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 Concept Videos

Survival Tree01:19

Survival Tree

504
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
504

You might also read

Related Articles

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

Sort by
Same author

Blueberry Bioactives as Adjunctive Nutritional Strategies for Pediatric Neurodevelopmental and Emotional-Behavioral Health: Mechanisms, Evidence, and Translational Challenges.

Nutrients·2026
Same author

Enhancing Conversion Reversibility and Initial Coulombic Efficiency of SnO<sub>2</sub> Anodes via NiO/Ni-Carbon Interfacial Design.

ACS applied materials & interfaces·2026
Same author

Bone tracer uptake in SPECT/CT is a potential indicator for treatment decision-making in cystic osteochondral lesions of the talus.

Bone & joint research·2026
Same author

Reconstructing the boundary of family involvement in shared decision-making: a confucian benevolence model for the Chinese context.

BMC medical ethics·2026
Same author

Carrier-Free Ce6&SR717 Nanomedicine Enables Abscopal Photoimmunotherapy via cGAS-STING Activation in Breast Cancer.

Molecular imaging·2026
Same author

Low-dose ultra-high-resolution temporal bone imaging using Sn100 kVp photon-counting CT: A comparative study with conventional CT.

European journal of radiology·2026

Related Experiment Video

Updated: Apr 20, 2026

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

12.5K

Software defect prediction based on residual/shuffle network optimized by upgraded fish migration optimization

Zhijing Liu1, Tong Su2, Michail A Zakharov3

  • 1Institute of Innovation and Entrepreneurship, Shandong Huayu University of Technology, Dezhou, 253034, Shandong, China. 18253487107@163.com.

Scientific Reports
|February 28, 2025
PubMed
Summary

This study introduces a novel AI method using Residual/Shuffle Networks and Fish Migration Optimization for accurate software defect prediction. The approach significantly enhances defect detection accuracy and reduces manual effort in software development.

Keywords:
Deep learningDefect predictionFeature generationResidual-shuffle networkSoftware defect predictionUpgraded fish migration optimization algorithm

More Related Videos

Using the FishSim Animation Toolchain to Investigate Fish Behavior: A Case Study on Mate-Choice Copying In Sailfin Mollies
10:50

Using the FishSim Animation Toolchain to Investigate Fish Behavior: A Case Study on Mate-Choice Copying In Sailfin Mollies

Published on: November 8, 2018

10.7K
Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT
08:04

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Published on: April 23, 2020

6.7K

Related Experiment Videos

Last Updated: Apr 20, 2026

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

12.5K
Using the FishSim Animation Toolchain to Investigate Fish Behavior: A Case Study on Mate-Choice Copying In Sailfin Mollies
10:50

Using the FishSim Animation Toolchain to Investigate Fish Behavior: A Case Study on Mate-Choice Copying In Sailfin Mollies

Published on: November 8, 2018

10.7K
Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT
08:04

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Published on: April 23, 2020

6.7K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Software Engineering

Background:

  • Software defects pose significant challenges, increasing development costs and impacting user satisfaction.
  • Existing defect prediction models often require substantial manual effort and may lack accuracy.
  • There is a need for advanced, automated methods to improve software quality.

Purpose of the Study:

  • To introduce a new, accurate method for predicting software defects.
  • To reduce the manual effort required in identifying software issues.
  • To leverage the synergy of deep learning and metaheuristics for code analysis.

Main Methods:

  • Utilized Residual/Shuffle (RS) Networks for deep learning-based code analysis.
  • Employed an enhanced Fish Migration Optimization (UFMO) algorithm for model training.
  • Extracted semantic and structural properties from software code.

Main Results:

  • Achieved an average accuracy of 93% on open-source projects.
  • Demonstrated superior performance compared to state-of-the-art models.
  • Reported significant improvements in precision (78-98%), recall (71-98%), F-measure (72-96%), and AUC (78-99%).

Conclusions:

  • The proposed model offers a simple, efficient, and effective solution for defect prediction.
  • This AI-driven approach can revolutionize software development by improving quality and reducing costs.
  • Further evaluation on proprietary software is recommended to broaden applicability.