检索结果-内蒙古大学图书馆

Semantic process mining: A conceptual application of main tools, framework and model analysis

International Journal of Hybrid Intelligent Systems 2020年第3期16卷 127-147页

作者： Okoye, Kingsley Writing Lab TecLabs Vicerrectoría de Investigación y Transferencia de Tecnología Tecnologico de Monterrey CP Nuevo Leon Monterrey 64849 Mexico School of Architecture Computing and Engineering College of Arts Technologies and Innovation University of East London E16 2RD United Kingdom

Semantics has been a major challenge when applying the process mining (PM) technique to real-time business processes. The several theoretical and practical efforts to bridge the semantic gap has spanned the advanced notion of the semantic-based process mining (SPM). Fundamentally, the SPM devotes its methods to the idea of making use of existing (semantic) technologies to support the analysis of PM techniques. In principle, the semantic-based process mining method is applied through the acquisition and representation of abstract knowledge about the domain processes in question. To this effect, this paper demonstrates how the semantic concepts and process modelling (reasoning) methods are used to improve the outcomes of PM techniques from the syntactic to a more conceptual level. To do this, the study proposes an SPM-based framework that shows to be intelligent with a high level of semantic reasoning aptitudes. Technically, this paper introduces a process mining approach that uses information (semantics) about different activities that can be found in any given process to make inferences and generate rules or patterns through the method for annotation, semantic reasoning, and conceptual assertions. In turn, the method is theoretically applied to enrich the informative values of the resultant models. Also, the study conducts and systematically reviews the current tools and methods that are used to support the outcomes of the process mining as well as evaluates the results of the different methods to determine the levels of impact and its implications for process mining. © 2020 - IOS Press and the authors. All rights reserved.

关键词： annotation events log ontologies process mining process models Semantic modelling semantic reasoning

来源：评论

学校读者我要写书评

暂无评论

Cloud-based remote control framework for unmanned surface vehicles ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 14564-14569页

作者： Zhao Wang Shaolong Yang Xianbo Xiang Antonio Vasilijević Nikola Mišković Ðula Nađ School of Naval Architecture and Ocean Engineering Huazhong University of Science and Technology Wuhan 430074 China Hubei Key Laboratory of Naval Architecture and Ocean Engineering Hydrodynamics (HUST) Wuhan 430074 PR China Laboratory for Underwater Systems and Technologies Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia

This paper proposes a cloud-based mission control framework for a fleet of unmanned vehicles. The framework enables easy remote access to fleet operations regardless of operator location. By leveraging cloud-based technologies the framework accomplishes scalable monitoring, remote control, data acquisition and sharing. While the front-end is applicable across mobile robotic systems, the back-end presented in this paper provides integration with the Robot Operating System (ROS); thus, enabling integration of various marine robotic agents based on the same robot framework. The proposed framework operation is demonstrated on the H2OmniX unmanned surface vehicles during trials in Biograd na Moru, Croatia.

关键词： remote control distributed control cloud-based control Robot Operating System

来源：评论

学校读者我要写书评

暂无评论

Predicting the Governing Factors for the Release of Colloidal Phosphorus Using Machine Learning

SSRN

引用

SSRN 2024年

作者： Khan, Sangar Gao, Huimin Milham, Paul J. Eltohamy, Kamel Mohamed Ullah, Habib Mu, Hongli Gao, Meixiang Yang, Xiaodong Hamid, Yasir Hooda, Peter S. Shaheen, Sabry M. Wu, Naicheng Department of Geography and Spatial Information Techniques Ningbo University Ningbo315211 China Hawkesbury Institute for the Environment University of Western Sydney LB 1797 PenrithNSW2751 Australia Water Relations and Field Irrigation Department Agricultural and Biological Research Division National Research Centre Cairo12622 Egypt College of Environmental Resource Sciences Zhejiang University Hangzhou310058 China Innovation Center of Yangtze River Delta Zhejiang University Zhejiang311400 China Faculty of Engineering Computing and the Environment Kingston University London United Kingdom University of Wuppertal School of Architecture and Civil Engineering Laboratory of Soil Groundwater Management Pauluskirchstraße 7 Wuppertal42285 Germany

The use of machine learning models in predicting the important variable for colloidal-phosphorus (P) release from soils is a relatively new area of research. Therefore, in this study, we investigated the major determinants of colloidal-P release from different land use/types such as farmland, desert, and forest soils and rivers. The study utilizes the structural equation model (SEM), multiple linear regression (MLR), and three learning models (Random Forest (RF), Support Vector Regression (SVR), and Shapley Additive exPlanations eXtreme Gradient Boosting (SHAP XGBoost)) to predict the release of colloidal-P from different soils by using soil iron (Fe), aluminum (Al), calcium (Ca), pH, total organic carbon (TOC) and precipitation as independent variables. Results show that colloidal-cations (Fe, Al, Ca) and colloidal-TOC strongly influence colloidal-P release, with bioclimatic variables and pH having weaker effects. The SHAP Xgboost model outperforms the other models, with an R2 value of 0.94 and an RMSE of 0.09. The relative importance ranking of the variables for predicting the release of colloidal-P from soils to water is consistent across all three models, with colloidal TOC ranked as the most important factor followed by colloidal-Ca, colloidal-Al, and precipitation. Partial dependence plot analysis demonstrates that increasing colloidal TOC leads to increased soil colloidal-P release. According to our research, the SHAP XGBoost model provides significant information that can help determine the variables that considerably influence CP contents as compared to RF, SVM, and MLR. © 2024, The Authors. All rights reserved.

关键词： Soils

来源：评论

学校读者我要写书评

暂无评论

Thermal conductivity and rheological behavior of silica / simulated body fluid - Dispersed Hardystonite and Åkermanite nanofluids: X-ray diffraction to analyze structure and morphology of a bio-ceramic

引用

International Communications in Heat and Mass Transfer 2025年 165卷

作者： Liu, Shulong Saidani, Taoufik Feng, Dulong Alawi, Mohammed Jameel Hussien, Mohamed Deebani, Wejdan Anhui Province Key Laboratory of Intelligent Computing and Applications Huaibei Normal University Huaibei235000 China Anhui Province Industrial Generic Technology Research Center for Alumics Materials Huaibei Normal University Huaibei235000 China School of Physics and Electronic Information Huaibei Normal University Huaibei235000 China Center for Scientific Research and Entrepreneurship Northern Border University Arar73213 Saudi Arabia Anhui Guangbo Mechanical Electronic Manufacturing Co. Ltd. Huaibei235000 China Electrical Engineering Department College of Engineering and Architecture Umm Al-Qura University Makkah Saudi Arabia Department of Chemistry Faculty of Science King Khalid University P.O. Box 9004 Abha61413 Saudi Arabia Department of Mathematics College of Science & Arts King Abdul Aziz University Rabigh21911 Saudi Arabia

Bioceramics are integral in biomedical applications due to their biocompatibility, bioactivity, and mechanical properties. This study compares the thermal and rheological behavior of two hybrid bio-nanofluids (bi-ns): Hardystonite/Silica and Åkermanite/Silica dispersed in simulated body fluid (SBF). Nanoparticle morphology and composition were analyzed using X-ray diffraction (XRD) and field emission scanning electron microscopy (FESEM), confirming the crystalline phases of both composites. Åkermanite/Silica showed better dispersion stability, with a higher zeta potential (−16.19 mV) than Hardystonite/Silica (−7.23 mV). The addition of silica (SiO2) improved stability for both, with zeta potential increases of ∼203 % and 69 %, respectively. Thermal conductivity of both nanofluids increased with temperature and volume fraction, with Åkermanite/Silica achieving a maximum enhancement of 13.16 % (20–40 °C). However, both showed negative thermal conductivity enhancements compared to SBF, especially at higher concentrations. Hardystonite/Silica demonstrated greater thermal compatibility with SBF. Rheologically, both nanofluids exhibited shear-thinning behavior. Hardystonite/Silica showed a stronger reduction in viscosity with temperature increase—up to 43.43 % at 0.25 % volume fraction—compared to 32.74 % for Åkermanite/Silica. These results highlight the interaction between thermal and flow properties in bi-ns, indicating that Hardystonite/Silica may be better suited for applications requiring thermal compatibility and viscosity control. The findings contribute to the optimization of hybrid nanofluids for bone-related biomedical applications. © 2025 Elsevier Ltd

关键词： Medical nanotechnology

来源：评论

学校读者我要写书评

暂无评论

A multi-material extrusion nozzle for functionally graded concrete printing 2

A multi-material extrusion nozzle for functionally graded co...

引用

2nd International Conference on Sustainable Smart Manufacturing, S2M 2019

作者： Craveiro, F. Bártolo, H. Duarte, J.P. Bártolo, P.J. CIAUD Lisbon School of Architecture Universidade de Lisboa Portugal School of Technology and Management Polytechnic of Leiriat Portugal Stuckeman Center for Design Computing Stuckeman School of Architecture and Landscape Architecture Penn State University United States School of Mechanical Aerospace and Civil Engineering The University of Manchester United Kingdom

ISBN: (纸本)9780367422721

3D printing (3DP) is one of the breakthrough innovations for architecture, engineering and the construction industry. However, most 3DP technologies are limited to the design and fabrication of physical parts with homogeneous material properties, assuring structural safety but with no efficient use of material resources. A different strategy must be used to produce building components with varying material constituent or distribution. A Computational Fluid Dynamics (CFD) analysis was carried out to simulate the behavior of two 3D printing print-heads designed to combine two different materials, one composed by a simple "Y" shape, and the other integrating a dynamic mixing rod. The dynamic one presents a good mixing behavior, allowing to produce building components with locally optimized performance. Future work will include experimental tests and the analysis of new materials to compare simulated and experimental material behaviors. © 2021 Taylor & Francis Group, London.

关键词： 3D printers

来源：评论

学校读者我要写书评

暂无评论

Identifying Users with Wearable Sensors based on Activity Patterns

引用

Procedia Computer Science 2020年 177卷 8-15页

作者： Muhammad Ehatisham-ul-Haq Maryam Naseer Malik Muhammad Awais Azam Usman Naeem Asra Khalid Mustansar Ali Ghazanfar Department of Computer Engineering University of Engineering and Technology Taxila Punjab 47050 Pakistan Whitecliffe Technologies Wellington New Zealand School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom School of Engineering & Computer Science Victoria University of Wellington New Zealand School of Architecture Computing and Engineering University of East London United Kingdom

We live in a world where ubiquitous systems surround us in the form of automated homes, smart appliances and wearable devices. These ubiquitous systems not only enhance productivity but can also provide assistance given a variety of different scenarios. However, these systems are vulnerable to the risk of unauthorized access, hence the ability to authenticate the end-user seamlessly and securely is important. This paper presents an approach for user identification given the physical activity patterns captured using on-body wearable sensors, such as accelerometer, gyroscope, and magnetometer. Three machine learning classifiers have been used to discover the activity patterns of users given the data captured from wearable sensors. The recognition results prove that the proposed scheme can effectively recognize a user’s identity based on his/her daily living physical activity patterns.

关键词： Activity recognition machine learning user identification wearable sensors

来源：评论

学校读者我要写书评

暂无评论

MAPA: Multi-accelerator pattern allocation policy for multi-tenant GPU servers

arXiv

引用

arXiv 2021年

作者： Ranganath, Kiran Suetterlein, Joshua D. Manzano, Joseph B. Song, Shuaiwen Leon Wong, Daniel Department of Electrical and Computer Engineering University of California RiversideCA United States High-Performance Computing Group Pacific Northwest National Lab WA United States Future System Architecture Lab School of Computer Science University of Sydney SydneyNSW Australia

Multi-accelerator servers are increasingly being deployed in shared multi-tenant environments (such as in cloud data centers) in order to meet the demands of large-scale compute-intensive workloads. In addition, these accelerators are increasingly being inter-connected in complex topologies and workloads are exhibiting a wider variety of inter-accelerator communication patterns. However, existing allocation policies are ill-suited for these emerging use-cases. Specifically, this work identifies that multi-accelerator workloads are commonly fragmented leading to reduced bandwidth and increased latency for inter-accelerator communication. We propose Multi-Accelerator Pattern Allocation (MAPA), a graph pattern mining approach towards providing generalized allocation support for allocating multi-accelerator workloads on multi-accelerator servers. We demonstrate that MAPA is able to improve the execution time of multi-accelerator workloads and that MAPA is able to provide generalized benefits across various accelerator topologies. Finally, we demonstrate a speedup of 12.4% for 75th percentile of jobs with the worst case execution time reduced by up to 35% against baseline policy using MAPA. © 2021, CC BY-NC-SA.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Referee: A Pattern-Guided Approach for Auto Design in Compiler-Based Analyzers

Referee: A Pattern-Guided Approach for Auto Design in Compil...

引用

IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)

作者： Fang Lv Hao Li Lei Wang Ying Liu Huimin Cui Jingling Xue Xiaobing Feng SKL Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science and Engineering University of New South Wales Australia

ISBN: (数字)9781728151434

ISBN: (纸本)9781728151441

Coding rules become more critical for security-oriented softwares, which prefer compilers as their base platforms due to simultaneous demands not only in a mature grammatical analysis, but also in compilation and optimization techniques. However, engineering such a compiler-based analyzer, exploring proper launch points before integrating hundreds of rules one by one in the frontend of compilers, is a completely manual decision-making process with heavy redundant efforts exhausted. To improve this, we introduce a novel pattern-guided approach, named Referee, to facilitate this process. Referee improves the manual approach significantly by making three advances: (1) our pattern-guided approach can significantly reduce the amount of redundant manual efforts required, (2) a twin-graph aided broadcasting process is developed to enable rule patterns to be characterized with partially developed rules, and (3) a reliable recommendation mechanism is used to pinpoint the launch point for a new rule based on the accumulated experience from handling earlier rules. We have implemented Referee in GCC 8.2 with 163 rules from SPACE-C and MISRA-C standards. Referee achieves an accuracy of 89.9% on recommendation of launch points for new rules to our GCC-based analyzer automatically when trained with 70% of all the rules. Decreasing the training data size to 60% and 50% still yields an accuracy of 87.7% and 81.5%, respectively. Therefore, Referee can significantly reduce the amount of manual efforts that would otherwise be required, with a careful selection of seeding rule patterns, providing an interesting and fruitful avenue for further research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Cross-layer Mobile Data-gathering Protocol for Underwater Sensor Networks

A Novel Cross-layer Mobile Data-gathering Protocol for Under...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Faisal Abdulaziz Alfouzan Seyed Mohammad Ghoreyshi Alireza Shahrabi Mahsa Sadeghi Ghahroudi College of Engineering and Architecture Al Yamamah University Riyadh Saudi Arabia School of Mathematical Sciences University of Southampton Southampton UK School of Computing Engineering and Built Environment Glasgow Caledonian University Glasgow UK

ISBN: (数字)9781728152073

ISBN: (纸本)9781728140537

In this paper, a novel Cross-Layer Mobile Data gathering (CLMD) scheme for Underwater Sensor Networks (UWSNs) is presented to improve the performance with a cross-layer design in the MAC and routing layer. CLMD develops a distributed cross-layer mobile data gathering solution that allows multiple sensors to efficiently and fairly share the bandwidth-limited high-delay underwater acoustic medium and aggregate data packets in a group of cluster heads which are visited by Autonomous Underwater Vehicle (AUV) in the periodic tours. The network lifetime is prolonged by reselecting the cluster heads in the different operational phases while the tour length is kept short to reduce the latency. The effectiveness of CLMD is validated through an extensive simulation study which reveals the performance improvement in the energy-saving, network lifetime, and packet delivery ratio.

关键词： Distributed databases Media Access Protocol Wireless sensor networks Bandwidth Sensor phenomena and characterization

来源：评论

学校读者我要写书评

暂无评论

Study on Deep Reinforcement Learning for Multi-Task Scheduling in Cloud Manufacturing

SSRN

引用

SSRN 2022年

作者： Xiao, Jiuhong Cai, Yishuai Wang, Wanru Chen, Yong College of Economic and Social Development Nankai University Tianjin300072 China Institute for Quantum Information State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha410073 China School of Information Management and Artificial Intelligence Zhejiang University of Finance and Economics Hangzhou310018 China College of Civil Engineering and Architecture Zhejiang University Hangzhou310058 China

Cloud manufacturing is an emerging manufacturing paradigm, which enables the simultaneous processing of multiple manufacturing tasks submitted by customers through centralized management and planning of manufacturing services offered by distributed enterprises. To date, various meta-heuristics algorithms such as ant colony optimization algorithm, and genetic algorithm have been widely employed to solve the cloud manufacturing multi-task scheduling (CMMS) problem to improve the efficiency of multi-task scheduling. However, these algorithms need sophisticated design procedures and laborious parameter tuning, making their adaptation to dynamic, large-scale manufacturing environments difficult. Deep reinforcement learning (DRL), because of its efficiency and flexibility, has recently attracted increasing attention from researchers and has shown promising performance in solving combinatorial optimization problems. Nevertheless, little is known about the performance of DRL technologies in solving the CMMS problem. Therefore, in this study, three state-of-the-art DRL technologies, including proximal policy optimization (PPO), deep deterministic policy gradient, and normalized advantage function, are selected to systematically investigate the potential of DRL in solving the CMMS problem. A comprehensive comparison of these DRL technologies is conducted in terms of effectiveness and efficiency, robustness and adaptability, and scalability. Experimental results indicate that PPO is superior to other technologies in solving the CMMS problem. © 2022, The Authors. All rights reserved.

关键词： Reinforcement 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：