IEEE

Fraudulent Credit Card Transaction Monitoring Using Deep Learning: A CNN-LSTM Approach for Single-Transaction Security Identification

Abstract: Credit card cash-out methods have become increasingly complex, with new fraudulent transaction forms emerging continuously. Effective management is hindered by challenges in obtaining ...
IEEE

AI-Powered Defect Detection using Deep Learning: A Pattern-Agnostic Faster R-CNN Approach for SEM Images with GPU Acceleration

Abstract: Semiconductor manufacturing requires highly precise defect detection to ensure product quality and yield. This paper presents a deep learning-based defect detection framework using Faster ...
IEEE

Hybrid Deep Learning for Portable Weather Forecasting: Real-Time Predictions Using CNN-LSTM-Transformer Models

Abstract: Accurate weather forecasting is critical for agriculture, disaster management, and transportation sectors. However, traditional forecasting systems often require extensive computational ...
IEEE

MFC-CNN: A Deep Learning Framework for Urban Building Height Estimation from GF-7 Imagery

Abstract: Estimating building heights by generating disparity maps from multi-view satellite images through stereo matching remains challenging in urban research. However, disparity maps produced by ...
IEEE

Digital-Twin-Enabled Federated Learning and CNN-Based Channel Estimation for Urban Vehicular Channels

Abstract: Urban vehicular channel estimation (UVCE) has long been a difficult task due to the intercarrier interference (ICI) and path loss caused by high-speed vehicle motion and urban geographical ...
IEEE

Automated Food Spoilage Detection Using Deep Learning: A CNN-Based Approach

Abstract: Food spoilage detection is critical in ensuring food safety and reducing waste. In this work, we offer a new neural network model, rotOrNot, intended for image analysis-based rotten food ...
IEEE

Automated Deep Learning System for Early Detection of Stroke Using CNN Architecture

Abstract: Strokes are a major cause of disability worldwide, with ischemic and hemorrhagic strokes accounting for the majority of cases. In India, stroke remains the second most common cause of ...
IEEE

Evaluation of Machine Learning Frameworks: VGG16, InceptionV3, ResNet50, and Custom CNN for Martian Surface Classification

Abstract: Feature classification of the Mars surface is very crucial in planetary science as well as in missions and disentanglement of the history behind the Red Planet. In this paper, research will ...
IEEE

Emotion Detection from Facial Cues Using CNN-Based Deep Learning

Abstract: Human emotion recognition is an evolving research area with significant applications in domains such as healthcare, education, security, and human-computer interaction. This study focuses on ...
IEEE

CNN vs Transfer Learning for Enhancing Spectrogram Classification of Baby Cries

Abstract: Audio is ever-present in our daily lives, whether it's a baby crying, an audio message, or noise. However raw audio signals are complex and often difficult to analyze directly. Spectrograms ...
IEEE

Predictive Autism Analysis: Integrating CNN and RNN with Ensemble Learning

Abstract: Timely identification of Autism Spectrum Disorder (ASD) is essential for successful intervention, but current diagnostic methods often depend on subjective observations, potentially missing ...
IEEE

Deep Learning for Aerial and Satellite Image Analysis: a CNN-Based Approach

Abstract: Applications like disaster management, urban planning, and environmental monitoring rely on satellite image categorization. This project develops a machine learning pipeline using ...