Results 91 to 100 of about 22,365 (196)

ВИЯВЛЕННЯ СТЕГАНОГРАФІЇ НА ЗОБРАЖЕННІ З ВИКОРИСТАННЯМ ЛЕГКОВАЖНИХ МОДЕЛЕЙ ГЛИБОКОГО НАВЧАННЯ

Кібербезпека: освіта, наука, техніка
У роботі  представлено комплексне експериментальне дослідження можливостей застосування легковажних згорткових нейронних мереж для задач стегоаналізу цифрових зображень в умовах обмежених обчислювальних ресурсів.
Наталія Лащевська, Юрій Мішкур   +1 more
doaj   +1 more source

Evaluation of the Feasibility of Coffee Variety Classification from Bean Images Using Convolutional Neural Networks

Acta Universitatis Cibiniensis. Series E: Food Technology
The study evaluates the feasibility of classifying Arabica and Robusta coffee beans using convolutional neural networks (CNNs). A custom CNN model (CNN_Coffee_Classifier) was developed and its performance was compared to that of three state-of-the-art ...
Zimka Michał, Pentoś Katarzyna
doaj   +1 more source

Enhancing Quranic Recitation Accuracy Using State-of-the-Art Audio Classification Techniques

Protek: Jurnal Ilmiah Teknik Elektro
- In this study, we investigate the potential of using state-of-the-art neural network architectures to increase the accuracy in classification of Quranic recitations per verse.
Hanaa Mohammed Osman, Maher Khalaf Hussein   +1 more
doaj   +1 more source

Perbandingan Performa Model SSD Mobilenet V2 dan FPNLite Dalam Deteksi Helm Pengendara Sepeda Motor

Komputika
Salah satu aspek penting dalam computer vision adalah deteksi objek yang bertujuan untuk mengidentifikasi dan menentukan posisi objek dalam gambar. Dalam konteks keselamatan, deteksi objek helm pada pengendara sepeda motor menjadi sangat penting untuk ...
Dionisius Reinaldo Ananda Setiawan, Yosefina Finsensia Riti, Nathanael Christian Perkasa Trisuwita   +2 more
doaj   +1 more source

Real-Time Monitoring Method for Cow Rumination Behavior Based on Edge Computing and Improved MobileNet v3

智慧农业
ObjectiveReal-time monitoring of cow ruminant behavior is of paramount importance for promptly obtaining relevant information about cow health and predicting cow diseases.
ZHANG Yu, LI Xiangting, SUN Yalin, XUE Aidi, ZHANG Yi, JIANG Hailong, SHEN Weizheng   +6 more
doaj   +1 more source

A Comparative Study of Three Pre-trained Convolutional Neural Networks in the Detection of Violence Against Women

Ciencia Ergo Sum
Se presenta una comparación de rendimiento entre tres modelos de redes CNN preentrenadas (VGG16, ResNet50 y MobileNet) en la detección en video de violencia física contra la mujer.
Ivan Gaytán Aguilar, Alejandro Aguilar Contreras, Roberto Alejo Eleuterio, Eréndira Rendón Lara, Grisel Miranda Piña, Everardo E. Granda Gutiérrez   +5 more
doaj  

Sustainable AI for diabetic foot ulcer detection: a deep learning approach for early diagnosis

Discover Applied Sciences
Diabetic foot ulcer (DFU) is one of the most expensive and debilitating complications of diabetes. According to procedures developed by the National Institute of Health and Clinical Excellence, early and effective treatment of DFU can minimize the ...
Saswati Debnath, Anshu Khurana, M. Senbagavalli, Shradha Naik, Jagdish Chandra Patni, Pawan Kumar Mishra, Jaydeep Kishore   +6 more
doaj   +1 more source

Enhancing early detection of Alzheimer’s disease through hybrid models based on feature fusion of multi-CNN and handcrafted features

Scientific Reports
Alzheimer’s disease (AD) is a brain disorder that causes memory loss and behavioral and thinking problems. The symptoms of Alzheimer’s are similar throughout its development stages, which makes it difficult to diagnose manually.
Abdulaziz M. Alayba, Ebrahim Mohammed Senan, Jalawi Sulaiman Alshudukhi   +2 more
doaj   +1 more source

Face Mask Detection using Mobilenet Technique

International Journal of Computer Applications, 2021
Chitra Nasa, Shikhar Mattoo, Shivam Sourav   +2 more
openaire   +1 more source

A hybrid system for detecting semiconductor wafer defects using modified MobileNet with multi-head attention. [PDF]

PLoS One
Dhar S, Al Farid F, Islam MS, Uddin J, Mansor S.   +4 more
europepmc   +1 more source