Graphic Processing Unit-Accelerated Neural Network Model for Biological Species Recognition

A graphic processing unit (GPU)-accelerated biological species recognition method using partially connected neural evolutionary network model is introduced in this paper. The partial connected neural evolutionary network adopted in the paper can overcome the disadvantage of traditional neural network with small inputs. The whole image is considered as the input of the neural network, so the maximal features can be kept for recognition. To speed up the recognition process of the neural network, a fast implementation of the partially connected neural network was conducted on NVIDIA Tesla C1060 using the NVIDIA compute unified device architecture (CUDA) framework. Image sets of eight biological species were obtained to test the GPU implementation and counterpart serial CPU implementation, and experiment results showed GPU implementation works effectively on both recognition rate and speed, and gained 343 speedup over its counterpart CPU implementation. Comparing to feature-based recognition method on the same recognition task, the method also achieved an acceptable correct rate of 84.6% when testing on eight biological species.

Classification and spectrum optimization method of grease based on infrared spectrum

The infrared(IR)absorption spectral data of 63 kinds of lubricating greases containing six different types of thickeners were obtained using the IR spectroscopy.The Kohonen neural network algorithm was used to identify the type of the lubricating grease.The results show that this machine learning method can effectively eliminate the interference fringes in the IR spectrum,and complete the feature selection and dimensionality reduction of the high-dimensional spectral data.The 63 kinds of greases exhibit spatial clustering under certain IR spectrum recognition spectral bands,which are linked to characteristic peaks of lubricating greases and improve the recognition accuracy of these greases.The model achieved recognition accuracy of 100.00%,96.08%,94.87%,100.00%,and 87.50%for polyurea grease,calcium sulfonate composite grease,aluminum(Al)-based grease,bentonite grease,and lithium-based grease,respectively.Based on the different IR absorption spectrum bands produced by each kind of lubricating grease,the three-dimensional spatial distribution map of the lubricating grease drawn also verifies the accuracy of classification while recognizing the accuracy.This paper demonstrates fast recognition speed and high accuracy,proving that the Kohonen neural network algorithm has an efficient recognition ability for identifying the types of the lubricating grease.

What are fungal species and how to delineate them?

This is the opening paper in the special issue of Fungal Diversity,which collates the data on defining species.Defining and recognizing species has long been a controversial issue.Since Darwin’s proposed origin of species,over 30 species criteria have been brought forth and used to define species boundaries.In recent times,phylogenetic analyses based on multiple loci have been extensively used as a method to define species boundaries.However,only a few mycologists are aware that phylogenetic species criteria can mask discordances among fungal groups,leading to inaccurately defined species bounda-ries.In the current review,we discuss species recognition criteria,how and where these criteria can be applied along with their limitations and derived alternatives.In order to delimit fungal species,authors need to take into account not only the phylogenetic and phenotypic coherence,but also the timing of events that lead to fungal speciation and subsequent diversi-fications.Variations in the rate of phenotypic diversifications and convergent fungal evolution make it difficult to establish a universal species recognition criterion.The best practice can only be defined in the context of each fungal group.In this review,we provide a set of guidelines,encouraging an integrative taxonomic approach for species delimitation that can be used to define fungal species boundaries in the future.The other papers in this special issue deal with fungal speciation in Ascomycota,Dothideomycetes,Basidiomycota,basal fungi,lichen-forming fungi,plant pathogenic fungi,and yeasts.

Diversity of wing patterns and abdomen-generated substrate sounds in 3 European scorpionfly species

In the genus Panorpa （Insecta： Mecoptera）, also known as scorpionflies, pre- mating behavior includes repeated sequences of slow wing movements （waving, fanning, flagging） which are accompanied by rapid abdomen vibrations that generate substantial substrate-borne sound. It is still unknown whether wing patterns or vibratory signals contain information about species identity, sex and/or the quality of potential mating part- ners. Besides species-specific pheromones, these multimodal signals may be of particular importance for the maintenance of reproductive isolation in sympatrically occurring scor- pionfly species. Here, we analyzed phyologenetic relationships among, and the pattern of forewings as well as substrate-borne sound in 3 different sympatric Central-European scorpionfly species （P communis, P germanica, and P alpina）. Divergence time estimates, based on 879 bp of the mitochondrial COI gene, indicate longstanding separate evolu- tionary histories for the studied Panorpa species. Morphological analysis revealed that wing length as an indicator of body size increased in the following order： P alpina 〈 P. germanica 〈 P. communis. Individuals can be assigned to the correct species and sex with high accuracy just by evaluation of the number of dark spots and the proportion of wing pigmentation. Despite high variability of interpulse period at an individual level, across species analysis revealed a positive correlation of average interpulse period as well as mean signal amplitude with forewing length. These results suggest wing patterns, but less likely vibratory signals, to contain information about species identity. Furthermore, receivers may be able to estimate the body size of a signaler solely on the basis of substrate-borne sound.

Female answer specificity to male drumming calls in three closely related species of the stonefly genus Zwicknia (Plecoptera: Capniidae)

This study examines the rate of female answers to conspecific versus heterospecific male vibratory calls in three,closely related stonefly species:Zwicknia bifrons,Z.acuta,and Z.rupprechti.In a previous study those three species were recognized on the basis of their distinct male drumming calls along with differences in genital morphology and genetic divergence.During this study no-choice playback experiments using original male call samples from each species were performed,and the answer rate of females to con・specific and heterospecific signal variants was measured.Mixed effect logistic regression models were used to test if male call species identity had a statistically significant effect on female answer probability.Females answered conspecific male calls with significantly higher probability than heterospecific calls in all the three examined species,suggesting that the divergence of vibrational communication can be an important component of the prezygotic isolation between them.Low,but well detectable responsiveness to heterospecific calls was observable between Z.bifrons and Z.acuta,the two species closest to each other regarding mitochondrial genetic divergence and male call pattern similarity.Thus,our results are most congruent with a tight,gradual coevolution of male calls and female preferences.

A multi-locus phylogenetic evaluation of Diaporthe (Phomopsis)

The genus Diaporthe(Phomopsis)includes important plant pathogenic fungi with wide host ranges and geographic distributions.In the present study,phylogenetic species recognition in Diaporthe is re-evaluated using a multi-locus phylogeny based on a combined data matrix of rDNA ITS,and partial sequences from the translation elongation factor 1-α(EF 1-α),βtubulin(TUB)and calmodulin(CAL)molecular markers.DNA sequences of available extype cultures have been included,providing a multi-locus backbone tree for future studies on Diaporthe.Four utilizable loci were analyzed individually and in combination,and ITS,EF 1-αand multi-locus phylogenetic trees are presented.The phylogenetic tree inferred by combined analysis of four loci provided the best resolution for species as compared to single gene analysis.Notes are provided for nine species previously known in Phomopsis that are transferred to Diaporthe in the present study.The unraveling of cryptic species complexes of Diaporthe based on Genealogical Concordance Phylogenetic Species Recognition(GCPSR)is emphasized.