No abstract

No abstract

The rapid development of light detection and ranging (LiDAR) techniques is advancing ecological and forest research. During the last decade, numerous single tree segmentation techniques have been developed using airborne LiDAR data. However, accurate crown segmentation using terrestrial or mobile LiDAR data, which is an essential prerequisite for extracting branch level forest characteristics, is still challenging mainly because of the difficulties posed by tree crown intersection and irregular crown shape. In the current work, we developed a comparative shortest-path algorithm (CSP) for segmenting tree crowns scanned using terrestrial (T)-LiDAR and mobile LiDAR. The algorithm consists of two steps, namely trunk detection and subsequent crown segmentation, with the latter inspired by the well-proved metabolic ecology theory and the ecological fact that vascular plants tend to minimize the transferring distance to the root. We tested the algorithm on mobile-LiDAR-scanned roadside trees and T-LiDAR-scanned broadleaved and coniferous forests in China. Point-level quantitative assessments of the segmentation results showed that for mobile-LiDAR-scanned roadside trees, all the points were classified to their corresponding trees correctly, and for T-LiDAR-scanned broadleaved and coniferous forests, kappa coefficients ranging from 0.83 to 0.93 were obtained. We believe that our algorithm will make a contribution to solving the problem of crown segmentation in T-LiDAR scanned-forests, and might be of interest to researchers in LiDAR data processing and to forest ecologists. In addition, our research highlights the advantages of using ecological theories as guidelines for processing LiDAR data.

High-dimensional data in many areas such as computer vision and machine learning tasks brings in computational and analytical difficulty. Feature selection which selects a subset from observed features is a widely used approach for improving performance and effectiveness of machine learning models with high-dimensional data. In this paper, we propose a novel AutoEncoder Feature Selector (AEFS) for unsupervised feature selection which combines autoencoder regression and group lasso tasks. Compared to traditional feature selection methods, AEFS can select the most important features by excavating both linear and nonlinear information among features, which is more flexible than the conventional self-representation method for unsupervised feature selection with only linear assumptions. Experimental results on benchmark dataset show that the proposed method is superior to the state-of-the-art method.

No abstract

Spatiotemporal feature learning is of central importance for action recognition in videos. Existing deep neural network models either learn spatial and temporal features independently (C2D) or jointly with unconstrained parameters (C3D). In this paper, we propose a novel neural operation which encodes spatiotemporal features collaboratively by imposing a weight-sharing constraint on the learnable parameters. In particular, we perform 2D convolution along three orthogonal views of volumetric video data, which learns spatial appearance and temporal motion cues respectively. By sharing the convolution kernels of different views, spatial and temporal features are collaboratively learned and thus benefit from each other. The complementary features are subsequently fused by a weighted summation whose coefficients are learned end-to-end. Our approach achieves state-of-the-art performance on largescale benchmarks and won the 1st place in the Moments in Time Challenge 2018. Moreover, based on the learned coefficients of different views, we are able to quantify the contributions of spatial and temporal features. This analysis sheds light on interpretability of the model and may also guide the future design of algorithm for video recognition.

The classification models were constructed to discover neuroprotective compounds against glutamate or H2O2-induced neurotoxicity through machine learning approaches.

A nonplanar but conjugated heteroacene, biindeno­[2,1-b]­thiophenylidene (BTP), is employed to design and synthesize solution-processable polymer semiconductors for organic field-effect transistors (OFETs) applications first. By copolymerizing with isoindigo (IDG), diketopyrrolopyrrole (DPP), and naphthalenediimide (NDI) derivatives, three novel BTP-based copolymers (PBTP-IDG, PBTP-DPP, and PBTP-NDI) have been synthesized and characterized successfully. The results indicate that three BTP-based polymers exhibit broad absorption spectra and good solubility in most common solvents. Because of the dominantly electron-deficient contributions to the whole polymer backbones, the energy levels of the lowest unoccupied molecular orbitals are decreased to ca. −4.0 eV for all these polymers, thus exhibiting good electron affinities. Moreover, the deep-lying energy levels of the highest occupied molecular orbitals (HOMO) have been demonstrated for three BTP-based polymers, with the HOMO values ranging from −5.48 to −5.80 eV. Investigation of the OFETs performance indicates that three BTP-based polymers exhibit well hole transport properties in ambient air and excellent ambipolar performance in a N2 glovebox. Compared with PBTP-IDG and PBTP-NDI, the uniform morphological structure, interconnected polycrystalline grain, and close π–π stacking distance endow PBTP-DPP with higher hole mobility of 1.43 cm2 V–1 s–1. Particularly, the well-balanced hole and electron mobilities of 0.68 and 0.13 cm2 V–1 s–1 have been demonstrated for the PBTP-DPP-based OFETs in a N2 atmosphere, respectively. The results suggest that the nonplanar BTP unit and its derivatives are promising π-conjugated building blocks for the design and synthesis of solution-processable polymer semiconductors with high charge-transporting performance.