Predicting multiple types of traffic accident severity with explanations: A multi-task deep learning framework

Z Yang, W Zhang, J Feng - Safety science, 2022 - Elsevier
Predicting traffic accident severity is essential for traffic accident prevention and vulnerable
road user safety. Furthermore, the explainability of the prediction is crucial for practitioners to …

Artificial intelligence based grid connected inverters for power quality improvement in smart grid applications

SR Das, PK Ray, AK Sahoo, KK Singh… - Computers & Electrical …, 2021 - Elsevier
Abstract The Smart Grid (SG) is treated as the next level of modern power system which
uses the bilateral flow of power and information. The ability of the smart grid for two-way …

Integrating multi-criteria decision-making with hybrid deep learning for sentiment analysis in recommender systems

S Angamuthu, P Trojovský - PeerJ Computer Science, 2023 - peerj.com
Expert assessments with pre-defined numerical or language terms can limit the scope of
decision-making models. We propose that decision-making models can incorporate expert …

An improved dense-to-sparse cross-modal fusion network for 3D object detection in RGB-D images

Y Chen, J Ni, G Tang, W Cao, SX Yang - Multimedia Tools and …, 2024 - Springer
Abstract 3D object detection has received extensive attention from researchers. RGB-D
sensors are often used for the information complementary in 3D object detection tasks due …

Deep learning-based vehicle trajectory prediction based on generative adversarial network for autonomous driving applications

CC Hsu, LW Kang, SY Chen, IS Wang… - Multimedia Tools and …, 2023 - Springer
Autonomous vehicles need to continuously navigate complex traffic environments by
efficiently analyzing the surrounding scene, understanding the behavior of other traffic …

Artificial intelligence interactive design system based on digital multimedia technology

C Liu - Advances in Multimedia, 2022 - Wiley Online Library
The current extraction speed of artificial intelligence interactive elements is low, with the low
effect, resulting in the poor effect of artificial intelligence interaction. Therefore, a new …

Construction and research of constructive English teaching model applying multimodal neural network algorithm

N Zhang, H Wang - Computational Intelligence and …, 2022 - Wiley Online Library
This article draws on previous research on constructive English teaching models and uses
multimodal neural network algorithm theory and constructive English teaching as the …

An Enhanced Detection Method of PCB Defect Based on D-DenseNet (PCBDD-DDNet)

H Kang, Y Yang - Electronics, 2023 - mdpi.com
Printed Circuit Boards (PCBs), as integral components of electronic products, play a crucial
role in modern industrial production. However, due to the precision and complexity of PCBs …

Enhancing Class Monitoring Through Video Analytics and Deep Learning Models

R Kushwaha, H Rawat, S Bando… - 2023 International …, 2023 - ieeexplore.ieee.org
This research paper introduces an innovative solution for enhancing class monitoring by
integrating video analytics and advanced deep-learning models for human activity …

[PDF][PDF] A Novel Hybrid Deep Multi-Criteria Model for Recommender System

NS Nassar - 2021 - academia.edu
Recommender systems are everywhere books, products, movies, and more. Traditional
recommender systems typically use a single criterion in the recommendation, while studies …