Contrastive Learning with Global and Local Representation for Mixed-Type Wafer Defect Recognition by Shantong Yin, Yangkun Zhang, Rui Wang

“…The accurate classification and segmentation of these defect patterns are of utmost significance as they are key to tracing the root causes of defects, thereby reducing costs and enhancing both product efficiency and quality. …”
Get full text

Active Learning Query Strategies for Linear Regression Based on Efficient Global Optimization by Tianxin Zong, Na Li, Zhigang Zhang

“…Active learning, a subfield of machine learning, can train a good model by selecting a minimum number of labeled samples. In many machine learning scenarios, needed information (such as the best value in unlabeled datasets) is acquired by prediction. …”
Get full text

Film Recommender System Menggunakan Metode Neural Collaborative Filtering by Ni’mah Khoiriyah Ayyiyah, Retno Kusumaningrum, Rismiyati Rismiyati

“…The evaluation of the model was carried out using the Root Mean Square Error regression score metric. The results on the model test show the best results with can average loss value of 0,1356 on the train label and 0,8898 on the val label, with the learning rate and batch size getting the best performance when the learning rate is 0,001 and the batch size is 1024. …”
Get full text

An Elastic Fine-Tuning Dual Recurrent Framework for Non-Rigid Point Cloud Registration by Munan Yuan, Xiru Li, Haibao Tan

“…Many advanced non-rigid alignment models are implemented using supervised learning; however, the large number of labels required for the training process makes their application difficult. …”
Get full text

Enhancing No Reference Laparoscopic Video Quality Assessment with Evolutionary ANFIS by Biswas Sria, Palanisamy Rohini

“…Performance comparison with other state-of-the-art methods reveals superior results, with high correlation scores of 0.9989 and 0.9446 for experts and 0.9956 and 0.9847 for non-experts, alongside low root mean square errors of 0.0828 and 0.1685 for expert and non-experts, respectively. …”
Get full text

ADAMTS7, a target in atherosclerosis, cooperates with its homolog ADAMTS12 to protect against myxomatous valve degeneration by Timothy J. Mead, Sumit Bhutada, Niccolò Peruzzi, Janet Adegboye, Deborah E. Seifert, Elisabeth Cahill, Jeanne Drinko, Eoin Donnellan, Anu Guggiliam, Zoran Popovic, Brian Griffin, Karin Tran-Lundmark, Suneel S. Apte

“…We conclude that the myxomatous degeneration in Adamts7−/−;Adamts12−/− valve leaflets reflects a complex disturbance of ECM proteostasis with accumulation of multiple ADAMTS7 and ADAMTS12 ECM substrates, and perturbation of regulatory pathways with roots in ECM, such as TGFβ signaling, which was increased in the mutant valves.…”
Get full text

Positive rhizosphere priming accelerates carbon release from permafrost soils by Nina L. Friggens, Gustaf Hugelius, Steven V. Kokelj, Julian B. Murton, Gareth K. Phoenix, Iain P. Hartley

“…Here, we provide direct evidence of live plant-induced positive rhizosphere priming in permafrost and active-layer soils across diverse soil types from Arctic and Subarctic Canada. By 13CO2 labelling plants in a controlled environment, we show that root activity increases carbon loss from previously frozen soils by 31%. …”
Get full text

Multi-Dimensional Anomaly Detection and Fault Localization in Microservice Architectures: A Dual-Channel Deep Learning Approach with Causal Inference for Intelligent Sensing by Suchuan Xing, Yihan Wang, Wenhe Liu

“…Traditional monitoring sensor tools struggle with heterogeneous metrics, temporal correlations, and precise root cause analysis in these environments. This paper proposes a dual-channel deep learning framework that integrates Temporal Convolutional Networks with Variational Autoencoders to address these challenges. …”
Get full text

Sentiment Analysis of Netizens on Constitutional Court Rulings in the 2024 Presidential Election by Wahyudi Ariannor, Sami M A B Alshalwi, Budi Susarianto

“…This study adopts an experimental methodology, involving several key stages such as data collection through Twitter web scraping, labelling, pre-processing, TF-IDF weighting, and algorithm testing. …”
Get full text

Impact of WRF Model Parameterization Settings on the Quality of Short-Term Weather Forecasts over Poland by Sebastian Kendzierski

“…To assess the model’s performance across different weather stations, statistical metrics such as the mean absolute error (MAE) and root mean square error (RMSE) were employed. The findings indicate that the configuration labeled “p2” produced the most accurate forecasts for temperature, wind speed, and atmospheric pressure, achieving MAE values of 1.5 °C, 1.6 m/s, and 2 hPa, respectively. …”
Get full text

Charged polystyrene microplastics inhibit uptake and transformation of 14C-triclosan in hydroponics-cabbage system by Enguang Nie, Yandao Chen, Shengwei Xu, Zhiyang Yu, Qingfu Ye, Qing X. Li, Zhen Yang, Haiyan Wang

“…PS-MPs also reduced the translocation of triclosan from the roots to the shoots in cabbage, with a reduction rate of 15.6 %, 28.3 %, and 65.8 % for PS-COO-, PS, and PS-NH3+, respectively. …”
Get full text

Machine learning application to predict binding affinity between peptide containing non-canonical amino acids and HLA-A0201. by Shan Jiang, Zhaoqian Su, Nathaniel Bloodworth, Yunchao Liu, Cristina E Martina, David G Harrison, Jens Meiler

“…Our model demonstrates robust performance, with 5-fold cross-validation yielding an R2 value of 0.477 and a root-mean-square error (RMSE) of 0.735, indicating strong predictive capability for peptides with NCAAs. …”
Get full text

Trinocular Vision-Driven Robotic Fertilization: Enhanced YOLOv8n for Precision Mulberry Growth Synchronization by Ma Ming, Osama Elsherbiny, Jianmin Gao

“…This study focused on addressing the issue of delayed root system development in mulberry trees during aerosol cultivation, which is attributed to the asynchronous growth of branches and buds. …”
Get full text

Advancing state of health estimation for electric vehicles: Transformer-based approach leveraging real-world data by Kosaku Nakano, Sophia Vögler, Kenji Tanaka

“…Despite the challenges posed by noisy EV real-world data, the model shows high accuracy, with a mean absolute error of 0.72% and a root mean square error of 1.17%. Moreover, our proposed pre-training strategies with unlabeled data, particularly SOH ordinal comparison, significantly enhance the model’s performance; using only 50% of the labeled data achieves results nearly identical to those obtained with the full dataset. …”
Get full text

Current–Pressure Dynamics Modeling on an Annular Magnetorheological Valve for an Adaptive Rehabilitation Device for Disabled Individuals by Fitrian Imaduddin, Zaenal Arifin, Ubaidillah, Essam Rabea Ibrahim Mahmoud, Abdulrahman Aljabri

“…The modeling yielded a 14th-order transfer function, labeled TF14, which closely aligns with experimental data, achieving a root mean square error of 12.64%. …”
Get full text

Quality improvement project to reduce length of stay for patients with urinary tract infections in an NHS hospital trust by Molly Crawford

“…A3 thinking (a quality improvement method) was used to define the problem, analyse the data, complete root cause analysis and test change. The project aimed to impact the whole hospital system; however, using quality improvement methodology, the area with the biggest potential impact was focused on which was the emergency department. …”
Get full text

Pesticide use in vegetable production in rural Uganda - A case study of Kabale District, South western Uganda by Hannington, Ngabirano, Grace, Birungi

“…Only 18% of the interviewed farmers could interpret instructions on pesticide container or bag labels correctly. All farmers (100%) had never attended any training on pesticide use. …”
Get full text

Underground Personnel Positioning Method Based on Self-training and NLOS Suppression by SHAO Xiaoqiang, HAN Zehui, MA Bo, YANG Yongde, YUAN Zewen, LI Xin

“…First, PDR and map information are combined to remove infeasible positions, and multi-granularity mesh filters are used to estimate the position and heading, and the map information is fully utilized to generate weak labels. Second, through multi-sensor data fusion, the weak label is iteratively improved, and training samples are generated to realize autonomous collection of training data. …”
Get full text

Spatiotemporal Super-Resolution of Satellite Sea Surface Salinity Based on a Progressive Transfer Learning-Enhanced Transformer by Zhenyu Liang, Senliang Bao, Weimin Zhang, Huizan Wang, Hengqian Yan, Juan Dai, Peikun Xiao

“…PTL effectively balanced structural detail acquisition and local accuracy correction by combining the gridded reanalysis products with scattered in situ observations as training labels. Validated against independent in situ measurements, TSR outperformed existing L3 salinity satellite products, as well as convolutional neural network and generative adversarial network-based SR models, particularly reducing the root mean square error (RMSE) by 33% and the mean bias (MB) by 81% compared to the SMOS input. …”
Get full text

Comprehensive analysis of the physiological and molecular responses of phosphate-solubilizing bacterium Burkholderia gladioli DJB4–8 in promoting maize growth by Dao-Jun Guo, Dao-Jun Guo, Dao-Jun Guo, Guo-Rong Yang, Pratiksha Singh, Juan-Juan Wang, Juan-Juan Wang, Xue-Mei Lan, Rajesh Kumar Singh, Jing Guo, Yu-Die Dong, Dong-Ping Li, Dong-Ping Li, Dong-Ping Li, Bin Yang, Bin Yang

“…By scanning electron microscope (SEM) and green fluorescent protein (GFP) labeling technique, it was found that strain DJB4–8 formed a colonization symbiotic system with maize roots. …”
Get full text