Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Mitochondrial respiratory capacity in kidney podocytes is high, age-dependent, and sexually dimorphic.

Kidney international·2026

Same author

FlashLightNet: An End-to-End Deep Learning Framework for Real-Time Detection and Classification of Static and Flashing Traffic Light States.

Sensors (Basel, Switzerland)·2025

Same author

YOLOv8-TF: Transformer-Enhanced YOLOv8 for Underwater Fish Species Recognition with Class Imbalance Handling.

Sensors (Basel, Switzerland)·2025

Same author

A Pilot Trial of Nicotinamide Riboside and Coenzyme Q10 on Inflammation and Oxidative Stress in CKD.

Clinical journal of the American Society of Nephrology : CJASN·2025

Same author

Mitochondrial respiratory capacity in kidney podocytes is high, age-dependent, and sexually dimorphic.

bioRxiv : the preprint server for biology·2024

Same author

Randomized Crossover Clinical Trial of Nicotinamide Riboside and Coenzyme Q10 on Metabolic Health and Mitochondrial Bioenergetics in CKD.

medRxiv : the preprint server for health sciences·2024

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 22, 2025

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

Class-Aware Fish Species Recognition Using Deep Learning for an Imbalanced Dataset.

Simegnew Yihunie Alaba¹, M M Nabi¹, Chiranjibi Shah²

¹Department of Electrical and Computer Engineering, James Worth Bagley College of Engineering, Mississippi State University, Starkville, MS 39762, USA.

Sensors (Basel, Switzerland)

|November 11, 2022

Summary

This summary is machine-generated.

Accurate fish species recognition is vital for ecosystem monitoring. A new class-aware loss function significantly improves object detection models, especially for imbalanced datasets, enhancing fish identification accuracy.

Keywords:

class-aware loss deep learning fish recognition imbalanced data object detection species classification

More Related Videos

The Three-Chamber Choice Behavioral Task using Zebrafish as a Model System

The Three-Chamber Choice Behavioral Task using Zebrafish as a Model System

Published on: April 14, 2021

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

Related Experiment Videos

Last Updated: Aug 22, 2025

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

The Three-Chamber Choice Behavioral Task using Zebrafish as a Model System

The Three-Chamber Choice Behavioral Task using Zebrafish as a Model System

Published on: April 14, 2021

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

Area of Science:

Marine biology
Computer vision
Machine learning

Background:

Accurate fish species recognition is essential for ecological monitoring, biodiversity assessment, and fisheries management.
Traditional classification methods struggle with multiple fish in single images and imbalanced datasets.
Object detection offers a more robust approach for complex underwater imagery.

Purpose of the Study:

To develop an improved object detection model for accurate fish species recognition.
To address the challenge of class imbalance in fish species datasets.
To introduce a novel class-aware loss function applicable to imbalanced object detection tasks.

Main Methods:

Formulated fish species recognition as an object detection problem.
Utilized a model combining MobileNetv3-large and VGG16 backbones with an SSD detection head.
Proposed and implemented a class-aware loss function weighting underrepresented species more heavily.

Main Results:

The class-aware loss function improved model performance by up to 79.7% on the SEAMAPD21 reef fish dataset.
The proposed model demonstrated superior performance compared to the original SSD object detection model on the Pascal VOC dataset.
The class-aware loss function effectively mitigated the class imbalance problem.

Conclusions:

The developed object detection model with class-aware loss significantly enhances fish species recognition accuracy.
The class-aware loss function is a valuable tool for improving object detection on imbalanced datasets across various domains.
This approach advances capabilities in ecological monitoring and biodiversity studies through improved species identification.