter based feature selection, and principal component analysis (PCA) as a feature extraction algorithm are considered. A number of machine learning approaches namely support vector machine (SVM), logistic regression (LR), bagging ensemble methods are considered for the diagnosis of spinal abnormality. The SVM, LR, bagging SVM and bagging LR models are applied on a dataset of 310 samples publicly available in Kaggle repository. The performance of classification of abnormal and normal spinal patients is evaluated in terms of a number of factors including training and testing accuracy, recall, and miss rate. The classifier models are also evaluated by optimizing the kernel parameters, and by using the results of receiver operating characteristic (ROC) and precision-recall curves. Results indicate that when 78% data are used for training, the observed training accuracies for SVM, LR, bagging SVM and bagging LR are 86.30%, 85.47%, 86.72% and 85.06%, respectively. On the other hand, the accuracies for the test dataset for SVM, LR, bagging SVM and bagging LR are the same being 86.96%. However, bagging SVM is the most attractive as it has a higher recall value and a lower miss rate compared to others. Hence, bagging SVM is suitable for the classification of spinal patients when applied on the most five important features of spinal samples.

Data-driven diagnosis of spinal abnormalities using feature selection and machine learning algorithms.

This paper presents a novel inexact full adder based on carbon nanotube field-effect transistors (CNTFET) for approximate computations, which has soared in popularity especially for image processing applications. The proposed design generates the output carry without error. Therefore, the propagation of incorrect value to higher bit positions is avoided. It has the least relative error distance (Relative ED) compared to other approximate full adders reported in the literature. Practical simulations by using MATLAB demonstrate higher peak signal to noise ratio (PSNR) and image quality for motion detector image processing application. HSPICE simulations also confirm the efficiency of the proposed design. Moreover, area occupation is investigated by using electric tool. Power consumption, delay, area and ED are important evaluating factors in this subject. Comparisons are made by a comprehensive parameter (PDAEDP), based on which the new design has 23.8%, 41.5%, 70.5%, 78% and 83.6% higher performance than TGA1, TGA2, AXA1, AXA2 and AXA3, respectively.

A Novel High-Speed, Low-Power CNTFET-Based Inexact Full Adder Cell for Image Processing Application of Motion Detector

Accurate acquisition of forest structural parameters, which is essential for the parameterization of forest growth models and understanding forest ecosystems, is also crucial for forest inventories and sustainable forest management. In this study, simultaneously acquired airborne full-waveform (FWF) LiDAR and hyperspectral data were used to predict forest structural parameters in subtropical forests of southeast China. The pulse amplitude and waveform shape of airborne FWF LiDAR data were calibrated using a physical process-driven and a voxel-based approach, respectively. Different suites of FWF LiDAR and hyperspectral metrics, i.e., point cloud (derived from LiDAR-waveforms) metrics (DPC), full-waveform (geometric and radiometric features) metrics (FW) and hyperspectral (original reflectance bands, vegetation indices and statistical indices) metrics (HS), were extracted and assessed using correlation analysis and principal component analysis (PCA). The selected metrics of DPC, FW and HS were used to fit regression models individually and in combination to predict diameter at breast height (DBH), Lorey’s mean height (HL), stem number (N), basal area (G), volume (V) and above ground biomass (AGB), and the capability of the predictive models and synergetic effects of metrics were assessed using leave-one-out cross validation. The results showed that: among the metrics selected from three groups divided by the PCA analysis, twelve DPC, eight FW and ten HS were highly correlated with the first and second principal component (r > 0.7); most of the metrics selected from DPC, FW and HS had weak relationships between each other (r < 0.7); the prediction of HL had a relatively higher accuracy (Adjusted-R2 = 0.88, relative RMSE = 10.68%), followed by the prediction of AGB (Adjusted-R2 = 0.84, relative RMSE = 15.14%), and the prediction of V had a relatively lower accuracy (Adjusted-R2 = 0.81, relative RMSE = 16.37%); and the models including only DPC had the capability to predict forest structural parameters with relatively high accuracies (Adjusted-R2 = 0.52–0.81, relative RMSE = 15.70–40.87%) whereas the usage of DPC and FW resulted in higher accuracies (Adjusted-R2 = 0.62–0.87, relative RMSE = 11.01–31.30%). Moreover, the integration of DPC, FW and HS can further improve the accuracies of forest structural parameters prediction (Adjusted-R2 = 0.68–0.88, relative RMSE = 10.68–28.67%).

Prediction of Forest Structural Parameters Using Airborne Full-Waveform LiDAR and Hyperspectral Data in Subtropical Forests

The design of inexact circuits at the transistor level remarkably improves figures of merits such as power consumption, delay, energy, and area. Therefore, inexact technique for designing circuits has attracted the attention of researchers worldwide. Designing inexact Full Adder cell as a building block of a variety of arithmetic circuits can affect the entire electronic system’s performance. In this paper, two novel inexact 1-bit Full Adder cells are presented using carbon nanotube field effect transistors (CNFETs). The capacitive threshold logic (CTL) is used to realize the proposed cells. Comprehensive simulations at two levels of abstraction, i.e., application and hardware are carried out to evaluate the efficacy of these circuits. First, the motion detector which is one of the image processing applications is deployed in MATLAB software to measure peak signal-to-noise ratio (PSNR) figure of merit. At hardware level, the HSPICE tool is used to carry out simulations and measure power, delay, po...

An efficient inexact Full Adder cell design in CNFET technology with high-PSNR for image processing

In this paper, the quality metrics evaluation on hyperspectral images has been presented using k-means clustering and segmentation. After classification the assessment of similarity between original image and classified image is achieved by measurements of image quality parameters. Experiments were carried out on four different types of hyperspectral images. Aerial and spaceborne hyperspectral images with different spectral and geometric resolutions were considered for quality metrics evaluation. Principal Component Analysis (PCA) has been applied to reduce the dimensionality of hyperspectral data. PCA was ultimately used for reducing the number of effective variables resulting in reduced complexity in processing. In case of ordinary images a human viewer plays an important role in quality evaluation. Hyperspectral data are generally processed by automatic algorithms and hence cannot be viewed directly by human viewers. Therefore evaluating quality of classified image becomes even more significant. An elaborate comparison is made between k-means clustering and segmentation for all the images by taking Peak Signal-to-Noise Ratio (PSNR), Mean Square Error (MSE), Maximum Squared Error, ratio of squared norms called L2RAT and Entropy. First four parameters are calculated by comparing the quality of original hyperspectral image and classified image. Entropy is a measure of uncertainty or randomness which is calculated for classified image. Proposed methodology can be used for assessing the performance of any hyperspectral image classification techniques.

/pdf/quality-metrics-evaluation-of-hyperspectral-images-55rs5i162x.pdf

Quality metrics evaluation of hyperspectral images

In this paper different classification methods are compared using base and meta(Combination of Multiple Classifier for training) level classifiers, for the fruitful diagnosis of Lower Back Pain. The Lower Back Pain becomes chronic with age, so needs to be correctly diagnose with symptoms in the early age. Five independent classifiers were implemented at base level and meta level. At meta level, five combinations of different classifiers were implemented, using voting technique. According to the scores, the overall classification using Naïve Bayes and Multilayer Perceptron got the maximum efficiency 83.87%. The purpose of this paper is to diagnose healthy individuals efficiently. To carry out study the Lower Back Pain Symptoms Dataset is used from very famous platform for predictive modeling, Kaggle. The experiments were carried out in WEKA (Waikato Environment for Knowledge Analysis), suite of machine learning software1.

/pdf/a-comparative-analysis-of-classificaton-methods-for-1kebvqqt0t.pdf

A Comparative Analysis of Classificaton methods for Diagnosis of Lower Back Pain

Hyperspectral image contains information as a set of contiguous spectral wavelength bands These images are three dimensional images having up to two hundred bands or more Although hyperspectral image contain hundreds of bands, a few number of bands can explain the vast majority of the information Hence, hyperspectral image is transformed into lower dimension by preserving the main features of the original data using dimension reduction techniques, which eliminate data redundancy In order to reduce the complexity and the time taken for processing of the hyperspectral images, Principal Component Analysis (PCA) is used to reduce the dimensionality while retaining all important features of the image In this paper, PCA and Noise Adjusted Principal Component Analysis (NAPCA) have been simulated in the area of hyperspectral image processing Experiments were carried out on three different types of aerial hyperspectral images having different spectral and spatial resolutions An elaborate performance evaluation for these data reduction techniques has been carried out by taking image quality parameters such as Peak Signal-to-Noise Ratio (PSNR) and Mean Square Error (MSE) Image quality parameters are calculated using original hyperspectral image and reconstructed images of PCA and NAPCA

Performance evaluation for data reduction techniques of hyperspectral images

Now a day's remote sensing imaging is extensively used in the study of land resources, surface geology, water resources, landslide study, forest study, urban development at large scale. Always there is a need to improve the spatial and spectral information of remote sensing data. This can be done either by building new satellites with high resolution power or by using image processing techniques. Building a new satellite with high power is much more expensive, so it is an advantage of using image processing techniques. Hyperspectral imaging sensor provides better spectral resolution, but provide poor spatial resolution and multispectral imaging sensor provides good spatial resolution but provide poor spectral resolution. There are many fusion techniques such as Gram Schmidt Pan Sharpening, Principal Component Transform, High Pass Filtering are used to sharpen Multispectral Image with panchromatic image. To sharpen the hyperspectral image we are trying to fuse the HSI with MSI with the existing techniques and are quantified using Mean Square Error, Peak Signal to Noise Ratio, Entropy, and Universal Image Quality Index.

High spatial resolution hyperspectral image using fusion technique

This paper proposes a Wrapper based Principal Component Selection (WPCS) method for improved classification accuracy of hyperspectral images. First, the hyperspectral image is transformed into feature space using the widely used Feature Extraction (FE) method such as the Principal Component Analysis (PCA). Next, the proposed WPCS method with an improved objective criterion has been applied on the PCA image to obtain the best heuristic set of Principal Components (PCs) with respect to the selected classifier. The generality of the method has been proven by using the widely used conventional Support Vector Machine (SVM) and a deep learning based 1-Dimentional Convolutional Neutral Network (1D-CNN) as wrappers. This paper also presents the comparison between the best heuristic PCs of SVM and 1D-CNN to draw interesting findings for improving classification accuracy. Simulations of the proposed method have been carried out on the real and challenging hyperspectral datasets such as Pavia University, Indian Pines, and Salinas, and the results are compared with representative methods such as SVM wrapper, K-Nearest Neighbour (KNN) wrapper and the state-of-the-art Distance Density based Convolutional Neural Network (DDCNN) method to substantiate the effectiveness of the proposed method.

Arvind Kumar Singh

Papers

Quality metrics evaluation of hyperspectral images

A Comparative Analysis of Classificaton methods for Diagnosis of Lower Back Pain

Performance evaluation for data reduction techniques of hyperspectral images

High spatial resolution hyperspectral image using fusion technique

Wrapper Based Principal Component Selection For Hyperspectral Image Classification