Article
Computer Science, Artificial Intelligence
Minghu Tan, Hong Shen, Kang Xi, Bin Chai
Summary: This paper investigates typical maneuvers of flying vehicles and introduces corresponding trajectory equations based on the kinematics model. Multiple accurate prediction methods for flying vehicle trajectory are proposed through neural network training and simulation verification.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Luca Rossi, Marina Paolanti, Roberto Pierdicca, Emanuele Frontoni
Summary: Human trajectory prediction is a complex subject that involves challenges such as human-space interaction, human-human interaction, multimodality, and generalizability. This study proposes new deep learning models and datasets to address these challenges and achieve better generalizability in predicting human trajectories. Experimental results demonstrate that the proposed models and datasets outperform state-of-the-art works and better capture the complexities of multimodal scenarios.
PATTERN RECOGNITION
(2021)
Article
Engineering, Geological
Shui-Long Shen, Khalid Elbaz, Wafaa Mohamed Shaban, Annan Zhou
Summary: This paper presents a novel deep learning model, WT-Adam-LSTM, for real-time prediction of shield moving trajectory during tunnelling. The model combines wavelet transform and Adam-optimised LSTM to remove noise and extract sequence patterns. It considers various factors such as shield performance database, complex geological conditions, soil geometry, and operational parameters. A case study was conducted to verify its performance and it outperformed other models like recurrent neural network, LSTM, and support vector regression.
Article
Computer Science, Artificial Intelligence
Wanjie Sun, Zhenzhong Chen, Feng Wu
Summary: A deep learning model is proposed in this paper to predict human-like visual scanpaths under task-free viewing conditions. The model combines features extracted by convolutional neural networks and simulates eye movements in different regions using Long Short-Term Memory networks.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Engineering, Marine
Da-wei Gao, Yong-sheng Zhu, Jin-fen Zhang, Yan-kang He, Ke Yan, Bo-ran Yan
Summary: Accurate prediction of ship trajectory is crucial in maritime transportation, with multi-step prediction gaining attention for its ability to predict time and position information in the future period. To overcome the complexity and low accuracy of existing methods, a physical hypothesis is introduced to balance the two, resulting in higher prediction accuracy. The proposed method combines the advantages of TPNet and LSTM, involving AIS data preprocessing, destination and support point solutions, and uncertainty analysis.
Article
Engineering, Marine
Wenxiong Wu, Pengfei Chen, Linying Chen, Junmin Mou
Summary: This paper proposes a trajectory prediction model integrating ConvLSTM and Seq2Seq models, which aims to improve the accuracy of ship trajectory prediction by extracting temporal and spatial features. Experimental results show that the proposed model performs better than other benchmark models, providing a promising solution for improving ship navigation safety and quality.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Engineering, Civil
Mengyin Fu, Ting Zhang, Wenjie Song, Yi Yang, Meiling Wang
Summary: This article analyzes NGSIM data and develops an LSTM-based framework to efficiently predict future trajectories of surrounding vehicles, projecting them into a spatio-temporal domain to create an octree map, resolving the issue of dynamic disturbances in autonomous driving.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Mathematics
Lixiang Zhang, Yian Zhu, Jiang Su, Wei Lu, Jiayu Li, Ye Yao
Summary: This paper proposes a hybrid trajectory prediction model based on K-Nearest Neighbor (KNN) and Long Short-Term Memory (LSTM) methods. The model takes into account the trajectory density and uses different methods for prediction in different sea areas. The spatio-temporal characteristics of the trajectory are fully considered to improve the prediction effect. Experimental results show that the proposed method has a small mean square error and outperforms other prediction methods.
Article
Computer Science, Artificial Intelligence
Parnian Afshar, Farnoosh Naderkhani, Anastasia Oikonomou, Moezedin Javad Rafiee, Arash Mohammadi, Konstantinos N. Plataniotis
Summary: The proposed MIXCAPS, a capsule network-based mixture of experts, outperforms other models in detecting lung cancer, showing excellent performance and generalization capabilities.
PATTERN RECOGNITION
(2021)
Article
Geography, Physical
Hao Cheng, Mengmeng Liu, Lin Chen, Hellward Broszio, Monika Sester, Michael Ying Yang
Summary: This paper proposes an attention-based graph model called GATraj, which strikes a good balance between prediction accuracy and inference speed. Extensive experiments show that GATraj achieves state-of-the-art performance and is highly efficient in real-time applications. The effectiveness of each proposed module in GATraj is validated through comprehensive ablation studies.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2023)
Article
Automation & Control Systems
Runmei Li, Zherui Zhong, Jin Chai, Jian Wang
Summary: This paper proposes a CC-LSTM vehicle trajectory prediction model that combines clustering analysis and feature fusion, which can meet the real-time and accuracy requirements of autonomous vehicles in complex driving environments.
INTERNATIONAL JOURNAL OF FUZZY SYSTEMS
(2022)
Article
Engineering, Civil
Zhiyuan Shi, Min Xu, Quan Pan
Summary: A constrained Long Short-Term Memory network is proposed for flight trajectory prediction, with three dynamic constraints introduced to maintain long-term dependencies. Density-Based Spatial Clustering of Applications with Noise and Linear Least Squares are used for data segmentation and preprocessing, while sliding windows ensure trajectory continuity. Multiple ADS-B ground stations contribute to the experimental dataset, and quantitative analysis shows the model outperforms other state-of-the-art models.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2021)
Article
Computer Science, Software Engineering
Pei Lv, Hui Wei, Tianxin Gu, Yuzhen Zhang, Xiaoheng Jiang, Bing Zhou, Mingliang Xu
Summary: This paper proposes a new movement description called trajectory distribution and develops a trajectory prediction method called social probability method based on it, which combines trajectory distributions and convolutional recurrent neural networks. By extracting features from the new movement description, the method generates robust and accurate predictions.
COMPUTATIONAL VISUAL MEDIA
(2022)
Article
Computer Science, Artificial Intelligence
Niccolo Bisagno, Cristiano Saltori, Bo Zhang, Francesco G. B. De Natale, Nicola Conci
Summary: Recurrent neural networks have been utilized to predict pedestrian motion in crowded scenes by learning the relative motion between individuals. This study proposes a framework that enriches the learning model with social relationships and environment layout to improve crowd motion prediction. Socially-related individuals exhibit coherent motion patterns, which are exploited to cluster trajectories with similar properties and enhance trajectory prediction accuracy, especially at the group level. Additionally, incorporating the environment layout into the model ensures a more realistic and reliable learning framework.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2021)
Article
Computer Science, Artificial Intelligence
Zafar Mahmood, Ali Daud, Rabeeh Ayaz Abbasi
Summary: This paper explores the prediction of rising stars in basketball as a machine learning problem, using co-player statistics as features for model training. The highest F-measure score achieved by derived features is 96%, with the Maximum Entropy Markov Model showing dominance in F-measure scores across different datasets. Ranking comparison shows that most labeled rising stars rank in the top 100 in subsequent seasons, and comparison with NBA most improved players reveals rising stars have better efficiency in those seasons.
KNOWLEDGE-BASED SYSTEMS
(2021)