检索结果-内蒙古大学图书馆

16th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2021

作者： Yang, Haotian Li, Min School of Information Engineering Nanchang Institute of Technology Jiangxi330099 China Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Jiangxi330099 China

ISBN: (纸本)9789811912528

The use of machine learning techniques to predict software defects has received extensive attention over the years. In practice, there are far fewer defective software samples than non-defective software samples, resulting in a high imbalance of sample categories. The problem of imbalanced data classification is a hotspot and difficulty in machine learning and data mining. In order to effectively solve the problem of software defect prediction, we introduce a classification model that combines SMOTE-Tomek sampling and ensemble learning algorithm XGBoost. Our initial experimental results on ten NASA software defect datasets indicate a clear superiority of the proposed techniques when compared to other hybrid model regarding various assessment metrics, such Accuracy, F-Measure, and AUC. © 2022, Springer Nature Singapore Pte Ltd.

关键词： NASA

来源：评论

学校读者我要写书评

暂无评论

Feature Selection Algorithm Based on Discernibility Matrix and Fruit Fly Optimization 16th

Feature Selection Algorithm Based on Discernibility Matrix a...

引用

16th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2021

作者： Ao, Jiaxin Ye, Jun Ji, Yuxuan Yang, Zhenyu College of Information Engineering Nanchang Institute of Technology Nanchang330000 China Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang330000 China

ISBN: (纸本)9789811912559

Feature selection methods that combine swarm intelligence optimization algorithms with rough sets have been widely used. Normally, this type of method can quickly search for feature subsets, effectively reducing the computational workload;However, in some decision tables of this type of method, there were also problems such as the searched feature subset containing redundant features, which led to a decrease in accuracy. Aiming at such problems in the current feature selection algorithms based on rough sets and fruit fly optimization, improvements have been made from two aspects. Firstly, a method for measuring the importance of discernibility matrix attributes was proposed and used as a heuristic factor to constructed a new fitness function;Secondly, guided by the fitness function, a fruit fly optimized feature selection method was designed, which can avoid redundant attributes in the feature subset. Examples and experimental results on the UCI datasets show that the new feature selection method can effectively search for the smallest feature subset and improve the stability. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Boosting Piezoelectric Output Performance of F@Bt/Pvdf Flexible Piezoelectric Nanogenerators Via Incorporation of Mxene

SSRN

引用

SSRN 2025年

作者： Wang, Shiwen Wu, Minghua Feng, Jie Feng, Mao Zheng, Zhirong Sun, Li Xu, Chenglong Textile college Zhejiang Fashion Institute of Technology Zhejiang Ningbo315211 China Ningbo Key Laboratory of Textile and Garment Intelligent Manufacturing Technology Textile college Zhejiang Fashion Institute of Technology Zhejiang Ningbo315211 China Key Laboratory of Advanced Textile Materials and Manufacturing Technology Ministry of Education College of Textile Science and Engineering Zhejiang Sci-Tech University Zhejiang Hangzhou310018 China Ningbo Runhe High-Tech Materials Co. Ltd. Zhejiang Ningbo315211 China

High output efficiency of wearable piezoelectric nanogenerators (PENG) can be achieved by improving the piezoelectric performance of composite nanofiber films. In this paper, a 2D conductive carbon material, MXene, was added to the F@BT/PVDF nanofiber-based film to obtain MXene/F@BT/PVDF PENG. MXene possess good electrical conductivity that can enhance the local electric field of F@BT/PVDF composite nanofiber film during the electrospinning process. This leads to higher polarization of the nanofiber films and enhanced piezoelectric properties of the MXene/F@BT/PVDF composite nanofiber film. The β phase content and the d33 value of the prepared MXene/F@BT/PVDF composite nanofiber film reached up to 95% and 48.7 ± 3 pc/N, respectively. In addition, the output voltage of the MXene/F@BT/PVDF PENG (MXene with 1.5 wt%) was measured to be 4.9 V, which was about 2 times higher than that of the F@BT/PVDF PENG. The study confirmed that the improvement was closely related to the content of MXene. Furthermore, the 2D MXene was compared with conductive carbon materials of other dimensions (0D carbon black and 1D CNTs), which revealed that the MXene/F@BT/PVDF PENG demonstrated the highest piezoelectric output performance. These results indicated that the addition of MXene improved the piezoelectric performance of the MXene/F@BT/PVDF PENG. Thus, a PENG exhibiting high piezoelectric output has been developed in this work through the synergistic enhancement effect of F@BT nanoparticles and 2D MXene. The findings of this study can prove to be extremely useful in various applications, such as wrist bending, respiratory vibration and knee, shoe at the stamp. © 2025, The Authors. All rights reserved.

关键词： Piezoelectricity

来源：评论

学校读者我要写书评

暂无评论

Electroactive Polypyrrole Bacterial Cellulose with Platelet Rich Plasma Composite Gel as Immunomodulatory Diabetes Wound Dressing

SSRN

引用

SSRN 2024年

作者： Wang, Hao He, Pengyu Tang, Guoliang Qi, Fuyu Lu, Xu Zhang, Maoxu Zheng, Ruizhu Li, Xiaohong Shi, Zhijun Yang, Guang Department of Biomedical Engineering College of Life Science and Technology Huazhong University of Science and Technology Wuhan430074 China State Key Laboratory of New Textile Materials and Advanced Processing Technologies Wuhan Textile University Wuhan430200 China

Diabetic ulcer is a common and severe chronic wound condition that presents significant challenges for healthcare. In this regard, Numerous therapeutic interventions have been investigated, with platelet-rich plasma (PRP) emerging as a promising option. However, PRP has inherent limitations, such as its susceptibility to rupture, and uncontrolled release of growth factors, necessitate alternative approaches. This study proposes an innovative design that combines polypyrrole-wrapped bacterial cellulose (PPy-BC) hydrogel with PRP to obtain the PPy-BC/ PRP (PBP) composite hydrogel with both electrical and biological activity. The PBP composite hydrogel exhibits favorable mechanical properties and conductivity, enabling precise regulation of PRP release and the immune microenvironment of diabetic wounds via electrical stimulation. The PBP composite hydrogel effectively promotes macrophage anti-inflammatory (M2) polarization, inhibits pro-inflammatory (M1) polarization, and reduces the expression of inflammatory cytokines, thereby reducing the wound hyperinflammation. In addition, diabetic wounds treated with PBP composite hydrogel show accelerated revascularization, collagen deposition, and overall acceleration of wound healing. Collectively, these demonstrate the promising potential of PBP composite hydrogel for treating diabetic wounds in clinic. © 2024, The Authors. All rights reserved.

关键词： Platelets

来源：评论

学校读者我要写书评

暂无评论

An Improved Method for Long-term Drift Compensation of Electronic Nose with Batch Control 12

An Improved Method for Long-term Drift Compensation of Elect...

引用

12th IEEE International Conference on Electronics Information and Emergency Communication, ICEIEC 2022

作者： Cui, Hao Dong, Xiaorui Shang, Kai Shandong Institute of Petroleum and Chemical Technology Key Laboratory of Intelligent Information Processing Shandong Province Dongying China College of Computer Science and Technology China University of Petroleum Shandong Province Qingdao China

ISBN: (数字)9781665407540

ISBN: (纸本)9781665407540

Sensor long-time drift compensation has always been a huge and important research challenge. To address this problem, this paper proposes a simple and efficient long-time drift compensation method based on a short-time memory-forgetting mechanism. The proposed improved method controls the update frequency of memory and forgetting by introducing a batch control coefficient to achieve a balance between the update frequency of memory queue and model iteration. In this paper, we use the gas sensor array drift dataset as the research object and design two experimental strategies to verify the processing time compression degree and the accuracy change of the classification model by adjusting the batch control coefficient. The experiments prove that the proposed method in this paper has an excellent effect on compressing data processing time and relieving hardware pressure, which has a certain reference value for related research. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Tolerance Classes Partition-Based Re-Definition of the Rough Approximations for Incomplete Information System

A Tolerance Classes Partition-Based Re-Definition of the Rou...

引用

International Conference on Image, Vision and intelligent Systems, ICIVIS 2021

作者： Wang, Lei Liu, Bin Cai, Xiangxiang Wang, Chong Jiangxi Provincial Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang330099 China College of Information Engineering Nanchang Institute of Technology Nanchang330099 China

ISBN: (纸本)9789811669620

The information with missing attribute value is known as the incomplete information system. In an incomplete information system, there exist tolerance relations satisfying reflexivity and symmetry among objects in the universe of discourse and the tolerance classes for each object can be derived from the tolerance relation directly. Generally speaking, the tolerance classes of all objects can form some coverages of the universe. The research of this paper is based on the tolerance classes of each object in the incomplete information system. Firstly, a method is proposed in which a partition of the universe is constructed by using tolerance classes of objects. Then, the upper and lower approximations of concept, i.e., a subset of universe, is re-defined on the basis of acquisition of the partition of the universe using proposed method and this new definition can improve the approximation accuracy of concept effectively compared to the traditional definition. Finally, an illustrated example is exhibited for demonstrating the method to obtain a partition to universe by tolerance class as well as the calculation of the rough approximations of concept based on the partition of universe by tolerance class. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Information use

来源：评论

学校读者我要写书评

暂无评论

Imagine Before Go: Self-Supervised Generative Map for Object Goal Navigation

Imagine Before Go: Self-Supervised Generative Map for Object...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Sixian Zhang Xinyao Yu Xinhang Song Xiaohan Wang Shuqiang Jiang Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing University of Chinese Academy of Sciences Beijing Institute of Intelligent Computing Technology Suzhou CAS

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

The Object Goal navigation (ObjectNav) task requires the agent to navigate to a specified target in an unseen environment. Since the environment layout is unknown, the agent needs to infer the unknown contextual objects from partially observations, thereby deducing the likely location of the target. Previous end-to-end RL methods capture contextual relationships through implicit representations while they lack notion of geometry. Alternatively, modular methods construct local maps for recording the observed geometric structure of unseen environment, however, lacking the reasoning of contextual relation limits the exploration efficiency. In this work, we propose the self-supervised generative map (SGM), a modular method that learns the explicit context relation via self-supervised learning. The SGM is trained to leverage both episodic observations and general knowledge to reconstruct the masked pixels of a cropped global map. During navigation, the agent maintains an incomplete local semantic map, meanwhile, the unknown regions of the local map are generated by the pretrained SGM. Based on the generated map, the agent sets the predicted location of the target as the goal and moves towards it. Experiments on Gibson, MP3D and HM3D show the effectiveness of our method. The code is available at https://***/sx-zhang/SGM.

关键词： Training Geometry Navigation Large language models Semantics Layout Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A new model based on differential evolutionary algorithm and Markov clustering for identifying protein complexes

A new model based on differential evolutionary algorithm and...

引用

第42届中国控制会议

作者： Zengyu Feng Shouheng Tuo Tianrui Chen School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an Key Laboratory of Big Data and Intelligent Computing

As the material basis for all life activities, proteins play a crucial role in performing life activities. Most real-life proteins perform various functions in the form of protein complexes, so it is essential for understanding of life activities to accurately identify protein complexes. Most of the existing approaches learn protein interactions directly from protein topology,ignoring the biological characteristics of the actual proteins. Nevertheless, actual protein complexes are usually composed of protein cores and protein attachments. In this study, a new MP-DE algorithm is designed from the core-attachment structure to generate protein complex cores using Markov clustering, while searching for attached proteins in the second-order neighborhood of core protein complexes based on differential evolution(DE) algorithm. The experimental results show that the proposed method has high detection accuracy and efficiency on the current mainstream protein-protein interaction(PPI) database.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scale-free distributed control for the DC MG cluster under DoS attacks: An asynchronous switched strategy

引用

Automatica 2025年 179卷

作者： Cheng, Fabin Lai, Jingang School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Huazhong University of Science and Technology Wuhan430074 China

This paper studies the voltage restoration problem of the DC Microgrid (MG) cluster with a two-layer communication structure under Denial-of-Service (DoS) attacks. Based on the open multiagent framework, an asynchronous switching strategy is designed to suppress the impact of DoS attacks on the entire MG cluster's voltage restoration. Meanwhile, we derived the relationship between attack model parameters and communication link switching mode selection through the general model of DoS attacks and asynchronous switching methods based on average dwell time. Moreover, the designed distributed control protocol is scale-free;that is, it does not rely on any information from the two-layer communication structure and the number of distributed generations (DGs), which makes it universal. Through rigorous theoretical proof, it has been proven that in the DC MG cluster with two-layer communication structures, voltage restoration can be achieved regardless of the number and structure of DGs being attacked. Finally, two simulation examples on the MATLAB/SimPowerSystem, including a DC MG cluster consisting of 8 DGs and an IEEE 33-node system are used to investigate the scalability and flexibility of the proposed distributed control algorithm. © 2025 Elsevier Ltd

关键词： Asynchronous switched strategy DC MG cluster Distributed control DoS attack Scale-free

来源：评论

学校读者我要写书评

暂无评论

Removing Scattered Light in Biomedical Images

Removing Scattered Light in Biomedical Images

引用

IEEE International Symposium on Biomedical Imaging

作者： Yuanhao Gong Wanlin Huang Wenhui Wu Shenzhen University China Guangdong Key Laboratory of Intelligent Information Processing China Reexen Technology Ltd.

Scattered light is a common issue in various biomedical images such as fluorescence and X-ray images, leading to a hazy view of the imaging objects and thus degrading the image quality. To tackle this issue, this paper proposes a novel mathematical model to remove such scattered light. Our model is guaranteed to produce an image with better image contrast than the input. We also present a Local Guided Total Variation filter to solve this model. The proposed filter has linear computation complexity with respect to the total number of pixels, resulting in a high computational performance. Extensive experiments have been conducted to confirm the effectiveness of the proposed model and efficiency of the presented filter. Our method can be applied to a wide range of images to remove their scattered light. The open-source code is publicly available at http://***.

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：