Hybrid Convolutional Neural Network Research Articles

Medical image segmentation network based on feature filtering with low number of parameters

In recent years, the medical image segmentation method based on hybrid convolutional neural network (CNN) and Vision Transformer (ViT) has made great progress, but it still faces the challenge of unbalanced global and local modeling, and excessive parameters. In addition, ViT repeatedly uses the whole feature map to model the global information, thus generating irrelevant and weakly related information, which will weaken the performance of the model when facing small datasets and segmentation targets. Therefore, this paper proposes a feature screening network based on similarity, named Screening Feature (SF)-MixedNet. Specifically, this paper first proposes a new feature extractor, namely Correlation based Similarity Transformer (CSimFormer). On the basis of parameter pruning, it uses the Screening Feature Multi-head Self Attention (SF-MSA) to establish the remote dependency, and calculates the similarity between local elements through the Location-Sensitive Mechanism (LsM) to obtain the weight matrix. Then, the correlation between regional elements is mined by Region Matching and Selection (RMS) mechanism, and the obtained information is filtered according to the corresponding rules to reduce the side effects of redundant information. Extensive experiments on Synapse dataset, ACDC dataset and SegPC-2021 dataset show that the segmentation accuracy reaches 83.51%, 92.20% and 81.27% respectively. Especially in the Synapse dataset, our method is 6.31% higher than the baseline. The method proposed in this paper effectively improves the segmentation accuracy, provides more detailed information for medical diagnosis and promotes the development of medical artificial intelligence technology.

Quantum classical hybrid convolutional neural networks for breast cancer diagnosis.

The World Health Organization states that early diagnosis is essential to increasing the cure rate for breast cancer, which poses a danger to women's health worldwide. However, the efficacy and cost limitations of conventional diagnostic techniques increase the possibility of misdiagnosis. In this work, we present a quantum hybrid classical convolutional neural network (QCCNN) based breast cancer diagnosis approach with the goal of utilizing quantum computing's high-dimensional data processing power and parallelism to increase diagnosis efficiency and accuracy. When working with large-scale and complicated datasets, classical convolutional neural network (CNN) and other machine learning techniques generally demand a large amount of computational resources and time. Their restricted capacity for generalization makes it challenging to maintain consistent performance across multiple data sets. To address these issues, this paper adds a quantum convolutional layer to the classical convolutional neural network to take advantage of quantum computing to improve learning efficiency and processing speed. Simulation experiments on three breast cancer datasets, GBSG, SEER and WDBC, validate the robustness and generalization of QCCNN and significantly outperform CNN and logistic regression models in classification accuracy. This study not only provides a novel method for breast cancer diagnosis but also achieves a breakthrough in breast cancer diagnosis and promotes the development of medical diagnostic technology.

Transformer-Integrated Hybrid Convolutional Neural Network for Dose Prediction in Nasopharyngeal Carcinoma Radiotherapy.

Radiotherapy is recognized as the major treatment of nasopharyngeal carcinoma. Rapid and accurate dose prediction can improve the efficiency of the treatment planning process and the quality of radiotherapy plans. Currently, deep learning-based methods have been widely applied to dose prediction for radiotherapy treatment planning. However, it is important to note that existing models based on Convolutional Neural Networks (CNN) often overlook long-distance information. Although some studies try to use Transformer to solve the problem, it lacks the ability of CNN to process the spatial information inherent in images. Therefore, we propose a novel CNN and Transformer hybrid dose prediction model. To enhance the transmission ability of features between CNN and Transformer, we design a hierarchical dense recurrent encoder with a channel attention mechanism. Additionally, we propose a progressive decoder that preserves richer texture information through layer-wise reconstruction of high-dimensional feature maps. The proposed model also introduces object-driven skip connections, which facilitate the flow of information between the encoder and decoder. Experiments are conducted on in-house datasets, and the results show that the proposed model is superior to baseline methods in most dosimetric criteria. In addition, the image analysis metrics including PSNR, SSIM, and NRMSE demonstrate that the proposed model is consistent with ground truth and produces promising visual effects compared to other advanced methods. The proposed method could be taken as a powerful clinical guidance tool for physicists, significantly enhancing the efficiency of radiotherapy planning. The source code is available at https://github.com/CDUTJ102/THCN-Net .

Exploring Recent NLP Advances for Tamil: Word Vectors and Hybrid Deep Learning Architectures

The advancements of deep learning methods and the availability of large corpora and data sets have led to an exponential increase in the performance of Natural Language Processing (NLP) methods resulting in successful NLP applications for various day-to-day tasks such as Language translation, Voice to text, Grammar checking, Sentiment analysis, etc. These advancements enabled the well-resourced languages to adapt themselves to the digital era while the gap for the low-resource languages widened. This research work explores the suitability of the recent advancements in NLP for Tamil, a low-resource language spoken mainly in South India, Sri Lanka, and Malaysia. From the literature survey, it has been found that there is a lack of comprehensive study on the effect of the recent advancements of NLP for the Tamil text. To fill this gap, this research work analysed the performance of deep learning based text representation and classification approaches namely word embedding, Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) for Tamil text classification tasks. Different dimensional pretrained word2Vec and FastText word vectors were built for Tamil and their effectiveness on Text classification was evaluated. The study found that the pre-trained 300- dimensional FastText word vector showed better performance than other pre-trained word vectors for Tamil text classification. Further, in this study, four simple hybrid CNN and Bi-GRU models were proposed for Tamil text classification and their performances were evaluated. The study found that hybrid CNN and Bi-GRU models perform better compared to the classical machine learning models, individual CNN and RNN models, and the Multilingual BERT model. These results confirm that the jointly learned embeddings with different deep learning architectures like CNN and RNN can achieve remarkable results for Tamil text classification, thus ensuring that the deep learning approaches can be successful for NLP on Tamil text.

Optimizing Plant Disease Classification with Hybrid Convolutional Neural Network–Recurrent Neural Network and Liquid Time-Constant Network

This paper addresses the practical challenge of detecting tomato plant diseases using a hybrid lightweight model that combines a Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). Traditional image classification models demand substantial computational resources, limiting their practicality. This study aimed to develop a model that can be easily implemented on low-cost IoT devices while maintaining high accuracy with real-world images. The methodology leverages a CNN for extracting high-level image features and an RNN for capturing temporal relationships, thereby enhancing model performance. The proposed model incorporates a Closed-form Continuous-time Neural Network, a lightweight variant of liquid time-constant networks, and integrates Neural Circuit Policy to capture long-term dependencies in image patterns, reducing overfitting. Augmentation techniques such as random rotation and brightness adjustments were applied to the training data to improve generalization. The results demonstrate that the hybrid models outperform their single pre-trained CNN counterparts in both accuracy and computational cost, achieving a 97.15% accuracy on the test set with the proposed model, compared to around 94% for state-of-the-art pre-trained models. This study provides evidence of the effectiveness of hybrid CNN-RNN models in improving accuracy without increasing computational cost and highlights the potential of liquid neural networks in such applications.

A method for measuring carbon emissions from power plants using a CNN-LSTM-Attention model with Bayesian optimization

Accurate measurement of CO2 emissions from coal-fired power plants is crucial for achieving China's “carbon neutrality” goal; however, traditional CO2 emission measurement methods have several limitations, and emerging prediction models rarely utilize real-time monitoring data from power plants at the micro level. To address these challenges, this study presents a novel hybrid convolutional neural network with long short-term memory (CNN-LSTM)-Attention model, leveraging real-time monitoring data to enhance the accuracy of CO2 emission predictions. The proposed model employs a hybrid architecture that leverages the strength of CNN, LSTM, and Attention mechanism. To address the challenges of multiple hyperparameters and difficult selection, the Bayesian optimization algorithm is used to optimize the hyperparameters ensuring optimal performance. Using historical operational data from a 660 MW generator set in Hubei province, the proposed model was evaluated and validated horizontally by using three evaluation metrics. Additionally, the vertical evaluation and validation of the proposed model were done using the operational data from other months. The results indicate that the proposed model achieved the highest performance across every evaluation index for predicting CO2 emissions from coalfired power plants, and the prediction accuracy of the CO2 emission in the future months is also guaranteed.

On-line recognition of mixture control chart patterns using hybrid CNN and LSTM for auto-correlated processes

Statistical process control (SPC), designed to detect and identify process disturbances, is an effective quality control method for ensuring process stability. Owing to the growing automation of the industry, the manufacturing process can be autocorrelated. Engineer process control (EPC) is typically used to address autocorrelation. However, process disturbances can be offset by feedback compensation, making control chart patterns (CCPs) difficult to identify. Most studies on control chart pattern recognition (CCPR) techniques are based on a single abnormal control chart pattern (CCP). However, a mixture of CCPs can occur during real-world manufacturing processes. With the development of intelligent manufacturing systems, early detection of abnormal concurrent CCPs has become an important issue. In this study, a hybrid model combining a convolutional neural network (CNN) and long short-term memory (LSTM) in an online detection system was used to recognize the concurrent CCPR problem in SPC-EPC processes. The results showed that the average accuracy of the deep learning CNN-LSTM method was 99.83%, which was significantly better than that of the machine learning method. In addition, the running time of the CNN-LSTM model was shortened. In a comparison of online monitoring between the deep learning method and the machine learning method, the CNN-LSTM model for an online monitoring system identified abnormal concurrent patterns faster. Therefore, the proposed CNN-LSTM online monitoring scheme can be applied confidently and successfully to identify mixture CCPs in an SPC-EPC process.

Enhancing the Recognition of Handwritten Arabic Characters through Hybrid Convolutional and Bidirectional Recurrent Neural Network Models

Handwritten Arabic character recognition remains a challenging task in pattern recognition due to the inherent complexities of the cursive script and visual similarities between characters. While deep learning techniques have demonstrated promising results in this domain, further enhancements to the model architecture can drive even greater performance improvements. This study introduces a hybrid deep learning approach that combines Convolutional Neural Networks (CNNs) with Bidirectional Recurrent Neural Networks, specifically Bidirectional Long Short-Term Memory (Bi-LSTM) and Bidirectional Gated Recurrent Units (Bi-GRU). By leveraging the strengths of both convolutional and recurrent neural network components, the proposed models are able to effectively capture spatial features as well as model the temporal dynamics and contextual relationships present in handwritten Arabic text. Experiments conducted on the AHCD and Hijjaa benchmark datasets show that the CNN-Bi-GRU framework achieved state-of-the-art accuracy rates of 97.05% and 91.78% respectively, outperforming previous deep learning-based methods. These results demonstrate the significant performance gains that can be achieved by integrating specialized temporal modeling and contextual representation capabilities into the handwriting recognition pipeline, without the need for explicit segmentation. The findings of this research represent a crucial advancement in the continued development of sophisticated and precise deep learning systems for Arabic handwriting recognition, with broad applications across domains that rely on efficient text extraction from handwritten documents.

IOT BASED ECG: HYBRID CNN-BILSTM APPROACH FOR MYOCARDIAL INFARCTION CLASSIFICATION

Cardiovascular disease such as ischemic heart disease and stroke are the most dangerous diseases in the WHO stats. Myocardial Infarction (MI), an ischemic disease of the heart, occurs due to a sudden blockage in the coronary arteries that supply blood to the heart causing a lack of oxygen and nutrients. The MI patient needs continuous monitoring using electrocardiography, the latter is always at risk of developing complications such as arrhythmias. As a solution, we proposed an internet of things (IoT) based ECG system for monitoring, the application layer was reserved for the detection of MI and arrhythmias using artificial intelligence so that the patients can keep being monitored even outside health facilities. For this purpose, this paper proposed a hybrid Convolutional Neural Network (CNN) – Bidirectional Long Short-Term Memory (BiLSTM) approach to classify ECG signals and evaluates its performance by using raw and preprocessed data, and comparing the results to related studies. Two datasets have been used in this classification. The results were promising, the model has scored 99.00% accuracy on raw data classifying 4 classes, and 99.73% accuracy on a larger preprocessed data for 3 classes classification. The proposed model is suitable to serve in our monitoring task.

Toward identity preserving in face sketch-photo synthesis using a hybrid CNN-Mamba framework

The synthesis of facial sketch-photo has important applications in practical life, such as crime investigation. Many convolutional neural networks (CNNs) based methods have been proposed to address this issue. However, due to the substantial modal differences between sketch and photo, the CNN’s insensitivity to global information, and insufficient utilization of hierarchical features, synthesized photos struggle to balance both identity preservation and image quality. Recently, State Space Sequence Models (SSMs) have achieved exciting results in computer vision (CV) tasks. Inspired by SSMs, we design a hybrid CNN–SSM model called FaceMamba for the Face Sketch-Photo Synthesis (FSPS) task. It includes an original Face Vision Mamba Attention for modeling in latent space using SSM. Additionally, it incorporates a general auxiliary method called Attention Feature Injection that combines encoding features, decoding features, and external auxiliary features using attention mechanisms. FaceMamba combines Mamba’s modeling ability for long-range dependencies with CNN’s powerful local feature extraction ability, and utilizes hierarchical features at the appropriate position. Adequate experimental and evaluation results reveal that FaceMamba has strong competitiveness in FSPS task, achieving the best balance between identity preservation and image quality.

Deep Learning Methods for Chest X-Ray Imaging-Based COVID-19 Pneumonia Detection

The COVID-19 pandemic currently underway has highlighted a need for fast and accurate screening tools to help identify the disease, particularly in resource-poor settings. In this paper, a deep convolutional neural network (CNN) model is proposed for the automatic detection of COVID-19 pneumonia using chest X-ray images that helps in reducing the cost and processing time compared to traditional testing procedures. It uses several deep-structured medical image data types and improvement of the deep learning model architecture to achieve good diagnostic accuracy. Our hybrid CNN architecture integrates VGG-16 for feature extraction and ResNet-50 for pattern complexity assessment in detecting fine changes characteristic of COVID-19 pneumonia. Our dataset for this study is a collection of few thousands labelled chest X-ray images categorized in three classes, which are COVID-19, viral pneumonia and healthy cases. More advanced data preprocessing methods such as normalized, augmentation, and filtered noise has also been carried out which enhances in the model performance. We have high accuracy, recall, and good F1-score in the experimental results proving model robustness are applicable in real-world clinical scenarios. These research results speak to the importance of AI for improving diagnosis workflows, especially in fast-to-deploy large scale scenarios needed during a pandemic to cope with healthcare burdens.

Hybrid Deep Learning Model for Traffic Flow and Speed Forecasting at Urban Junction

The hybrid deep learning model H-CNN-LSTM (Hybrid Convolution Neural Network and Long Short-Term Memory) is introduced in this paper. The model combines CNN to extract traffic flow and speed features, LSTM networks to model temporal dependencies, and employs a combined matrix and a rolling forward input method during data input, enhancing the coarse-grained extraction of traffic data and further refining the utilization of adjacent data. Our research focuses on the complex dynamic traffic conditions of Fuli East Road in Xigu District, Lanzhou City of China. Using detailed traffic video data collected during one month of evening rush hours, we predict future traffic using the H-CNN-LSTM model. By comparing it with other prediction methods, we validate the effectiveness of our approach in predicting traffic flow and speed in real-world traffic scenarios

Dual-stage machine learning approach for advanced malicious node detection in WSNs

Within wireless sensor networks (WSNs), a multitude of vulnerabilities can arise, particularly those originating from malicious nodes (MNs), which lead to compromised data integrity, network stability, and critical application reliability. Although security and energy efficiency remain critical, current MN detection methods are resource-intensive and time-consuming, rendering them unsuitable for constrained WSNs. Although machine learning-based methods excel at detecting MNs, they often incur significant time overhead owing to extensive data transmission and coordination, leading to increased latency and energy consumption within the network. This study introduces DSMND, a novel dual-stage MN detection scheme that harnesses machine learning to enhance MN identification in WSNs. The initial stage uses dynamic threshold detection and decision-tree algorithms at the cluster head (CH) level. This adaptive detection process optimizes CH resource levels, feature counts, and threshold values for efficient MN identification. When thresholds are exceeded, the second stage activates on the server side, employing an advanced MN detection model that seamlessly integrates a hybrid convolutional neural network and a random forest classifier to boost detection accuracy. Leveraging SensorNetGuard, a dataset with diverse node and network features, further enhances reliability. Extensive analysis shows that our scheme achieves up to 99.5 % detection accuracy at the CH level and nearly 100 % at the server side. The average execution time is 124.63 ms, making it 97 % faster than conventional methods. Additionally, DSMND reduces CH power consumption by up to 70 % and extends network lifetime by 2.7 times compared to existing methods. These results confirm the effectiveness of our approach for real-time detection and mitigation of MNs within WSNs.

Hybrid convolutional neural networks in human resource recommendation

The study proposes a new algorithm combining a gradient boosting tree algorithm with a hybrid convolutional neural network in order to design a better human resource recommendation algorithm to solve the problem of employment difficulties and recruitment difficulties. The algorithm combines the excellent feature transformation ability of gradient boosting trees with the excellent classification ability of hybrid convolutional neural networks, complementing the shortcomings of each of the two algorithms. The outcomes showed that the algorithm performed best with the learning rate set to 0.3 and the maximum tree depth set to 3. The algorithm now has the lowest loss percentage and highest F1-Score value. The maximum-median hybrid pooling approach used in the study had considerable improvements over the algorithm’s pooling strategy (PS), and it had the greatest recall and F1-Score values of all pooling strategies (0.8108 and 0.7418, respectively). The new algorithm outperformed the gradient boosting tree algorithm and the hybrid convolutional neural network algorithm in terms of recall and F1-Score values, and regardless of the length of the job recommendation, the recall and F1-Score values of the new algorithm were consistently higher than those of the old algorithm. The recall and F1-Score values of the new algorithm, with a job recommendation length of 70, were 0.8198 and 0.7432, respectively, both greater than those of the other algorithms, according to a comparison of it with other conventional HR recommendation algorithms. The study’s newly created algorithm increases the efficacy and precision of HR suggestions.

A study on improving drug–drug interactions prediction using convolutional neural networks

Appropriate studies on drug–drug interactions (DDIs) can evade possible adverse side effects due to the ingestion of multiple drugs. This paper proposes a novel framework called Similarity Network Fusion and Hybrid Convolutional Neural Network (SNF–HCNN) to predict the DDIs better. The proposed framework leverages data from DrugBank, PubChem, and SIDER. Seven critical drug features are extracted: Target, Transporter, Enzymes, Chemical substructure, Carrier, Offside, and Side effects. The Jaccard Similarity measure evaluates the similarity of drug features to construct a comprehensive similarity matrix that effectively captures potential drug relationships and patterns. The similarity selection process identifies the most relevant features, reduces redundancy, and enhances identifying potential drug interactions. Integrating Similarity Network Fusion (SNF) with the selected similarity matrix ensures a comprehensive representation of drug features and leads to superior accuracy compared to conventional methods. Our experimental results demonstrate the effectiveness of the proposed hybrid convolutional neural network (HCNN) architectures, such as CNN+LR (CNN+Logistic Regression), CNN+RF (CNN+Random Forest), and CNN+SVM (CNN+Support Vector Machine), showing impressive accuracies of 95.19%, 94.45%, and 93.65%, respectively. Moreover, CNN+LR outperforms other approaches regarding precision, sensitivity, F1-score, and AUC score, which implicate better outcomes for ensuring medication safety aspects in clinical settings in the future.

Patient Health Monitoring Using Fibrillation Detection in Electrocardiogram Signal

Fibrillation (Fib) is the most well-known sort of sporadic heartbeat. The sporadic termination of electrical impulses causes the atria (the top chambers in the heart) to tremble (or fibrillate). Cardiovascular arrhythmias happen in older people with coronary disease. Now and again, individuals with Fib have no manifestations, and their condition is just recognizable upon actual assessment. The issues include inconsistent heartbeats when the heart is reliably in a sporadic mood, as anticipated through the patient well-being observation framework (PHMS). The PHMS proposed calculation is ready to anticipate the inconsistent pulses by the location of the R top in electrocardiogram signals (ECG) and the unpredictable beat anticipated by utilizing the P wave along with the QRS complex with the T wave for one heart cycle. Hence, this paper proposes a hybrid Convolutional Neural Network (CNN) and Recurrent Neural Networks (RNN), termed hybrid C-RNN, to proceed with the characterization and determination of the arrhythmic beats. This work also analyzes the QRS peak variations, followed by classification. The practicability of the heartbeat characterization utilizing hybrid C-RNN is completed by metrics like accuracy, sensitivity, and specificity. The proposed model achieved an accuracy of 98.57%, sensitivity of 1%, and specificity of 9.565217e-01%. This is compared best with some existing approaches in the result section.

Next step for bitcoin: Confluence of technical indicators and machine learning

Cryptocurrencies are quickly becoming a key tool in investment decisions. The volatile nature of bitcoin prices has spurred the demand for robust predictive models. The primary objective of this study is to evaluate and compare the effectiveness of different machine learning models with the combination of technical indicators in predicting bitcoin prices. The study used 27 critical technical indicators to evaluate four machine learning techniques, namely Artificial Neural Network (ANN), a Hybrid Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM), Support Vector Machine (SVM), and Random Forest. The results showed that ANN and SVM achieve a significant prediction accuracy of 81% and 82%, respectively, which is higher than the results of traditional models such as standard ARIMA. In practical applications, these methods often improve prediction accuracy by 20-30% over traditional models. The novelty of the analysis lies in the use of temporal and spatial trends via momentum, ROC, and %K features, making for a holistic approach to cryptocurrency market forecasting. This study underscores the critical importance of specific technical indicators and the imperative role of data mining in revolutionizing cryptocurrency market navigation. The research results highlight opportunities to improve investment strategies and risk management policies in the bitcoin market using machine learning models, making the latter valuable to investors and financial experts.

A Hybrid Convolutional Neural Network Model for the Classification of Multi‐Class Skin Cancer

ABSTRACTSkin cancer is a significant public health issue, making accurate and early diagnosis crucial. This study proposes a novel and efficient hybrid deep‐learning model for accurate skin cancer diagnosis. The model first employs DeepLabV3+ for precise segmentation of skin lesions in dermoscopic images. Feature extraction is then carried out using three pretrained models: MobileNetV2, EfficientNetB0, and DenseNet201 to ensure balanced performance and robust feature learning. These extracted features are then concatenated, and the ReliefF algorithm is employed to select the most relevant features. Finally, obtained features are classified into eight categories: actinic keratosis, basal cell carcinoma, benign keratosis, dermatofibroma, melanoma, melanocytic nevus, squamous cell carcinoma, and vascular lesion using the kNN algorithm. The proposed model achieves an F1 score of 93.49% and an accuracy of 94.42% on the ISIC‐2019 dataset, surpassing the best individual model, EfficientNetB0, by 1.20%. Furthermore, the evaluation of the PH2 dataset yielded an F1 score of 94.43% and an accuracy of 94.44%, confirming its generalizability. These findings signify the potential of the proposed model as an expedient, accurate, and valuable tool for early skin cancer detection. They also indicate combining different CNN models achieves superior results over the results obtained from individual models.

Hybrid convolutional neural network optimized with an artificial algae algorithm for glaucoma screening using fundus images.

We developed an optimized decision support system for retinal fundus image-based glaucoma screening. We combined computer vision algorithms with a convolutional network for fundus images and applied a faster region-based convolutional neural network (FRCNN) and artificial algae algorithm with support vector machine (AAASVM) classifiers. Optic boundary detection, optic cup, and optic disc segmentations were conducted using TernausNet. Glaucoma screening was performed using the optimized FRCNN. The Softmax layer was replaced with an SVM classifier layer and optimized with an AAA to attain enhanced accuracy. Using three retinal fundus image datasets (G1020, digital retinal images vessel extraction, and high-resolution fundus), we obtained accuracy of 95.11%, 92.87%, and 93.7%, respectively. Framework accuracy was amplified with an adaptive gradient algorithm optimizer FRCNN (AFRCNN), which achieved average accuracy 94.06%, sensitivity 93.353%, and specificity 94.706%. AAASVM obtained average accuracy of 96.52%, which was 3% ahead of the FRCNN classifier. These classifiers had areas under the curve of 0.9, 0.85, and 0.87, respectively. Based on statistical Friedman evaluation, AAASVM was the best glaucoma screening model. Segmented and classified images can be directed to the health care system to assess patients' progress. This computer-aided decision support system will be useful for optometrists.

A Hybrid Convolutional and Graph Neural Network for Human Action Detection in Static Images

A Hybrid Convolutional and Graph Neural Network for Human Action Detection in Static Images