Article
Mathematics
Cheng-Hong Yang, Tshimologo Molefyane, Yu-Da Lin
Summary: Economic forecasting is crucial and machine learning has been used to provide accurate predictions. This study demonstrates that a gated recurrent unit (GRU) neural network model outperforms other models in forecasting government expenditure.
Article
Computer Science, Information Systems
Ziyu Sheng, Shiping Wen, Zhong-Kai Feng, Kaibo Shi, Tingwen Huang
Summary: Runoff forecasting is crucial for the rational use and protection of water resources. This article proposes a novel framework called ResGRU Plus, which combines GRU, ResNet, and SENet to improve the depth and accuracy of the model. Multiple experiments show that ResGRU Plus outperforms traditional models and achieves state-of-the-art performance in runoff forecasting.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Engineering, Multidisciplinary
Haiping Lin, Amin Gharehbaghi, Qian Zhang, Shahab S. Band, Hao Ting Pai, Kwok-Wing Chau, Amir Mosavi
Summary: In this research, deep learning-based neural network models are developed to forecast the mean monthly groundwater level in Qosacay plain, Iran. The new double-GRU model coupled with multiplication layer (GRU2x model) is chosen as the best model based on performance evaluation metrics.
ENGINEERING APPLICATIONS OF COMPUTATIONAL FLUID MECHANICS
(2022)
Article
Engineering, Electrical & Electronic
Yuchen Zhao, Fei Meng, Xingtong Lu
Summary: This paper introduces an improved lattice Boltzmann method based on deep learning, which combines convolutional neural network (CNN) and gated recurrent unit neural network (GRU) to significantly reduce computation time and improve computational efficiency. The proposed method also deals with non-stationary and steady-state problems.
SIGNAL IMAGE AND VIDEO PROCESSING
(2023)
Article
Computer Science, Information Systems
Liyang Zhang, Hiroyuki Suzuki, Akio Koyama
Summary: This research involves attaching multiple sensors to tableware to detect meal information, using algorithms such as recurrent neural network and multi-instance learning to achieve high accuracy. Users can browse processed meal information and suggestions through the system.
INTERNET OF THINGS
(2021)
Article
Mathematics, Applied
Yuting Li, Yong Li
Summary: This paper introduces a homotopy gated recurrent unit (H-GRU) model to improve the long-term dependency of recurrent neural networks (RNN) and validates it in hyperchaos prediction tasks. The results show that the proposed model outperforms baseline models in prediction accuracy and replicating hyperchaotic attractors.
COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION
(2022)
Article
Computer Science, Artificial Intelligence
J. Ashok Kumar, S. Abirami, Tina Esther Trueman, Erik Cambria
Summary: Toxicity identification is a serious issue in online communities, and an automatic system like MCBiGRU is proposed for detecting toxic comments. Experimental results show that the MCBiGRU model outperforms in terms of multilabel metrics.
Article
Acoustics
Zhen Li, Saleem Riaz, Muhammad Waqas, Munira Batool
Summary: This paper proposes an adaptive diagnosis method that combines DGRU, WPD, and ELM for rolling bearing, which effectively eliminates noise, extracts features, and outputs diagnosis results to monitor the health status of rolling bearings.
SHOCK AND VIBRATION
(2022)
Article
Computer Science, Artificial Intelligence
Masaki Ikuta, Jun Zhang
Summary: Computed tomography (CT) is an important medical imaging technology. Traditional CT image reconstruction methods are not effective for low-dose X-ray CT imaging. This article proposes a novel neural network based on iterative reconstruction and recurrent neural network for CT image reconstruction, which outperforms traditional methods and other deep learning techniques in terms of image quality and metrics.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Health Care Sciences & Services
Dong-Her Shih, Ching-Hsien Liao, Ting-Wei Wu, Xiao-Yin Xu, Ming-Hung Shih
Summary: The proposed CNN-GRU model in this study has a high accuracy in detecting dysarthria, which is of great significance for the diagnosis and treatment of patients with neurological diseases.
Article
Engineering, Multidisciplinary
Weibin Chen, Danial Sharifrazi, Guoxi Liang, Shahab S. Band, Kwok Wing Chau, Amir Mosavi
Summary: This study proposes a data-driven modeling technique to predict the discharge coefficient of streamlined weirs based on an experimental dataset and compares the performance of machine learning and deep learning algorithms. The results show that the proposed three-layer hierarchical deep learning algorithm with a convolutional layer and two subsequent GRU layers, hybridized with linear regression, achieves lower error metrics.
ENGINEERING APPLICATIONS OF COMPUTATIONAL FLUID MECHANICS
(2022)
Article
Engineering, Civil
Amin Gharehbaghi, Redvan Ghasemlounia, Farshad Ahmadi, Mohammad Albaji
Summary: This study uses a deep learning-based neural network model to predict groundwater level fluctuations and identifies temperature, precipitation, and water diversion discharge as the most influential factors. By tuning the hyperparameters, the best model is chosen and achieves good prediction results.
JOURNAL OF HYDROLOGY
(2022)
Article
Chemistry, Medicinal
Edison Mucllari, Vasily Zadorozhnyy, Qiang Ye, Duc Duy Nguyen
Summary: Advances in deep neural networks have made powerful machine learning methods available in various fields. This research proposes using new NC-GRU AutoEncoder to create neural molecular fingerprints, improving the performance of various molecular-related tasks.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2023)
Article
Physics, Multidisciplinary
Yu Zhang, Yingying He, Likai Zhang
Summary: Recognition of abnormal driving behavior is important for driving reliability and safety. This paper proposes a novel data-driven method combining a convolutional neural network and a Bidirectional gated recurrent unit to improve accuracy and robustness in recognizing abnormal driving behavior.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Sydney Mambwe Kasongo, Yanxia Sun
Summary: This paper introduces a method for implementing IDS based on DGRU, and evaluates its performance using the NSL-KDD benchmark dataset. Experimental results demonstrate a significant performance improvement of DGRU IDS compared to existing methods.
Article
Computer Science, Artificial Intelligence
Changxing Wu, Jinsong Su, Yidong Chen, Xiaodong Shi
Article
Computer Science, Artificial Intelligence
Han Xiao, Yidong Chen, Xiaodong Shi, Ge Xu
Article
Computer Science, Interdisciplinary Applications
Jialiang Lin, Yao Yu, Yu Zhou, Zhiyang Zhou, Xiaodong Shi
Article
Mathematical & Computational Biology
Jiangbin Zheng, Zheng Zhao, Min Chen, Jing Chen, Chong Wu, Yidong Chen, Xiaodong Shi, Yiqi Tong
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2020)
Article
Computer Science, Artificial Intelligence
Han Xiao, Yidong Chen, Xiaodong Shi
Summary: Knowledge representation is a critical issue in knowledge engineering and artificial intelligence, with knowledge embedding methods playing an important role. This paper introduces a semantic model based on multi-view clustering for generating semantic representations of knowledge elements and improving entity retrieval. Extensive experiments demonstrate substantial improvements of this model against baselines on various knowledge graph tasks.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2021)
Article
Materials Science, Multidisciplinary
Yong Chen, Liming Chen, Qiong Huang, Zhigang Zhang
Summary: In FMLs, replacing aluminum with magnesium leads to faster perforation and energy dissipation, but also reduces delamination damage at the metal-composite interface.
MECHANICS OF ADVANCED MATERIALS AND STRUCTURES
(2021)
Article
Computer Science, Artificial Intelligence
Jiangbin Zheng, Yidong Chen, Chong Wu, Xiaodong Shi, Suhail Muhammad Kamal
Summary: Neural Sign Language Translation (SLT) models often overlook non-manual features such as facial expressions, leading to translation errors. This paper proposes two novel schemes to enhance the performance of traditional SLT models with a focus on facial expression information. Experimental results show significant improvements in translation accuracy.
Article
Computer Science, Artificial Intelligence
Jialiang Lin, Yingmin Wang, Yao Yu, Yu Zhou, Yidong Chen, Xiaodong Shi
Summary: Source code is crucial for researchers to reproduce and replicate the results of AI papers. To address the labor-intensive and time-consuming task of manual collection, researchers propose a method to automatically identify and extract source code from papers. They find that 20.5% of top AI conference papers have available source code, but 8.1% of the source code repositories are no longer accessible.
INTERNATIONAL JOURNAL OF SOFTWARE ENGINEERING AND KNOWLEDGE ENGINEERING
(2022)
Article
Computer Science, Interdisciplinary Applications
Jun Ren, Quan Zhang, Ying Zhou, Yudi Hu, Xuejing Lyu, Hongkun Fang, Jing Yang, Rongshan Yu, Xiaodong Shi, Qiyuan Li
Summary: Research shows that the proposed MURPXMBD algorithm can reduce noise in single-cell RNA sequencing data, improve the quality and accuracy of clustering algorithms, help discover new cell types, and enhance the performance of dataset integration algorithms.
JOURNAL OF BIOMEDICAL INFORMATICS
(2022)
Article
Computer Science, Interdisciplinary Applications
Jialiang Lin, Yao Yu, Jiaxin Song, Xiaodong Shi
Summary: Proper citation is crucial for academic writing to accumulate knowledge and maintain academic integrity. This study proposes a method called Citation Recommendation for Published Scientific Entity (CRPSE), which utilizes cooccurrences between published scientific entities and in-text citations from previous researchers to effectively recommend source papers. A statistical analysis of missing citations in prestigious computer science conferences in 2020 reveals that 475 published scientific entities in computer science and mathematics lack proper citations. It is found that many entities mentioned without citations are well-accepted research results.
Proceedings Paper
Computer Science, Artificial Intelligence
Xun Zhou, Zhiyang Zhou, Xiaodong Shi
Summary: Inspired by the success of FastSpeech, this paper proposes FCH-TTS, a fast, controllable, and universal neural text-to-speech model that can generate high-quality spectrograms. Unlike FastSpeech, FCH-TTS uses a simpler attention-based soft alignment mechanism to improve its adaptability to different languages. It also introduces a fusion module to better model speaker features and ensure the desired timbre. Experimental results demonstrate that FCH-TTS achieves the fastest inference speed and the best speech quality compared to baseline models.
2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhaohong Lai, Biao Fu, Shangfei Wei, Xiaodong Shi
Summary: This paper proposes a framework called Prompt-BEN that enhances biomedical entity normalization using continuous prompts. The method fine-tunes only a few parameters and utilizes embeddings with continuous prefix prompts to capture semantic similarity. It also designs a contrastive loss with a synonym marginalized strategy for the BEN task. Experimental results demonstrate that the method achieves competitive or even greater linking accuracy compared to state-of-the-art fine-tuning-based models while having about 600 times fewer tuned parameters.
NATURAL LANGUAGE PROCESSING AND CHINESE COMPUTING, NLPCC 2022, PT II
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Yidong Chen, Enjun Zhong, Yiqi Tong, Yanru Qiu, Xiaodong Shi
Summary: This paper introduces a novel document-level machine translation Quality Estimation (QE) model based on Centering Theory (CT), and releases an open-source Chinese-English corpus for document-level machine translation QE. Experimental results demonstrate that the proposed model outperforms the baseline model significantly.
MACHINE TRANSLATION, CCMT 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yiqi Tong, Yidong Chen, Guocheng Zhang, Jiangbin Zheng, Hongkang Zhu, Xiaodong Shi
Summary: Back-translation is an effective data augmentation method for improving the performance of Neural Machine Translation (NMT). By proposing a constraint random decoding method and using an evolution decoding algorithm, more diverse synthetic sentences can be generated while maintaining quality.
MACHINE TRANSLATION, CCMT 2021
(2021)
Review
Computer Science, Information Systems
Suhail Muhammad Kamal, Yidong Chen, Shaozi Li, Xiaodong Shi, Jiangbin Zheng
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.