Hybrid Convolutional Neural Network Research Articles

Predicting Grapevine Physiological Parameters Using Hyperspectral Remote Sensing Integrated with Hybrid Convolutional Neural Network and Ensemble Stacked Regression

Grapevine rootstocks are gaining importance in viticulture as a strategy to combat abiotic challenges, as well as enhance scion physiology. Direct leaf-level physiological parameters like net assimilation rate, stomatal conductance to water vapor, quantum yield of PSII, and transpiration can illuminate the rootstock effect on scion physiology. However, these measures are time-consuming and limited to leaf-level analysis. This study used different rootstocks to investigate the potential application of aerial hyperspectral imagery in the estimation of canopy level measurements. A statistical framework was developed as an ensemble stacked regression (REGST) that aggregated five different individual machine learning algorithms: Least absolute shrinkage and selection operator (Lasso), Partial least squares regression (PLSR), Ridge regression (RR), Elastic net (ENET), and Principal component regression (PCR) to optimize high-throughput assessment of vine physiology. In addition, a Convolutional Neural Network (CNN) algorithm was integrated into an existing REGST, forming a hybrid CNN-REGST model with the aim of capturing patterns from the hyperspectral signal. Based on the findings, the performance of individual base models exhibited variable prediction accuracies. In most cases, Ridge Regression (RR) demonstrated the lowest test Root Mean Squared Error (RMSE). The ensemble stacked regression model (REGST) outperformed the individual machine learning algorithms with an increase in R2 by (0.03 to 0.1). The performances of CNN-REGST and REGST were similar in estimating the four different traits. Overall, these models were able to explain approximately 55–67% of the variation in the actual ground-truth data. This study suggests that hyperspectral features integrated with powerful AI approaches show great potential in tracing functional traits in grapevines.

ReMAR: a preoperative CT angiography guided metal artifact reduction framework designed for follow-up CTA of endovascular coiling

Objective. Follow-up computed tomography angiography (CTA) is necessary for ensuring occlusion effect of endovascular coiling. However, the implanted metal coil will introduce artifacts that have a negative spillover into radiologic assessment. Method. A framework named ReMAR is proposed in this paper for metal artifacts reduction (MARs) from follow-up CTA of patients with coiled aneurysms. It employs preoperative CTA to provide the prior knowledge of the aneurysm and the expected position of the coil as a guidance thus balances the metal artifacts removal performance and clinical feasibility. The ReMAR is composed of three modules: segmentation, registration and MAR module. The segmentation and registration modules obtain the metal coil knowledge via implementing aneurysms delineation on preoperative CTA and alignment of follow-up CTA. The MAR module consisting of hybrid convolutional neural network- and transformer- architectures is utilized to restore sinogram and remove the artifact from reconstructed image. Both image quality and vessel rendering effect after metal artifacts removal are assessed in order to responding clinical concerns. Main results. A total of 137 patients undergone endovascular coiling have been enrolled in the study: 13 of them have complete diagnosis/follow-up records for end-to-end validation, while the rest lacked of follow-up records are used for model training. Quantitative metrics show ReMAR significantly reduced the metal-artifact burden in follow-up CTA. Qualitative ranks show ReMAR could preserve the morphology of blood vessels during artifact removal as desired by doctors. Significance. The ReMAR could significantly remove the artifacts caused by implanted metal coil in the follow-up CTA. It can be used to enhance the overall image quality and convince CTA an alternative to invasive follow-up in treated intracranial aneurysm.

An optical photothermal infrared investigation of lymph nodal metastases of oral squamous cell carcinoma

In this study, optical photothermal infrared (O-PTIR) spectroscopy combined with machine learning algorithms were used to evaluate 46 tissue cores of surgically resected cervical lymph nodes, some of which harboured oral squamous cell carcinoma nodal metastasis. The ratios obtained between O-PTIR chemical images at 1252 cm−1 and 1285 cm−1 were able to reveal morphological details from tissue samples that are comparable to the information achieved by a pathologist’s interpretation of optical microscopy of haematoxylin and eosin (H&E) stained samples. Additionally, when used as input data for a hybrid convolutional neural network (CNN) and random forest (RF) analyses, these yielded sensitivities, specificities and precision of 98.6 ± 0.3%, 92 ± 4% and 94 ± 5%, respectively, and an area under receiver operator characteristic (AUC) of 94 ± 2%. Our findings show the potential of O-PTIR technology as a tool to study cancer on tissue samples.

Using computational learning for non-melanoma skin cancer and actinic keratosis near-infrared hyperspectral signature classification

BackgroundThe early detection of Non-Melanoma Skin Cancer (NMSC) is essential to ensure patients receive the most effective treatment. Diagnostic screening tools for NMSC are crucial due to high confusion rates with other types of skin lesions, such as Actinic Keratosis. Nevertheless, current means of diagnosing and screening patients rely on either visual criteria, that are often conditioned by subjectivity and experience, or highly invasive, slow, and costly methods, such as histological diagnoses. From this, the objectives of the present study are to test if classification accuracies improve in the Near-Infrared region of the electromagnetic spectrum, as opposed to previous research in shorter wavelengths. MethodsThis study utilizes near-infrared hyperspectral imaging, within the range of 900.6 and 1454.8 nm. Images were captured for a total of 125 patients, including 66 patients with Basal Cell Carcinoma, 42 with cutaneous Squamous Cell Carcinoma, and 17 with Actinic Keratosis, to differentiate between healthy and unhealthy skin lesions. A combination of hybrid convolutional neural networks (for feature extraction) and support vector machine algorithms (as a final activation layer) was employed for analysis. In addition, we test whether transfer learning is feasible from networks trained on shorter wavelengths of the electromagnetic spectrum. ResultsThe implemented method achieved a general accuracy of over 80 %, with some tasks reaching over 90 %. F1 scores were also found to generally be over the optimal threshold of 0.8. The best results were obtained when detecting Actinic Keratosis, however differentiation between the two types of malignant lesions was often noted to be more difficult. These results demonstrate the potential of near-infrared hyperspectral imaging combined with advanced machine learning techniques in distinguishing NMSC from other skin lesions. Transfer learning was unsuccessful in improving the training of these algorithms. ConclusionsWe have shown that the Near-Infrared region of the electromagnetic spectrum is highly useful for the identification and study of non-melanoma type skin lesions. While the results are promising, further research is required to develop more robust algorithms that can minimize the impact of noise in these datasets before clinical application is feasible.

Hybrid deep learning-based traffic congestion control in IoT environment using enhanced arithmetic optimization technique

The Internet of Things (IoT) is essential in several Internet application areas and remains a key technology for communication technologies. Shorter delays in transmission between Roadside Units (RSUs) and vehicles, road safety, and smooth traffic flow are the major difficulties of Intelligent Transportation System (ITS). Machine Learning (ML) was an advanced technique to find hidden insights into ITSs. This article introduces an Improved Arithmetic Optimization with Deep Learning Driven Traffic Congestion Control (IAOADL-TCC) for ITS in Smart Cities. The presented IAOADL-TCC model enables traffic data collection and route traffic on existing routes for avoiding traffic congestion in smart cities. The IAOADL-TCC algorithm exploits a hybrid convolution neural network attention long short-term memory (HCNN-ALSTM) method for traffic congestion control. In addition, an IAOA-based hyperparameter tuning strategy is derived to optimally modify the parameters of the HCNN-ALSTM model. The presented IAOADL-TCC model effectively enhances the flow of traffic and reduces congestion. The experimental validation was performed using the road traffic dataset from the Kaggle repository. The proposed model obtained an average accuracy of 98.03 % with an error rate of 1.97 %. The experimental analysis stated the superior performance of the IAOADL-TCC approach over other DL methods.

Goats on the Move: Evaluating Machine Learning Models for Goat Activity Analysis Using Accelerometer Data.

Putting sensors on the bodies of animals to automate animal activity recognition and gain insight into their behaviors can help improve their living conditions. Although previous hard-coded algorithms failed to classify complex time series obtained from accelerometer data, recent advances in deep learning have improved the task of animal activity recognition for the better. However, a comparative analysis of the generalizing capabilities of various models in combination with different input types has yet to be addressed. This study experimented with two techniques for transforming the segmented accelerometer data to make them more orientation-independent. The methods included calculating the magnitude of the three-axis accelerometer vector and calculating the Discrete Fourier Transform for both sets of three-axis data as the vector magnitude. Three different deep learning models were trained on this data: a Multilayer Perceptron, a Convolutional Neural Network, and an ensemble merging both called a hybrid Convolutional Neural Network. Besides mixed cross-validation, every model and input type combination was assessed on a goat-wise leave-one-out cross-validation set to evaluate its generalizing capability. Using orientation-independent data transformations gave promising results. A hybrid Convolutional Neural Network with L2-norm as the input combined the higher classification accuracy of a Convolutional Neural Network with the lower standard deviation of a Multilayer Perceptron. Most of the misclassifications occurred for behaviors that display similar accelerometer traces and minority classes, which could be improved in future work by assembling larger and more balanced datasets.

Predicting 3D printed plastic part properties: A deep learning approach with thermographic and vibration data fusion

Additive Manufacturing (AM) holds transformative potential for the manufacturing industry, yet its widespread adoption is hindered by inconsistent product properties. This study addresses this challenge by pioneering a novel predictive method to assess the impact of in-process sensing on part property prediction in Fused Deposition Modeling (FDM), serving as a representative case study. Focused on five critical mechanical properties, including surface roughness, tensile strength, elongation at break, micro-hardness, and warpage, we systematically explore various sensor combinations by integrating Inertial Measurement Unit (IMU) sensors and a thermal camera with machine setting parameters. Utilizing deep learning models, specifically hybrid Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM) architectures, we encode time-series sensor data into signal images and evaluate performance across different sensor configurations. Our best-performing model achieves an impressive 99% correlation in predicting tensile strength, albeit with less robust performance in predicting warpage and micro-hardness, suggesting additional influencing factors. Furthermore, the employed signal imaging technique outperforms a handcrafted feature selection alternative. These findings carry significant implications for advancing the broader adoption of AM in critical applications, addressing challenges associated with inconsistent product properties and unlocking its full potential.

A hybrid convolutional neural network for sarcasm detection from multilingual social media posts

A hybrid convolutional neural network for sarcasm detection from multilingual social media posts

Artificial Intelligence-Based Brain Tumor Segmentation Using Adaptive Hybrid CNN and Classification by Multi-Scale Dilated MobileNet with Attention Mechanism for MRI Images

In the medical field, the demanding task is predicting the type of cancer cell, and the analysis to reduce the death rate. MRI technique is used for capturing the brain image because of its high-quality performance and non-ionizing radiation. These collected input images carry only the area of tissues as bright and remove the cerebrospinal fluid to increase the quality of the image. The supervised learning method indicates marvelous performances in solving the problems related to the segmentation and detection of medical images. In the existing model, Convolutional Neural Network (CNN) is used, and the execution of CNN is carried out in different layers. This network consists of different layers that lead to various challenges, such as execution cost and time being high, fetching the wrong input, arising misdiagnosis of the disease. Prediction using different datasets is difficult and creates an overfitting problem, and large memory is needed in the existing method. To overcome this entire issue, an advanced model is developed. Input images collected from online sources are given to the Brain tumor segmentation stage, where the Adaptive Hybrid Convolutional Neural Network (AHCNN) is utilized. Here, the TransResUNet and Fully Convolutional Network (FCN) is utilized to construct the AHCNN for effectively segmenting brain tumors. Here, the parameters are optimized using Flock Member Movement-Based Hybrid Coati with Tomtit Flock Optimization (FMM-HCTFO). The TransResUNet and FCN outcomes are fed to the prediction stage. Here, the brain tumor classification is done using the Multi-scale Dilated Adaptive MobileNet with Attention Mechanism (MSDM-AM) technique. Here, also the parameters are optimized using FMM-HCTFO. Finally, the brain tumor will be classified using the MSDM-AM technique. The achievement of the developed model for the prediction of the brain is increased by tuning the variables using the proposed algorithms.

A novel solar flare forecast model with deep convolution neural network and one-against-rest approach

We present a novel deep Convolutional Neural Network model with one-against-rest approach (OAR-CNN) and modify the hybrid Convolutional Neural Network (H-CNN) model of Zheng et al. (2019) for multiclass flare prediction to forecast whether an active region generates multiclass flare within 24 h. Additionally, in the OAR-CNN and H-CNN models, we employ the decision strategies of majority voting and probability threshold, respectively, comparing the prediction outcomes of these two strategies. Our models undergo training and testing on the same 10 cross-validation datasets as employed by Zheng et al. (2019), and then compare the results with previous studies using forecast verification metrics, with a focus on the true skill statistic (TSS). The major results are summarized as follows. (1) This is the first attempt to utilize the decision strategies of majority voting and probability threshold in the OAR-CNN model for multiclass solar flare prediction. (2) In both the OAR-CNN and H-CNN models, the predictive results with the probability threshold decision strategy are higher than those with majority voting across all six classes (i.e., No-flare, C, M, X, ⩾C, and ⩾M class), except for a slight decrease in the C class in the OAR-CNN model. (3) The OAR-CNN and modified H-CNN models with the probability threshold decision strategy demonstrate comparable statistical scores across all categories and outperform previous studies. (4) In the prediction of four-class flare, our proposed OAR-CNN model with the probability threshold decision strategy achieves relatively high mean TSS scores of 0.744, 0.429, 0.567, and 0.630 for No-flare, C, M, and X class, respectively, surpassing or comparable to results from prior studies. Furthermore, our model achieves high TSS scores of 0.744 ± 0.042 for ⩾C–class and 0.764 ± 0.089 for ⩾M-class predictions.

A hybrid CNN–RNN model for rainfall–runoff modeling in the Potteruvagu watershed of India

AbstractAccurate rainfall‐runoff analysis is essential for water resource management, with artificial intelligence (AI) increasingly used in this and other hydrological areas. The need for precise modelling has driven substantial advancements in recent decades. This study employed six AI models. These were the support vector regression model (SVR), the multilinear regression model (MLR), the extreme gradient boosting model (XGBoost), the long‐short‐term memory (LSTM) model, the convolutional neural network (CNN) model, and the convolutional recurrent neural network (CNN‐RNN) hybrid model. It covered 1998–2006, with 1998–2004 for calibration/training and 2005–2006 for validation/testing. Five metrics were used to measure model performance: coefficient of determination (R2), Nash‐Sutcliffe efficiency (NSE), mean absolute error (MAE), root‐mean square error (RMSE), and RMSE‐observations standard deviation ratio (RSR). The hybrid CNN‐RNN model performed best in both training and testing periods (training: R2 is 0.92, NSE is 0.91, MAE is 10.37 m3s−1, RMSE is 13.13 m3s−1, and RSR is 0.30; testing: R2 is 0.95, NSE is 0.94, MAE is 12.18 m3s−1, RMSE is 15.86 m3s−1, and RSR is 0.25). These results suggest the hybrid CNN‐RNN model is highly effective for rainfall‐runoff analysis in the Potteruvagu watershed.

Enhancing Cataract Detection through Hybrid CNN Approach and Image Quadration: A Solution for Precise Diagnosis and Improved Patient Care

Cataracts, characterized by lens opacity, pose a significant global health concern, leading to blurred vision and potential blindness. Timely detection is crucial, particularly in regions with a shortage of ophthalmologists, where manual diagnosis is time-consuming. While deep learning and convolutional neural networks (CNNs) offer promising solutions, existing models often struggle with diverse datasets. This study introduces a hybrid CNN approach, training on both full retinal fundus images and quadrated parts (i.e., the fundus images divided into four segments). Majority voting is utilized to enhance accuracy, resulting in a superior performance of 97.12%, representing a 1.44% improvement. The hybrid model facilitates early cataract detection, aiding in preventing vision impairment. Integrated into applications, it supports ophthalmologists by providing rapid, cost-efficient predictions. Beyond cataract detection, this research addresses broader computer vision challenges, contributing to various applications. In conclusion, our proposed approach, combining CNNs and image quadration enhances cataract detection’s accuracy, robustness, and generalization. This innovation holds promise for improving patient care and aiding ophthalmologists in precise cataract diagnosis.

Transformer-enhanced two-stream complementary convolutional neural network for hyperspectral image classification

Convolutional neural networks (CNNs) and Transformers have been widely employed in hyperspectral image (HSI) classification, due to their advantages in extracting local-range and global-range features respectively. However, some hybrid CNNs and Transformer-based methods still face some shortcomings in effectively exploiting local-global features in HSI. In this article, a Transformer-enhanced two-stream complementary convolutional neural network is proposed for HSI classification. It mainly comprises the spectral feature extraction stream, spatial feature extraction stream, and a spectral-spatial weight feature complementary module. Firstly, in spectral feature extraction stream, a hybrid convolution block is proposed to extract high-resolution spectral features. And then an attention mechanism, which is based on a Transformer encoder, is used to learn key informative features in spectral channel. The spatial feature extraction stream is designed for spatial feature extraction, and it has a similar architecture to the spectral feature extraction stream. Secondly, a spectral-spatial weight feature complementary module is developed to fully exploit the features which are based on the feature weight in spectral tokens and spatial tokens, they are from spectral and spatial feature extraction streams separately, and then the spectral-spatial tokens with different semantic features are derived. Finally, the spectral-spatial tokens are fed into the linear layer to produce classification outcomes. Furthermore, simplified convolution kernels are employed in our proposed method to decrease the total parameters. Results from experiments on four extensively used HSI datasets highlight the superior performance of our proposed method over other cutting-edge methods.

Disease detection and classification in pomegranate fruit using hybrid convolutional neural network with honey badger optimization algorithm

ABSTRACT Fruit cultivation plays a pivotal role in improvement of the agricultural economy. Pomegranate is a nutritionally rich fruit that is highly valuable because of its excellent antioxidant properties, richness in vitamins and fiber. Pomegranate is affected by diseases, which can severely affect its yield and quality. Timely disease detection is vital for effective disease control in pomegranate orchards. This study presents a novel approach for disease detection in pomegranate and categorization of pomegranate using a hybrid Convolutional Neural Network (CNN) coupled with the Honey Badger Optimization Algorithm (HBOA). The proposed hybrid CNN-HBOA approach leverages the strengths of both CNN and metaheuristic optimization algorithm HBOA. The CNN model was designed to extract high-level features from images of pomegranate affected by various diseases, and HBOA was employed to fine-tune the CNN parameters to improve the accuracy and robustness of the model. Initially, the quality of the images was enhanced using a contrast enhancement technique, and the images were segmented using the Detectron2 algorithm. Finally, the extracted features were fed as input to the disease detection stage wherein the CNN classifies the disease. Furthermore, the classification accuracy of the CNN model was enhanced using the HBOA algorithm. The performance of the hybrid CNN-HBOA algorithm was evaluated using a vast collection of images depicting multiple disease categories of pomegranate. Experimental results demonstrate the superiority of the hybrid CNN-HBOA system, which achieves a detection accuracy of 99.58%, precision of 100%, recall of 99.71% and F1 score of 99.75% compared to other existing state-of-the-art models.

Agricultural innovation through deep learning: a hybrid CNN-Transformer architecture for crop disease classification

ABSTRACT A novel deep learning approach for crop disease classification using a Hybrid Convolutional Neural Network (CNN)-Transformer architecture is proposed. Utilizing the Plant Village, corn/maize leaf, and rice disease image datasets, the preprocessing retains essential features to enhance classification accuracy. The CNN extracts local features, while the Vision Transformer (ViT) captures global contexts by segmenting input images into patches. The Feature Attention Module (FAM) enhances crucial features and captures global aspects. The multilevel feature fusion network integrates these features, converting the fused vector into class probabilities. The proposed crop disease classification model provided a higher classification accuracy of 98.92%.

A hybrid convolutional neural network and support vector machine classifier for Amharic character recognition

A hybrid convolutional neural network and support vector machine classifier for Amharic character recognition

Hybrid CNN-Transformer Network With Circular Feature Interaction for Acute Ischemic Stroke Lesion Segmentation on Non-Contrast CT Scans.

Lesion segmentation is a fundamental step for the diagnosis of acute ischemic stroke (AIS). Non-contrast CT (NCCT) is still a mainstream imaging modality for AIS lesion measurement. However, AIS lesion segmentation on NCCT is challenging due to low contrast, noise and artifacts. To achieve accurate AIS lesion segmentation on NCCT, this study proposes a hybrid convolutional neural network (CNN) and Transformer network with circular feature interaction and bilateral difference learning. It consists of parallel CNN and Transformer encoders, a circular feature interaction module, and a shared CNN decoder with a bilateral difference learning module. A new Transformer block is particularly designed to solve the weak inductive bias problem of the traditional Transformer. To effectively combine features from CNN and Transformer encoders, we first design a multi-level feature aggregation module to combine multi-scale features in each encoder and then propose a novel feature interaction module containing circular CNN-to-Transformer and Transformer-to-CNN interaction blocks. Besides, a bilateral difference learning module is proposed at the bottom level of the decoder to learn the different information between the ischemic and contralateral sides of the brain. The proposed method is evaluated on three AIS datasets: the public AISD, a private dataset and an external dataset. Experimental results show that the proposed method achieves Dices of 61.39% and 46.74% on the AISD and the private dataset, respectively, outperforming 17 state-of-the-art segmentation methods. Besides, volumetric analysis on segmented lesions and external validation results imply that the proposed method is potential to provide support information for AIS diagnosis.

Super-resolution of diffusion-weighted images using space-customized learning model.

Diffusion-weighted imaging (DWI) is a noninvasive method used for investigating the microstructural properties of the brain. However, a tradeoff exists between resolution and scanning time in clinical practice. Super-resolution has been employed to enhance spatial resolution in natural images, but its application on high-dimensional and non-Euclidean DWI remains challenging. This study aimed to develop an end-to-end deep learning network for enhancing the spatial resolution of DWI through post-processing. We proposed a space-customized deep learning approach that leveraged convolutional neural networks (CNNs) for the grid structural domain (x-space) and graph CNNs (GCNNs) for the diffusion gradient domain (q-space). Moreover, we represented the output of CNN as a graph using correlations defined by a Gaussian kernel in q-space to bridge the gap between CNN and GCNN feature formats. Our model was evaluated on the Human Connectome Project, demonstrating the effective improvement of DWI quality using our proposed method. Extended experiments also highlighted its advantages in downstream tasks. The hybrid convolutional neural network exhibited distinct advantages in enhancing the spatial resolution of DWI scans for the feature learning of heterogeneous spatial data.

Uncertainty Quantification With Mixed Data by Hybrid Convolutional Neural Network for Additive Manufacturing

Uncertainty Quantification With Mixed Data by Hybrid Convolutional Neural Network for Additive Manufacturing

Performance Evaluation of Hybrid Machine Learning Algorithms for Online Lending Credit Risk Prediction

ABSTRACT Peer-to-Peer systems are still in the early stages of development when it comes to the processing of credit and the appraisal of the risk associated with it. In this study, we used a hybrid convolutional neural network with logistic regression, a gradient-boosting decision tree, and a k-nearest neighbor to predict the credit risk in a P2P lending club. The lending clubs publicly available P2P loan data was used to train the model. In order to address the issue of data imbalance within the dataset, specifically between the non-defaulter and defaulter classes, the synthetic minority oversampling technique sampling approach is utilized. We developed the architecture of our hybrid model by removing the fully connected layer with the soft-max, which is the final layer of the fully connected CNN model and replaced by LR, GBDT, and k-NN algorithms. The experimental results show that the hybrid CNN-kNN model outperforms the CNN-GBDT and CNN-LR models based on the performance metrics accuracy, recall, F1-score, and area under the curve for both all input and important features. This shows that hybrid machine learning models effectively identify and categorize credit risk in peer-to-peer lending clubs, hence assisting in financial loss prevention.