Article
Agricultural Economics & Policy
Lucie Maruejols, Hanjie Wang, Qiran Zhao, Yunli Bai, Linxiu Zhang
Summary: Despite rising incomes and efforts to reduce extreme poverty, the feeling of poverty remains common. This study identifies factors associated with subjective poverty and compares the performance of three machine learning algorithms in predicting subjective poverty status. The findings suggest that subjective poverty is mostly associated with monetary income for low-income households, while a combination of low income, low endowment, and large expenditure is key for middle-income households. This research provides insights for policy interventions to address poverty and highlights the importance of considering non-income domains for improving well-being.
CHINA AGRICULTURAL ECONOMIC REVIEW
(2023)
Article
Computer Science, Information Systems
Vikas Jain, Ashish Phophalia
Summary: The study introduces the M-ary Random Forest (MaRF) method, which improves performance by splitting data at nodes using multiple features and demonstrates that its efficiency is higher compared to state-of-the-art methods.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Multidisciplinary Sciences
Wei Huang, Yinke Liu, Peiqi Hu, Shiyu Ding, Shuhui Gao, Ming Zhang
Summary: This study analyzes the main factors influencing relative poverty among farmers in China by constructing a relative poverty index system and using machine learning methods. The research findings show that machine learning algorithms, especially XGBoost, can be well applied in the field of relative poverty and provide new directions and references for future research.
Article
Economics
Hanjie Wang, Lucie Maruejols, Xiaohua Yu
Summary: The study demonstrates that a machine learning algorithm incorporating satellite remote sensing data and socioeconomic survey data can accurately predict energy poverty, with precipitation and PM2.5 being the most important environmental indicators.
Article
Mathematics
Erwin Cornelius, Olcay Akman, Dan Hrozencik
Summary: The study proposes a clustered random forest approach to predict COVID-19 patient mortality, showing comparable predictive performance to other methods. Analysis of demographic information and subsequent neural network modeling and k-means clustering provide insight into the mortality risks associated with COVID-19.
Article
Thermodynamics
Khizar Abbas, Khalid Manzoor Butt, Deyi Xu, Muhammad Ali, Khan Baz, Sanwal Hussain Kharl, Mansoor Ahmed
Summary: The study reveals the widespread severe energy poverty in developing countries, particularly in Asia and Africa. It identifies the most susceptible countries and the key socioeconomic determinants of extreme multidimensional energy poverty. The findings emphasize the significance of accurate assessment and policy measures to eradicate severe energy poverty.
Article
Chemistry, Physical
Xiaoyu Liu, Dali Ji, Xiaoheng Jin, Vanesa Quintano, Rakesh Joshi
Summary: By combining the random forest (RF) model with experimentally observed X-ray photoelectron spectroscopy (XPS) data, a complete chemical analysis dataset of Co(III)/Co(II) ratio for thermally synthesized Co-rGO supercapacitor electrodes was constructed. The predicted dataset showed less than 8% error compared to experimental validation.
Article
Environmental Sciences
Abolfazl Jaafari, Saeid Janizadeh, Hazem Ghassan Abdo, Davood Mafi-Gholami, Behzad Adeli
Summary: This study investigates the relationship between geoenvironmental factors and land degradation (specifically gully erosion) and produces spatially explicit maps of land susceptibility to gully erosion. The study finds that distance from roads and rivers, altitude, and normalized difference vegetation index are the most influential factors in gully erosion occurrence.
JOURNAL OF ENVIRONMENTAL MANAGEMENT
(2022)
Article
Thermodynamics
Shule Wang, Ziyi Shi, Yanghao Jin, Ilman Nuran Zaini, Yan Li, Chuchu Tang, Wangzhong Mu, Yuming Wen, Jianchun Jiang, Par Goran Jonsson
Summary: An in-depth understanding of pyrolytic kinetics is crucial for comprehending the process of thermal decomposition. This study successfully constructed a model to predict the mean values of model-free activation energies of pyrolysis for five different feedstocks using the random forest machine learning method. The results indicate the potential of machine learning methods for quick initial pyrolytic kinetic estimation. The study also revealed the correlations between atomic ratios and activation energies, as well as the influence of ash content on activation energy, depending on the organic component species present in the feedstocks.
ENERGY CONVERSION AND MANAGEMENT
(2022)
Article
Computer Science, Artificial Intelligence
Mario Juez-Gil, Alvar Arnaiz-Gonzalez, Juan J. Rodriguez, Carlos Lopez-Nozal, Cesar Garcia-Osorio
Summary: The paper introduces a MapReduce Rotation Forest and its implementation under the Spark framework, addressing the issue of long training and prediction times in the original Rotation Forest in the context of Big Data. By parallelizing both PCA calculation and tree training, the proposed solution retains the performance of the original Rotation Forest while achieving competitive execution time.
INFORMATION FUSION
(2021)
Article
Biology
Wojciech Lesinski, Krzysztof Mnich, Agnieszka Kitlas Golinska, Witold R. Rudnicki
Summary: The study aimed to predict drug-induced liver injury (DILI) using gene expression profiles in cancer cell lines and drug chemical properties. Machine learning models were built, with significantly improved accuracy using the Super Learner approach, categorizing substances into low-risk and high-risk categories.
Article
Computer Science, Artificial Intelligence
Ruben I. Carino-Escobar, Gustavo A. Alonso-Silverio, Antonio Alarcon-Paredes, Jessica Cantillo-Negrete
Summary: Tree ensemble algorithms, like random forest, are widely used in machine learning, but the number of trees in the ensemble is an important hyperparameter. A new algorithm called feature-ranked self-growing forest (FSF) is introduced, which automatically grows the ensemble based on the structural diversity of the trees' nodes. The performance of FSF was tested with classification and regression datasets and compared to random forest, showing superior performance in most cases.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Agronomy
Svetlana Kresova, Sebastian Hess
Summary: This study analyzed official data from Russia's regions from 2015 to 2019, using 12 predictor variables to explain the regional raw milk price. The findings showed that drinking milk production, income, livestock numbers, and population density were the four most important determinants of the variation in regional raw milk prices in Russia.
Article
Biochemical Research Methods
Shuwei Yin, Xiao Tian, Jingjing Zhang, Peisen Sun, Guanglin Li
Summary: A machine learning software named PCirc was developed in this study for predicting plant circRNAs, achieving high accuracy and effectiveness in tests.
BMC BIOINFORMATICS
(2021)
Article
Ecology
Robin Singh Bhadoria, Manish Kumar Pandey, Pradeep Kundu
Summary: Human intervention causing forest fires hinders nature's ability to recover, leading to climate change consequences that we must take responsibility for and minimize. Mitigating fires by predicting and controlling their spread can be enhanced through machine learning models, like the proposed RVFR model, which achieves higher accuracy in predicting forest fires based on past data.
ECOLOGICAL INFORMATICS
(2021)
Article
Health Care Sciences & Services
Norashikin Mustafa, Nik Shanita Safii, Aida Jaffar, Nor Samsiah Sani, Mohd Izham Mohamad, Abdul Hadi Abd Rahman, Sherina Mohd Sidik
Summary: The study translated and validated a Malay version of the mHealth App Usability Questionnaire (MAUQ) for future research and usage in Malaysia. The M-MAUQ demonstrated good reliability and validity, making it suitable for assessing the usability of mHealth apps in Malay.
JMIR MHEALTH AND UHEALTH
(2021)
Article
Environmental Sciences
R. A. Ali, N. N. L. Nik Ibrahim, W. A. Wan Ab Karim Ghani, H. L. Lam, N. S. Sani
Summary: This study utilizes process network synthesis and data mining techniques as optimization models to evaluate the potential of decision-making in municipal solid waste management, with findings showing that the multilayer perceptron model performed well and can serve as a basis for decision-making in waste management. Integrating optimization models can provide an efficient tool for waste management decision-making.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL SCIENCE AND TECHNOLOGY
(2022)
Article
Mathematics
Salam Salameh Shreem, Mohd Zakree Ahmad Nazri, Salwani Abdullah, Nor Samsiah Sani
Summary: Selecting the most minimal set of genes from microarray datasets for clinical diagnosis and prediction is a challenging task in machine learning. This study proposes a gene selection method called SU-RSHSA that combines the advantages of the Symmetrical Uncertainty (SU) filter and Reference Set Harmony Search Algorithm (RSHSA) wrapper to generate a small subset of genes with high classification accuracy.
Article
Computer Science, Information Systems
Ali Sabah Abdulameer, Sabrina Tiun, Nor Samsiah Sani, Masri Ayob, Adil Yaseen Taha
Summary: Due to the overabundance of information on the web, existing clustering methods have limitations in clustering short texts. This study proposes an enhanced framework by expanding document terms to improve the clustering performance of web search results.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Energy & Fuels
Amit Chhabra, Sudip Kumar Sahana, Nor Samsiah Sani, Ali Mohammadzadeh, Hasmila Amirah Omar
Summary: A new optimization algorithm h-DEWOA was introduced to address the Cloud Bag-of-Tasks Scheduling (CBS) problem by enhancing the exploration ability and solution diversity of the Whale Optimization Algorithm (WOA), achieving superior scheduling solutions and demonstrating excellent performance in experiments.
Article
Computer Science, Information Systems
Nur Afyfah Suwadi, Morched Derbali, Nor Samsiah Sani, Meng Chun Lam, Haslina Arshad, Imran Khan, Ki-Il Kim
Summary: This study utilizes machine learning classification methods to predict water quality index (WQI) and identifies important features for prediction. The optimized Random Forest classifier with the WQI parameter selected by information gain achieved the highest performance. The study shows that the parameters oxygen (DO) and biochemical oxygen demand (BOD) are important features for predicting WQI. The proposed model has reasonable accuracy and minimal parameters, making it suitable for real-time water quality detection systems.
WIRELESS COMMUNICATIONS & MOBILE COMPUTING
(2022)
Article
Environmental Sciences
Illa Iza Suhana Shamsuddin, Zalinda Othman, Nor Samsiah Sani
Summary: Traditionally, evaluating water quality has been expensive and ineffective for real-time monitoring. This study utilizes machine learning methods to construct a model capable of predicting water quality and finds that the Support Vector Machines (SVM) model performs the best in predicting river water quality. Additionally, the use of kernel functions, grid search methods, and multiclass classification techniques significantly impacts the effectiveness of the SVM model.
Article
Chemistry, Multidisciplinary
Ahmad Fikri Mohamed Nafuri, Nor Samsiah Sani, Nur Fatin Aqilah Zainudin, Abdul Hadi Abd Rahman, Mohd Aliff
Summary: This study proposes a clustering-based approach to classify B40 students based on their performance in higher education institutions, aiming to assist the government in reducing dropout rates, increasing graduation rates, and boosting students' socioeconomic status.
APPLIED SCIENCES-BASEL
(2022)
Article
Medicine, General & Internal
Atheer Bassel, Amjed Basil Abdulkareem, Zaid Abdi Alkareem Alyasseri, Nor Samsiah Sani, Husam Jasim Mohammed
Summary: This article introduces the classification and identification methods for skin cancer, and proposes a classifier stacking method based on three-fold cross-validation. The method trains the system with deep learning and other machine learning methods in three levels on the training set, and achieves high accuracy on the test set.
Article
Engineering, Multidisciplinary
Rabiatul Adawiyah Ali, Nik Nor Liyana Nik Ibrahim, Wan Azlina Wan Abdul Karim Ghani, Nor Samsiah Sani, Hon Loong Lam
Summary: This study presents a decision-making integration framework based on hybrid process network synthesis and machine learning for equipment selection in municipal solid waste management. The P-graph is used to generate possible structures, and data from feasible structures are processed and evaluated using WEKA software. The J48 model is found to be the best for equipment selection with an 80:20 train and test learning technique. The framework is represented by a graphical user interface in MATLAB, focusing on the selection of waste conversion technologies.
JOURNAL OF APPLIED SCIENCE AND ENGINEERING
(2022)
Article
Computer Science, Information Systems
Abdallah Abdallah, Mohamad Khairi Ishak, Nor Samsiah Sani, Imran Khan, Fahad R. Albogamy, Hirofumi Amano, Samih M. Mostafa
Summary: This article proposes a novel DDoS traffic detection method based on information entropy and deep neural network (DNN). By calculating the information entropy value of data packets and using DNN for identification, it can accurately detect DDoS activity efficiently.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Computer Science, Theory & Methods
Mohd Aliff, Mohammad Imran, Sairul Izwan, Mohd Ismail, Nor Samsiah, So Shimooka, Tetsuya Akagi, Shujiro Dohta, Weihang Tian, Ahmad Athif
Summary: Pipeline transportation is crucial in today's world, and compact and portable pipe inspection robots with pneumatic actuators are needed. This study focuses on proposing mechanisms such as sliding, holding, and bending units to enable easy and efficient movement of robots in pipelines.
INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Waleed Shahjehan, Abid Ullah, Syed Waqar Shah, Imran Khan, Nor Samsiah Sani, Ki-Il Kim
Summary: This paper proposes an energy-efficient hybrid precoding algorithm based on RF chains selection for mmWave massive MIMO networks to reduce energy consumption and cost, and provide desirable quality-of-service. Simulation results show that the algorithm can effectively improve system performance under different operating conditions.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Computer Science, Theory & Methods
Ashraf Abdelhadi, Suhaila Zainudin, Nor Samsiah Sani
Summary: Performance indicators are crucial for organizational success as they measure current performance and track progress towards business objectives. This study utilized regression models to predict accurate KPIs based on student enrollment data, demonstrating that using linear regression with a 40% training and 60% testing split produced the best results.
INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS
(2022)
Article
Computer Science, Theory & Methods
Norsuhada Mansor, Nor Samsiah Sani, Mohd Aliff
Summary: In this study, the performance of machine learning techniques in predicting employee attrition was compared, with the optimized SVM model demonstrated as the best predictor with an accuracy rate of 88.87%. Various preprocessing steps and optimization techniques were applied to the dataset for analysis.
INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS
(2021)