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

GGLA-NeXtE2NET: A Dual-Branch Ensemble Network With Gated Global-Local Attention for Enhanced Brain Tumor Recognition by Adnan Saeed, Khurram Shehzad, Shahzad Sarwar Bhatti, Saim Ahmed, Ahmad Taher Azar

Get full text

Analysis of Effects of Drill Collars on the Voltage of Electromagnetic Wave Logging While Drilling by GUO Tongzheng

“…By using a cylindrical layered medium model, the characteristics of coil voltage changing with borehole mud and formation parameters can be simulated, and the effects of drill collars on voltage can be analyzed. …”
Get full text

XTNSR: Xception-based transformer network for single image super resolution by Jagrati Talreja, Supavadee Aramvith, Takao Onoye

“…The model processes grid-like image patches effectively and reduces computational complexity by integrating a Patch Embedding layer. …”
Get full text

Information exchange model of multi control nodes in trustworthy and controllable network by WANG Peng, LUO Jun-zhou, LI Wei, ZHENG Xiao, QU Yan-sheng

“…A new model based on two-layer Chord was proposed to realize information exchange between multi control nodes in trustworthy and controllable network.It constructs the two-layer Chord by constructing Chord between control nodes in AS and between ASes respectively.It uses this two-layer Chord to generate a two-layer aggregation tree automatically in exchanging process,which is used to realize basic information communication services.It provides AS administrative isolation for security and availability by guaranteeing path convergence for the same information in AS,and improves efficiency of communication.Meanwhile,it guarantees load balance between control nodes.Experiments verify that IEM has good performance.…”
Get full text

Frequency-Modulated Antipodal Chaos Shift Keying Chaotic Communication on Field Program Gate Array: Prototype Design and Performance Insights by Filips Capligns, Ruslans Babajans, Darja Cirjulina, Deniss Kolosovs, Anna Litvinenko

“…The employment of FM over a chaotic modulation layer provides a passband operation (currently at an intermediate frequency of 10.7 MHz) while adding the benefits of carrier frequency offset robustness and constant signal envelope. …”
Get full text

Optimization and Analysis of Electrical Heating Ice-Melting Asphalt Pavement Models by Jiguo Liu, Kai Xu, Zhi Chen, Wenbo Peng, Longhai Wei

“…Existing studies primarily focus on optimizing cable-heated asphalt pavement through indoor model tests or finite element results. To obtain more accurate and reasonable temperature rise processes and heat transfer results, we propose a new evaluation metric for heat transfer capability and optimization in electric heating asphalt pavement. …”
Get full text

Reliable unmanned aerial vehicle-based thermal infrared target detection method for monitoring Procapra przewalskii in Qinghai by Guoqing Zhang, Wei Luo, Yongxiang Zhao, Quanqin Shao, Lin Li, Keyu Mei, Guohong Li

“…This technique employs YOLOv8s as the base model and proposes a multi-frame processing (MFP) method (YOLO-MFP). …”
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

Evidence classification method of chat text based on DSR and BGRU model by Yu ZHANG, Binglong LI, Xuejuan LI, Heyu ZHANG

“…It is always unlikely to efficiently identify and extract chat text evidence related to criminal events, due to the complex semantics such as “slang” in the chat content and the huge amount of chat text data generated by social software such as instant messaging.Based on this motivation, a chat text evidence classification model (DSR-BGRU) based on the DSR (dynamic semantic representation) model and the BGRU (bidirectional gated recurrent unit) model was proposed.The chat text data was pre-processed to preserve the characteristics of the criminal field.Then a multi-layer chat text feature extraction and classification model using the Keras framework was proposed.With the text matrix composed of vector representation of words in the DSR model as the input vector, the input layer of the DSR model featured the chat text from the semantic level.Then the hidden layer of the BGRU model extracted the context characteristics of the text composed of the word vectors.The softmax classification layer recognized and extracted the chat text evidence.The experimental results show that the proposed DSR-BGRU can more accurately identify and extract chat records compared with other models and methods for text classification, and it can also effectively extract the criminal text information from the chat information with the accuracy rate 92.06% and the F1 score 91.00%.…”
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

Construction of a model of subsoil moisture movement in cultivated slope lands by Andrey A. Mikhaylin

“…Insufficient study of the dynamics of moisture movement both in the soil loosened by the tillage tool and in the zone of uncultivated subsoil wall in the conditions of moisture deficient south of Russia necessitated for development of a mathematical model of subsoil moisture transfer. A distinctive feature of this model is the study of moisture transfer in the zone of the upper soil layer of 0.60 m by the developed universal tillage tool for cultivating of sloping and plain lands. …”
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

Leveraging Multi-Level Semantic Understanding in a Unified NER Model by Yuqian Zhao, Jiuchun Ren

“…To this end, we propose the MLSU (Multi-level Semantic Understanding) model for unified NER tasks. The overall architecture leverages an Encoder-Decoder structure that integrates sequence and grid-level semantic blocks, enhancing the model&#x2019;s ability to process complex text structures effectively. …”
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

Telecom Fraud Recognition Based on Large Language Model Neuron Selection by Lanlan Jiang, Cheng Zhang, Xingguo Qin, Ya Zhou, Guanglun Huang, Hui Li, Jun Li

“…In the realm of natural language processing (NLP), text classification constitutes a task of paramount significance for large language models (LLMs). …”
Get full text

Modelling and Dynamic Response of Steel Reticulated Shell under Blast Loading by Ximei Zhai, Yonghui Wang

“…The elaborate finite element model of the Kiewitt-8 single-layer reticulated shell with span of 40 m subjected to central blast loading was established and all the process from the detonation of the explosive charge to the demolition, including the propagation of the blast wave and its interaction with structure was reproduced. …”
Get full text

Developing an experimental model of early knee osteoarthritis after medial meniscus posterior root release: an in vivo study by Lika Dzidzishvili, Irene Isabel López‐Torres, Carlos Carnero Guerrero, Emilio Calvo

“…Abstract Purpose To develop a predictable and reproducible model of knee osteoarthritis after medial meniscus posterior root release. …”
Get full text

Potential areas for groundwater exploration in the Puyango Catamayo Hydrographic Demarcation, Ecuador, using a analytic hierarchy process based on GIS and remote sensing by V.X. Macas-Espinosa, K.F. López-Escobar

“…From the methodological point of view, Multi-Criteria Decision Analysis is applied, using an Analytic Hierarchy Process, which takes as thematic layers the  rock permeability, the rainfall, the drainage density,  the terrain slope, and the normalized difference vegetation index. …”
Get full text

Blockchain-Enabled Deep Recurrent Neural Network Model for Clickbait Detection by Abdul Razaque, Bandar Alotaibi, Munif Alotaibi, Fathi Amsaad, Ansagan Manasov, Salim Hariri, Banu B. Yergaliyeva, Aziz Alotaibi

“…The multi-layered clickbait detection is main phase of the proposed BDRNN that consists of three models: content-to-vector model (layer-1), deep neural network model(layer-2), and Blockchain-enabled malicious content detection model (layer-3). …”
Get full text