Deep belief network
View article: FusionNet: A parallel deep learning model for speech recognition with feature clustering
FusionNet: A parallel deep learning model for speech recognition with feature clustering Open
FusionNet is a parallel, hybrid deep-learning framework engineered for next-generation speech recognition and on-device speech-to-text processing. The system is implemented as an Android application (Java/XML) and integrated with Firebase …
View article: FusionNet: A parallel deep learning model for speech recognition with feature clustering
FusionNet: A parallel deep learning model for speech recognition with feature clustering Open
FusionNet is a parallel, hybrid deep-learning framework engineered for next-generation speech recognition and on-device speech-to-text processing. The system is implemented as an Android application (Java/XML) and integrated with Firebase …
View article: Blind Source Separation: A Comparative Study of Classical Statistical Methods and Deep Learning Architectures
Blind Source Separation: A Comparative Study of Classical Statistical Methods and Deep Learning Architectures Open
This master's project investigates Blind Source Separation (BSS), a signal processing problem aimed at extracting individual source signals from mixed observations without prior knowledge. The report presents a detailed study of both class…
View article: Blind Source Separation: A Comparative Study of Classical Statistical Methods and Deep Learning Architectures
Blind Source Separation: A Comparative Study of Classical Statistical Methods and Deep Learning Architectures Open
This master's project investigates Blind Source Separation (BSS), a signal processing problem aimed at extracting individual source signals from mixed observations without prior knowledge. The report presents a detailed study of both class…
View article: PRECISION MEDICINE IN LUNG CANCER-MULTI- OMICS DATA FUSION WITH DEEP LEARNING FOR ACCURATE CLASSIFICATION AND PREDICTION
PRECISION MEDICINE IN LUNG CANCER-MULTI- OMICS DATA FUSION WITH DEEP LEARNING FOR ACCURATE CLASSIFICATION AND PREDICTION Open
Precision medicine in oncology increasingly leverages multi-omics data fusion and advanced machine learning to improve diagnostic accuracy and clinical decision-making. This study presents a deep learning-based framework for the accuratecl…
View article: KNEE OSTEOARTHRITIS PREDICTION AND CLASSIFICATION FROM X-RAY IMAGES USING DEEP LEARNING AIML
KNEE OSTEOARTHRITIS PREDICTION AND CLASSIFICATION FROM X-RAY IMAGES USING DEEP LEARNING AIML Open
Kellgren–Lawrence (KL) grading system is a radiographic-based grading system used to figure out how bad knee osteoarthritis (KOA) is. KOA is a degenerative joint disease that gets worse over time and changes the structure of X-ray pictures…
View article: Classification of Alzheimer’s disease using advanced deep learning and ensemble techniques
Classification of Alzheimer’s disease using advanced deep learning and ensemble techniques Open
Alzheimer’s disease (AD), a leading cause of dementia, presents persistent challenges in accurate staging and diagnosis from neuroimaging data. This study investigates advanced deep learning approaches for classifying AD from brain MRI, fo…
View article: From Decision Models to Prediction Models: Enhancing Supplier Selection with Machine Learning and Deep Learning
From Decision Models to Prediction Models: Enhancing Supplier Selection with Machine Learning and Deep Learning Open
This study extends the traditional Multi-Criteria Decision-Making (MCDM) framework for supplier selection in circular supply chains by integrating predictive machine learning (ML) and deep learning (DL) models. Conceptually, it bridges the…
View article: From Decision Models to Prediction Models: Enhancing Supplier Selection with Machine Learning and Deep Learning
From Decision Models to Prediction Models: Enhancing Supplier Selection with Machine Learning and Deep Learning Open
This study extends the traditional Multi-Criteria Decision-Making (MCDM) framework for supplier selection in circular supply chains by integrating predictive machine learning (ML) and deep learning (DL) models. Conceptually, it bridges the…
View article: A Physics-Aware Attention LSTM Autoencoder for Early Fault Diagnosis of Battery Systems
A Physics-Aware Attention LSTM Autoencoder for Early Fault Diagnosis of Battery Systems Open
Battery safety is paramount for electric vehicles. Early fault diagnosis remains a challenge due to the subtle nature of anomalies and the interference of dynamic operating noise. Existing data-driven methods often suffer from "physical bl…
View article: A Physics-Aware Attention LSTM Autoencoder for Early Fault Diagnosis of Battery Systems
A Physics-Aware Attention LSTM Autoencoder for Early Fault Diagnosis of Battery Systems Open
Battery safety is paramount for electric vehicles. Early fault diagnosis remains a challenge due to the subtle nature of anomalies and the interference of dynamic operating noise. Existing data-driven methods often suffer from "physical bl…
View article: Implicit Regularization of hyperparameters in deep learning
Implicit Regularization of hyperparameters in deep learning Open
View article: Towards Robust and Effective Point Cloud Normal Estimation and Denoising via Patch-based Deep Learning
Towards Robust and Effective Point Cloud Normal Estimation and Denoising via Patch-based Deep Learning Open
This research is about enhancing the performance of deep learning-based methods for estimating normal vectors and removing noise for 3D point clouds, especially for those with significant noise and irregular distributions. The outcome of t…
View article: Evolving Interpretable Circuit Representations for Deep Learning Reverse Engineering
Evolving Interpretable Circuit Representations for Deep Learning Reverse Engineering Open
Reverse engineering deep learning models is crucial for understanding their decision-making processes, identifying potential vulnerabilities, and ensuring trustworthiness. However, the inherent complexity of deep neural networks poses a si…
View article: Evolving Interpretable Circuit Representations for Deep Learning Reverse Engineering
Evolving Interpretable Circuit Representations for Deep Learning Reverse Engineering Open
Reverse engineering deep learning models is crucial for understanding their decision-making processes, identifying potential vulnerabilities, and ensuring trustworthiness. However, the inherent complexity of deep neural networks poses a si…
View article: Deep Kernel Machines: Synergistic Representation and Margin Optimization for Robust Generalization
Deep Kernel Machines: Synergistic Representation and Margin Optimization for Robust Generalization Open
Deep learning has achieved unprecedented success in learning complex representations from high-dimensional data, revolutionizing fields from computer vision to natural language processing. However, despite their empirical prowess, deep neu…
View article: Deep Kernel Machines: Synergistic Representation and Margin Optimization for Robust Generalization
Deep Kernel Machines: Synergistic Representation and Margin Optimization for Robust Generalization Open
Deep learning has achieved unprecedented success in learning complex representations from high-dimensional data, revolutionizing fields from computer vision to natural language processing. However, despite their empirical prowess, deep neu…
View article: MuSL: Multimodal deep learning for generalizable prediction of synthetic lethality from sequence, transcriptomic, and network data
MuSL: Multimodal deep learning for generalizable prediction of synthetic lethality from sequence, transcriptomic, and network data Open
MuSL: Multimodal deep learning for generalizable prediction of synthetic lethality from sequence, transcriptomic, and network data Model Architecture The MuSL framework integrates multimodal biological data through a tri-branch deep learni…
View article: Deep Manifold PCA for Interpretable and Robust Representation Learning in Foundation Models
Deep Manifold PCA for Interpretable and Robust Representation Learning in Foundation Models Open
Foundation models have demonstrated unprecedented capabilities across a wide range of tasks, yet their complexity often renders them opaque, making their decisions difficult to interpret and their internal representations vulnerable to adv…
View article: Deep Manifold PCA for Interpretable and Robust Representation Learning in Foundation Models
Deep Manifold PCA for Interpretable and Robust Representation Learning in Foundation Models Open
Foundation models have demonstrated unprecedented capabilities across a wide range of tasks, yet their complexity often renders them opaque, making their decisions difficult to interpret and their internal representations vulnerable to adv…
View article: MuSL: Multimodal deep learning for generalizable prediction of synthetic lethality from sequence, transcriptomic, and network data
MuSL: Multimodal deep learning for generalizable prediction of synthetic lethality from sequence, transcriptomic, and network data Open
MuSL: Multimodal deep learning for generalizable prediction of synthetic lethality from sequence, transcriptomic, and network data Model Architecture The MuSL framework integrates multimodal biological data through a tri-branch deep learni…
View article: Bayesian deep learning for vehicle battery health prognostics: Incorporating behavioral perception and informative priors
Bayesian deep learning for vehicle battery health prognostics: Incorporating behavioral perception and informative priors Open
View article: Comparison of Different Port Path Optimization Methods: Traditional Methods, Deep Learning Methods, and Multimodal Fusion Methods, Highlighting Their Advantages, Disadvantages, and Application Scenarios.
Comparison of Different Port Path Optimization Methods: Traditional Methods, Deep Learning Methods, and Multimodal Fusion Methods, Highlighting Their Advantages, Disadvantages, and Application Scenarios. Open
Comparison of Different Port Path Optimization Methods: Traditional Methods, Deep Learning Methods, and Multimodal Fusion Methods, Highlighting Their Advantages, Disadvantages, and Application Scenarios.
View article: Machine and deep learning classifiers for binary and multi-class network intrusion detection systems
Machine and deep learning classifiers for binary and multi-class network intrusion detection systems Open
The rapid proliferation of the internet and advancements in communication technologies have significantly improved networking and increased data vol ume. This phenomenon has subsequently caused a multitude of novel attacks, thereby present…
View article: Ultra-short-term wind power prediction method based on optimized signal decomposition and deep learning
Ultra-short-term wind power prediction method based on optimized signal decomposition and deep learning Open
View article: Super-resolution of satellite-derived SST data via Generative Adversarial Networks
Super-resolution of satellite-derived SST data via Generative Adversarial Networks Open
In this work, we address the super-resolution problem of satellite-derived sea surface temperature (SST) using deep generative models. Although standard gap-filling techniques are effective in producing spatially complete datasets, they in…
View article: Super-resolution of satellite-derived SST data via Generative Adversarial Networks
Super-resolution of satellite-derived SST data via Generative Adversarial Networks Open
In this work, we address the super-resolution problem of satellite-derived sea surface temperature (SST) using deep generative models. Although standard gap-filling techniques are effective in producing spatially complete datasets, they in…
View article: Advanced Data Collection Techniques in Cloud Security: A Multi-Modal Deep Learning Autoencoder Approach
Advanced Data Collection Techniques in Cloud Security: A Multi-Modal Deep Learning Autoencoder Approach Open
Cloud security is an important concern. To identify and stop cyber threats, efficient data collection methods are necessary. This research presents an innovative method to cloud security by integrating numerous data sources and modalities …
View article: Self-Attention-Based Deep Learning for Missing Sensor Data Imputation in Real-Time Probe Card Monitoring
Self-Attention-Based Deep Learning for Missing Sensor Data Imputation in Real-Time Probe Card Monitoring Open
In industrial monitoring of semiconductor probe cards, real-time sensor data acquisition and processing are essential for anomaly detection and predictive maintenance. However, missing data resulting from possible sensor malfunctions prese…
View article: NeuroAgeFusionNet an ensemble deep learning framework integrating CNN, transformers, and GNN for robust brain age estimation using MRI scans
NeuroAgeFusionNet an ensemble deep learning framework integrating CNN, transformers, and GNN for robust brain age estimation using MRI scans Open
Brain age prediction based on anatomical MRI scans, as an essentially new measure in neuroimaging and aging research, provides a crucial marker for the early diagnosis of neurodegenerative diseases, cognitive health appraisal, and biologic…