检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Electrical, Computer and Energy Technologies, ICECET 2023

作者： Kaligambe, Abraham Nakagawa, Kota Fujita, Goro Graduate School of Engineering and Science Shibaura Institute of Technology Power System Laboratory Tokyo Japan Shibaura Institute of Technology Power System Laboratory Department of Electrical Engineering Tokyo Japan

ISBN: (纸本)9798350327816

As the adoption of renewable energy surges, the global proliferation of solar photovoltaic (PV) systems intensifies. However, PV panels remain vulnerable to defects during transportation, installation, and harsh weather exposures, compromising their longevity and efficiency. Traditional visual and I-V curve tests, frequently employed for PV system maintenance, often fall short due to their restricted defective detection capacity, and extended inspection durations. While infrared (IR) and electroluminescence (EL) imaging methods excel in efficiency, their accompanying equipment is prohibitively expensive. Addressing this gap, the paper introduces a novel, cost-effective EL imaging solution using a modified consumer camera. The findings highlight the efficacy of EL imaging in detecting an array of solar cell defects, underscored by the affordability of the setup. The accessible and cost-friendly nature of the EL methodology offers a promising inspection alternative for small to medium-sized PV systems, marking a significant stride in PV inspection innovations. © 2023 IEEE.

关键词： electroluminescence imaging inspection photovoltaic solar defects

来源：评论

学校读者我要写书评

暂无评论

RESEARCH ON THE IMPACT OF ACTIVATION FUNCTIONS ON NEURAL NETWORK MODELS FOR PREDICTING VIBRATION RESPONSES

RESEARCH ON THE IMPACT OF ACTIVATION FUNCTIONS ON NEURAL NET...

引用

2024 CSAA/IET International Conference on Aircraft Utility systems, AUS 2024

作者： Yang, Hongji Xia, Tianxiang Wu, Ke AVIC Nanjing Engineering Institute of Aircraft System Nanjing China Aviation Science and Technology Key Laboratory of Aviation Mechanical and Electrical System Nanjing China

In the research of mechanical environments for aerospace electromechanical systems, the computational method for vibration response is crucial as it affects various aspects of product structure and systems design. In recent years, the intersection between vibration response and deep learning has been a hot research area, yet many challenges remain to be addressed. This article focuses on the research regarding the impact of different activation functions on neural network models for predicting vibration responses. Activation functions are designed for three typical models: multilayer perceptron (MLP), recurrent neural network (RNN), and convolutional neural network (CNN). The study investigates the influence of different activation functions on prediction results under the condition of noisy vibration signals. This article provides a reference for research at the intersection of deep learning and vibration response prediction. © The Institution of engineering & technology 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Development of a high-resolution near-surface meteorological forcing dataset for the Third Pole region

引用

science China Earth sciences 2025年第4期68卷 1274-1290页

作者： Yaozhi JIANG Wenjun TANG Kun YANG Jie HE Changkun SHAO Xu ZHOU Hui LU Yingying CHEN Xin LI Jiancheng SHI School of Resources and Environment University of Electronic Science and Technology of ChinaChengdu611731China Department of Earth System Science Ministry of Education Key Laboratory for Earth System ModelingInstitute for Global Change StudiesTsinghua UniversityBeijing100084China National Tibetan Plateau Data Center State Key Laboratory of Tibetan Plateau Earth SystemEnvironment and ResourcesInstitute of Tibetan Plateau ResearchChinese Academy of SciencesBeijing100101China State Key Laboratory of Hydroscience and Engineering Tsinghua UniversityBeijing100084China Tsinghua University(Department of Earth System Science)-Xi’an Institute of Surveying and Mapping Joint Research Center for Next-Generation Smart Mapping Beijing100084China National Space Science Center Chinese Academy of SciencesBeijing100190China

Recently,the Third Pole(TP)region has experienced rapid environmental *** data are essential for hydrometeorological and ecological applications but still have large uncertainties on the TP owing to the heterogeneous land surface,complex terrain,and sparse weather *** this study,a long-term(1979–2020)high-resolution(1/30°)meteorological forcing dataset for the TP(TPMFD)was developed,as a sister to the widely used China Meteorological Forcing Dataset(CMFD).The TPMFD comprises seven components necessary for driving land surface *** have previously contributed precipitation and downward shortwave radiation data for the TPMFD,and this study presents the development of five other components and focuses on validations for all ***,2-meter air temperature,2-meter specific humidity,10-meter wind speed,and surface air pressure were generated by combining the fifth-generation atmospheric reanalysis for European Center for Medium-Range Weather Forecasts(ERA5),a short-term high-resolution atmospheric simulation,and in situ observations,and the downward longwave radiation was calculated using semi-physical *** cross-validation and independent-validation demonstrated that most variables in the developed dataset outperformed those in widely used reanalysis datasets,including ERA5,ERA5-Land,and the Global Land Data Assimilation system(GLDAS).This dataset is expected to be beneficial for climate analyses and modeling applications of land-surface processes on the TP.

关键词： Meteorological data Third Pole High-resolution Data downscaling and merging

来源：评论

学校读者我要写书评

暂无评论

RESEARCH ON DYNAMIC LOAD IDENTIFICATION OF THE UNDERWATER PROPULSION system

RESEARCH ON DYNAMIC LOAD IDENTIFICATION OF THE UNDERWATER PR...

引用

2024 CSAA/IET International Conference on Aircraft Utility systems, AUS 2024

作者： Yang, Hongji Xia, Tianxiang Liu, Yancheng Zhang, Xiaobo Yang, Le AVIC Nanjing Engineering Institute of Aircraft System Nanjing China Aviation Science and Technology Key Laboratory of Aviation Mechanical and Electrical System Nanjing China

As an important electromechanical system, the problem of dynamic load identification of underwater propulsion system has always been a challenge in engineering. The underwater environment is unfavorable for testing vibration responses, with significant noise and ill-conditioned dynamic load identification algorithms, all of which can lead to large errors in the identification results. To overcome these challenges, this paper designs a fixture for dynamic load identification of underwater thrusters, dividing the overall structure into two parts: underwater and water surface. Through this approach, sensors are installed on the water surface part to test the vibration response of the overall structure, while the transfer relationships of the structure are obtained through finite element simulation. Additionally, to address the ill-posed problem of dynamic load identification algorithms, this paper introduces the Tikhonov regularization algorithm to improve the accuracy of dynamic load identification. The identification results demonstrate that the proposed method is reliable and effective, with good adaptability to the problem of dynamic load identification for underwater thrusters. © The Institution of engineering & technology 2024.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Giant reversible barocaloric effects with high thermal cycle stability in epoxybonded(MnCoGe)_(0.96)(CuCoSn)_(0.04) composite

引用

International Journal of Minerals,Metallurgy and Materials 2024年第11期31卷 2528-2534页

作者： Yafei Kuang Kun Tao Bo Yang Peng Tong Yan Zhang Zhigang Sun Kewei Zhang Dunhui Wang Jifan Hu Liang Zuo College of Materials Science and Engineering Taiyuan University of Science and TechnologyTaiyuan 030024China Shanxi Key Laboratory of Magnetic and Electric Functional Materials and Applications Taiyuan University of Science and TechnologyTaiyuan 030024China Key Laboratory of Materials Physics Institute of Solid State PhysicsChinese Academy of SciencesHefei 230031China Key Laboratory for Anisotropy and Texture of Materials(Ministry of Education) School of Materials Science and EngineeringNortheastern UniversityShenyang 110819China School of Electronics and Information Hangzhou Dianzi UniversityHangzhou 310018China

Hexagonal MnMX-based(M=Co or Ni,X=Si or Ge)alloys exhibit giant reversible barocaloric ***,giant volume expansion would result in the as-cast MnMX ingots fragmenting into powders,and inevitably bring the deterioration of mechanical properties and *** fragmentation can bring degradation of structural transformation entropy change during cyclic application and removal of *** this paper,giant reversible barocaloric effects with high thermal cycle stability can be achieved in the epoxy bonded(MnCoGe)0.96(CuCoSn)0.04 *** reversible isothermal entropy change of 43.0 J·kg^(−1)·K^(−1) and adiabatic temperature change from barocaloric effects(ΔT_(BCE))of 15.6 K can be obtained within a wide temperature span of 30 K at 360 MPa,which is mainly attributed to the integration of the change in the transition temperature driven by pressure of−101 K·GPa^(−1) and suitable thermal hysteresis of 11.1 ***,the variation of reversibleΔ_(TBCE) against the applied hydrostatic pressure reaches up to 43 K·GPa^(−1),which is at the highest level among the other reported giant barocaloric *** importantly,after 60 thermal cycles,the composite does not break and the calorimetric curves coincide well,demonstrating good thermal cycle stability.

关键词： barocaloric effects cycle stability reversible isothermal entropy change reversible adiabatic temperature change MnCoGe alloys

来源：评论

学校读者我要写书评

暂无评论

Securing STAR-FC-RIS empowered integrated sensing and multiuser communications against target eavesdropping

引用

science China(information sciences) 2024年第11期67卷 335-346页

作者： Shuying LIN Yulong ZOU Fu XIAO Bin LI School of Telecommunications and Information Engineering Nanjing University of Posts and Telecommunications School of Computer Science Nanjing University of Posts and Telecommunications Key Laboratory of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications

This paper investigates a simultaneous-transmitting-and-reflecting fully-connected reconfigurable intelligent surface(STAR-FC-RIS) empowered integrated sensing and multiuser communications(ISAMC) network, where a dual-functional radar-communication base station detects a malicious radar target nearby and communicates with multiple legitimate users on the other side of the STAR-RIS. We utilize an integrated architecture that combines the fully-connected(FC)-RIS, an emerging type of beyond-diagonal(BD)-RIS, with the time-switching(TS)-STAR-RIS to enhance both the sensing and communications at the cost of possible target intercepting and propose the simultaneous-transmitting-and-reflecting fully-connected RIS(STAR-FCR) schemes to strike a balance between sensing and communications performance. Thereafter, observing the security-reliability performance tradeoff of the downlink ISAMC, we conduct closed-form analyses to compare COPs of round-robin scheduling(RS) and multiuser scheduling(MS) with the aid of a TS-based STAR-FC-RIS. Furthermore, we derive closed-form expressions of the sensing outage probability, communications outage probability(COP), and communications intercept probability, where an average of the three probabilities is exploited to obtain an optimized time allocation(OTA) of the *** results verify that the STAR-FCR-MS scheme outperforms the STAR-FCR-RS scheme in terms of sensing reliability and communications security. Moreover, an OTA remarkably enhances the overall performance of the STAR-FCR schemes of ISAMC systems.

关键词： simultaneous-transmitting-and-reflecting reconfigurable intelligent surface (RIS) fully-connected beyond-diagonal RIS integrated sensing and communications multiuser scheduling security

来源：评论

学校读者我要写书评

暂无评论

Three-Branch BERT-Based Text Classification Network for Gastroscopy Diagnosis Text

引用

International Journal of Crowd science 2024年第1期8卷 56-63页

作者： Wang, Zhichao Zheng, Xiangwei Zhang, Jinsong Zhang, Mingzhe School of Information Science and Engineering Shandong Normal University Jinan250358 China State Key Laboratory of High-end Server & Storage Technology Jinan250013 China

During a hospital visit, a significant volume of Gastroscopy Diagnostic Text (GDT) data are produced, representing the unstructured gastric medical records of patients undergoing gastroscopy. As such, GDTs play a crucial role in evaluating the patient’s health, shaping treatment plans, and scheduling follow-up visits. However, given the free-text nature of GDTs, which lack a formal structure, physicians often find it challenging to extract meaningful insights from them. Furthermore, while deep learning has made significant strides in the medical domain, to our knowledge, there are not any readily available text-based pre-trained models tailored for GDT classification and analysis. To address this gap, we introduce a Bidirectional Encoder Representations from Transformers (BERT) based three-branch classification network tailored for GDTs. We leverage the robust representation capabilities of the BERT pre-trained model to deeply encode the texts. A unique three-branch decoder structure is employed to pinpoint lesion sites and determine cancer stages. Experimental outcomes validate the efficacy of our approach in GDT classification, with a precision of 0.993 and a recall of 0.784 in the early cancer category. In pinpointing cancer lesion sites, the weighted F1 score achieved was 0.849. © The author(s) 2024.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Lignin derived absorbent for efficient and sustainable CO_(2) capture

引用

Chinese Journal of Chemical engineering 2023年第2期54卷 89-97页

作者： Yuandong Cui Bin He Yu Lei Yu Liang Wanting Zhao Jian Sun Xiaomin Liu School of Chemistry and Chemical Engineering Qingdao UniversityQingdao 266071China School of Life Science Beijing Institute of TechnologyBeijing 100081China Key Laboratory of Medical Molecule Science and Pharmaceutics Engineering Ministry of Industry and Information TechnologyBeijing Engineering Research Center of Cellulose and Its DerivativesAdvanced Research Institute of Multidisciplinary ScienceBeijing Institute of TechnologyBeijing 100081China

High and cost-efficient capture of CO_(2) is a prerequisite and an inevitable path of carbon emission reduction. To address the challenges(high cost, low efficiency, less sustainability, etc.) of existing petroleum-based CO_(2) absorbents, herein, a class of efficient and sustainable lignin-based absorbents were resoundingly prepared by grafting the active amine group on a lignin derived compound vanillin and alkali lignin. The results demonstrated that vanillin modified by acrylamide achieved the excellent absorption capacity among the three absorbents, whose ability was 0.114 g CO_(2) per gram of absorbent under 25 ℃ and 100 kPa. In addition, the absorbent retained stable absorbability of CO_(2) after 6 *** absorbing capacity of the absorbent formed by the coupling of vanillin and acrylamide to CO_(2) was much greater than their own(i.e. 0 g CO_(2) ·g^(-1)vanillin, 0.01 g CO_(2) ·g^(-1) acrylamide, respectively).Detailed information revealed the multi-site synergistic absorption mechanism, in which CO_(2) has C and O double interactions with the amide group of the absorbent, and single interaction with the hydroxyl oxygen on the benzene ring of the absorbent. The absorption capacity of modified lignin for CO_(2) is as high as 0.12 g CO_(2) per gram of absorbent, which is comparable with that of model compound *** work not only provides a new idea for the design of bio-absorbents for CO_(2) capture, but explores the application potential of lignin-based materials.

关键词： Lignin(model compound) CO_(2)absorption Amide group Multi-site Acid-base Hydrogen bonding

来源：评论

学校读者我要写书评

暂无评论

Leveraging EfficientNetB3 in a Deep Learning Framework for High-Accuracy MRI Tumor Classification

引用

Computers, Materials & Continua 2024年第10期81卷 867-883页

作者： Mahesh Thyluru Ramakrishna Kuppusamy Pothanaicker Padma Selvaraj Surbhi Bhatia Khan Vinoth Kumar Venkatesan Saeed Alzahrani Mohammad Alojail Department of Computer Science&Engineering Faculty of Engineering and TechnologyJAIN(Deemed-to-be University)Bengaluru562112India School of Computer Science and Engineering VIT-AP UniversityAmaravati522241India Department of Computer Science&Technology Madanapalle Institute of Technology&ScienceMadanapalle517325India School of Science Engineering and EnvironmentUniversity of SalfordManchesterM54WTUK School of Computer Science Engineering&Information Systems(SCORE) Vellore Institute of Technology(VIT)Vellore632014India Management Information System Department College of Business AdministrationKing Saud UniversityRiyadh11531Saudi Arabia Adjunct Research Faculty Centre for Research Impact&OutcomeChitkara UniversityRajpuraPunjab140401India

Brain tumor is a global issue due to which several people suffer,and its early diagnosis can help in the treatment in a more efficient *** different types of brain tumors,including gliomas,meningiomas,pituitary tumors,as well as confirming the absence of tumors,poses a significant challenge using MRI *** approaches predominantly rely on traditional machine learning and basic deep learning methods for image *** methods often rely on manual feature extraction and basic convolutional neural networks(CNNs).The limitations include inadequate accuracy,poor generalization of new data,and limited ability to manage the high variability in MRI *** the EfficientNetB3 architecture,this study presents a groundbreaking approach in the computational engineering domain,enhancing MRI-based brain tumor *** approach highlights a major advancement in employing sophisticated machine learning techniques within Computer science and engineering,showcasing a highly accurate framework with significant potential for healthcare *** model achieves an outstanding 99%accuracy,exhibiting balanced precision,recall,and F1-scores across all tumor types,as detailed in the classification *** successful implementation demonstrates the model’s potential as an essential tool for diagnosing and classifying brain tumors,marking a notable improvement over current *** integration of such advanced computational techniques in medical diagnostics can significantly enhance accuracy and efficiency,paving the way for wider *** research highlights the revolutionary impact of deep learning technologies in improving diagnostic processes and patient outcomes in neuro-oncology.

关键词： Deep learning MRI brain tumor cassification EfficientNetB3 computational engineering healthcare technology artificial intelligence in medical imaging tumor segmentation neuro-oncology

来源：评论

学校读者我要写书评

暂无评论

Novel Sparse Codebook Design for MIMO-SCMA

引用

IEEE Transactions on Vehicular technology 2025年第5期74卷 8407-8412页

作者： Lei, Tuofeng Luo, Qu Ni, Shuyan Chen, Shimiao Yu, Lisu Xiao, Pei Space Engineering University Key Laboratory of Intelligent Space TTC&O Ministry of Education Beijing101416 China University of Electronic Science and Technology of China National Key Laboratory of Science and Technology on Communications Chengdu610054 China Nanchang University School of Information Engineering Nanchang330031 China Xidian University State Key Laboratory of ISN Xi'an710071 China

The combination of multiple-input multiple-output (MIMO) and sparse code multiple access (SCMA), referred to as MIMO-SCMA, can be leveraged to achieve high spectrum efficiency and provide massive connectivity for future machine-type communication networks. This paper aims to design enhanced sparse codebooks for MIMO-SCMA by jointly combining frequency and spatial diversity over Rayleigh fading channels. First, based on the pairwise error probability (PEP), novel codebook design criteria have been presented, namely the hybrid minimum product distance of the Euclidean distance (MPD-ED) and the minimum Euclidean distance of the superimposed constellation at each frequency element (MED-FE). Then, enhanced mother constellations (MC) are proposed by maximizing the MPD-ED of the MC based on the alternating optimization. Subsequently, the multi-dimensional codebooks are obtained by applying user-specific rotation of the proposed MC to maximize the MED-FE, where the unitary rotations are considered to fully leverage the Euclidean space of the transmit antennas while maintaining the MPD-ED value of the codebook. Finally, numerical results demonstrate that the proposed approach significantly outperforms the state-of-the-art codebooks. © 1967-2012 IEEE.

关键词： Fading channels

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：