Comparison of CNN-Based Architectures for Detection of Different Object Classes by Nataliya Bilous, Vladyslav Malko, Marcus Frohme, Alina Nechyporenko

“…The main metrics for comparison were mAP, Precision, Recall, F1-Score, and the ability of the neural network to work in real-time. (3) Results: The most important metrics for evaluating the efficiency and performance of models for a given task are accuracy (mAP), F1-Score, and processing speed (FPS). These metrics allow us to evaluate both the accuracy of object recognition and the ability to use the models in real-world environments where high processing speed is important. (4) Conclusion: Although different neural networks perform better on certain types of metrics, YOLO outperforms them on all metrics, showing the best results of mAP-0.88, F1-0.88, and FPS-48, so the focus was on these models.…”
Get full text

A Physics-Coupled Deep Learning Framework for Hydrodynamic Diffusion Modeling in Watershed Systems: Integrating Spatiotemporal Networks and Environmental Constraints by L. Jia, N. Yen, Y. Pei

“…Accurate comprehension and computational modeling of fluid transport, environmental processes, and substance diffusion depend heavily on solving governing equations. …”
Get full text

TA-SSM net: tri-directional attention and structured state-space model for enhanced MRI-Based diagnosis of Alzheimer’s disease and mild cognitive impairment by Sichen Bao, Fengbo Zheng, Lifen Jiang, Qiuyuan Wang, Yong Lyu

“…Additionally, gradient checkpointing is applied within the SSM to enhance processing efficiency, allowing the model to handle whole-brain scans while preserving spatial correlations. …”
Get full text

Virtual reality as a learning tool: Evaluating the use and effectiveness of simulation laboratories in educational settings by Mila Dodevska, Eftim Zdravevski, Ivan Chorbev, Magdalena Kostoska, Frederico Branco, Paulo Jorge Coelho, Ivan Miguel Pires, Petre Lameski

Get full text

Formal Verification of Code Conversion: A Comprehensive Survey by Amira T. Mahmoud, Ahmad A. Mohammed, Mahitap Ayman, Walaa Medhat , Sahar Selim , Hala Zayed, Ahmed H. Yousef, Nahla Elaraby 

Get full text

The impact of geological structures on groundwater potential assessment in volcanic rocks in the Borena Sayint district, northwestern Ethiopian Plateau: a review by B. Mihret, A. Wuletaw

Get full text

Investigation of the Wear Behavior of AA6063/Zirconium Oxide Nanocomposites Using Hybrid Machine Learning Algorithms by R. Reena Roy, Leninisha Shanmugam, A. Vinothini, Nirmala Venkatachalam, G. Sumathy, Bhavadharini Murugeshan, P. Mercy Rajaselvi Beaulah, Gizachew Assefa Kerga

Get full text

A food safety targeted sampling decision-making method based on association rule mining and GNNs by Jiabin Yu, Xinyue Ma, Xin Zhang, Xiaoyu Cui, Shuaixiang Chen, Zhiyao Zhao

Get full text

Scrambling power of soft photons by Xuan-Lin Su, Alioscia Hamma, Antonino Marcianò

“…Abstract Observable scattering processes entail emission-absorption of soft photons. …”
Get full text

Mathematical analysis of spectral estimation algorithms resolution by V. A. Kakora, A. V. Grinkevich

“…The classical methods of evaluating the energy spectra of discretized deterministic and stochastic processes are generally based on the use of procedures that use the fast Fourier transformation (FFT). …”
Get full text

APPROACH TO THE RESEARCH OF THE MULTIVARIATERELATIONSHIP BY THE EXAMPLE OF RUSSIAN STOCK MARKET by Marina A. Skorik, Andrey G. Nefedov

“…All theoretical foundations are supported by praxis in computer class. The Mathcad based program «SEMESTR» provides the wide range of possibilities for performing laboratory works by course due to automation of the multivariate data processing. …”
Get full text

The Framework for Simulation of Bioinspired Security Mechanisms against Network Infrastructure Attacks by Andrey Shorov, Igor Kotenko

“…The protection mechanisms based on this approach consist of distributed prosedures of information collection and processing, which coordinate the activities of the main devices of a computer network, identify attacks, and determine nessesary countermeasures. …”
Get full text

Reducing the dynamic range of infrared images based on block-priority equalization and compression of histograms by S. I. Rudikov, V. Yu. Tsviatkou, A. P. Shkadarevich

“…Image processing methods are used.Results. To reduce the computational complexity of transforming the dynamic range of infrared images, a block-priority modification of the adaptive histogram equalization method is proposed. …”
Get full text

Fast Adapting Ensemble: A New Algorithm for Mining Data Streams with Concept Drift by Agustín Ortíz Díaz, José del Campo-Ávila, Gonzalo Ramos-Jiménez, Isvani Frías Blanco, Yailé Caballero Mota, Antonio Mustelier Hechavarría, Rafael Morales-Bueno

Get full text

Applying MLP-Mixer and gMLP to Human Activity Recognition by Takeru Miyoshi, Makoto Koshino, Hidetaka Nambo

“…Convolutional neural networks (CNNs), initially proposed for computer vision tasks, are examples of models applied to sensor data. …”
Get full text

Multi-Objective Optimization of Machine Learning-Based Nonlinear Equalizers for Digital Coherent Optical Interconnects by Lucas C. Dantas, Hildo Guillardi Junior, Plinio Dester, Rafael A. Penchel, Jose Augusto de Oliveira, Marcelo L. F. Abbade, Leandra I. Abreu, Jinlong Wei, Ivan Aldaya

“…The growing demand for high-capacity optical networks has driven the advancement of digital coherent optical communication systems, which rely on sophisticated signal processing to mitigate transmission impairments, including nonlinear fiber distortions. …”
Get full text

Emulator of PR‐DNS: Accelerating Dynamical Fields With Neural Operators in Particle‐Resolved Direct Numerical Simulation by Tao Zhang, Lingda Li, Vanessa López‐Marrero, Meifeng Lin, Yangang Liu, Fan Yang, Kwangmin Yu, Mohammad Atif

“…Abstract Particle‐resolved direct numerical simulations (PR‐DNS) play an increasing role in investigating aerosol‐cloud‐turbulence interactions at the most fundamental level of processes. However, the high computational cost associated with high resolution simulations poses considerable challenges for large domain or long duration simulation using PR‐DNS. …”
Get full text

Power Efficient Clustering for Wireless Multimedia Sensor Network by Seng-Kyoun Jo, Muhammad Ikram, Ilgu Jung, Won Ryu, Jinsul Kim

“…In WMSNs, wirelessly interconnected devices enable ubiquitously retrieving multimedia contents such as video and audio streams, and still images along with scalar data from surroundings for wide range of applications are constrained by processing, memory, and power resources. Image compression via low-complexity and resource efficient transforms has been addressed by several researchers to prolong network lifetime where energy conservation is achieved through sharing computational load among sensor nodes and by adjusting the transmission ranges of camera nodes. …”
Get full text

A reduced order pseudochannel model accounting for flow maldistribution in automotive catalysis by Pratheeba Chanda Nagarajan, Henrik Ström, Jonas Sjöblom

“…Catalytic converters, as part of EATS, involve complex physico-chemical processes. To accurately predict their behavior in realistic geometries, transient 3D models are necessary. …”
Get full text

A Review on Recent Contribution of Meshfree Methods to Structure and Fracture Mechanics Applications by S. D. Daxini, J. M. Prajapati

“…Meshfree methods are viewed as next generation computational techniques. With evident limitations of conventional grid based methods, like FEM, in dealing with problems of fracture mechanics, large deformation, and simulation of manufacturing processes, meshfree methods have gained much attention by researchers. …”
Get full text