Deep Learning-Based Classification of Macrofungi: Comparative Analysis of Advanced Models for Accurate Fungi Identification

被引:1
|
作者
Ozsari, Sifa [1 ]
Kumru, Eda [2 ]
Ekinci, Fatih [3 ]
Akata, Ilgaz [4 ]
Guzel, Mehmet Serdar [1 ]
Acici, Koray [5 ]
Ozcan, Eray [1 ]
Asuroglu, Tunc [6 ,7 ]
机构
[1] Ankara Univ, Fac Engn, Dept Comp Engn, TR-06830 Ankara, Turkiye
[2] Ankara Univ, Grad Sch Nat & Appl Sci, TR-06830 Ankara, Turkiye
[3] Ankara Univ, Inst Nucl Sci, Dept Med Phys, TR-06100 Ankara, Turkiye
[4] Ankara Univ, Fac Sci, Dept Biol, TR-06100 Ankara, Turkiye
[5] Ankara Univ, Fac Engn, Dept Artificial Intelligence & Data Engn, TR-06830 Ankara, Turkiye
[6] Tampere Univ, Fac Med & Hlth Technol, Tampere 33720, Finland
[7] VTT Tech Res Ctr Finland, Tampere 33101, Finland
关键词
macrofungi classification; deep learning; DenseNet121; fungi identification; machine learning models; MUSHROOMS;
D O I
10.3390/s24227189
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
This study focuses on the classification of six different macrofungi species using advanced deep learning techniques. Fungi species, such as Amanita pantherina, Boletus edulis, Cantharellus cibarius, Lactarius deliciosus, Pleurotus ostreatus and Tricholoma terreum were chosen based on their ecological importance and distinct morphological characteristics. The research employed 5 different machine learning techniques and 12 deep learning models, including DenseNet121, MobileNetV2, ConvNeXt, EfficientNet, and swin transformers, to evaluate their performance in identifying fungi from images. The DenseNet121 model demonstrated the highest accuracy (92%) and AUC score (95%), making it the most effective in distinguishing between species. The study also revealed that transformer-based models, particularly the swin transformer, were less effective, suggesting room for improvement in their application to this task. Further advancements in macrofungi classification could be achieved by expanding datasets, incorporating additional data types such as biochemical, electron microscopy, and RNA/DNA sequences, and using ensemble methods to enhance model performance. The findings contribute valuable insights into both the use of deep learning for biodiversity research and the ecological conservation of macrofungi species.
引用
收藏
页数:22
相关论文
共 50 条
  • [1] Improving Rock Type Identification Through Advanced Deep Learning-Based Segmentation Models: A Comparative Study
    Aydin, Ilhan
    Kilic, Ayse Didem
    Sener, Taha Kubilay
    APPLIED SCIENCES-BASEL, 2025, 15 (03):
  • [2] Comparative Study of Deep Learning-Based Sentiment Classification
    Seo, Seungwan
    Kim, Czangyeob
    Kim, Haedong
    Mo, Kyounghyun
    Kang, Pilsung
    IEEE ACCESS, 2020, 8 (08): : 6861 - 6875
  • [3] Deep Learning-Based Sentiment Classification: A Comparative Survey
    Mabrouk, Alhassan
    Diaz Redondo, Rebeca P.
    Kayed, Mohammed
    IEEE ACCESS, 2020, 8 : 85616 - 85638
  • [4] Deep learning-based classification models for beehive monitoring
    Berkaya, Selcan Kaplan
    Gunal, Efnan Sora
    Gunal, Serkan
    ECOLOGICAL INFORMATICS, 2021, 64
  • [5] A Comparative Text Classification Study with Deep Learning-Based Algorithms
    Koksal, Omer
    Akgul, Ozlem
    2022 9TH INTERNATIONAL CONFERENCE ON ELECTRICAL AND ELECTRONICS ENGINEERING (ICEEE 2022), 2022, : 387 - 391
  • [6] Comparative analysis of deep learning-based pansharpening methods for improved image classification accuracy
    Yilmaz, Volkan
    Asikoglu, Deryanur
    JOURNAL OF APPLIED REMOTE SENSING, 2023, 17 (03)
  • [7] Transfer learning-based quantized deep learning models for nail melanoma classification
    Mujahid Hussain
    Makhmoor Fiza
    Aiman Khalil
    Asad Ali Siyal
    Fayaz Ali Dharejo
    Waheeduddin Hyder
    Antonella Guzzo
    Moez Krichen
    Giancarlo Fortino
    Neural Computing and Applications, 2023, 35 : 22163 - 22178
  • [8] Finetuned Deep Learning Models for Fuel Classification: A Transfer Learning-Based Approach
    Shanmugam, Hemachandiran
    Gnanasekaran, Aghila
    ENERGIES, 2025, 18 (05)
  • [9] Transfer learning-based quantized deep learning models for nail melanoma classification
    Hussain, Mujahid
    Fiza, Makhmoor
    Khalil, Aiman
    Siyal, Asad Ali
    Dharejo, Fayaz Ali
    Hyder, Waheeduddin
    Guzzo, Antonella
    Krichen, Moez
    Fortino, Giancarlo
    NEURAL COMPUTING & APPLICATIONS, 2023, 35 (30): : 22163 - 22178
  • [10] Comparative Analysis of Deep Learning Models for Myanmar Text Classification
    Phyu, Myat Sapal
    Nwet, Khin Thandar
    INTELLIGENT INFORMATION AND DATABASE SYSTEMS (ACIIDS 2020), PT I, 2020, 12033 : 76 - 85