Study on Photovoltaic Plant Site Selection Models Based on Geographic and Environmental Features by RAO Zhi, YANG Zaimin, YANG Xiongping, LI Jiaming, YANG Ping, WEI Zhichu

“…[Conclusions] The TCN-Informer model exhibited significant advantages in terms of accuracy and robustness for GHI prediction， enabling a more effective capture of temporal variation patterns in solar irradiance. It has a strong engineering application potential and provides solid data support for solar resource evaluation and photovoltaic site planning.…”
Get full text

Hybrid Deep Learning Architecture with Adaptive Feature Fusion for Multi-Stage Alzheimer’s Disease Classification by Ahmad Muhammad, Qi Jin, Osman Elwasila, Yonis Gulzar

“…Traditional convolutional neural networks (CNNs) and deep learning models often fail to effectively integrate localized brain changes with global connectivity patterns, limiting their efficacy in Alzheimer’s disease (AD) classification. …”
Get full text

Smart adaptive learning and optimized feature clustering for enhanced image retrieval by P. Umaeswari, Sujata Patil, Parameshachari Bidare Divakarachari, Przemysław Falkowski-Gilski

“…CBIR extracts key features related to texture, shape, and color using techniques such as Local Binary Pattern, Zernike Moments, and Color Moments. Additionally, an Entropy-based Divergence (ED) function is incorporated into a Convolutional Neural Network (CNN) named EDCNN to improve matching accuracy by reducing redundant activation in hidden layers. …”
Get full text

Application of a KAN-LSTM Fusion Model for Stress Prediction in Large-Diameter Pipelines by Zechao Li, Shiwei Qin

“…The model is trained and validated using actual pipeline monitoring data, ensuring that it accurately captures both the temporal dependencies and nonlinear stress patterns inherent in such systems. By modifying the fully connected layer of the original LSTM model, we develop a novel LSTM-KAN model and evaluate its performance through comprehensive predictive analysis. …”
Get full text

Fusion ConvLSTM-Net: Using Spatiotemporal Features to Increase Residential Load Forecast Horizon by Abhishu Oza, Dhaval K. Patel, Bryan J. Ranger

“…In this paper, we propose Fusion ConvLSTM-Net, a novel fusion encoder-decoder architecture that combines both spatial and temporal features to extend the load forecast to a full 24 hour period. We evaluated the model against several benchmark neural network models by: 1) testing different forecast window sizes ranging from 1.5 to 24 hours, 2) assessing model performance across multiple households, and 3) performing large-scale forecasting by aggregating predictions from 100 households. …”
Get full text

RQPool: A Novel Multi-Branch Graph-Level Anomaly Detection by Aaron Alex Philip, Ziad Kobti

“…Many systems such as social networks, communication systems, and biological networks are naturally represented as graphs with entities as nodes and interactions as edges. …”
Get full text

Deep Temporal and Structural Embeddings for Robust Unsupervised Anomaly Detection in Dynamic Graphs by Samir Abdaljalil, Hasan Kurban, Rachad Atat, Erchin Serpedin, Khalid Qaraqe

“…Detecting anomalies in dynamic graphs is a complex yet essential task, as existing methods often fail to capture long-term dependencies required for identifying irregularities in evolving networks. We introduce Temporal Structural Graph Anomaly Detection (<sc>T-StructGAD</sc>), an unsupervised framework that leverages Graph Convolutional Gated Recurrent Units (<monospace>GConvGRU</monospace>s) and Long Short-Term Memory networks (<monospace>LSTM</monospace>s) to jointly model both structural and temporal dynamics in graph node embeddings. …”
Get full text

Censoring Sensitivity Analysis for Benchmarking Survival Machine Learning Methods by János Báskay, Tamás Mezei, Péter Banczerowski, Anna Horváth, Tamás Joó, Péter Pollner

“…Five models were evaluated: Cox proportional hazards, survival tree, random survival forest, gradient-boosted survival analysis, and mixture density networks. …”
Get full text

Hybrid AI for Predictive Cyber Risk Assessment: Federated Graph-Transformer Architecture With Explainability by Jaime Govea, Rommel Gutierrez, William Villegas-Ch, Alexandra Maldonado Navarro

“…The model was trained and evaluated using public datasets (CIC-IDS2017, UNSW-NB15, MITRE ATT&#x0026;CK, TON_IoT) and synthetically generated traffic from honeypots and real anonymized networks. …”
Get full text

Histopathological-based brain tumor grading using 2D-3D multi-modal CNN-transformer combined with stacking classifiers by Naira Elazab, Fahmi Khalifa, Wael Gab Allah, Mohammed Elmogy

“…Our pipeline uses complementary feature extraction techniques to capture domain-specific knowledge related to brain tumor morphology, such as texture and intensity patterns. An efficient method of learning hierarchical patterns within the tissue is the 2D-3D hybrid convolution neural network (CNN), which extracts contextual and spatial features. …”
Get full text

Variational Methods in Optical Quantum Machine Learning by Marco Simonetti, Damiano Perri, Osvaldo Gervasi

“…Our research proposes new variational methods based on a deep learning system based on an optical quantum neural network applied to Machine Learning models for point classification. …”
Get full text

Personal Information Sharing Behavior Using Social Media by Ashraf Sharif, Shafiq Ur Rehman, Khalid Mahmood

“…This study explores personal information sharing behavior publication patterns and trends on social media from 2007-2024 with an aim to highlight the annual growth of personal information sharing behavior (PISB) on social media platforms, key patterns in the PISB literature in terms of frequently cited authors, countries, institutions, sources, highly cited papers, collaboration and authorship patterns, thematic evolution, keyword and key factor analysis (such as countries, sources, and keywords). …”
Get full text

Enhancing microgrid forecasting accuracy with SAQ-MTCLSTM: A self-adjusting quantized multi-task ConvLSTM for optimized solar power and load demand predictions by Ehtisham Lodhi, Nadia Dahmani, Syed Muhammad Salman Bukhari, Sujan Gyawali, Sanjog Thapa, Lin Qiu, Muhammad Hamza Zafar, Naureen Akhtar

Get full text

Deep-m6Am: a deep learning model for identifying N6, 2′-O-Dimethyladenosine (m6Am) sites using hybrid features by Islam Uddin, Salman A. AlQahtani, Sumaiya Noor, Salman Khan

“…Finally, a multilayer deep neural network (DNN) is used as a classification algorithm for identifying m6Am sites. …”
Get full text

A Novel Optimization Approach for Revolutionizing Architectural Design in Chinese Cultural Heritage by Xueyong Li, Xiaoqing Yang

“…Using this approach, machine learning models may be taught to see patterns, fix errors, and make wise predictions under different conditions.   …”
Get full text

Impact of Normalization Techniques on Synthetic Load Profile Generation Using Deep Generative Models by Luis H. T. Bandoria, Walquiria N. Silva, Madson C. De Almeida

Get full text

Hydroelectric Unit Fault Diagnosis Based on Modified Fractional Hierarchical Fluctuation Dispersion Entropy and AdaBoost-SCN by Xing Xiong, Zhexi Xu, Rende Lu, Yisheng Li, Bingyan Li, Fengjiao Wu, Bin Wang

“…Then, a novel method for evaluating the complexity of time-series signals, called MFHFDE, is presented. …”
Get full text

Interpretable Deep Learning for Diabetic Retinopathy: A Comparative Study of CNN, ViT, and Hybrid Architectures by Weijie Zhang, Veronika Belcheva, Tatiana Ermakova

“…Deep learning models have been widely used for automated DR classification, with Convolutional Neural Networks (CNNs) being the most established approach. …”
Get full text

IoT in Smart Urban Planning: A Comprehensive Review of Applications, Developments, and Engineering Perspectives by Ahmed A. Zakaria, Tasneem Amr, Amany A. Ragheb

“…Challenges related to power management, network scalability, cybersecurity, and sustainability are discussed, along with future research directions including tinyML, 6G networks, and biodegradable sensor platforms. …”
Get full text

Deep Learning Innovations: ResNet Applied to SAR and Sentinel-2 Imagery by Giuliana Bilotta, Luigi Bibbò, Giuseppe M. Meduri, Emanuela Genovese, Vincenzo Barrile

“…A test dataset derived from Sentinel-2 raster images is utilised to evaluate the effectiveness of the neural network (NN). …”
Get full text