Abstract Motile cilia are critical for diverse cellular activities, affecting the survival and development of most eukaryotic organisms. Central microtubules, located in lumen ciliary axonemes, non-centrosomal microtubules crucial motile beating. However, formation mechanism central remain elusive. Here, using Drosophila model, we identify Ccdc13 as a novel regulator assembly. We show that localizes along is essential its sperm flagella, with deletion consequently motility fertility male...

Abstract With the intensification of ecosystem damage, birds have become symbolic species ecosystem. Ornithology with interdisciplinary technical research plays a great significance for protecting and evaluating quality. Deep learning shows progress birdsongs recognition. However, as number network layers increases in traditional CNN, semantic information gradually becomes richer detailed disappears. Secondly, global carried by entire input may be lost convolution, pooling, or other...

As important members of the ecosystem, birds are good monitors ecological environment. Bird recognition, especially birdsong has attracted more and attention in field artificial intelligence. At present, traditional machine learning deep widely used recognition. Deep can not only classify recognize spectrums birdsong, but also be as a feature extractor. Machine is often to extracted handcrafted parameters. data samples classifier, directly determines performance classifier. Multi-view...

In the automatic apple sorting task, it is necessary to automatically classify certain species. A shallow convolutional neural network (CNN) architecture proposed for this purpose. After collecting a number of images and labelling them, training data obtained through series augmentation operations, then parameter optimization are carried out Caffe framework. The feasibility method verified by experiments which divided into two cases. case no occlusion, classification accuracy reaches...

Birds play a vital and indispensable role in biodiversity environmental conservation. Protecting bird diversity is crucial for maintaining the balance of nature, promoting ecosystem health, ensuring sustainable development. The Broad Learning System (BLS) exhibits an excellent ability to extract highly discriminative features from raw inputs construct complex feature representations by combining nodes enhancement nodes, thereby enabling effective recognition classification various birdsongs....

This paper addresses the problem of fast similar image retrieval, especially for large-scale datasets with millions images. We present a new framework which consists two dependent algorithms. First, feature is proposed to represent images, dubbed compact based clustering (CFC). For each image, we first extract cluster centers local features, and then calculate distribution histograms features statistics spatial information in form clustering, replacing thousands features. It can reduce...

Birds are a kind of environmental indicator organism, which can reflect the changes in ecological environment and biodiversity, recognition birdsongs further help understand protect birds natural environment. Extreme learning machine (ELM) has advantages fast speed good generalization ability, is widely used classification problems. Input layer weights hidden thresholds two key factors affecting ELM performance. As one swarm intelligence optimization methods, differential evolution (DE) be...

Along with the development of data scale and high complexity sound signals, feature extraction classification methods signals have become a major research hotspot. However, current signal are difficult to accurately stably provide high-precision effect for due complex frequency distribution influence noise. Therefore, robust method based on multi-scale multi-directional Gabor filters Mel cepstral coefficient (MtWGM) was proposed. This performs preprocessing by mixing hard threshold soft...

In the classification of birdsong, effect traditional feature extraction methods and identifying birds through deep learning is still not ideal. Therefore, this paper proposes a birdsong method based on Gabor_Wt image convolutional neural network. According to two-dimensional wavelet spectrogram signal can present more detailed information characteristics birdsong. The obtained by using transform from audio. images are extracted texture with 2D-Gabor filters. With network structure, WT_CNN...

Fir trees account for about a quarter of the country's building materials. grow quickly, and have certain economic, social, ecological other benefits. Different fir require different growth environments, so it is necessary to accurately identify seeds cultivate them more specifically, as maximize various benefits trees. In this paper, six kinds seeds, namely Abies fabri, Cryptomeria japonica, Metasequoia glyptostroboides, Cathaya argyrophylla, Keteleeria fortune, Picea asperata, were used...

This paper describes an effective and efficient image classification framework nominated distributed deep representation learning model (DDRL). The aim is to strike the balance between computational intensive approaches (tuned parameters) which are intended for computing, that focused on designed parameters but often limited by sequential computing cannot scale up. In evaluation of our approach, it shown DDRL able achieve state-of-art accuracy efficiently both medium large datasets. result...

Birds are sensitive to environmental changes and important indicator groups for biodiversity observation. The determination of bird species provides an basis ecological balance. Birdsong is biological feature birds identifying birds. Therefore, this paper proposes a birdsong recognition method based on multi-feature fusion. power spectrum audio obtained by fast Fourier transform, the Mel frequency point multiplication with filter banks. Multi-feature fusion fuse texture information extracted...

In the process of training classifier with self-training algorithm, this paper proposes a method based on clustering to reduce problem low classification accuracy due error unlabelled samples. The calculates centroids labelled samples by KNN and selects that are close class from as higher confidence. At same time, semi-supervised ensemble is proposed taking advantage differences among classifiers idea ensemble. results show comparison experiment public data sets bird song fully verifies...

ELM (Extreme Learning Machine) is a random method for Single-hidden layer feedforward neural network construction, and MFCC (Mel-frequency Cepstrum Coefficient) kind of feature parameter speech recognition. Based on Ensemble research bird songs recognition technology, this paper firstly preprocesses the data collected by web crawler, then extracts parameters from data, gets improved through differential calculation. Finally, used classification The experimental results show that can achieve...