Mitigating data bias and ensuring reliable evaluation of AI models with shortcut hull learning by Wenhao Zhou, Faqiang Liu, Hao Zheng, Rong Zhao

“…Unexpectedly, our experimental results suggest that under this framework, convolutional models—typically considered weak in global capabilities—outperform transformer-based models, challenging prevailing beliefs. …”
Get full text

Novel approach for Arabic fake news classification using embedding from large language features with CNN-LSTM ensemble model and explainable AI by Omar Ibrahim Aboulola, Muhammad Umer

“…Deep learning models, Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), EfficientNetB4, Inception, Xception, ResNet, ConvLSTM and a novel voting ensemble framework combining CNN and LSTM are employed for text classification. …”
Get full text

Characterization and Automated Classification of Underwater Acoustic Environments in the Western Black Sea Using Machine Learning Techniques by Maria Emanuela Mihailov

“…Acoustic data are processed using advanced signal processing (broadband Sound Pressure Level (SPL), Power Spectral Density (PSD)) for feature extraction (Mel-spectrograms for deep learning; PSD statistical moments for classical/unsupervised ML). The framework evaluates Convolutional Neural Networks (CNNs), Random Forest, and Support Vector Machines (SVMs) for noise event classification, alongside Gaussian Mixture Models (GMMs) for anomaly detection. …”
Get full text

Hierarchical Knowledge Transfer: Cross-Layer Distillation for Industrial Anomaly Detection by Junning Xu, Sanxin Jiang

“…To address these issues, this work proposes a Hierarchical Knowledge Transfer (HKT) framework for detecting industrial surface anomalies. …”
Get full text

An Efficient Acoustic Metamaterial Design Approach Integrating Attention Mechanisms and Autoencoder Networks by Yangyang Chu, Yiping Liu, Bingke Wang, Zhifeng Zhang

“…In the feedforward network, the improved forward prediction model shows superior performance compared to the traditional Convolutional Neural Network model and the model based only on the Convolutional Block Attention Module attention mechanism, with a prediction accuracy of 99.65%. …”
Get full text

A Configurable Accelerator for CNN-Based Remote Sensing Object Detection on FPGAs by Yingzhao Shao, Jincheng Shang, Yunsong Li, Yueli Ding, Mingming Zhang, Ke Ren, Yang Liu

“…An RTL-level CNNs field programable gate arrays accelerator with microinstruction sequence scheduling data flow is then designed. The hardware framework is built upon the Xilinx VC709. The results show that, under INT16 or INT8 precision, the system achieves remarkable throughput in most convolutional layers of the network, with an average performance of 153.14 giga operations per second (GOPS) or 301.52 GOPS, which is close to the system’s peak performance, taking full advantage of the platform’s parallel computing capabilities.…”
Get full text

PGBTR: a powerful and general method for inferring bacterial transcriptional regulatory networks by Wei-Cheng Gu, Bin-Guang Ma

“…Here we propose a powerful, general, and stable computational framework called PGBTR (Powerful and General Bacterial Transcriptional Regulatory networks inference method), which employs Convolutional Neural Networks (CNN) to predict bacterial transcriptional regulatory relationships from gene expression data and genomic information. …”
Get full text

Enhanced real-time Parkinson’s disease monitoring and severity prediction using a multi-faceted deep learning approach by Marreddy Naga Sabari, Deepak Ch

“…This research proposes a novel deep learning framework using a convolutional long short-term memory (LSTM) network to detect tremor anomalies in PD patients. …”
Get full text

Usage of Neural-Based Predictive Modeling and IIoT in Wind Energy Applications by Adrian-Nicolae Buturache, Stelian Stancu

“…New, cost-effective technologies have been developed, led by customer awareness of green technologies and a legal framework proposed at the European Union level. The stochastic nature of wind speed is transferred to wind turbine output, making wind energy difficult to predict. …”
Get full text

Finger drawing on smartphone screens enables early Parkinson's disease detection through hybrid 1D-CNN and BiGRU deep learning architecture. by Zhaohui Zhu, E Wu, Pengfei Leng, Jiajun Sun, Mingming Ma, Zhigeng Pan

“…Our hybrid model combined multi-scale convolutional feature extraction (using parallel 1D-Convolutional branches) with bidirectional temporal pattern recognition (via gated recurrent unit [GRU] networks) to analyze movement abnormalities and detect the disease.…”
Get full text

Lung-AttNet: An Attention Mechanism-Based CNN Architecture for Lung Cancer Detection With Federated Learning by Chamak Saha, Somak Saha, Md. Asadur Rahman, Md. Mahmudul Haque Milu, Hiroki Higa, Mohd Abdur Rashid, Nasim Ahmed

“…To address this, we propose Lung-AttNet, a novel lightweight convolutional neural network (CNN) model enhanced with an attention mechanism. …”
Get full text

Fractal-Based Architectures with Skip Connections and Attention Mechanism for Improved Segmentation of MS Lesions in Cervical Spinal Cord by Rukiye Polattimur, Mehmet Süleyman Yıldırım, Emre Dandıl

“…In our previous study, we introduced the FractalSpiNet architecture by incorporating fractal convolutional block structures into the U-Net framework to develop a deeper network for segmenting MS lesions in the CPC. …”
Get full text

Advanced investing with deep learning for risk-aligned portfolio optimization. by Minh Duc Nguyen

“…We combine two prediction models, Long Short-Term Memory (LSTM) and One-Dimensional Convolutional Neural Network (1D-CNN), with three portfolio frameworks: Mean-Variance with Forecasting (MVF), Risk Parity Portfolio (RPP), and Maximum Drawdown Portfolio (MDP). …”
Get full text

Novel approach for predicting fake news stance detection using large word embedding blending and customized CNN model. by Abdulaziz Altamimi

“…Thus, instigated by the quintessential necessity, there is a dire need to construct a framework for the automatic detection and identification of fake news at its inception. …”
Get full text

Non-stationary signal combined analysis based fault diagnosis method by Zhe CHEN, Yuqi HU, Shiqing TIAN, Huimin LU, Lizhong XU

“…Considering the complementarity between the deep learning,spectrum and time frequency analysis methods,a multi-stream framework was designed by combining the convolutional network,Fourier transform and wavelet package decomposition methods,with the aim to analyze the non-stationary signal.Accordingly,a none-stationary signal combined analysis based fault diagnosis method was proposed to extract features in difference aspects.The fault diagnosis experiments demonstrate that the combined analysis method can efficiently and stably depict the fault and significantly improve the performance of fault diagnosis.…”
Get full text

Real-Time Player Engagement Measurement Using Nonintrusive Game Telemetry by Ammar Rashed, Shervin Shirmohammadi, Mohamed Hefeeda

“…In this article, we present a novel framework for nonintrusive, real-time, and indirect measurement of engagement in multiplayer online games based on flow theory. …”
Get full text

Spatial–Temporal Transformer for Optimizing Human Health Through Skeleton-Based Body Sports Action Recognition by Faze Liang, Lejia Ou, Zujun Lei, Xiaohong Tu, Kai Xin

“…These components collectively enable the framework to handle complex co-movement patterns, occlusions, and variability in execution styles. …”
Get full text

Multiple sclerosis diagnosis with brain MRI retrieval: A deep learning approach by R.M. Haggag, Eman M. Ali, M.E. Khalifa, Mohamed Taha

“…This study proposes a novel Content-Based Medical Image Retrieval (CBMIR) framework using Convolutional Neural Networks (CNN) and Transfer Learning (TL) for MS diagnosis using MRI data. …”
Get full text

Attentive Self-supervised Contrastive Learning (ASCL) for plant disease classification by Getinet Yilma, Mesfin Dagne, Mohammed Kemal Ahmed, Ravindra Babu Bellam

“…The ASCL framework enhances interpretability by incorporating attention mechanisms, such as squeeze-excitation and convolutional block attention module, which highlight key regions in plant images, aiding in transparent decision-making. …”
Get full text

Remote sensing semantic segmentation based on multimodal feature alignment and fusion by B. Chang, T. Balz

“…The overarching algorithmic framework is analogous to that of the Unet model. First, the data in different modalities is aggregated and the image size is reduced through the use of multi-level downsampling modules based on the Haar wavelet transform. …”
Get full text