检索结果-内蒙古大学图书馆

Solar Energy Forecasting Using Machine Learning Techniques for Enhanced Grid Stability

IEEE Access 2025年 13卷 93735-93754页

作者： Attuluri R. Vijay Babu N. Bharath Kumar Rajanand Patnaik Narasipuram Soundhar Periyannan Alireza Hosseinpour Aymen Flah Department of Electrical and Electronics Engineering Vignan’s Foundation for Science Technology and Research Guntur Andhra Pradesh India Energy Group Cyient Ltd. Pune Maharashtra India Atria Power Bengaluru Karnataka India Department of Electrical Engineering University of Zabol Zabol Iran National Engineering School of Gabes University of Gabes Gabes Tunisia Applied Science Research Center Applied Science Private University Amman Jordan Jadara University Research Center Jadara University Irbid Jordan ENET Centre CEET VSB-Technical University of Ostrava Ostrava Czech Republic

The increasing integration of solar photovoltaic (PV) systems into modern energy grids presents significant challenges due to the intermittent and weather-dependent nature of solar energy generation. Accurate short-term forecasting is essential to ensure grid stability and optimize energy resource allocation. This study proposes a comprehensive data-driven framework for solar energy forecasting using multiple machine learning (ML) techniques, including Multiple Linear Regression, Ridge, Lasso, Decision Tree Regression, Support Vector Regression, and ensemble-based models such as Random Forest, AdaBoost, Bagging, and Gradient Boosting Regressors. The framework incorporates advanced feature engineering using high-resolution meteorological and solar geometric parameters-such as relative humidity, temperature, cloud cover, zenith angle, azimuth, and angle of incidence-to enhance model accuracy. Historical solar power and weather datasets were used to train and evaluate the models across multiple performance metrics. Among the models, the Gradient Boosting Regressor demonstrated the best performance, achieving an $R^{2}$ of 0.827, RMSE of 399.44, and MAE of 253.62, marking a significant improvement over baseline models. The study also evaluates model robustness and discusses feature relevance, hyperparameter optimization strategies, and deployment considerations for real-time grid operations. These findings provide practical insights for stakeholders aiming to implement intelligent solar forecasting systems in smart grid environments, thereby contributing to enhanced energy management and grid resilience.

关键词： Forecasting Solar energy Predictive models Humidity Biological system modeling Machine learning Accuracy Atmospheric modeling Support vector machines Real-time systems

来源：评论

学校读者我要写书评

暂无评论

A review of cybersecurity challenges and recommendations in the healthcare sector

A review of cybersecurity challenges and recommendations in ...

引用

Business Analytics for technology and Security (ICBATS), International Conference on

作者： Nitinkumar Shingari Seema Verma Beenu Mago Muhammad Sheraz Javeid Banasthali Vidyapith Rajasthan India Banasthali University Rajasthan India School of Information Technology Skyline University College Sharjah UAE Applied Science Research Center Applied Science Private University Amman Jordan

There are a large number of risks inherent in the contemporary business world. The healthcare industry is specifically vulnerable to cybercrime as it depends to a large extent on electronic health information. The increasing threat presented by cybercrime should be considered by organizations when formulating their emergency operating mechanisms. It is also important for healthcare providers to understand the critical cybersecurity scenarios and to prepare themselves according. The only ways security risks and dangers can be decreased are through alertness, awareness, preparedness, and rapid response. This is not easy but can be achieved if one is willing to remain committed to this cause for a long time; it will lead to extensive benefits for a strong healthcare ecosystem. Thus, the current study provides the cybersecurity challenges and recommendations in healthcare sector.

关键词： Training Industries COVID-19 Pandemics Ecosystems Medical services Organizations

来源：评论

学校读者我要写书评

暂无评论

Pursued Strength-Ductility Synergy in Ni Superalloys Produced by Laser Powder Bed Fusion: Crystallographic Lamellar Versus Directionally Solidified Microstructure

SSRN

引用

SSRN 2024年

作者： Wang, Peng Liang, Jingjing Zhu, YuPing Yang, JunYing Zhou, Yizhou Sun, Xiaofeng Li, Jinguo Shi-changxu Innovation Center for Advanced Materials Institute of Metal Research Chinese Academy of Sciences Shenyang110016 China School of Materials Science and Engineering University of Science and Technology of China Shenyang110016 China

As a unique solidification microstructure of Ni superalloys produced by laser powder bed fusion (L-PBF), the crystallographic lamellar microstructure (CLM) exhibits a strong texture with and orientation, but in-depth mechanical properties studies remain lacking. In this study, comparative studies are conducted to reveal the unique deformation and strengthening mechanism of the CLM and non-CLM under room and high-temperature tensile conditions. However, substantial differences are observed in grain size, the number of grain boundaries, geometrical necessary dislocation (GND), elemental segregation, and crystallographic texture. The tensile results showed that the specimen with CLM exhibited an outstanding strength-ductility synergy due to the presence of high-proportioned texture and unique / boundary. The regularly distributed grains can serve as strong obstacles for slip bands and cracks propagating in grains. Moreover, the texture together with / boundary can elevate the local flow stresses and result in the activation of profuse deformation mechanisms, such as Planar slip bands, Stacking faults (SFs), and deformation twins. This work provides cross-scale insights into the deformation mechanisms and underscores the potential of CLM for developing high-temperature structural applications in Ni superalloy. © 2024, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

H2−CH4 van der Waals compounds under rapid compression

引用

Physical Review B 2024年第22期110卷 224109-224109页

作者： Jinwei Yan Israel Osmond Ross T. Howie Eugene Gregoryanz Miriam Peña-Alvarez Center for Science at Extreme Conditions and School of Physics and Astronomy University of Edinburgh Edinburgh EH9 3FD United Kingdom Center for High-Pressure Science and Technology Advanced Research Shanghai 201203 China Key Laboratory of Materials Physics Institute of Solid State Physics HFIPS Chinese Academy of Sciences Hefei 230031 China

Under high pressure, methane and hydrogen form (CH4)2H2, CH4(H2)2, and (CH4)3(H2)25 van der Waals compounds with stoichiometries determined by the H2 concentration. This study investigates the effect of compression rates (up to 183 GPa/s) on the formation and morphology of these compounds at pressures up to 60 GPa utilizing dynamic diamond anvil cells combined with time-resolved Raman spectroscopy. Compression rates exceeding 100 GPa/s inhibit the formation of (CH4)3(H2)25, while CH4(H2)2 and (CH4)2H2 remain unaffected. Furthermore, lower compression rates yield distinct leaflike and globular sample morphologies depending on the H2 concentration, while rates above 20 GPa/s consistently result in textureless mixtures, regardless of H2 concentration. These combined results demonstrate the competition between transition time and kinetic barriers, together with the critical role of the compression rate during dynamic-pressure nonequilibrium processes.

关键词： Van der Waals forces

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of CNN-based Deep Learning Approaches on Complex Activity Recognition 7

Comparative Analysis of CNN-based Deep Learning Approaches o...

引用

7th International Conference on Digital Arts, Media and technology, DAMT 2022 and 5th ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering, NCON 2022

作者： Mekruksavanich, Sakorn Jantawong, Ponnipa Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Faculty of Applied Science Department of Mathematics Bangkok Thailand

ISBN: (纸本)9781665495103

For those with Parkinson's disease, freezing of gait (FOG) could be a distressing condition. In individuals with diabetes, FOG could have a significant influence on their quality of life and cause falls, which can be dangerous. A questionnaire has traditionally been used to measure the severity of FOG symptoms;nevertheless, this technique is subjective and can not accurately reflect the intensity of this illness. The adoption of sensor-based devices may give reliable and objective information to follow the progression of symptoms, allowing for better Parkinson's disease management and therapy. A compact deep convolutional neural network comprising squeeze and excitation components, which we called SE-DeepConV model, was designed to identify FOG utilizing wearable data from the sensors. The SE-DeepConV model was constructed and evaluated using a publicly accessible standard FOG dataset, particularly the Daphnet dataset. The SE-DeepConV model outperforms other benchmark deep learning models in terms of accuracy, with the most outstanding accuracy of 95.65%, according to research observations. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Direct Identification of Intact Proteins Using a Low-Resolution Mass Spectrometer with CIDn/ETnoD

引用

Journal of the American Society for Mass Spectrometry 2024年第7期35卷 1507-1515页

作者： Kuo, Cheng-Yu Zheng, Yi-Feng Wang, Wei-Chen Toh, Jie-Teng Hsu, Yu-Ming Chien, Han-Ju Chang, Chih-Jui Lai, Chien-Chen Institute of Molecular Biology National Chung Hsing University Taichung402 Taiwan Department of Biochemical Science and Technology National Chiayi University Chiayi600 Taiwan Department of Molecular Biology and Human Genetics Tzu Chi University Hualien City970 Taiwan Advanced Plant and Food Crop Biotechnology Center National Chung Hsing University Taichung402 Taiwan Graduate Institute of Chinese Medical Science China Medical University Taichung406 Taiwan Doctoral Program in Translational Medicine National Chung Hsing University Taichung402 Taiwan Rong Hsing Translational Medicine Research Center National Chung Hsing University Taichung402 Taiwan

Over the past decades, proteomics has become increasingly important and a heavily discussed topic. The identification of intact proteins remains a major focus in this field. While most intact proteins are analyzed using high-resolution mass spectrometry, identifying them through low-resolution mass spectrometry continues to pose challenges. In our study, we investigated the capability of identifying various intact proteins using collision-induced dissociation (CID) and electron transfer without dissociation (ETnoD). Using myoglobin as our test protein, stable product ions were generated with CID, and the identities of the product ions were identified with ETnoD. ETnoD uses a short activation time (AcT, 5 ms) to create sequential charge-reduced precursor ion (CRI). The charges of the fragments and their sequences were determined with corresponding CRI. The product ions can be selected for subsequent CID (termed CIDn) combined with ETnoD for further sequence identification and validation. We refer to this method as CIDn/ETnoD. The use of a multistage CID activation (CIDn) and ETnoD protocol has been applied to several intact proteins to obtain multiple sequence identifications. © 2024 The Authors. Published by American Chemical Society.

关键词： Dissociation

来源：评论

学校读者我要写书评

暂无评论

Navigating Towards Fairness with Data Selection 39

Navigating Towards Fairness with Data Selection

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Yixuan Li, Zhidong Wang, Yang Chen, Fang Fan, Xuhui Zhou, Feng School of Statistics and Data Science Southeast University China Data Science Institute University of Technology Sydney Australia School of Computing Macquarie University Australia Center for Applied Statistics School of Statistics Renmin University of China China Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing China

ISBN: (纸本)157735897X

Machine learning algorithms often struggle to eliminate inherent data biases, particularly those arising from unreliable labels, which poses a significant challenge in ensuring fairness. Existing fairness techniques that address label bias typically involve modifying models and intervening in the training process, but these lack flexibility for large-scale datasets. To address this limitation, we introduce a data selection method designed to efficiently and flexibly mitigate label bias, tailored to more practical needs. Our approach utilizes a zero-shot predictor as a proxy model that simulates training on a clean holdout set. This strategy, supported by peer predictions, ensures the fairness of the proxy model and eliminates the need for an additional holdout set, which is a common requirement in previous methods. Without altering the classifier’s architecture, our modality-agnostic method effectively selects appropriate training data and has proven efficient and effective in handling label bias and improving fairness across diverse datasets in experimental evaluations. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhancing strength and ductility simultaneously in Ti5553 alloy via heterogeneous structure architecture

引用

Materials science and Engineering: A 2025年 940卷

作者： Yang, Yujing Ma, Yingjie Wang, Qian Jia, Yandi Qi, Min Huang, Sensen Lei, Jiafeng Yang, Rui School of Materials Science and Engineering University of Science and Technology of China Shenyang110016 China Shi-changxu Innovation Center for Advanced Materials Institute of Metal Research Chinese Academy of Sciences Shenyang110016 China Shenyang National Laboratory for Materials Science Institute of Metal Research Chinese Academy of Sciences Wenhua Road 72 Shenyang110016 China

Here we reported a novel approach to construct heterostructure in metastable β alloy achieving superior mechanical properties by β grain partially recrystallizing. First of all, the as-received microstructure composed of recrystallized and deformed β grains was obtained by forging near β-transus temperature. The microstructure difference between recrystallized and deformed β grains was characterized in detail and the formation mechanism was analyzed. By direct aging treatment, the multi-scale α lamellar microstructure consisting of coarse α lamellae precipitating in recrystallized β grains and thin α lamellae in deformed β grains was realized in Ti5553 alloy. Compared with solution plus aging treatment, the direct aging microstructure exhibits remarkable enhancement in both tensile strength (1519.7 MPa) and elongation (7.7 %). Deformation-induced hardening contributing to the superior tensile strength of the heterostructure was confirmed by loading-unloading-reloading tests. Finally, the different strain distribution and deformation behaviors between recrystallized and deformed β regions were investigated by in-situ tensile experiment to analyze the hardening mechanism. This work is expected to provide a new idea for the heterostructure construction in high strength β titanium alloys. © 2025

关键词： Tensile strength

来源：评论

学校读者我要写书评

暂无评论

Efficiency enhancement to 24.62%in inverted perovskite solar cells through poly(ionic liquid)bulk modification

引用

Energy Materials and Devices 2024年第1期2卷 64-75页

作者： Xingyuan Chen Tong Wang Jiabao Yang Xingyu Pu Hui Chen Bingxiu Xue Long Jiang Jianbo Yin Qi Cao Xuanhua Li State Key Laboratory of Solidification Processing Center for Nano Energy MaterialsSchool of Materials Science and Engi-neeringNorthwestern Polytechnical UniversityXi’an 710072China Research&Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen 518057China Smart Materials Laboratory Department of Applied PhysicsSchool of Physical Science and TechnologyNorthwestern Polytechnical UniversityXi’an 710072China State Key Laboratory for Performance and Structure Safety of Petroleum Tubular Goods and Equipment Materials CNPC Tubular Goods Research InstituteXi’an 710077China

Small-molecule ionic liquids(ILs)are frequently employed as efficient bulk phase modifiers for perovskite ***,their inherent characteristics,such as high volatility and ion migration properties,pose challenges in addressing the stability issues associated with perovskite solar cells(PSCs).In this study,we design a poly(IL)with multiple active sites,named poly[4-styrenesulfonyl(trifluoromethylsulfonyl)imide]pyri-dine(P[STFSI][PPyri]),as an efficient additive of perovskite *** S=O in the sulfonyl group chelates with uncoordinated Pb^(2+)and forms hydrogen bonds with the organic cations in the perovskite,suppressing the volatilization of the organic *** N+in pyridine can fix halide ions through electrostatic interaction with I-and Br-ions to prevent halide ion migration.P[STFSI][PPyri]demonstrates the ability to passivate defects and suppress nonradiative recombination in ***,it facilitates the fixation of organic and halide ions,thereby enhancing the device’s stability and photoelectric ***,the introduction of P[STFSI][PPyri]as a dopant in the devices resulted in an excellent efficiency of 24.62%,demonstrating outstanding long-term operational stability,with the encapsulated device maintaining 87.6%of its initial effi-ciency even after 1500 h of continuous maximum power point *** strategy highlights the promising potential of poly(IL)as an effective additive for PSCs,providing a combination of high performance and stabil-ity.

关键词： inverted perovskite solar cells bulk modification defect passivation

来源：评论

学校读者我要写书评

暂无评论

Disentangling Tabular Data Towards Better One-Class Anomaly Detection

arXiv

引用

arXiv 2024年

作者： Ye, Jianan Tan, Zhaorui Hu, Yijie Yang, Xi Cheng, Guangliang Huang, Kaizhu School of Advanced Technology Xi’an Jiaotong-Liverpool University China School of Electrical Engineering Electronics and Computer Science University of Liverpool United Kingdom Data Science Research Center Duke Kunshan University China

Tabular anomaly detection under the one-class classification setting poses a significant challenge, as it involves accurately conceptualizing "normal" derived exclusively from a single category to discern anomalies from normal data variations. Capturing the intrinsic correlation among attributes within normal samples presents one promising method for learning the concept. To do so, the most recent effort relies on a learnable mask strategy with a reconstruction task. However, this wisdom may suffer from the risk of producing uniform masks, i.e., essentially nothing is masked, leading to less effective correlation learning. To address this issue, we presume that attributes related to others in normal samples can be divided into two non-overlapping and correlated subsets, defined as CorrSets, to capture the intrinsic correlation effectively. Accordingly, we introduce an innovative method that disentangles CorrSets from normal tabular data. To our knowledge, this is a pioneering effort to apply the concept of disentanglement for one-class anomaly detection on tabular data. Extensive experiments on 20 tabular datasets show that our method substantially outperforms the state-of-the-art methods and leads to an average performance improvement of 6.1% on AUC-PR and 2.1% on AUC-ROC. Codes are available at https://***/yjnanan/Disent-AD. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine 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：