检索结果-内蒙古大学图书馆

JGURD: joint gradient update relational direction-enhanced method for knowledge graph completion

PEERJ COMPUTER SCIENCE 2025年 11卷 e2808-e2808页

作者： Ding, Lianhong Li, Mengxiao Gao, Shengchang Li, Juntao Yuan, Ruiping Yu, Jianye Beijing Wuzi Univ Sch Informat Beijing Peoples R China Shandong First Med Univ Peoples Hosp Informat Dept Shandong Peoples R China

Relational direction plays an important role in multi-relational knowledge graphs (KGs). Current knowledge graph completion (KGC) methods suffer from insufficient utilization of relation correlation information. To address this issue, this article proposes a novel KGC framework, namely JGURD, which uses the encoder-decoder structure to achieve Joint Gradient Update with Relational Direction information. It combines graph convolutional networks (GCNs) with KG embedding methods, defining a update mechanism for entities and relationships to joint gradient updates. To incorporate entity information into the update of relationships, the forward propagation gradients of the triple score function are recorded, and entity gradient information is fused into relationship updates. To fully utilize relational direction information, a relation correlation graph (RCG) is constructed based on the topological patterns of relationship pairs. We design a multi-relation encoder combining GCN and multi-layer attention mechanism on RCG to comprehensively capture local and global structures of the RCG. To enhance the interpretability and adaptability of JGURD, three different decoders are employed. Experimental results show that JGURD outperforms the second-place HHAN-KGC, and the Hits@3 and MRR metrics on the FB15k dataset increased by 6.8% and 8.9%, respectively.

关键词： Knowledge graph completion Graph neural networks Joint gradient update Link prediction Relational direction encoder-decoder Multi-relational graph

来源：评论

学校读者我要写书评

暂无评论

Assessment of land use and land cover change detection and prediction using deep learning techniques for the southwestern coastal region, Goa, India

引用

ENVIRONMENTAL MONITORING AND ASSESSMENT 2024年第6期196卷 527页

作者： Naik, Nitesh Chandrasekaran, Kandasamy Sundaram, Venkatesan Meenakshi Panneer, Prabhavathy Natl Inst Technol Dept Comp Sci & Engn Mangalore 575025 Karnataka India Natl Inst Technol Dept Comp Sci & Engn Pondicherry 609609 India Sch Informat Technol & Engn Vellore Inst Technol Vellore 632014 TamilNadu India

Understanding the connections between human activities and the natural environment depends heavily on information about land use and land cover (LULC) in the form of accurate LULC maps. Environmental monitoring using deep learning (DL) is rapidly growing to preserve a sustainable environment in the long term. For establishing effective policies, regulations, and implementation, DL can be a valuable tool for assessing environmental conditions and natural resources that will positively impact the ecosystem. This paper presents the assessment of land use and land cover change detection (LULCCD) and prediction using DL techniques for the southwestern coastal region, Goa, also known as the tourist destination of India. It consists of three components: (i) change detection (CD), (ii) quantification of LULC changes, and (iii) prediction. A new CD assessment framework, Spatio-Temporal encoder-decoder Self Attention Network (STEDSAN), is proposed for the LULCCD process. A dual branch encoder-decoder network is constructed using strided convolution with downsampling for the encoder and transpose convolution with upsampling for the decoder to assess the bitemporal images spatially. The self-attention (SA) mechanism captures the complex global spatial-temporal (ST) interactions between individual pixels over space-time to produce more distinct features. Each branch accepts the LULC map of 2 years as one of its inputs to determine binary and multiclass changes among the bitemporal images. The STEDSAN model determines the patterns, trends, and conversion from one LULC type to another for the assessment period from 2005 to 2018. The binary change maps were also compared with the existing state of the art (SOTA) CD methods, with STEDSAN having an overall accuracy of 94.93%. The prediction was made using an recurrent neural network (RNN) known as long short term memory network (LSTM) for the year 2025. Experiments were conducted to determine area-wise changes in several LULC classes

关键词： LULC encoder-decoder Self-attention Change map Recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

A Variational Bayesian Inference-Based En-decoder Framework for Traffic Flow Prediction

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第3期25卷 2966-2975页

作者： Kong, Jianlei Fan, Xiaomeng Jin, Xuebo Lin, Sen Zuo, Min Beijing Technol & Business Univ Sch Artificial Intelligence Beijing Peoples R China Beijing Acad Agr & Forestry Sci Res Ctr Intelligent Equipment Technol Beijing 100097 Peoples R China Beijing Technol & Business Univ Natl Engn Lab Agriprod Qual Traceabil Beijing Peoples R China

Accurate traffic flow prediction, a hotspot for intelligent transportation research, is the prerequisite for traffic flow prediction for making travel plans. The speed of traffic flow can be affected by roads condition, weather, holidays, etc. Moreover, sensors to catch the information about traffic flow will be interfered with by environmental factors such as illumination, collection time, occlusion, etc. Therefore, the traffic flow in the practical transportation system is complicated, uncertain, and challenging to predict accurately. Motivated from the aforementioned issues and challenges, in this paper, we propose a deep encoder-decoder prediction framework based on variational Bayesian inference. A Bayesian neural network is designed by combining variational inference with Gated Recurrent Units (GRU) which is used as the deep neural network unit of the encoder-decoder framework to mine the intrinsic dynamics of traffic flow. Then, the variational inference is introduced into the multi-head attention mechanism to avoid noise-induced deterioration of prediction accuracy. The proposed model achieves superior prediction performance on the Guangzhou urban traffic flow dataset over the benchmarks, particularly when the long-term prediction.

关键词： Traffic flow prediction time-series data prediction variational Bayesian inference multi-head attention deep learning encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Automatic segmentation of brain glioma based on XY-Net

引用

MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING 2024年第1期62卷 153-166页

作者： Xu, Wenbin Liu, Jizhong Fan, Bing Nanchang Univ Nanchang Key Lab Med & Technol Res Nanchang 330006 Peoples R China Jiangxi Prov Peoples Hosp Affiliated Hosp 1 Dept Radiol Nanchang Med Coll Nanchang 330006 Peoples R China

Glioma is a malignant primary brain tumor, which can easily lead to death if it is not detected in time. Magnetic resonance imaging is the most commonly used technique to diagnose gliomas, and precise outlining of tumor areas from magnetic resonance images (MRIs) is an important aid to physicians in understanding the patient's condition and formulating treatment plans. However, relying on radiologists to manually depict tumors is a tedious and laborious task, so it is clinically important to investigate an automated method for outlining glioma regions in MRIs. To liberate radiologists from the heavy task of outlining tumors, we propose a fully convolutional network, XY-Net, based on the most popular U-Net symmetric encoder-decoder structure to perform automatic segmentation of gliomas. We construct two symmetric sub-encoders for XY-Net and build interconnected X-shaped feature map transmission paths between the sub-encoders, while maintaining the feature map concatenation between each sub-encoder and the decoder. Moreover, a loss function composed of the balanced cross-entropy loss function and the dice loss function is used in the training task of XY-Net to solve the class unevenness problem of the medical image segmentation task. The experimental results show that the proposed XY-Net has a 2.16% improvement in dice coefficient (DC) compared to the network model with a single encoder structure, and compare with some state-of-the-art image segmentation methods, XY-Net achieves the best performance. The DC, HD, recall, and precision of our method on the test set are 74.49%, 10.89 mm, 78.06%, and 76.30%, respectively. The combination of sub-encoders and cross-transmission paths enables the model to perform better;based on this combination, the XY-Net achieves an end-to-end automatic segmentation of gliomas on 2D slices of MRIs, which can play a certain auxiliary role for doctors in grasping the state of illness.

关键词： Glioma Fully convolutional network Tumor segmentation encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Concrete spalling detection system based on semantic segmentation using deep architectures

引用

COMPUTERS & STRUCTURES 2024年 300卷

作者： Yasmin, Tamanna La, Duc La, Kien Nguyen, Minh Tuan La, Hung Manh Univ Nevada Dept Comp Sci & Engn Adv Robot & Automat Lab 1664 North Virginia StMS0171 Reno NV 89557 USA Univ Utah Kahlert Sch Comp 50 Cent Campus DrRoom 3190 Salt Lake City UT 84112 USA Thai Nguyen Univ Thai Nguyen Univ Technol Dept Elect Engn Adv Wireless Commun Network Lab 6663-2 Natl Rd Thai Nguyen 240000 Vietnam

This paper presents a method for detecting the location of spalling and assessing the severity level of the spalling in concrete surfaces. The proposed method is constructed based on deep learning architectures and multi-class semantic segmentation. The proposed method can detect each pixel as a non-spalling, a deepspalling, or a shallow-spalling. The proposed method consists of three different deep learning architectures with several encoders as backbone networks. Both qualitative and quantitative analyses show that the deep learning architecture with a certain encoder network can detect spalling with different severity levels very well. Additionally, the paper proposes a method to analyze the deep spalling areas of concrete to show their severity levels. The performance analysis shows that this approach provides very convincing results with respect to the actual affected spalling areas. The results convey that this paper achieved a higher level of performance for detecting spalling and assessing the severity of the spalling.

关键词： Spalling detection Spalling severity Deep architecture encoder-decoder Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

From Data to Diagnosis: Enhancing Radiology Reporting With Clinical Features Encoding and Cross-Modal Coherence

引用

IEEE ACCESS 2024年 12卷 127341-127356页

作者： Iqbal, Saeed Qureshi, Adnan N. Khan, Faheem Aurangzeb, Khursheed Akbar, Muhammad Azeem Univ Cent Punjab Fac Informat Technol & Comp Sci Dept Comp Sci Lahore 54000 Pakistan Newman Univ Fac Arts Soc & Profess Studies Birmingham B32 3NT W Midlands England Gachon Univ Dept Comp Engn Seongnam Si 13120 South Korea King Saud Univ Coll Comp & Informat Sci Dept Comp Engn Riyadh 11543 Saudi Arabia LUT Univ Dept Software Engn Lappeenranta 53851 Finland

The integration of radiology reports for healthcare treatment using AI presents a transformative opportunity to enhance patient care and optimize healthcare delivery. Generating accurate radiology reports is crucial for guiding patient treatment in the clinical traditional applications or machines. However, the task of writing these reports can be a significant burden on medical practitioners. To address this challenge, we propose an adaptive, multi-modal technique for generating reports from chest X-rays. Our technique is based on the measurement that the content of clinical reports is highly accompanied by particular information present in the X-ray images. It comprises two key stages: Firstly, we introduce wisdom learning that leverages textual embedding to automatically extract and preserve medical wisdom from radiology reports. This wisdom base eliminates the need for manual labor in distilling valuable insights. Secondly, we employ a Cross-modal coherence technique to enhance the semantic alignment between reports, disease labels, and images. By utilizing clinical embedding, we channel the learning process of the visual feature attribute, ensuring meaningful associations between the different modalities. We conducted comprehensive evaluations of our model using both natural language generation metrics and clinical efficacy assessments on publicly available IU-Xray datasets. Through ablation analyses, we affirm the individual contributions of each module in improving the quality of generated reports. Moreover, when both modules are employed together, our approach surpasses existing state-of-the-art techniques across a wide range of evaluation metrics. This highlights the effectiveness of our technique in generating high-quality radiology reports and alleviating the burden on radiologists using intelligent medical applications or machines.

关键词： Medical diagnostic imaging Radiology Medical services Visualization Feature extraction Coherence Clinical diagnosis Encoding Clinical and visual features radiology reports encoder-decoder feature embedding wisdom learning

来源：评论

学校读者我要写书评

暂无评论

Forwardformer: Efficient Transformer With Multi-Scale Forward Self-Attention for Day-Ahead Load Forecasting

引用

IEEE TRANSACTIONS ON POWER SYSTEMS 2024年第1期39卷 1421-1433页

作者： Qu, Kai Si, Gangquan Shan, Zihan Wang, Qianyue Liu, Xiaoliang Yang, Chen Xi An Jiao Tong Univ Sch Elect Engn State Key Lab Elect Insulat & Power Equipment Xian 710049 Peoples R China

Accurate load forecasting can maintain the safety and stability of power grids. The mainstream models are based on complex recurrent or convolutional neural networks (RNNs, CNNs), and in recent years they are often used in combination with the attention mechanism. The shortcomings of these models are that they cannot get rid of sequential computation and fail to capture long-term dependence. For better application in day-ahead load forecasting (DALF), we propose a new network architecture, i.e., Forwardformer, which is implemented by imposing some effective improvements on the Transformer (a pioneering network model with applications in Natural Language Processing (NLP)). The core of Forwardformer is the multi-scale forward self-attention (MSFSA) and the correction structure of the encoder-dual decoder, which confer better computational efficiency and forecasting accuracy. Meanwhile, to improve forecasting accuracy on special days (weekends, holidays, etc.), the MSFSA configures dilated attention and global attention for them, respectively. Experiments performed on datasets from China and America demonstrated that the Forwardformer requires less runtime while being superior in forecasting accuracy. Especially in terms of weekends and holidays, it has outstanding advantages and provides a new solution to the DALF problem.

关键词： Load modeling Forecasting Load forecasting Predictive models Transformers Time series analysis Power system stability Correction structure encoder-decoder forwardformer holidays multi-scale forward self-attention short-term load forecasting weekends

来源：评论

学校读者我要写书评

暂无评论

Deep reinforcement learning solve the task fairness-oriented flexible pickup and delivery problem

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 278卷

作者： Tian, Ran Sun, Zhihui Lu, Xin Li, Zhaobin Chang, Longlong Northwest Normal Univ Dept Comp Sci & Engn Lanzhou 730070 Peoples R China

The Task Fairness-oriented Flexible Pickup and Delivery Problem (TF2PDP) stems from the actual needs of multi-warehouse management strategies and is one of the key challenges in the current field of logistics and distribution. In TF2PDP, on the one hand, it is necessary to ensure that the total driving time of the fleet to complete all orders according to the time window requirements is the shortest, and to make the task allocation among vehicles relatively fair;On the other hand, it is necessary to quickly compute to get the route planning for a heterogeneous fleet of vehicles to fulfill all the orders in a complex scenario and make the total fleet traveling time the shortest. However, there are currently few related studies on this problem, and it is difficult for traditional heuristic algorithms to quickly find a feasible solution to this problem. Therefore, we construct a Heterogeneous Attention Framework with Parallel encoders (HAFPE) based on the deep reinforcement learning method to quickly calculate the approximate optimal solution of TF2PDP. First, we propose a vehicle selection based on a combined mask and travel time strategy to make the task as fair as possible among vehicles. Second, we propose a Parallel encoder-decoder Model to automatically select orders, which combines convolutional block attention and multi-head attention to shorten the total fleet travel time as much as possible. To verify the performance of the algorithm, we compare the proposed deep reinforcement learning method with multiple heuristics and reinforcement learning algorithms on datasets of various problem sizes. Experimental results show that our method distributes tasks relatively fairly on most datasets, and the time consumption to complete the task is better than other baseline methods.

关键词： Pickup and delivery problem Heterogeneous fleets Deep reinforcement learning encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Research on stock prediction based on CED-PSO-StockNet time series model

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-28页

作者： Chen, Xinying Yang, Fengjiao Sun, Qianhan Yi, Weiguo Dalian Jiaotong Univ Sch Comp & Commun Engn 794 Huanghe Rd Dalian Liaoning Peoples R China Dalian Jiaotong Univ Sch Software 794 Huanghe Rd Dalian Liaoning Peoples R China

To tackle the challenge of low accuracy in stock prediction within high-noise environments, this paper innovatively introduces the CED-PSO-StockNet time series model. Initially, the model decomposes raw stock data using the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) technique and reconstructs the components by estimating their frequencies via the extreme point method. This process enhances component stability and mitigates noise interference. Subsequently, an encoder-decoder framework equipped with an attention mechanism is employed for precise prediction of the reconstructed components, facilitating more effective extraction and utilization of data features. Furthermore, this paper utilizes an Improved Particle Swarm Optimization (IPSO) algorithm to optimize the model parameters. On the Pudong Bank dataset, through ablation experiments and comparisons with baseline models, various optimization strategies incorporated into the proposed CED-PSO-StockNet model were effectively validated. Compared to the standalone LSTM model, CED-PSO-StockNet achieved a remarkable 45.59% improvement in the R2 metric. To further assess the model's generalization capability, this paper also conducted comparative experiments on the Ping An Bank dataset, and the results underscored the significant advantages of CED-PSO-StockNet in the domain of stock prediction.

关键词： Stock prediction CEEMDAN encoder-decoder Attention mechanism PSO

来源：评论

学校读者我要写书评

暂无评论

ChemReco: automated recognition of hand-drawn carbon-hydrogen-oxygen structures using deep learning

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-15页

作者： Ouyang, Hengjie Liu, Wei Tao, Jiajun Luo, Yanghong Zhang, Wanjia Zhou, Jiayu Geng, Shuqi Zhang, Chengpeng Hunan Univ Chinese Med Sch Informat Changsha 410208 Hunan Peoples R China

Chemical molecular structures are a direct and convenient means of expressing chemical knowledge, playing a vital role in academic communication. In chemistry, hand drawing is a common task for students and researchers. If we can convert hand-drawn chemical molecular structures into machine-readable formats, like SMILES encoding, computers can efficiently process and analyze these structures, significantly enhancing the efficiency of chemical research. Furthermore, with the progress of educational technology, automated grading is gaining popularity. When machines automatically recognize chemical molecular structures and assess the correctness of the drawings, it offers great convenience to teachers. We created ChemReco, a tool designed to identify chemical molecular structures involving three atoms: C, H, and O, providing convenience for chemical researchers. Currently, there are limited studies on hand-drawn chemical molecular structures. Therefore, the primary focus of this paper is constructing datasets. We propose a synthetic image method to rapidly generate images resembling hand-drawn chemical molecular structures, enhancing dataset acquisition efficiency. Regarding model selection, the hand-drawn chemical molecule structural recognition model developed in this article achieves a final recognition accuracy of 96.90%. This model employs the encoder-decoder architecture of EfficientNet + Transformer, demonstrating superior performance compared to other encoder-decoder combinations.

关键词： Deep learning SMILES coding Image recognition Convolutional neural network Hand-drawn chemical molecular structure Chemical molecular structure recognition encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：