Image 1 of 1
, the journal maintains a 2025/2026 CiteScore of 11.7 (Q1) and a roughly 50% acceptance rate, with a substantial portion of submissions coming from Chinese researchers . For detailed submission metrics, visit LetPub.
Neural Computing and Applications is a solid Q2 journal for neural network and application-oriented AI research. It is not as selective as Pattern Recognition or Neurocomputing, but it is easier than IEEE TNNLS or Neural Networks. Suitable for PhD graduates and early-career researchers needing SCI publications with reasonable speed. neural computing and applications letpub
: Peer review typically takes around 3.5 months for the first round. , the journal maintains a 2025/2026 CiteScore of 11
Just had my paper accepted in NCAA! The journal is a top-tier Q1 Springer journal . While the standard review time can be lengthy—around 9 months on average—I found the reviewers' feedback incredibly detailed and fair. It is not as selective as Pattern Recognition
Real-world applications in forecasting, diagnostics, and intelligent control.
"Language presenting your work in well-written English gives it its best chance," she read on the LetPub profile. Knowing that reviewers at NCAA look for clarity as much as innovation, Elena decided to use professional editing services to ensure her neuro-fuzzy logic wasn't lost in translation.
In modern smart manufacturing environments, the accurate and real-time detection of surface defects remains a critical challenge due to the scarcity of defective samples and the high variability of defect scales. Traditional Convolutional Neural Networks (CNNs) often struggle to extract meaningful features from small or subtle defects in complex industrial backgrounds. This paper proposes a novel hybrid deep learning framework, named the , to address these limitations. The proposed architecture integrates a pre-trained ResNet-50 backbone with a custom-designed Multi-Scale Feature Fusion (MSFF) module and a Convolutional Block Attention Module (CBAM). The MSFF module captures hierarchical contextual information at different resolutions, while the CBAM highlights salient defect regions while suppressing background noise. We evaluated the proposed method on three publicly available benchmark datasets: NEU-DET (steel surfaces), PCB-DAT (printed circuit boards), and MT-DEF (magnetic tile defects). Experimental results demonstrate that AGMS-Net achieves a mean Average Precision (mAP) of 89.4% on the NEU-DET dataset, outperforming state-of-the-art methods such as YOLOv5 and Faster R-CNN by a margin of 3.2% and 4.1%, respectively. Furthermore, the model maintains a competitive inference speed, making it suitable for real-time industrial deployment.