Survey of federated learning research by Chuanxin ZHOU, Yi SUN, Degang WANG, Huawei GE

“…Federated learning has rapidly become a research hotspot in the field of security machine learning in recent years because it can train the global optimal model collaboratively without the need for multiple data source aggregation.Firstly, the federated learning framework, algorithm principle and classification were summarized.Then, the main threats and challenges it faced, were analysed indepth the comparative analysis of typical research programs in the three directions of communication efficiency, privacy and security, trust and incentive mechanism was focused on, and their advantages and disadvantages were pointed out.Finally, Combined with application of edge computing, blockchain, 5G and other emerging technologies to federated learning, its future development prospects and research hotspots was prospected.…”
Get full text

Research of the Rigid-flexible Coupling Dynamics Characteristic of the Conveying Belt of Belt Conveyor by Mao Jun, Li Xiaojing, Chen Hongyue, Liang Jinglong

“…To research the dynamics characteristics of the belt conveyor in actual working condition,by using the new method to establish the dynamics equation of the belt conveyor,that is through the "flexible beam and belt unit" to establish the mechanics equation,the coefficient matrix is derived.By using the RecurDyn software,the rigid-flexible coupling model of machine is built and according to coefficient matrix,the dynamics analysis is carried out,the dynamic characteristics of the conveying belt is obtained,it shows the conclusion that according to the conditions set by the different conditions of the belt conveyor,the method by using the rigid-flexible coupling simulation analysis is more close to the actual working condition.The correctness and advancement of the rigid-flexible coupling dynamics simulation analysis method are verified.A more effective and closer to the actual method of analysis for improving the system stability and structure optimize is provided.…”
Get full text

An ensemble deep learning framework for energy demand forecasting using genetic algorithm-based feature selection. by Mohd Sakib, Tamanna Siddiqui, Suhel Mustajab, Reemiah Muneer Alotaibi, Nouf Mohammad Alshareef, Mohammad Zunnun Khan

“…Recent advancements in computing power and the availability of large datasets have fueled the development of machine learning models. However, selecting the most appropriate features to enhance prediction accuracy and robustness remains a key challenge. …”
Get full text

Thai Morning Glory Price Forecasting Using Deep Learning by Kanokwan Waeodi, Laor Boongasame, Karanrat Thammarak

“…This study established advanced machine-learning-driven forecasting models to enhance the accuracy of price predictions for Thai morning glory, a widely consumed leafy green vegetable. …”
Get full text

Antimicrobial Susceptibility Profiles of <i>Escherichia coli</i> Isolates from Clinical Cases of Ducks in Hungary Between 2022 and 2023 by Ádám Kerek, Ábel Szabó, Ákos Jerzsele

“…The effectiveness of predictive models suggests that machine learning tools can aid in the early detection of MDR, contributing to the optimization of treatment strategies and the mitigation of resistance spread. …”
Get full text

Nitrogen content estimation of apple trees based on simulated satellite remote sensing data by Meixuan Li, Xicun Zhu, Xicun Zhu, Xinyang Yu, Cheng Li, Dongyun Xu, Ling Wang, Dong Lv, Yuyang Ma

“…The support vector machine model constructed based on Sentinel-2 satellite simulated data was the optimal nitrogen content inversion model, with an average R² value of 0.81 and an average RMSE value of 0.15 for training sets across different phenological periods, and an average R² value of 0.61 and an average RMSE value of 0.23 for validation sets.DiscussionThis study systematically evaluated the applicability and accuracy differences of multi-source satellite data for estimating nitrogen content in apple trees, and clarified the variation patterns of nitrogen-sensitive spectral bands and optimal modeling strategies across key phenological stages. …”
Get full text

Robust-PFedproto: robust federated prototype learning based on personalized layers by XU Mingdi, LI Zhengxiao, WANG Zihang, JIN Chaoyang

“…These layers, positioned before each client’s decision layer, were optimized to enhance client model adaptation to local datasets and improve localized task prediction accuracy. …”
Get full text

Autoregressive Neural Network for Cloud Concentration Forecast from Hemispheric Sky Images by Cristian Crisosto

“…Finally, the cloud concentration five minutes in advance at the IMUK is forecasted using machine learning methods. A persistence model forecast to provide a reference for comparison was generated. …”
Get full text

An Improved Method for Sizing Standalone Photovoltaic Systems Using Generalized Regression Neural Network by Tamer Khatib, Wilfried Elmenreich

“…The previous work is based on the analytical method which faced some concerns regarding the difficulty of finding the model’s coefficients. Therefore, the proposed approach in this research is based on a combination of an analytical method and a machine learning approach for a generalized artificial neural network (GRNN). …”
Get full text

RL Perceptron: Generalization Dynamics of Policy Learning in High Dimensions by Nishil Patel, Sebastian Lee, Stefano Sarao Mannelli, Sebastian Goldt, Andrew Saxe

“…We obtain optimal schedules for the learning rates and task difficulty—analogous to annealing schemes and curricula during training in RL—and show that the model exhibits rich behavior, including delayed learning under sparse rewards, a variety of learning regimes depending on reward baselines, and a speed-accuracy trade-off driven by reward stringency. …”
Get full text

Habitat radiomics predicts occult lymph node metastasis and uncovers immune microenvironment of head and neck cancer by Xinwei Chen, Huan Jiang, Min Pan, Chengmin Feng, Yanshi Li, Lin Chen, Yuxi Luo, Long Liu, Juan Peng, Guohua Hu

“…Based on Logistic Regression (LR), Support Vector Machine (SVM), and Random Forest (RF) classifiers, nine radiomics models were built to confirm the optimal predictive performance. …”
Get full text

Prediction of prognosis in acute ischemic stroke after mechanical thrombectomy based on multimodal MRI radiomics and deep learning by Lei Pei, Xiaowei Han, Chenfeng Ni, Junli Ke

“…The performance of each model in predicting poor prognosis was assessed using receiver operating characteristic (ROC) curve analysis, with the optimal model visualized as a nomogram. …”
Get full text

Enhanced Visualization of Erythrocytes Through Photoluminescence Using NaYbF₄:Yb³⁺,Er³⁺ Nanoparticles by Vivian Torres-Vera, Lorena M. Coronado, Ana Patricia Valencia, Alejandro Von Chong, Esteban Rua, Michelle Ng, Jorge Rubio-Retama, Carmenza Spadafora, Ricardo Correa

“…Under these conditions, the UCNPs exhibited minimal cytotoxicity and were found to predominantly localize at the erythrocyte membrane periphery, indicating surface adsorption rather than internalization. Additionally, a machine learning model (Random Forest) was implemented that classified the photoluminescent signal with 80% accuracy and 83% precision, with the signal intensity identified as the most relevant feature. …”
Get full text

Advanced computing to support urban climate neutrality by Gregor Papa, Rok Hribar, Gašper Petelin, Vida Vukašinović

“…By integrating these computational tools, cities can develop and optimize complex models that enable real-time, data-driven decisions. …”
Get full text

Impact of occupancy behavior on building energy efficiency: What’s next in detection and monitoring technologies? by Wenjie Song, John Calautit

“…Particular attention is paid to data-driven methods, including probabilistic models such as Hidden Markov Models (HMMs), classical machine learning algorithms such as Support Vector Machines (SVMs) and K-Nearest Neighbors (KNN), and deep learning architectures such as Convolutional Neural Networks (CNNs), all of which have demonstrated high accuracy in both laboratory and real-world settings. …”
Get full text

Risk assessment of water inrush from coal floor based on enhanced samples with class distribution by Shiwei Liu, Jiaxin Zhao, Hao Yu, Jiaqi Chen

“…Compared to other optimization models, our model showed the best prediction performance, with an error reduction of 42.95–51.27% and results biased towards safety. …”
Get full text

Study on Spark Image Detection for Abrasive Belt Grinding via Transfer Learning with YOLOv8 by Jian Huang, Guangpeng Zhang

“…The generalization ability of the model is enhanced through the following innovative strategies: (1) a cross-view transfer learning framework based on dynamic anchor box optimization is designed, and the parameters of the front spark detection model YOLOv8 are transferred to the side and 45°-angle detection tasks; (2) an attention-guided feature alignment module is introduced to alleviate the feature distribution shift caused by view differences; and (3) a curriculum learning strategy is adopted, where the datasets of different views are trained separately first and then sampled to reconstruct the dataset for further training, gradually increasing the weight of samples from complex views. …”
Get full text

A Decision-Making Framework for Multi-Objective Transportation Problem Using Fully Triangular Intuitionistic Fuzzy Sets by Vishwas Deep Joshi, Priya Agarwal, Huda Alsaud, Lenka Čepová, B. Swarna

Get full text

Feature-based enhanced boosting algorithm for depression detection by Muhammad Sadiq Rohei, Kasturi Dewi Varathan, Shivakumara Palaiahnakote, Nor Badrul Anuar

“…This approach resulted in generating an optimized feature set that augmented both the model’s accuracy and its interpretability. …”
Get full text

AMMap tool for additive manufacturing design, alloy discovery, and path planning by Alexander M Richter, Adam M Krajewski, Zhening Yang, Allison M Beese, Zi-Kui Liu

“…Equilibrium thermodynamic calculations and solidification simulations, such as Scheil–Gulliver, can be used to predict feasible compositions or compositional paths, acting as constraints before empirical or machine learning models are applied to predict properties of interest. …”
Get full text