A transportation Revitalization index prediction model based on Spatial-Temporal attention mechanism

Advanced Engineering Informatics, Год журнала: 2024, Номер 61, С. 102519 - 102519

Опубликована: Апрель 3, 2024

Язык: Английский

---

ZF-QDCNN: ZFNet and quantum dilated convolutional neural network based Alzheimer's disease detection using MRI images

Network Computation in Neural Systems, Год журнала: 2025, Номер unknown, С. 1 - 45

Опубликована: Фев. 11, 2025

Alzheimer's disease (AD) is a severe neurological disorder that leads to irreversible memory loss. In the previous research, early-stage often presents with subtle issues are difficult differentiate from normal age-related changes. This research designed novel detection model called Zeiler and Fergus Quantum Dilated Convolutional Neural Network (ZF-QDCNN) for AD using Magnetic Resonance Imaging (MRI). Initially, input MRI images taken specific dataset, which pre-processed Gaussian filter. Then, brain area segmentation performed by utilizing Channel-wise Feature Pyramid Medicine (CFPNet-M). After segmentation, relevant features extracted, classification of ZF-QDCNN, integration (ZFNet) (QDCNN). Moreover, ZF-QDCNN demonstrated promising performance, achieving an accuracy 91.7%, sensitivity 90.7%, specificity 92.7%, f-measure 91.8% in detecting AD. Additionally, proposed effectively identifies classifies images, highlighting its potential as valuable tool early diagnosis management condition.

Язык: Английский

---

Fuzzy ensemble-based federated learning for EEG-based emotion recognition in Internet of Medical Things

Journal of Industrial Information Integration, Год журнала: 2025, Номер unknown, С. 100789 - 100789

Опубликована: Фев. 1, 2025

Язык: Английский

---

A multi-modal sensing based terrain identification approach for active lower limb exoskeletons

Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 126862 - 126862

Опубликована: Фев. 1, 2025

Язык: Английский

---

An enhanced combined model for water quality prediction utilizing spatiotemporal features and physical-informed constraints

Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 126937 - 126937

Опубликована: Фев. 1, 2025

Язык: Английский

---

Predicting Reward-Based Crowdfunding Success with Multimodal Data: A Theory-Guided Framework

Information & Management, Год журнала: 2025, Номер unknown, С. 104131 - 104131

Опубликована: Март 1, 2025

Язык: Английский

---

Graph Convolutional Networks with Multi-Scale Dynamics for Traffic Speed Forecasting

Applied Soft Computing, Год журнала: 2025, Номер unknown, С. 112966 - 112966

Опубликована: Март 1, 2025

Язык: Английский

---

Audio Deepfake Detection Using Deep Learning

Engineering Reports, Год журнала: 2025, Номер 7(3)

Опубликована: Март 1, 2025

ABSTRACT This study introduces an enhanced Siamese convolutional neural network (Siamese CNN) architecture with a novel StacLoss function and self‐attention modules for efficient identification of audio deepfakes. Our module directly compares unprocessed original modified by initially applying operations dual branches to extract complex characteristics from raw signals. These are followed residual connections, which enhance the network's performance. The trained in layered way alongside these fundamental layers detect multi‐headed attention within frames. output represents customized version contrastive loss function. It aids distinguishing between audios minimizing pairs that have same identity while maximizing distance manipulated samples enhances process extracting features compared standard techniques. efficacy method has been verified examining range modifications, its resilience thoroughly assessed on ASVspoof2019 dataset comprehensive testing across all possible manipulation situations. proposed (CNN) outperformed both machine deep learning models, achieving impressive metrics. achieved remarkable accuracy 98%, precision 97%, recall 96%, F 1 score 96.5%, ROC‐AUC 99%, equal error rate (EER) 2.95%.

Язык: Английский

---

Discriminative Deformable Part Model for Pedestrian Detection with Occlusion Handling

AI, Год журнала: 2025, Номер 6(4), С. 70 - 70

Опубликована: Апрель 3, 2025

Efficient pedestrian detection plays an important role in many practical daily life applications, such as autonomous cars, video surveillance, and intelligent driving assistance systems. The main goal of systems, especially vehicles, is to prevent accidents. By recognizing pedestrians real time, these systems can alert drivers or even autonomously apply brakes, minimizing the possibility collisions. However, occlusion a major obstacle detection. Pedestrians are typically occluded by trees, street poles, other pedestrians. State-of-the-art methods based on fully visible little-occluded pedestrians; hence, their performance declines with increasing level. To meet this challenge, detector capable handling preferred. increase accuracy for pedestrians, we propose new method called Discriminative Deformable Part Model (DDPM), which uses concept breaking human image into deformable parts via machine learning. In existing works, has been performed intuition. our novel approach, learning used objects humans, combining benefits removing drawbacks previous works. We also dataset Eastern clothes accommodate detector’s evaluation under different intra-class variations proposed achieves higher Pascal VOC VisDrone Detection datasets when compared popular methods.

Язык: Английский

---

Fusion of KANO theory and Attention-BiLSTM models for user demand analysis and trend prediction

Information Fusion, Год журнала: 2025, Номер unknown, С. 103210 - 103210

Опубликована: Апрель 1, 2025

Язык: Английский

---