Article
Computer Science, Theory & Methods
Michel J. F. Rosa, Celia Ghedini Ralha, Maristela Holanda, Aleteia P. F. Araujo
Summary: The use of cloud platforms in scientific workflows presents challenges for users in selecting resources efficiently. To address this issue, a provisioning service called CRCPs is proposed to predict resource and cost, allowing users to optimize performance and budget before workflow execution. The results demonstrate the adequacy of CRCPs in estimating and optimizing resources, time, and cost.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2021)
Article
Computer Science, Information Systems
Priyanka Nehra, A. Nagaraju
Summary: This paper proposes a Support Vector Regression-based methodology to predict a host's future utilization using multiple resource's utilization history. Compared to existing approaches, the proposed method performs better in terms of root mean square error, mean absolute percentage error, mean square error, mean absolute error, and R2.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Multidisciplinary Sciences
Xiangdong Pei, Min Yuan, Guo Mao, Zhengbin Pang
Summary: This paper proposes a multidimensional fusion CBA-net fault prediction model, which effectively extracts and learns the spatial and temporal features in the fault log to achieve fine-grained and accurate fault prediction for large supercomputing systems.
Article
Engineering, Civil
W. G. Zhang, H. R. Li, C. Z. Wu, Y. Q. Li, Z. Q. Liu, H. L. Liu
Summary: This study established predictive models for assessing surface settlement induced by EPB tunneling using different soft computing techniques and validated them with datasets from three tunnel construction projects in Singapore. The results showed that the XGBoost model had slightly better accuracy in predicting ground settlement and was more computationally efficient.
Article
Environmental Sciences
Weibin Zeng, Xiaoming Wan, Mei Lei, Gaoquan Gu, Tongbin Chen
Summary: Phytoextraction using hyperaccumulator Pteris vittata has been applied for arsenic removal, but standardization of this technology faces challenges due to differences in studies. Factors influencing arsenic concentration in P. vittata include soil components like organic matter and available arsenic, as well as environmental factors such as total potassium concentration and rainfall. Predictive models established for greenhouse and field conditions showed the importance of soil available arsenic and rainfall in determining arsenic concentration in P. vittata, indicating potential for improving phytoextraction efficiency and technological standardization.
ENVIRONMENTAL POLLUTION
(2022)
Article
Green & Sustainable Science & Technology
Mostafa A. Rushdi, Shigeo Yoshida, Koichi Watanabe, Yuji Ohya
Summary: Wind solar towers are a new scheme for harvesting renewable energy, utilizing solar and wind sources for power generation. This study describes the setup of such a tower system at Kyushu University in Japan and demonstrates how regression models can be trained for thermal updraft prediction using data collected from the system. Through sensitivity analysis-guided feature selection, a linear regression model was found to provide highly accurate thermal updraft predictions.
Article
Computer Science, Artificial Intelligence
Haixia Zhao, Wenhu Li, Li Gan, Sulin Wang
Summary: This research proposes a prediction model for athletes' sports performance using Neural Networks as the underlying framework, aiming to enhance sports performance and scientific training. The model utilizes neural network algorithms for training and optimization, analyzes temporal patterns, extracts statistical features, and evaluates its accuracy by comparing prediction errors with traditional models. The results show that the proposed method achieves an overall prediction accuracy of 97.6%, surpassing previous approaches with higher accuracy, reduced latency, improved recall, and increased scalability.
Article
Economics
Holger Dette, Weichi Wu
Summary: We propose an estimator for the high-dimensional covariance matrix of a locally stationary process with a smoothly varying trend. This estimator is used to derive consistent predictors for nonstationary time series. Unlike existing methods, our predictor does not rely on fitting an autoregressive model nor require a vanishing trend. Simulations and a study on financial indices demonstrate the finite sample properties of our methodology.
JOURNAL OF BUSINESS & ECONOMIC STATISTICS
(2022)
Article
Chemistry, Medicinal
Alma Ramic, Ana Matosevic, Barbara Debanic, Ana Mikelic, Ines Primozic, Anita Bosak, Tomica Hrenar
Summary: A series of Cinchona alkaloid derivatives were synthesized and tested for their inhibitory activity against human acetylcholinesterase (AChE) and butyrylcholinesterase (BChE). The results showed that these compounds could reversibly inhibit AChE and BChE in the nanomolar to micromolar range. Among them, N-(meta-fluorobenzyl)cinchonidinium bromide exhibited the highest selectivity for BChE, with 533 times higher preference than AChE. The creation of multivariate linear regression models using machine learning techniques provided a valuable tool for identifying new potential leads.
Article
Green & Sustainable Science & Technology
Yufei Wang, Qixing Yang, Hua Xue, Yang Mi, Yijun Tu
Summary: This paper proposes a novel prediction model for photovoltaic (PV) power. By combining HP filter, OVMD, and EENN model, it overcomes the challenges posed by the fluctuation and non-stationarity of PV power. Numerical results demonstrate that the proposed model performs significantly better than other models in terms of prediction accuracy.
IET RENEWABLE POWER GENERATION
(2022)
Article
Geochemistry & Geophysics
Wenjing Wang, Zhenwei Shi
Summary: The proposed cloud detection network, ABNet, includes All-scale feature Fusion modules and a Boundary point Prediction module, which can optimize features, recover spatial information, and improve accuracy near cloud boundaries.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Engineering, Marine
Jae-Hyeon Son, Yooil Kim
Summary: This study developed a computational procedure to predict the structural response of a ship voyaging through irregular seaways while considering relevant uncertainties from a probabilistic perspective. The ship's structural response was represented by linear Volterra series and Laguerre polynomials, with unknown coefficients treated as random variables and probability determined through Bayesian linear regression model. Validation was done using a linear oscillator model and practical application involved analyzing experimental ship data for probabilistic predictions of vertical bending moment time series and estimation of fatigue damage using stochastic time series.
Article
Computer Science, Hardware & Architecture
Javad Dogani, Farshad Khunjush, Mohammad Reza Mahmoudi, Mehdi Seydali
Summary: This paper presents a hybrid method for predicting multivariate time series workload of host machines in cloud data centers. It constructs a training set through statistical analysis, extracts hidden spatial features using convolutional neural networks, and extracts temporal correlation features using a GRU network optimized with attention mechanism.
JOURNAL OF SUPERCOMPUTING
(2023)
Article
Biochemical Research Methods
Amir Bahmani, Ziye Xing, Vandhana Krishnan, Utsab Ray, Frank Mueller, Amir Alavi, Philip S. Tsao, Michael P. Snyder, Cuiping Pan
Summary: Executing genomic applications on cloud computing facilities often lacks tools to predict the most appropriate instance type, leading to over- or under-matching of resources. Hummingbird, a tool for predicting performance of computing instances on multiple cloud platforms with varying memory and CPU, can accurately predict the fastest, cheapest, and most cost-efficient compute instances economically.
Article
Thermodynamics
Tianyao Ji, Jin Wang, Mengshi Li, Qinghua Wu
Summary: In this paper, a short-term wind power forecast method based on chaotic analysis is proposed. Simulation studies conducted on wind power data from neighboring wind farms have shown the effectiveness of the proposed method and its advantage over the classic LSSVM model in terms of accuracy and stability.
ENERGY CONVERSION AND MANAGEMENT
(2022)