Rapid and non-destructive monitoring of the drying process of glutinous rice using visible-near infrared hyperspectral imaging by Kabiru Ayobami Jimoh, Norhashila Hashim, Rosnah Shamsudin, Hasfalina Che Man, Mahirah Jahari

“…The best performance accuracy (RP2≥99.99░%)was obtained when the SG1D and Gaussian process regression (GPR) model were combined with iteratively retained informative variable algorithm (SG1D-IRIV-GPR), variable iterative space shrinkage (SG1D-VISSA-GPR) and variable combination population analysis (SG1D-VCPA-GPR) for the prediction of MC, GI, and ΔE, respectively. …”
Get full text

YOLOv8n-WSE-Pest: A Lightweight Deep Learning Model Based on YOLOv8n for Pest Identification in Tea Gardens by Hongxu Li, Wenxia Yuan, Yuxin Xia, Zejun Wang, Junjie He, Qiaomei Wang, Shihao Zhang, Limei Li, Fang Yang, Baijuan Wang

“…To enable the intelligent monitoring of pests within tea plantations, this study introduces a novel image recognition algorithm, designated as YOLOv8n-WSE-pest. Taking into account the pest image data collected from organic tea gardens in Yunnan, this study utilizes the YOLOv8n network as a foundation and optimizes the original loss function using WIoU-v3 to achieve dynamic gradient allocation and improve the prediction accuracy. …”
Get full text

Development of a three-species gut microbiome diagnostic model for acute pancreatitis and its association with systemic inflammation: a prospective cross-sectional study by Yuanyuan Gou, Long Yao, Wenli Yang, Qian Chen, Yuetao Wen, Jie Cao

“…High-throughput 16S rRNA sequencing analyzed taxonomic profiles, while a random forest algorithm was employed to construct a diagnostic model based on differentially abundant species. …”
Get full text

Prospects of application of artificial neural networks for forecasting of cargo transportation volume in transport systems by D. T. Yakupov, O. N. Rozhko

“…The authors consider the possibility of forecasting to use ANN for these economic indicators not as an alternative to the traditional methods of statistical forecasting, but as one of the available simple means for solving complex problems.Materials and methods. When predicting the ANN, three methods of learning were used: 1) the Levenberg-Marquardt algorithm-network training stops when the generalization ceases to improve, which is shown by the increase in the mean square error of the output value; 2) Bayes regularization method - network training is stopped in accordance with the minimization of adaptive weights; 3) the method of scaled conjugate gradients, which is used to find the local extremum of a function on the basis of information about its values and gradient. …”
Get full text

Geographical features and management strategies for microplastic loads in freshwater lakes by Huike Dong, Ruixuan Zhang, Xiaoping Wang, Jiamin Zeng, Lei Chai, Xuerui Niu, Li Xu, Yunqiao Zhou, Ping Gong, Qianxue Yin

“…To address this gap, our study utilizes Machine Learning (the random forest algorithm), combined with number-to-mass transformation techniques to generate a global prediction. …”
Get full text

Enhanced dry SO₂ capture estimation using Python-driven computational frameworks with hyperparameter tuning and data augmentation by Robert Makomere, Hilary Rutto, Alfayo Alugongo, Lawrence Koech, Evans Suter, Itumeleng Kohitlhetse

“…SHapley Additive exPlanations was essential for comprehending the prediction mechanism through feature significance and the impact of varying feature thresholds on the predicted output. …”
Get full text

A systematic review of the role of quantitative CT in the prognostication and disease monitoring of interstitial lung disease by Giles Dixon, Hannah Thould, Matthew Wells, Krasimira Tsaneva-Atanasova, Chris J. Scotton, Michael A. Gibbons, Shaney L. Barratt, Jonathan C.L. Rodrigues

“…Hurdles exist to widespread adoption including governance concerns, appropriate algorithm anchoring and standardisation of image acquisition. …”
Get full text

Mapping the air temperature in China from time-normalized MODIS land surface temperature data via zone-based stacking ensemble models by Yan Xin, Yongming Xu, Xudong Tong, Yaping Mo, Yonghong Liu, Shanyou Zhu

Get full text

AI-based virtual immunocytochemistry for rapid and robust fine needle aspiration biopsy diagnosis by Irfan Ahmed, Wei Zhang, Pikting Cheung, Vardhan Basnet, Zulfiqar Ali, May PY Tse, Fraser Hill, Tom Tak Lam Chan, Haibo Hu, Xinyue Li, Condon Lau

“…In total, the geometrical features of 8.48 million segmented cells (4.24 million pairs) were translated into a tabular format and paired based on the Euclidean cell matching algorithm. This approach facilitated the prediction of cell labels, achieving sensitivity and specificity of 0.98 and 0.97 (0.94 and 0.99), respectively for CD3 (PAX5). …”
Get full text

Plasma cfDNA multi-omic biomarkers profiling for detection and stratification of gastric carcinoma by Shiyi Song, Xiuli Zhang, Pin Cui, Weihuang He, Jiyuan Zhou, Shubing Wang, Yong Xiong, Shu Xu, Xiaohui Lin, Guozeng Huang, Xiaohua Tan, Qinglong Xu, Yongling Liu, Qingqun Li, Kehua Yuan, Mingji Feng, Hanming Lai, Hui Yang, Shaorong Zhang

“…And these biomarkers were extracted from WGS data to build machine learning algorithm based classifiers, prediction models, to discriminate GC patients from healthy individuals, achieving extremely high precision of sensitivity at 94.87% and specificity at 99.35%. …”
Get full text

Capacity Estimation of Lithium-Ion Battery Systems in Fuel Cell Ships Based on Deep Learning Model by Xiangguo Yang, Jia Tang, Qijia Song, Yifan Liu, Lin Liu, Xingwei Zhou, Yuelin Chen, Telu Tang

“…A TCN-BiGRU model is then developed, with hyperparameters determined by the Kepler optimization algorithm (KOA). Cells from a battery pack under consistent conditions are used for training, while other cells in the same pack serve as the test set. …”
Get full text

Discrepancy in Metabolic Dysfunction–Associated Steatotic Liver Disease Prevalence in a Large Northern California Cohort by Luis A. Rodriguez, Lue-Yen S. Tucker, Varun Saxena, Theodore R. Levin

“…Annual MASLD prevalence was identified based on International Classification of Diseases, Ninth or Tenth Revision, Clinical Modification diagnosis codes, the application of natural language processing of all radiology imaging report text that included the liver, and the application of the Dallas Steatosis Index, a MASLD prediction algorithm. Results: Between 2009 and 2018, the estimated MASLD prevalence ranged from 0.37% to 0.95% using diagnosis codes, 0.88%–1.37% using imaging, and 6.14%–11.27% using the Dallas Steatosis Index. …”
Get full text

Non-Destructive Early Detection of Drosophila Suzukii Infestation in Sweet Cherries (c.v. <i>Sweet Heart</i>) Based on Innovative Management of Spectrophotometric Multilinear Corre... by Giuseppe Altieri, Mahdi Rashvand Avaei, Attilio Matera, Francesco Genovese, Vincenzo Verrastro, Naouel Admane, Orkhan Mammadov, Sabina Laveglia, Giovanni Carlo Di Renzo

“…To model the data fit/prediction, principal components regression and partial least squares regression algorithms were considered. …”
Get full text

Quantifying training response in cycling based on cardiovascular drift using machine learning by Artur Barsumyan, Artur Barsumyan, Raman Shyla, Anton Saukkonen, Christian Soost, Jan Adriaan Graw, Rene Burchard, Rene Burchard, Rene Burchard

“…Based on aerobic decoupling (power-to-heart rate ratio) and cardiovascular drift of each test ride, a prediction model was created using ML (Logistic regression, Variational Gaussian Process models and k-nearest neighbors algorithm) that indicated whether or not an athlete was responding to the training. …”
Get full text

Harnessing Artificial Intelligence and Innovative Vaccines for Mpox Diagnosis and Control: A Comprehensive Narrative Review by Excel Onajite Ernest-Okonofua, Zainab Abdullahi Zubairu, Malik Olatunde Oduoye, Maryam Tariq, Syed Muhammad, Zainab Siddiqua, Monica Vuyyuru, Benjamin Wafula, Riaz Akhtar, Abdulbasit Fasasi, Samuel Chinonso Ubechu, Bakare Sikiru Olayinka

“…Future directions should be focused on healthcare professionals to establish the validity and reliability of the models, a measure of the algorithm’s robustness, and the continuous auditing of AI systems.…”
Get full text

Rapid discrimination and quantification of chemotypes in Perillae folium using FT-NIR spectroscopy and GC–MS combined with chemometrics by Dai-xin Yu, Cheng Qu, Jia-yi Xu, Jia-yu Lu, Di-di Wu, Qi-nan Wu

“…Based on FT-NIR data, different chemotypes were accurately classified. The random forest algorithm achieved >90 % accuracy in chemotype classification. …”
Get full text

Integrative machine learning and molecular simulation approaches identify GSK3β inhibitors for neurodegenerative disease therapy by Hassan H. Alhassan

“…Among all models, the Random Forest (RF) algorithm had the best prediction accuracy, with a value of 0.6832 on the test set and 0.7432 on the training set, and was employed to screen the target library of 11,032 phytochemicals. …”
Get full text

Machine learning-driven design of rare metal doped niobium alloys with enhanced strength and ductility by Zhenqiang Xiong, Zhaokun Song, Jianwei Li, Heran Wang, Xiaoxin Zhang, Bin Liang, Dong Wang

“…The model was integrated with the Non-dominated Sorting Genetic Algorithm (NSGA-III) to design alloys with superior comprehensive properties. …”
Get full text

Construction and application of a digital twin model for multi-objectiveoptimization of intelligent tape conveyor system by Wei CHEN, Jingzhao LI, Qing SHI, Jichao LIU, Huashun LI

“…In evaluating system performance, we establish key performance indicators: the amount of spillage, wear of crucial components, total power used by the cleaning mechanism, and accuracy in predicting the sweeping force. We compare our system’s performance under various operational scenarios against an array of common optimization algorithms. …”
Get full text

Imbalanced Power Spectral Generation for Respiratory Rate and Uncertainty Estimations Based on Photoplethysmography Signal by Soojeong Lee, Mugahed A. Al-antari, Gyanendra Prasad Joshi, Yeong Hyeon Gu

“…However, machine learning (ML) algorithm errors embedded in health monitoring systems can be problematic in medical decision-making because some data have much larger sample sizes in the training set than others. …”
Get full text