Article
Environmental Sciences
Paul L. Ohlert, Martin Bach, Lutz Breuer
Summary: This study evaluates the accuracy of inverse distance weighting (IDW) in designating nitrate vulnerable zones. Using a dataset of 5790 groundwater monitoring sites in Bavaria, the results show that IDW interpolation method has significant errors in determining areas with groundwater nitrate concentration above the threshold. The average absolute error of nitrate concentration is 7.0 mg NO3/l, and the number of measurement sites above 50 mg NO3/l is underestimated. These underestimations persist even when the interpolation is done separately for hydrogeological regions. Therefore, IDW method is not reliable for the designation of nitrate vulnerable zones.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Computer Science, Information Systems
Darren Yates, Md Zahidul Islam
Summary: The FastForest algorithm, with its three optimizing components, achieves faster processing speed on hardware-constrained devices while maintaining high accuracy, suitable for both PC and smartphone platforms. Empirical testing shows excellent performance against other ensemble classifiers, surpassing them in various tests.
INFORMATION SCIENCES
(2021)
Review
Computer Science, Interdisciplinary Applications
Ankit Thakkar, Ritika Lohiya
Summary: This article provides a detailed overview of intrusion detection using machine learning techniques, discussing the steps performed by ML techniques for detecting and classifying intrusions. It summarizes the state-of-the-art ML techniques used for intrusion detection and classification, along with their advantages and limitations. The paper also addresses the challenges faced by ML-based IDS and discusses future research directions to enhance the efficiency and effectiveness of IDS. This review serves as an incentive for novice researchers interested in working in the field of ML-based IDS.
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING
(2023)
Article
Physics, Multidisciplinary
Shihu Liu, Haiyan Gao
Summary: This paper proposes a self-information weighting-based method to rank all nodes in graph data and verifies its effectiveness through experiments.
Article
Environmental Sciences
Meng Wang, Yusen Duan, Zhuozhi Zhang, Juntao Huo, Yu Huang, Qingyan Fu, Tao Wang, Junji Cao, Shun-cheng Lee
Summary: This study analyzed data from a highway sampling site in Shanghai from 2016 to 2019 using a machine learning algorithm, and found that non-exhaust emissions (road dust) have increased their contribution to PM2.5 over recent years, with road dust increasing at a faster rate than exhaust emissions.
ENVIRONMENTAL POLLUTION
(2022)
Article
Environmental Sciences
Kabir Peerbhay, Onisimo Mutanga, Romano Lottering, Na'eem Agjee, Riyad Ismail
Summary: This study successfully mapped riparian bugweed in riparian environments using a combination of hyperspectral data and LiDAR technology, achieving a detection rate of 88%, a false positive rate of 7.14%, and an overall accuracy of 83%. Compared to using original hyperspectral wavebands, integrating LiDAR can more accurately map the locations of invasive alien plants.
GEOCARTO INTERNATIONAL
(2021)
Article
Environmental Sciences
Ricardo Martinez Prentice, Miguel Villoslada Pecina, Raymond D. Ward, Thaisa F. Bergamo, Chris B. Joyce, Kalev Sepp
Summary: In the study, high-resolution images obtained by multispectral cameras mounted on Unmanned Aerial Vehicles were used to classify coastal wetland sites. The Random Forest classifier outperformed the K-Nearest Neighbors algorithm, especially in pixel-based classification. The findings suggest that for heterogeneous environments like wetlands, pixel-based classification provides a more realistic interpretation of plant community distribution.
Article
Environmental Sciences
Mazen E. E. Assiri, Salman Qureshi
Summary: The study aimed to improve the accuracy of precipitation products through developing a multi-source data fusion method. Results showed that the random forest regression algorithm combined with existing precipitation products and surface characteristics could significantly enhance precipitation estimation accuracy.
Article
Computer Science, Artificial Intelligence
Jose Paulo G. de Oliveira, Carmelo J. A. Bastos-Filho, Sergio Campello Oliveira
Summary: Quality control is critical in the modern electronic circuit industry, and the advancement in manufacturing techniques has led to higher demands for flexible and efficient testing methods with cost control. Automated test solutions based on machine learning, such as autoencoders, are effective in detecting anomalies in electronic systems.
ADVANCED ENGINEERING INFORMATICS
(2022)
Article
Computer Science, Artificial Intelligence
Xu Tan, Jiawei Yang, Susanto Rahardja
Summary: Isolation Forest is widely used for outlier detection in large-scale data due to its low computational complexity. However, it may fail to detect outliers in specific regions due to artifacts caused by the chosen hyperplanes. To address this issue, a random-projection based Isolation Forest is proposed, which transforms the data and improves outlier detection performance.
PATTERN RECOGNITION LETTERS
(2022)
Article
Ergonomics
Yunxuan Li, Meng Li, Jinghui Yuan, Jian Lu, Mohamed Abdel-Aty
Summary: The study analyzed factors influencing traffic violations and predicted the probability of violations using both logistic regression and random forest algorithm. Results showed that certain factors like time period, location, and traffic conditions can increase the likelihood of traffic violations. Additionally, using the ProWSyn method to handle imbalanced data improved the random forest algorithm's performance in predicting traffic violations.
ACCIDENT ANALYSIS AND PREVENTION
(2021)
Article
Chemistry, Multidisciplinary
Yu-Ting Lyu, Chia-Ming Jan, Herchang Ay, Chiu-Feng Lin, Haw-Ching Yang, Min-Chun Chuang, Heng-Sheng Lin, Tsung-Pin Hung
Summary: This study develops an EDM process abnormal diagnosis system that can extract and diagnose machining abnormalities using the coefficient of variation feature and a composite voting model. It provides real-time monitoring of machine abnormalities through an online monitoring system.
APPLIED SCIENCES-BASEL
(2022)
Article
Environmental Sciences
Wenjing Guo, Zhipeng Gao, Huaming Guo, Wengeng Cao
Summary: The relative importance of groundwater geochemicals and sediment characteristics in predicting groundwater arsenic distributions in the Hetao Basin, China was evaluated using a random forest machine-learning model. The model showed that Fe(II) and SO42- were the most prominent variables in predicting groundwater arsenic concentrations, indicating that arsenic enrichment was caused by the reductive dissolution of Fe(III) oxides and sulfate reduction. Other factors such as climate, sediment characteristics, and soil properties also played important roles in predicting groundwater arsenic concentrations. The study highlights the significance of groundwater geochemicals and sediment characteristics in improving the precision and accuracy of predictions.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Computer Science, Artificial Intelligence
Chunhui Wu, Wenjuan Li
Summary: This study investigates feature selection methods and introduces an ensemble of Neural Networks and Random Forest to enhance intrusion detection performance. The experimental results show that compared to similar approaches, this method can better identify important and relevant features.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2021)
Article
Computer Science, Software Engineering
Mahmood Safaei, Maha Driss, Wadii Boulila, Elankovan A. Sundararajan, Mitra Safaei
Summary: Wireless sensor networks (WSNs) have gained worldwide attention for their practicality but face accuracy issues due to environmental factors. This research aims to design and implement a global outlier-detection approach for WSNs, achieving up to 99% accuracy in anomaly detection according to experiment results.
SOFTWARE-PRACTICE & EXPERIENCE
(2022)