Hybrid Deep Learning Approach Research Articles

Enhanced Detection Performance of Acute Vertebral Compression Fractures Using a Hybrid Deep Learning and Traditional Quantitative Measurement Approach: Beyond the Limitations of Genant Classification

Objective: This study evaluated the applicability of the classical method, height loss ratio (HLR), for identifying major acute compression fractures in clinical practice and compared its performance with deep learning (DL)-based VCF detection methods. Additionally, it examined whether combining the HLR with DL approaches could enhance performance, exploring the potential integration of classical and DL methodologies. Methods: End-to-End VCF Detection (EEVD), Two-Stage VCF Detection with Segmentation and Detection (TSVD_SD), and Two-Stage VCF Detection with Detection and Classification (TSVD_DC). The models were evaluated on a dataset of 589 patients, focusing on sensitivity, specificity, accuracy, and precision. Results: TSVD_SD outperformed all other methods, achieving the highest sensitivity (84.46%) and accuracy (95.05%), making it particularly effective for identifying true positives. The complementary use of DL methods with HLR further improved detection performance. For instance, combining HLR-negative cases with TSVD_SD increased sensitivity to 87.84%, reducing missed fractures, while combining HLR-positive cases with EEVD achieved the highest specificity (99.77%), minimizing false positives. Conclusion: These findings demonstrated that DL-based approaches, particularly TSVD_SD, provided robust alternatives or complements to traditional methods, significantly enhancing diagnostic accuracy for acute VCFs in clinical practice.

Harnessing advanced hybrid deep learning model for real-time detection and prevention of man-in-the-middle cyber attacks

The growing number of connected devices in smart home environments has amplified security risks, particularly from Man-in-the-Middle (MitM) attacks. These attacks allow cybercriminals to intercept and manipulate communication streams between devices, often remaining undetected. Traditional rule-based methods struggle to cope with the complexity of these attacks, creating a need for more advanced, adaptive intrusion detection systems. This research introduces the AEXB Model, a hybrid deep learning approach that combines the feature extraction capabilities of an AutoEncoder with the classification power of XGBoost. By combining these complementary methods, the model enhances detection accuracy and significantly reduces false positives. The AEXB Model’s methodology encompasses robust preprocessing steps, including data cleaning, scaling, and dimensionality reduction, followed by comprehensive feature engineering and selection techniques, such as Recursive Feature Elimination (RFE) and correlation analysis. By applying this approach to the Intrusion Detection in Smart Home (IDSH) dataset, the model achieves an impressive 97.24% accuracy, demonstrating its effectiveness in identifying anomalous network behavior indicative of MitM attacks. Additionally, the model’s real-time detection capabilities allow for rapid responses to threats, thus providing continuous protection in dynamic smart home environments.

Energy consumption forecasting for oil and coal in China based on hybrid deep learning

The consumption forecasting of oil and coal can help governments optimize and adjust energy strategies to ensure energy security in China. However, such forecasting is extremely challenging because it is influenced by many complex and uncertain factors. To fill this gap, we propose a hybrid deep learning approach for consumption forecasting of oil and coal in China. It consists of three parts, i.e., feature engineering, model building, and model integration. First, feature engineering is to distinguish the different correlations between targeted indicators and various features. Second, model building is to build five typical deep learning models with different characteristics to forecast targeted indicators. Third, model integration is to ensemble the built five models with a tailored, self-adaptive weighting strategy. As such, our approach enjoys all the merits of the five deep learning models (they have different learning structures and temporal constraints to diversify them for ensembling), making it able to comprehensively capture all the characteristics of different indicators to achieve accurate forecasting. To evaluate the proposed approach, we collected the real 880 pieces of data with 39 factors regarding the energy consumption of China ranging from 1999 to 2021. By conducting extensive experiments on the collected datasets, we have identified the optimal features for four targeted indicators (i.e., import of oil, production of oil, import of coal, and production of coal), respectively. Besides, we have demonstrated that our approach is significantly more accurate than the state-of-the-art forecasting competitors.

Capturing complex electricity load patterns: A hybrid deep learning approach with proposed external-convolution attention

Capturing complex electricity load patterns: A hybrid deep learning approach with proposed external-convolution attention

Hybrid Deep Learning and OCR-Based Approach to Real-Time Automatic Number Plate Identification

Hybrid Deep Learning and OCR-Based Approach to Real-Time Automatic Number Plate Identification

Cycle GAN-Based MRI Augmentation and Hybrid Deep Learning Approach (GDP) for Binary Classification of Alzheimer's Disease: Differentiating Normal and Very Mild Dementia

Cycle GAN-Based MRI Augmentation and Hybrid Deep Learning Approach (GDP) for Binary Classification of Alzheimer's Disease: Differentiating Normal and Very Mild Dementia

A Hybrid Deep Learning Approach for Multi-Class Cyberbullying Classification Using Multi-Modal Social Media Data

Cyberbullying involves the use of social media platforms to harm or humiliate people online. Victims may resort to self-harm due to the abuse they experience on these platforms, where users can remain anonymous and spread malicious content. This highlights an urgent need for efficient systems to identify and classify cyberbullying. Many researchers have approached this problem using various methods such as binary and multi-class classification, focusing on text, image, or multi-modal data. While deep learning has advanced cyberbullying detection and classification, the multi-class classification of cyberbullying using multi-modal data, such as memes, remains underexplored. This paper addresses this gap by proposing several multi-modal hybrid deep learning models, such as LSTM+ResNet, LSTM+CNN, LSTM+ViT, GRU+ResNet, GRU+CNN, GRU+ViT, BERT+ResNet, BERT+CNN, BERT+ViT, DistilBERT+ResNet, DistilBERT+CNN, DistilBERT+ViT, RoBERTa+ResNet, RoBERTa+CNN, and RoBERTa+ViT, for classifying multi-classes of cyberbullying. The proposed model incorporates a late fusion process, combining the LSTM, GRU, BERT, DistilBERT, and RoBERTa models for text extraction and the ResNet, CNN, and ViT models for image extraction. These models are trained on two datasets: a private dataset, collected from various social media platforms, and a public dataset, obtained from previously published research. Our experimental results demonstrate that the RoBERTa+ViT model achieves an accuracy of 99.20% and an F1-score of 0.992 on the public dataset, and an accuracy of 96.10% and an F1-score of 0.959 on the private dataset when compared with other hybrid models.

Wearable Sensor-Based Behavioral User Authentication Using a Hybrid Deep Learning Approach with Squeeze-and-Excitation Mechanism

Behavior-based user authentication has arisen as a viable method for strengthening cybersecurity in an age of pervasive wearable and mobile technologies. This research introduces an innovative approach for ongoing user authentication via behavioral biometrics obtained from wearable sensors. We present a hybrid deep learning network called SE-DeepConvNet, which integrates a squeeze-and-excitation (SE) method to proficiently simulate and authenticate user behavior characteristics. Our methodology utilizes data collected by wearable sensors, such as accelerometers, gyroscopes, and magnetometers, to obtain a thorough behavioral appearance. The suggested network design integrates convolutional neural networks for spatial feature extraction, while the SE blocks improve feature identification by flexibly recalibrating channel-wise feature responses. Experiments performed on two datasets, HMOG and USC-HAD, indicate the efficacy of our technique across different tasks. In the HMOG dataset, SE-DeepConvNet attains a minimal equal error rate (EER) of 0.38% and a maximum accuracy of 99.78% for the Read_Walk activity. Our model presents outstanding authentication (0% EER, 100% accuracy) for various walking activities in the USC-HAD dataset, encompassing intricate situations such as ascending and descending stairs. These findings markedly exceed existing deep learning techniques, demonstrating the promise of our technology for secure and inconspicuous continuous authentication in wearable devices. The suggested approach demonstrates the potential for use in individual device security, access management, and ongoing uniqueness verification in sensitive settings.

Real-World Steam Powerplant Boiler Tube Leakage Detection Using Hybrid Deep Learning

The detection of boiler water-wall tube leakage in steam power plants is essential to prevent efficiency loss, unexpected shutdowns, and costly repairs. This study proposes a hybrid deep learning approach that combines convolutional neural networks (CNNs) with a support vector machine (SVM) classifier to allow early and accurate leak detection. The methodology utilizes temperature data from multiple sensors positioned at critical points in the boiler system. The data of each sensor are independently processed by a dedicated CNN model, allowing for the autonomous extraction of sensor-specific features. These features are then fused to create a comprehensive feature representation of the system’s condition, which is analyzed by an SVM classifier to accurately identify leakages. By utilizing the feature extraction capabilities of CNNs and the classification strength of an SVM, this approach effectively identifies subtle operational anomalies that are indicative of potential leaks. The model demonstrates high detection accuracy and minimizes false-positives, providing a robust solution for real-time monitoring and proactive maintenance strategies in industrial systems.

A Hybrid Deep Learning Approach for Enhanced Sentiment Classification and Consistency Analysis in Customer Reviews

Consumer reviews play a pivotal role in shaping purchasing decisions and influencing the reputation of businesses in today’s digital economy. This paper presents a novel hybrid deep learning model, WDE-CNN-LSTM, designed to enhance the sentiment classification of consumer reviews. The model leverages the strengths of Word Embeddings (WDE), Long Short-Term Memory (LSTM) networks, and Convolutional Neural Networks (CNNs) to capture temporal and local text data features. Extensive experiments were conducted across binary, three-class, and five-class classification tasks, with the proposed model achieving an accuracy of 98% for binary classification, 98% for three-class classification, and 95.21% for five-class classifications. The WDE-CNN-LSTM model consistently outperformed standalone CNN, LSTM, and WDE-LSTM models regarding precision, recall, and F1-score, achieving up to 98.26% in F1-score for three-class classification. The consistency analysis also revealed a high alignment between the predicted sentiment and customer ratings, with a consistency rate of 96.00%. These results demonstrate the efficacy of this hybrid architecture in handling complex sentiment classification tasks (SCTs), offering significant improvements in accuracy, classification metrics, and sentiment consistency. The findings have important implications for improving sentiment analysis in customer review systems, contributing to more reliable and accurate sentiment classification.

A semantic segmentation framework with UNet-pyramid for landslide prediction using remote sensing data

Landslides are frequent all over the world, posing serious threats to human life, infrastructure, and economic operations, making them chronic disasters. This study proposes a novel landslide detection methodology that is automated and based on a hybrid deep learning approach. Currently, Deep Learning is constrained by the lack of applicability, lack of data, and low efficiency in landslide detection but with recent advancement in deep learning-based solutions for landslide detection has sparked considerable advantages over traditional techniques. In order to prevent and mitigate disaster, we introduced a hybrid model based on remote sensing technologies such as satellite images. Specifically, the proposed approach consists hybrid U-Net model integrated with a pyramid pooling layer for landslide detection, which uses high-resolution landslide images from the Landslide4Sense dataset. The UNet-Pyramid model has the following modifications: To improve feature acquisition and advancements to strengthen the model’s attention U-Net architecture is integrated with the pyramid pooling layers and OBIA technique. The UNet-Pyramid model was trained and validated using labeled images taken from the Landslide4Sense dataset and the validated set using OBIA to improve its efficacy. The overall Precision, Recall, and F1 Score of the UNet-pyramid model for landslide detection are 91%, 84%, and 87%, respectively.

Forecasting power system flexibility requirements: A hybrid deep-learning approach

The rapid growth of Variable and Renewable Energies (VRE) worldwide poses significant challenges to power systems, particularly in managing rapid changes in load and generation. A critical research gap exists in effectively forecasting Residual Load (RL) to enhance power system flexibility, as existing methods often struggle with the volatility and non-linearities introduced by VRE. This paper addresses this gap by proposing a novel hybrid forecasting framework that integrates Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and a Convolutional Long Short-Term Memory (ConvLSTM-2D) Artificial Neural Network (ANN). This framework is designed to more accurately capture complex patterns in RL data, thereby improving forecast accuracy under high volatility conditions. We apply this methodology to forecast half-hourly RL for 2021 in the French region of Occitanie, achieving an average Mean Absolute Percentage Error (MAPE) of 4.29 %. Our results demonstrate that the proposed framework significantly outperforms existing models, offering consistent accuracy over time and proving highly suitable for practical daily use among energy stakeholders.

Architecture-Aware Augmentation: A Hybrid Deep Learning and Machine Learning Approach for Enhanced Parkinson's Disease Detection.

Parkinson's Disease (PD) is a progressive neurodegenerative disorder affecting millions worldwide. Early detection is crucial for improving patient outcomes. Spiral drawing analysis has emerged as a non-invasive tool to detect early motor impairments associated with PD. This study examines the performance of hybrid deep learning and machine learning models in detecting PD using spiral drawings, with a focus on the impact of data augmentation techniques. We compare the accuracy of Vision Transformer (ViT) with K-Nearest Neighbors (KNN), Convolutional Neural Networks (CNN) with Support Vector Machines (SVM), and Residual Neural Networks (ResNet-50) with Logistic Regression, evaluating their performance on both augmented and non-augmented data. Our findings reveal that ViT with KNN, initially achieving 96.77% accuracy on unaugmented data, experienced a notable decline across all augmentation techniques, suggesting it relies heavily on global patterns in spiral drawings. In contrast, ResNet-50 with Logistic Regression showed consistent improvement with data augmentation, reaching 93.55% accuracy when rotation and flipping techniques were applied. These results highlight that hybrid models respond differently to augmentation, and careful selection of augmentation strategies is necessary for optimizing model performance. Our study provides important insights into the development of reliable diagnostic tools for early PD detection, emphasizing the need for appropriate augmentation techniques in medical image analysis.

Artificial Intelligence-Based Classification of CT Images Using a Hybrid SpinalZFNet.

The kidney is an abdominal organ in the human body that supports filtering excess water and waste from the blood. Kidney diseases generally occur due to changes in certain supplements, medical conditions, obesity, and diet, which causes kidney function and ultimately leads to complications such as chronic kidney disease, kidney failure, and other renal disorders. Combining patient metadata with computed tomography (CT) images is essential to accurately and timely diagnosing such complications. Deep Neural Networks (DNNs) have transformed medical fields by providing high accuracy in complex tasks. However, the high computational cost of these models is a significant challenge, particularly in real-time applications. This paper proposed SpinalZFNet, a hybrid deep learning approach that integrates the architectural strengths of Spinal Network (SpinalNet) with the feature extraction capabilities of Zeiler and Fergus Network (ZFNet) to classify kidney disease accurately using CT images. This unique combination enhanced feature analysis, significantly improving classification accuracy while reducing the computational overhead. At first, the acquired CT images are pre-processed using a median filter, and the pre-processed image is segmented using Efficient Neural Network (ENet). Later, the images are augmented, and different features are extracted from the augmented CT images. The extracted features finally classify the kidney disease into normal, tumor, cyst, and stone using the proposed SpinalZFNet model. The SpinalZFNet outperformed other models, with 99.9% sensitivity, 99.5% specificity, precision 99.6%, 99.8% accuracy, and 99.7% F1-Score in classifying kidney disease.

Hybrid deep learning and machine learning approach for detecting spatial and temporal forgeries in videos

Hybrid deep learning and machine learning approach for detecting spatial and temporal forgeries in videos

Hybrid Deep Learning Approach for Enhanced Detection and Mitigation of DDOS Attack in SDN Networks

The pervasiveness of (DDoS) Distributed Denial of Service attacks has intensified the demand for effective and dependable detection methods in Software-Defined Networks (SDNs). This proposed study introduces a hybrid Deep Learning framework designed to identify and address DDoS attacks in Software-Defined Networking (SDN) contexts. Due to the centralization of SDN control planes, these networks are especially susceptible to DDoS attacks, which can saturate system resources and disrupt critical services. Utilizing the CICDDoS2019 dataset, this research integrates Recurrent Neural Networks (RNN), Deep Belief Networks (DBN), and Adaptive Feature Dimensionality Learning (AFDL) to improve detection accuracy and efficiency. In order to appropriately differentiate between attack and normal traffic, the proposed hybrid model combines both temporal dependencies and feature correlations achieving an accuracy of 99.80%. This research enhances SDN security by offering a scalable and reliable DDoS detection solution capable of adapting to real-time network requirements, addressing the prospective of DL in protecting network infrastructures.

QDCNN-DMN: A hybrid deep learning approach for brain tumor classification using MRI images

Brain Tumor (BT) is the deadliest tumors found globally, which commonly develop in both adults and children. Due to the variety of tumor cells is difficult to categorize a large variety of tumor types, which also leads to more complexity. The key intention of this work is to build and create a useful approach for classifying BT using a hybrid Quantum Dilated Convolutional Neural Network-Deep Maxout Network (QDCNN-DMN). Here, the Magnetic Resonance Imaging (MRI) is used as the input to the image enhancement framework, where it is sharpened using logarithmic transformations. Deep Embedded Clustering (DEC) is used in the skull-stripping process. After that, tumor segmentation is done by the Structure Correcting Adversarial Network (SCAN), and then, the statistical and some other important features are extracted. Subsequently, BT detection and classification are done by the proposed hybrid QDCNN-DMN. The QDCNN-DMN is framed by the incorporation of Quantum Dilated Convolutional Neural Network (QDCNN) and Deep Maxout Network (DMN). It is demonstrated that QDCNN-DMN observed superior specificity, sensitivity, and accuracy with 93.7%, 94.5% and 94.0% based on the Figshare dataset for the BT classification.

Decoding Imagined Speech from EEG Data: A Hybrid Deep Learning Approach to Capturing Spatial and Temporal Features.

Neuroimaging is revolutionizing our ability to investigate the brain's structural and functional properties, enabling us to visualize brain activity during diverse mental processes and actions. One of the most widely used neuroimaging techniques is electroencephalography (EEG), which records electrical activity from the brain using electrodes positioned on the scalp. EEG signals capture both spatial (brain region) and temporal (time-based) data. While a high temporal resolution is achievable with EEG, spatial resolution is comparatively limited. Consequently, capturing both spatial and temporal information from EEG data to recognize mental activities remains challenging. In this paper, we represent spatial and temporal information obtained from EEG signals by transforming EEG data into sequential topographic brain maps. We then apply hybrid deep learning models to capture the spatiotemporal features of the EEG topographic images and classify imagined English words. The hybrid framework utilizes a sequential combination of three-dimensional convolutional neural networks (3DCNNs) and recurrent neural networks (RNNs). The experimental results reveal the effectiveness of the proposed approach, achieving an average accuracy of 77.8% in identifying imagined English speech.

MobileH-Transformer: Enabling real-time leaf disease detection using hybrid deep learning approach for smart agriculture

Agriculture has produced the vast majority of food for the world’s population throughout human history and plays a significant role in the economies of many countries, particularly on the continents of Asia and Africa. However, the quality and quantity of crop yields are influenced by various natural factors, including leaf diseases. While recent studies leveraged advanced deep learning models to accurately detect early disease symptoms, a significant gap remains in adapting these models for resource-constrained devices with limited computational capabilities, such as drones and smartphones. In this paper, we introduce MobileH-Transformer, a novel hybrid model combining convolutional neural networks (CNN) and Transformer architectures for accurate leaf disease detection with minimal computation demands. The proposed model integrates the CNN component with a novel dual convolutional block offering the ability to extract diverse features and reduce the input size for the Transformer component. In addition, it leverages CNN’s local feature extraction and Transformer’s global dependency learning, resulting in better accuracy with less computation resource consumption. The evaluation results on public datasets show that our model achieves competitive F1-score values of 97.20% on the corn leaf disease and 96.80% on the subset of the PlantVillage datasets, surpassing recent studies with only 0.4 Giga Floating Point Operations (GFLOPs) and ensures real-time processing on mobile devices at 30.5 frames per second (FPS).

Directorial Editing: A Hybrid Deep-Learning Approach to Content-Aware Image Retargeting and Resizing

Directorial Editing: A Hybrid Deep-Learning Approach to Content-Aware Image Retargeting and Resizing