检索结果-内蒙古大学图书馆

Chaotic time series prediction of nonlinear systems based on various neural network models

CHAOS SOLITONS & FRACTALS 2023年 175卷

作者： Sun, Ying Zhang, Luying Yao, Minghui Beijing Informat Sci & Technol Univ Sch Appl Sci Beijing 100192 Peoples R China Tiangong Univ Sch Aeronaut & Astronaut Tianjin 300387 Peoples R China

This paper discusses the chaos prediction of nonlinear systems using various neural networks based on the modified substructure data-driven modeling architecture. In the modeling step, we construct two-coefficient loss functions according to the linear multi-step method to improve the prediction accuracy of neural networks. Then, the predicted response data of the system is given by the forward Euler method and neural networks. Under such architecture, chaos forecasting is carried out on a five-degree-of-freedom duffing oscillator system via the feedforward neural network (FNN), long short-term memory (LSTM) network and LSTM encoder-decoder (LSTM ED). The numerical simulation results show that the model can predict chaotic time series even if a small amount of information and samples are known, and the prediction window is twice that of the observation window. Among these models, LSTM ED exhibits the highest accuracy in both short-term and long-term chaos prediction. Furthermore, the prediction results mainly involve three evaluation indicators: absolute error, mean absolute error, normalized root mean square error. Through error analysis and noise processing, LSTM ED shows superior stability, robustness and extrapolation ability. Its prediction error is about half of FNN and the maximum increase in accuracy is 71.3 %.

关键词： Neural networks LSTM model encoder-decoder model Chaos prediction Time series

来源：评论

学校读者我要写书评

暂无评论

FrameSum: Leveraging Framing Theory and Deep Learning for Enhanced News Text Summarization

引用

APPLIED SCIENCES-BASEL 2024年第17期14卷

作者： Zhang, Xin Wei, Qiyi Zheng, Bin Liu, Jiefeng Zhang, Pengzhou Commun Univ China Sch Comp & Cyber Sci Beijing 100024 Peoples R China Univ Elect Sci & Technol China Sch Informat & Software Engn Chengdu 610054 Peoples R China Commun Univ China State Key Lab Media Convergence & Commun Beijing 100024 Peoples R China

Framing theory is a widely accepted theoretical framework in the field of news communication studies, frequently employed to analyze the content of news reports. This paper innovatively introduces framing theory into the text summarization task and proposes a news text summarization method based on framing theory to address the global context of rapidly increasing speed and scale of information dissemination. Traditional text summarization methods often overlook the implicit deep-level semantic content and situational frames in news texts, and the method proposed in this paper aims to fill this gap. Our deep learning-based news frame identification module can automatically identify frame elements in the text and predict the dominant frame of the text. The frame-aware summarization generation model (FrameSum) can incorporate the identified frame feature into the text representation and attention mechanism, ensuring that the generated summary focuses on the core content of the news report while maintaining high information coverage, readability, and objectivity. Through empirical studies on the standard CNN/Daily Mail dataset, we found that this method performs significantly better in improving summary quality and maintaining the accuracy of news facts.

关键词： news text summarization framing theory deep learning framework recognition encoder-decoder model

来源：评论

学校读者我要写书评

暂无评论

A deep reinforcement learning-based approach for the home delivery and installation routing problem

引用

INTERNATIONAL JOURNAL OF PRODUCTION ECONOMICS 2022年 244卷

作者： Qiu, Huaxin Wang, Sutong Yin, Yunqiang Wang, Dujuan Wang, Yanzhang Dalian Univ Technol Sch Econ & Management Dalian 116023 Peoples R China Univ Elect Sci & Technol China Sch Econ & Management Chengdu 610064 Peoples R China Sichuan Univ Business Sch Chengdu 610064 Peoples R China

This paper investigates a home delivery and installation routing problem with synchronization constraints stemming from a home industry company in China who provides the last-mile delivery of home decoration and furniture. The company first arranges for products to be delivered from door to door, and later the technicians come to perform the installation service for the customers. The products for each customer must be firstly delivered to the customer by a vehicle and then installed by technicians. The objective is to identify the optimal delivery routes of the vehicles and optimal service routes of the technicians so as to minimize the total travel distance of the delivery and service routes. A deep reinforcement learning method in an encoder-decoder fashion with multi-head attention mechanism and beam search strategy is developed to solve the problem. To evaluate the designed method, extensive numerical experiments based on real service networks provided by the company are conducted. The results show that the proposed method can effectively solve the problem, which outperforms some classical strategies, and some meaningful management implications are provided.

关键词： Delivery and installation routing problem Deep reinforcement learning encoder-decoder model Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

A parallel workflow framework using encoder-decoder LSTMs for uncertainty quantification in contaminant source identification in groundwater

引用

JOURNAL OF HYDROLOGY 2023年 619卷

作者： Anshuman, Aatish Eldho, T. I. Indian Inst Technol Dept Civil Engn Mumbai 400076 India

Groundwater contamination is a major problem and it can be contaminated by natural or manmade activities. Contaminant sources cannot be identified promptly after a contamination event due to slow groundwater movement in aquifers. To limit the further spread of the plume and to take appropriate remedial measures, it is essential to determine the release rates associated with source locations as soon as a contaminant is detected in one of the observation wells in the aquifer. Conventional techniques for contaminant source identification such as the simulation-optimization (SO) uses a simulation model, which is based on estimated or, measured hydrogeological parameters, for replicating the aquifer response to contamination at source locations. However, the associated intrinsic uncertainty in the parameters can affect the estimated release histories at the source locations. To assess confidence in the results, it is important to consider stochasticity in the hydrogeological parameters for contaminant release history estimation requiring numerous runs of the SO model for corresponding breakthrough curves. The present study proposes a novel surrogate simulation optimization (SSO) framework which utilizes an encoder-decoder Long Short-Term Memory (ED-LSTM) based surrogate model along with Multiverse Optimization (MVO) for contaminant source identification. The comparison of ED-LSTM with other surrogate models shows its better accuracy and significantly low computational time requirement compared to the simulation model. To enhance the computational efficiency further, the SSO model is embedded in a parallel workflow for the quantification of uncertainty associated with the inverse modelling. The study shows that the proposed workflow can be efficiently used for uncertainty quantification in contaminant source identification due to stochastic parameters with a reduced computational cost.

关键词： Contaminant Source identification Uncertainty quantification Surrogate modelling encoder-decoder model Long Short-Term Memory (LSTM) Parallel Computing

来源：评论

学校读者我要写书评

暂无评论

Weather Radar Echo Extrapolation Method Based on Deep Learning

引用

ATMOSPHERE 2022年第5期13卷

作者： Zhang, Fugui Lai, Can Chen, Wanjun Univ Elect Sci & Technol China Sch Elect Sci & Engn Chengdu 611731 Peoples R China Chengdu Univ Informat Technol Sch Elect Engn Chengdu 610225 Peoples R China

In order to forecast some high intensity and rapidly changing phenomena, such as thunderstorms, heavy rain, and hail within 2 h, and reduce the influence brought by destructive weathers, this paper proposes a weather radar echo extrapolation method based on deep learning. The proposed method includes the design and combination of the data preprocessing, convolutional long short-term memory (Conv-LSTM) neuron and encoder-decoder model. We collect eleven thousand weather radar echo data in high spatiotemporal resolution, these data are then preprocessed before they enter the neural network for training to improve the data's quality and make the training better. Next, the neuron integrates the structure and the advantages of convolutional neural network (CNN) and long short-term memory (LSTM), called Conv-LSTM, is applied to solve the problem that the full-connection LSTM (FC-LSTM) cannot extract the spatial information of input data. This operation replaced the full-connection structure in the input-to-state and state-to-state parts so that the Conv-LSTM can extract the information from other dimensions. Meanwhile, the encoder-decoder model is adopted due to the size difference of the input and output data to combine with the Conv-LSTM neuron. In the neural network training, mean square error (MSE) loss function weighted according to the rate of rainfall is added. Finally, the matrix "point-to-point" test method, including the probability of detection (POD), critical success index (CSI), false alarm ratio (FAR) and spatial test method contiguous rain areas (CRA), is used to examine the radar echo extrapolation's results. Under the threshold of 30 dBZ, at the time of 1 h, we achieved 0.60 (POD), 0.42 (CSI) and 0.51 (FAR), compared with 0.42, 0.28 and 0.58 for the CTREC algorithm, and 0.30, 0.24 and 0.71 for the TITAN algorithm. Meanwhile, at the time of 1 h, we achieved 1.35 (total MSE ) compared with 3.26 for the CTREC algorithm and 3.05 for the TITAN algorithm. The r

关键词： weather radar echo extrapolation deep learning Conv-LSTM encoder-decoder model loss function

来源：评论

学校读者我要写书评

暂无评论

Saliency and ballness driven deep learning framework for cell segmentation in bright field microscopic images

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年 118卷

作者： Asha, S. B. Gopakumar, G. Subrahmanyam, Gorthi R. K. Sai Amrita Vishwa Vidyapeetham Amrita Sch Comp Dept Comp Sci & Engn Vallikavu India Indian Inst Technol Tirupati Dept Elect Engn Tirupati India

Cell segmentation is the most significant task in microscopic image analysis as it facilitates differential cell counting and analysis of sub-cellular structures for diagnosing cytopathological diseases. Bright-field microscopy is considered the gold standard among different types of optical microscopes used for cell analysis due to its simplicity and cost-effectiveness. However, automatic cell segmentation in bright field microscopy is challenging due to imaging artifacts, poor contrast, overlapping cells, and wide variability of cells. Also, the availability of labeled bright-field images is limited, further constraining the research in developing supervised models for automated cell segmentation. In this research, we propose a novel cell segmentation framework termed Saliency and Ballness driven U-shaped Network (SBU-net) to overcome these challenges. The proposed architecture comprises a novel data-driven feature fusion module that enhances the perceivable structure of cells using its saliency and ballness features. This, together with an encoder-decoder model having dilated convolutions and a novel combination loss function, captured the global context of cell structures and produced accurate cell segmentation results. SBU-net is evaluated using two publicly available bright-field datasets of T cells and pancreatic cancer cells. The model is subjected to 5-fold cross-validation and outperformed state-of-the-art models by producing mean Intersection over Union (IoU) scores of 0.804, 0.829, and mean Dice of 0.891, 0.906, respectively. The architecture was also tested on a fluorescent dataset to see how well it could generalize, and it came out with a mean IoU of 0.892 and a mean Dice of 0.948, outperforming other models reported in the literature.

关键词： Deep learning based semantic segmentation encoder-decoder model Microscopic image analysis Bright-field microscopy

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Trajectory Prediction in Extremely Crowded Scenarios

引用

SENSORS 2019年第5期19卷 1223页

作者： Shi, Xiaodan Shao, Xiaowei Guo, Zhiling Wu, Guangming Zhang, Haoran Shibasaki, Ryosuke Univ Tokyo Ctr Spatial Informat Sci Kashiwa Chiba 2778568 Japan Univ Tokyo Earth Observat Data Integrat & Fus Res Initiat Tokyo 1538505 Japan

Pedestrian trajectory prediction under crowded circumstances is a challenging problem owing to human interaction and the complexity of the trajectory pattern. Various methods have been proposed for solving this problem, ranging from traditional Bayesian analysis to Social Force model and deep learning methods. However, most existing models heavily depend on specific scenarios because the trajectory model is constructed in absolute coordinates even though the motion trajectory as well as human interaction are in relative motion. In this study, a novel trajectory prediction model is proposed to capture the relative motion of pedestrians in extremely crowded scenarios. Trajectory sequences and human interaction are first represented with relative motion and then integrated to our model to predict pedestrians' trajectories. The proposed model is based on Long Short Term Memory (LSTM) structure and consists of an encoder and a decoder which are trained by truncated back propagation. In addition, an anisotropic neighborhood setting is proposed instead of traditional neighborhood analysis. The proposed approach is validated using trajectory data acquired at an extremely crowded train station in Tokyo, Japan. The trajectory prediction experiments demonstrated that the proposed method outperforms existing methods and is stable for predictions of varying length even when the model is trained with a controlled short trajectory sequence.

关键词： trajectory prediction human interaction LSTM crowded scenarios encoder-decoder model deep learning

来源：评论

学校读者我要写书评

暂无评论

An Overview on Image Segmentation Techniques for Reversible Data Hiding

INTERNATIONAL JOURNAL OF MATHEMATICAL ENGINEERING AND MANAGE...

引用

INTERNATIONAL JOURNAL OF MATHEMATICAL ENGINEERING AND MANAGEMENT SCIENCES 2024年第5期9卷 1163-1184页

作者： Gupta, Rasika Delhi Technol Univ Dept Comp Sci & Engn Delhi India

The fields of image processing and computer vision have witnessed significant growth due to the proliferation of digital images across diverse domains. Image Segmentation is the fundamental task in digital image processing, finding applications in pivotal areas such as medical imaging, covert communication, autonomous driving, satellite imaging, among others. One particularly intriguing application of image segmentation lies in Reversible Data Hiding (RDH), where the delineation of the main Region of Interest (ROI) and Non-Region of Interest (NROI) using segmentation plays a crucial role for effective data encryption in the images. Over the last two decades, various studies focussed on developing an efficient data hiding approach, which can embed secret data within ROI and NROI part of image while ensuring its quality. A comprehensive survey has been conducted that meticulously examines different segmentation techniques, along with its usage in reversible data hiding. The main objective of this survey is to compare the performance metrics of reversible data hiding after applying different image segmentation techniques. The image segmentation techniques have been categorized systematically into three main classes: i) Traditional segmentation techniques, encompassing a spectrum of approaches like thresholding, region-based and edge detection based techniques, ii) Machine Learning (ML) based approach consisting of Clustering, Support Vector Machine (SVM) and iii) Deep Learning (DL) based technique, propelled by Convolutional Neural Networks (CNNs) that have emerged as a transformative paradigm, revolutionizing segmentation tasks with their ability to learn complex images. The survey finds out that PSNR value of data embedded images is high after applying deep learning based segmentation technique.

关键词： encoder-decoder model Dilated convolution model ROI segmentation Reversible data hiding .

来源：评论

学校读者我要写书评

暂无评论

Recognition of printed Urdu script in Nastaleeq font by using CNN-BiGRU-GRU Based encoder-decoder Framework

引用

INTELLIGENT SYSTEMS WITH APPLICATIONS 2023年 18卷

作者： Zia, Sohail Azhar, Muhammad Lee, Bumshik Tahir, Adnan Ferzund, Javed Murtaza, Fozia Ali, Moazam Comsats Univ Islamabad Dept Comp Sci Sahiwal Campus Sahiwal 57000 Pakistan Chosun Univ Dept Informat & Commun Engn Gwangju 61452 South Korea Islamia Univ Bahalwapur Dept Comp Sci & IT Rahim Yar Khan Campus Punjab 64200 Pakistan

RNN based Deep learning models has shown tremendous success in sequential and temporal data where the order is critical to achieve higher accuracy in context understanding. RNN family like LSTM, BLSTM, GRU, BiGRU etc. are the mainly used models in these kind of sequential tasks. RNN family based encoder-decoder frameworks are widely used for the recognition of various languages scripts. However, in Urdu, very less research has been done especially with the deep learning models. The existing research work for printed Urdu recognition have shown that the current models only work for very basic sentences of Urdu but in case of complex words and sentences, these algorithms totally fail in terms of accuracy and the time complexity in identification of the Nastaleeq font writing. To identify printed Urdu text in images, we have proposed an encoder-decoder based hybrid deep learning approach with Convolutional Neural Network (CNN) for feature extraction part, bi-directional Gated Recurrent Unit network (BiGRU) as encoder and Gated Recurrent Unit network (GRU) as decoder. The CNN layer of the algorithm is used to obtain ligature features in Urdu, which are subsequently utilized by encoder (BiGRU) and decoder (GRU) to recognize the sentences by accurately distinguishing the characters and joiners. Experimental results have shown that our proposed CNN-BiGRU-GRU hybrid technique with specific hyper-parameter tuning performs well as compared to other state-of-the-art algorithms in terms of epochs (70 epochs as compared to 100 with BLSTM-LSTM based encoder decoder), 6 percent increase of Character Recognition Accuracy (86.95 percent as compared to 81.08 percent of BLSTM-LSTM), 10 percent increase of Word Recognition Accuracy (WRA) (89.48% as compared to 79.06 percent of BLSTM-LSTM) and less time complexity (18 seconds less than BLSTM-LSTM with same system configuration).

关键词： OCR Deep learning Sequence learning GRU BiGRU encoder-decoder model

来源：评论

学校读者我要写书评

暂无评论

ReFIGG: retinal fundus image generation using GAN

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL SCIENCE AND ENGINEERING 2023年第3期26卷 316-323页

作者： Nair, Sharika Sasidharan Meharban, M. S. Rajagiri Sch Engn & Technol Dept Comp Sci & Engn Ernakulam Kerala India

The effective training of deep architectures mainly depends on a large number of well-explained data. This is a problem in the medical field where it is hard and costly to gain such images. The tiny blood-vessels of the retina are the only part of the human structure that can be directly and non-intrusively foreseen within the living. Hence, it can be easily obtained and examined by automatic tools. Fundus imaging;a basic check-up process in ophthalmology provides essential data to make it easier for doctors to detect various eye-related diseases at prior phases. Fundus image generation is a challenging process to carry out by constructing composite models of the eye structure. In this paper, we overcome the issue of unavailability of medical fundus datasets by synthesising them artificially through an encoder-decoder generator model to the existing MCML method of generative adversarial networks (GAN) for easier, quicker, and early analysis.

关键词： fundus image generative adversarial networks GAN encoder-decoder model image synthesis deep learning

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：