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

“…Testing on the same testbed allows real-time evaluation of microgrid responses, where the BEMS, EKF-based SoC estimation algorithms interact dynamically with the injected false measurements. …”
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

“…Firstly, the accuracy of the algorithm is verified using the 2190-degree XGM2019e_2159 gravity field model and the 2159-degree EGM2008 gravity field model. …”
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 finite volume method using the SIMPLE algorithm was used to resolve the problem. The goal was to enhance the thermal performance (in terms of the thermal enhancement factor, TEF) by increasing the heat transfer together with reducing the pressure loss, compared with a conventional V-baffles (CVB). …”
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

The potential role of next-generation sequencing in identifying MET amplification and disclosing resistance mechanisms in NSCLC patients with osimertinib resistance by Xiao Xiao, Xiao Xiao, Ren Xu, Ren Xu, Jun Lu, Beibei Xin, Chenyang Wang, Kexin Zhu, Hao Zhang, Xinyu Chen

“…With FISH results as gold standard, enumeration algorithm was applied to establish the optimal model for identifying MET amplification using gene copy number (GCN) data.ResultsThe optimal model for identifying MET amplification was constructed based on the GCN of MET, BRAF, CDK6 and CYP3A4, which achieved a 74.0% overall agreement with FISH and performed well in identifying MET amplification except polysomy with a sensitivity of 85.7% and a specificity of 93.9%. …”
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

“…The U-Net generator is a 3-channel input, 16-layer architecture while the PatchGan discriminator is a 6-channel input, 7-layer architecture. …”
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

Estimation and evaluation of iron reserves in the eastern area of Eileh1 mine, Razavi Khorasan province by Hamid Esmati Daroneh, Maryam Gholamzadeh

“…E1-RC-BH-9.2 and E1-RC-BH-27, while the minimum depth is 9 meters, associated with Rasol borehole No. …”
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

“…While a spatial resolution degradation within 120 m has little impact on quantification, a high spatial resolution is important for detecting low-emission plumes. …”
Get full text

Performance evaluation of inset feed microstrip patch antenna parameters with different substrate materials for 5G wireless applications by Kebbekoppalu Shrinivasa Praveena, M Patil Chandrashekar

“…The proposed method uses a new hybrid GA-PSO algorithm with Dynamic Adaptive Mutation and Inertia Control (DAMIC). …”
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

A large-scale prospective nested case-control study: developing a comprehensive risk prediction model for early detection of pancreatic cancer in the community-based ESPRIT-AI coho... by Chaoliang Zhong, Penghao Li, Jia Zhao, Xue Han, Beilei Wang, Gang Jin

“…Multiple machine learning algorithms were compared, with the best performing algorithm selected for the final predictive model, subsequently validated using a real-world external test cohort. …”
Get full text

A cross-sectional study of evaluating cervical spondylotic myelopathy based on gait and plantar pressures by Xuhong Zhang, Zichuan Wu, Hanlin Song, Aochen Xu, Junbin Liu, Junzhe Sheng, Baifeng Sun, Min Qi, Chen Xu, Yang Liu

“…Gait parameters were obtained by capturing video of the patient while walking via a smartphone-based computer vision algorithm (using the OpenPose framework), and plantar pressure distributions were measured using wireless sensor-equipped insoles (sampling rate 50–100 Hz). …”
Get full text

Inversion of Leaf Chlorophyll Content in Different Growth Periods of Maize Based on Multi-Source Data from “Sky–Space–Ground” by Wu Nile, Su Rina, Na Mula, Cha Ersi, Yulong Bao, Jiquan Zhang, Zhijun Tong, Xingpeng Liu, Chunli Zhao

“…This study proposes an improved method based on multi-source data, combining the Sentinel-2A spectral response function (SRF) and computer algorithms, to overcome the limitations of traditional methods. …”
Get full text

Preliminary performance analysis using the PPP-RTK service of the National Land and Mapping Center in Taiwan by J.-Y. Lin, C.-H. Chu, F.-Y. Chu, K.-W. Chiang, M.-L. Tsai

“…Regarding real-time performance, while (Precise Point Positioning-Real Time Kinematic)PPP-RTK's corresponding accuracy is not as high as Network-RTK (NRTK), PPP-RTK can provide rapid positioning solutions with a single antenna and single Global Navigation Satellite System(GNSS) receiver. …”
Get full text