Article
Engineering, Civil
Aya Selmoune, Jeongin Yun, Myoungkook Seo, Hyeokhyeon Kwon, Changhee Lee, Jinwoo Lee
Summary: Pedestrians are at a higher risk of serious injury in vehicle collisions, especially on residential roads without dividers and with blind spots. Traditional safety features are not always effective in preventing accidents. To address this issue, a collision risk warning service using CCTVs and radar to detect objects in real-time has been proposed. User surveys conducted on university campus roads showed that the service was considered necessary and significantly contributed to traffic safety.
JOURNAL OF ADVANCED TRANSPORTATION
(2023)
Article
Computer Science, Artificial Intelligence
Wenchao Huang, Yu Cao, Xu Cheng, Zongkai Guo
Summary: Air quality is changing due to various factors such as industry, agriculture, and human activities. Traditional machine learning methods fail to consider the time series and long-range dependencies in the data, leading to an inaccurate prediction of air quality. In this study, an attention mechanism based on LSTM is introduced to attenuate unimportant information. An integrated model combining lightGBM and LSTM-attention is constructed, which outperforms other models in terms of prediction accuracy.
PEERJ COMPUTER SCIENCE
(2022)
Article
Engineering, Multidisciplinary
Dewen Seng, Qiyan Zhang, Xuefeng Zhang, Guangsen Chen, Xiyuan Chen
Summary: By utilizing deep learning and supervised learning techniques, a comprehensive prediction model based on LSTM was developed for air quality indicators like PM2.5, CO, NO2, O-3, and SO2. Normalized and transformed environmental data were used to predict overall air quality in Beijing.
ALEXANDRIA ENGINEERING JOURNAL
(2021)
Article
Construction & Building Technology
R. Janarthanan, P. Partheeban, K. Somasundaram, P. Navin Elamparithi
Summary: The National Air Monitoring Program in India covers 240 cities and uses a deep learning model to accurately predict AQI values, promoting sustainable development and controlling pollution levels.
SUSTAINABLE CITIES AND SOCIETY
(2021)
Article
Environmental Sciences
Keyong Hu, Xiaolan Guo, Xueyao Gong, Xupeng Wang, Junqing Liang, Daoquan Li
Summary: This paper studies air quality data collected in Beijing and proposes a spatio-temporal deep learning model called Conv1D-LSTM for accurate prediction. The study reveals spatial correlations, temporal dependencies, and feature correlations in the dataset, and addresses the problem of data missing.
ATMOSPHERIC POLLUTION RESEARCH
(2022)
Article
Green & Sustainable Science & Technology
Grigore Cican, Adrian-Nicolae Buturache, Radu Mirea
Summary: Air quality forecasting in metropolitan areas is challenging due to emission dynamics, high population density, and uncertainty in defining meteorological conditions. This study improves the prediction of NO2 concentration using LSTM and GRU, which outperform traditional methods. The data used for modeling are from the National Air Quality Monitoring Network.
Article
Green & Sustainable Science & Technology
Nishat Tasnim Toosty, Aya Hagishima, Wasimul Bari, Sheikh Ahmad Zaki
Summary: Remote work became the new norm during the COVID-19 pandemic, and this study investigated the impact of Malaysia's Movement Control Order (MCO) on the air conditioner (AC) usage behavior of remote workers. The study found that stopping AC use during remote work was the most significant behavior change due to the MCO, and factors such as age and ethnicity influenced AC-usage behavior in remote work.
SUSTAINABLE PRODUCTION AND CONSUMPTION
(2022)
Article
Economics
Zagros Z. Dilshad, Swar O. Ahmed, Bootan Rahman
Summary: This study examines the effects of the COVID-19 pandemic on employment in the Kurdistan Region Government, including lower wages and job loss. The findings show that the crisis has led to salary cuts, business shutdowns, and reduced working hours. There is no association between losing salary and working status, but there is a correlation between gender and business shutdown.
JOURNAL OF THE KNOWLEDGE ECONOMY
(2023)
Article
Psychology, Multidisciplinary
Dongxuan Wang, Dapeng Lian, Yazhou Xing, Shiying Dong, Xinyu Sun, Jia Yu
Summary: This paper aims to analyze the fluctuation of academic performance among ordinary Chinese college students and establish prediction systems. Through questionnaire surveys and machine learning, four classification prediction models were built, and traits of students who did not pass exams were discovered, which could help student counselors and educators take targeted measures.
FRONTIERS IN PSYCHOLOGY
(2022)
Article
Public, Environmental & Occupational Health
Yingchen Wang, Xiangran Kong, Fang Li, Hongyan Zhao
Summary: This study examines the professional development challenges faced by Chinese public health professionals and identifies issues such as burnout, sleep issues, mood issues, friends' support, exercise, and other challenges.
FRONTIERS IN PUBLIC HEALTH
(2023)
Article
Chemistry, Analytical
Yakubu Imrana, Yanping Xiang, Liaqat Ali, Zaharawu Abdul-Rauf, Yu-Chen Hu, Seifedine Kadry, Sangsoon Lim
Summary: In a network architecture, an intrusion detection system is widely used to protect critical assets. Existing intrusion detection systems struggle to achieve high detection rates with low false alarms due to the large volume of data and irrelevant features. This study proposes a novel feature-driven approach that combines a statistical model and bidirectional long short-term memory for accurate predictions of network intrusions. The experimental results demonstrate the superiority of this approach in terms of detection accuracy, F-score, and false alarm rate.
Article
Chemistry, Multidisciplinary
Asdrubal Lopez-Chau, Lisbeth Rodriguez-Mazahua, Farid Garcia-Lamont, Maricela Quintana-Lopez, Carlos A. Rojas-Hernandez
Summary: This paper presents a method to address the problem caused by random zeros in independence tests. The method merges levels of variables to create contingency tables with one degree of freedom. The method provides a complete panorama of the associations between variables in a dataset.
APPLIED SCIENCES-BASEL
(2022)
Article
Medicine, Research & Experimental
Xuan Huang, Junmin Li, Xiaoying Pang, Jialei Zhu, Jiaqian Pan, Yueyan Li, Jing Tang
Summary: This study investigated the correlation between single nucleotide polymorphisms (SNPs) at various loci and adverse drug reactions (ADRs) in gynecologic cancer patients receiving platinum-based chemotherapy (PPCT). The results showed that specific SNPs were associated with an increased risk of leucopenia and neutropenia, indicating their potential as predictors of hematotoxicity in PPCT-treated patients with gynecologic cancer.
CTS-CLINICAL AND TRANSLATIONAL SCIENCE
(2023)
Article
Virology
HoiMan Ng, Teng Zhang, Guoliang Wang, SiMeng Kan, Guoyi Ma, Zhe Li, Chang Chen, Dandan Wang, MengIn Wong, ChioHang Wong, Jinliang Ni, Xiaohua Douglas Zhang
Summary: Influenza is a major respiratory disease, and the study in Macau reveals differences in influenza epidemics compared to other places, with significant variations in infection risks among different years and age groups, especially between tourists and locals.
Article
Computer Science, Artificial Intelligence
Bingchun Liu, Zhecheng Yu, Qingshan Wang, Peng Du, Xinming Zhang
Summary: This study explores a comprehensive and effective stock price prediction model by considering the indirect effects of air pollutants on investor psychology and combining financial data. The experimental results show that the BiLSTM model based on air pollutants data has a prediction accuracy of 94.1% in stock prediction, indicating its application value.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)