EfficientNet-b0-Based 3D Quantification Algorithm for Rectangular Defects in Pipelines by Di Wu, Yong Hong, Jie Wang, Shaojun Wu, Zhihao Zhang, Yizhang Liu

“…The network uses the EfficientNet structure for feature extraction, while the training and validation process utilizes the PyTorch Lightning framework. …”
Get full text

A study on early diagnosis for fracture non-union prediction using deep learning and bone morphometric parameters by Hui Yu, Qiyue Mu, Zhi Wang, Yu Guo, Jing Zhao, Guangpu Wang, Qingsong Wang, Xianghong Meng, Xiaoman Dong, Shuo Wang, Jinglai Sun

Get full text

A Drug-Target Interaction Prediction Method Based on Attention Perception and Modality Fusion by PENG Yang, ZHU Xiaofei, HU Dongdong

“…The existing prediction methods based on graph neural networks have achieved good results, but there are still two challenges: first, how to extract the deep features and rich semantic information in drugs and targets more efficiently; and second, how to explicitly model and learn the interactions between drugs and targets for better prediction and interpretation. …”
Get full text

XAI-XGBoost: an innovative explainable intrusion detection approach for securing internet of medical things systems by Yousif Hosain, Muhammet Çakmak

“…Explainable AI techniques, namely SHAP and LIME, are employed to provide global and local insights into model predictions, enhancing interpretability and trustworthiness. The system was evaluated using the WUSTL-EHMS-2020 dataset, which contains network flow and biometric data, achieving outstanding performance: 99.22% accuracy, 98.35% precision, 99.91% recall, 99.12% F1-score, and 100% ROC-AUC. …”
Get full text

Federated Learning Enhanced MLP–LSTM Modeling in an Integrated Deep Learning Pipeline for Stock Market Prediction by Jayaraman Kumarappan, Elakkiya Rajasekar, Subramaniyaswamy Vairavasundaram, Ketan Kotecha, Ambarish Kulkarni

“…In the performance evaluation, quantitative measures like Root-Mean-Square Error (RMSE), and accuracy are seven used. …”
Get full text

Understanding the ancient classic and famous prescriptions via the property of Chinese materia medica by Dan Qin, Dan Qin, He Zhang, Bin Du, Hui Wang, Ligang Liu, Yun Wang

“…The property of Chinese materia medica (PCMM), a multidimensional representation of medicinal properties, offers a novel perspective for systematically analyzing TCM formulas.ObjectiveIn this study, we aim to investigate the implicit medication patterns of ACFPs from the PCMM perspective, establish a feature extraction model based on the property combination of Chinese materia medica (PCCMM), and evaluate its effectiveness in representing and reconstructing ACFPs.MethodsBased on the Chinese Pharmacopoeia (ChP), we constructed a CMM–PCCMM network as the forward feature extraction process. …”
Get full text

Development and Comparison of Machine Learning and Deep Learning Models for Speech Audiometry Prediction by Jae sung Shin, Jun Ma, Mao Makara, Nak-Jun Sung, Seong Jun Choi, Sung yeup Kim, Min Hong

Get full text

Leveraging Deep Learning and Multimodal Large Language Models for Near-Miss Detection Using Crowdsourced Videos by Shadi Jaradat, Mohammed Elhenawy, Huthaifa I. Ashqar, Alexander Paz, Richi Nayak

Get full text

Individualized lesion-symptom mapping using explainable artificial intelligence for the cognitive impact of white matter hyperintensities by Ryanne Offenberg, Alberto De Luca, Geert Jan Biessels, Frederik Barkhof, Wiesje M. van der Flier, Argonde C. van Harten, Ewoud van der Lelij, Josien Pluim, Hugo Kuijf

“…A convolutional neural network (CNN) predicts cognitive scores and is combined with explainable artificial intelligence (XAI) to map the relation between cognition and vascular lesions.This method was evaluated primarily using real white matter hyperintensity maps of 821 memory clinic patients and simulated cognitive data, with weighted lesions and noise levels. …”
Get full text

EfficientNet-B0 outperforms other CNNs in image-based five-class embryo grading: a comparative analysis by Vincent Jaehyun Shim, Hosup Shim, Sangho Roh

“…Artificial intelligence-powered grading systems offer a more objective and consistent approach by reducing human biases and enhancing accuracy and reliability. Methods: We evaluated the performance of five convolutional neural network architectures—EfficientNet-B0, InceptionV3, ResNet18, ResNet50, and VGG16— in grading blastocysts into five quality classes using only embryo images, without incorporating clinical or patient data. …”
Get full text

Effect of Noises and GSM Codings on Pre-Trained Speaker Embedding Models in Forensic Voice Comparison by Mohammed Hamzah Alsalihi, David Sztaho

“…Samples are compared pairwise with and without enrollment for suspect speakers (known) because, often, forensic voice comparisons don’t have multiple samples of offenders. Speaker embedding features are extracted using four pre-trained techniques: X-vector, Emphasized channel attention, propagation and aggregation in time delay neural network (ECAPA-TDNN), large-scale self-supervised (Wavlm) and framework for self-supervised learning (Wav2vec) pre-trained. …”
Get full text

Embedded Descriptor Generation in Faster R-CNN for Multi-Object Tracking by Younis Younis, Khalil Alsaif

“…In this study, a new method is proposed for multi-object tracking based on descriptors generated by a neural network that is embedded in the Faster R-CNN. This embedding allows the proposed method to directly output a descriptor for each object detected by the Faster R-CNN, based on the features detected by the Faster R-CNN to detect the object. …”
Get full text

Transfer learning and multi-phase training for accurate diacritization of Arabic poetry by Gheith A. Abandah, Ashraf E. Suyyagh, Mohammad R. Abdel-Majeed

Get full text

Full‐Depth Reconstruction of Long‐Term Meridional Overturning Circulation Variability From Satellite‐Measurable Quantities via Machine Learning by Huaiyu Wei, Kaushik Srinivasan, Andrew L. Stewart, Aviv Solodoch, Georgy E. Manucharyan, Andrew McC. Hogg

“…Using a neural network interpretation technique, we identify ocean bottom pressure near the western boundary and along dense‐water export pathways as the dominant input features for MOC reconstruction. …”
Get full text

Remote Sensing Fine Estimation Model of PM_2.5 Concentration Based on Improved Long Short-Term Memory Network: A Case Study on Beijing–Tianjin–Hebei Urban Agglomeration i... by Yiye Ji, Yanjun Wang, Cheng Wang, Xuchao Tang, Mengru Song

“…Second, to effectively capture temporal dependencies and emphasize key features, an improved Long Short-Term Memory Network (LSTM) model, Bi-LSTM-SA, was constructed by combining a bidirectional LSTM (Bi-LSTM) model with a self-adaptive attention mechanism (SA). …”
Get full text

Multitask semantic change detection guided by spatiotemporal semantic interaction by Yinqing Wang, Liangjun Zhao, Yueming Hu, Hui Dai, Yuanyang Zhang

“…To further enhance detection performance, a dynamic depthwise separable convolution is designed in the CTIM module, which can adaptively adjust convolution kernels to more precisely capture change features in different regions of the image. Experimental results on three SCD datasets show that the proposed method outperforms other existing methods in various evaluation metrics. …”
Get full text

AI-Generated Artwork as a Modern Interpretation of Historical Paintings by Wai Yie Leong

“…Artificial intelligence (AI) offers unprecedented opportunities to reinterpret historical paintings, bringing classical masterpieces into modern artworks We explored the application of AI, particularly generative models such as generative adversarial networks (GANs) and neural style transfers (NST) in the contemporary interpretations of historical paintings. …”
Get full text

Feedback-Based Validation Learning by Chafik Boulealam, Hajar Filali, Jamal Riffi, Adnane Mohamed Mahraz, Hamid Tairi

“…Unlike conventional methods that utilize validation datasets for performance evaluation post-training, FBVL integrates these datasets into the training process. …”
Get full text

2D Object Detection: A Survey by Emanuele Malagoli, Luca Di Persio

Get full text

Decoding Pain Dynamics: EEG Insights into Neural Responses and Classification via RQA Analysis by Mahsa Tavasoli, Zahra Einalou, Reza Akhondzadeh

“…For this purpose, at the first step phasic pain is produced using coldness, then dynamical features via EEG are analyzed via Recurrence Quantification Analysis (RQA) method and finally Rough neural network classifier has been used for achieving accuracy to detect and categorize pain and non-pain states. …”
Get full text