2021 International Conference on Computational Science and Computational Intelligence (CSCI), Год журнала: 2023, Номер unknown, С. 1714 - 1720
Опубликована: Дек. 13, 2023
Язык: Английский
2021 International Conference on Computational Science and Computational Intelligence (CSCI), Год журнала: 2023, Номер unknown, С. 1714 - 1720
Опубликована: Дек. 13, 2023
Язык: Английский
Indonesian Journal of Computer Science, Год журнала: 2024, Номер 13(3)
Опубликована: Июнь 15, 2024
Community health center is a services in Indonesia that aims to organize first-level public efforts. The current condition observed level one centers relates the provided. A large portion of patients who have experienced express dissatisfaction with service This research determine quality community and provide advices improve services. method used this Servperf Importance Performance Analysis. Based on performance method, mean 3,39 importance 4,38. Meanwhile, Analysis obtained conformity between 77,49% seven atrributes dimensions enter quadrant I are top priority for improvement. proposed improvements made future by adjusting main attributes diagram.
Язык: Английский
Процитировано
0Axioms, Год журнала: 2023, Номер 12(10), С. 989 - 989
Опубликована: Окт. 19, 2023
In this paper, we have parameterized a timelike (Tlike) circular surface (CIsurface) and obtained its geometric properties, including striction curves, singularities, Gaussian mean curvatures. Afterward, the situation for Tlike roller coaster (RCOsurface) to be flat or minimal is examined in detail. Further, illustrate approach’s outcomes with number of pertinent examples.
Язык: Английский
Процитировано
0Research Square (Research Square), Год журнала: 2023, Номер unknown
Опубликована: Дек. 21, 2023
Abstract This paper explores a neural network-based approach for constructing prediction intervals (PIs) of total organic carbon (TOC) content. In contrast to conventional methods that focus solely on minimizing error, the proposed method utilizes dual-output network optimized by novel loss function called \({\mathcal{L}}_{QCE}\) emphasizes overall PI quality through balanced consideration coverage probability, interval width, and cumulative deviation. Consequently, this facilitates generation higher-quality PIs under specified significance levels. Case studies illustrate that, in comparison prevailing techniques such as Pearce's Gaussian process regression, our achieves notable over 40% reduction invalid intervals, accompanied an approximate 50% improvement quality. Additionally, we introduce ensemble learning assess inherent model uncertainties, further augmenting precision PIs. summary, presented methodology offers competitive solution uncertainty quantification well log data mining, providing innovative effective enhance TOC
Язык: Английский
Процитировано
02021 International Conference on Computational Science and Computational Intelligence (CSCI), Год журнала: 2023, Номер unknown, С. 1714 - 1720
Опубликована: Дек. 13, 2023
Язык: Английский
Процитировано
0