Classification of Suncus murinus species complex (Soricidae: Crocidurinae) in Peninsular Malaysia using image analysis and machine learning approaches

Abstract

BackgroundTaxonomists frequently identify specimen from various populations based on the morphological characteristics and molecular data. This study looks into another invasive process in identification of house shrew (Suncus murinus) using image analysis and machine learning approaches. Thus, an automated identification system is developed to assist and simplify this task. In this study, seven descriptors namely area, convex area, major axis length, minor axis length, perimeter, equivalent diameter and extent which are based on the shape are used as features to represent digital image of skull that consists of dorsal, lateral and jaw views for each specimen. An Artificial Neural Network (ANN) is used as classifier to classify the skulls of S. murinus based on region (northern and southern populations of Peninsular Malaysia) and sex (adult male and female). Thus, specimen classification using Training data set and identification using Testing data set were performed through two stages of ANNs.ResultsAt present, the classifier used has achieved an accuracy of 100% based on skulls’ views. Classification and identification to regions and sexes have also attained 72.5%, 87.5% and 80.0% of accuracy for dorsal, lateral, and jaw views, respectively. This results show that the shape characteristic features used are substantial because they can differentiate the specimens based on regions and sexes up to the accuracy of 80% and above. Finally, an application was developed and can be used for the scientific community.ConclusionsThis automated system demonstrates the practicability of using computer-assisted systems in providing interesting alternative approach for quick and easy identification of unknown species.

Wing Interferential Patterns (WIPs) and machine learning, a step toward automatized tsetse (Glossina spp.) identification

“…These systems deliver faster, more accurate, and more consistent semi or fully-automated identification than any human taxonomist. For instance, a group of entomologists at the Natural history museum in London have used the Digital Automated Identification System (DAISY) to identify 15 species of parasitic wasps via digital images of wings, with 100% accuracy, each identification taking a few seconds 32 . The need for community participation in blood-sucking invasive species identification, for example, Aedes (Ochloretatus) albopictus , Skuse 1895 has pushed deep learning methodology in the entomological survey field.…”

Morphology and Mitochondrial Lineage Investigations Corroborate the Systematic Status and Pliocene Colonization of Suncus niger (Mammalia: Eulipotyphla) in the Western Ghats Biodiversity Hotspot of India

“…The morphological characteristics of Suncus species often overlap, leading to misunderstandings during taxonomic evaluation. To address these issues, machine learning methods were recently employed to differentiate the S. murinus species complex in Peninsular Malaysia [53]. Prior to this study, although the identity and systematics of the Indian endemic eutherian (S. niger) were well accepted [7,8,54,55], it was necessary to reassess this taxon from its type locality.…”

Functional data geometric morphometrics with machine learning for craniodental shape classification in shrews

“…The skulls of C. malayana, C. monticola and S. murinus can be viewed from different angles, i.e., dorsal, jaws, ventral and lateral depending on the shape of the specimen (Figure 1). However, the ventral view was excluded in this study because both ventral and dorsal are identical in shape 16 . A total of 90 specimens of three different shrew species (C. malayana, C. monticola, S. murinus) were retrieved from the Museum of Zoology, Universiti Malaya (UM), Kuala Lumpur, Malaysia.…”

“…Skull digital images were captured using Nikon D90 with 15x magnification and stored in the Tagged Image File Format (tiff) format with a resolution of 4288 x 2848 pixels. Adobe Photoshop CS6 was also used to improve the image quality 16.…”