Deep Learning in Finance: A Survey of Applications and Techniques by Ebikella Mienye, Nobert Jere, George Obaido, Ibomoiye Domor Mienye, Kehinde Aruleba

“…Machine learning (ML) has transformed the financial industry by enabling advanced applications such as credit scoring, fraud detection, and market forecasting. At the core of this transformation is deep learning (DL), a subset of ML that is robust in processing and analyzing complex and large datasets. …”
Get full text

Hybrid FFT-ARMA-Burg Modeling and LSTM-Enhanced BBO Optimization for Fault Diagnosis in Induction Motors by Khadidja Boudraa, Mohammed Assam Ouali, Mohamed Ladjal

“… Induction motors (IM) are crucial in industrial systems, and fault diagnosis reliably and effectively is of importance for maintaining efficiency. The detection of a broken rotor bar(RBB) is one of the most challenging tasks in condition monitoring due to the complexity of fault features in motor current signals. …”
Get full text

An Innovative Framework for Quality Assurance in Logistics Packaging by Henriett Matyi, Péter Tamás

“…<i>Background</i>: As a result of the effort to satisfy unique customer needs, the complexity of production and service processes is constantly increasing. …”
Get full text

Classification of power quality disturbances in microgrids using a multi-level global convolutional neural network and SDTransformer approach. by Junzhuo Jiang, Hao Wu, Changhua Zhong, Hong Song

“…The model effectively retains the signal's original one-dimensional temporal attributes while also delving into more complex features. This approach exhibits strong resistance to noise and enhanced generalization skills, markedly improving the detection accuracy of power quality issues within microgrids.…”
Get full text

Generation of Genuine Multipartite Entangled States via Indistinguishability of Identical Particles by Kobra Mahdavipour, Farzam Nosrati, Stefania Sciara, Roberto Morandotti, Rosario Lo Franco

“…We also show that this graph-theoretical approach allows for the optimization of the generation efficiency of specific multipartite entangled states by exploring a variety of generation schemes. …”
Get full text

Bridge Crack Segmentation Algorithm Based on Improved U-Net by Yanhao Fang, Jie LYu, Yonghua Xia, Yingke Wang

“…Initially, the model integrates an ECA (Efficient Channel Attention) module with the original U-Net to dynamically calibrate channel features. …”
Get full text

SLGMA-UNet: Comprehensive Feature Aggregation With Context-Sensitive Attention for Medical Image Segmentation by Xinghuo Ye, Na Wang

“…Experiments conducted on five medical datasets, including ISIC2017, ISIC2018, CVC-ClinicDB, Kvasir-SEG, and GLAS, demonstrate that SLGMA-UNet outperforms existing models, achieving accuracy improvements of 4.2-7.8% (mean Intersection over Union, mIoU) and 3.6-6.4% (Dice Similarity Coefficient, DSC), along with enhanced edge detection and reduced errors in complex cases. Ablation studies confirm the positive and synergistic effects of the additional components. …”
Get full text

In-operando control of sum-frequency generation in tip-enhanced nanocavities by Philippe Roelli, Isabel Pascual Robledo, Iris Niehues, Javier Aizpurua, Rainer Hillenbrand

“…The tip acts as an efficient broadband antenna, focusing incident CW infrared illumination onto the nanocavity. …”
Get full text

Building rooftop extraction from high resolution aerial images using multiscale global perceptron with spatial context refinement by Qinglie Yuan

“…Overall, quantitative analysis and visual experiments confirmed that the proposed model is more efficient and superior to other state-of-the-art methods, with a 95.18% F1 score on the WHU dataset and a 93.29% F1 score on the Massub dataset.…”
Get full text

Investigation on potential bias factors in histopathology datasets by Farnaz Kheiri, Shahryar Rahnamayan, Masoud Makrehchi, Azam Asilian Bidgoli

“…The analysis was conducted on two cutting-edge DNN models: KimiaNet, a state-of-the-art DNN trained on TCGA images, and the self-trained EfficientNet. In this research study, the balanced accuracy metric is used to evaluate the performance of a model trained to classify data centers, which was originally designed to learn cancerous patterns, with the aim of investigating the potential factors contributing to the higher balanced accuracy in data center detection.…”
Get full text

Concave Magnetic-Responsive Hydrogel Discs for Enhanced Bioassays by Amin Ghaffarzadeh Bakhshayesh, Huiyan Li

“…The increased surface area and ease of fabrication make our CMDs efficient and adaptable for various biological and biomedical applications, particularly in point-of-care diagnostics where rapid and accurate biomarker detection is critical.…”
Get full text

Deep Space Insights: Machine Learning Revolutionizing Astrophysical Discoveries by Dutta Samya, Paul Prithwineel

“…It integrates Machine Learning as a highly impressive advancement for making scalable, efficient, and accurate tools for astronomical data which face increasing complexity and volume. …”
Get full text

Selective electrocatalytic nitrate reduction to dinitrogen: Mechanisms, catalysts, and challenges by Jiayu Chen, Anni Wu, Yongfeng Xie, Yumin Zhang, Hu Zheng, Wei Teng

“…While extensive research has focused on ammonia production, selective N2 production remains challenging due to complex pathways, limitations in detection, and the difficulty of controlling reaction on the electrocatalysts. …”
Get full text

Sustainable uric acid sensor based on a lab-fabricated electrode modified with rice straw-derived carbon materials by Pakin Noppawan, Jaroon Jakmunee, Andrew J. Hunt, Nontipa Supanchaiyamat, Suwiwat Sangon, Jamras Lerdsri, Thidarat Kruatian, Jantima Upan

“…The electrochemical oxidation of uric acid exhibits a distinct peak at 0.18 V in differential pulse voltammetry (DPV), indicative of efficient charge transfer kinetics. A linear range spanning 20 to 225 µM was obtained with a limit of detection (LOD) of 3.76 µM, signifying exceptional analytical sensitivity. …”
Get full text

A refined lion optimizer for deep learning by Jian Rong, Chenhao Ma, Qinghui Zhang, Yong Cao, Weili Kou

“…The YOLOV8, YOLOV11 on VOC2012 data and Object detection with Vision Transformers on Caltech 101 dataset are trained for Object detection. …”
Get full text

DK-SLAM: Monocular Visual SLAM with Deep Keypoint Learning, Tracking, and Loop Closing by Hao Qu, Lilian Zhang, Jun Mao, Junbo Tie, Xiaofeng He, Xiaoping Hu, Yifei Shi, Changhao Chen

“…To mitigate cumulative positioning errors, DK-SLAM incorporates a novel online learning module that utilizes binary features for loop closure detection. This module dynamically identifies loop nodes within a sequence, ensuring accurate and efficient localization. …”
Get full text

Multimodal lightweight neural network for Alzheimer's disease diagnosis integrating neuroimaging and cognitive scores by Bhoomi Gupta, Ganesh Kanna Jegannathan, Mohammad Shabbir Alam, Kottala Sri Yogi, Janjhyam Venkata Naga Ramesh, Vemula Jasmine Sowmya, Isa Bayhan

“…Evaluation on the ADNI dataset demonstrates that Light-Mo-DAD achieves 98.0% accuracy, 98.5% sensitivity, and 97.5% specificity, highlighting its robustness in early AD detection. These results suggest that the proposed architecture not only enhances diagnostic accuracy but also offers strong potential for real-time, mobile deployment in clinical settings, supporting neurologists in efficient and reliable Alzheimer's diagnosis.…”
Get full text

Research on Concrete Crack Damage Assessment Method Based on Pseudo-Label Semi-Supervised Learning by Ming Xie, Zhangdong Wang, Li’e Yin

“…Compared with the mainstream models, this method effectively alleviates the problem of data annotation dependence through a semi-supervised strategy while maintaining high accuracy. It provides an efficient structural health monitoring solution for engineering practice, which is of great value to promote the application of intelligent detection technology in infrastructure operation and maintenance.…”
Get full text

Determination of Tacrolimus in Plasma by Paper Spray In-situ Mass Spectrometry Based on Multistage Fragmentation by Fei PAN, Shuang YANG, Zi-yu QU, Di ZHANG, Chun-xia WANG, Hong-bin ZHEN, Zi-hong YE, Xin-hua DAI, Xiang FANG, Hai-di JIANG, Jie XIE, You JIANG

“…This method was applied to monitor tacrolimus levels in 20 plasma samples, with concentrations ranging from 5.62 to 36.75 μg/L and RSD between 1.75% and 14.41%, indicating that the method has good precision and can meet the needs of clinical blood drug concentration monitoring. The entire detection process only takes 1 min to obtain quantitative results, and in scenarios requiring rapid detection of blood drugs, this method is expected to become an efficient alternative, with the potential to be applied to the concentration monitoring of other immunosuppressants.…”
Get full text

Rapid acquisition and surface defects recognition based on panoramic image of small-section hydraulic tunnel by Haoyu Wang, Jichen Xie, Jinyang Fu, Cong Zhang, Dingping Chen, Zhiheng Zhu, Xuesen Zhang

“…Small-section hydraulic tunnels are characterized by small spaces and various section forms, under complex environments, which makes it difficult to carry out an inspection by the mobile acquisition equipment. …”
Get full text