检索结果-内蒙古大学图书馆

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Sundararamaiah, Munikrishnaiah Rao Katru, Chandrasekhar Kolli, Chandra Sekhar Sutaria, Kruti Rao, K.B. Venkata Brahma Maranan, Ramya Indian Land SC29707 United States Aditya University Department of Computer Science and Engineering Andhra Pradesh Surampalem533437 India Parul institute of Engineering and Technology Parul University Computer Science and Engineering Faculty of Engineering and Technology Gujarat India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Vaddeswaram522302 India Saveetha School of Engineering SIMATS Department of Research and Innovation Tamil Nadu Chennai India

ISBN: (纸本)9798331505745

People are making daily purchases and sales through the internet, and most of them require them to use their credit cards. Besides making things easier for the customer, this heightens the probability of online credit card frauds. Credit card fraud detection has increased in several nations in the recent past due to the increased incidence of fraud that requires it to become even more of a security issue than before. In this paper, a new deep-learning-based approach for credit card fraud detection is proposed. It is based on the preprocessing stage, hybrid feature selection, and classification stage. In the first instance, the proposed method is used on the Credit Card Fraud Detection (CCF) data set. A prescreening step that uses Z-score Min-Max normalization is applied to ensure that the ranges of each data set are the same. The Crayfish Optimization Algorithm (COA) and the Emperor Penguin Optimizer (EPO) are integrated and used to identify the better attributes. Next, a similarity-navigated graph neural network (SNGNN) is utilized for classification so that the fraudulent transactions and the transactions that are not fraudulent can be differentiated easily. The overall system is also enhanced with Greylag Goose Optimization (GGO) that maximizes the chances of detection. The proposed method achieves a high accuracy in detecting fraudulent transactions, which means the proposed process has virtually limitless potential to speed up the entire process. Thus, high effectiveness is proved by the 99% accuracy rate of the suggested method. This exceptional outcome proves the robustness of the approach and its ability to adapt to various patterns of dependence and data changes. © 2025 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Thickness simulation of landfast ice along Mawson Coast,East Antarctica based on a snow/ice high-resolution thermodynamic model

引用

Advances in Climate Change research 2022年第3期13卷 375-384页

作者： Xin-Qing LI Feng-Ming HUI Jie-Chen ZHAO Meng-Xi ZHAI Xiao CHENG School of Geospatial Engineering and Science Sun Yat-sen Universityand Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)Zhuhai 519082China Harbin Engineering University Qingdao Graduate School Qingdao Innovation and Development Base(Center)of Harin Engineering UniversityQingdao266000China MNR Key Laboratory for Polar Science Polar Research Institute of ChinaShanghai 200136China

Landfast ice plays an important role in atmosphere‒ocean interactions and ecosystems in the near coast area of *** the characteristics and variations of landfast ice is crucial to the study of climates and field activities in *** this study,a high-resolution thermodynamic snow-ice(HIGHTSI)model was applied to simulate the seasonal changes of landfast ice along the Mawson Coast,East Antarctica,through ERA-Interim reanalysis *** ocean heat-flux(Fw)values(10,15,20 and 25 W m−2)were used in sensitivity *** results showed that it is reasonable to simulate landfast ice using the HIGHTSI model,and the simulation of landfast ice thickness matched best well with field measurements when Fw was 20 W m^(−2).Then,2-D distributions of landfast ice from 2006 to 2018 were modeled by HIGHTSI with 2-D ERA-Interim reanalysis data in a 0.125°×0.125°cell grid as external *** results showed that fast ice was thicker along the coast and thinner near open water,and usually reaches its maximal thickness in October,varying from 1.2 to 2.0 m through the study *** was no statistical trend for the thickness during the study period.

关键词： Landfast ice Modeling HIGHTSI Antarctica

来源：评论

学校读者我要写书评

暂无评论

Homogenous metallic deposition regulated by abundant lithiophilic sites in nickel/cobalt oxides nanoneedle arrays for lithium metal batteries

引用

Journal of Energy Chemistry 2023年第2期77卷 11-18,I0001页

作者： Fenqiang Luo Dawei Xu Yongchao Liao Minghao Chen Shuirong Li Dechao Wang Zhifeng Zheng Fujian Provincial Industry Technologies Development Base for New Energy Fujian Provincial Engineering and Research Center of Clean and High-valued Technologies for BiomassXiamen Key Laboratory for High-valued Conversion Technology of Agricultural BiomassCollege of EnergyXiamen UniversityXiamen 361102FujianChina China Fujian Innovation Laboratory of Energy Materials Science and Technology(Tan Kah Kee Innovation Laboratory) Xiamen 361102FujianChina

Although lithium(Li)metal delivers the highest theoretical capacity as a battery anode,its high reactivity can generate Li dendrites and"dead"Li during cycling,resulting in poor reversibility and low Li *** uniform Li plating/stripping is the core of solving these ***,we design a highly lithiophilic carbon film with an outer sheath of the nanoneedle arrays to induce homogeneous Li plating/*** excellent conductivity and 3D framework of the carbon film not only offer fast charge transport across the entire electrode but also mitigate the volume change of Li metal during *** abundant lithiophilic sites ensure stable Li plating/stripping,thereby inhibiting the Li dendritic growth and"dead"Li *** resulting composite anode allows for stable Li stripping/plating under 0.5 mA cm^(-2) with a capacity of 0.5 mA h cm^(-2) for 4000 h and 3 mA cm^(-2) with a capacity of3 mA h cm^(-2) for 1000 *** Ex-SEM analysis reveals that lithiophilic property is different at the bottom,top,or channel in the structu re,which can regulate a bottom-up uniform Li deposition *** cells paired with LFP show a stable capacity of 155 mA h g^(-1) under a current density of *** pouch cell can keep powering light-emitting diode even under 180°bending,suggesting its good flexibility and great practical applications.

关键词： Nickel/cobalt oxides Nanoneedle arrays Lithiophilic sites Lithium metal batteries

来源：评论

学校读者我要写书评

暂无评论

Enhancing resilience in complex energy systems through real-time anomaly detection: a systematic literature review

引用

Energy Informatics 2024年第1期7卷 96页

作者： Aghazadeh Ardebili, Ali Hasidi, Oussama Bendaouia, Ahmed Khalil, Adem Khalil, Sabri Luceri, Dalila Longo, Antonella Abdelwahed, El Hassan Qassimi, Sara Ficarella, Antonio Department of Engineering for Innovation University of Salento Lecce Italy Bologna Italy Computer Science Department Faculty of Sciences Semlalia Cadi Ayyad University Marrakesh Morocco Computer Science Department Faculty of Science and Technology Cadi Ayyad University Marrakesh Morocco Department of Research and Development HSPI SpA-Roma Rome Italy Department of Embedded Systems and Artificial Intelligence MAScIR UM6P Rabat Morocco

As real-time data sources expand, the need for detecting anomalies in streaming data becomes increasingly critical for cutting edge data-driven applications. Real-time anomaly detection faces various challenges, requiring automated systems that adapt continuously to evolving data patterns due to the impracticality of human intervention. This study focuses on energy systems (ES), critical infrastructures vulnerable to disruptions from natural disasters, cyber attacks, equipment failures, or human errors, leading to power outages, financial losses, and risks to other sectors. Early anomaly detection ensures energy supply continuity, minimizing disruption impacts, an enhancing system resilience against cyber threats. A systematic literature review (SLR) is conducted to answer 5 essential research questions in anomaly detection due to the lack of standardized knowledge and the rapid evolution of emerging technologies replacing conventional methods. A detailed review of selected literature, extracting insights and synthesizing results has been conducted in order to explore anomaly types that can be detected using Machine Learning algorithms in the scope of Energy Systems, the factors influencing this detection success, the deployment algorithms and security measurement to take in to consideration. This paper provides a comprehensive review and listing of advanced machine learning models, methods to enhance detection performance, methodologies, tools, and enabling technologies for real-time implementation. Furthermore, the study outlines future research directions to improve anomaly detection in smart energy systems. © The Author(s) 2024.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

A comprehensive study of affordable“water-in-salt”electrolytes and their properties

引用

Green Chemical engineering 2025年第1期6卷 126-135页

作者： Aritsa Bunpheng Panwad Chavalekvirat Kanokporn Tangthana-umrung Varisara Deerattrakul Khanin Nueangnoraj Wisit Hirunpinyopas Pawin Iamprasertkun School of Bio-Chemical Engineering and Technology Sirindhorn International Institute of TechnologyThammasat UniversityPathum Thani12120Thailand Research Unit in Sustainable Electrochemical Intelligent Thammasat UniversityPathum Thani12120Thailand National Nanotechnology Center(NANOTEC) National Science and Technology Development Agency(NSTDA)Khlong LuangPathum Thani12120Thailand Department of Chemistry and Centre of Excellence for Innovation in Chemistry Faculty of ScienceKasetsart UniversityBangkok10900Thailand

The search for alternative electrolytes has been extremely topical in recent years with the“water-in-salt”electrolyte,especially,lithium bis(trifluoromethanesulfonyl)imide(LiTFSI)coming to the fore in the context of highvoltage ***,“water-in-LiTFSI”exhibits ultra-high cost and low ionic transport when compared with the aqueous lithium-halide,-nitrate as well as-sulphate salts(quoted as LiX).This work rediscovered the properties of a“water-in-salt”(LiX electrolytes)made from a variety of concentration from 1 m to saturated *** changes of physical properties e.g.,viscosity,pH,conductivity,density,and temperature during mixing were then *** electrochemical properties of electrolyte were tested using carbon-based materials(YEC-8A)as a model system(three electrode configuration),and the finding was then expanded to a coin cell supercapacitor for benchmarking the performance per cost *** has been found that the use of highly concentrated LiX electrolytes does not always enhance the potential *** and LiI shown the redox properties while increasing the concentration can speed up the redox process(voltage remains unchanged).Using superconcentrated LiCl can slightly expand the potential window;however,corrosion is the main task to be ***,voltage expansion of LiNO_(3)is found to be approximately 2.2 V,which is comparable to *** breakdown cost of the electrolyte also shows that LiTFSI exhibits the lowest energy density per cost unit(dollars),while LiNO_(3)provides the most feasible cost in term of power *** then marked that the electrolytes such as LiBr and LiI can be used as redox additive *** work also shows the fundamental insight into the physical and electrochemical properties of LiX for possible alternative use as a cheap“water-insalt”electrolyte in energy storage apart from LiTFSI.

关键词： Water-in-salt Electrolyte Lithium Energy storage Carbon

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential Mechanisms of Zhu-Ye-Qing Wine in Preventing Cardiovascular and Cerebrovascular Diseases Based on Network Pharmacology

引用

Critical Reviews in Biomedical engineering 2024年第6期52卷 15-31页

作者： Bai, Yujie Zhang, Xin Wang, Fang Li, Ying Guo, Shiwei Feng, Jingjing Xu, Chenshuai Gao, Huan Guo, Jianfeng College of Chemistry and Chemical Engineering North University of China Taiyuan030051 China Shanxi Provincial Key Laboratory for Chinese Lujiu Plant Extraction and Health Taiyuan030051 China Tianjin University of Science and Technology Tianjin300457 China Shanxi Seabuckthorn Medicinal Tea Joint Innovation Research and Development Base Taiyuan030051 China

Cardiovascular and cerebrovascular disease (CCVD) is a complex disease with a long latency period, and the most effective diagnosis and treatment methods are risk assessment and preventive interventions before onset. According to traditional Chinese medicine (TCM), Zhu-Ye-Qing wine (ZYQW) has the effect of invigorating blood and removing blood stasis. However, whether ZYQW can improve the progression of CCVD has not been reported. This study aims to explore the possible mechanism of ZYQW on CCVD through network pharmacology, and finally 249 potential targets of ZYQW and 2080 potential targets of CCVD are obtained. The key targets mainly include MAPK3, TP53, RELA, MAPK1 and AKT1. The main KEGG pathways include TNF signaling pathway, lipid and atherosclerosis pathway signaling pathway. The components in ZYQW are identified by ultra-performance liquid chromatography-mass spectrometry (UHPLC-CQE-CQE-MS/MS). Through network pharmacology, molecular docking and molecular dynamics simulation, the potential key components and prevention mechanisms of ZYQW in the prevention of CCVD are determined. ZYQW may be an effective and safe health food for the prevention of CCVD, providing guidance and basis for the further development of medicinal foods. © 2024 by Begell House, Inc.

关键词： Medicinal chemistry

来源：评论

学校读者我要写书评

暂无评论

Accelerated initiation of oblique detonation induced by disturbance in detonative zone

引用

Chinese Journal of Aeronautics 2023年第11期36卷 153-164页

作者： Yichen ZHANG Gaoxiang XIANG Jia YU Ke JIN Kek Boon GOH Institute of Extreme Mechanics Northwestern Polytechnical UniversityXi’an 710129China Research and Development Institute Northwestern Polytechnical University in ShenzhenShenzhen 518057China Innovation Center NPU Chongqing Northwestern Polytechnical UniversityChongqing 401135China School of Aerospace Science and Technology Xidian UniversityXi’an 710126China Department of Mechanical Engineering School of EngineeringMonash University MalaysiaSelangor 47500Malaysia

In the real flow for high altitude,the initiation mechanism of the oblique detonation involves the coupling of complex wave structures and combustion waves,which may result in the phenomenon of *** approach of stable initiation is one of the key factors that restricting the oblique detonation engine from theory to *** wave structure,initiation characteristics and characteristic parameters of the flow field are analyzed,the two-dimensional Euler equation considering the detailed chemical reactions of multi-component are ***,the approaches of blunt bump and transverse jet are combined used to shorten the detonation distance of the oblique *** show that these methods can promote the accelerated initiation of the oblique detonation effectively,and the detonation distance can be shortened more than 90%.There are two wave structures induced by the blunt bump:weak coupled and strong coupled,adding the transverse jet promotes the transition between these two wave ***,the shape of the bump and the characteristic parameters of the transverse jet are *** streamline-shape bump can eliminate the recirculation zone formed after the circle bump and the ellipse *** transverse jet will produce an oblique detonation wave at the front of the jet position,which changes the wave structure and initiation mode of the oblique detonation *** is expected to reveal the accelerated initiation mechanism of oblique detonation under the induction zone disturbance and complex flow environment,deepen the understanding of the detonation law of oblique detonation wave under real flow conditions,and provide a scientific basic for the development of the combustor of the oblique detonation engine.

关键词： Acetylene Oblique detonation Initiation acceleration Blunt bump Transverse jet Numerical simulation

来源：评论

学校读者我要写书评

暂无评论

Eco-innovative approaches for recycling non-polyester/cotton blended textiles

Waste Management Bulletin

引用

Waste Management Bulletin 2025年第1期3卷 255-270页

作者： Arun, Chandra Manivannan Panneerselvan, Logeshwaran Nachimuthu, Gunasekhar Conaty, Meredith Palanisami, Thava Environmental Plastic Innovation Cluster (EPIC) Global Innovative Centre for Advanced Nanomaterials (GICAN) College of Engineering Science and Environment The University of Newcastle New South Wales Australia NSW Department of Primary Industries Australian Cotton Research Institute Narrabri Australia Cotton Research and Development Corporation (CRDC) Narrabri NSW Australia

Blended textile waste constitutes a substantial portion of the global textile waste stream, making recycling essential for minimizing the industry's environmental impact. Although polyester/cotton recycling is well developed, many other blended textiles are routinely landfilled owing to a lack of effective recycling technologies. This review critically assesses existing strategies for recycling non-polyester/cotton blends, highlighting the key challenges and opportunities for innovation. In the sorting stage, integrating artificial intelligence (AI) and machine learning (ML) enhances efficiency and accuracy. Advanced methods, such as green chemistry, mechanical recycling, and enzymatic treatments, have proven effective for most blended textiles;however, fibers, such as polypropylene, still lack defined closed-loop recycling routes. Life cycle assessment (LCA) indicates that recycling textile waste can reduce environmental impacts by 60%, but the absence of comprehensive LCA studies on diverse recycling approaches limits reliability. Furthermore, while textile recycling is sustainable, concerns regarding the emission of hazardous additives and organic pollutants pose ecological and health risks. Therefore, advanced recycling technologies for non-polyester/cotton blends are crucial for achieving sustainability. Future research should focus on developing efficient recycling methods for complex blends, addressing the environmental impact of hazardous substances, and standardizing LCA methodologies to ensure economic and environmental viability. © 2025 The Authors

关键词： Artificial intelligence Eco-innovation Green chemistry Life cycle assessment Non-polyester/cotton blends Textile recycling Waste management

来源：评论

学校读者我要写书评

暂无评论

On understanding the impacts of shared public transportation on urban traffic and road safety using an agent-based simulation with heterogeneous fleets: a case study of Casablanca city

引用

Quality and Quantity 2022年第6期56卷 3893-3932页

作者： El Ouadi, Jihane Errousso, Hanae Malhene, Nicolas Benhadou, Siham National and High School of Electricity and Mechanic HASSAN II University Casablanca 8118 Morocco Research Foundation for Development and Innovation in Science and Engineering Casablanca 8118 Morocco EIGSI La Rochelle 17041 France EIGSI Casablanca 20410 Morocco

Simulation and computer modeling have a key role in understanding transportation systems. Focusing on the main system, real-time retrieval of outputs based on mutual interactions of the whole autonomous entities makes the agent-based simulation very promising. This paper deals with an agent-based simulation to investigate and evaluate the potential impacts of implementing Shared Public Transports (SPT) in urban areas. Such a system is intended to integrate the two flows of passengers and containerized freights in Public Transportation (PT) patterns towards more sustainable, efficient, and socially suitable mobility. The proposed model is coupled with a stochastic process in order to provide a range of real-world data of Casablanca city (Morocco) based on institutional surveys. In this respect, two urban transportation systems of freight are tested: (1) the conventional transportation system, (2) the SPT system with heterogeneous fleets. In an effort to sustain efficient and safe movements, this paper examines SPT performances according to a set of key evaluation metrics. Results show that PT stopping remains the most relevant factor when evaluating metrics of the number of waiting containers and waiting time of demand by rates of 82.440% and 62.580%, respectively. Such a waiting containers metric is significantly affected by the volume of demand to transport per time slot by a rate of 78.140%. Under SPT, traffic congestion is the main factor to consider in managing PT with a rate of 65.690% in order to reduce potential accidents. However, demand volume could increase the on-street illegal parking metric by 90.070%. More details are provided below. © 2021, The Author(s), under exclusive licence to Springer Nature B.V.

关键词： Agent-based simulation City logistics Evaluation metrics Passengers and goods Public transportation Shared vehicles

来源：评论

学校读者我要写书评

暂无评论

Federated Learning of Creep Rupture Time and High Temperature Tensile Strength Prediction Models

引用

Tetsu-To-Hagane/Journal of the Iron and Steel Institute of Japan 2025年第5期111卷 246-262页

作者： Sakurai, Junya Torigata, Keisuke Matsunaga, Manabu Takanashi, Naoto Hibino, Shinya Kizu, Kenichi Morita, Akira Inomoto, Masahiro Shimohata, Nobuaki Toyota, Kodai Nakamura, Tadaaki Hashimoto, Keita Okubo, Tatsuya Beheshti, Loic Richard, Vincent Demura, Masahiko Research Network and Facility Services Division National Institute for Materials Science Japan Materials & Structural Dept. Technology Platform Center Corporate Research and Development Division IHI Corporation Japan Engineering G. Aero Engine Space & Defense Business Area Rocket Development Dept. IHI Corporation Japan Kawasaki Heavy Industries Ltd Japan Maintenance Coordination Group Operations Department Thermal Power Division The Kansai Electric Power Co. Inc. Japan Materials Research Laboratory Technical Development Group Kobe Steel Ltd Japan Electric Power Development Co. Ltd Japan Japan Atomic Energy Agency Japan Research & Innovation Center Mitsubishi Heavy Industries Ltd Japan Elix Inc. Japan

Creep testing is time-consuming and costly, leading institutions to limit the number of tests conducted to the minimum necessary for their specific objectives. By pooling data from each institution, it is anticipated that predictive models can be developed for a wide range of materials, including welded joints and degraded materials exposed to service conditions. However, the data obtained by each institution is often highly confidential, making it challenging to share with others. Federated learning, a type of privacy-preserving computation technology, allows for learning while keeping data confidential. Utilizing this approach, it is possible to develop creep life prediction models by leveraging data from various institutions. In this paper, we constructed global deep neural network models for predicting the creep rupture life of heat-resistant ferritic steels in collaboration with eight institutions using the federated learning system we developed for this purpose. Each institution built a local model using only its own data for comparison. While these local models demonstrated good predictive accuracy for their respective datasets, their predictive performance declined when applied to data from other institutions. In contrast, the global model constructed using federated learning showed reasonably good predictive performance across all institutions. The distance between each institution's data was defined in the space of explanatory variables, with the NIMS data, which had the largest dataset, serving as the reference point. The global model maintained high predictive accuracy regardless of the distance from the NIMS data, whereas the predictive accuracy of the NIMS local model significantly decreased as the distance increased. © 2025 The Iron and Steel Institute of Japan.

关键词： Creep testing

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：