Pattern Matching-Based Denoising for Images with Repeated Sub-Structures by Anil Kumar Mysore Badarinarayana, Christoph Pratsch, Thomas Lunkenbein, Florian Jug

“…State-of-the-art image denoising methods are dominated by supervised Convolution neural network (CNN)-based methods. However, supervised CNNs cannot be used if a noise-free ground truth is unavailable. …”
Get full text

An Evidential Solar Irradiance Forecasting Method Using Multiple Sources of Information by Mohamed Mroueh, Moustapha Doumiati, Clovis Francis, Mohamed Machmoum

“…Comparisons with deep learning-based methods, such as long short-term memory (LSTM) networks and recurrent neural networks (RNNs), demonstrate that the proposed approach is competitive with state-of-the-art techniques, delivering reliable predictions with significantly less training data. …”
Get full text

Conversion to Variable Flow Rate—Advanced Control of a District Heating (DH) System with a Focus on Operational Data by Stanislav Chicherin

“…The results show a significant reduction in excess heat supply during warm days, with improvements in heat demand prediction accuracy (17.3% average error) compared to standard models. Notably, the optimized configuration led to a 21% reduction in total greenhouse gas (GHG) emissions (including 6537 tons of CO₂ annually), a 55.3% decrease in annualized operational costs, and a positive net present value (NPV) by year nine, with an internal rate of return (IRR) of 25.4%. …”
Get full text

Interruption-Aware Computation Offloading in the Industrial Internet of Things by Khoi Anh Bui, Myungsik Yoo

“…Experimental results show that our approach effectively reduces the average total service delay by optimizing the tradeoff between system delay and availability in IIoT networks. …”
Get full text

Fractal-Based Robotic Trading Strategies Using Detrended Fluctuation Analysis and Fractional Derivatives: A Case Study in the Energy Market by Ekaterina Popovska, Galya Georgieva-Tsaneva

“…This paper presents an integrated robotic trading strategy developed for the day-ahead energy market that includes different methods for time series analysis and forecasting, such as Detrended Fluctuation Analysis (DFA), Rescaled Range Analysis (R/S analysis), fractional derivatives, Long Short-Term Memory (LSTM) Networks, and Seasonal Autoregressive Integrated Moving Average (SARIMA) models. …”
Get full text

The impact of individual and social environmental factors on the health of elderly migrants in China: an analysis based on social-ecological systems theory by Aidi Liao, Jingjin He, Xiafei Tao

“…To improve their health, targeted strategies should focus on fostering diverse social networks, enhancing comprehensive health education, optimizing public health services, and creating an equitable institutional framework.…”
Get full text

Characterization of Porosity and Copper Infiltration Mechanism in Sintered Steel via Computed Tomography by Pengcheng Lin, Linshan Wang, Shuanghua Liang, Xuebing Liang, Qiang Hu, Limin Wang, Xuanhui Qu

“…Molten copper preferentially penetrates high-connectivity networks, prioritizing irregular angular regions. Medium-sized pores (10.52–23.76 μm) with optimal connectivity are predominantly filled. …”
Get full text

A Novel Real-Time Battery State Estimation Using Data-Driven Prognostics and Health Management by Juliano Pimentel, Alistair A. McEwan, Hong Qing Yu

“…The method leverages an optimized bidirectional Long Short-Term Memory (Bi-LSTM) network, trained with enhanced datasets filtered via exponentially weighted moving averages (EWMAs) and refined through SHAP-based feature attribution. …”
Get full text

Drying Apple Slices in a Rotating-Tray Convective Dryer: A Study on Dehydration Characteristics and Qualitative Attributes by Hamid Ghasemkhani, Farhad Khoshnam, Mohamad Reza Kamandar

“…To improve quality attributes of the final dried product and execute a better management of the required energy, optimal process and technology it is essential to dry agri-food materials. …”
Get full text

The More, the Better? Evaluating the Role of EEG Preprocessing for Deep Learning Applications by Federico Del Pup, Andrea Zanola, Louis Fabrice Tshimanga, Alessandra Bertoldo, Manfredo Atzori

“…Preprocessing is crucial for EEG data analysis, yet there is no consensus on the optimal strategies in deep learning scenarios, leading to uncertainty about the extent of preprocessing required for optimal results. …”
Get full text

Impact of farmer training on potato yield: a case of smallholder potato farmers in Malawi by Ednah Kangogo, David Jakinda Otieno, Julius Okello, Obed Mwenye, Eliya Kapalasa

“…This requires advances in agricultural practices, technology and distribution networks. Farmer training has been proven to be a crucial component in this transformative process. …”
Get full text

Numerical investigation of flow field characteristics over vertical drops with sudden contraction for different contraction ratios by Hossein Shahin, Afshin Eghbalzadeh, Mitra Javan

“…The findings suggest that optimizing the contraction ratio is an effective design parameter for improving energy dissipation efficiency and overall hydraulic performance.…”
Get full text

Investigating artificial intelligence in predicting and evaluating sperm and embryo quality in the in vitro fertilization (IVF): a systematic review by Shahrzad kaveh, Aida Ghaffari, Solmaz Sohrabei

“…Two studies used neural networks for successful treatment prediction, and eight employed ML methods such as NB, SVM, and RF, with an average AUC of 0.91. …”
Get full text

Image Similarity Quantum Algorithm and Its Application in Image Retrieval Systems by Qingchuan Yang, Xianing Feng, Lianfu Wei

Get full text

Auto-embedding transformer under multi-source information fusion for few-shot fault diagnosis by Bo Wang, Shuai Zhao, Qian Zhao, Yang Bai

“…In the final stage, the architecture integrates global max pooling and global average pooling operations to optimize feature abstraction and improve resilience to data variations. …”
Get full text

Advancing smart communities with a deep learning framework for sustainable resource management. by Yongyan Zhao

“…The framework leverages long short-term memory (LSTM) networks for temporal data, convolutional neural networks (CNNs) for spatial analysis, and autoencoders for anomaly detection. …”
Get full text

Integration of FEM-based permeation analysis and AI-based predictive models for improved chemical grout permeation assessment in heterogeneous soils by Khin Nyein Chan Kyaw, Kuo Chieh Chao, Shinya Inazumi

“…Additionally, AI models, including neural networks and gradient boosting decision trees, were trained on FEM-derived datasets to predict permeation velocities and ranges with high accuracy (R² = 0.849). …”
Get full text

Lightning Prediction in the Tehran Region Using the WRF Model With Multiple Physical Parameterizations and an Ensemble Approach by Sakineh Khansalari, Maryam Gharaylou

“…The uncertainty in lightning simulation and the model's sensitivity to physical parameterization highlight the importance of using an ensemble approach in the WRF model. By averaging outputs from different configurations in the ensemble, a more optimal result, closer to observed data, can be achieved. …”
Get full text

Exploring the Structure of Growth and Maturation Research Among Basketball Players Using R Tools by Ximing Shang, Jorge Arede, Nuno Leite

“…Citation network analysis reveals that GAM research on basketball players predominantly addresses sports performance, strength, and injuries. …”
Get full text

Novel GSIP: GAN-based sperm-inspired pixel imputation for robust energy image reconstruction by Gamal M. Mahmoud, Wael Said, Magdy M. Fadel, Mostafa Elbaz

“…This paper introduces a novel approach for missing pixel imputation based on Generative Adversarial Networks (GANs). We propose a new GAN architecture incorporating an identity module and a sperm motility-inspired heuristic during filtration to optimize the selection of pixels used in reconstructing missing data. …”
Get full text