检索结果-内蒙古大学图书馆

Performance Evaluation of Machine Learning Models for Predicting Energy Consumption and Occupant Dissatisfaction in Buildings

引用

BUILDINGS 2025年第1期15卷 39-39页

作者： Hosamo, Haidar Mazzetto, Silvia Prince Sultan Univ Dept Architecture SALab Sustainable Architecture Lab Riyadh 12435 Saudi Arabia Oslo Metropolitan Univ Dept Built Environm St Olavs PlassPOB 4 NO-0130 Oslo Norway

This study evaluates the performance of 15 machine learning models for predicting energy consumption (30-100 kWh/m2year) and occupant dissatisfaction (Percentage of Dissatisfied, PPD: 6-90%), key metrics for optimizing building performance. Ten evaluation metrics, including Mean Absolute Error (MAE, average prediction error), Root Mean Squared Error (RMSE, penalizing large errors), and the coefficient of determination (R2, variance explained by the model), are used. XGBoost achieves the highest accuracy, with an energy MAE of 1.55 kWh/m2year and a PPD MAE of 3.14%, alongside R2 values of 0.99 and 0.97, respectively. While these metrics highlight XGBoost's superiority, its margin of improvement over LightGBM (energy MAE: 2.35 kWh/m2year, PPD MAE: 3.89%) is context-dependent, suggesting its application in high-precision scenarios. ANN excelled at PPD predictions, achieving the lowest MAE (1.55%) and Mean Absolute Percentage Error (MAPE: 4.97%), demonstrating its ability to model complex nonlinear relationships. This nonlinear modeling advantage contrasts with LightGBM's balance of speed and accuracy, making it suitable for computationally constrained tasks. In contrast, traditional models like linear regression and KNN exhibit high errors (e.g., energy MAE: 17.56 kWh/m2year, PPD MAE: 17.89%), underscoring their limitations with respect to capturing the complexities of building performance datasets. The results indicate that advanced methods like XGBoost and ANN are particularly effective owing to their ability to model intricate relationships and manage high-dimensional data. Future research should validate these findings with diverse real-world datasets, including those representing varying building types and climates. Hybrid models combining the interpretability of linear methods with the precision of ensemble or neural models should be explored. Additionally, integrating these machine learning techniques with digital

关键词： machine learning models energy consumption prediction occupant dissatisfaction building performance optimization evaluation metrics advanced algorithms sustainable building management A comprehensive evaluation of 15 machine learning algorithms for dual-output predictions of energy consumption and occupant dissatisfaction, addressing a significant gap in existing research by combining energy and comfort modeling. This study employs 10 diverse evaluation metrics to provide a multidimensional analysis of model performance, emphasizing trade-offs among accuracy, computational efficiency, and reliability. Additionally, actionable insights into the suitability of specific algorithms, such as XGBoost and ANNs, are highlighted for their ability to handle complex datasets, advancing sustainable and occupant-focused building management in the Architecture, Engineering, and Construction (AEC) domain.

来源：评论

学校读者我要写书评

暂无评论

Voting-Based Intervention Planning Using AI-Generated Images

引用

IEEE Computer Graphics and Applications 2025年第02期45卷 31-46页

作者： Kavouras, Ioannis Rallis, Ioannis Sardis, Emmanuel Doulamis, Anastasios Doulamis, Nikolaos National Technical University of Athens Zografou15772 Greece

The continuous evolution of artificial intelligence and advanced algorithms capable of generating information from simplified input creates new opportunities for several scientific fields. Currently, the applicability of such technologies is limited to art and medical domains, but it can be applied to engineering domains to help the architects and urban planners design environmentally friendly solutions by proposing several alternatives in a short time. This work utilizes the image-inpainting algorithm for suggesting several alternative solutions to four European cities. In addition, this work suggests the utilization of a voting-based framework for finding the most preferred solution for each case study. The voting-based framework involves the participation of citizens and as a result decentralizes and democratizes the urban planning process. Finally, this research indicates the importance of deploying generative models in engineering applications, by proving that generative AI models are capable of supporting the architects and urban planners in urban planning procedures. © 1981-2012 IEEE.

关键词： Generative AI Artificial Intelligence Art Urban Planning Medical Diagnostic Imaging Image Synthesis Climate Change Visualization Diffusion Models Treatment Plan Urbanization Greenhouse Gas Design Process Effects Of Climate Change Heat Stress Urban Planning Urban Environments Democratization Planning Process Generative Adversarial Networks Diffusion Model Public Participation advanced algorithms Textual Descriptions Cross Case Analysis Urban Regeneration Planning Stage Urban Design Generation Algorithm Secret Ballot Voting Results Real Solution Assistive Tools Imaging Solutions Urban Resilience Architectural Design Creativity Aesthetic Appeal

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence and recommender systems in e-commerce. Trends and research agenda

引用

INTELLIGENT SYSTEMS WITH APPLICATIONS 2024年 24卷

作者： Valencia-Arias, Alejandro Uribe-Bedoya, Hernan Gonzalez-Ruiz, Juan David Santos, Gustavo Sanchez Ramirez, Edgard Chaponan Univ Senor Sipan Sch Ind Engn Chiclayo 14001 Peru Inst Tecnol Metropolitano Dept Ciencias Ambientales & Construcc Medellin 050034 Colombia Univ Nacl Colombia Dept Econ Grp Invest Finanzas & Sostenibilidad Medellin 050034 Colombia Univ Ricardo Palma Lima 15039 Peru Univ Senor Sipan Escuela Contabilidad Chiclayo 14001 Peru

Combining recommendation systems and AI in e-commerce can improve the user experience and decisionmaking. This study uses a method called bibliometrics to look at how these systems and artificial intelligence are changing. Of the 120 documents, 91 were analyzed. This shows a growth of 97.16% in the topic. The most influential authors were Paraschakis and Nilsson, with three publications and 43 citations. The magazine Electronic Commerce Research has four publications and 60 citations. China is the top country for citations, with 120, followed by India with 25 publications. The results show that research increased in 2021 and 2022. This shows a shift towards sentiment analysis and convolutional neural networks. The identification of new keywords, such as content-based image retrieval and knowledge graph, shows promising areas for future research. This study provides a solid foundation for future research in e-commerce recommender systems.

关键词： advanced algorithms User experience Sentiment analysis Convolutional Neural Networks PRISM-2020

来源：评论

学校读者我要写书评

暂无评论

Research on the Location Selection of R Enterprise's Distribution Center Based on Analytic Hierarchy Process and Grey Relational Degree Method 7

Research on the Location Selection of R Enterprise's Distrib...

引用

7th International Conference on Traffic Engineering and Transportation System (ICTETS)

作者： Song, Rui Liu, Yingxin Shenyang Univ Inst Informat Engn Shenyang Liaoning Peoples R China

ISBN: (纸本)9781510674479

Logistics distribution center is an important part of logistics system, whether its location is reasonable will directly affect the operational efficiency and economic benefits of logistics system. Scientific and reasonable location distribution can effectively reduce transportation costs, save distribution time and improve logistics service quality. In this paper, taking the location of distribution center of R enterprise as an example, the combination of hierarchical analysis and gray correlation method is used to clarify the relative relationship between the elements and the target decision by the gray correlation method, while the relative importance between the elements is chosen to analyze by the hierarchical analysis method, and finally the comprehensive correlation degree is calculated. The fusion of these two methods is an advanced algorithm.

关键词： logistics distribution center site selection Analytic hierarchy process Gray correlation degree method advanced algorithms

来源：评论

学校读者我要写书评

暂无评论

Predicting parameters and sensitivity assessment of nano-silica-based fiber-reinforced concrete: a sustainable construction material

引用

JOURNAL OF MATERIALS RESEARCH AND TECHNOLOGY-JMR&T 2023年 23卷 3943-3960页

作者： Amin, Muhammad Nasir Khan, Kaffayatullah Sufian, Muhammad Al-Ahmad, Qasem M. S. Deifalla, Ahmed Farouk Alsharari, Fahad King Faisal Univ Coll Engn Dept Civil & Environm Engn Al Hasa 31982 Saudi Arabia Southeast Univ Sch Civil Engn Nanjing 210096 Peoples R China Future Univ Egypt Struct Engn & Construction Management Dept New Cairo 11835 Egypt Jouf Univ Coll Engn Dept Civil Engn Sakakah 72388 Saudi Arabia

This study evaluates the compressive strength (C-S) of nano-silica-based fiber-reinforced concrete (NS-FRC) by using advanced machine learning (ML) individual and ensembled techniques. The employed advanced ML approaches used for the analysis are Support Vector Machine (SVM), Multi-Layer Perceptron (MLP) and eXtreme Gradient Boosting (XGB). Furthermore, the level of accuracy for the employed advanced algorithms is also evaluated by the k-fold cross-validation technique. Statistical checks, i.e., root mean square error (RMSE), mean absolute error (MAE) and mean absolute percent error (MAPE), are also applied to validate the performance of algorithms. Sensitivity analysis is also made to explore the influence of input parameters on the C-S of NS-FRC. Among all, the XGB technique is found most effective for an accurate C-S prediction of NS-FRC. In XGB model, the coefficient of determination (R2) is 0.95, which is comparatively more than that of SVM (0.90) and MLP (0.90). The MAE value of XGB algorithm is 3.3 MPa which is lower than that of SVM (4.8 MPa) and MLP (4.5 MPa). In addition, RMSE value is also less for XGB algorithm (3.8 MPa) as compared to that of SVM (5.5 MPa) and MLP (5.9 MPa). Furthermore, the employed XGB models exhibited highest R2 of 0.95 as compared to the models reported in the available literature. The sensitivity analysis revealed that the nano-silica influenced the C-S of NS-FRC by 7%. Moreover, discussion reveals that nano-silica in concrete can have several benefits, such as improved microstructure, enhanced strength, prolonged durability, reduced cement content, and less carbon emission.(c) 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Sustainable construction Nano-silica NS-FRC Compressive strength advanced algorithms XGBoost

来源：评论

学校读者我要写书评

暂无评论

Experiences and Proposals of Use of Generative AI in advanced Software Courses 15

Experiences and Proposals of Use of Generative AI in Advance...

引用

15th IEEE Global Engineering Education Conference (IEEE EDUCON)

作者： Palacios-Alonso, Daniel Urquiza-Fuentes, Jaime Angel Velazquez-Iturbide, J. Guillen-Garcia, Julio Univ Rey Juan Carlos Dept Comp & Stat Madrid Spain

ISBN: (纸本)9798350394023;9798350394030

the last year, we have witnessed the popularization of generative artificial intelligence. Its output includes text, code, image, audio, speech, voice, music, and video. Therefore, it impacts education courses where students are required to elaborate on any of these artifacts. In particular, the generation of code affects informatics courses, where assignments usually ask students to develop and deliver programming code. The impact of generative artificial intelligence on informatics courses has been mainly studied for introductory programming courses. These studies have shown that generative artificial intelligence is able to produce highly sophisticated programs, but also that its results and rationale can be inaccurate. Moreover, the impact of generative artificial intelligence has not been studied for other informatics subjects. In this paper, we present our preliminary experience and proposals on three advanced software courses, namely video games, advanced algorithms and language processors. For the video games course, we present the opportunities of use of generative artificial intelligence and the results of a survey conducted with students on their use to obtain different media products. For the algorithms course, we present the result of a session driven by the instructor on different design techniques, showing the merits and demerits of the answers generated. For the language processors course, a proposal of use of generative artificial intelligence is presented, broken down into the parts of a typical language processor. The paper concludes with some suggestions for instructors.

关键词： informatics education generative artificial intelligence video games advanced algorithms language processors

来源：评论

学校读者我要写书评

暂无评论

'Enhancing Stroke Prediction with Machine Learning in Smart Healthcare Systems' 15

'Enhancing Stroke Prediction with Machine Learning in Smart ...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Nayak, Shivam Gupta, Nishi Chandigarh University Department of Mathematics Gharauan Punjab Mohali India

ISBN: (纸本)9798350370249

New approaches to early detection and early treatment are needed because it is a most concern cause of increase in cases of Brain deaths. Goal of this work is to increase the accuracy and timeliness of stroke risk assessments by providing a model employing machine learning for stroke prediction. Using a variety of datasets that include both established risk variables and recently developed predictors, the model makes use of sophisticated algorithms to identify complex patterns suggestive of future stroke occurrences. The model's effectiveness in early identification is demonstrated by the results, providing a viable path for proactive healthcare interventions. By highlighting incredible potential in ML in lower down the affect in strokes, the study adds to the changing field of preventative medicine © 2024 IEEE.

关键词： advanced algorithms Clinical Decision Support Data-driven Healthcare Early Detection Health Outcomes Healthcare Analytics Healthcare Data Healthcare Informatics Healthcare Innovation Innovative Health Technologies Machine Learning Morbidity and Mortality Patient Risk Profiling Personalized Healthcare Predictive Modelling Preventive Medicine Proactive Interventions Public Health Risk Assessment Stroke Prediction Model

来源：评论

学校读者我要写书评

暂无评论

Advancing Edge Computing Paradigms with Novel Architectures and algorithms for Real-Time Processing 2

Advancing Edge Computing Paradigms with Novel Architectures ...

引用

2nd International Conference Computational and Characterization Techniques in Engineering and Sciences, IC3TES 2024

作者： Ramesh, P.S. Mathu Sudhanan, S.R. Dineshkumar, R. Manigandan, K. Parthipan, V. Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Care College of Engineering Department of Computer Science and Engineering Tamil Nadu Trichy India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Chennai India Mohan Babu University School of Liberal Arts & Sciences Department of English Andhra Pradesh Tirupati India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350364699

This paper focuses on the advancements of the edge computing paradigms regarding the creation of new emerging architectures and algorithms for improving real-time computing. Looking at the results obtained, the proposed architecture provided 40% reduced latency rates, and 50% higher throughput than the baseline models while using 20% less energy. Key algorithms, including data compression, stream processing, and adaptive algorithms, were evaluated, with the hybrid approach showing the most significant improvements: The improvements were made in the latency where there was a 50% decrease in the latency and in the throughput where there was a 40% increase, and in the accuracy which is 30% enhanced. The above outcomes demonstrate the efficiency of offered solutions in the context of the discussed problems of real-time data processing;the recognition of the edge computing prospects regarding the further evolution of different applications. © 2024 IEEE.

关键词： Adaptive algorithms advanced algorithms Data Compression Edge Computing Energy Efficiency Latency Reduction Novel Architectures Real-Time Processing Stream Processing Throughput Improvement

来源：评论

学校读者我要写书评

暂无评论

Evaluation of lateral and axial resolution of pixel-based beamformers in photoacoustic tomography using a linear US probe

Evaluation of lateral and axial resolution of pixel-based be...

引用

IEEE International Ultrasonics Symposium (IUS)

作者： Pi-Martin, Irene Cebrecos, Alejandro Garcia-Garrigos, Juan J. Jimenez, Noe Camarena, Francisco Univ Politecn Valencia CSIC Inst Instrumentac Imagen Mol i3M Valencia Spain

ISBN: (数字)9781665466578

ISBN: (纸本)9781665466578

Many photoacoustic tomography (PAT) systems have been developed using conventional linear ultrasound probes with reduced angular spectra, which limits the resolution of tomographic reconstructions. These limitations are partially compensated by employing advanced reconstruction algorithms that take advantage of the intrinsic characteristics of the photoacoustic signals. The aim of this work is to theoretically, numerically and empirically characterise the lateral and axial resolution using two nearby point objects that are separated until they can be distinguished as two independent sources in the reconstructed image. It is also intended to study the effect of the main limitations of linear probes (geometry, frequency response and angular spectrum) on the spatial resolution. The results of this study shed light on the suitability of using each type of algorithm depending on the limiting conditions of the probe used and the imaging objective.

关键词： photoacoustics tomography resolution advanced algorithms

来源：评论

学校读者我要写书评

暂无评论

Overview of the PI (2DoF) algorithm in wind power system optimization and control

引用

FRONTIERS IN ENERGY RESEARCH 2024年 12卷

作者： Desalegn, Belachew Tamrat, Bimrew Bahir Dar Univ Bahir Dar Inst Technol Bahir Dar Energy Ctr Bahir Dar Ethiopia Wolaita Sodo Univ Coll Nat & Computat Sci Dept Phys Wolaita Sodo Ethiopia Bahir Dar Univ Bahir Dar Inst Technol Fac Mech & Ind Engn Bahir Dar Ethiopia

Recent research generally reports that the intermittent characteristics of sustainable energy sources pose great challenges to the efficiency and cost competitiveness of sustainable energy harvesting technologies. Hence, modern sustainable energy systems need to implement a stringent power management strategy to achieve the maximum possible green electricity production while reducing costs. Due to the above-mentioned characteristics of sustainable energy sources, power management systems have become increasingly sophisticated nowadays. For addressing the analysis, scheduling, and control problems of future sustainable power systems, conventional model-based methods are completely inefficient as they fail to handle irregular electric power disturbances in renewable energy generations. Consequently, with the advent of smart grids in recent years, power system operators have come to rely on smart metering and advanced sensing devices for collecting more extensive data. This, in turn, facilitates the application of advanced machine learning algorithms, which can ultimately cause the generation of useful information by learning from massive data without assumptions and simplifications in handling the most irregular operating behaviors of the power systems. This paper aims to explore various application objectives of some machine learning algorithms that primarily apply to wind energy conversion systems (WECSs). In addition, an enhanced proportional integral (PI) (2DoF) algorithm is particularly introduced and implemented in a doubly fed induction generator (DFIG)-based WECS to enhance the reliability of power production. The main contribution of this article is to leverage the superior qualities of the PI (2DoF) algorithm for enhanced performance, stability, and robustness of the WECS under uncertainties. Finally, the effectiveness of the study is demonstrated by developing a virtual reality in a MATLAB-Simulink environment.

关键词： wind power system doubly fed induction generator-based wind energy conversion system optimization and control advanced algorithms proportional integral (2DoF)

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：