Results 131 to 140 of about 118,357 (248)

Real‐Time, Label‐Free Classification of Cell Death Pathways via Holotomography‐Based Deep Learning Framework

Advanced Intelligent Systems, EarlyView.
A 3D holotomography system coupled with a deep learning model distinguishes how cells die—apoptosis, necroptosis or necrosis—without any fluorescent labels. Training on refractive index maps of HeLa cells yields 97% accuracy and flags necroptosis hours before chemical dyes.
Minwook Kim, Wei Sun Park, Geon Kim, Sanggeun Oh, Jaephil Do, Juyeon Park, Jihwan Yu, Won Do Heo, YongKeun Park   +8 more
wiley   +1 more source

Edge Information‐Augmented Auxiliary Diagnosis Method for Cervical Cancer in Medical Decision‐Making Systems

Advanced Intelligent Systems, EarlyView.
To address the problems of insufficient utilization of multiscale features and inefficient feature sharing between tasks in the model, this study proposes an edge‐enhanced intelligent cervical cancer screening method that achieves feature reuse and improves efficiency by jointly optimizing nucleolus segmentation and lesion classification.
Li Wen, Xiaoqing Zhang, Tingyi Dai, Fangfang Gou, Jia Wu   +4 more
wiley   +1 more source

A CRDNet‐Based Watermarking Algorithm for Fused Visible–Infrared Images

Advanced Intelligent Systems, EarlyView.
CRDnet includes encoders and decoders based on residual and dense structures, a fusion network robust to 12 visible and infrared image fusion algorithms, and predictors for predicting watermarked infrared images. The encoder and decoder incorporate preprocessing steps, attention mechanisms, and activation functions suitable for infrared images.
Yu Bai, Li Li, Shanqing Zhang, Ting Luo, Chin‐Chen Chang   +4 more
wiley   +1 more source

Synthetic Electrocardiogram Spectrogram Generation Using Generative Adversarial Network‐Based Models: A Comparative Study

Advanced Intelligent Systems, EarlyView.
Cardiovascular diseases are leading death causes; electrocardiogram (ECG) analysis is slow, motivating machine learning and deep learning. This study compares deep convolutional generative adversarial network, conditional GAN, and Wasserstein GAN with gradient penalty (WGAN‐GP) for synthetic ECG spectrograms; Fréchet Inception Distance (FID) and ...
Giovanny Barbosa‐Casanova, Norelli Schettini, Winston Percybrooks, Begoña García‐Zapirain   +3 more
wiley   +1 more source

MFI-ResNet: Efficient ResNet Architecture Optimization via MeanFlow Compression and Selective Incubation

ResNet has achieved tremendous success in computer vision through its residual connection mechanism. ResNet can be viewed as a discretized form of ordinary differential equations (ODEs). From this perspective, the multiple residual blocks within a single ResNet stage essentially perform multi-step discrete iterations of the feature transformation for ...
Sun, Nuolin, Wang, Linyuan, Wei, Haonan, Li, Lei, Yan, Bin   +4 more
openaire   +2 more sources

Autonomous Robotic Colonoscopy: A Supervised Learning Approach for Enhanced Navigation and Collision Detection

Advanced Intelligent Systems, EarlyView.
A novel autonomous robotic colonoscopy is introduced through supervised learning approaches. The proposed system consists of 3 degrees of freedom motorized colonoscope with an integrated navigation module that can infer a target steering point and collision probability.
Bohyun Hwang, Dae Kyung Sohn, Seonggun Joe, Byungkyu Kim   +3 more
wiley   +1 more source

An enhanced ResNet-50 deep learning model for arrhythmia detection using electrocardiogram biomedical indicators

Evolutionary Systematics, 2023
R. Anand, S. V. Lakshmi, Digvijay Pandey, B. Pandey   +3 more
semanticscholar   +1 more source

Robust Dysarthric Speech Recognition with GAN Enhancement and LLM Correction

Advanced Intelligent Systems, EarlyView.
This study tackles dysarthric speech recognition by combining generative adversarial network (GAN)‐generated synthetic data with large language model (LLM)‐based error correction. The approach integrates three key elements: an improved CycleGAN to generate synthetic dysarthric speech for data augmentation, a multimodal automatic speech recognition core
Yibo He, Kah Phooi Seng, Chee Shen Lim, Li Minn Ang   +3 more
wiley   +1 more source

ResNetMF: Improving Recommendation Accuracy and Speed with Matrix Factorization Enhanced by Residual Networks

Acta Informatica Pragensia
Background: Recommendation systems are essential for personalized user experiences but struggle to balance accuracy and efficiency.Objective: This paper presents ResNetMF, an innovative hybrid framework designed to address these limitations by combining ...
Mustafa Payandenick, YinChai Wang, Mohd Kamal Othman, Muhammad Payandenick   +3 more
doaj   +1 more source

Iterative Data Curation for Machine Learning‐Based Inverse Design of Active Composite Plates for Four‐Dimensional Printing

Advanced Intelligent Systems, EarlyView.
A machine learning framework is developed for the inverse design of 4D‐printed active composite plates. It utilizes a forward model to predict shapes from patterns and an inverse model to suggest initial patterns for desired shapes. This framework integrates a genetic algorithm to refine the predicted patterns, ensuring higher accuracy in achieving ...
Teerapong Poltue, Chao Zhang, Frédéric Demoly, Kun Zhou, H. Jerry Qi   +4 more
wiley   +1 more source