Strawberry R-CNN: Recognition and counting model of strawberry based on improved faster R-CNN

Ecological Informatics, Год журнала: 2023, Номер 77, С. 102210 - 102210

Опубликована: Июль 12, 2023

Язык: Английский

---

A regularized constrained two-stream convolution augmented Transformer for aircraft engine remaining useful life prediction

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 133, С. 108161 - 108161

Опубликована: Март 11, 2024

Язык: Английский

---

WildARe-YOLO: A lightweight and efficient wild animal recognition model

Ecological Informatics, Год журнала: 2024, Номер 80, С. 102541 - 102541

Опубликована: Фев. 23, 2024

Язык: Английский

---

A novel approach for detecting deep fake videos using graph neural network

Journal Of Big Data, Год журнала: 2024, Номер 11(1)

Опубликована: Фев. 1, 2024

Abstract Deep fake technology has emerged as a double-edged sword in the digital world. While it holds potential for legitimate uses, can also be exploited to manipulate video content, causing severe social and security concerns. The research gap lies fact that traditional deep detection methods, such visual quality analysis or inconsistency detection, need help keep up with rapidly advancing used create fakes. That means there's more sophisticated techniques. This paper introduces an enhanced approach detecting videos using graph neural network (GNN). proposed method splits process into two phases: mini-batch convolution stream four-block CNN comprising Convolution, Batch Normalization, Activation function. final step is flattening operation, which essential connecting convolutional layers dense layer. fusion of these phases performed three different networks: FuNet-A (additive fusion), FuNet-M (element-wise multiplicative FuNet-C (concatenation fusion). further evaluates model on datasets, where achieved impressive training validation accuracy 99.3% after 30 epochs.

Язык: Английский

---

Deep learning-based chatbot by natural language processing for supportive risk management in river dredging projects

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 131, С. 107744 - 107744

Опубликована: Янв. 12, 2024

Язык: Английский

---

Physics-infused deep neural network for solution of non-associative Drucker–Prager elastoplastic constitutive model

Journal of the Mechanics and Physics of Solids, Год журнала: 2024, Номер 185, С. 105570 - 105570

Опубликована: Фев. 12, 2024

Язык: Английский

---

An optimal initialisation for robust model reference adaptive PI controller for grid-tied power systems under unbalanced grid conditions

Engineering Applications of Artificial Intelligence, Год журнала: 2023, Номер 124, С. 106589 - 106589

Опубликована: Июнь 16, 2023

Язык: Английский

---

Integrating artificial intelligence in cyber security for cyber-physical systems

Electronic Research Archive, Год журнала: 2023, Номер 31(4), С. 1876 - 1896

Опубликована: Янв. 1, 2023

<abstract><p>Due to the complexities of systems thinking and communication between independent Cyber-Physical Systems (CPSs) areas through accumulative expansion, several security threats are posed, such as deception channels for information sharing, hardware aspects virtual machines. CPSs have become increasingly complex, sophisticated, knowledgeable fully independent. Because their complex interactions heterogeneous objective components, subject significant disturbances from intended unintended events, making it extremely difficult scientists predict behavior. This paper proposes a framework Business based on Artificial Intelligence (CPBS-AI). It summarizes safety risks in distinct CPS levels, threat modeling scientific challenges they face building effective solutions. research provides thorough overview current state-of-the-art static capable adapting detection tracking approaches methodological limitations, namely, difficulty identifying runtime attacks caused by hibernation or uncertainty. The way networks reduce CPS. negligible exhibit an inability be identified, avoided blocked Intrusion Prevention Security (IPSSs), misbehavior database measures is analyzed. Neural Networks (NN) Variable Structure Control (VSC) designed estimate prevent risk applications using nonlinear monitoring system VSC. NN VSC evaluate different system. evaluation proposed CPBS-AI request time analysis, accuracy, loss reliability analysis. overall effectiveness about 96.01%.</p></abstract>

Язык: Английский

---

Method of recognizing sleep postures based on air pressure sensor and convolutional neural network: For an air spring mattress

Engineering Applications of Artificial Intelligence, Год журнала: 2023, Номер 121, С. 106009 - 106009

Опубликована: Фев. 26, 2023

Язык: Английский

---

A multiple conditions dual inputs attention network remaining useful life prediction method

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 133, С. 108160 - 108160

Опубликована: Фев. 29, 2024

Язык: Английский

---