4.7 Article

Improvement of thermal comfort for underground space: Data enhancement using variational autoencoder

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Computer Science, Artificial Intelligence

Variational model for low-resource natural language generation in spoken dialogue systems

Van-Khanh Tran et al.

Summary: This paper introduces a variational-based NLG framework to address the issue of limited annotated data in NLG in two scenarios, domain adaptation and low-resource in-domain training data. Experimental results demonstrate that the proposed methods outperform previous methods with sufficient training data and are able to perform well with small amounts of in-domain data or quickly adapt to new domains with low-resource data.

COMPUTER SPEECH AND LANGUAGE (2021)

Article Robotics

Multimodal Deep Generative Models for Trajectory Prediction: A Conditional Variational Autoencoder Approach

Boris Ivanovic et al.

Summary: Human behavior prediction models are crucial for designing safe and proactive robot planning algorithms, but modeling complex interaction dynamics and capturing multiple possible outcomes is challenging. The CVAE approach can generate multimodal probability distributions over future human trajectories, prompting research on various methods for human behavior prediction.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

Article Construction & Building Technology

Environmental standards for healthy ventilation in metros: Status, problems and prospects

Jiawei Leng et al.

Summary: The metro plays a crucial role in big cities, with environmental hygiene and ventilation control being essential. The Chinese metro industry has established regulations and standards, but still faces challenges such as thermal comfort, environmental pollution, and energy efficiency. Further research and collaboration can enhance the efficiency and energy-saving potential of metro environmental control.

ENERGY AND BUILDINGS (2021)

Article Construction & Building Technology

Influence of environmental variables on thermal comfort and air quality perception in office buildings in the humid subtropical climate zone of Brazil

Candi Citadini de Oliveira et al.

Summary: This study evaluates the influence of environmental variables on users' thermal comfort and air quality perception in a humid subtropical climate. Factors such as air temperature, humidity ratio, and air movement were found to directly or indirectly affect thermal comfort. The study supports the use of a hybrid ventilation strategy for energy savings and improvement of indoor air quality.

ENERGY AND BUILDINGS (2021)

Article Construction & Building Technology

Thermal comfort in naturally ventilated university classrooms: A seasonal field study in Xi'an, China

Xue Wang et al.

Summary: This study investigates seasonal variations in thermal environment and comfort in classrooms in cold area in China, observing significant differences in temperature, humidity, and CO2 concentration and suggesting cooling in summer and proper ventilation in winter.

ENERGY AND BUILDINGS (2021)

Article Green & Sustainable Science & Technology

Integrating corporate website information into qualitative assessment for benchmarking green supply chain management practices for the chemical industry

Shuo Gao et al.

Summary: This study proposes a multi-criteria decision framework to help companies in the Chinese chemical industry effectively implement green supply chain management. The research reveals that environmental management, eco-design, and resource recycling are the most important GSCM themes, with top management support, life cycle assessment, environmental risk management, recycling technology advancement, and reverse logistics integration being the top five practices.

JOURNAL OF CLEANER PRODUCTION (2021)

Article Computer Science, Artificial Intelligence

Recurrent generative adversarial networks for unsupervised WCE video summarization

Libin Lan et al.

Summary: This paper proposes a new method for unsupervised WCE video summarization using a variety of techniques, optimizing the process of generating WCE video summaries through a generative adversarial framework with a summarizer and discriminator. Experimental results demonstrate that the model significantly outperforms other methods on various datasets.

KNOWLEDGE-BASED SYSTEMS (2021)

Article Radiology, Nuclear Medicine & Medical Imaging

Realistic generation of diffusion-weighted magnetic resonance brain images with deep generative models

Alejandro Ungria Hirte et al.

Summary: By using the Introspective Variational Autoencoder and the StyleBased Generative Adversarial Network, high quality, diverse, and realistic magnetic resonance images can be generated, evaluated by neuroradiologists blinded to the study as being of superior quality. These findings demonstrate that generative models can serve as a method for data augmentation in the medical field.

MAGNETIC RESONANCE IMAGING (2021)

Review Green & Sustainable Science & Technology

Intelligent building control systems for thermal comfort and energy-efficiency: A systematic review of artificial intelligence-assisted techniques

Ghezlane Halhoul Merabet et al.

Summary: This paper provides a comprehensive review of AI-based techniques for building control systems, discussing the challenges faced in using AI for energy productivity and comfort improvement. It also outlines the main future directions in relation with AI-based building control systems for human comfort and energy-efficiency management.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2021)

Review Environmental Sciences

Effect of thermal, acoustic, and lighting environment in underground space on human comfort and work efficiency: A review

Xian Dong et al.

Summary: The development and utilization of underground spaces can alleviate the shortage of urban land resources, ensure urban safety, and enhance the urban ecological environment. Environmental factors such as thermal, acoustic, and lighting significantly influence human comfort and work efficiency in underground spaces. Current standards mainly reference aboveground buildings, highlighting the need for further research and improvement in evaluating human comfort in underground environments.

SCIENCE OF THE TOTAL ENVIRONMENT (2021)

Article Ergonomics

Crash data augmentation using variational autoencoder

Zubayer Islam et al.

Summary: In this study, a data augmentation technique using variational autoencoder was proposed to reproduce crash data effectively. The generated data showed high statistical similarity to real data and outperformed other oversampling techniques like SMOTE and ADASYN in terms of specificity and sensitivity. The flexibility in decision boundary choice provided by VAE helped to overcome overfitting issues present in other methods.

ACCIDENT ANALYSIS AND PREVENTION (2021)

Article Green & Sustainable Science & Technology

Impact of building greening on building energy consumption: A quantitative computational approach

Renlu Qiao et al.

JOURNAL OF CLEANER PRODUCTION (2020)

Article Computer Science, Artificial Intelligence

Likelihood-based hybrid ORESTE method for evaluating the thermal comfort in underground mines

Suizhi Luo et al.

APPLIED SOFT COMPUTING (2020)

Article Construction & Building Technology

A thermal comfort field study on subway passengers during air-conditioning season in Beijing

Song Pan et al.

SUSTAINABLE CITIES AND SOCIETY (2020)

Article Transportation Science & Technology

A variational autoencoder solution for road traffic forecasting systems: Missing data imputation, dimension reduction, model selection and anomaly detection

Guillem Boquet et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2020)

Article Construction & Building Technology

Summer thermal comfort in nursing homes in the Mediterranean climate

N. Forcada et al.

ENERGY AND BUILDINGS (2020)

Article Engineering, Manufacturing

Generation of geometric interpolations of building types with deep variational autoencoders

Jaime de Miguel Rodriguez et al.

DESIGN SCIENCE (2020)

Article Engineering, Civil

Impact of Data Loss for Prediction of Traffic Flow on an Urban Road Using Neural Networks

Teresa Pamula

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2019)

Article Computer Science, Information Systems

Recurrent neural network-based semantic variational autoencoder for Sequence-to-sequence learning

Myeongjun Jang et al.

INFORMATION SCIENCES (2019)

Article Construction & Building Technology

A discussion about thermal comfort evaluation in a bus terminal

Vitor E. M. Cardoso et al.

ENERGY AND BUILDINGS (2018)

Article Transportation Science & Technology

Real-time crash prediction in an urban expressway using disaggregated data

Franco Basso et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2018)

Article Construction & Building Technology

Balancing indoor thermal comfort and energy consumption of ACMV systems via sparse swarm algorithms in optimizations

Deqing Zhai et al.

ENERGY AND BUILDINGS (2017)

Review Green & Sustainable Science & Technology

Indoor thermal comfort predictions: Selected issues and trends

Harimi Djamila

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2017)

Article Construction & Building Technology

Influence of short-term thermal experience on thermal comfort evaluations: A climate chamber experiment

Wenjie Ji et al.

BUILDING AND ENVIRONMENT (2017)

Article Environmental Sciences

On the determination of the thermal comfort conditions of a metropolitan city underground railway

George Katavoutas et al.

SCIENCE OF THE TOTAL ENVIRONMENT (2016)

Article Computer Science, Information Systems

Experimental testing of a random neural network smart controller using a single zone test chamber

Abbas Javed et al.

IET NETWORKS (2015)

Article Engineering, Electrical & Electronic

Missing traffic data: comparison of imputation methods

Yuebiao Li et al.

IET INTELLIGENT TRANSPORT SYSTEMS (2014)

Article Construction & Building Technology

Thermal environment characterisation of a glass-covered semi-outdoor space subjected to natural climate mitigation

G. Pagliarini et al.

ENERGY AND BUILDINGS (2011)

Review Construction & Building Technology

Forty years of Fanger's model of thermal comfort: comfort for all?

J. van Hoof

INDOOR AIR (2008)