Article
Computer Science, Artificial Intelligence
M. Tanveer, A. Tiwari, R. Choudhary, M. A. Ganaie
Summary: This study proposes a novel large scale pinball twin support vector machine (LPTWSVM) to address the limitations of the twin support vector machines (TWSVMs), using a unique pinball loss function and improving model performance by eliminating matrix inversion calculation and minimizing structural risk.
Article
Engineering, Industrial
Chukwuka Christian Ohueri, Md Asrul Nasid Masrom, Hadina Habil, Mohamud Saeed Ambashe
Summary: This study provides insights into the challenges and enablers of implementing IoT-DT for reducing ROC emissions in buildings. By analyzing questionnaire data and interview findings, the study establishes best practices that can strategically strengthen enablers and mitigate challenges, contributing to the successful implementation of IoT-DT for ROC emissions in buildings.
ENGINEERING CONSTRUCTION AND ARCHITECTURAL MANAGEMENT
(2023)
Article
Computer Science, Artificial Intelligence
Zhizheng Liang, Lei Zhang
Summary: In this paper, novel twin support vector machines (TSVMs) are proposed to handle uncertain data, where each uncertain sample is modeled as a random vector with Gaussian distributions. By deriving an important theorem to simplify the models and using a quasi-Newton optimization algorithm, the optimization problem becomes tractable. Experimental results show that the proposed models outperform some existing algorithms in terms of classification performance, especially for uncertain cross-plane problems.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
H. Moosaei, S. Ketabchi, M. Razzaghi, M. Tanveer
Summary: In this paper, two efficient approaches of twin support vector machines (TWSVM) are proposed, including reformulating the formulation by introducing different norms and presenting an efficient algorithm using the generalized Newton's method. Experimental results demonstrate that the new methods outperform baseline methods in terms of performance and computational time.
NEURAL PROCESSING LETTERS
(2021)
Article
Green & Sustainable Science & Technology
Rafael Gomes Alves, Rodrigo Filev Maia, Fabio Lima
Summary: This paper presents a digital twin model of a smart irrigation system, which utilizes an internet of things platform and a discrete event simulation model to enable automatic data flow and interaction. The system allows farmers to evaluate the behavior and test different irrigation strategies, leading to improvements in agricultural operations and water usage reduction.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Computer Science, Artificial Intelligence
Jiamin Xu, Huamin Wang, Libo Zhang, Shiping Wen
Summary: In this paper, a twin depth support vector machine (TDSVM) is proposed, which considers the influence of depth when calculating the distance. By strengthening the center and weakening the edge, a robust SVM framework is constructed, which can identify outliers in the dataset and achieve better generalization performance.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Xijiong Xie, Yanfeng Li, Shiliang Sun
Summary: This paper proposes two novel multi-view deep models, namely DMvTSVM based on DNN and AE network, to optimize the classification performance of each view by finding non-parallel hyperplanes and using similarity regularization and weight adjustment strategy to improve the model performance.
INFORMATION FUSION
(2023)
Article
Computer Science, Information Systems
Chenyu Wang, Zhipeng Cai, Yingshu Li
Summary: As the number of IoT devices increases, sustainability is becoming a bottleneck in industrial systems. Digital twin (DT) technology plays a promising role in facilitating interaction between IoT assets and digital services. However, high-fidelity models of DTs require efficient data flows, which are limited by factors such as data collection strategy and energy supply.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Artificial Intelligence
Pei-Yi Hao
Summary: This article introduces a novel asymmetric dual-regression model that combines twin-support vector machine theory with the principles of possibilistic regression analysis, providing better modeling of data distribution and confidence measure for predicted outputs. The proposed approach efficiently solves multiple smaller problems during training, leading to reduced time cost.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2021)
Article
Computer Science, Cybernetics
M. Tanveer, M. Tabish, Jatin Jangir
Summary: Analyzing unlabeled data and identifying underlying clustering principles is essential in various fields. Novel unsupervised machine learning algorithms, such as TBSVC, are developed for this purpose. However, TBSVC is sensitive to noise and lacks resampling stability. A new method, pinSTBSVC, uses a pinball loss function to improve sparsity and performance in plane-based clustering algorithms. Experimental results show that pinSTBSVC outperforms existing methods, demonstrating its effectiveness in real-world datasets and applications.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
M. A. Ganaie, M. Tanveer, Alzheimer's Disease Neuroimaging Initiative
Summary: This paper introduces a novel fuzzy least squares projection twin support vector machines for class imbalance learning, which outperforms baseline models in experiments.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Information Systems
Jayson P. Van Marter, Anand G. Dabak, Naofal Al-Dhahir, Murat Torlak
Summary: Ranging solutions for IoT localization applications aim to achieve high accuracy at low cost using Bluetooth low energy (BLE) technology. However, accurately measuring the distance with BLE poses challenges due to multipath components and model imperfections. To address this, we propose a data-driven SVR method that achieves decimeter-level accuracy with single antenna devices, outperforming the model-based MUSIC method which requires multiple antennas. Our method also proves robust in various multipath environments and offers computational complexity reduction compared to MUSIC.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Urban Studies
Gary White, Anna Zink, Lara Codeca, Siobhan Clarke
Summary: A digital twin is a digital representation of a physical process, place, system or device, originally designed for manufacturing processes but now used for smart city planning. By creating digital twin smart cities, the public can view 3D models of cities online to provide feedback, enhancing transparency and interaction in urban planning.
Article
Computer Science, Artificial Intelligence
Ankush Manocha, Yasir Afaq, Munish Bhatia
Summary: Since the development of smart healthcare services, different solutions, such as combining IoT, DT, FoT, CoT, and Blockchain, have been developed to increase patient's life expectancy by reducing healthcare cost. The proposed smart context-aware physical activity monitoring framework employs deep learning to analyze the physical movements of the elderly and detect irregular physical events in real time. Moreover, the framework ensures data security using advanced features of blockchain and demonstrates the effectiveness of DT in smart healthcare solutions. The proposed methodology's performance is evaluated in terms of event recognition, model training and testing, latency rate, and data processing cost.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Business
Sachin S. Kamble, Angappa Gunasekaran, Harsh Parekh, Venkatesh Mani, Amine Belhadi, Rohit Sharma
Summary: A digital twin is an integration of virtual and physical systems using disruptive technologies to develop sustainable, intelligent manufacturing systems. This paper presents a systematic literature review on digital supply chain twin dimensions with sustainable performance objectives and suggests that advancements in technologies have increased the potential of digital twin applications in the supply chain. The results indicate the need for a digital supply chain twin to include the entire supply chain and provide a framework for implementation.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2022)
Article
Green & Sustainable Science & Technology
Zhan-Sheng Liu, Xin-Tong Meng, Ze-Zhong Xing, Cun-Fa Cao, Yue-Yue Jiao, An-Xiu Li
Summary: This article proposes an intelligent safety risk prediction framework for prefabricated construction hoisting. It can predict hoisting risk in real-time and investigate the spatial-temporal evolution law of the risk. By building a multi-dimensional and multi-scale Digital Twin model and utilizing the Digital Twin-Support Vector Machine algorithm, the safety management level of prefabricated hoisting has been improved.
Article
Chemistry, Multidisciplinary
Jingjing Wang, Ke Pan, Cong Wang, Wenxiang Liu, Jiajia Wei, Kun Guo, Zhansheng Liu
Summary: This study assesses the carbon emissions in the bridge construction stage using the life cycle assessment method and establishes a carbon cost calculation model. The monetization of carbon emissions helps clarify the environmental impact of bridge construction and should be included in cost accounting.
APPLIED SCIENCES-BASEL
(2022)
Article
Multidisciplinary Sciences
Guoliang Shi, Zhansheng Liu, Xiaolin Meng, Zeqiang Wang
Summary: This study proposes an intelligent method for the health monitoring of cable network structures, based on the fusion of twin simulation and sensory data. It establishes a high-fidelity twin model using genetic algorithm and captures the key components of the structure using Bayesian probability formula and multiple mechanical parameters. The feasibility and effectiveness of the proposed method are validated through a case study on the Speed Skating Gymnasium of 2022 Winter Olympic Games.
Article
Chemistry, Multidisciplinary
Yuhong Zhao, Naiqiang Wang, Zhansheng Liu
Summary: This paper proposes a digital twin modeling theory for construction safety assessment, aiming to solve the difficulty in describing the safety status of different construction stages in traditional assessment methods. By collecting information through IoT, a digital twin model is established and analyzed using machine learning for safety assessments. The analysis results on the settlement of tunnel construction demonstrate the high accuracy of the digital twin model in predicting settlement value and dynamically assessing safety state.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Analytical
Zedong Jiao, Xiuli Du, Zhansheng Liu, Liang Liu, Zhe Sun, Guoliang Shi
Summary: This paper proposes a sustainable digital twin (DT) model called SDTOM-BI for the operation and maintenance of building infrastructures. The model expands the traditional 'factor-energy consumption' to three parts of 'factor-event-energy consumption', allowing the model to track energy consumption-related factors based on the relevance of random events. It also combines with Bayesian network (BN) and random forest (RF) to improve the correlation between factors and results, leading to more accurate forecasts. The application of the model in a real-world gymnasium is provided to illustrate and verify its effectiveness.
Review
Green & Sustainable Science & Technology
Zedong Jiao, Xiuli Du, Zhansheng Liu, Liang Liu, Zhe Sun, Guoliang Shi, Ruirui Liu
Summary: This article systematically summarizes the methods, integration, and application of related technologies for intelligent operation of large public buildings, as well as their development trends and challenges. By using quantitative and qualitative bibliometric statistical methods, a B-IRO model based on system theory was developed, and the current status of intelligent operation and maintenance-related technologies and applications was sorted out. A framework for the entire industry was established, and future development trends were proposed as further research directions.
Article
Green & Sustainable Science & Technology
Zhansheng Liu, Xiaotao Sun, Zhe Sun, Liang Liu, Xiaolin Meng
Summary: There are some problems in the security management of large stadiums, and an intelligent security system based on the digital twin concept is proposed to improve the efficiency of security management. The modeling method combines physical and virtual models to analyze and control the security management process of buildings, enhancing the integration and intelligence of the security system.
Article
Green & Sustainable Science & Technology
Zhansheng Liu, Jie Xue, Naiqiang Wang, Wenyan Bai, Yanchi Mo
Summary: The most negative effects of earthquakes are the damage and collapse of buildings. Seismic building retrofitting and repair can effectively reduce the negative impact on post-earthquake buildings. This paper proposes a damage assessment method using CV and AR to improve the intelligence of damage assessments for post-earthquake buildings.
Review
Construction & Building Technology
Weiyu Ji, Lu Yang, Zhansheng Liu, Shuxin Feng
Summary: Human-building interaction is a rising field that explores the interactions and impacts between humans and building systems. Sensing technology is crucial for data collection in this discipline. This study evaluates 127 research articles and provides a systematic review of sensing technology implementation in various HBI research topics.
Article
Green & Sustainable Science & Technology
Zeqiang Wang, Zehua Zhang, Zhansheng Liu, Majid Dezhkam, Yifeng Zhao, Marinella Giunta
Summary: This paper proposes a method for the safety control of cable net structures based on the concept of digital twins, which enables real-time monitoring and control to ensure safety throughout the construction process.
Article
Green & Sustainable Science & Technology
Zhansheng Liu, Zehua Zhang, Chao Yuan
Summary: In this paper, a multi-factor-based assessment method for the serviceability safety of cable net structures was proposed using the digital twin model. The method includes the selection of key indicators and the construction of a comprehensive dataset for support-vector-regression-based structural safety assessment.
Article
Green & Sustainable Science & Technology
Yuhong Zhao, Ruirui Liu, Zhansheng Liu, Yun Lu, Liang Liu, Jingjing Wang, Wenxiang Liu
Summary: This article focuses on the correlation between energy consumption data and environmental data in zero-carbon buildings. It proposes an anomaly detection and correction method based on the correlation relationships, and demonstrates the reasonableness of the fitting equations used for error correction. The method is applicable to various scenarios within the realm of zero-carbon buildings.
Article
Green & Sustainable Science & Technology
Guoliang Shi, Zhansheng Liu, Dengzhou Xian, Rongtian Zhang
Summary: This study proposes an intelligent assessment method for structural reliability driven by a sustainability target, which incorporates digital twin technology to establish an intelligent evaluation framework for structural reliability. The high-fidelity twin model is established to analyze the mechanical response of the structure under different load cases and obtain the coupling relationship between component failure and reliability indicators. The twinning model can be used to analyze the reliability of the structure in real time and help to set maintenance measures of structural safety, ensuring the safety and sustainability of the structure during its normal service period.
Article
Construction & Building Technology
Zeqiang Wang, Guoliang Shi, Zhansheng Liu, Yanchi Mo, Bo Si, Yang Hu, Yongliang Wang
Summary: In this paper, an analysis method based on a genetic algorithm optimized back propagation neural network (GA-BPNN) was proposed to evaluate the influence of construction errors on cable force in cable net structures. Using the speed skating stadium of the 2022 Winter Olympic Games as a case study, the research analyzed the structure of the venue and determined the principle of construction error analysis based on the characteristics of cable network structure and GA-BPNN calculation. The influence of construction errors on cable force response was analyzed, and the most critical components were identified. The results demonstrate that the proposed method efficiently and accurately predicts the influencing factors of structural safety risk and prevents structural accidents caused by construction errors.
Article
Construction & Building Technology
Zhansheng Liu, Jie Xue
Summary: This research evaluates the MR seismic retrofitting training system and finds it to be excellent. The study aims to provide guidance and reference for the future development and improvement of training systems.