检索结果-内蒙古大学图书馆

6th International Conference on Energy, Power and Grid, ICEPG 2024

作者： Li, Haoyuan Guo, Xinyu Yu, Zehao Wang, Yuexuan Feng, Bowei Shenyang University of Technology School of Automation and Electrical Engineering Shenyang China Shenyang University of Technology School of Environmental and Chemical Engineering Shenyang China Shenyang University of Technology School of Information Science and Engineering Shenyang China Shenyang University of Technology School of Art and Design Shenyang China

ISBN: (纸本)9798350377798

Traditional ships rely on diesel engines, consume a large amount of fossil fuels, and seriously pollute the marine environment. Therefore, in order to cope with energy crisis and environmental pollution, it is urgent to use new energy such as solar energy. Although solar power generation has broad application prospects in the shipbuilding industry, its power generation efficiency is relatively low. To address these issues, the PID control algorithm based on BP neural network will be applied to the maximum power tracking (MPPT) of solar photovoltaic arrays, and the BP neural network will be used to accurately adjust the three parameters of KP, KI, and KD. Through experimental verification, the algorithm can achieve a maximum power of 482.5W in approximately 1.3s of the system. The PID control algorithm based on BP neural network has an average maximum power increase of 97.4W compared to the other four classic algorithms, about 20%, indicating significant efficiency of the algorithm;After stabilization, the tracking speed and accuracy were significantly improved. The photovoltaic system using this algorithm can achieve large-scale access on ships and has good MPPT performance in navigation environments. © 2024 IEEE.

关键词： Solar power generation

来源：评论

学校读者我要写书评

暂无评论

Ionogel electrolyte based on porous graphitic C_(3)N_(4)nanosheets for room temperature to 150℃quasi-solid-state lithium batteries

引用

Journal of Energy Chemistry 2025年第5期104卷 494-504页

作者： Zhaoen Liu Xueao Jiang Jiayin Chen Weijian Liu Long Zhao Yang Lv Zhiyong Li Yan Zhang Xiwen Wang Shiguo Zhang College of Energy Engineering Huanghuai UniversityZhumadian 463000HenanChina College of Materials Science and Engineering State Key Laboratory of Advanced Design and Manufacturing Technology for VehicleHunan UniversityChangsha 410082HunanChina School of Chemistry and Chemical Engineering Henan Normal UniversityXinxiang 453007HenanChina

Ionogels,generally formed by immobilizing ionic liquids(ILs)with polymer gelators,hold considerable promise as quasi-solid-state electrolytes(QSSEs)for lithium metal batteries(LMBs)due to their high safety and electrode ***,their practical use in high-temperature LMBs suffers from the softened polymer chains of gelator at high temperatures,leading to liquid leakage and severe growth of Li ***,a novel inorganic ionogel(PCNIL)combining lithium salt-containing IL with porous graphitic carbon nitride nanosheets(PCN)is developed through direct physical *** exhibits a superior ionic conductivity(0.75 mS cm^(-1))at room temperature similar to that of neat IL electrolyte(LiIL)and a Li^(+)transference number(0.56)greatly higher than that of Li-IL(0.20).Furthermore,PCNIL maintains a temperature-independent shear storage modulus of up to 5 MPa from room temperature to 150℃.Consequently,the Li|PCNIL|Li symmetrical cell demonstrates extended reversible lithium plating/stripping over 1200 h without dendritic *** robust mechanical strength,excellent thermal stability,and electrochemical stability of PCNIL allow Li|PCNIL|LiFePO_(4)cells to operate stably in a wide temperature range of 25–150℃.

关键词： Ionogels Graphitic carbon nitride Quasi-solid-state electrolytes High temperature Lithium metal batteries

来源：评论

学校读者我要写书评

暂无评论

Ultrathin organic solvent nanofiltration membrane with polydopamine-HKUST-1 interlayer for organic solvent separation

引用

Journal of Environmental Sciences 2024年第7期141卷 182-193页

作者： Haike Li Xindong Li Guozai Ouyang Lijinhong Huang Lang Li Wenhao Li Wanfu Huang Duokun Li Ganzhou Key Laboratory of Basin Pollution Simulation and Control Jiangxi University of Science and TechnologyGanzhou 341000China Innovation Center for Water Quality Security Technology at Ganjiang River Basin Jiangxi University of Science and TechnologyGanzhou 341000China School of Architecture and Design Jiangxi University of Science and TechnologyGanzhou 341000China WA School of Mines:Minerals Energy and Chemical EngineeringCurtin UniversityWA 6845Australia School of Materials Science and Engineering Tiangong UniversityTianjin 300387China

Polydopamine(PDA)and metal-organic skeleton HKUST-1 were co-deposited on the base membrane of hexamethylenediamine(HDA)-crosslinked polyetherimide(PEI)ultrafiltration membrane as the interlayer,and high-throughput organic solvent nanofiltration membrane(OSN)was prepared by interfacial polymerization and solvent activation *** polyamide(PA)layer surface roughness from 28.4 nm in PA/PEI to 78.3 nm in PA/PDA-HKUST-10.6/PEI membrane,reduced the thickness of the separation layer from 79 to 14 nm,and significantly improved the hydrophilic,thermal and mechanical *** flux of the PA/PDA-HKUST-10.6/PEI membrane in a 0.1 g/L Congo Red(CR)ethanol solution at 0.6 MPa test pressure reached 21.8 L/(m^(2)·hr)and the rejection of CR was 92.8%.Solvent adsorption test,N,N-dimethylformamide(DMF)immersion experiment,and long-term operation test in ethanol showed that the membranes had high solvent *** solvent flux test demonstrated that,under the test pressure of 0.6 MPa,the flux of different solvents ranked as follows:methanol(56.9 L/(m^(2)·hr))>DMF(39.6 L/(m^(2)·hr))>ethanol(31.2 L/(m^(2)·hr))>IPA(4.5 L/(m^(2)·hr))>N-hexane(1.9 L/(m^(2)·hr)).The ability of the membranes to retain dyes in IPA/water dyes solution was also *** flux of the membrane was 30.4 L/(m^(2)·hr)and the rejection of CR was 91.6%when the IPA concentration reached 50%.This OSN membrane-making strategy is economical,environment-friendly and efficient,and has a great application prospect in organic solvent separation systems.

关键词： Interfacial polymerization Organic solvent nanofiltration Interlayer Metal-organic frameworks Polydopamine

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Network and GAN-Based Reversible Data Hiding in Encrypted Images: A Privacy-Preserving Approach

引用

SN Computer Science 2024年第1期5卷 45页

作者： Nalavade, Jagannath E. Patil, Akshta Buchade, Amar Jadhav, Nagesh Department of Computer Science and Engineering MIT Art Design and Technology University School of Computing Pune India Department of Computer Engineering Rajarambapu Institute of Technology Sakharale Sangli India

In light of recent incidents involving the leakage of private photographs of Hollywood celebrities from iCloud, the need for robust methods to safeguard image content has gained paramount importance. This paper addresses this concern by introducing a novel framework for reversible image editing (RIT) supported by reversible data hiding with encrypted images (RDH-EI) techniques. Unlike traditional approaches vulnerable to hacking, this framework ensures both efficient and secure data embedding while maintaining the original image’s privacy. The framework leverages two established methods: secret writing and knowledge activity. While secret writing is susceptible to hacking due to the complex nature of cipher languages, RDH-EI-supported RIT adopts a more secure approach. It replaces the linguistic content of the original image with the semantics of a different image, rendering the encrypted image visually indistinguishable from a plaintext image. This novel substitution prevents cloud servers from detecting encrypted data, enabling the adoption of reversible data hiding (RDH) methods designed for plaintext images. The proposed framework offers several distinct advantages. Firstly, it ensures the confidentiality of sensitive information by concealing the linguistic content of the original image. Secondly, it supports reversible image editing, enabling the restoration of the original image from the encrypted version without any loss of data. Lastly, the integration of RDH techniques designed for plaintext images empowers the cloud server to embed supplementary data while preserving image quality. Incorporating convolutional neural network (CNN) and generative adversarial network (GAN) models, the framework ensures accurate data extraction and high-quality image restoration. The applications of this concealed knowledge are vast, spanning law enforcement, medical data privacy, and military communication. By addressing limitations of previous methods, it opens new avenues

关键词： Deep hiding Deep neural network GAN model Reversible data hiding (RDH)

来源：评论

学校读者我要写书评

暂无评论

Prediction of the geological indicators in TBM tunnel based on optimized proportion of surrounding rock grades

引用

Underground Space 2023年第4期11卷 204-217页

作者： Xiao Guo Wei Guo Jianqin Liu Jinli Qiao Guisong Hu School of Mechanical Engineering Tianjin UniversityTianjin 300350China Key Laboratory of Mechanism Theory and Equipment Design of Ministry of Education Tianjin UniversityTianjin 300350China School of Civil and Transportation Engineering Hebei University of TechnologyTianjin 300401China

With tunnel boring machine being used in underground engineering,accurate geological indicators have been the important basis for tunnel boring machine(TBM)*** propagation neural network(BPNN)has been used to predict the geological indicators of tunnels in previous ***,these studies ignored the imbalance proportion of surrounding rock grades,leading to the indiscriminate use of data,thus affecting the predictive effect of *** order to prove the importance of the proportion of surround-ing rock grade in geological prediction,we mainly attempt to utilize particle swarm optimization(PSO)to optimize the proportion of sample data,and integrate with BPNN to establish a PSO-BPNN theoretical model to predict geological *** the same time,combined with the actual engineering data,5 tunneling indicators were selected as input and 4 geological indicators were selected as out-put by a variety of dimensionality reduction *** geological indicators are density,uniaxial compressive strength,internal fric-tion angle(u)and Poisson’s ratio(e).On this basis,the PSO-BPNN prediction model was established in *** comparing the prediction of traditional BPNN,PSO-BPNN and other optimization-integrated models,the result shows that optimized proportion of surrounding rock grades reduces the prediction error and improves the interpretability of the prediction ***,we com-bined the theory of surrounding rock partition to illustrate the rationality of surrounding rock proportion in PSO result,that is,the proportion of complex surrounding rock should be increased appropriately to improve the prediction ***,based on the optimization-integrated models with engineering data and the surrounding rock classification theory,the importance of proportion of surrounding rock grades for tunnel geological prediction is confirmed.

关键词： TBM BPNN Particle swarm optimization Prediction of geological indicators Sample imbalance

来源：评论

学校读者我要写书评

暂无评论

A thermodynamics-consistent spatiotemporally-nonlocal model for microstructure-dependent heat conduction

引用

Applied Mathematics and Mechanics(English Edition) 2024年第11期45卷 1929-1948页

作者： Yu ZHANG Daming NIE Xuyao MAO Li LI Zhejiang Lab Hangzhou310058China Wuhan Second Ship Design and Research Institute Wuhan430064China State Key Laboratory of Intelligent Manufacturing Equipment and Technology School of Mechanical Science and EngineeringHuazhong University of Science and TechnologyWuhan430074China

The spatiotemporally-nonlocal phenomena in heat conduction become significant but challenging for metamaterials with artificial ***,the microstructure-dependent heat conduction phenomena are captured under the hypothesis of spatiotemporally local *** capture the microstructure-dependent heat conduction phenomena,a generalized nonlocal irreversible thermodynamics is proposed by removing both the temporally-local and spatially-local equilibrium hypotheses from the classical irreversible *** generalized nonlocal irreversible thermodynamics has intrinsic length and time parameters and thus can provide a thermodynamics basis for the spatiotemporally-nonlocal law of heat *** remove the temporallylocal equilibrium hypothesis,the generalized entropy is assumed to depend not only on the internal energy but also on its first-order and high-order time *** remove the spatially local equilibrium hypothesis,the thermodynamics flux field in the dissipation function is assumed to relate not only to the thermodynamics force at the reference point but also to the thermodynamics force of the neighboring *** the developed theoretical framework,the thermodynamics-consistent spatiotemporally-nonlocal models can then be developed for heat transfer *** examples are provided to illustrate the applications of steady-state and transient heat conduction problems.

关键词： nonlocality spatiotemporal nonlocality irreversible thermodynamics heat transfer metamaterial

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Applying Federated Learning to Distributed Intrusion Detection Systems Through Explainable AI

IEEE Networking Letters

引用

IEEE Networking Letters 2024年第3期6卷 198-202页

作者： Oki, Ayaka Ogawa, Yukio Ota, Kaoru Dong, Mianxiong Muroran Institute of Technology School of Information and Electronic Engineering Muroran050-8585 Japan Kagawa University Faculty of Engineering and Design Takamatsu761-0396 Japan Muroran Institute of Technology Department of Information and Electronic Engineering Muroran050-8585 Japan

We apply federated learning (FL) to a distributed intrusion detection system (IDS), in which we deploy numerous detection servers on the edge of a network. FL can mitigate the impact of decreased training data in each server and exhibit almost the same detection rate as that of the non-distributed IDS for all attack classes. We verify the effect of FL using explainable artificial intelligence (XAI);this effect is demonstrated by the distance between the feature set of each attack class in the distributed IDS and that in the non-distributed IDS. The distance increases for independent learning and decreases for FL. © 2019 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

AI/ML Applications in Spoofing Detection in 5G Networks: Challenges and Solutions 3

AI/ML Applications in Spoofing Detection in 5G Networks: Cha...

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Singh, Monika Hegde, Raveesh Jha, Mahesh Kumar Choudhary, Amar Rubini, P. Cmr Institute of Technology Bengaluru India Alliance University Alliance College of Engineering and Design Bengaluru India Cmr University School of Engineering and Technology Bengaluru India

ISBN: (纸本)9798331515911

5G networks has advanced connectivity, high data, low latency and reliability. Along with these features new challenges come with respect to security, particularly spoofing attacks. One of the necessity in 5G and future wireless communication is to prevent the spoofing attacks depending on the applications. Artificial Intelligence (AI) and Machine Learning (ML) present promising solutions for detecting and mitigating spoofing threats in 5G networks. This paper explains the different types of spoofing and applications, challenges, and future prospects of AI/ML in addressing spoofing in 5G networks. AI/ML algorithms can be used in detection of the location of attackers. This paper also analyses current methodologies, highlight key challenges, and discuss potential advancements that could enhance the security of 5G networks. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Nanodiamond/Ti_(3)C_(2) MXene-coated quartz crystal microbalance humidity sensor with high sensitivity and high quality factor

引用

Rare Metals 2024年第6期43卷 2719-2729页

作者： Yao Yao Qiao Chen Yan-Qi Li Xian-He Huang Wei-Wei Ling Zhe-MiaoXie Jia-QiWang Chang-Ming Chen College of Communication Engineering Chengdu University of Information TechnologyChengdu 610225China School of Automation Chongqing University of Posts and TelecommunicationsChongqing 400065China School of Automation Engineering University of Electronic Science and Technology of ChinaChengdu 611731China Advanced Micro-/Nano-Devices Lab Department of Systems Design EngineeringUniversity of WaterlooWaterlooON N2L 3GlCanada

To address the challenge of achieving both high sensitivity and a high quality factor in quartz crystal microbalance(QCM)humidity sensors,a nanodiamond(ND)/Ti_(3)C_(2)MXene composite-coated QCM humidity sensor was *** material characteristics of ND,Ti_(3)C_(2)MXene,and ND/Ti_(3)C_(2)MXene composite were analyzed by transmission electron microscopy(TEM)and Fourier transform infrared(FTIR)*** experimental results demonstrated that the hydrophilic ND nanoparticles coated on Ti_(3)C_(2) MXene nanosheet prevented the self-stacking of Ti_(3)C_(2)MXene and enhanced the sensitivity of Ti_(3)C_(2) MXene-based QCM humidity ***,the high mechanical modulus of Ti_(3)C_(2) MXene material helped ND/Ti_(3)C_(2)MXene composite-coated QCM humidity sensor to achieve a high quality factor(>20,000).ND/Ti_(3)C_(2)MXene compositecoated QCM humidity sensor exhibited a sensitivity of 82.45 Hz/%RH,a humidity hysteresis of 1.1%RH,fast response/recovery times,acceptable repeatability,and good stability from 11.3%RH to 97.3%*** response mechanism of ND/Ti_(3)C_(2) MXene composite-coated QCM humidity sensor was analyzed in combination with a bi-exponential kinetic adsorption ***,the potential application of ND/Ti_(3)C_(2)MXene composite-coated QCM humidity sensor was demonstrated through its frequency response to wooden blocks with different moisture contents.

关键词： Humidity sensor Quartz crystal microbalance Nanodiamond Ti_(3)C_(2)MXene High quality factor

来源：评论

学校读者我要写书评

暂无评论

Unveiling cognitive processes in digital reading through behavioural cues: A hybrid intelligence (HI) approach

引用

British Journal of Educational technology 2025年第2期56卷 678-711页

作者： Lee, Yoon Migut, Gosia Specht, Marcus Industrial Design Graduate School of Design University of Seoul Seoul Korea Republic of Research Lab Faculty of Education and Psychology University of Oulu Oulu Finland Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft Netherlands

Learner behaviours often provide critical clues about learners' cognitive processes. However, the capacity of human intelligence to comprehend and intervene in learners' cognitive processes is often constrained by the subjective nature of human evaluation and the challenges of maintaining consistency and scalability. The recent widespread AI technology has been applied to learning analytics (LA), aiming at a more accurate, consistent and scalable understanding of learning to compensate for challenges that human intelligence faces. However, machine intelligence has been criticized for lacking contextual understanding and difficulties dealing with complex human emotions and social cues. In this work, we aim to understand learners' internal cognitive processes based on the external behavioural cues of learners in a digital reading context, using a hybrid intelligence (HI) approach, bridging human and machine intelligence. Based on the behavioural frameworks and the insights from human experts, we scope specific behavioural cues that are known to be relevant to learners' attention regulation, which is highly relevant for learners' cognitive processes. We utilize the public WEDAR dataset with 30 subjects' video data, behaviour annotation and pre–post tests on multiple choice and summarization tasks. We apply the explainable AI (XAI) approach to train the machine learning model so that human evaluators can also understand which behavioural features were essential for predicting the usage of the cognitive processes (ie, higher-order thinking skills [HOTS] and lower-order thinking skills [LOTS]) of learners, providing insights for the next-round feature engineering and intervention design. The result indicates that the dominant use of attention regulation behaviours is a reliable indicator of low use of LOTS with 79.33% prediction accuracy, while reading speed is a valuable indicator for predicting the overall usage of HOTS and LOTS, ranging from 60.66% to 78.66% accuracy,

关键词： Contrastive 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：