Article
Computer Science, Software Engineering
Xing Xu, Chengxing Liu, Yun Zhao, Xiaoshu Lv
Summary: The article proposes a traffic flow prediction model based on the WOA optimized BiLSTM_Attention structure to obtain the best network performance, and compares it with conventional neural network models, showing superior performance.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Qiuxia Chen, Ying Song, Jianfeng Zhao
Summary: By using the improved wavelet neural network model and particle swarm optimization algorithm, the accuracy and stability of short-term traffic flow prediction can be enhanced.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Engineering, Multidisciplinary
He Yan, Tian'an Zhang, Yong Qi, Dong-Jun Yu
Summary: A novel least squares twin support vector regression method is proposed in this study to alleviate the negative effect of outliers in traffic data. An iterative algorithm is designed to solve the non-smooth L-1-norm terms, and a comprehensive traffic flow indicator system is utilized. The proposed method is extended to a nonlinear version by hybridizing kernels and optimized by an adaptive fruit fly optimization algorithm for improved prediction performance.
APPLIED MATHEMATICAL MODELLING
(2022)
Article
Physics, Multidisciplinary
Wenrui Qu, Jinhong Li, Wenting Song, Xiaoran Li, Yue Zhao, Hanlin Dong, Yanfei Wang, Qun Zhao, Yi Qi
Summary: This study compares the performances of three different types of entropy weight methods in traffic flow prediction. By applying these methods to integrate prediction models, it is found that the EWM-C model produces the most accurate predictions, and the issues with the EWM-A and EWM-B methods are discussed.
Article
Chemistry, Multidisciplinary
Weiqing Zhuang, Yongbo Cao
Summary: Most previous traffic flow prediction models focused on the time series aspect, neglecting the spatial correlation of traffic flow. This paper proposes a method that combines the k-nearest neighbor algorithm with bidirectional long short-term memory network model to predict the spatio-temporal characteristics of short-term traffic flow. Experimental results show that the proposed model outperforms other existing models in terms of prediction accuracy, with improvements ranging from 13% to 77%.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Artificial Intelligence
Licheng Qu, Jiao Lyu, Wei Li, Dongfang Ma, Haiwei Fan
Summary: Accurate traffic speed forecasting is critical and the proposed feature injected recurrent neural networks (FI-RNNs) show great potential in improving prediction accuracy by combining sequential time data with contextual factors. Case studies on real-world data sets demonstrate that the injection of contextual features can greatly enhance the accuracy of time series prediction, outperforming other state-of-the-art traffic prediction methods.
Article
Computer Science, Theory & Methods
He Yan, Liyong Fu, Yong Qi, Dong-Jun Yu, Qiaolin Ye
Summary: This paper focuses on improving traffic flow prediction performance through ensemble learning method, proposing an effective and robust ensemble method. By using improved least squares twin support vector regression methods and a pruning scheme, this method demonstrates superior performance in predicting traffic flow.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2022)
Article
Engineering, Civil
Shanliang Zhu, Yu Zhao, Yanjie Zhang, Qingling Li, Wenwu Wang, Shuguo Yang
Summary: This paper proposes a novel short-term traffic flow prediction method based on wavelet transform and multi-dimensional Taylor network, which achieved better prediction performance and generalization ability in a certain area of Shenzhen, China.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2021)
Article
Computer Science, Software Engineering
Anupriya, Anita Singhrova
Summary: The digital growth has led to the expansion of mobile and wireless scenarios, increasing the demand for efficient resource management. The software defined mobile network controller has emerged as a promising solution. This paper proposes the use of an intelligent whale optimization algorithm to improve the reliability and efficiency of the mobile network.
AUTOMATED SOFTWARE ENGINEERING
(2022)
Article
Computer Science, Information Systems
Ke Zhao, Dudu Guo, Miao Sun, Chenao Zhao, Hongbo Shuai
Summary: This paper proposes a combined traffic flow prediction model based on VMD and improved IDBO-LSTM. The model smooths historical traffic flow data using VMD and optimizes LSTM parameters using the IDBO algorithm. Experimental results show that the proposed model has significant advantages in accuracy and addressing data issues.
Article
Engineering, Electrical & Electronic
Nan Zhao, Fengqi Zhang, Yalian Yang, Serdar Coskun, Xianke Lin, Xiaosong Hu
Summary: This article proposes a predictive energy management strategy for connected plug-in hybrid electric vehicles (PHEVs) based on real-time dynamic traffic prediction. The strategy involves predicting future traffic information using a wavelet neural network (WNN) and optimizing the parameters of the network using a particle swarm optimization (PSO) algorithm. A long short-term memory-based velocity predictor is also proposed for the strategy. The performance of the strategy is verified using actual traffic data and results show improvements in fuel economy of 17.57% and 28.19% respectively.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Dawen Xia, Maoting Zhang, Xiaobo Yan, Yu Bai, Yongling Zheng, Yantao Li, Huaqing Li
Summary: This paper proposes a distributed long short-term memory weighted model (WND-LSTM) to handle traffic flow prediction big data, aiming to improve accuracy, efficiency, and scalability. The model is used to forecast traffic flow on Sanlihe East Road in Beijing, with experimental results showing significant accuracy improvement compared to other methods.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Multidisciplinary Sciences
Xiaomei Sun, Haiou Zhang, Jian Wang, Chendi Shi, Dongwen Hua, Juan Li
Summary: The researchers developed a hybrid model called VMD-LSTM-GBRT for reliable and accurate streamflow forecasting. This model uses feature extraction, feature learning, and ensemble strategies to predict streamflow, and it demonstrated high accuracy and stability in the experiment.
SCIENTIFIC REPORTS
(2022)
Article
Energy & Fuels
Mu Chai, Zhenan Liu, Kuanfang He, Mian Jiang
Summary: This paper designs a set of online PV power generation parameter measurement and monitoring devices to achieve real-time monitoring of electrical parameters during the PV power generation process. By analyzing the structure and working principle of PV cells, a mathematical model is established, and a wavelet neural network is used to predict short-term PV power generation. The weight and parameters of the wavelet neural network are optimized using the particle swarm optimization algorithm, and the effectiveness and accuracy of the model are verified.
ENERGY SCIENCE & ENGINEERING
(2023)
Article
Engineering, Multidisciplinary
Guowen Dai, Jinjun Tang, Wang Luo
Summary: Traffic congestion in China seriously restricts the healthy and sustainable development of cities due to travel inconvenience, air pollution, and economic losses. Intelligent transportation systems, including traffic flow prediction, are important in improving road network efficiency and reducing urban traffic congestion. This paper proposes an ensemble short-term traffic flow prediction method based on optimized variational mode decomposition (OVMD) and combined long short-term memory network (LSTM).
ALEXANDRIA ENGINEERING JOURNAL
(2023)
Article
Construction & Building Technology
Gabriele Bernardini, Tiago Miguel Ferreira, Pilar Baquedano Julia, Rafael Ramirez Eudave, Enrico Quagliarini
Summary: This research offers a methodology for combined spatiotemporal flood risk assessment, considering hazard, physical vulnerability, user exposure, and vulnerability. It adopts a mesoscale approach and investigates indoor and outdoor users' exposure and vulnerability, using the Analytical Hierarchy Process to combine risk factors.
SUSTAINABLE CITIES AND SOCIETY
(2024)
Article
Construction & Building Technology
Ying Liu, Chunli Chu, Ruijun Zhang, Shaoqing Chen, Chao Xu, Dongliang Zhao, Chunchun Meng, Meiting Ju, Zhi Cao
Summary: This study investigates the effects of increasing road, wall, and roof albedo on mitigating the urban heat island (UHI) effect in different areas of Tianjin. The results reveal that increasing road albedo is more effective in fringe areas, while increasing wall and roof albedo is more effective in central areas. The temperature changes induced by albedo changes also show seasonal characteristics.
SUSTAINABLE CITIES AND SOCIETY
(2024)
Article
Construction & Building Technology
Xisheng Lin, Yunfei Fu, Daniel Z. Peng, Chun-Ho Liu, Mengyuan Chu, Zengshun Chen, Fan Yang, Tim K. T. Tse, Cruz Y. Li, Xinxin Feng
Summary: This study employed computational fluid dynamics and neural network models to investigate and predict pollutant dispersion in urban environments, providing valuable insights for designing effective strategies to mitigate the impacts of hazardous pollutants.
SUSTAINABLE CITIES AND SOCIETY
(2024)
Article
Construction & Building Technology
Dipanjan Nag, Arkopal Kishore Goswami
Summary: Future-oriented urban planning should continue to focus on the principles of accessible and walkable cities. The perception of people is crucial for developing better urban walking infrastructure, but current evaluation tools often neglect the "perceived" features of the walking network. This study used conjoint analysis to evaluate users' perception of link and network attributes, revealing the importance of considering both in improving the walking environment.
SUSTAINABLE CITIES AND SOCIETY
(2024)
Article
Construction & Building Technology
Yongxin Su, Tao Zhang, Mengyao Xu, Mao Tan, Yuzhou Zhang, Rui Wang, Ling Wang
Summary: This study proposes an optimization method for household integrated demand response (HIDR) by combining rough knowledge and a dueling deep Q-network (DDQN), aiming to address uncertainties in a household multi-energy system (HMES). The simulation results demonstrate that the proposed method outperforms rule-based methods and DDQN in terms of energy cost savings.
SUSTAINABLE CITIES AND SOCIETY
(2024)
Article
Construction & Building Technology
Sijia Sun, S. F. A. Batista, Monica Menendez, Yuanqing Wang, Shuang Zhang
Summary: This paper comprehensively analyzes the energy consumption characteristics of electric buses (EBs) and diesel buses (DBs) on different bus lane configurations and operational conditions. The study shows that EBs consume less energy in suburban areas when using regular lanes, while both EBs and DBs save substantial energy when operating on dedicated bus lanes in downtown areas. Notably, shared-use bus lanes have the highest energy consumption.
SUSTAINABLE CITIES AND SOCIETY
(2024)
Article
Construction & Building Technology
Shangshang Shen, Dan Yan, Xiaojie Liu
Summary: This study developed a comprehensive theoretical framework for evaluating, diagnosing, and optimizing multi-functional urban agriculture. The framework was applied in Xiamen, China to identify the obstacles that impede its coordinated development and propose optimized modes for its development. Results showed that urban agriculture in Xiamen exhibits sound social function, moderate economic function, and poor ecological function.
SUSTAINABLE CITIES AND SOCIETY
(2024)
Article
Construction & Building Technology
Oluwafemi E. Adeyeri, Akinleye H. Folorunsho, Kayode I. Ayegbusi, Vishal Bobde, Tolulope E. Adeliyi, Christopher E. Ndehedehe, Akintomide A. Akinsanola
Summary: This study examines the impact of land cover, vegetation health, climatic forcings, elevation heat loads, and terrain characteristics on land surface temperature distribution over West Africa. The random forest model performs the best in downscaling predictands. The southern regions consistently exhibit healthy vegetation, while areas with unhealthy vegetation coincide with hot land surface temperature clusters. Positive Normalized Difference Vegetation Index trends in the Sahel highlight rainfall recovery and subsequent greening. Southwest winds cause the upwelling of cold waters, resulting in low land surface temperatures in southern West Africa. Considering LVCET factors is crucial for prioritizing greening initiatives and urban planning.
SUSTAINABLE CITIES AND SOCIETY
(2024)
Article
Construction & Building Technology
Yuchi Cao, Yan Li, Shouyun Shen, Weiwei Wang, Xiao Peng, Jiaao Chen, Jingpeng Liao, Xinyi Lv, Yifan Liu, Lehan Ma, Guodian Hu, Jinghuan Jiang, Dan Sun, Qingchu Jiang, Qiulin Liao
Summary: The study reveals significant disparities in urban green equity, with high property price areas having better access to green spaces than low property price areas. Landscape and greening have the most significant impact on urban green space differentiation.
SUSTAINABLE CITIES AND SOCIETY
(2024)
Article
Construction & Building Technology
Shaobo Sun, Kui Shan, Shengwei Wang
Summary: Economizer control is an important measure for energy savings in air-conditioning systems during moderate seasons. Humidity measurement uncertainties have a significant impact on enthalpy-based economizer control, and an uncertainty-tolerant control strategy is proposed to mitigate these effects.
SUSTAINABLE CITIES AND SOCIETY
(2024)
Article
Construction & Building Technology
Ding Mao, Peng Wang, Yi-Ping Fang, Long Ni
Summary: This study analyzes the structure, function, operation, and failure characteristics of district heating networks (DHNs) and proposes vulnerability analysis methods. The effectiveness of these methods is validated through application to a DHN in a Chinese city. The study finds that the heat source connectivity efficiency loss rate effectively characterizes topological and functional vulnerability. It also reveals that controllable DHNs have higher functional vulnerability under large area failure scenarios.
SUSTAINABLE CITIES AND SOCIETY
(2024)
Article
Construction & Building Technology
Hamid Karimi, Saeed Hasanzadeh, Hedayat Saboori
Summary: This paper presents a stochastic and cooperative approach for the operation of a cluster of interconnected multi-energy systems. The proposed model investigates the interaction among energy systems and integrates hydrogen and water systems into the overall energy structure. The model studies the performance of energy system agents in decentralized and cooperative scheduling.
SUSTAINABLE CITIES AND SOCIETY
(2024)
Article
Construction & Building Technology
Zhiyu Yan, Xiaogang Guo, Zilong Zhao, Luliang Tang
Summary: This study proposes a novel framework for fine-grained information extraction and dynamic spatial-temporal awareness in disaster-stricken areas based on social media data. The framework utilizes deep learning modules to extract location and water depth information from text and images, and analyzes the spatio-temporal distribution characteristics. The results show that the fusion of text and image-based information can enhance the perception of flood processes.
SUSTAINABLE CITIES AND SOCIETY
(2024)
Article
Construction & Building Technology
M. A. Pans, G. Claudio, P. C. Eames
Summary: This study simulated and optimized a speculative district heating system in an existing urban area in Loughborough, UK. The system used only renewable heat sources and thermal energy storage to address the mismatch between heat generation and demand. The study assessed the impact of long-term storage volume and charging temperature on system cost and energy efficiency.
SUSTAINABLE CITIES AND SOCIETY
(2024)
Article
Construction & Building Technology
Jianmei Zhong, Wei Zhang, Xiaoli Wang, Jinsheng Zhan, Tao Xia, Lingzhi Xie, Xiding Zeng, Kun Yang, Zhangyu Li, Ruiwen Zou, Zepu Bai, Qing Wang, Chenyang Zhang
Summary: This study aims to propose a suitable air distribution design and reduce the energy consumption of the BSL-4 laboratory. It analyzes the diffusion characteristics of aerosols, infection risk under different air distributions, and ventilation parameters. The results show that the proposed energy-saving operation strategy can reduce the energy consumption of the laboratory by 15-30%.
SUSTAINABLE CITIES AND SOCIETY
(2024)