A Scalable and Generalised Deep Learning Framework for Anomaly Detection in Surveillance Videos DOI Creative Commons
Sabah Abdulazeez Jebur, Laith Alzubaidi, Ahmed Saihood

et al.

International Journal of Intelligent Systems, Journal Year: 2025, Volume and Issue: 2025(1)

Published: Jan. 1, 2025

Anomaly detection in videos is challenging due to the complexity, noise, and diverse nature of activities such as violence, shoplifting, vandalism. While deep learning (DL) has shown excellent performance this area, existing approaches have struggled apply DL models across different anomaly tasks without extensive retraining. This repeated retraining time‐consuming, computationally intensive, unfair. To address limitation, a new framework introduced study, consisting three key components: transfer enhance feature generalization, model fusion improve representation, multitask classification generalize classifier multiple training from scratch when task introduced. The framework’s main advantage its ability requiring for each task. Empirical evaluations demonstrate effectiveness, achieving an accuracy 97.99% on RLVS (violence detection), 83.59% UCF dataset (shoplifting 88.37% both datasets using single Additionally, tested unseen dataset, achieved 87.25% 79.39% violence shoplifting datasets, respectively. study also utilises two explainability tools identify potential biases, ensuring robustness fairness. research represents first successful resolution generalization issue detection, marking significant advancement field.

Language: Английский

Deep learning in food category recognition DOI Creative Commons
Yudong Zhang, Lijia Deng, Hengde Zhu

et al.

Information Fusion, Journal Year: 2023, Volume and Issue: 98, P. 101859 - 101859

Published: May 27, 2023

Integrating artificial intelligence with food category recognition has been a field of interest for research the past few decades. It is potentially one next steps in revolutionizing human interaction food. The modern advent big data and development data-oriented fields like deep learning have provided advancements recognition. With increasing computational power ever-larger datasets, approach's potential yet to be realized. This survey provides an overview methods that can applied various tasks, including detecting type, ingredients, quality, quantity. We core components constructing machine system recognition, augmentation, hand-crafted feature extraction, algorithms. place particular focus on learning, utilization convolutional neural networks, transfer semi-supervised learning. provide relevant studies promote further developments industrial applications.

Language: Английский

Citations

244
Explainable artificial intelligence approaches for COVID-19 prognosis prediction using clinical markers DOI Creative Commons
Krishnaraj Chadaga, Srikanth Prabhu, Niranjana Sampathila

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Jan. 20, 2024

Language: Английский

Citations

29
A novel fusion framework of deep bottleneck residual convolutional neural network for breast cancer classification from mammogram images DOI Creative Commons

Kiran Jabeen,

Muhammad Attique Khan, Mohamed Abdel Hameed

et al.

Frontiers in Oncology, Journal Year: 2024, Volume and Issue: 14

Published: Feb. 22, 2024

With over 2.1 million new cases of breast cancer diagnosed annually, the incidence and mortality rate this disease pose severe global health issues for women. Identifying disease’s influence is only practical way to lessen it immediately. Numerous research works have developed automated methods using different medical imaging identify BC. Still, precision each strategy differs based on available resources, issue’s nature, dataset being used. We proposed a novel deep bottleneck convolutional neural network with quantum optimization algorithm classification diagnosis from mammogram images. Two architectures named three-residual blocks four-residual bottle been parallel single paths. Bayesian Optimization (BO) has employed initialize hyperparameter values train selected dataset. Deep features are extracted average pool layer both models. After that, kernel-based canonical correlation analysis entropy technique fusion. The fused feature set further refined an generalized normal distribution optimization. finally classified several classifiers, such as bi-layered wide-neural networks. experimental process was conducted publicly INbreast, maximum accuracy 96.5% obtained. Moreover, method, sensitivity 96.45, 96.5, F1 score value 96.64, MCC 92.97%, Kappa respectively. utilized infected regions. In addition, detailed comparison few recent techniques showing framework’s higher rate.

Language: Английский

Citations

22
Identification of kidney stones in KUB X-ray images using VGG16 empowered with explainable artificial intelligence DOI Creative Commons
Fahad Ahmed, Sagheer Abbas, Atifa Athar

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: March 14, 2024

Abstract A kidney stone is a solid formation that can lead to failure, severe pain, and reduced quality of life from urinary system blockages. While medical experts interpret kidney-ureter-bladder (KUB) X-ray images, specific images pose challenges for human detection, requiring significant analysis time. Consequently, developing detection becomes crucial accurately classifying KUB images. This article applies transfer learning (TL) model with pre-trained VGG16 empowered explainable artificial intelligence (XAI) establish takes categorizes them as stones or normal cases. The findings demonstrate the achieves testing accuracy 97.41% in identifying X-rays dataset used. delivers highly accurate predictions but lacks fairness explainability their decision-making process. study incorporates Layer-Wise Relevance Propagation (LRP) technique, an enhance transparency effectiveness address this concern. XAI specifically LRP, increases model's transparency, facilitating comprehension predictions. play important role assisting doctors identification stones, thereby execution effective treatment strategies.

Language: Английский

Citations

13
Chest X-ray Images for Lung Disease Detection Using Deep Learning Techniques: A Comprehensive Survey DOI
Mohammed A. A. Al‐qaness,

Jie Zhu,

Dalal AL-Alimi

et al.

Archives of Computational Methods in Engineering, Journal Year: 2024, Volume and Issue: 31(6), P. 3267 - 3301

Published: Feb. 19, 2024

Language: Английский

Citations

10
MFFSP: Multi-scale feature fusion scene parsing network for landslides detection based on high-resolution satellite images DOI
Penglei Li, Yi Wang, Tongzhen Si

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 127, P. 107337 - 107337

Published: Oct. 27, 2023

Language: Английский

Citations

22
Detection of various lung diseases including COVID-19 using extreme learning machine algorithm based on the features extracted from a lightweight CNN architecture DOI Creative Commons
Md. Nahiduzzaman, Md. Omaer Faruq Goni,

Md. Robiul Islam

et al.

Journal of Applied Biomedicine, Journal Year: 2023, Volume and Issue: 43(3), P. 528 - 550

Published: June 26, 2023

Around the world, several lung diseases such as pneumonia, cardiomegaly, and tuberculosis (TB) contribute to severe illness, hospitalization or even death, particularly for elderly medically vulnerable patients. In last few decades, new types of lung-related have taken lives millions people, COVID-19 has almost 6.27 million lives. To fight against diseases, timely correct diagnosis with appropriate treatment is crucial in current pandemic. this study, an intelligent recognition system seven been proposed based on machine learning (ML) techniques aid medical experts. Chest X-ray (CXR) images were collected from publicly available databases. A lightweight convolutional neural network (CNN) used extract characteristic features raw pixel values CXR images. The best feature subset identified using Pearson Correlation Coefficient (PCC). Finally, extreme (ELM) perform classification task assist faster reduced computational complexity. CNN-PCC-ELM model achieved accuracy 96.22% Area Under Curve (AUC) 99.48% eight class classification. outcomes demonstrated better performance than existing state-of-the-art (SOTA) models case COVID-19, detection both binary multiclass classifications. For classification, precision, recall fi-score ROC are 100%, 99%, 100% 99.99% respectively demonstrating its robustness. Therefore, overshadowed pioneering accurately differentiate other that can physicians treating patient effectively.

Language: Английский

Citations

19
CNN-based Approach for Enhancing Brain Tumor Image Classification Accuracy DOI Open Access
Abdul Muis,

Sunardi Sunardi,

Anton Yudhana

et al.

International journal of engineering. Transactions B: Applications, Journal Year: 2024, Volume and Issue: 37(5), P. 984 - 996

Published: Jan. 1, 2024

Brain tumors are one of the deadliest diseases in world. This disease can attack anyone regardless gender or certain age groups. The diagnosis brain is carried out by manually identifying images resulting from Computerized Tomography Scan Magnetic Resonance Imaging, making it possible for diagnostic errors to occur. In addition, be made using biopsy techniques. technique very accurate but takes a long time, around 10 15 days and involves lot equipment medical personnel. Based on this, machine learning technology needed which classify based produced MRI. research aims increase accuracy previous classification so that do not occur tumors. method used this Convolutional Neural Network AlexNet Google Net architectures. results obtained an 98% architecture 96% GoogleNet. result higher when compared with research. finding reduce computational burden during model training. help physicians diagnose quickly accurately.

Language: Английский

Citations

7
Optimization of vision transformer-based detection of lung diseases from chest X-ray images DOI Creative Commons

Jinsol Ko,

S.Y. Park, Hyun Goo Woo

et al.

BMC Medical Informatics and Decision Making, Journal Year: 2024, Volume and Issue: 24(1)

Published: July 8, 2024

Abstract Background Recent advances in Vision Transformer (ViT)-based deep learning have significantly improved the accuracy of lung disease prediction from chest X-ray images. However, limited research exists on comparing effectiveness different optimizers for within ViT models. This study aims to systematically evaluate and compare performance various optimization methods ViT-based models predicting diseases Methods utilized a image dataset comprising 19,003 images containing both normal cases six diseases: COVID-19, Viral Pneumonia, Bacterial Middle East Respiratory Syndrome (MERS), Severe Acute (SARS), Tuberculosis. Each model (ViT, FastViT, CrossViT) was individually trained with each method (Adam, AdamW, NAdam, RAdam, SGDW, Momentum) assess their prediction. Results When tested balanced-sample sized classes, RAdam demonstrated superior compared other optimizers, achieving 95.87%. In imbalanced sample size, FastViT NAdam achieved best an 97.63%. Conclusions We provide comprehensive strategies developing architectures, which can enhance these

Language: Английский

Citations

6
The effectiveness of deep learning vs. traditional methods for lung disease diagnosis using chest X-ray images: A systematic review DOI

Samira Sajed,

Amir Sanati,

Jorge Esparteiro Garcia

et al.

Applied Soft Computing, Journal Year: 2023, Volume and Issue: 147, P. 110817 - 110817

Published: Sept. 9, 2023

Language: Английский

Citations

15