检索结果-内蒙古大学图书馆

Soliton Molecule and Breather-Soliton Molecule Structures for a General Sixth-Order Nonlinear Equation

Chinese Physics Letters 2021年第8期38卷 1-6页

作者： Kai-Hua Yin Xue-Ping Cheng Ji Lin School of Mathematics Physics and Information ScienceZhejiang Ocean UniversityZhoushan 316022China Key Laboratory of Oceanographic Big Data Mining&Application of Zhejiang Province Zhoushan 316022China Institute of Nonlinear Physics Zhejiang Normal UniversityJinhua 321004China

Starting from a general sixth-order nonlinear wave equation,we present its multiple kink solutions,which are related to the famous Hirota *** also investigate the restrictions on the coefficients of this wave equation for possessing multiple kink *** introducing the velocity resonance mechanism to the multiple kink solutions,we obtain the soliton molecule solution and the breather-soliton molecule solution of the sixth-order nonlinear wave equation with particular *** three-dimensional image and the density map of these soliton molecule solutions with certain choices of the involved free parameters are well *** matching the parametric restrictions of the sixth-order nonlinear wave equation for having three-kink solution with the coefficients of the integrable bidirectional Sawada-Kotera-Caudrey-Dodd-Gibbons(SKCDG)equation,the breather-soliton molecule solution for the bidirectional SKCDG equation is also illustrated.

关键词： soliton equation nonlinear

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Martime 5G Communication System Based on Software Defined Radio and Open Air Interface

Design and Implementation of Martime 5G Communication System...

引用

IEEE International Conference on Unmanned Systems (ICUS)

作者： Yushuo Wang Kun Yang Jianjun Ding Xuyang Chen Qiang Li Tong Peng Key Laboratory of Oceanographic Big Data Mining & Application Zhejiang Ocean University Zhoushan China

This article proposes an innovative maritime 5G communication system based on Software Defined Radio (SDR) and OpenAirInterface (OAI),which shows advantages of high scalability and low cost. By implementing with recent research on OAI-based software base station technology, we established a core network, 5G software base station (gNB), user terminal (UE), and uplink/downlink systems to test the stability and transmission rate of the entire platform based on the testing software such as Iperf. We obtained the communication performance indicators of the equipment in marine environments and compared them with the test results in terrestrial environments, which fills the gap in the accessible test solution for 5G communication systems in marine environments. The results show that the proposed test solution can be used for reliable and accurate performance eveluation of 5G communication systems in marine environments with the feature of easy-implmentation and easy-scalability. Future research can be exploited by increasing the complexity and diversity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ship Early Warning System Based on Nine Axis Sensors

Ship Early Warning System Based on Nine Axis Sensors

引用

Electrical Engineering and Automation (IFEEA), International Forum on

作者： Jianjun Ding Kun Yang Yupeng Liu Jinglong Lin Key Laboratory of Oceanographic Big Data Mining & Application Zhejiang Ocean University Zhoushan China

In view of the various dangerous situations that ships may face the sea, such as sea wind, waves, and ocean currents, which can cause problems such as tilting, ascending and descending, and swaying of the ship’s body, this paper proposes a ship attitude recognition method based on the MPU9250 nine-axis sensor. The method aims to achieve real-time and accurate monitoring and warning of ship movements, with technical advantages such as instant response, continuous monitoring, and low energy consumption. The system utilizes wireless communication technology for terminal data uploading and interaction, and employs 2G/3G/4G/5G technology for remote data transmission and warning functionality, enabling real-time data transmission and remote warning capabilities. Additionally, a machine learning-based algorithm is designed to analyze sensor datas. Experimental results demonstrate that the system can accurately monitor ship attitude changes and abnormal movements, and issue timely warning signals, which are of significant importance for ship safety and operational efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LoRa Path-Loss Model and Verification for Maritime Environment

LoRa Path-Loss Model and Verification for Maritime Environme...

引用

IEEE International Conference on Unmanned Systems (ICUS)

作者： Hao Zeng Kun Yang Jianming Wu Jianjun Ding Chengyuan Wen Xin Li Key Laboratory of Oceanographic Big Data Mining & Application Zhejiang Ocean University Zhoushan China

Maritime communication faces the influence of many irresistible factors such as air pressure and waves, which leads to the degradation of the efficiency and quality of maritime communication, and increases the difficulty of channel modeling. In this paper, we conducted LoRa data testing, analyzed and simulated a LoRa path loss model for maritime environment, focusing on the influence of antenna height, sea surface roughness and other channel model parameters. According to the simulation results, it is concluded that changing the standard deviation of surface height distribution and the mean-square surface slope affects the influence of the reflection path on the large-scale fading. In addition, by appropriately increasing the antenna height on board, the communication coverage can be extended accordingly.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Attribute Reduction of Object Granules of Concept Lattice Based on Three-Way Decision

Attribute Reduction of Object Granules of Concept Lattice Ba...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Tong-Jun Li Run-Ze Zhang School of Information Engineering Zhejiang Ocean University Zhoushan Zhejiang China Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province China

Formal concept analysis is a key tool in data analysis and knowledge representation and a specific method for granular computing. Object granules constitute the basic granular knowledge in a concept lattice. Three-way decision is a reasonable approach to extracting decision rules. This study employs the principle of three-way decision to divide all the object granules of a formal context into three parts: positive, negative and boundary regions, then two groups of certainty decision rules are extracted from the positive region and the negative region, and one group of possibility decision rules is induced from the boundary region. The notion of attribute reduction keeping the performance of the decision rules unchanged are proposed. An approach for computing attribute reducts is put forward by utilizing the discernibility matrix and discernibility function. Some examples are taken to explain or show the relevant conclusions and prove the feasibility of the reduction method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Underwater image enhancement based on improved adaptive MSRCR and Gamma function

Underwater image enhancement based on improved adaptive MSRC...

引用

Cloud Computing, big data applications and Software Engineering (CBASE), International Conference on

作者： Lin Zhang Tong Peng School of Information Engineering Zhejiang Ocean University Zhoushan China Key Laboratory of Oceanographic Big Data Mining and Application of Zhejiang Province Zhoushan China

In order to solve the problem that light is absorbed by different scales and scattered by particles in water, resulting in overall color deviation, low contrast and unclear details of the image, an underwater image enhancement algorithm based on improved adaptive MSRCR(Multi-Scale Retinex with Color Restoration) and two-dimensional gamma function based on details is proposed. Firstly, the weight of the convolution function in different scales is redistributed according to the image gradient information as the selection factor, and then the guided filter and gaussian filter are used as the adaptive MSRCR surround function and linear fusion to solve the problems of color decay and insufficient sharpness. Finally, the improved two-dimensional gamma function with CLAHE(Contrast Limited Adaptive Histogram Equalization) algorithm is used to correct the image contrast after fusion. The experimental results show that the enhanced image processed by this method has good enhancement effect in underwater image elimination of color distortion, image detail enhancement and obtaining real and natural restored image, and has obvious advantages over other contrast algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-Label Classification Algorithm Based on Self-paced Learning and LDA

A Multi-Label Classification Algorithm Based on Self-paced L...

引用

6th International Conference on Intelligent Computing and Signal Processing (ICSP)

作者： Qiangqiang Wang Shenming Gu School of Information Engineering Zhejiang Ocean University Zhoushan China Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhoushan China

To address the problem that existing multi-label learning algorithms treat all samples equally during model training and ignore inter-sample variability, this paper proposes a multi-label classification algorithm based on self-paced learning and LDA (SPLDA for short). SPLDA first constructs an adaptive self-paced function based on the label prediction loss values in multi-label data, and introduces a self-paced learning framework. Secondly, the linear discriminant analysis regularization term in the low-dimensional space of the samples is constructed by combining the principles of minimizing the within-class distance and maximizing the between-class distance in this framework. Next, a multi-label classification model is trained using alternating optimization methods. Finally, the experimental results on 5 real datasets and 3 evaluation metrics show that SPLDA outperforms the existing multi-label classification algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Image Enhancement of Rural Orchard Security Monitoring under Low Illumination 22

Research on Image Enhancement of Rural Orchard Security Moni...

引用

Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering

作者： Zili Zhou Shenming Gu School of Information Engineering Zhejiang Ocean University China Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhejiang Ocean University China

ISBN: (纸本)9781450397148

It is great significance to improve the quality of the monitoring image for the low illumination situation and to improve the security of the rural orchard. In this paper, an improved block homomorphic filtering algorithm is proposed to improve the quality of video surveillance image due to low illuminance in real environment. On the basis of image block adaptation and according to different illumination conditions, the filtering effect is improved by adding and adjusting the weight factor of the transfer function, and the blocking edge effect is alleviated by smoothing filtering. In order to solve the problem of low saturation of low illumination image, the image saturation is adjusted hierarchically and the saturation lower than the threshold value is nonlinear pulled up, so as to restore the color saturation of the image as much as possible. The experimental results show that the PSNR, SSIM and IE are improved by 6%, 21% and 4% respectively. Ultimately, it can improve effectively the image quality of orchard video monitoring under low illumination.

关键词： Rural orchard, Improved block homomorphic filtering, Saturation stratification adjustment Monitoring image, Low illumination

来源：评论

学校读者我要写书评

暂无评论

Fine-grained classification network for fish based on the attention mechanism and EfficientNet 22

Fine-grained classification network for fish based on the at...

引用

Proceedings of the 2022 4th International Conference on Robotics, Intelligent Control and Artificial Intelligence

作者： Yaohan Gong Shenming Gu Linting Guan School of Information Engineering Zhejiang Ocean University China Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhejiang Ocean University China

ISBN: (纸本)9781450398343

Many countries have been interested in the sustainable development of marine resources. Countries can protect the sustainable development of fishery resources by joining international fisheries organizations such as CCSBT, IATTC, IOTC, ICCAT, and others, and by adhering to the Code of Conduct for Responsible Fisheries. Traditional fishing supervision methods, on the other hand, frequently have the issue that the amount of original data is cumbersome and expensive, which cannot be handled manually and wastes a lot of manpower. This paper investigates fine-grained fish classification methods based on deep learning and attention mechanisms and proposes one that can target complex background and actual working scenarios, allowing countries to reallocate human capital to management and law enforcement activities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Super-resolution adversarial generative fish classification based on Swin-Transformer 22

Super-resolution adversarial generative fish classification ...

引用

Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering

ISBN: (纸本)9781450397148

The development of fish detection and identification technology is crucial in fishery production. Due to the large intra-class difference and high inter-class similarity, fish classification tasks are considered to be fine-grained. In addition, the acquisition of fish images is often affected by lumps, angles, complex backgrounds, weather, and other factors, which makes the classification task difficult. We present a fish classification method that combines super-resolution reconstruction, multi-scale feature information, and self-attention to improve image quality and classification. Through super-resolution reconstruction and data augmentation, image quality can be improved. A feature extraction network based on Swin-Transformer is used to extract the image's multi-scale feature information and self-attention. The method was evaluated using the Nature Conservancy's publicly available fisheries monitoring dataset. The results of the experiments reveal that the approach may significantly increase image quality while completing the fish classification. At the same time, we compared our results to those of other approaches.

关键词：

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：