ViFusion: Enhanced 3D object detection via virtual point augmentation and dynamic multi-source feature fusion

EEG scalp data processing using FIR filter, Kaiser windowing technique with features extraction and classification for epileptic seizure detection

Dimensionless features and comprehensive fuzzy-based models for fault diagnosis of rolling element bearings under varying operating conditions.

Structure-guided lensless reconstruction via physics-aware decomposition in low-light conditions

Enhancement of OCT signal interpretability in deep penetration laser welding of aluminum

Acute lymphoblastic leukemia (ALL) is a hematological malignancy characterized by the rapid proliferation of immature white blood cells in the bone marrow. Early and accurate diagnosis is essential for improving clinical outcomes; however, distinguishing between lymphocytes and lymphoblasts poses significant challenges owing to their subtle morphological similarities. Traditional manual diagnostic methods, which rely on expert evaluations, are inherently time-consuming and subject to human error. In recent years, machine learning and deep learning approaches have emerged as promising tools for automating and enhancing diagnostic processes. This review systematically examines state-of-the-art traditional and deep learning techniques applied for ALL detection and classification. We provide a comprehensive analysis of various methodologies, including supervised machine learning algorithms and advanced deep learning architectures, with a focus on critical stages such as image preprocessing, feature extraction, and blast cell quantification. Furthermore, we discuss the performance metrics and accuracy benchmarks, highlighting the potential of these techniques to match or exceed human diagnostic capabilities. The review concludes with a discussion of the current challenges, recent developments, and future directions in the application of artificial intelligence for ALL diagnosis, underscoring the need for continued innovation to meet emerging clinical demands.

A comprehensive review of EMG/EEG based wheelchair control systems for individuals with disabilities: HMI and BCI perspectives.

Ophthalmic diseases such significantly impair the vision of numerous individuals globally. Accurate and real-time 3D reconstruction of macular edema and retinal tears is crucial for improving surgical efficiency and success rates. However, lesion areas often exhibit considerable noise and high heterogeneity, and the imaging devices employed may introduce electronic noise and artifacts. Current 2D medical image segmentation techniques fail to achieve optimal outcomes. To overcome these challenges, we propose the Tri-Path Fourier-Temporal Modulation Network (TriFTM-Net). TriFTM-Net synergistically integrates spatial, frequency, and spatiotemporal features. This design effectively augments both feature representation and extraction. TriFTM-Net comprises three critical modules: the Tri-Path Spectral Hierarchical Encoder (TPSHE), which amplifies feature representation by integrating tri-path features; the Feature Re-Modulation (FRM), which reduces noise interference and enhances feature extraction; and the Hierarchical Feature Reconstruction Module (HFRM), which improves detail preservation in upsampled images. Comparative analysis with thirteen baseline methods demonstrates that our approach achieves the highest Dice scores, IoU, and Kappa coefficient on the OIMHS dataset.Our code is publicly available at https://github.com/IMOP-lab/TriFTM-Net.

Towards a lightweight YOLOv8n for aquaculture feeding detection: Architectural improvements for feature enhancement and computational efficiency

Precise reconstruction of plant phenotypes is crucial for smart agriculture. Conventional methods struggle with low efficiency and strong dependency on high-quality data, especially for low-texture and structurally complex crops like wheat. We propose a novel 3D reconstruction framework—Plant3R—that fuses deep feature learning with 3D Gaussian Splatting (3DGS). It innovatively uses the Matching and Stereo 3D Reconstruction (MASt3R) model for sparse point cloud reconstruction and camera pose estimation via its 3D feature matching capabilities, which substantially improve image matching rates and the quality of sparse point clouds. Subsequently, 3DGS is employed for rendering and optimization, enabling end-to-end, high-fidelity, and high-robust 3D reconstruction of wheat plants. Validated on potted wheat at multiple growth stages using handheld images, our experimental results demonstrate that Plant3R performs well in feature extraction and matching, and the reconstructed point cloud provides a good geometric prior for the subsequent rendering stage. In most scenes, its key rendering metrics—Peak Signal-to-Noise Ratio (PSNR) > 34, Structural Similarity Index Measure (SSIM) of 0.94, and Learned Perceptual Image Patch Similarity (LPIPS) < 0.26—surpassed Neural Radiance Fields (NeRF) and the original 3DGS. Moreover, extracted phenotypic traits such as plant height, leaf length, and width showed high correlation with manual measurements (R 2 > 0.94), confirming its utility for accurate and quantitative phenotype analysis. Overall, Plant3R not only improves the rendering quality and geometric precision of 3D modeling, but also provides a reliable tool for accurate phenotypic parameter extraction and high-throughput crop phenotyping in precision agriculture.

Design and application of garment art patterns based on visual sample generation

Exploring cognitive workload recognition using CogRepLKNet with EEG-fMRI.

Filter, Detector, Predictor: The expanding repertoire of retinal computation in vertebrates.

RefLaTEA: a robust visualization and analysis framework leveraging background data for enhanced insight.

This data article presents an image dataset compiled for the purpose of machine learning-based identification and prediction of adulteration levels in Teff (Eragrostis tef (Zucc.) Trotter) flour. The dataset includes images of pure white, mixed, and red Teff flour varieties, as well as these flours adulterated with wood flour (sawdust) and gypsum (calcium sulfate) powder. Adulteration levels range from 10% to 40% in 5% increments. The data collection process involved preparing Teff flour from naturally dried and milled Teff grains. Samples of 100 grams of each Teff flour variety were then mixed with the adulterants at the specified concentrations. A total of 5,000 raw images were captured using an 18-megapixel Canon EOS 7D camera under controlled studio lighting (300 W incandescent lamps), with the samples placed 30 cm from the camera lens in a 10 cm x 10 cm plastic box. To enhance the dataset's diversity and quantity, 25,000 augmented images were generated by shuffling image pixels' locations with various block sizes (1 × 1, 2 × 2, 4 × 4, 8 × 8, and 16 × 16). This dataset is a valuable resource for researchers and students in Teff adulteration using image processing and feature extraction. It also holds potential for use by Food and Drug Administration Authorities and law enforcement to develop automated methods for detecting Teff flour adulteration, offering an alternative to time-consuming physio-chemical laboratory tests. The dataset's structure and augmentation methods are detailed to ensure reproducibility and encourage further research into robust machine learning models for food quality control.

A wearable system enabling acute stress monitoring and closed-loop mitigation through transcutaneous median nerve stimulation.

FreqConvMamba: Frequency-guided hierarchical hybrid SSM-CNN for medical image segmentation.

Multi-view based network for malware classification

The advancement of an (in vitro/ex vivo) hybrid model framework for forecasting polyviral lung disease outcomes addresses the pressing need for sophisticated tools to understand the complexities of these infections. The primary objective of this study is to advance the development and application of an (in vitro/ex vivo) hybrid model framework for forecasting polyviral lung disease outcomes. This phase of data collection for lung infections, involving single and co-infecting viruses, utilizes ex vivo models (perfused lung tissue slices) and in vitro models (lung cell cultures). Before employing Local Binary Patterns for image analysis, data pre-processing, including Weighted Local Gabor Binary Pattern, is essential. Feature extraction is a critical initial step in enhancing the dataset for developing a hybrid model framework (in vitro/ex vivo) to predict polyviral lung disease outcomes. By employing VGG16 and CBRACDC algorithms, a hybrid model framework (in vitro/ex vivo) is created to forecast polyviral lung disease outcomes. Incorporating the Random Survival Forest algorithm into the hybrid model framework brings numerous benefits for polyviral lung disease prognosis. Python was utilized extensively throughout the development and analysis phases, contributing to the framework's robustness and versatility. The observed minimum cost value of 1.079 indicates the algorithm's optimal performance based on the defined objective. Future research avenues could focus on integrating advanced computational techniques, such as deep learning and artificial intelligence, to improve the predictive accuracy and scalability of hybrid models for forecasting polyviral lung disease outcomes. This could enable personalized medicine approaches and more targeted therapeutic interventions.

In-situ monitoring methods and deep learning models are increasingly being used for the quality assessment of parts fabricated using laser powder bed fusion to overcome the limitations of poor process repeatability. However, the massive data collection required for part-quality monitoring results in high transmission loads and storage costs. To address this problem, this study utilized the compressed sensing theory to acquire compressed photodiode signals. These signals were then used to train and test convolutional neural networks (CNN) to identify the lack-of-fusion, normal, and keyhole modes. At a compressive-sampling rate of 25%, the classification accuracy decreased from 93.1% (raw signals) to 79.3%. However, increasing the compression rate from 25% to 90% did not significantly decrease the classification accuracy. The linear mapping of the raw signal via a Gaussian measurement matrix causes coordinate information folding, thereby impairing the representation of latent features. Therefore, Gaussian process modeling was adopted for the features extracted using a pretrained CNN to mitigate the temporal information collapse and allow the compressed signals to achieve an accuracy comparable to that of the raw data. Furthermore, the sparsity and rank complexity of the melt-pool radiation signals were evaluated using sparse representation and principal component analysis.