检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Ding, Mengqian Liu, Jun Luo, Yang Wuhan University of Science and Technology School of Computer Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China

ISBN: (纸本)9798350386226

The relatively simple genome, short life cycle, and easy observation of Caenorhabditis elegans (C. elegans) make it an excellent model organism for aging research. Age-stage prediction of C. elegans can help to assess the effectiveness of anti-aging interventions, better explore the role of individual differences in the aging process, and thus promote the development of medicine. However, there are still some problems in accurately predicting the age stages of C. elegans. On the one hand, there may be individual differences among C. elegans due to natural variation and environmental factors. On the other hand, nematode data sets are scarce and image information is complex. In this paper, we perform the age prediction task by studying the body contour morphology, biomarkers, and internal organ changes of C. elegans. Specifically, to address the effects of individual differences and datasets, this paper combines the body contour features, protein aggregation features, and pharyngeal terminal bulb features of C. elegans. In addition, considering the complex information of C. elegans images, this paper proposes a hybrid CNN and Transformer feature extraction method (DFCT), which can fully extract the global and local features of the image. A Dual Path Adaptive Feature Fusion Module (DAFM) is used to fuse the features. A series of experiments are conducted to verify the effectiveness of the proposed method. The experimental results show that the method proposed in this paper outperforms other methods in terms of accuracy and precision, especially in dividing 25 age stages into 3 categories, with an accuracy of 85.93%. © 2024 IEEE.

关键词： age estimation biological image analysis Caenorhabditis elegans CNN and Transformer image classification

来源：评论

学校读者我要写书评

暂无评论

DHCT-DT: Dual-branch Hybrid CNN-Transformer Combined with Dual-Teacher Semi-Supervised Network for Kidney Ultrasound Image Segmentation

DHCT-DT: Dual-branch Hybrid CNN-Transformer Combined with Du...

引用

2024 IEEE International Conference on systems, Man, and Cybernetics, SMC 2024

作者： Luo, Yang Liu, Jun Ding, Mengqian School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China

ISBN: (纸本)9781665410205

Accurate segmentation of kidney ultrasound (KUS) images is of great significance for the diagnosis of kidney diseases. However, KUS images have challenges such as low contrast, large size variations, and acoustic shadow interference. In addition, obtaining labeled data is a major challenge in the field of medical image segmentation. This paper proposes a dual-branch hybrid CNN Transformer combined with a dual teacher semi-supervised segmentation network (DHCT-DT) based on the MT model. The reliability of guidance can be improved between two teachers by constructing consistency regularization constraints. The U-Net architecture is employed between the main teacher and student model. The auxiliary teacher model adopts a dual-branch hybrid CNN Transformer architecture. The multi-scale channel fusion attention mechanism (MSCF) is introduced to capture the feature correlation information of KUS images at different scales and channels. Two different training methods can combine their advantages to fully extract local and global information from images. To demonstrate the applicability of the proposed method, experiments were conducted on two datasets: a KUS dataset and a breast ultrasound (BUS) dataset. Both datasets demonstrated the most competitive segmentation performance. For example, in a semi-supervised experiment using only 10% labeled data in the BUS dataset, the Dice coefficient, Jaccard coefficient, HD, and ASSD reached 82.28%, 76,36%, 13.36mm, and 3.71mm. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Improved Joint Distribution Adaptation for Fault Diagnosis 8th

Improved Joint Distribution Adaptation for Fault Diagnosis

引用

8th International Conference on Data Mining and Big Data, DMBD 2023

作者： Gao, Dali Mao, Xiaobin Sheng, Long Wang, Shuangling Science and Technology on Information System Engineering Laboratory Nanjing210023 China

ISBN: (纸本)9789819708369

In the blast furnace (BF) ironmaking process, it is difficult to obtain labeled fault samples and the probability distribution drifts significantly. Therefore, transfer learning has been introduced to fault diagnosis of BF. Most of the existing transfer learning methods achieve domain adaptation by reducing the marginal and conditional distribution discrepancies, without considering the prior distribution. To address this issue, this paper provides a theoretical derivation of the effect of the prior distribution discrepancies on knowledge transfer, and proposes a new method called Improved Joint Distribution Adaptation (IJDA). The model performs reconstruction of the weighted source data to offset the discrepancies of prior distribution, and extracts domain-invariant features by aligning joint distribution to achieve knowledge transfer. In the transfer BF fault diagnosis experiments, the proposed method achieves promising performance improvement. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Fast mode decomposition for few-mode fiber based on lightweight neural network

引用

Chinese Optics Letters 2024年第2期22卷 88-95页

作者：赵佳佳陈国辉毕轩蔡汪洋岳磊唐明 School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha 410114China Wuhan National Laboratory for Optoelectronics(WNLO)and National Engineering Laboratory for Next Generation Internet Access System School of Optical and Electronic InformationHuazhong University of Science and TechnologyWuhan 430074China

In this paper,we present a fast mode decomposition method for few-mode fibers,utilizing a lightweight neural network called *** method can quickly and accurately predict the amplitude and phase information of different modes,enabling us to fully characterize the optical field without the need for expensive experimental *** train the MobileNetV3-Light using simulated near-field optical field maps,and evaluate its performance using both simulated and reconstructed near-field optical field *** validate the effectiveness of this method,we conduct mode decomposition experiments on a few-mode fiber supporting six linear polarization(LP)modes(LP01,LP11e,LP11o,LP21e,LP21o,LP02).The results demonstrate a remarkable average correlation of 0.9995 between our simulated and reconstructed near-field lightfield *** the mode decomposition speed is about 6 ms per frame,indicating its powerful real-time processing *** addition,the proposed network model is compact,with a size of only 6.5 MB,making it well suited for deployment on portable mobile devices.

关键词： deep learning lightweight neural network few-mode fiber mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Passive on-chip isolators based on the thin-film lithium niobate platform

引用

Chinese Physics B 2025年第3期34卷 408-413页

作者： Jiacheng Liu Gongyu Xia Qilin Hong Pingyu Zhu Kai-Kai Zhang Keyu Xia Ping Xu Shiqiao Qin Zhihong Zhu College of Advanced Interdisciplinary Studies&Hunan Provincial Key Laboratory of Novel Nano Optoelectronic Information Materials and Devices National University of Defense TechnologyChangsha 410073China Institute for Quantum Information and State Key Laboratory of High-Performance Computing College of Computer Science and TechnologyNational University of Defense TechnologyChangsha 410073China College of Engineering and Applied Sciences National Laboratory of Solid State Microstructuresand Collaborative Innovation Center of Advanced MicrostructuresNanjing UniversityNanjing 210023China

Optical isolators,the photonic analogs of electronic diodes,are essential for ensuring the unidirectional flow of light in optical systems,thereby mitigating the destabilizing effects of back ***-film lithium niobate(TFLN),hailed as“the silicon of photonics,”has emerged as a pivotal material in the realm of chip-scale nonlinear optics,propelling the demand for compact optical *** report a breakthrough in the development of a fully passive,integrated optical isolator on the TFLN platform,leveraging the Kerr effect to achieve an impressive 10.3 dB of isolation with a minimal insertion loss of 1.87 *** theoretical simulations have demonstrated that our design,when applied to a microring resonator with a Q factor of 5×10^(6),can achieve 20 dB of isolation with an input power of merely 8 *** advancement underscores the immense potential of lithium niobate-based Kerr-effect isolators in propelling the integration and application of high-performance on-chip lasers,heralding a new era in integrated photonics.

关键词： thin-film lithium niobate Kerr effect optical isolator

来源：评论

学校读者我要写书评

暂无评论

Enhancing Network Design through Statistical Evaluation of MANET Routing Protocols

引用

Computers, Materials & Continua 2024年第7期80卷 319-339页

作者： Ibrahim Alameri Tawfik Al-Hadhrami Anjum Nazir Abdulsamad Ebrahim Yahya Atef Gharbi Faculty of Medical Sciences Jabir ibn Hayyan Medical UniversityAlkufa QuNajaf54001Iraq Computer Science Department School of Science and TechnologyNottingham Trent UniversityNottinghamNG118NSUK Department of Computing Faculty of Engineering Sciences&Technology(FEST)Hamdard UniversityKarachi74600Pakistan Department of Information Technology College of Computing and Information TechnologyNorthern Border UniversityArar91431Saudi Arabia Department of Information System College of Computing and Information TechnologyNorthern Border UniversityArar91431Saudi Arabia

This paper contributes a sophisticated statistical method for the assessment of performance in routing protocols salient Mobile Ad Hoc Network(MANET)routing protocols:Destination Sequenced Distance Vector(DSDV),Ad hoc On-Demand Distance Vector(AODV),Dynamic Source Routing(DSR),and Zone Routing Protocol(ZRP).In this paper,the evaluation will be carried out using complete sets of statistical tests such as Kruskal-Wallis,Mann-Whitney,and *** articulates a systematic evaluation of how the performance of the previous protocols varies with the number of nodes and the mobility *** study is premised upon the Quality of Service(QoS)metrics of throughput,packet delivery ratio,and end-to-end delay to gain an adequate understanding of the operational efficiency of each protocol under different network *** findings explained significant differences in the performance of different routing protocols;as a result,decisions for the selection and optimization of routing protocols can be taken effectively according to different network *** paper is a step forward in the general understanding of the routing dynamics of MANETs and contributes significantly to the strategic deployment of robust and efficient network infrastructures.

关键词： Routing protocols statistical approach friedman MANET

来源：评论

学校读者我要写书评

暂无评论

Comparison of Machine Learning Methods for Air Quality Prediction Based on Particulate Matter (PM2.5)

Comparison of Machine Learning Methods for Air Quality Predi...

引用

2025 International Conference on Advancement in Data science, E-learning and information system, ICADEIS 2025

作者： Mar'i, Farhanna Marianingsih, Susi Abdillah, Rifqi Elfaiz, Ersha Aisyah Setyo Prayoga, Riza Akhsani Fahmi, Muhamad Universitas Negeri Surabaya Faculty of Engineering Department of Informatics Engineering Surabaya Indonesia Jayapura University of Science and Technology Department of Information System Jayapura Indonesia Universitas Negeri Surabaya Faculty of Engineering Department of Information Technology Education Surabaya Indonesia Universitas Airlangga Faculty of Science and Technology Department of Biomedical Engineering Surabaya Indonesia

ISBN: (纸本)9798331513320

Particulate PM2.5 has a major effect on human health compared to other types of pollutants such as NO2, 03, CO, and SO2. PM2.5 is the worst type of major pollutant for human health that can cause various types of serious diseases and even death. PM2.5 is defined as an ambient air particle, which is one of the particle elements found in the free air of the earth's surface in the troposphere layer, which is very small in size, reaching 2.5 pollutants. The method of predicting air quality index values can be done using machine learning techniques with time series data analysis. This study will compare machine learning methods with two approaches, namely statistical regression with RF and ARIMA and deep learning method, namely LSTM. Based on the research results, the best machine learning method approach is statistical regression, namely the RF method with accuracy evaluation using RMSE, MAE, and MSE, which are respectively with a minimum value of 0.162, 0.108, and 0.026, followed by the LSTM and ARIMA methods. © 2025 IEEE.

关键词： Polycyclic aromatic hydrocarbons

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Mortality Prediction of COVID-19 Patients with Cardiovascular Disease 9

Deep Learning-based Mortality Prediction of COVID-19 Patient...

引用

9th IEEE International Conference on Data science in Cyberspace, DSC 2024

作者： Zheng, Huilin Liang, Yingyi Zhang, Daming Shi, Kai Dong, Luxi Xie, Xiaolan Guilin University of Technology Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin University of Technology College of Computer Science and Engineering Guilin China

ISBN: (纸本)9798350391367

Coronavirus disease 2019 (COVID-19) is one of the most dangerous diseases in recorded human history due to its high contagiousness and rapid dissemination. Moreover, people who already have medical issues like cardiovascular disease (CVD) have a higher risk of getting seriously ill. Therefore, this study proposes a deep learning-based prediction model for the mortality of COVID-19 patients with CVD. The research substances are introduced as follows. First, we obtain the original dataset from the Kaggle website provided by the Mexican government, and extract our experimental data. After that, we develop a deep learning-based prediction model for the mortality of COVID-19 patients with CVD while applying a 5-fold cross-validation approach for the model training and validation. Finally, we evaluate the performance of the proposed model and also compare it with many common machine learning models. In our experimental results, the proposed model achieved higher performance than all of the other models. It facilitates decision-making and provides an accurate mortality prediction for COVID-19 patients with CVD. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Improvement in hydrogen storage performance of MgH_(2) by vanadium doped with ZIF-8 derived a single-atom catalyst V-N-C

引用

Rare Metals 2024年第6期43卷 2623-2635页

作者： Fei-Fan Hong Wei-Tao Shi Ruo-Lin Zhao Yi Fan Zi-Qi Liu Si-Zhi Ding Hai-Zhen Liu Wen-Zheng Zhou Jin Guo Zhi-Qiang Lan Guangxi Novel Battery Materials Research Center of Engineering Technology and Center on Nanoenergy Research Guangxi Colleges and Universities Key Laboratory of Blue Energy and Systems IntegrationCarbon Peak and Neutrality Science and Technology Development InstituteSchool of Physical Science and TechnologyGuangxi UniversityNanning 530004China Nanning Engineering Technology Research Center for Power Transmission System of New Energy Vehicle Transportation CollegeNanning UniversityNanning 530200China

Herein,the successful preparation of a singleatom catalyst V-N-C using vanadium-doped zeolitic imidazolate framework(ZIF)-8 as a precursor is *** experimental results showed that the V-N-C had a good promoting effect on the hydrogen storage performance of MgH_(2),and the optimal addition amount of V-N-C was 10wt%.The hydrogenation and dehydrogenation apparent activation energies of 10 wt%V-N-C-catalyzed MgH_(2)were reduced by 44.9 and 53.5 kJ·mol^(-1),respectively,compared to those of additive-free MgH_(2).The 10 wt%V-N-C-catalyzed MgH_(2)could reabsorb 5.92 wt%of hydrogen in 50 min at 150℃,with a capacity retention rate of 99.1%after 30 cycles of hydrogen absorption and *** analysis showed that V-N-C was partially transformed into VN and metallic V when it was milled with MgH_(2);the in-situ-formed VN and metallic V played an important role in improving the hydrogen storage performance of MgH_(2).This approach provides a potential solution for obtaining high-performance Mg-based hydrogen storage materials through synergistic interactions between V,N and C.

关键词： MgH_(2) Hydrogen storage materials Catalyst Hydrogen storage perormance

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Covert Communication

引用

China Communications 2024年第9期21卷 40-59页

作者： Shen Weiguo Chen Jiepeng Zheng Shilian Zhang Luxin Pei Zhangbin Lu Weidang Yang Xiaoniu Innovation Studio of Academician Yang National Key Laboratory of Electromagnetic Space SecurityJiaxing 314033China College of Information Engineering Zhejiang University of TechnologyHangzhou 310023China School of Information Science and Technology Fudan UniversityShanghai 200438China

In recent years,deep learning has been gradually used in communication physical layer receivers and has achieved excellent *** this paper,we employ deep learning to establish covert communication systems,enabling the transmission of signals through high-power signals present in the prevailing environment while maintaining covertness,and propose a convolutional neural network(CNN)based model for covert communication receivers,namely Deep *** model leverages CNN to execute the signal separation and recovery tasks commonly performed by traditional *** enables the direct recovery of covert information from the received *** simulation results show that the proposed Deep CCR exhibits significant advantages in bit error rate(BER)compared to traditional receivers in the face of noise and multipath *** verify the covert performance of the covert method proposed in this paper using the maximum-minimum eigenvalue ratio-based method and the frequency domain entropy-based *** results indicate that this method has excellent covert *** also evaluate the mutual influence between covert signals and opportunity signals,indicating that using opportunity signals as cover can cause certain performance losses to covert *** the interference-tosignal power ratio(ISR)is large,the impact of covert signals on opportunity signals is minimal.

关键词： convolutional neural network covert communication 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：