• Journal of the Korean Wood Science and Technology
• /
• 제45권6호
• /
• pp.797-808
• /
• 2017

Automatic wood species identification systems have enabled fast and accurate identification of wood species outside of specialized laboratories with well-trained experts on wood species identification. Conventional automatic wood species identification systems consist of two major parts: a feature extractor and a classifier. Feature extractors require hand-engineering to obtain optimal features to quantify the content of an image. A Convolutional Neural Network (CNN), which is one of the Deep Learning methods, trained for wood species can extract intrinsic feature representations and classify them correctly. It usually outperforms classifiers built on top of extracted features with a hand-tuning process. We developed an automatic wood species identification system utilizing CNN models such as LeNet, MiniVGGNet, and their variants. A smartphone camera was used for obtaining macroscopic images of rough sawn surfaces from cross sections of woods. Five Korean softwood species (cedar, cypress, Korean pine, Korean red pine, and larch) were under classification by the CNN models. The highest and most stable CNN model was LeNet3 that is two additional layers added to the original LeNet architecture. The accuracy of species identification by LeNet3 architecture for the five Korean softwood species was 99.3%. The result showed the automatic wood species identification system is sufficiently fast and accurate as well as small to be deployed to a mobile device such as a smartphone.

• 식물분류학회지
• /
• 제47권2호
• /
• pp.124-131
• /
• 2017

Species identification is a fundamental and routine process in plant systematics, and linguistic-based dichotomous keys are widely used in the identification process. Recently, novel tools for species identification have been developed to improve the accuracy, ease to use, and accessibility related to these tasks for a broad range of users given the advances in information and communications technology. A visual identification key is such an approach, in which couplets consist of images of plants or a part of a plant instead of botanical terminology. We developed a visual identification key for 101 taxa of Orchidaceae in Korea and evaluated its performance. It uses short statements for image couplets to avoid misinterpretations by users. The key at the initial steps (couplets) uses relatively easy characters that can be determined with the naked eye. The final steps of the visual key provide images of species and information about distributions and flowering times to determine the species that best fit the available information. The number of steps required to identify a species varies, ranging from three to ten with an average of 4.5. A performance test with senior college students showed that species were accurately identified using the visual key at a rate significantly higher than when using a linguistic-based dichotomous key and a color manual. The findings presented here suggest that the proposed visual identification key is a useful tool for the teaching of biodiversity at schools, for the monitoring of ecosystems by citizens, and in other areas that require rapid, easy, and accurate identifications of species.

• Journal of applied mathematics & informatics
• /
• 제18권1_2호
• /
• pp.273-286
• /
• 2005

Parameter identification problem of a three species (predator, mutualist-prey, and mutualist) ecological system with reaction-diffusion phenomenon is investigated in this paper. The mathematical model of the parameter identification problem is constructed and continuous dependence of the solution for the direct problem on the parameters identified is obtained. Finally, the existence of optimal solution and an optimality necessary condition for the parameter identification problem are given.

• 대한본초학회지
• /
• 제21권2호
• /
• pp.129-133
• /
• 2006

Objectives : Cervus elaphus species are some of the most medicinally important genera in the Oriental medicine. This study was performed to determine if Cenvus elaphus species could be identified by sequencing analysis and to verify Basic Local Alignment Search Tool (BLAST) search, which was used to assess genetic identification. Methods : The DNAs of Cervus elaphus species were extracted, amplified by PCR, and sequenced. The DNAs of Cervus species were identified by BLAST search in website. Results : By BLAST search one of Cervus elaphus species was identified as Cervus elaphussibericus but the other was identified as Cervus elaphus nelsoni. This work showed that identification can efficiently be performed by BLAST search. Conclusion : These results suggest that sequencing following BLAST search might be able to provide the identification of Cervus elaphus species.

• Asian-Australasian Journal of Animal Sciences
• /
• 제20권12호
• /
• pp.1887-1894
• /
• 2007

In this paper, a rapid and reliable gene-targeted species-specific polymerase chain reaction (PCR) technique based on a two-step process was established to identify bifidobacteria in dairy products. The first step was the PCR assay for genus Bifidobacterium with genus specific primers followed by the second step, which identified the species level with species-specific primer mixtures. Ten specific primer pairs, designed from nucleotide sequences of the 16-23S rRNA region, were developed for the Bifidobacterium species including B. angulatum, B. animalis, B. bifidum, B. breve, B. catenulatum, B. infantis, B. longum, B. minimum, B. subtile, and B. thermophilum. This technique was applied to the identification of Bifidobacterium species isolated from 6 probiotic products, and four different Bifidobacterium spp. (B. bifidum, B. longum, B. infantis, and B. breve) were identified. The findings indicated that the 16S-23S rDNA gene-targeted species-specific PCR technique is a simple and reliable method for identification of bifidobacteria in probiotic products. PCR combined with Denaturing Gradient Gel Electrophoresis (DGGE) for identification of the bifidobacteria was also evaluated and compared with the gene-targeted species-specific technique. Results indicated that for fermented milk products consistency was found for both species-specific PCR and PCR-DGGE in detecting species. However, in some lyophilized products, the bands corresponding to these species were not visualized in the DGGE profile but the specific PCR gave a positive result.

• 한국수산과학회지
• /
• 제36권5호
• /
• pp.541-548
• /
• 2003

Species identification in hydroacoustic survey is one of the key requirements to estimate biomass of organism and to understand the structure of zooplankton community. Feasibility of species identification using two frequencies (38 and 120 kHz) was investigated on the basis of mean volume backscattering strength difference (MVBS). Virtual echogram technique was applied to two frequencies data sets that obtained from surveys in the Antarctic Ocean and Yellow Sea. Virtual echogram method using MVBS revealed the possibility of species identification, which species identification relying on visual scrutiny of single frequency acoustic data resulted in significant errors in biomass estimation. Through noise cancellation using MVBS, much of the acoustic noise caused by acoustic instruments could be removed in new virtual echogram, and the biomass estimation and data quality was improved.

• Journal of Microbiology and Biotechnology
• /
• 제29권6호
• /
• pp.887-896
• /
• 2019

Matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS)-based pathogen identification relies on the ribosomal protein spectra provided in the proprietary database. Although these mass spectra can discern various pathogens at species level, the spectra-based method still has limitations in identifying closely-related microbial species. In this study, to overcome the limits of the current MALDI-TOF MS identification method using ribosomal protein spectra, we applied MALDI-TOF MS of low-mass profiling to the identification of two genetically related Bacillus species, the food-borne pathogen Bacillus cereus, and the insect pathogen Bacillus thuringiensis. The mass spectra of small molecules from 17 type strains of two bacilli were compared to the morphological, biochemical, and genetic identification methods of pathogens. The specific mass peaks in the low-mass range (m/z 500-3,000) successfully identified various closely-related strains belonging to these two reference species. The intensity profiles of the MALDI-TOF mass spectra clearly revealed the differences between the two genetically-related species at strain level. We suggest that small molecules with low molecular weight, 714.2 and 906.5 m/z can be potential mass biomarkers used for reliable identification of B. cereus and B. thuringiensis.

• ALGAE
• /
• 제38권1호
• /
• pp.23-38
• /
• 2023

Accurately identifying species is the basis of all biological studies. There has been much confusion in the identification of Grateloupiacean species, which have finely pinnate gross morphology similar to Grateloupia filicina (the type species of the family). The objective of this study was to comprehensively investigate species identification and distribution of G. filicina-like species in the Northwest Pacific, based on the rbcL sequences. A total of 118 specimens from 78 sites in Korea and Japan were collected from 2001 to 2021 and analyzed for their rbcL sequences. Additional 341 sequences downloaded from the GenBank were included in our comprehensive dataset. Based on these sequences, we documented the nomenclatural history and geographical distribution of the species, and commented on the application of species name. G. asiatica was the most abundant G. filicina-like species in the Northwest Pacific, and its high degree of morphological variation caused many misidentifications. In particular, G. dalianensis, G. serra, and G. variata require reconsideration of their conspecificity with G. asiatica using more specimens from China. By contrast, G. oligoclora was presumed to be a heterotypic synonym of G. subpectinata. The occurrence of G. acuminata, G. ramosissima, and G. livida in Korea resulted from misidentifications with other species.

• 한국수산과학회지
• /
• 제49권2호
• /
• pp.224-233
• /
• 2016

The objective of this study was to develop an artificial neural network (ANN) model for the acoustic identification of commercially important fish species in Korea. A broadband echo acquisition and processing system operating over the frequency range of 85-225 kHz was used to collect and process species-specific, time-frequency feature images from six fish species: black rockfish Sebastes schlegeli, black scraper Thamnaconus modesutus [K], chub mackerel Scomber japonicus, goldeye rockfish Sebastes thompsoni, konoshiro gizzard shad Konosirus punctatus and large yellow croaker Larimichthys crocea. An ANN classifier was developed to identify fish species acoustically on the basis of only 100 dimension time-frequency features extracted by the principal components analysis (PCA). The overall mean identification rate for the six fish species was 88.5%, with individual identification rates of 76.6% for black rockfish, 82.8% for black scraper, 93.8% for chub mackerel, 90.6% for goldeye rockfish, 96.9% for konoshiro gizzard shad and 90.6% for large yellow croaker, respectively. These results demonstrate that individual live fish in well-controlled environments can be identified accurately by the proposed ANN model.

• Fisheries and Aquatic Sciences
• /
• 제26권11호
• /
• pp.678-688
• /
• 2023

Flatfish are one of the largest families in the order Pleuronectiformes and are economically important edible marine fish species. However, they have similar morphological characteristics leading to challenges in classifying correctly, which may result in mislabeling and illegal sales, such as fraudulent labeling of processed food. Therefore, accurate identification is important to ensure the quality and safety of domestic markets in Korea. Species-specific primers were prepared from the mainly consumed eleven species of the order Pleuronectiformes. To rapidly identify the 11 flatfish species, a highly efficient, rapid, multiplex polymerase chain reaction (PCR) with species-specific primers was developed. Species-specific primer sets were designed for the mitochondrial DNA cytochrome c oxidase subunit I gene. Species-specific multiplex PCR (MSS-PCR) either specifically amplified a PCR product of a unique size or failed. This MSS-PCR analysis is easy to perform and yields reliable results in less time than the previous Sanger sequencing methods. This technique could be a powerful tool for the identification of the 11 species b the family Pleuronectidae and can contribute to the prevention of falsified labeling and protection of consumer rights.