Article
Automation & Control Systems
Robertas Jurkus, Julius Venskus, Povilas Treigys
Summary: According to the Global Maritime Insurance annual report, maritime accidents, such as vessel collisions and anomalies at sea, remain a significant issue. This study analyzes historical data and proposes an alternative trajectory calculation strategy using Universal Transverse Mercator (UTM). By using UTM and an autoencoder architecture, the accuracy of vessel trajectory prediction improves by almost 30% compared to conventional methods. The research compares different recurrent network architectures and validates the methods in real historical datasets.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Transportation Science & Technology
Thanh Tran, Dan He, Jiwon Kim, Mark Hickman
Summary: This study proposes a sub-area level incident prediction model for predicting traffic incidents across a large-scale road network. Compared to traditional approaches, this model can predict incident occurrence within any given sub-area using a single model, and it consistently outperforms benchmark models in various experiments.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2023)
Article
Materials Science, Multidisciplinary
Kohei Sase, Yasushi Shibuta
Summary: A novel method combining deep generative models and recurrent neural networks is proposed to predict multi-atom cooperative phenomena at the atomic scale. The method successfully identifies different crystal orientations in polycrystalline nickel and predicts microstructure evolution in polycrystalline iron.
Article
Engineering, Civil
Yuchu He, Zhijuan Jia, Mingsheng Hu, Geng Zhang, Hanjie Dong
Summary: Through intelligent analysis and prediction of vehicle trip data, this technology enhances user driving experience and improves urban traffic conditions. However, existing models suffer from insufficient information, data deviation, and linear feature addition. To address these drawbacks, a novel method named HAHIF is proposed, which achieves good prediction results on a public dataset.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Civil
Kan Guo, Yongli Hu, Zhen Qian, Hao Liu, Ke Zhang, Yanfeng Sun, Junbin Gao, Baocai Yin
Summary: This paper introduces an optimized graph convolution recurrent neural network for traffic prediction, which can better explore the spatial and temporal information of traffic data and learns an optimized graph through a data-driven approach to reveal the latent relationship among road segments.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2021)
Article
Computer Science, Information Systems
Peixiao Wang, Yan Zhang, Tao Hu, Tong Zhang
Summary: This study proposes a dynamic temporal graph neural network model that considers missing values and dynamic spatial relationships for urban traffic flow prediction. The model achieves good prediction results and outperforms existing baselines on a real traffic dataset.
INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE
(2023)
Article
Mathematics
Yanbing Li, Wei Zhao, Huilong Fan
Summary: The accuracy of short-term traffic flow prediction is crucial for the construction of smart cities. This paper proposes a dynamic perceptual graph neural network model that effectively analyzes the relationship between the temporal and spatial dimensions of traffic data flow, resulting in more accurate predictions of future traffic speeds.
Article
Green & Sustainable Science & Technology
Xiaoyuan Feng, Yue Chen, Hongbo Li, Tian Ma, Yilong Ren
Summary: Traffic flow prediction is a vital component of intelligent transportation systems, and accurate predictions can help issue early congestion warnings and reduce greenhouse gas emissions. A novel model called GRGCAN is proposed, which incorporates temporal and spatial feature extractors, an attention mechanism, and a residual connection. Experimental results on real-world datasets demonstrate that GRGCAN achieves better prediction accuracy and computational efficiency compared to baseline models, with a low MAPE of 15.97% and 12.13%.
Article
Green & Sustainable Science & Technology
Sura Mahmood Abdullah, Muthusamy Periyasamy, Nafees Ahmed Kamaludeen, S. K. Towfek, Raja Marappan, Sekar Kidambi Raju, Amal H. H. Alharbi, Doaa Sami Khafaga
Summary: Recently, researchers have been using deep learning techniques to detect and reduce traffic congestion. This research proposes a bidirectional recurrent neural network (BRNN) with Gated Recurrent Units (GRUs) to classify and predict traffic congestion. The results show that the proposed model outperforms existing state-of-the-art methods.
Article
Physics, Multidisciplinary
Shun Wang, Yong Zhang, Yongli Hu, Baocai Yin
Summary: Traffic flow prediction is an important and challenging task in intelligent transportation systems. Existing methods only consider temporal and spatial dependence in traffic data, lacking exploration of the implicit semantic relationship in traffic knowledge. To address this, a Knowledge Fusion Enhanced Graph Neural Network (KFGNN) module is proposed, which models the transportation system as topological graphs containing various types of knowledge. Experimental results demonstrate that the knowledge-enhanced models outperform classic GCN-based models in terms of prediction performance.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Yi Zhou, Yihan Liu, Nianwen Ning, Li Wang, Zixing Zhang, Xiaozhi Gao, Ning Lu
Summary: This study proposes a knowledge representation learning-actuated spatial-temporal graph neural network (KR-STGNN) for traffic flow prediction. By combining knowledge embedding with traffic features and dynamically updating traffic features, as well as capturing spatial-temporal dependencies, the method shows superior forecasting performances, especially for short-term prediction.
COMPLEX & INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Information Systems
Jose F. Rodrigues-, Marco A. Gutierrez, Gabriel Spadon, Bruno Brandoli, Sihem Amer-Yahia
Summary: This study introduces an artificial neural network architecture, LIG-Doctor, based on two Minimal Gated Recurrent Unit networks, which achieved consistent improvements in prognosis prediction for patients. The results could inspire future research on similar problems.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Hardware & Architecture
Gianni D'Angelo, Francesco Palmieri
Summary: The main aim of this work is to support modern network traffic classification methods by mining more expressive and meaningful features from basic features using a novel deep neural network architecture. Through experiments and theoretical analysis, it is demonstrated that the traffic classifier obtained by stacking autoencoder with a fully connected neural network significantly improves accuracy compared to existing machine learning approaches, pure convolutional and recurrent stacked neural networks, and pure feed-forward networks. This classifier is also able to maintain high accuracy even with imbalanced training datasets.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Fuxian Li, Jie Feng, Huan Yan, Depeng Jin, Yong Li
Summary: This article proposes a novel model for flow prediction in irregular regions. It utilizes CNN and GNN to capture spatial dependence in grid-based and irregular regions, and introduces a location-aware and time-aware graph attention mechanism based on dynamic node attribute embedding and multi-view graph reconstruction. Experimental results demonstrate that the model outperforms 10 baselines by reducing prediction error by around 8%.
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2022)
Article
Engineering, Civil
Mingzhe Liu, Tongyu Zhu, Junchen Ye, Qingxin Meng, Leilei Sun, Bowen Du
Summary: Forecasting traffic flow is crucial in urban areas, and a novel method called Spatio-Temporal AutoEncoder (ST-AE) is proposed to more effectively incorporate various intrinsic patterns in real-world traffic flows. The method learns the patterns from traffic flow data and predicts future traffic flows by projecting the current hidden states to the future hidden states.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Rui Lv, Dingheng Wang, Jiangbin Zheng, Zhao-Xu Yang
Summary: In this paper, the authors investigate tensor decomposition for neural network compression. They analyze the convergence and precision of tensor mapping theory, validate the rationality of tensor mapping and its superiority over traditional tensor approximation based on the Lottery Ticket Hypothesis. They propose an efficient method called 3D-KCPNet to compress 3D convolutional neural networks using the Kronecker canonical polyadic (KCP) tensor decomposition. Experimental results show that 3D-KCPNet achieves higher accuracy compared to the original baseline model and the corresponding tensor approximation model.
Article
Computer Science, Artificial Intelligence
Xiangkun He, Zhongxu Hu, Haohan Yang, Chen Lv
Summary: In this paper, a novel constrained multi-objective reinforcement learning algorithm is proposed for personalized end-to-end robotic control with continuous actions. The approach trains a single model using constraint design and a comprehensive index to achieve optimal policies based on user-specified preferences.
Article
Computer Science, Artificial Intelligence
Zhijian Zhuo, Bilian Chen, Shenbao Yu, Langcai Cao
Summary: In this paper, a novel method called Expansion with Contraction Method for Overlapping Community Detection (ECOCD) is proposed, which utilizes non-negative matrix factorization to obtain disjoint communities and applies expansion and contraction processes to adjust the degree of overlap. ECOCD is applicable to various networks with different properties and achieves high-quality overlapping community detection.
Article
Computer Science, Artificial Intelligence
Yizhe Zhu, Chunhui Zhang, Jialin Gao, Xin Sun, Zihan Rui, Xi Zhou
Summary: In this work, the authors propose a Contrastive Spatio-Temporal Distilling (CSTD) approach to improve the detection of high-compressed deepfake videos. The approach leverages spatial-frequency cues and temporal-contrastive alignment to fully exploit spatiotemporal inconsistency information.
Review
Computer Science, Artificial Intelligence
Laijin Meng, Xinghao Jiang, Tanfeng Sun
Summary: This paper provides a review of coverless steganographic algorithms, including the development process, known contributions, and general issues in image and video algorithms. It also discusses the security of coverless steganography from theoretical analysis to actual investigation for the first time.
Article
Computer Science, Artificial Intelligence
Yajie Bao, Tianwei Xing, Xun Chen
Summary: Visual question answering requires processing multi-modal information and effective reasoning. Neural-symbolic learning is a promising method, but current approaches lack uncertainty handling and can only provide a single answer. To address this, we propose a confidence based neural-symbolic approach that evaluates NN inferences and conducts reasoning based on confidence.
Article
Computer Science, Artificial Intelligence
Anh H. Vo, Bao T. Nguyen
Summary: Interior style classification is an interesting problem with potential applications in both commercial and academic domains. This project proposes a method named ISC-DeIT, which combines data-efficient image transformer architectures and knowledge distillation, to address the interior style classification problem. Experimental results demonstrate a significant improvement in predictive accuracy compared to other state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Shashank Kotyan, Danilo Vasconcellos Vargas
Summary: This article introduces a novel augmentation technique called Dynamic Scanning Augmentation to improve the accuracy and robustness of Vision Transformer (ViT). The technique leverages dynamic input sequences to adaptively focus on different patches, resulting in significant changes in ViT's attention mechanism. Experimental results demonstrate that Dynamic Scanning Augmentation outperforms ViT in terms of both robustness to adversarial attacks and accuracy against natural images.
Article
Computer Science, Artificial Intelligence
Hiba Alqasir, Damien Muselet, Christophe Ducottet
Summary: The article proposes a solution to improve the learning process of a classification network by providing shape priors, reducing the need for annotated data. The solution is tested on cross-domain digit classification tasks and a video surveillance application.
Article
Computer Science, Artificial Intelligence
Dexiu Ma, Mei Liu, Mingsheng Shang
Summary: This paper proposes a method using neural dynamics solvers to solve infinity-norm optimization problems. Two improved solvers are constructed and their effectiveness and superiority are demonstrated through theoretical analysis and simulation experiments.
Article
Computer Science, Artificial Intelligence
Francesco Gregoretti, Giovanni Pezzulo, Domenico Maisto
Summary: Active Inference is a computational framework that uses probabilistic inference and variational free energy minimization to describe perception, planning, and action. cpp-AIF is a header-only C++ library that provides a powerful tool for implementing Active Inference for Partially Observable Markov Decision Processes through multi-core computing. It is cross-platform and improves performance, memory management, and usability compared to existing software.
Article
Computer Science, Artificial Intelligence
Zelin Ying, Dawei Cheng, Cen Chen, Xiang Li, Peng Zhu, Yifeng Luo, Yuqi Liang
Summary: This paper proposes a novel stock market trends prediction framework called SMART, which includes a self-supervised stock technical data sequence embedding model S3E. By training with multiple self-supervised auxiliary tasks, the model encodes stock technical data sequences into embeddings and uses the learned sequence embeddings for predicting stock market trends. Extensive experiments on China A-Shares market and NASDAQ market prove the high effectiveness of our model in stock market trends prediction, and its effectiveness is further validated in real-world applications in a leading financial service provider in China.
Article
Computer Science, Artificial Intelligence
Hao Li, Hao Jiang, Dongsheng Ye, Qiang Wang, Liang Du, Yuanyuan Zeng, Liu Yuan, Yingxue Wang, C. Chen
Summary: DHGAT1, a dynamic hyperbolic graph attention network, utilizes hyperbolic metric properties to embed dynamic graphs. It employs a spatiotemporal self-attention mechanism and weighted node representations, resulting in excellent performance in link prediction tasks.
Article
Computer Science, Artificial Intelligence
Jiehui Huang, Zhenchao Tang, Xuedong He, Jun Zhou, Defeng Zhou, Calvin Yu-Chian Chen
Summary: This study proposes a progressive learning multi-scale feature blending model for image deraining tasks. The model utilizes detail dilation and texture extraction to improve the restoration of rainy images. Experimental results show that the model achieves near state-of-the-art performance in rain removal tasks and exhibits better rain removal realism.
Article
Computer Science, Artificial Intelligence
Lizhi Liu, Zilin Gao, Yinhe Wang, Yongfu Li
Summary: This paper proposes a novel discrete-time interconnected model for depicting complex dynamical networks. The model consists of nodes and edges subsystems, which consider the dynamic characteristic of both nodes and edges. By designing control strategies and coupling modes, the stabilization and synchronization of the network are achieved. Simulation results demonstrate the effectiveness of the proposed methods.