InvMOE: MOEs Based Invariant Representation Learning for Fault Detection in Converter Stations by Hao Sun, Shaosen Li, Hao Li, Jianxiang Huang, Zhuqiao Qiao, Jialei Wang, Xincui Tian

“…To overcome these issues, we propose InvMOE, a novel fault detection algorithm with two core components: (1) invariant representation learning, which captures task-relevant features and mitigates background noise interference, and (2) multi-task training using a mixture of experts (MOE) framework to adaptively optimize feature learning across tasks and address label sparsity. …”
Get full text

Predicting the Remaining Useful Life of an Aircraft Engine Using a Stacked Sparse Autoencoder with Multilayer Self-Learning by Jian Ma, Hua Su, Wan-lin Zhao, Bin Liu

“…Because they are key components of aircraft, improving the safety, reliability and economy of engines is crucial. …”
Get full text

Normalised Diagnostic Contribution Index (NDCI) Integration to Multi Objective Sensor Optimisation Framework (MOSOF)—An Environmental Control System Case by Burak Suslu, Fakhre Ali, Ian K. Jennions

“…Building on previous work, the proposed approach leverages a multi-objective genetic algorithm to optimise key criteria, including performance, cost, reliability management, and compatibility. …”
Get full text

Gap-filling of land surface temperature in arid regions by combining Landsat 8 and 9 imageries by Fahime Arabi Aliabad, Ebrahim Ghaderpour, Ahmad Mazidi, Fatemeh Houshmandzade

“…The aims of this research are to determine the optimal parameters for the reconstruction of Landsat-LST images, required in many applications, by the harmonic analysis of time series algorithm (HANTS) and to investigate the possibility of improving LST reconstruction accuracy using Landsat 8 and 9 images simultaneously. …”
Get full text

YOLO11-ARAF: An Accurate and Lightweight Method for Apple Detection in Real-World Complex Orchard Environments by Yangtian Lin, Yujun Xia, Pengcheng Xia, Zhengyang Liu, Haodi Wang, Chengjin Qin, Liang Gong, Chengliang Liu

“…In response to the insufficient recognition performance and poor generalization capacity of existing detection algorithms under unstructured orchard scenarios, we constructed a customized apple image dataset captured under varying illumination conditions and introduced an improved detection architecture, YOLO11-ARAF, derived from YOLO11. …”
Get full text

CoNfasTT: A Configurable, Scalable, and Fast Dual Mode Logic-Based NTT Design by Eldar Cohen, Leonid Yavits, Benjamin M. Zaidel, Alexander Fish, Itamar Levi

“…Our implementation offers several potential optimizations, including a unique, fully-combinational, and low-cost modular reduction technique within the K-RED algorithm. …”
Get full text

Large-scale S-box design and analysis of SPS structure by Lan ZHANG, Liangsheng HE, Bin YU

“…A class of optimal linear transformation P over a finite field<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML"> <mrow> <msup> <mrow> <mrow><mo>(</mo> <mrow> <msubsup> <mi>F</mi> <mn>2</mn> <mi>m</mi> </msubsup> </mrow> <mo>)</mo></mrow></mrow> <mn>4</mn> </msup> </mrow></math></inline-formula> was constructed based on cyclic shift and XOR operation.Using the idea of inverse proof of input-output relation of linear transformation for reference, a proof method was put forward that transformed the objective problem of optimal linear transformation into several theorems of progressive relation, which not only solved the proof of that kind of optimal linear transformation, but also was suitable for the proof of any linear transformation.By means of small-scale S-box and optimal cyclic shift-XOR linear transformation P, a large-scale S-box model with 2-round SPS structure was established, and a series of lightweight large-scale S-boxes with good cryptographic properties were designed.Only three kind of basic operations such as look-up table, cyclic shift and XOR were used in the proposed design scheme, which improved the linearity and difference uniformity of large-scale S-boxes.Theoretical proof and case analysis show that, compared with the existing large-scale S-box construction methods, the proposed large-scale S-box design scheme has lower computational cost and better cryptographic properties such as difference and linearity, which is suitable for the design of nonlinear permutation coding of lightweight cryptographic algorithms.…”
Get full text

An End-to-End Solution for Large-Scale Multi-UAV Mission Path Planning by Jiazhan Gao, Liruizhi Jia, Minchi Kuang, Heng Shi, Jihong Zhu

“…Additionally, we integrate a Multi-Start Greedy Rollout Baseline to evaluate diverse trajectories via parallelized greedy searches, thereby reducing policy gradient variance and improving training stability. Experiments demonstrated significant improvements in scalability, particularly in 100-node scenarios, where our method drastically reduced inference time compared to conventional methods, while maintaining a competitive path cost efficiency. …”
Get full text

Future of Alzheimer's detection: Advancing diagnostic accuracy through the integration of qEEG and artificial intelligence by Sahar Rezaei, Farzan Asadirad, Alireza Motamedi, Mohammadsadegh Kamran, Farzaneh Parsa, Haniyeh Samimi, Parna Ghannadikhosh, Mahdi Zahmatyar, Seyed Ali Hosseinzadeh, Hossein Arabi

“…This review highlights the significant potential of AI-enhanced qEEG as a non-invasive, cost-effective tool for the diagnosis of AD in its prodromal and dementia stages, while also identifying areas requiring further research to optimize its clinical application. …”
Get full text

Enhanced CLIP-GPT Framework for Cross-Lingual Remote Sensing Image Captioning by Rui Song, Beigeng Zhao, Lizhi Yu

“…Remote Sensing Image Captioning (RSIC) aims to generate precise and informative descriptive text for remote sensing images using computational algorithms. Traditional &#x201C;encoder-decoder&#x201D; approaches face limitations due to their high training costs and heavy reliance on large-scale annotated datasets, hindering their practical applications. …”
Get full text

Conformal Segmentation in Industrial Surface Defect Detection with Statistical Guarantees by Cheng Shen, Yuewei Liu

“…Traditional defect detection methods predominantly rely on manual inspection, which suffers from low efficiency and high costs. Some machine learning algorithms and artificial intelligence models for defect detection, such as Convolutional Neural Networks (CNNs), present outstanding performance, but they are often data-dependent and cannot provide guarantees for new test samples. …”
Get full text

Using Wireless Sensor Networks to Achieve Intelligent Monitoring for High-Temperature Gas-Cooled Reactor by Jianghai Li, Jia Meng, Xiaojing Kang, Zhenhai Long, Xiaojin Huang

“…High-temperature gas-cooled reactors (HTGR) can incorporate wireless sensor network (WSN) technology to improve safety and economic competitiveness. WSN has great potential in monitoring the equipment and processes within nuclear power plants (NPPs). …”
Get full text

Automating the Design of Scalable and Efficient IoT Architectures Using Generative Adversarial Networks and Model-Based Engineering for Industry 4.0 by William Villegas-Ch, Jaime Govea, Diego Buenano-Fernandez, Aracely Mera-Navarrete

“…Traditional approaches, such as heuristic and genetic algorithms, have proven insufficient in automating and optimizing large-scale IoT configurations, resulting in a high design and validation time cost. …”
Get full text

Machine Learning Approach to Model Soil Resistivity Using Field Instrumentation Data by Md Jobair Bin Alam, Ashish Gunda, Asif Ahmed

“…The ability to infer these variables through a singular measurable soil property, soil resistivity, can potentially improve sub-surface characterization. This research leverages various machine learning algorithms to develop predictive models trained on a comprehensive dataset of sensor-based soil moisture, matric suction, and soil temperature obtained from prototype ET covers, with known resistivity values. …”
Get full text

Adaptive multi-agent reinforcement learning for dynamic pricing and distributed energy management in virtual power plant networks by Jian-Dong Yao, Wen-Bin Hao, Zhi-Gao Meng, Bo Xie, Jian-Hua Chen, Jia-Qi Wei

“…Extensive simulations across diverse scenarios demonstrate that our approach consistently outperforms baseline methods, including Stackelberg game models and model predictive control, achieving an 18.73% reduction in costs and a 22.46% increase in VPP profits. The MARL framework shows particular strength in scenarios with high renewable energy penetration, where it improves system performance by 11.95% compared with traditional methods. …”
Get full text

Challenges of the Biopharmaceutical Industry in the Application of Prescriptive Maintenance in the Industry 4.0 Context: A Comprehensive Literature Review by Johnderson Nogueira de Carvalho, Felipe Rodrigues da Silva, Erick Giovani Sperandio Nascimento

“…The results obtained revealed that prescriptive maintenance offers opportunities for improvement in the production process, such as cost reduction and greater proximity to all actors in the areas of production, maintenance, quality, and management. …”
Get full text

From Neural Networks to Emotional Networks: A Systematic Review of EEG-Based Emotion Recognition in Cognitive Neuroscience and Real-World Applications by Evgenia Gkintoni, Anthimos Aroutzidis, Hera Antonopoulou, Constantinos Halkiopoulos

“…Despite these advances, challenges remain more significant in real-time EEG processing, where a trade-off between accuracy and computational efficiency limits practical implementation. High computational cost is prohibitive to the use of deep learning models in real-world applications, therefore indicating a need for the development and application of optimization techniques. …”
Get full text

Bridging the Gap: A Review of Machine Learning in Water Quality Control by Herlina Abdul Rahim, Nur Athirah Syafiqah Noramli, Indrabayu

“…ML-driven solutions, including LSTM networks and random forest models, enable real-time anomaly detection (e.g., 85% accurate algal bloom prediction 7 days in advance) and operational optimization (15% cost reduction in wastewater treatment). …”
Get full text

Integrating Learning-Driven Model Behavior and Data Representation for Enhanced Remaining Useful Life Prediction in Rotating Machinery by Tarek Berghout, Eric Bechhoefer, Faycal Djeffal, Wei Hong Lim

“…This allows for more precise maintenance scheduling from imperfect predictions, reducing downtime and operational costs while improving system reliability under varying conditions.…”
Get full text

PP-QADMM: A Dual-Driven Perturbation and Quantized ADMM for Privacy Preserving and Communication-Efficient Federated Learning by Anis Elgabli

“…We provide a rigorous theoretical proof of convergence, showing that PP-QADMM converges to the optimal solution for convex problems while achieving a convergence rate comparable to standard ADMM, but with significantly lower communication and energy costs, and robust privacy protection. …”
Get full text