检索结果-内蒙古大学图书馆

High-fidelity model to predict heat transfer enhancement for liquid film boiling on uniform micro-structured wicking surfaces

引用

National science Review 2024年第6期11卷 93-95页

作者： Vishwanath Ganesan Mohammad Jalal Inanlu Nenad Miljkovic Department of Mechanical Science and Engineering University of Illinois Urbana-Champaign Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign Materials Research Laboratory University of Illinois Urbana-Champaign International Institute for Carbon Neutral Energy Research (WPI-I2CNER) Kyushu University Institute for Sustainability Energy and Environment (iSEE)University of Illinois Urbana-Champaign

The field of thermal management in highpower electronic devices is a critical area of study, focusing on the efficient dissipation of heat to prevent device overheating and failure [1]. A key aspect of this field is understanding the dynamics of thin liquid film boiling, both on uniform and non-uniform micro-structured wicking surfaces, which can significantly enhance the heat transfer effectiveness[2].

关键词： structured predict micro liquid model boiling enhancement film heat high-fidelity

来源：评论

学校读者我要写书评

暂无评论

An Innovative Next Activity Prediction Approach Using Process Entropy and DAW-Transformer

arXiv

引用

arXiv 2025年

作者： Zare, Hadi Abbasi, Mostafa Ahang, Maryam Najjaran, Homayoun Department of Electrical and Computer Engineering Faculty of Engineering and Computer Science University of Victoria Victoria Canada Department of Mechanical Engineering Faculty of Engineering and Computer Science University of Victoria Victoria Canada

Purpose - In Business Process Management (BPM), accurate prediction of the next activities is vital for operational efficiency and decision-making. Current Artificial Intelligence (AI)/Machine Learning (ML) models struggle with the complexity and evolving nature of business process event logs, balancing accuracy and interpretability. This paper proposes an entropy-driven model selection approach and DAW-Transformer, which stands for Dynamic Attribute-Aware Transformer, to integrate all attributes with a dynamic window for better accuracy. Design/methodology/approach - This paper introduces a novel next-activity prediction approach that uses process entropy to assess the complexity of event logs and dynamically select the most suitable ML model. A new transformer-based architecture with multi-head attention and dynamic windowing mechanism, DAW-Transformer, is proposed to capture long-range dependencies and utilize all relevant event log attributes. Experiments were conducted on six public datasets, and the performance was evaluated with process entropy. Finding - The results demonstrate the effectiveness of the approach across these publicly available datasets. DAW-Transformer achieved superior performance, especially on high-entropy datasets such as Sepsis exceeding Limited window Multi-Transformers by 4.69% and a benchmark CNN-LSTM-SAtt model by 3.07%. For low-entropy datasets like Road Traffic Fine, simpler, more interpretable algorithms like Random Forest performed nearly as well as the more complex DAW-Transformer and offered better handling of imbalanced data and improved explainability. Originality/ value - This work’s novelty lies in the proposed DAW-Transformer, with a dynamic window and considering all relevant attributes. Also, entropy-driven selection methods offer a robust, accurate, and interpretable solution for next-activity prediction. © 2025, CC BY-NC-SA.

关键词： Administrative data processing

来源：评论

学校读者我要写书评

暂无评论

Miniature Underwater Robot – An Experimental Case Study 40th

Miniature Underwater Robot – An Experimental Case Study

引用

40th IMAC, A Conference and Exposition on Structural Dynamics, 2022

作者： Davaria, Sheyda Krishnan, Manu Sriram Malladi, Vijaya V. N. Tarazaga, Pablo A. Department of Electrical and Computer Engineering Virginia Tech BlacksburgVA United States Department of Aerospace Engineering Virginia Tech BlacksburgVA United States Mechanical Engineering-Engineering Mechanics Department Michigan Tech HoughtonMI United States Department of Mechanical Engineering Texas A&M University College StationTX United States

ISBN: (纸本)9783031054044

One of the easiest to observe conditions where waves occur in nature is the undulatory motion of aquatic animals and micro-organisms. In these bio-mechanisms, there is oscillatory locomotion which results in propulsion as the motion is accompanied by energy transfer from one end of the specimen or structure to the other end. Recent years have also seen a rise in the replication of the propulsive capabilities of these animals into aquatic robots. The use of smart materials to actuate and mimic the fin and tail characteristics of a fish has been attempted in various ways. Miniature robots actuated by piezoelectric materials have been effectively used for propulsion due to their simplicity and innovative actuating mechanism. These miniature robots find their application in the regime of underwater propulsion because of their size, flexibility, and ability to mimic fish locomotion. In most of these studies, the undulatory motion of these aquatic robots is achieved by discretizing the fin of the robot into multiple segments and synchronizing the oscillatory motion of individual segments to replicate continuous traveling waves. As a part of such endeavors, the present work attempts to use smart materials to actuate and mimic the fin motion characteristics of a fish. The bio-inspired design of the miniature robots consists of two brass shims supported by four piezoelectric bimorphs. The undulatory motion displayed by aquatic animals is mimicked by generating anechoic traveling waves in these brass fins. Anechoic traveling waves propagate in a structure without undergoing reflections at the structural boundaries. Such waves are generated by taking advantage of the structural dynamics of the fin under multi-input excitation. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Piezoelectricity

来源：评论

学校读者我要写书评

暂无评论

Experimental study on flow characteristics in a new separator 19

Experimental study on flow characteristics in a new separato...

引用

19th International Conference on Future Networks and Communications, FNC 2024 / 21st International Conference on Mobile Systems and Pervasive Computing, MobiSPC 2024 / 14th International Conference on Sustainable Energy Information Technology, SEIT 2024

作者： Alsafadi, Ibrahim Kharoua, Nabil Meribout, M. Islam, Md. Khezzar, L. Afshin, G. Mechanical Engineering Department Khalifa University of Science & Technology Abu Dhabi127788 United Arab Emirates Mechanical Engineering Department Ecole Nationale Polytechnique de Constantine BP 75 A Nouvelle ville RP Constantine Algeria Electrical Engineering & Computer Science Department Khalifa University of Science & Technology PO. Box 2533 Abu Dhabi United Arab Emirates

The confined multiphase swirling flow characteristics were studied in the presence of a new bluff body for gas/liquid separation. It is a hollow cylinder with a tapered front. The flow visualization was performed using High Speed Camera. The gas-to-liquid ratio was controlled by manipulating the air and water flow rates in the flow loop. Based on previous studies, the generated air core exhibits different regimes with stable and unstable regions along the pipe axis. The proposed bluff body should be placed with the stable region to avoid the loss of separation efficiency due to the oscillations of the air core. Three flow regimes were considered based on the water flow rate. At the low water flow rate, the air core is thinner and breaks down a few centimeters upstream of the bluff body. The generated bubbles are sucked inside the bluff body. Increasing the air flow rates causes the air core to get closer to the bluff body until reaching it completely and might enlarge exceeding the bluff body diameter. For all the cases considered, the air core is wavy with highly instable diameter and length. When increasing the water flow rate, a more stable air core is formed closer to the bluff body. The high-water flow rate appears to be necessary to stabilize the air core and reach flow regimes favorable for an efficient separation through both the annular space and the internal passage. © 2024 The Authors. Published by Elsevier B.V.

关键词： Swirling flow

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Solar Electrification Station for Sustainable Energy Access

Design and Implementation of Solar Electrification Station f...

引用

2024 International Conference on Communication, Computing and Internet of Things, IC3IoT 2024

作者： Prathibha, Soma Siva Chandran, S. Kirthiga, M. Dhanya, K. Abhijay Gopal, S. Manish, M. Sri Sairam Engineering College Department Of Information Technology Chennai India Sri Sairam Engineering College Department Of Mechanical Engineering Chennai India Sri Sairam Engineering College Department Of Electronics And Communication Chennai India Electrical And Electronics Engineering Sri Sairam Engineering College Chennai India Sri Sairam Engineering College Department Of Electrical Engineering Chennai India Sri Sairam Engineering College Department Of Computer Science And Business Systems Chennai India

ISBN: (纸本)9798350352689

A power outage can have serious consequences in today's modern society, since technology has become an essential component of our everyday existence. Also continuous power breakdowns have far-reaching consequences in our increasingly connected world. From communication disruptions to healthcare risks, transportation challenges, economic setbacks, and psychological impact, the hardships faced by people during power outages are significant. People suffer a great deal as a result of frequent power outages, which can interfere with vital services like emergency response and healthcare as well as disrupt communication and transportation networks. To address the hardships faced by remote and underprivileged villages due to continuous power breakdowns, a solar electrification station is developed as a sustainable energy solution. The project focuses on providing a reliable and uninterrupted power source, particularly during the rainy season when floods disrupt normal life. The installation of a 3kW monocrystalline solar panel system, operated as a standalone solar system, powers the village school, ensuring uninterrupted education for students. © 2024 IEEE.

关键词： Rural areas

来源：评论

学校读者我要写书评

暂无评论

Differentially private locality sensitive hashing based federated recommender system

Differentially private locality sensitive hashing based fede...

引用

作者： Hu, Hongsheng Dobbie, Gillian Salcic, Zoran Liu, Meng Zhang, Jianbing Lyu, Lingjuan Zhang, Xuyun Department of Electrical Computer and Software Engineering The University of Auckland Auckland New Zealand School of Computer Science The University of Auckland Auckland New Zealand Department of Electrical and Computer Engineering The University of Auckland Auckland New Zealand School of Mechanical Electrical and Information Engineering Shandong University Weihai Shandong China Department of Computer Science and Technology Nanjing University Nanjing China Department of Computer Science National University of Singapore Singapore Department of Computing Macquarie University Sydney Australia

Recommender systems are important applications in big data analytics because accurate recommendation items or high-valued suggestions can bring high profit to both commercial companies and customers. To make precise recommendations, a recommender system often needs large and fine-grained data for training. In the current big data era, data often exists in the form of isolated islands, and it is difficult to integrate the data scattered due to privacy security concerns. Moreover, privacy laws and regulations make it harder to share data. Therefore, designing a privacy-preserving recommender system is of paramount importance. Existing privacy-preserving recommender system models mainly adapt cryptography approaches to achieve privacy preservation. However, cryptography approaches have heavy overhead when performing encryption and decryption operations and they lack a good level of flexibility. In this paper, we conduct privacy analysis on the existing locality sensitive hashing (LSH) approach based privacy-preserving recommender system and show how an attacker can retrieve user's information under such a recommender system. Given such privacy risks, we propose differentially private LSH approach to build recommender system that can offer differential privacy guarantees for users. Our proposed efficient and scalable federated recommender system can make full use of multiple source data from different data owners while guaranteeing privacy preservation of users' data in contributing parties. Extensive experiments on real-world benchmark datasets show that our approach can achieve both high time efficiency and accuracy under small privacy budgets. © 2021 John Wiley & Sons, Ltd.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Wavelength-multiplexed orbital angular momentum meta-holography

引用

PhotoniX 2024年第1期5卷 276-289页

作者： Jaehyuck Jang Seong-Won Moon Joohoon Kim Jungho Mun Stefan A.Maier Haoran Ren Junsuk Rho Department of Chemical Engineering Pohang University of Science and Technology(POSTECH)Pohang 37673Republic of Korea Department of Materials Science and Engineering Stanford UniversityStanfordCA 94305USA Department of Mechanical Engineering Pohang University of Science and Technology(POSTECH)Pohang 37673Republic of Korea School of Electrical and Computer Engineering Purdue UniversityWest LafayetteIN 47907USA School of Physics and Astronomy Monash UniversityMelbourneVIC 3800Australia Department of Physics Imperial College LondonLondon SW72AZUK Department of Electrical Engineering Pohang University of Science and Technology(POSTECH)Pohang 37673Republic of Korea POSCO-POSTECH-RIST Convergence Research Center for Flat Optics and Metaphotonics Pohang 37673Republic of Korea National Institute of Nanomaterials Technology(NINT) Pohang 37673Republic of Korea

The field of high-bandwidth holography has been extensively studied over the past *** angular momentum(OAM)holography,which utilizes vortex beams with theoretically unbounded OAM modes as information carriers,showcases the large capacitance of hologram ***,OAM holography has been limited to a single wavelength,restricting its potential for full-color holography and *** this study,we propose wavelength and OAM multiplexed holography that utilizes the multiple dimensions of light—wavelength and OAM—to provide a multi-color platform that expands the information capacity of holographic storage *** proposed wavelength-OAM multiplexed holography is physically realized by a metasurface,the state-of-the-art optical element consisting of an array of artificially engineered *** silicon meta-atoms,the constituents of the metasurface,are engineered to possess wavelength selectivity by tailoring the dispersion of polarization *** meta-atoms are used to encode the calculated OAM-preserved phase maps based on our *** sampling grid of the phase map is rotated by 45°,which effectively suppress higher-order diffraction,providing a great strategy for achieving large field-of-view(FOV)*** successfully demonstrate six holographic images that are selectively reconstructed under the illumination of light with specific wavelengths(λ=450,635 nm)and topological charges(l=-2,0,2),without high-order *** work suggests that ultrathin meta-holograms can potentially realize ultrahigh-bandwidth full-color holography and holographic video displays with large FOV.

关键词： Metasurface Meta-holography Wavelength-multiplexed holography OAM holography

来源：评论

学校读者我要写书评

暂无评论

Internal Short Circuit Detection for Parallel-Connected Battery Cells Using Convolutional Neural Network

引用

Automotive Innovation 2022年第2期5卷 107-120页

作者： Niankai Yang Ziyou Song Mohammad Reza Amini Heath Hofmann Department of Naval Architecture and Marine Engineering University of MichiganAnn ArborMI 48109USA Department of Mechanical Engineering National University of SingaporeSingapore 117575Singapore Department of Electrical Engineering and Computer Science University of MichiganAnn ArborMI 48109USA

Reliable and timely detection of an internal short circuit(ISC)in lithium-ion batteries is important to ensure safe and efficient *** paper investigates ISC detection of parallel-connected battery cells by considering cell non-uniformity and sensor limitation(i.e.,no independent current sensors for individual cells in a parallel string).To characterize ISC-related signatures in battery string responses,an electro-thermal model of parallel-connected battery cells is first established that explicitly captures *** analyzing the data generated from the electro-thermal model,the distribution of surface tem-perature among individual cells within the battery string is identified as an indicator for ISC detection under the constraints of sensor limitations.A convolutional neural network(CNN)is then designed to estimate the ISC resistance by using the cell surface temperature and the total capacity of the string as *** on the estimated ISC resistance from CNN,the strings are classified as faulty or non-faulty to guide the examination or replacement of the *** algorithm is evaluated in the presence of signal noises in terms of accuracy,false alarm rate,and missed detection rate,verifying the effectiveness and robustness of the proposed approach.

关键词： Internal short circuit Parallel-connected battery cells Convolutional neural network Cell temperature distribution

来源：评论

学校读者我要写书评

暂无评论

Deploying Faster R-CNN for Real-Time Tiger Monitoring in Wildlife Conservation 3

Deploying Faster R-CNN for Real-Time Tiger Monitoring in Wil...

引用

3rd International Conference on Automation, Computing and Renewable Systems, ICACRS 2024

作者： Saravanan, S. Raj, J. Relin Francis Rajkumar, G. Vinoth Kumar, C. Antony Vasantha Soundiraraj, N. Bharathi, K. Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai India Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Electronics and Communication Engineering J.P. College of Engineering Tenkasi India Department of Mechanical Engineering Rohini College of Engineering and Technology Kanyakumari India Department of Electrical and Electronics Engineering PSNA College of Engineering and Technology Dindigul India Department of Computer Science and Engineering SCAD College of Engineering and Technology Cheranmahadevi India

ISBN: (纸本)9798331532420

This study introduces a real-time tiger monitoring system built on the Faster R-CNN deep learning framework, designed to support wildlife conservation through accurate tiger detection and tracking. The primary aim is to effectively identify and monitor tigers across various environments, using an extensive dataset drawn from Google’s Open Images Dataset and further enriched with synthetic images created by Generative Adversarial Networks (GANs). These synthetic images simulate challenging conditions, such as low lighting and uncommon camera angles, to improve the model’s robustness and adaptability in field settings. The model is initialized with a pre-trained ResNet50 backbone, utilizing transfer learning to accelerate training while ensuring precise detection. Advanced techniques such as dynamic data augmentation and hard negative mining have been integrated to minimize false positives and increase model resilience. Hyperparameter tuning, including cyclical learning rate scheduling and anchor box optimization, is applied to maximize both accuracy and recall, refining the model's ability to capture tiger-specific features under diverse conditions. To facilitate real-time monitoring, the model is deployed on NVIDIA Jetson devices, supporting edge processing without relying on cloud-based infrastructure. This deployment strategy ensures efficient data processing in remote areas, where stable network connectivity may be limited. Non-Maximum Suppression is used to reduce duplicate detections, while a Kalman Filter maintains tracking stability across video frames, ensuring seamless observation of tigers in motion. This optimized Faster R-CNN-based approach enables high-accuracy, low-latency tiger detection, equipping conservationists with reliable data on tiger presence and movement patterns. By enhancing detection and tracking capabilities, this system aims to support informed decision-making in wildlife conservation and habitat management. © 2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Designing an Improved Deep Learning-Based Classifier for Breast Cancer Identification in Histopathology Images 12

Designing an Improved Deep Learning-Based Classifier for Bre...

引用

12th Iranian/2nd International Conference on Machine Vision and Image Processing, MVIP 2022

作者： Babaahmadi, Amirreza Khalafi, Sahar Esfahani, Fatemeh Malekipour University of Tehran School of Mechanical Engineering College of Engineering Tehran Iran Isfahan University of Technology Department of Electrical and Computer Engineering Isfahan Iran Concordia University Department of Mechanical Indistrial and Aerospace Engineering Montreal Canada

ISBN: (纸本)9781665412162

Cancer is a rampant phenomenon caused by uncontrollable cells that grow and spread throughout the body. Invasive Ductal Carcinoma 1 is the most common type of breast cancer, which can be fatal for females if not detected early. As a result, prompt diagnosis is critical to maximizing surveillance rates and, in the meantime, minimizing long-term mortality rates. Nowadays, modern computer vision and deep learning techniques have transformed the medical image analysis arena. computer vision application in medical image analysis has provided us with remarkable results, enhanced accuracy, and reduced costs. The main purpose of designing a new algorithm to detect unusual patches of breast images, was to acquire both high accuracy and low computational cost, simultaneously. Therefore, a novel architecture has been designed by utilizing Xception and *** new algorithm achieves 93.4% balanced accuracy and 94.8% for F1-Score, which outperforms previously published algorithms for identifying IDC histopathology images that use deep learning techniques. © 2022 IEEE.

关键词： Diagnosis

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：