Analysis of argument structure constructions in a deep recurrent language model by Pegah Ramezani, Pegah Ramezani, Achim Schilling, Achim Schilling, Patrick Krauss, Patrick Krauss

“…In future work, we plan to compare these model-derived representations with neuroimaging data from continuous speech perception, further bridging computational and biological perspectives on language processing.…”
Get full text

Exploring the process—structure–property relationship of nylon aramid 3D printed composites and parameter optimization using supervised machine learning techniques by Mohammed Raffic Noor Mohamed, Ganesh Babu Karuppiah, Dharani Kumar Selvan, Rajasekaran Saminathan, Shubham Sharma, Shashi Prakash Dwivedi, Sandeep Kumar, Mohamed Abbas, Dražan Kozak, Jasmina Lozanovic

“…The main goals of this research are to identify the significant input parameters using supervised machine learning methods and investigate the relationship between the process, structure, and properties of components created using fused deposition modeling utilizing nylon aramid composite filaments. …”
Get full text

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

“…Recently, high-performing models based on Transformers and multi-layer perceptrons (MLPs) have also been proposed. …”
Get full text

Service model of smart tourism cities integrated with low-altitude technology by Luo Tian Yang

“…The model comprises the Core Technology Layer, Service Application Layer, and Governance and Collaboration Layer, each of which incorporates specific influencing factors, such as R&D investments, operational efficiency, and policy support. …”
Get full text

Maize quality detection based on MConv-SwinT high-precision model. by Ning Zhang, Yuanqi Chen, Enxu Zhang, Ziyang Liu, Jie Yue

“…The fused features, combined with those processed by the convolutional module, are fed into an attention layer. …”
Get full text

Modeling circuit mechanisms of opposing cortical responses to visual flow perturbations. by J Galván Fraile, Franz Scherr, José J Ramasco, Anton Arkhipov, Wolfgang Maass, Claudio R Mirasso

“…In this study, our objective was to uncover the neural dynamics that govern V1 neurons' responses to visual flow perturbations using a biologically realistic computational model. By subjecting the model to sudden changes in visual input, we observed opposing cortical responses in excitatory layer 2/3 (L2/3) neurons, namely, depolarizing and hyperpolarizing responses. …”
Get full text

Effect of fracture energy estimation on the predictions of mode II behavior of bonded joints using cohesive zone models by Michele Perrella, Enrico Armentani, Giuseppe Lamanna, Valentino Paolo Berardi

“…Fracture behavior of adhesive joints is an important topic in structural design of new structural elements or in retrofitting of existing ones. The mechanical models available in literature capable of predicting the failure mode of these junctions are mainly formulated within the cohesive zone model (CZM). …”
Get full text

Assessments and investigation of process parameter impacts on surface roughness, microstructure, tensile strength, and porosity of 3D printed polyetherether ketone (PEEK) materials by Shimelis Tamene Gobena, Abraham Debebe Woldeyohannes

“…AM techniques, such as fused deposition modeling (FDM), offer a solution by constructing objects layer by layer, minimizing waste. …”
Get full text

Seismic phase recognition model with low SNR based on U-net by Jianxian Cai, Zhongjie Sun, Mengying Zhang, Fenfen Yan, Li Wang, Ling Li

“…In this model, Bi-GRU bidirectional gated recurrent unit and Attention attention mechanism are added between the U-net coding layer and the decoding layer. …”
Get full text

Enhanced Lightweight YOLO Model for Efficient Vehicle Detection in Satellite Imagery by Mohamad Haniff Junos, Anis Salwa Mohd Khairuddin, Elmi Abu Bakar, Ahmad Faizul Hawary

“…To solve these problems, this work proposes an enhanced lightweight object detection model based on the YOLOv4 Tiny model. The proposed model incorporates multiple modifications, including integrating a Mix-efficient layer aggregation network within its backbone network to optimize efficiency by reducing parameter generation. …”
Get full text

Warpage Prediction in Wire Arc Additive Manufacturing: A Comparative Study of Isotropic and Johnson–Cook Plasticity Models by Saeed Behseresht, Young Ho Park

“…However, due to the inherent layered nature of the process and significant heat accumulation, parts can experience severe warping, often leading to part rejection. …”
Get full text

Emotion-Aware RoBERTa enhanced with emotion-specific attention and TF-IDF gating for fine-grained emotion recognition by Fatimah Alqarni, Alaa Sagheer, Amira Alabbad, Hala Hamdoun

“…Although transformer-based models like RoBERTa have advanced contextual understanding in text, they still face limitations in identifying subtle emotional cues, handling class imbalances, and processing noisy or informal input. …”
Get full text

Seismic characterization of lava flow facies in the critical zone of the deccan traps using shear wave velocity models by Rashi Sharma, Rahul Dehiya, Sudipta Sarkar, Raymond Duraiswami

Get full text

Towards Optimizing Neural Network-Based Quantification for NMR Metabolomics by Hayden Johnson, Aaryani Tipirneni-Sajja

“…<b>Methods:</b> This work investigates practices for dataset and model development in the task of metabolite quantification directly from simulated NMR spectra for three neural network models: the multi-layered perceptron, the convolutional neural network, and the transformer. …”
Get full text

Effect of fracture energy estimation on the predictions of mode II behavior of bonded joints using cohesive zone models by Michele Perrella, Enrico Armentani, Giuseppe Lamanna, Valentino Paolo Berardi

“… Fracture behavior of adhesive joints is an important topic in structural design of new structural elements or in retrofitting of existing ones. The mechanical models available in literature capable of predicting the failure mode of these junctions are mainly formulated within the cohesive zone model (CZM). …”
Get full text

Bio-inspired motion detection models for improved UAV and bird differentiation: a novel deep learning framework by Najiba Said Hamed Al-Zadjali, Sundaravadivazhagan Balasubaramanian, Charles Savarimuthu, Emanuel O. Rances

“…The model consists of three core components: a Bio-Inspired Convolutional Neural Network (Bio-CNN) for spatial feature extraction, Gated Recurrent Units (GRUs) for capturing temporal motion dynamics, and a novel Bio-Response Layer that adjusts attention based on movement intensity, object proximity, and velocity consistency. …”
Get full text

Model of property relations in the Soviet Lithuania village (Case of Stungiai village) by Žilvinas Kačiuška

“…The cultural and economical lag of Lithuania is often said to be caused by a mental gap, which was constructed by a model of collectivism and planned economy. Herewith, slowly changing categories in cognition impact reflections on market economy model and its mode of functioning.   …”
Get full text

Performance Evaluation of YOLOv11 and YOLOv12 Deep Learning Architectures for Automated Detection and Classification of Immature Macauba (<i>Acrocomia aculeata</i>) Fruits by David Ribeiro, Dennis Tavares, Eduardo Tiradentes, Fabio Santos, Demostenes Rodriguez

“…Inference throughput averaged 3.9 ms per image for YOLOv11x and 6.7 ms for YOLOv12x, highlighting a trade-off between speed and architectural complexity. Fused model representations revealed optimized layer fusion and reduced computational overhead (GFLOPs), facilitating efficient deployment. …”
Get full text

Mitigating Cyber Risks in Smart Cyber-Physical Power Systems Through Deep Learning and Hybrid Security Models by M. A. S. P. Dayarathne, M. S. M. Jayathilaka, R. M. V. A. Bandara, V. Logeeshan, S. Kumarawadu, Chathura Wanigasekara

“…The study emphasizes the difficulties in identifying cyber risks in grids with significant renewable integration, such as frequency instability and diminished system inertia, and suggests energy storage alternatives and sophisticated forecasting models to mitigate these issues. By incorporating a novel pre-processing method that leverages feature derivatives, the proposed models achieve over 98% accuracy in detecting cyber threats, providing a robust framework for protecting smart power grids from evolving cyber risks.…”
Get full text

Balancing Efficiency and Efficacy: A Contextual Bandit-Driven Framework for Multi-Tier Cyber Threat Detection by Ibrahim Mutambik, Abdullah Almuqrin

“…This paper introduces a contextual bandit-based reinforcement learning approach, designed to reduce operational expenditures and enhance detection cost-efficiency by introducing an adaptive decision boundary within a layered detection scheme. The proposed framework continually measures the confidence of each participating detection model, applying a reward-driven mechanism to balance cost and accuracy. …”
Get full text