Convolutional Neural Network Projects for M.E, M.Tech, Masters, MS abroad, and PhD students. These Convolutional Neural Network ieee projects are implemented with future work and extension for final year project submission with research paper publishing. These research projects guide final year students to learn, practice, and complete their academic submissions successfully. Each project includes complete source code, project report, PPT, a tutorial, documentation, and a research paper.
Latest Convolutional Neural Network Projects
-
A Learnable Counter-Condition Analysis Framework for Functional Connectivity-Based Neurological Disorder Diagnosis
This project focuses on detecting brain disorders using brain activity data. It combines diagnosis and explanation in a single system to make results more reliable. The system learns which brain connections are important for each person. It can also simulate changes in brain activity to understand how disorders affect the brain. -
A Novel Three-Dimensional Direction-of-Arrival Estimation Approach Using a Deep Convolutional Neural Network
This project focuses on finding the direction from which signals come in a three-dimensional space. It uses a special type of artificial intelligence called a deep convolutional neural network to analyze data from a small antenna array. The system can accurately predict angles from any direction, even when multiple signals arrive at the same time. The goal is to make signal detection faster, precise, and reliable in different conditions. -
A Transformer-Based Knowledge Distillation Network for Cortical Cataract Grading
This project focuses on automatically grading cortical cataracts, a type of eye disease that is hard to detect. The system uses advanced AI called a Transformer to carefully analyze eye images. It breaks the eye into zones and looks at important details like location, size, and density of the cataract. The method can handle missing information and uncertain data, making it more accurate than previous approaches. -
Accelerating Neural ODEs Using Model Order Reduction
This project makes neural networks faster and more efficient by using ideas from physics and mathematics. It focuses on Neural ODEs, which normally take a long time to run. The researchers use a special method called model order reduction to simplify the calculations without losing accuracy. Their approach works well for tasks like image and time-series classification, making these networks usable on devices with limited resources. -
Advanced Learning Technologies for Intelligent Transportation Systems: Prospects and Challenges
This project studies how smart transportation systems can be improved using deep learning. It looks at how traffic, vehicles, roads, and weather affect transportation. The study explains modern AI methods for predicting traffic, recognizing vehicles, and monitoring road conditions. It also highlights challenges and future ideas to make transportation safer and more efficient. -
An Epileptic EEG Detection Method Based on Data Augmentation and Lightweight Neural Network
This project focuses on detecting epilepsy using brain signals. The researchers combined two datasets and improved them to train a small, efficient neural network. The model can accurately identify epilepsy with high reliability. It works well even on low-cost devices and wearable technology, making real-time detection possible. -
An Introduction to Adversarially Robust Deep Learning
This project studies how deep learning models, which are used in fields like medical imaging and speech recognition, can be easily fooled by tiny changes in input data. It reviews past research on making these models more reliable. The work explains why previous solutions did not fully succeed. It also points out new directions for improving the safety and robustness of these systems. -
Attention Feature Fusion Network via Knowledge Propagation for Automated Respiratory Sound Classification
This project focuses on detecting lung problems in children using recorded breathing sounds. It uses a computer program that learns patterns in these sounds to tell if a child has a respiratory disease. The system works remotely, so doctors can diagnose patients without face-to-face visits. It is more accurate than older methods and can help in situations like pandemics. -
Deep Conditional Generative Adversarial Networks for Efficient Channel Estimation in AmBC Systems
This project improves how battery-free devices communicate using signals from the environment. It uses a deep learning method called a conditional GAN to clean and estimate noisy signal data. The approach learns signal patterns better than older methods and makes communication more accurate and reliable. -
Deep Ensemble Learning With Pruning for DDoS Attack Detection in IoT Networks
This project focuses on protecting Internet of Things devices from online attacks that overload networks, known as DDoS attacks. It introduces a system called DEEPShield, which uses advanced machine learning models to detect both strong and weak attacks quickly. The system works efficiently even on small devices with limited memory. It also uses a new dataset to improve accuracy and reduce errors in detecting threats. -
Deep Learning for Retrospective Motion Correction in MRI: A Comprehensive Review
This project focuses on using deep learning to fix problems caused by movement during MRI scans. When a person moves, the MRI images can become blurry or distorted. The study reviews different deep learning methods that can correct these motion errors and improve image quality. It also discusses challenges, trends, and future research directions in this field. -
Deep Representation Learning With Sample Generation and Augmented Attention Module for Imbalanced ECG Classification
This project focuses on building a smart system to monitor heartbeats and detect irregular heart patterns. It uses a new deep learning method to identify abnormal beats more accurately. The system improves learning by balancing data and paying more attention to important heartbeat features. Tests show it works well on real heartbeat data and can help detect arrhythmias effectively. -
EAG-RS: A Novel Explainability-Guided ROI-Selection Framework for ASD Diagnosis via Inter-Regional Relation Learning
This project focuses on using brain scans to detect autism. It studies how different regions of the brain interact in complex ways. The method finds important brain areas that help distinguish autistic patients from others. The approach is explainable, meaning it shows why it makes each diagnosis and works better than earlier methods. -
Efficient Quantum Image Classification Using Single Qubit Encoding
This project explores using quantum computing to classify images more efficiently. It develops a new method that uses only a single quantum bit to mimic traditional deep learning techniques. The approach reduces complexity and requires fewer resources than existing methods. Tests on common image datasets show promising accuracy, and the method could be improved further in the future. -
FedDCT: Federated Learning of Large Convolutional Neural Networks on Resource-Constrained Devices Using Divide and Collaborative Training
This project focuses on making advanced machine learning models usable on devices with limited memory, like smartphones or wearable sensors. Instead of having each device train a big model alone, the method splits the model into smaller parts and lets multiple devices train them together. Devices in a group can also learn from each other, which improves the results. The approach reduces memory needs, speeds up training, and works well on both standard and medical datasets. -
Fetal-BET: Brain Extraction Tool for Fetal MRI
This project focuses on automatically identifying the fetal brain in MRI images. The researchers created a large dataset of fetal brain scans from different MRI types. They used deep learning to teach a computer to detect and separate the brain from other tissues. This method works accurately even when the scans are from different machines or show abnormal brains. -
GAN-Based Evasion Attack in Filtered Multicarrier Waveforms Systems
This project studies how advanced AI, called GANs, can trick wireless communication systems. It shows that fake signals made by GANs can look almost exactly like real ones. The research tested this on modern multi-carrier signals used in networks. The results show that receivers can be fooled 99.7% of the time, revealing a serious security risk. -
Intelligent Electrocardiogram Acquisition Via Ubiquitous Photoplethysmography Monitoring
This project focuses on using wearable device signals to detect heart problems. It studies PPG data, which can be measured continuously and easily by consumer devices. The goal is to find unusual patterns in PPG that indicate when an ECG test should be taken. The proposed method uses a deep learning model to accurately predict these heart abnormalities. -
LAFIT: Efficient and Reliable Evaluation of Adversarial Defenses With Latent Features
This project studies how deep learning models, especially convolutional neural networks, can be tricked by tiny changes in input that humans cannot notice. The research introduces a new method called LAFIT to test how strong these models are against such attacks. It shows that using hidden information inside the model can make attacks more effective. The work helps make AI systems safer by better evaluating their weaknesses. -
Masked Modeling-Based Ultrasound Image Classification via SelfSupervised Learning
This project uses artificial intelligence to improve how ultrasound images are analyzed. It teaches a computer to understand images without needing human labeling. The system learns by filling in missing parts of images, helping it recognize patterns more effectively. This method makes ultrasound image classification more accurate, even when the images are unclear or noisy.
Did you like this research project?
To get this research project Guidelines, Training and Code…