Article
Computer Science, Artificial Intelligence
Xinming Zhang, Min Yan, Binglei Xie, Haiqiang Yang, Hang Ma
Summary: Bus travel time is often unpredictable due to traffic conditions and passenger flow, leading to the need for bus dispatching. This study focuses on real-time bus dispatching through bus arrival time prediction and timetable redesign. A combination of SVR and Kalman Filter improves prediction accuracy, while an automatic timetable redesign method minimizes the impact on the initial schedule. The proposed methods enhance the efficiency of transit resource allocation and maintain normal working order.
ADVANCED ENGINEERING INFORMATICS
(2021)
Article
Green & Sustainable Science & Technology
Rafidah Md Noor, Nadia Bella Gustiani Rasyidi, Tarak Nandy, Raenu Kolandaisamy
Summary: Public transportation is essential for communities to carry out daily activities, with buses being a commonly used mass transportation method. The smart transportation concept combines technology and strategy, with smart ideas being crucial for IoT applications. This study utilizes Artificial Neural Network and Support Vector Machine algorithms to predict travel time for university shuttle buses, outperforming SVM. Recommendations for suitable routes are provided, with future directions for the field discussed.
Article
Engineering, Electrical & Electronic
Zhiping Dong, Hao Wen, Zaixin Song, Chunhua Liu
Summary: In this article, a three-dimensional space vector modulation (3-D SVM) strategy for three-phase open-end winding drives with common dc bus is proposed, which can be conducted in both a-b-c and alpha-beta-z coordinates, leading to full utilization of the dc bus voltage and convenient over-modulation adjustment. The voltage vector distributions in the 3-D spaces with a-b-c and alpha-beta-z coordinates are revealed, and three adjacent voltage vectors are selected for reference voltage vector synthesis based on the relationship between leg-voltage potentials. Furthermore, the overmodulation in different coordinates is also investigated. Experimental results validate the feasibility of the proposed 3-D SVM for OWDs with common dc bus.
IEEE TRANSACTIONS ON POWER ELECTRONICS
(2023)
Article
Oncology
Chenjun Huang, Meng Fang, Huijuan Feng, Lijuan Liu, Ya Li, Xuewen Xu, Hao Wang, Ying Wang, Lin Tong, Lin Zhou, Chunfang Gao
Summary: This study successfully identified 13 N-glycan structures as effective biomarkers for AFP-negative hepatocellular carcinoma (ANHCC) using differential gene expression screening and machine learning algorithms. The LR algorithm showed the best diagnostic performance in identifying ANHCC patients and demonstrated high accuracy in independent validation.
INTERNATIONAL JOURNAL OF CANCER
(2021)
Article
Computer Science, Information Systems
R. Geetha, K. Ramyadevi, M. Balasubramanian
Summary: The prediction of electricity consumption is crucial for smart energy management, as it plays an important role in planning power generation and distribution systems and understanding customer lifestyles. However, existing forecasting models have shown subpar accuracy and require improvement.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Engineering, Multidisciplinary
Marwah Sattar Hanoon, Ali Najah Ahmed, Arif Razzaq, Atheer Y. Oudah, Ahmed Alkhayyat, Yuk Feng Huang, Pavitra Kumar, Ahmed El-Shafie
Summary: This study investigates the capability of various machine learning algorithms in predicting the power production of a reservoir located in China. The proposed models can efficiently predict the hydropower generation and provide valuable insights for energy decision-makers.
AIN SHAMS ENGINEERING JOURNAL
(2023)
Article
Chemistry, Multidisciplinary
Sherif M. Dabour, Ahmed A. Aboushady, Mohamed A. Elgenedy, I. A. Gowaid, Mohamed Emad Farrag, Ayman S. Abdel-Khalik, Ahmed M. Massoud, Shehab Ahmed
Summary: This paper studies PWM schemes to reduce switching common mode voltage (CMV) in symmetrical nine-phase machines. Two schemes are proposed and evaluated through simulations and experimental studies. Results show that the peak CMV is reduced by 22.2% and 88.8% respectively for the two schemes.
APPLIED SCIENCES-BASEL
(2022)
Article
Mathematics, Interdisciplinary Applications
Oznur Oztunc Kaymak, Yigit Kayamank
Summary: This paper discusses the impact of global economic recession and the COVID-19 pandemic on oil prices, and aims to improve a model for more accurate predictions. The study finds that this model outperforms other models and artificial neural networks in forecasting crude oil prices.
CHAOS SOLITONS & FRACTALS
(2022)
Article
Materials Science, Characterization & Testing
S. Bandara, P. Rajeev, E. Gad, B. Sriskantharajah, I. Flatley
Summary: This paper introduces a stress wave propagation technique combined with artificial neural network algorithm for assessing the condition of timber poles, with the success rates of ANN model, SVM classifier, and k-means clustering algorithm being 92%, 87%, and 81% respectively. Through signal classification, intact and defective poles can be accurately identified.
JOURNAL OF NONDESTRUCTIVE EVALUATION
(2021)
Review
Computer Science, Information Systems
Akash Samanta, Sumana Chowdhuri, Sheldon S. Williamson
Summary: This paper provides a comprehensive review of state-of-the-art ML-based data-driven fault detection/diagnosis techniques for LIB systems, serving as a valuable reference and guide for the research community. ML methods have shown promising advantages over conventional techniques, while current issues and future challenges in LIB fault diagnosis are also addressed for better understanding and guidance.
Article
Chemistry, Physical
Yuan Tian, Xinxin Wang, Yanrong Liu, Wenping Hu
Summary: This study establishes two databases to predict the solubility of CO2 and N2 in various kinds of ILs under different temperature and pressure conditions. By dividing ILs into multiple ionic fragments and combining with support vector machine and artificial neural network, a quantitative structure-property relationship model is built to establish the relationship between gas solubility and ILs structure. The results show that both IFC-SVM and IFC-ANN models can accurately and reliably predict the solubility of CO2 and N2 in ILs, guiding the screening of ILs.
JOURNAL OF MOLECULAR LIQUIDS
(2023)
Article
Water Resources
Sarmad Dashti Latif, K. L. Chong, Ali Najah Ahmed, Y. F. Huang, Mohsen Sherif, Ahmed El-Shafie
Summary: Sediment transport is crucial for predicting flood events, tracking coastal erosion, planning for water supplies, and managing irrigation. AI-based models, such as LSTM, ANN, and SVM, were investigated in predicting sediment transport in the Johor river, with LSTM outperforming other models.
APPLIED WATER SCIENCE
(2023)
Article
Engineering, Manufacturing
Ke Xu, Jiaqi Lyu, Souran Manoochehri
Summary: This study introduced an real-time monitoring system based on acoustic emission and laser scanning technology to detect warpage defects during the printing process. Machine learning models trained by AE sensory data can accurately identify warpage of various sizes in real time.
JOURNAL OF MANUFACTURING PROCESSES
(2022)
Article
Engineering, Electrical & Electronic
Yunlong Liu, Steven Liu, Cong Wang, Jiayan Jiang, Junjie Li, Shu Ye
Summary: An improved SVM and VBC function are proposed in this article to address the voltage balance issues in 5L-NNPP converters, achieving decoupling of voltage control. The performance of the improved SVM is investigated and validated through simulation and experimental results.
IEEE TRANSACTIONS ON POWER ELECTRONICS
(2021)
Article
Engineering, Civil
Jia Wang, Xu Wang, Soon Thiam Khu
Summary: This study proposes a hybrid decomposition-based multi-model and multi-parameter ensemble streamflow forecast method, which combines signal decomposition and artificial intelligence models to improve the accuracy and efficiency of streamflow prediction. The results demonstrate that this method effectively reduces forecast uncertainty and expands ensemble size, making it suitable for nonlinear and non-stationary hydrological series forecasting.
JOURNAL OF HYDROLOGY
(2023)