Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A lightweight explainable deep learning framework for coal classification.

Avijit Paul1, Farjahan Akter Boby2, Yamina Islam3

  • 1Department of Electronics & Telecommunication Engineering, Rajshahi University of Engineering & Technology, Rajshahi, Bangladesh.

Scientific Reports
|July 13, 2026
PubMed
Summary

Related Concept Videos

Aggregates Classification01:29

Aggregates Classification

Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
Classification of Systems-I01:26

Classification of Systems-I

Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

5-ALA in Oncology: Current Clinical Applications, Biological Limitations, and Emerging Translational Strategies.

Biomedicines·2026
Same author

Atherosclerotic Plaque Characterization Magnetic Resonance Imaging In Vitro at 1.5 Tesla for the Assessment of Coronary Artery Disease.

Journal of clinical medicine·2026
Same author

Deep Learning and Cardiovascular Diseases: An Updated Narrative Review.

Journal of clinical medicine·2026
Same author

Advanced security in fog environments using encryption and adaptive user activity tracking.

Scientific reports·2026
Same author

Empowering photodynamic therapy with artificial intelligence: current trends and future directions.

Frontiers in oncology·2026
Same author

Glycinebetaine Improves Photosynthetic Performance and Antioxidant Defense in Barley Under Water Deficit Conditions.

Biomolecules·2026

A new lightweight convolutional neural network offers accurate and efficient coal classification, outperforming traditional methods. This AI model uses advanced deep learning techniques for improved resource management and environmental compliance in mining.

Area of Science:

  • Computer Science, Artificial Intelligence, Machine Learning, Deep Learning
  • Materials Science, Mineral Processing, Coal Science

Background:

  • Traditional coal classification methods (visual inspection, lab analysis) are slow, subjective, and difficult to scale for industrial needs.
  • Accurate coal classification is crucial for optimizing energy production, resource utilization, and environmental compliance.

Purpose of the Study:

  • To develop a custom, task-adaptive, lightweight convolutional neural network (CNN) for high-performance coal classification.
  • To achieve high classification accuracy with significantly reduced computational overhead compared to existing models.

Main Methods:

  • Proposed a novel CNN architecture integrating Separable Convolutional Blocks, Inverted Residual Blocks, and Squeeze and Excitation mechanisms.
  • Trained and evaluated the model on the large-scale DsCGF dataset (>270,000 images) under diverse real-world conditions.
Keywords:
Coal classificationDeep learningDsCGF datasetExplainable AIGrad-CAMGrad-CAM++Inverted residual blockLightweight CNNScore-CAMSeparable convolutionSqueeze and excitation

Related Experiment Videos

  • Employed explainable AI techniques (Grad-CAM, Grad-CAM++, Score-CAM) for model interpretability and visualization.

    • Main Results:

    • Achieved high classification accuracies: 93.73% (Anhui Guobei production), 99.97% (Anhui Guobei non-production), 99.26% (Inner Mongolia Erlintu production), and 90.50% (Shanxi Wangjialing production).
    • Model utilizes only 1.72 million parameters with an average inference time of 0.023s per image, demonstrating low computational complexity.
    • Outperformed or matched established transfer learning models (MobileNetV2, DenseNet201, Xception) in accuracy, precision, recall, and F1 score.

    Conclusions:

    • The proposed lightweight CNN provides a practical, interpretable, and resource-efficient solution for automated coal classification.
    • This AI-driven approach significantly advances intelligent mining systems by enabling accurate and rapid material identification.
    • The model's efficiency and interpretability make it suitable for real-world industrial applications requiring robust coal sorting.