A case study on the application of a data-driven (XGBoost) approach on the environmental and socio-economic perspectives of agricultural groundwater management by Sheng-Wei Wang, Yen-Yu Chen, Shu-Han Hsu, Yu-Hsuan Kao, Masaomi Kimura, Li-chiu Chang, Tzi-Wen Pan, Chuen-Fa Ni

“…Bayesian optimization was used to determine the best-fit hyperparameters, resulting in RMSE, MAE, and R² values ranging from 0.923 to 2.497 m, 0.709–2.132 m, and 0.057–0.914, respectively, during model validation. …”
Get full text

Development of a Conditional Generative Adversarial Network Model for Television Spectrum Radio Environment Mapping by Oluwatobi Emmanuel Dare, Kennedy Okokpujie, Emmanuel Adetiba, Olabode Idowu-Bismark, Abdultaofeek Abayomi, Raymond Jules Kala, Emmanuel Owolabi, Udeme Christopher Ukpong

“…A REM construction model with few constraints and optimal performance is needed to better support cognitive radio for dynamic spectrum sharing (DSS) and other benefits of REM. …”
Get full text

Implementing Remote Radiotherapy Planning to Increase Patient Flow at a Johannesburg Academic Hospital, South Africa: Protocol for a Prospective Feasibility Study by Duvern Ramiah, Sonwabile Ngcezu, Oluwatosin Ayeni, Okechinyere Achilonu, Mariam Adeleke, Theo Nair, Joseph Otten, Daniel Mmereki

“…Phase 1 (feasibility) encompasses system commissioning, including beam modeling, computed tomography (CT)-to-electron density calibration, multileaf collimator (MLC) optimization, and dose calculations using the anisotropic analytical algorithm. …”
Get full text

Forest aboveground carbon storage estimation and uncertainty analysis by coupled multi-source remote sensing data in Liaoning Province by Hancong Fu, Hengqian Zhao, Ge Liu, Yujiao Zhang, Xiadan Huangfu, Jinbao Jiang

“…Finally, selecting 12.5 m as the optimal fitting radius of the model, we obtained the forest AGC stock results at the spot scale of the GEDI and ICESat-2 in the province. …”
Get full text

Damage prediction of rear plate in Whipple shields based on machine learning method by Chenyang Wu, Xiangbiao Liao, Lvtan Chen, Xiaowei Chen

“…Efficient numerical tools for precisely predicting the damage degree can greatly accelerate the design and optimization of advanced protective structures. Current hypervelocity impact research primarily focuses on the interaction between projectile and front plate and the movement of debris cloud. …”
Get full text

Augmenting Naïve Bayes Classifiers with <i>k</i>-Tree Topology by Fereshteh R. Dastjerdi, Liming Cai

“…Therefore, this algorithm can be employed to ensure efficient approximation of Bayesian networks with <i>k</i>-tree augmented Naïve Bayesian classifiers of the guaranteed minimum loss of information.…”
Get full text

Invisible Manipulation: Deep Reinforcement Learning-Enhanced Stealthy Attacks on Battery Energy Management Systems by Qi Xiao, Lidong Song, Jong Ha Woo, Rongxing Hu, Bei Xu, Kai Ye, Ning Lu

“…To minimize real-time computational demands, we transform this online optimization problem into an offline DRL training problem, utilizing high-fidelity simulation data from a digital twin-based microgrid testbed. …”
Get full text

Development of a machine learning-based predictive risk model combining fatty acid metabolism and ferroptosis for immunotherapy response and prognosis in prostate cancer by Zhenwei Wang, Zhihong Dai, Yuren Gao, Zhongxiang Zhao, Zhen Li, Liang Wang, Xiang Gao, Qiuqiu Qiu, Xiaofu Qiu, Zhiyu Liu

“…A machine learning-based prognostic model, optimized using the Lasso + Random Survival Forest (RSF) algorithm, achieved a high C-index of 0.876 and demonstrated strong predictive accuracy (1-, 2-, and 3-year AUCs: 0.77, 0.75, and 0.78, respectively). …”
Get full text

Modeling Marine Geoid in the China Seas and Its Adjacent Ocean Based on Satellite Altimeter-Derived Gravity Anomaly Model by Huiying Zhang, Xin Liu, Zhen Li, Xiaotao Chang, Heping Sun, Hui Li, Jinyun Guo

“…The SDUST2022 GRA marine gravity anomaly model is the global marine gravity anomaly model constructed by integrating multi-source altimeter satellites, including ICEsat-2 laser altimeter satellite for the first time. The model optimizes the deflection of the vertical accuracy imbalance. …”
Get full text

Thermal performance enhancement in a solar air heater fitted with flapped V-baffles: Numerical study by Chinnapat Turakarn, Pitak Promthaisong, Teerapat Chompookham

“…The energy costs can be effectively managed by VG as well as improving thermal performance if the VG was optimally designed.The effect of flapped V-baffles (FVB) on thermal performance enhancement in a solar air heater in the turbulent flow regime was numerically investigated. …”
Get full text

Machine learning-based radiomics for differentiating lung cancer subtypes in brain metastases using CE-T1WI by Xueming Xia, Wei Du, Qiheng Gou

“…Among them, 173 individuals had NSCLC with 228 BMs, while 87 patients were diagnosed with SCLC with 142 BMs. …”
Get full text

18F-FDG dose reduction using deep learning-based PET reconstruction by Ryuji Akita, Komei Takauchi, Mana Ishibashi, Shota Kondo, Shogo Ono, Kazushi Yokomachi, Yusuke Ochi, Masao Kiguchi, Hidenori Mitani, Yuko Nakamura, Kazuo Awai

“…Compared to the recommended dose in the European Association of Nuclear Medicine (EANM) guidelines for 90 s per bed position (4.7 MBq/kg), this represents a dose reduction of 36%. Further optimization of DLR algorithms is required to maintain comparable diagnostic accuracy in patients weighing 75 kg or more.…”
Get full text

Patterns of inflammation and immune activation by coreceptor use in people living with HIV-1 by Francisco Xavier Guerra-Castillo, Francisco Xavier Guerra-Castillo, Sandra Pinto-Cardoso, Santiago Ávila-Ríos, Monserrat Chávez-Torres, Amy Peralta-Prado, Carolina González-Torres, Javier Gaytán-Cervantes, Brenda Requena-Benitez, Dafne Díaz-Rivera, Carmen Alaez-Verson, María Concepción Hernández-García, Vilma Carolina Bekker-Méndez

“…Elevated levels of IL-6 were significantly associated with the R5 group (p = 0.01), while the X4 group showed increased expression of CD38+ and HLA-DR+CD38+ markers, although not statistically significant. …”
Get full text

Instrument Performance Analysis for Methane Point Source Retrieval and Estimation Using Remote Sensing Technique by Yuhan Jiang, Lu Zhang, Xingying Zhang, Xifeng Cao, Haiyang Dou, Lingfeng Zhang, Huanhuan Yan, Yapeng Wang, Yidan Si, Binglong Chen

“…The results indicate that an optimal plume estimation requires high spatial and spectral resolution alongside an adequate SNR. …”
Get full text

A machine learning approach to identifying key predictors of Peruvian school principals' job satisfaction by Luis Alberto Holgado-Apaza, Dany Dorian Isuiza-Perez, Nelly Jacqueline Ulloa-Gallardo, Yban Vilchez-Navarro, Ruth Nataly Aragon-Navarrete, Wilian Quispe Layme, Marleny Quispe-Layme, Danger David Castellon-Apaza, Remo Choquejahua-Acero, Jaime Cesar Prieto-Luna

“…The Histogram-Based Gradient Boosting algorithm, optimized with Bayesian techniques and trained with data balanced through Random Oversampling, achieved a balanced accuracy of 0.63 on a test set with real-world class distribution. …”
Get full text

Development and validation of dynamic clinical subphenotypes in acute pancreatitis patients using vital sign trajectories in intensive care units: a multinational cohort study by Zichen Wang, Wen Wang, Jiayue Xu, Qiao He, Che Sun, Shuangyi Xie, Kang Zou, Qing Xia, Xin Sun

“…For hyperinflammatory phenotype, the algorithm-estimated lowest-risk fluid range was 4100–4300 mL on day 1 and 3400–3600 mL on day 2; for phenotype hypoinflammatory phenotype, the optimal ranges were 2800–3800 mL and 1400–2600 mL, respectively. …”
Get full text

Comprehensive analysis on soil nitrogen prediction using near-infrared spectroscopy: Models, methods, and insights for precision agriculture by Xiaoyu Wang, Zhiyou Zhang, Yujiao Li, Jie Li, Qing Yang, Qiqi Liu, Zhijie Gong, Mengling Zhang, Xu Wang, Guanghui Xie

“…Key findings include: (1) Sample sizes for modeling predominantly ranged between 22 and 163 (80.0 %); (2) Fourier transform near-infrared spectrometers were the most widely used NIR spectrometers (43.5 %), followed by a grating near-infrared spectrometer (17.4 %); (3) The most common NIR spectrometer wavelength range was 12,804–588 cm−1 (60.9 %); (4) Smoothing techniques (SG, average, and Whittaker) were the dominant preprocessing methods (44.4 %), while partial least squares (PLS) as the most effective modeling algorithm (69.7 %). …”
Get full text

Research on Characteristics and Influencing Factors of High Temperature Disaster Risk in Wuhan Based on Local Climate Zone by Shujing GUO, Li ZHANG

“…Furthermore, highly correlated LCZ types are screened out under the optimal size, the multicollinearity of all LCZ landscape pattern indices is examined and those with multicollinearity are excluded. …”
Get full text

Machine learning for detection of diffusion abnormalities-related respiratory changes among normal, overweight, and obese individuals based on BMI and pulmonary ventilation paramet... by Xin-Yue Song, Xin-Peng Xie, Wen-Jing Xu, Yu-Jia Cao, Bin-Miao Liang

“…We evaluated the effectiveness of various supervised ML algorithms and identified the optimal configurations for these applications. …”
Get full text

Construction and application of a drought classification model for tea plantations based on multi-source remote sensing by Yang Xu, Yilin Mao, He Li, Xiaojiang Li, Litao Sun, Kai Fan, Zhipeng Li, Shuting Gong, Zhaotang Ding, Yu Wang

“…To address this gap, we propose RSDCM (Remote Sensing-based Drought Classification Model), an improved Genetic Algorithm-Backpropagation (GA-BP) combined with MS + TIR framework that optimizes initial weights and thresholds via GA's global search (hidden layer=1, neurons in the hidden layers=5, 50 generations, population size=5, NonUnifMutation operators) to escape local minima and accelerate convergence. …”
Get full text