Latest Publications & Patents on Neural Networks
This is our latest selection of worldwide publications and patents in english on Neural Networks, between many scientific online journals, classified and focused on neural network, artificial neuron, epoch, neural architecture, machine learning, deep learning and support vector machine.
Tip: further to this selection on Neural Networks, you can search and filter our:
* free publications search tool * by author, topic, keywords, date or journal.
* free patents search tool * for patents in english from the European Patent Office.
Predicting Six-Month Survival to Optimize Clinical Decisions
Published on 2025-02-23 by Jaehyuk Lee, Youngchae Cho, Yeunwoong Kyung, Eunchan Kim @MDPI
Abstract: Colorectal cancer (CRC) has a relatively high five-year survival rate compared to other cancers; however, this rate drops significantly in patients with malignant CRC. One critical factor in palliative care decision-making is the ability to accurately predict patient survival, with the six-month survival period commonly used as a threshold. In this study, we evaluated the performance of five machine learning models—logistic regression, decision tree, random forest, multilayer perce[...]
Our summary: Evaluation of machine learning models for predicting six-month survival in patients with malignant colorectal cancer using a synthetic dataset. XGBoost demonstrated the highest performance with 95% accuracy, precision, recall, and F1-score. Feature importance analysis identified smoking status and surgical history as key factors influencing predictions.
machine learning, six-month survival, colorectal cancer, XGBoost
Publication
A Transformer-Based Approach for Efficient Geometric Feature Extraction from Vector Shape Data
Published on 2025-02-23 by Longfei Cui, Xinyu Niu, Haizhong Qian, Xiao Wang, Junkui Xu @MDPI
Abstract: The extraction of shape features from vector elements is essential in cartography and geographic information science, supporting a range of intelligent processing tasks. Traditional methods rely on different machine learning algorithms tailored to specific types of line and polygon elements, limiting their general applicability. This study introduces a novel approach called “Pre-Trained Shape Feature Representations from Transformers (PSRT)”, which utilizes transforme[...]
Our summary: Efficient extraction of shape features from vector elements using transformer encoders with self-supervised pre-training tasks. Enables general shape feature extraction for line and polygon elements, enhancing training efficiency and accuracy in various tasks. Offers a unified, efficient solution for processing vector shape data.
Transformer-Based Approach, Geometric Feature Extraction, Vector Shape Data, Pre-Trained Shape Feature Representations
Publication
A Study of the Dynamics of Sea Ice Albedo in the Sea of Okhotsk
Published on 2025-02-23 by Yingzhen Zhou, Wei Li, Nan Chen, Takenobu Toyota, Yongzhen Fan, Tomonori Tanikawa, Knut Stamnes @MDPI
Abstract: This study utilizes a novel albedo retrieval framework combining radiative transfer modeling with scientific machine learning (RTM-SciML) to investigate sea ice dynamics in the Sea of Okhotsk. By validating albedo estimates derived from the MODIS sensor against in situ pyranometer measurements near the Hokkaido coast, we achieved a robust Pearson coefficient of 0.86 and an RMSE of 0.089 for all sea ice types, with even higher correlations for specific surfaces like snow-covered ice (Pearson-r = [...]
Our summary: Study of sea ice albedo dynamics in Sea of Okhotsk using RTM-SciML framework, validation of albedo estimates from MODIS sensor, cross-sensor comparisons with SGLI, integration with AMSR-2 data for analysis of regional climate processes.
sea ice dynamics, albedo retrieval, radiative transfer modeling, scientific machine learning
Publication
Estimating Collision Probabilities with Trajectory Prediction Boundaries Using Deep Learning Models
Published on 2025-02-23 by Robertas Jurkus, Julius Venskus, Jurgita Markevi?i?t?, Povilas Treigys @MDPI
Abstract: We investigate maritime accidents near Bornholm Island in the Baltic Sea, focusing on one of the most recent vessel collisions and a way to improve maritime safety as a prevention strategy. By leveraging Long Short-Term Memory autoencoders, a class of deep recurrent neural networks, this research demonstrates a unique approach to forecasting vessel trajectories and assessing collision risks. The proposed method integrates trajectory predictions with statistical techniques to construct probabilis[...]
Our summary: Investigating maritime accidents near Bornholm Island in the Baltic Sea, focusing on recent vessel collisions and improving maritime safety. Leveraging Long Short-Term Memory autoencoders to forecast vessel trajectories and assess collision risks. Introducing collision risk score to evaluate boundary overlaps for collision detection.
collision probabilities, trajectory prediction boundaries, deep learning models, maritime accidents
Publication
A Spatiotemporal-Adaptive-Network-Based Method for Predicting Axial Forces in Assembly Steel Struts with Servo System of Foundation Pits
Published on 2025-02-22 by Weiwei Liu, Jianchao Sheng, Jian Zhou, Jinbo Fu, Wangjing Yao, Kuan Chang, Zhe Wang @MDPI
Abstract: The axial force in assembly steel struts with servo systems is a critical indicator of stability in foundation pit support systems. Due to its high sensitivity to temperature variations and direct influence on the lateral deformation of the foundation pit enclosure structure, accurate prediction is essential for safety monitoring and early warning. This study proposes a novel method for predicting the axial force in assembly steel struts with servo systems based on a spatiotemporal adaptive netw[...]
Our summary: Novel method for predicting axial forces in assembly steel struts with servo systems based on spatiotemporal adaptive network. Historical data fed into LSTM network, self-attention mechanism captures global dependencies, CNN extracts local spatial features, and excavation data used to derive stratification-related features for more accurate predictions. Validation on deep foundation pit data shows improved performance.
LSTM network, self-attention mechanism, convolutional neural network, spatiotemporal adaptive network
Publication
New Method for Improving Tracking Accuracy of Aero-Engine On-Board Model Based on Separability Index and Reverse Searching
Published on 2025-02-22 by Hui Li, Yingqing Guo, Xinyu Ren @MDPI
Abstract: Throughout its service life, an aero-engine will experience a series of health conditions due to the inevitable performance degradation of its major components, and characteristics will deviate from their initial states. For improving tracking accuracy of the self-tunning on-board engine model on the engine output variables throughout the engine service life, a new method based on the separability index and reverse search algorithm was proposed in this paper. By using this method, a qualified tr[...]
Our summary: New method proposed for improving tracking accuracy of on-board aero-engine model throughout service life, based on separability index and reverse search algorithm. Higher accuracy maintained in engine life compared to sample memory factors method. Real-time monitoring of engine gas path parameters possible with training set center generated by proposed method.
tracking accuracy, aero-engine, separability index, reverse searching
Publication
Fluid flow simulation
Patent published on the 2025-02-19 in EP under Ref EP4510034 by ROLLS ROYCE PLC [GB] (Loh Jessica Sher En [gb], Arafat Naheed Anjum [gb], Kong Wai Kin Adams [gb], Chan Wai Lee [gb], Conduit Bryce D [gb], Lim Wei Xan [gb], Oo Thant Zin [gb])
Abstract: A method of using a computer implemented neural network for a simulation of aerodynamic performance of a technical object having a geometry, the method comprising:Training the neural network using a plurality of sets of encodings of pre-computed computational fluid dynamics, CFD, outputs, wherein the training is generated using inputs comprising:a geometry of at least one training technical object;spatial locations of input nodes of the neural network as node attributes;a relationship between th[...]
Our summary: Method using neural network for aerodynamic simulation of technical objects, training with pre-computed CFD outputs, generating predicted aerodynamic performance.
Fluid flow simulation, neural network, aerodynamic performance, computational fluid dynamics
Patent
Method, system and computer readable medium for assisting or enhancing 5g radio planning
Patent published on the 2025-02-19 in EP under Ref EP4510672 by UNIV CATALUNYA POLITECNICA [ES] (Almasan Paul [es], SuÁrez-varela JosÉ [es], Lutu Andra [es], Cabellos-aparicio Albert [es], Barlet-ros Pere [es])
Abstract: A method, system, and computer programs for assisting or enhancing 5G radio planning are proposed. The method comprises obtaining information about a new deployment of 5G-generation radio cells in a given area; obtaining information about previous-generation radio cells already deployed in the given area, and computing a plurality of key performance indicators, KPI, of the previous-generation radio cells by processing the obtained information, providing a plurality of KPI previous-generation rec[...]
Our summary: Method, system, and computer programs for assisting or enhancing 5G radio planning by obtaining information about new and previous-generation radio cells, computing key performance indicators, generating representations using deep learning, and producing KPIs with a neural network model.
5G, radio planning, deep learning, neural network
Patent
EN 
FR 
DE 
ES 
IT