[Study of Modeling Samples Selection Method Based on Near Infrared Spectrum].

For more wheat varieties classification problem, we use near infrared spectrumto do qualitative analysis. Increasing the size of modeling sample could increase information of the model, however, at the same time, it also makes information redundancy so that modeling time and storage space will increase, thus, we need to decrease the size of modeling sample though selecting them. Some information must be lost and the effects of the model must be worse if we select samples blindly. We put forward the k nearest neighbor-density sample selection based on the traditional selection methods. Experiments use the near infrared diffuse reflection spectrum of wheat seed from lots of days. First, we use preprocessing and feature extraction to deal with the wheat original spectrum, then select modeling sample by three methods that are random sampling, k nearest neighbor and k nearest neighbor-density, finally, we establish the models of BPR(Biomimetic Pattern Recognition) and BPRI(Biomimetic Pattern Recognition Improved). The experimental results show that in the model of BPR we get the best results using the selection method of k nearest neighbor-density, especially it also decreases the size of modeling sample deeply, and in the model of BPRI the results using the selection method of k nearest neighbor-density are much better than random sampling and a little better than k nearest neighbor, but in the meanwhile the size of modeling sample using the selection method of k nearest neighbor-density are much smaller than k nearest neighbor. The experimental results prove that the sample selection method of k nearest neighbor-density can not only greatly reduce the modeling sample size, and ensure the quality of the model, it has obvious effect on varieties classification problem of wheat.

[Maize Hybrid Seed Purity Identification Based on Near Infrared Reflectance (NIR) and Transmittance (NIT) Spectra].

This article explore the feasibility of using Near Infrared Reflectance (NIR) and Transmittance (NIT) Spectroscopy (908.1-1677.2 nm wavelength range) to identify maize hybrid purity, and compare the performance of NIR and NIT spectroscopy. Principle Component Analysis (PCA) and Orthogonal Linear Discriminant Analysis (OLDA) were used to reduce the dimension of spectra which have been pretreated by first derivative and vector normalization. The hybrid purity identification model of Nonghua101 and Jingyu16 were built by SVM. Models based on NIR spectra obtained correct identification rate as 100% and 90% for Nonghua101 and Jingyu16 respectively. But NIR spectra were greatly influenced by the placement of seeds, and there existed significant difference between NIR spectra of embryo and non-embryo side. Models based on NIT spectroscopy yielded correct identification rate as 98% both for Nonghua101 and Jingyu16. NIT spectra of embryo and non-embryo side were highly similar. The results indicate that it is feasible to identify maize hybrid purity based on NIR and NIT spectroscopy, and NIT spectroscopy is more suitable to analyze single seed kernel than NIR spectroscopy.

A survey on few-shot class-incremental learning.

Large deep learning models are impressive, but they struggle when real-time data is not available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for deep neural networks to learn new tasks from just a few labeled samples without forgetting the previously learned ones. This setup can easily leads to catastrophic forgetting and overfitting problems, severely affecting model performance. Studying FSCIL helps overcome deep learning model limitations on data volume and acquisition time, while improving practicality and adaptability of machine learning models. This paper provides a comprehensive survey on FSCIL. Unlike previous surveys, we aim to synthesize few-shot learning and incremental learning, focusing on introducing FSCIL from two perspectives, while reviewing over 30 theoretical research studies and more than 20 applied research studies. From the theoretical perspective, we provide a novel categorization approach that divides the field into five subcategories, including traditional machine learning methods, meta learning-based methods, feature and feature space-based methods, replay-based methods, and dynamic network structure-based methods. We also evaluate the performance of recent theoretical research on benchmark datasets of FSCIL. From the application perspective, FSCIL has achieved impressive achievements in various fields of computer vision such as image classification, object detection, and image segmentation, as well as in natural language processing and graph. We summarize the important applications. Finally, we point out potential future research directions, including applications, problem setups, and theory development. Overall, this paper offers a comprehensive analysis of the latest advances in FSCIL from a methodological, performance, and application perspective.

Rapid colorimetric sensor for ultrasensitive and highly selective detection of Fumonisin B1 in cereal based on laccase-mimicking activity of silver phosphate nanoparticles.

Ag3PO4 nanoparticles (NPs) was prepared through a facile coprecipitation method, and was first found to have excellent laccase-mimicking catalytic activity. The study confirms that Fumonisin B1 (FB1) can effectively hinder the production of superoxide anion (O2-) between Ag3PO4 NPs and dissolved oxygen, and further inhibit laccase-mimicking activity of Ag3PO4 NPs. Thus, a novel rapid colorimetric sensor for FB1 analysis in cereal was first established using laccase-mimicking activity as sensing signal. The absorbance variation of sensing solution is directly related to the amount of FB1, and the color change is further combined with smartphone for quantitively analysis of FB1. The limit of detection (LOD) of the sensor is determined as low as 1.73 µg·L-1, which is far lower than the maximum residue limits (MRLs) of FB1 set by European Commission and US Food and Drug Administration (FDA). The average recovery of 87.8-104.5% for FB1 detection was obtained in cereal.

Early Supplementation with Starter Can Improve Production Performance of Lambs but this Growth Advantage Disappears after 154 Days of Age.

The aim of this experiment was to study the sustained effects of early supplementation with a starter on the performance of lambs during the pre-weaning, post-weaning, and fattening periods. Sixty male Hu lambs (3.59 ± 0.05 kg) were randomly assigned to two (30 lambs per group) treatments. The lambs were fed milk replacer from three days of age. The early supplementation (ES) group was supplemented with a starter ration at seven days of age, the control (CON) group was supplemented at 21 days of age, and lambs in both groups were weaned from milk replacer at 28 days of age. Eight lambs from each group were randomly slaughtered at 98 days of age, and the remaining lambs were fed the same nutrient level of a fattening ration until slaughter at 200 days of age. The results showed that early supplementation with starter significantly improved average daily feed intake (ADFI) and average daily weight gain (ADG) in the pre-weaning period (7-28 days of age), and ADFI and slaughter performance (live weight before slaughter, carcass weight and dressing percentage) in the post-weaning period (29-98 days of age, p < 0.05). In addition, early supplementation with the starter had no significant effect (p > 0.05) on ADFI, ADG, and slaughter performance, but significantly decreased (p < 0.05) the feed-to-gain ratio (F/G) of lambs during the fattening period (99-200 days of age). In addition, early supplementation with starter increased the ratio of rumen and reticulum weight to total stomach weight in lambs (p < 0.05). In conclusion, early supplementation with starter can reduce feed costs and improve the performance of lambs, while the growth advantage produced by early supplementation had initially disappeared by 154 days of age.

Phylogenetic and Comparative Analyses of Complete Chloroplast Genomes of Chinese Viburnum and Sambucus (Adoxaceae).

Phylogenetic analyses of complete chloroplast genome sequences have yielded significant improvements in our understanding of relationships in the woody flowering genus Viburnum (Adoxaceae, Dipsacales); however, these relationships were evaluated focusing only on Viburnum species within Central and South America and Southeast Asia. By contrast, despite being a hotspot of Viburnum diversity, phylogenetic relationships of Viburnum species in China are less well known. Here, we characterized the complete chloroplast (cp) genomes of 21 Viburnum species endemic to China, as well as three Sambucus species. These 24 plastomes were highly conserved in genomic structure, gene order and content, also when compared with other Adoxaceae. The identified repeat sequences, simple sequence repeats (SSRs) and highly variable plastid regions will provide potentially valuable genetic resources for further population genetics and phylogeographic studies on Viburnum and Sambucus. Consistent with previous combined phylogenetic analyses of 113 Viburnum species, our phylogenomic analyses based on the complete cp genome sequence dataset confirmed the sister relationship between Viburnum and the Sambucus-Adoxa-Tetradoxa-Sinadoxa group, the monophyly of four recognized sections in Flora of China (i.e., Viburnum sect. Tinus, Viburnum sect. Solenotinus, Viburnum sect. Viburnum and Viburnum sect. Pseudotinus) and the nonmonophyly of Viburnum sect. Odontotinus and Viburnum sect. Megalotinus. Additionally, our study confirmed the sister relationships between the clade Valvatotinus and Viburnum sect. Pseudotinus, as well as between Viburnum sect. Opulus and the Odontotinus-Megalotinus group. Overall, our results clearly document the power of the complete cp genomes in improving phylogenetic resolution, and will contribute to a better understanding of plastome evolution in Chinese Adoxaceae.

Characteristic of the complete chloroplast genome of Symphoricarpos sinensis, an important ornamental plant endemic to China.

Symphoricarpos sinensis is an important ornamental plant in China. Due to the lack of efficient molecular markers, although recent studies supported that Symphoricarpos was phylogenetically closely related to Lonicera, Triosteum, Heptacodium, and Leycesteria, relationships among these taxa remained uncertain. To examine the phylogenetic position of Symphoricarpos within Caprifoliaceae, we characterized the complete chloroplast (cp) genome of S. sinensis. The results showed that S. sinensis shared a typical quadripartite structure as with most angiosperms. It was 155,738 bp in length, including two inverted repeat (IR) regions (24,010 bp), a small single-copy (SSC) region (18,942 bp) and a large single-copy (LSC) region (88,776 bp). Phylogenetic analysis demonstrated that Caprifoliaceae and Adoxaceae formed two distinct monophyletic clades, and S. sinensis was closely related to lonicera and Triosteum, albeit with low support. The whole cp genome of S. sinensis will be useful resources for future studies on phylogeny and conservation in Symphoricarpos.