Jove
Visualize
Contact Us

Related Concept Videos

Methods of Classification and Identification01:28

Methods of Classification and Identification

248
Bacterial identification relies on a diverse array of techniques to classify and understand microorganisms, each tailored to uncover specific characteristics. Traditional morphological approaches, while still valuable, are limited for closely related or structurally simple organisms. Modern methods integrate biochemical, serological, genetic, and advanced molecular tools to achieve greater accuracy.Morphological and Biochemical TechniquesMorphological characteristics, such as cell shape and...
248

You might also read

Related Articles

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

Sort by
Same author

Enhancing skin lesion classification: a CNN approach with human baseline comparison.

PeerJ. Computer science·2025
Same author

Securing digital images: A chaos-driven scrambling algorithm using the Rössler system.

PloS one·2025
Same author

Obstacle Detection System for Navigation Assistance of Visually Impaired People Based on Deep Learning Techniques.

Sensors (Basel, Switzerland)·2023
Same author

A Framework for Susceptibility Analysis of Brain Tumours Based on Uncertain Analytical Cum Algorithmic Modeling.

Bioengineering (Basel, Switzerland)·2023
Same author

Event-Specific Transmission Forecasting of SARS-CoV-2 in a Mixed-Mode Ventilated Office Room Using an ANN.

International journal of environmental research and public health·2022
Same author

The Assessment of Medication Effects in Omicron Patients through MADM Approach Based on Distance Measures of Interval-Valued Fuzzy Hypersoft Set.

Bioengineering (Basel, Switzerland)·2022
Same journal

RETRACTION: Real-Time Modulation of Physical Training Intensity Based on Wavelet Recursive Fuzzy Neural Networks.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Multidimensional Heterogeneous Network Link Adaptation Based on Mobile Environment.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Framework to Segment and Evaluate Multiple Sclerosis Lesion in MRI Slices Using VGG-UNet.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Facial Emotion Recognition Using a Novel Fusion of Convolutional Neural Network and Local Binary Pattern in Crime Investigation.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Automatic Intelligent System Using Medical of Things for Multiple Sclerosis Detection.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Intangible Cultural Heritage Reproduction and Revitalization: Value Feedback, Practice, and Exploration Based on the IPA Model.

Computational intelligence and neuroscience·2026
See all related articles
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 Video

Updated: Sep 21, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

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

Published on: October 27, 2023

1.7K

A Modified ResNeXt for Android Malware Identification and Classification.

Marwan Ali Albahar1, Mahmoud Said ElSayed2, Anca Jurcut2

  • 1School of Computer Science, Umm Al-Qura University, Mecca, Saudi Arabia.

Computational Intelligence and Neuroscience
|May 31, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces an improved deep learning model designed to better detect and categorize harmful Android applications. By converting complex software features into visual images, the researchers trained a specialized neural network to automatically distinguish between safe and malicious files. This approach reduces the need for manual security analysis and improves the accuracy of identifying specific malware types. Testing on a standard dataset demonstrated that this method achieves high performance in classifying threats. The findings suggest that visual-based deep learning provides a robust alternative to traditional security screening techniques.

Keywords:
deep learningconvolutional neural networkthreat detectionmobile security

Frequently Asked Questions

More Related Videos

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

897
Identification and Classification of Position-specific GABAA Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons
08:04

Identification and Classification of Position-specific GABAA Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons

Published on: June 6, 2025

539

Related Experiment Videos

Last Updated: Sep 21, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

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

Published on: October 27, 2023

1.7K
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

897
Identification and Classification of Position-specific GABAA Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons
08:04

Identification and Classification of Position-specific GABAA Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons

Published on: June 6, 2025

539

Area of Science:

  • Cybersecurity and Android malware identification research within computer science
  • Deep learning architectures for automated threat detection systems

Background:

Security experts currently face challenges in effectively stopping the proliferation of malicious software targeting mobile platforms. Prior research has shown that traditional detection methods often struggle to keep pace with evolving digital threats. No prior work had resolved the difficulty of automatically categorizing diverse malware families without extensive manual intervention. That uncertainty drove the need for more efficient computational approaches to protect mobile ecosystems. It was already known that deep learning architectures could process complex data patterns for classification purposes. However, standard models frequently lack the precision required for identifying subtle variations in malicious code. This gap motivated the development of specialized frameworks tailored for high-stakes security environments. Researchers now seek to leverage advanced image processing to enhance the reliability of automated threat identification.

Purpose Of The Study:

The aim of this study is to improve the classification and identification of dangerous mobile applications. Android malware poses a significant threat to the security of modern software ecosystems. Identifying malicious trends systematically remains a challenge for current detection systems. The researchers sought to enhance the efficiency of the malware detection process through advanced computational modeling. They proposed a modified ResNeXt model to address the limitations of existing classification techniques. This work focuses on embedding a new regularization method to optimize the performance of the neural network. The authors also aimed to reduce the reliance on manual feature engineering by using automated deep learning approaches. This study addresses the need for more precise options in the fight against mobile security assaults.

Main Methods:

Review approach involved developing a modified neural network architecture to improve software classification performance. The researchers embedded a new regularization technique into the model to refine the learning process. They converted nonintuitive software features into fingerprint images to facilitate automated data analysis. This design utilized a convolutional neural network to process the visualized samples directly. The team tested fifteen different combinations of image sections to ensure comprehensive evaluation. They relied on the Drebin dataset to provide a standardized benchmark for their experiments. The approach prioritized the automation of feature extraction to bypass manual engineering requirements. Finally, the authors compared their results against several existing methods to establish the efficacy of their proposed framework.

Main Results:

Key findings from the literature indicate that the modified model achieved an accuracy of 98.25% using Android certificates. The researchers observed that their approach successfully separated normal data from malicious samples with high precision. Extensive trials on the Drebin dataset confirmed the effectiveness of the proposed methodology across various configurations. The study revealed that visual-based deep learning eliminates the frequent need for manual feature engineering. Comparisons showed that the new model outperformed several existing detection methods in classification tasks. The experimental results highlight the utility of grayscale images for analyzing complex software samples. The authors demonstrated that their regularization technique significantly improves the classification task. These results provide a robust foundation for automated threat identification within mobile ecosystems.

Conclusions:

The authors propose that their modified architecture offers a more precise option for identifying malicious mobile software. Synthesis and implications suggest that visual-based classification significantly improves the efficiency of current security workflows. The researchers demonstrate that their approach outperforms several existing methods when tested on standard datasets. Their findings indicate that converting software features into images allows for robust automated feature extraction. This study implies that deep learning models can successfully replace labor-intensive manual engineering tasks. The authors conclude that their specific regularization technique enhances the overall performance of the classification task. They suggest that high accuracy rates confirm the efficacy of using grayscale images for threat analysis. Future security systems may benefit from integrating these automated visual identification frameworks to better protect users.

The researchers propose a modified ResNeXt model that incorporates a novel regularization technique. This architecture converts complex software attributes into grayscale fingerprint images, allowing a convolutional neural network to automatically extract discriminatory patterns that separate benign applications from malicious ones.

The study utilizes the Drebin dataset to evaluate the performance of the proposed model. This collection contains various Android malware samples, which the researchers processed into fifteen distinct image combinations to test the robustness of their classification framework.

A convolutional neural network is necessary to automatically learn features from visualized data. This approach avoids the high costs associated with domain experts and eliminates the need for manual feature engineering, which is often required in traditional security analysis methods.

The researchers employ grayscale images to represent the nonintuitive features of Android software. This visual data type serves as the primary input for the neural network, enabling the system to identify malicious trends without relying on raw code analysis.

The modified model achieved an accuracy of 98.25% using Android certificates. This performance metric demonstrates the effectiveness of the proposed architecture when compared against several existing methods for malware detection.

The authors claim that their methodology provides a more precise alternative for malware identification. They suggest that this approach improves the efficiency of the detection process compared to traditional techniques that rely on frequent manual engineering.