Identification of sweetpotato virus disease-infected leaves from field images using deep learning by Ziyu Ding, Fanguo Zeng, Haifeng Li, Jianyu Zheng, Junzhi Chen, Biao Chen, Wenshan Zhong, Xuantian Li, Zhangying Wang, Lifei Huang, Xuejun Yue, Xuejun Yue

“…The APF module combines a channel attention mechanism with multi-scale feature fusion to enhance the model’s performance in disease pixel segmentation. …”
Get full text

AuxTransUNet: Enhancing Remote Sensing Image Segmentation of Open-Pit Mining Areas in Qinghai–Tibet Plateau by Fangzhou Hong, Guojin He, Guizhou Wang, Zhaoming Zhang, Yan Peng

“…However, existing approaches face notable limitations. Many deep learning models, especially those based on convolutional neural networks (CNNs), struggle to capture the complex and heterogeneous morphological features of mining areas in diverse geographic settings. …”
Get full text

Evaluation of Machine Learning Algorithms for NB-IoT Module Energy Consumption Estimation Based on Radio Channel Quality by Dusan Bortnik, Vladimir Nikic, Srdjan Sobot, Dejan Vukobratovic, Ivan Mezei, Milan Lukic

“…Using these features, we tested 11 machine learning models for energy consumption estimation, assessing their performance and memory footprint, both of which are critical factors for resource-constrained embedded systems. …”
Get full text

Integrating routine blood biomarkers and artificial intelligence for supporting diagnosis of silicosis in engineered stone workers by Daniel Sanchez‐Morillo, Antonio León‐Jiménez, María Guerrero‐Chanivet, Gema Jiménez‐Gómez, Antonio Hidalgo‐Molina, Antonio Campos‐Caro

“…Twenty‐one primary biochemical markers derived from peripheral blood extraction were obtained retrospectively from clinical hospital records. Relief‐F features selection technique was applied, and the resulting subset of 11 biomarkers was used to build five machine learning models, demonstrating high performance with sensitivities and specificities in the best case greater than 82% and 89%, respectively. …”
Get full text

Deep fusion of incomplete multi-omic data for molecular mechanism of Alzheimer’s disease by Linhui Xie, Yash Raj, Mingzhao Tong, Kwangsik Nho, Paul Salama, Andrew J. Saykin, Shiaofen Fang, Jingwen Yan

“…In this study, we developed an interpretable deep trans-omic fusion neural network, TransFuse, to include incomplete -omic data for training of prediction models. When evaluated using the data from two Alzheimer’s disease cohorts, TransFuse generally showed superior or comparable performance over competing methods in a wide range of metrics like classification accuracy and F1 score. …”
Get full text

Machine learning and microfluidic integration for oocyte quality prediction by Hassan Saffari, Davood Fathi, Peyman Palay, Hamid Gourabi, Rouhollah Fathi

“…For unsupervised learning, K-Means, DBSCAN, Agglomerative Clustering, and Gaussian Mixture Models were applied. Among them, Agglomerative Clustering yielded the best performance (Silhouette = 0.49, Davies–Bouldin = 0.73), showing meaningful grouping patterns among oocytes. …”
Get full text

The Impact of Digital Media Use on Muslim Entrepreneurs' Intention to Apply for Halal Certificate: Empirical Evidence from Indonesia by Ahmad Ajib Ridlwan, Yan Putra Timur, Muhammad Nafik Hadi Ryandono, Erika Takidah, Azreen Hamiza Abdul Aziz, Rosa Prafitri Juniarti

“…This study aims to examine factors that influence Muslim entrepreneurs' halal certification applications through digital media, using the DeLone and McLean and the Unified Theory of Acceptance and Use of Technology (UTAUT) models. This quantitative study analyses 350 Indonesian Muslim entrepreneurs using partial least square structural equation modeling (PLS-SEM). …”
Get full text

PassAI: An Explainable Machine Learning Framework for Predicting Soccer Pass Outcomes Using Multimodal Match Data by Ryota Takamido, Jun Ota, Hiroki Nakamoto

“…It also provided interpretable feedback through visual saliency maps and feature sensitivity analysis. Furthermore, RemOve And Retrain was also performed to verify the faithfulness of the generated explanation, and the visual saliency maps were highly faithful. …”
Get full text

Oriented ice eddy detection network based on the Sentinel-1 dual-polarization data by Jinqun Wu, Jinqun Wu, Yiqin Zheng, Tingting Wang, Chunyong Ma, Chunyong Ma, Ge Chen, Ge Chen

Get full text

IncSAR: A Dual Fusion Incremental Learning Framework for SAR Target Recognition by George Karantaidis, Athanasios Pantsios, Ioannis Kompatsiaris, Symeon Papadopoulos

“…However, real-world applications demand that models incrementally learn new information without forgetting previously acquired knowledge. …”
Get full text

Advances in machine transliteration methods, limitations, challenges, applications and future directions by A’la Syauqi, Aji Prasetya Wibawa

“…Hybrid approaches integrate multiple methodologies, while semantic knowledge-based models enhance accuracy by incorporating linguistic features. …”
Get full text

Density-Aware Tree–Graph Cross-Message Passing for LiDAR Point Cloud 3D Object Detection by Jingwen Zhao, Jianchao Li, Wei Zhou, Haohao Ren, Yunliang Long, Haifeng Hu

“…To bridge the gap between local precision and global contexts, we design a tree–graph cross-message-passing (TGCMP) mechanism that enables bidirectional interaction between graph and tree features. The experimental results of three large-scale benchmarks, KITTI, nuScenes, and Waymo, show that our method achieves competitive performance. …”
Get full text

Automated characterization of abdominal MRI exams using deep learning by Joonghyun Kim, Allison Chae, Jeffrey Duda, Arijitt Borthakur, Daniel J. Rader, James C. Gee, Charles E. Kahn, Penn Medicine BioBank, Walter R. Witschey, Hersh Sagreiya

“…We applied Grad-CAM to visualize image regions influencing pulse sequence predictions and highlight relevant anatomical features. To enhance performance, we implemented a majority voting approach to aggregate slice-level predictions, achieving 100% accuracy at the volume level for all tasks. …”
Get full text

Composite Power Management Strategy for Hybrid Powered Compound-Wing Aircraft in Level Flight by Siqi An, Xu Peng, Yuantao Gan, Jingyu Yang, Guofei Xiang, Songyi Dian

“…To obtain the desired features and design the regularity strategy of the power system, linear and nonlinear models are established based on the configuration of an electro-gasoline series hybrid power system installed in the proposed aircraft, with mathematical modelling of key components and units. …”
Get full text

An Artificial Neural Network Stratifies the Risks of Reintervention and Mortality after Endovascular Aneurysm Repair; a Retrospective Observational study. by Alan Karthikesalingam, Omneya Attallah, Xianghong Ma, Sandeep Singh Bahia, Luke Thompson, Alberto Vidal-Diez, Edward C Choke, Matt J Bown, Robert D Sayers, Matt M Thompson, Peter J Holt

“…ANN models predicted endograft complications and mortality with excellent discrimination between a low-risk and high-risk group. …”
Get full text

Accelerated brain ageing during the COVID-19 pandemic by Ali-Reza Mohammadi-Nejad, Martin Craig, Eleanor F. Cox, Xin Chen, R. Gisli Jenkins, Susan Francis, Stamatios N. Sotiropoulos, Dorothee P. Auer

“…Brain age prediction models are trained from hundreds of multi-modal imaging features using a cohort of 15,334 healthy participants. …”
Get full text

Advances in weed identification using hyperspectral imaging: A comprehensive review of platform sensors and deep learning techniques by Bright Mensah, Nitin Rai, Kelvin Betitame, Xin Sun

“…Techniques like image calibration, standard normal variate, multiplicative scatter correction, Savitsky-Golay smoothing, derivatives, and features selection are among the most used techniques, (d) traditional machine learning models namely support vector machines (SVM), partial least square discriminant analysis (PLS-DA), maximum likelihood classifiers (MLC), and random forest (RF) are the widely employed classifiers for weed identification, (e) the application of deep learning technique, namely convolutional neural networks (CNNs) are limited, but its application demonstrated superior performance accuracies compared to traditional machine learning models. …”
Get full text

Visual explainability of 250 skin diseases viewed through the eyes of an AI‐based, self‐supervised vision transformer—A clinical perspective by Ramy Abdel Mawgoud, Christian Posch

“…Methods Using a public data set containing images of 250 different skin diseases, one small ViT was pretrained S) for 300 epochs (=ViT‐SS), and two were fine‐tuned supervised from ImageNet‐weights for 300 epochs (=ViT‐300) and for 78 epochs due to heavier regularization (=ViT‐78), respectively. The models generated 250 self‐attention maps each. These maps were analyzed in a blinded manner using a ‘DermAttention’ score, and the models were primarily compared based on their ability to focus on disease‐relevant features. …”
Get full text

Parametric optimization of flow in a solar chimney power plant under variable semi elliptical constraints by Rajamurugu Natarajan, S. Yaknesh, K B Prakash, Mohammed Al Awadh, Qasem M. Al-Mdallal

“…Abstract In response to the ongoing quest for more efficient renewable energy sources, this research addresses a significant gap in understanding the performance variations of Solar Chimney Power Plant (SCPP) models, particularly focusing on the influence of flow parameters in full and half-inclined collector sections featuring semi-elliptical curvature. …”
Get full text

Neural Network Ensemble Method for Deepfake Classification Using Golden Frame Selection by Khrystyna Lipianina-Honcharenko, Nazar Melnyk, Andriy Ivasechko, Mykola Telka, Oleg Illiashenko

“…We integrate multiple deep learning models, including ResNet50, EfficientNetB0, Xception, InceptionV3, and Facenet, with an XGBoost meta-model for enhanced classification performance. …”
Get full text