Article
Environmental Sciences
Teresa Salazar-Rojas, Fredy Ruben Cejudo-Ruiz, Guillermo Calvo-Brenes
Summary: This study establishes a method to predict heavy metal concentrations in leaves and road dust based on their magnetic properties measurements. Machine learning algorithms were used to establish prediction models, with support vector machine proving to be the most accurate. The results showed that the prediction models based on the magnetic properties of leaves yielded better results than those based on road dust and certain evergreen species.
ENVIRONMENTAL POLLUTION
(2022)
Article
Computer Science, Information Systems
Zichen Zhang, Shifei Ding, Yuting Sun
Summary: This paper introduces a new method called multiple birth support vector regression (MBSVR), which constructs the regressor from multiple hyperplanes obtained by solving small quadratic programming problems, aiming for faster computation and better fitting precision.
INFORMATION SCIENCES
(2021)
Article
Environmental Sciences
Putri Anis Syahira Mohamad Jamil, Nur Athirah Diyana Mohammad Yusof, Karmegam Karuppiah, Irniza Rasdi, Vivien How, Shamsul Bahri Mohd Tamrin, Muhammad Hasnolhadi Samsudin, Sivasankar Sambasivam, Nayef Shabbab Almutairi
Summary: Real-time exposure air monitoring is crucial for protecting the respiratory health of Malaysian traffic police. However, existing monitoring stations do not provide sufficient data for accurate exposure information. This report presents the conceptual design of a wireless exposure indicator system and evaluates its field performance through collocation. The study confirms the accuracy of measurements for PM2.5, CO, and NO2 by comparing prototype results with reference instruments. The prototype successfully computes and transmits real-time monitoring data on levels of harmful air exposure.
Article
Engineering, Marine
Fan Zhou, Yunli Fan, Jing Zou, Bowen An
Summary: Ship emission monitoring is an interdisciplinary research problem that requires addressing challenges in data acquisition, transmission, and analysis. This study proposes a paradigm for constructing a ship emission monitoring sensor web (SEMSW) and has established a model in China's Waigaoqiao port area. The model plays a significant role in scientific research and maritime law enforcement.
Article
Environmental Sciences
A. Samad, S. Garuda, U. Vogt, B. Yang
Summary: Air pollution is a serious concern due to the rapid expansion in commercial, social, and economic aspects, which increases pollutant concentrations worldwide and disrupts human life. Monitoring these concentrations plays a vital role in controlling pollution levels, but it is not easy as it requires costly installation of monitoring stations. This research used machine learning methods to simulate pollutant concentrations in Stuttgart and found that nearby monitoring stations significantly affect predictions. The applicability of this methodology was also tested in another German city, Karlsruhe, and proved successful.
ATMOSPHERIC ENVIRONMENT
(2023)
Article
Engineering, Electrical & Electronic
Dung H. P. Nguyen, Vinh V. Le, Tu N. Nguyen, Bing-Hong Liu, Shao- Chu, Shi-Ming Hu
Summary: In this article, a practical approach is proposed to utilize public buses for building a vehicular network with attached sensors for air pollution monitoring, aiming to minimize the deployment cost. The problem is formulated as an integer linear programming model based on flow network representation and specific requirements. Additionally, an approximation algorithm and a greedy-based algorithm are suggested to handle large-scale problems and demonstrate their performances through experiments.
IEEE SENSORS JOURNAL
(2022)
Review
Environmental Sciences
Lu Liang
Summary: The global sensor market is rapidly expanding due to surging needs, but calibration efforts have been focused on a limited selection of sensors. Relative humidity correction, regression, and machine learning are the mainstream calibration techniques. Machine learning is a key trend in calibration, but issues such as calibration duration and spatial mismatch still need to be addressed.
ENVIRONMENTAL RESEARCH
(2021)
Article
Computer Science, Artificial Intelligence
Huajuan Huang, Xiuxi Wei, Yongquan Zhou
Summary: This article reviews the recent developments in twin support vector regression (TSVR). It introduces the basic concepts and models of TSVR, summarizes the improved algorithms and applications in recent years, and analyzes the advantages and disadvantages of representative algorithms through experiments. The article also discusses the research conducted on TSVR.
Article
Energy & Fuels
Dessislava Petrova-Antonova, Jelyazko Jelyazkov, Irena Pavlova
Summary: The air quality platform proposed in the paper monitors, collects, and aggregates data from multiple sources in different formats, allowing for comparison of measurements from different data sources and supporting monitoring and validation of sensors. The platform design includes a multi-layered architecture, data model, functional design, and integration of external APIs, enabling seamless aggregation and analysis of vast amounts of diverse data.
ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS
(2021)
Article
Computer Science, Artificial Intelligence
Quentin Klopfenstein, Samuel Vaiter
Summary: This paper investigates the addition of linear constraints to Support Vector Regression with a linear kernel, proving that the problem remains a semi-definite quadratic problem. A generalization of the Sequential Minimal Optimization algorithm is proposed to solve the optimization problem with linear constraints, showing convergence. Practical performance of this approach is demonstrated on simulated and real datasets, highlighting its usefulness compared to classical methods.
Article
Biotechnology & Applied Microbiology
A. Zafra-Perez, C. Boente, A. Sanchez de la Campa, J. A. Gomez-Galan, J. D. de la Rosa
Summary: This study proposes a novel methodology for the space-time monitoring of PM concentrations in open-pit mines using mobile low-cost sensors. The study revealed the main sources of PM within the mine and discovered the routes of escape of fugitive emissions from the mine. These findings are important for solving the monitoring issue in mining ambiances and promoting the environmentally friendly development of mines.
ENVIRONMENTAL TECHNOLOGY & INNOVATION
(2023)
Article
Physics, Multidisciplinary
Huan Liu, Jiankai Tu, Chunguang Li
Summary: This paper proposes a distributed SVOR algorithm to solve ordinal regression problems in distributed environments. Theoretical analysis and experimental results demonstrate that the proposed method can achieve good performance in scenarios where privacy protection or centralized data processing is not feasible.
Article
Engineering, Electrical & Electronic
Tran Anh Khoa, Nguyen Quang Minh, Hoang Hai Son, Cao Nguyen Dang Khoa, Dinh Ngoc Tan, Nguyen VanDung, Nguyen Hoang Nam, Dang Ngoc Minh Duc, Nguyen Trung Tin
Summary: Climate change poses a significant challenge to the development of countries producing agricultural commodities, and traditional weather station models have limitations in accurately predicting climate change. Therefore, a combination of wireless sensor networks and machine learning with the Internet of Things is being considered as a more effective approach for climate prediction.
INTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS
(2021)
Article
Chemistry, Analytical
Jaime Gomez-Suarez, Patricia Arroyo, Maria Cerrato-Alvarez, Esther Hontanon, Sergio Masa, Philippe Menini, Lionel Presmanes, Raimundo Alfonso, Eduardo Pinilla-Gil, Jesus Lozano
Summary: This study compared the performance of two metal-oxide semiconductor sensors for monitoring tropospheric ozone in ambient air, showing that the manufactured sensors outperformed commercial ones. The machine learning algorithm based on Support Vector Regression successfully converted resistive values into ozone concentration.
Article
Computer Science, Artificial Intelligence
Shili Peng, Wenwu Wang, Yinli Chen, Xueling Zhong, Qinghua Hu
Summary: This article presents a new idea for addressing the challenge of unifying classification and regression in machine learning. It proposes converting the classification problem into a regression problem and using regression methods to solve key problems in classification. Experimental results demonstrate that the proposed method outperforms existing algorithms in terms of prediction accuracy and model uncertainty.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Agriculture, Multidisciplinary
Md Sumon Shahriar, Daniel Smith, Ashfaqur Rahman, Mark Freeman, James Hills, Richard Rawnsley, Dave Henry, Greg Bishop-Hurley
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2016)
Article
Agriculture, Multidisciplinary
Daniel Smith, Ashfaqur Rahman, Greg J. Bishop-Hurley, James Hills, Sumon Shahriar, David Henry, Richard Rawnsley
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2016)
Article
Engineering, Electrical & Electronic
Ashfaqur Rahman, Greg Timms, Md. Sumon Shahriar, Charlotte Sennersten, Andrew Davie, Craig A. Lindley, Andrew D. Hellicar, Greg Smith, David Biggins, Mac Coombe
IEEE SENSORS JOURNAL
(2016)
Article
Agriculture, Multidisciplinary
P. L. Greenwood, D. R. Paull, J. McNally, T. Kalinowski, D. Ebert, B. Little, D. V. Smith, A. Rahman, P. Valencia, A. B. Ingham, G. J. Bishop-Hurley
CROP & PASTURE SCIENCE
(2017)
Article
Computer Science, Artificial Intelligence
Sumaira Tasnim, Ashfaqur Rahman, Amanullah Maung Than Oo, Md Enamul Haque
KNOWLEDGE-BASED SYSTEMS
(2018)
Article
Agriculture, Multidisciplinary
Ashfaqur Rahman, Stuart Arnold, Joel Janek Dabrowski
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2019)
Article
Automation & Control Systems
Akhlaqur Rahman, Jiong Jin, Antonio L. Cricenti, Ashfaqur Rahman, Ambarish Kulkarni
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2019)
Article
Parasitology
Amy Bell, Jody McNally, Daniel V. Smith, Ashfaqur Rahman, Peter Hunt, Andrew C. Kotze, Sonja Dominik, Aaron Ingham
VETERINARY PARASITOLOGY
(2019)
Article
Computer Science, Theory & Methods
Mahbuba Afrin, Jiong Jin, Ashfaqur Rahman, Yu-Chu Tian, Ambarish Kulkarni
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2019)
Article
Computer Science, Artificial Intelligence
Mahbub E. Khoda, Joarder Kamruzzaman, Iqbal Gondal, Tasadduq Imam, Ashfaqur Rahman
Summary: This paper introduces a novel malware oversampling technique to address the performance degradation issue in machine learning methods for imbalanced data. By combining fuzzy set theory with a novel loss function, two malware detection approaches are proposed, achieving over 9% improvement in terms of F1_score. This can lead to enhanced privacy and security in edge computing services.
APPLIED SOFT COMPUTING
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Ashfaqur Rahman, Philip Smethurst, Michael Attard, Rob Dunne
TRENDS AND APPLICATIONS IN KNOWLEDGE DISCOVERY AND DATA MINING, 2017
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Robert Dunne, Dave Henry, Richard Rawnsley, Ashfaqur Rahman
TRENDS AND APPLICATIONS IN KNOWLEDGE DISCOVERY AND DATA MINING, 2017
(2017)
Article
Computer Science, Artificial Intelligence
Sumaira Tasnim, Ashfaqur Rahman, Amanullah Maung Than Oo, Md Enamul Haque
INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE AND APPLICATIONS
(2017)
Article
Telecommunications
Akhlaqur Rahman, Jiong Jin, Antonio Cricenti, Ashfaqur Rahman, Marimuthu Palaniswami, Tie Luo
JOURNAL OF SENSOR AND ACTUATOR NETWORKS
(2016)