Convolutional Neural Network Technique Research Articles

Image processing based on neural networks

This article integrates convolutional neural network (CNN) and graph convolutional network (GCN) techniques. Performance is improved by the suggested architecture's use of crucial methods such as dropout, batch normalization, and rank-based random pooling. The network was trained and tested on a sizable amount of breast lesion imaging data, and its precision was evaluated in comparison to other methods. The findings showed a significant increase in accuracy, resulting in high rates of malignant lesion diagnosis with few false positives. The effective fusion of CNN and GCN methods highlights the potential for improving the detection of malignant breast lesions and provides a viable path for further study in this area.

Multi-Label Classification of Chest X-ray Abnormalities Using Transfer Learning Techniques.

In recent years, deep neural networks have enabled countless innovations in the field of image classification. Encouraged by success in this field, researchers worldwide have demonstrated how to use Convolutional Neural Network techniques in medical imaging problems. In this article, the results were obtained through the use of the EfficientNet in the task of classifying 14 different diseases based on chest X-ray images coming from the NIH (National Institutes of Health) ChestX-ray14 dataset. The approach addresses dataset imbalances by introducing a custom split to ensure fair representation. Binary cross entropy loss is utilized to handle the multi-label difficulty. The model architecture comprises an EfficientNet backbone for feature extraction, succeeded by sequential layers including GlobalAveragePooling, Dense, and BatchNormalization. The main contribution of this paper is a proposed solution that outperforms previous state-of-the-art deep learning models average area under the receiver operating characteristic curve-AUC-ROC (score: 84.28%). The usage of the transfer-learning technique and traditional deep learning engineering techniques was shown to enable us to obtain such results on consumer-class GPUs (graphics processing units).

Automated Computer-Aided Detection and Classification of Intracranial Hemorrhage Using Ensemble Deep Learning Techniques.

Diagnosing Intracranial Hemorrhage (ICH) at an early stage is difficult since it affects the blood vessels in the brain, often resulting in death. We propose an ensemble of Convolutional Neural Networks (CNNs) combining Squeeze and Excitation-based Residual Networks with the next dimension (SE-ResNeXT) and Long Short-Term Memory (LSTM) Networks in order to address this issue. This research work primarily used data from the Radiological Society of North America (RSNA) brain CT hemorrhage challenge dataset and the CQ500 dataset. Preprocessing and data augmentation are performed using the windowing technique in the proposed work. The ICH is then classified using ensembled CNN techniques after being preprocessed, followed by feature extraction in an automatic manner. ICH is classified into the following five types: epidural, intraventricular, subarachnoid, intra-parenchymal, and subdural. A gradient-weighted Class Activation Mapping method (Grad-CAM) is used for identifying the region of interest in an ICH image. A number of performance measures are used to compare the experimental results with various state-of-the-art algorithms. By achieving 99.79% accuracy with an F-score of 0.97, the proposed model proved its efficacy in detecting ICH compared to other deep learning models. The proposed ensembled model can classify epidural, intraventricular, subarachnoid, intra-parenchymal, and subdural hemorrhages with an accuracy of 99.89%, 99.65%, 98%, 99.75%, and 99.88%. Simulation results indicate that the suggested approach can categorize a variety of intracranial bleeding types. By implementing the ensemble deep learning technique using the SE-ResNeXT and LSTM models, we achieved significant classification accuracy and AUC scores.

FlameTransNet: Advancing Forest Flame Segmentation with Fusion and Augmentation Techniques

Forest fires pose severe risks, including habitat loss and air pollution. Accurate forest flame segmentation is vital for effective fire management and protection of ecosystems. It improves detection, response, and understanding of fire behavior. Due to the easy accessibility and rich information content of forest remote sensing images, remote sensing techniques are frequently applied in forest flame segmentation. With the advancement of deep learning, convolutional neural network (CNN) techniques have been widely adopted for forest flame segmentation and have achieved remarkable results. However, forest remote sensing images often have high resolutions, and relative to the entire image, forest flame regions are relatively small, resulting in class imbalance issues. Additionally, mainstream semantic segmentation methods are limited by the receptive field of CNNs, making it challenging to effectively extract global features from the images and leading to poor segmentation performance when relying solely on labeled datasets. To address these issues, we propose a method based on the deeplabV3+ model, incorporating the following design strategies: (1) an adaptive Copy-Paste data augmentation method is introduced to learn from challenging samples (Images that cannot be adequately learned due to class imbalance and other factors) effectively, (2) transformer modules are concatenated and parallelly integrated into the encoder, while a CBAM attention mechanism is added to the decoder to fully extract image features, and (3) a dice loss is introduced to mitigate the class imbalance problem. By conducting validation on our self-constructed dataset, our approach has demonstrated superior performance across multiple metrics compared to current state-of-the-art semantic segmentation methods. Specifically, in terms of IoU (Intersection over Union), Precision, and Recall metrics for the flame category, our method has exhibited notable enhancements of 4.09%, 3.48%, and 1.49%, respectively, when compared to the best-performing UNet model. Moreover, our approach has achieved advancements of 11.03%, 9.10%, and 4.77% in the same aforementioned metrics as compared to the baseline model.

Brain Tumor Classification from MRI Using Image Enhancement and Convolutional Neural Network Techniques.

The independent detection and classification of brain malignancies using magnetic resonance imaging (MRI) can present challenges and the potential for error due to the intricate nature and time-consuming process involved. The complexity of the brain tumor identification process primarily stems from the need for a comprehensive evaluation spanning multiple modules. The advancement of deep learning (DL) has facilitated the emergence of automated medical image processing and diagnostics solutions, thereby offering a potential resolution to this issue. Convolutional neural networks (CNNs) represent a prominent methodology in visual learning and image categorization. The present study introduces a novel methodology integrating image enhancement techniques, specifically, Gaussian-blur-based sharpening and Adaptive Histogram Equalization using CLAHE, with the proposed model. This approach aims to effectively classify different categories of brain tumors, including glioma, meningioma, and pituitary tumor, as well as cases without tumors. The algorithm underwent comprehensive testing using benchmarked data from the published literature, and the results were compared with pre-trained models, including VGG16, ResNet50, VGG19, InceptionV3, and MobileNetV2. The experimental findings of the proposed method demonstrated a noteworthy classification accuracy of 97.84%, a precision success rate of 97.85%, a recall rate of 97.85%, and an F1-score of 97.90%. The results presented in this study showcase the exceptional accuracy of the proposed methodology in accurately classifying the most commonly occurring brain tumor types. The technique exhibited commendable generalization properties, rendering it a valuable asset in medicine for aiding physicians in making precise and proficient brain diagnoses.

Intelligent Fault Diagnosis of Rolling Element Bearings Based on Modified AlexNet.

The reliable and safe operation of industrial systems needs to detect and diagnose bearing faults as early as possible. Intelligent fault diagnostic systems that use deep learning convolutional neural network (CNN) techniques have achieved a great deal of success in recent years. In a traditional CNN, the fully connected layer is located in the final three layers, and such a layer consists of multiple layers that are all connected. However, the fully connected layer of the CNN has the disadvantage of too many training parameters, which makes the model training and testing time longer and incurs overfitting. Additionally, because the working load is constantly changing and noise from the place of operation is unavoidable, the efficiency of intelligent fault diagnosis techniques suffers great reductions. In this research, we propose a novel technique that can effectively solve the problem of traditional CNN and accurately identify the bearing fault. Firstly, the best pre-trained CNN model is identified by considering the classification's success rate for bearing fault diagnosis. Secondly, the selected CNN model is modified to effectively reduce the parameter quantities, overfitting, and calculating time of this model. Finally, the best classifier is identified to make a hybrid model concept to achieve the best performance. It is found that the proposed technique performs well under different load conditions, even in noisy environments, with variable signal-to-noise ratio (SNR) values. Our experimental results confirm that this proposed method is highly reliable and efficient in detecting and classifying bearing faults.

HSI combined with CNN model detection of heavy metal Cu stress levels in apple rootstocks

In recent years, the prolonged application of copper-based fungicides, ripening agents, and fertilizers in agricultural activities has resulted in copper (Cu) levels in the soil exceeding safe levels. Excess Cu has a negative impact on plant growth and crop yields. The practice of grafting horticultural crops onto appropriate rootstocks is frequently employed as a preventive measure against copper accumulation and its associated toxicity. Therefore, the selection of high-quality rootstocks that are not contaminated with heavy metal Cu is important for the growth of grafted crops and the breeding of grafted crops. This study proposed a technique based on convolutional neural network (CNN) and hyperspectral imaging (HSI) for the rapid, non-destructive, and accurate identification of copper contamination levels in apple rootstocks. The effect of different heavy metal Cu contamination levels on leaves was obtained by measuring chlorophyll content in leaves using the ultraviolet spectrophotometer method. A hybrid strategy for spectral variable selection was utilized, involving competitive adaptive reweighted sampling and successive projection algorithms. A traditional partial least squares discriminant analysis linear classification model, and least squares support vector machine, random forest, and extreme learning machine nonlinear models were developed. The results showed that the accuracy of the CNN model and Macro-F1 were 99.6% and 99.2%, respectively, which were better than the traditional linear and nonlinear models. Principal component analysis and t-distributed stochastic neighbor embedding were used for visual analysis to investigate the clustering patterns among sample classes. The results indicated that the combination of CNN and HSI techniques has great potential for classifying copper contamination levels in apple rootstocks.

TRANSFER LEARNING BASED CNN FOR COVID 19

Covid-19 has significantly impacted individuals and health care systems on a global scale. Finding COVID-19 is difficult because there aren't manytesting kits available. A deep transfer learning-based CNN technique is used to recognize Covid 19 in chest CTimages. Chest CT scans from both Covid and non-Covid sources are included in the dataset used to train themodel. Computed tomography (CT) is a faster and more precise means of infection diagnosis when compared to x-ray imaging. This is because CT scan pictures show more potential infection indicators than x-rays, which explains why. X-rays do, however, release less ionizing energy than a CT scan. Deep transfer learning approaches can both train and fine- tune the weights of networks that have previously been trained using datasets, which is why they are effective for this. Inorder to evaluate pictures, deep learning in computer vision especially uses convolutional neural networks (CNNs). For the classification of CT scan pictures to manage the complex structure, deep architecture is needed. We hypothesize that using radiographical fluctuations of covid-19 in CT images, pre-trained deep transfer learning-based CNN models may be able to extract certain graphical properties of covid-19 and provide a clinical diagnosis. The main advantages oftransfer learning include reduced training time, improved neural network performance, and the absence of a large amount of data. Key Words: Covid 19, CNN, ResNet101, Transfer Learning

A lightweight multiscale convolutional neural network for garbage sorting

Waste sorting plays a vital role in establishing a sustainable society by effectively reducing resource waste and promoting its recycling. However, traditional garbage sorting heavily relies on manual labor, which is inefficient, costly, and constrained by limited human resources. To address these challenges, this paper employs the convolutional neural network technique in deep learning for intelligent waste sorting. Firstly, a multi-scale processing strategy is introduced to enhance the system's resilience and accuracy by considering feature information at various scales. Secondly, a lightweight approach using tiny convolutions instead of large convolutions is adopted to reduce model parameters. Combining the advantages of both, we constructed a lightweight multiscale convolution (LMConv) and experiments the Lightweight Multiscale Convolutional Neural Network (LMNet) based on LMConv, and its optimal convolutional architecture is determined through ablation experiments. The experiment results demonstrate that LMNet outperforms other well-known convolutional neural network models in the area of garbage sorting.

Design of automated system for online inspection using the convolutional neural network (CNN) technique in the image processing approach

—Presently, many achievements in various fields such as dyeing, textile or packaging industry have been significantly gained. In this situation, the large scale of products has produced without any efficient inspection methods. It requires workers to detect manually by supervising the hundreds of meters of fabric or nylon. To avoid inconveniences or mistakes by human in manual operation, a novel idea to develop the automated inspection system is mentioned. The main architecture of this system comprises computational mechanics of several components, equipment placement and installation. Owing to the heavy load, two servo motors and chain drive are suggested to integrate in the driving mechanism. In this research, the principal factors to identify defect on surface are advanced techniques of computer vision. Several filters and image processing methods are implemented while the motion of rolls is executing. To validate our works, the real-world platform of proposed approach is entirely fulfilled. Some tests have been applied in this hardware in order to obtain the practical results. From these achievements, it could be obviously proved that our approach is feasible, efficient, and applicable for related industries.

Efficient mixed-type wafer defect pattern recognition using a novel joint attention skipped graph convolutional neural network

For wafer foundries to maintain high yield and quality, errors in manufacturing wafers must be identified and corrected. To find the source of problems and increase overall yield, defect pattern recognition (DPR) is essential. Nevertheless, mixed-type DPR, which includes identifying numerous types of flaws at once, poses more difficulties because of the variety of spatial features, the unpredictability of flaw patterns, and the fluctuating amount of flaws present. So, a novel joint attention skipped graph convolutional neural network (JAS-GCNN) technique is suggested in this paper to analyse the difficulty of mixed-type DPR. The JAS- GCNN effectively captures locally as well as globally interconnections among faults on a wafer by fusing the strength of GCNN along with focused processes. The JAS-GCNN facilitates the learning of complicated fault patterns by allowing information to propagate across multiple layers by utilising skip connections. We do trials on the MixedWM38 WaferMap dataset, which contains a variety of defect types, to assess the proposed technique. The outcomes show that when compared to cutting-edge techniques, the JAS-GCNN performs better. It successfully detects various faults and performs defect classification jobs with high accuracy.

An Augmented Modulated Deep Learning Based Intelligent Predictive Model for Brain Tumor Detection Using GAN Ensemble.

Brain tumor detection in the initial stage is becoming an intricate task for clinicians worldwide. The diagnosis of brain tumor patients is rigorous in the later stages, which is a serious concern. Although there are related pragmatic clinical tools and multiple models based on machine learning (ML) for the effective diagnosis of patients, these models still provide less accuracy and take immense time for patient screening during the diagnosis process. Hence, there is still a need to develop a more precise model for more accurate screening of patients to detect brain tumors in the beginning stages and aid clinicians in diagnosis, making the brain tumor assessment more reliable. In this research, a performance analysis of the impact of different generative adversarial networks (GAN) on the early detection of brain tumors is presented. Based on it, a novel hybrid enhanced predictive convolution neural network (CNN) model using a hybrid GAN ensemble is proposed. Brain tumor image data is augmented using a GAN ensemble, which is fed for classification using a hybrid modulated CNN technique. The outcome is generated through a soft voting approach where the final prediction is based on the GAN, which computes the highest value for different performance metrics. This analysis demonstrated that evaluation with a progressive-growing generative adversarial network (PGGAN) architecture produced the best result. In the analysis, PGGAN outperformed others, computing the accuracy, precision, recall, F1-score, and negative predictive value (NPV) to be 98.85, 98.45%, 97.2%, 98.11%, and 98.09%, respectively. Additionally, a very low latency of 3.4 s is determined with PGGAN. The PGGAN model enhanced the overall performance of the identification of brain cell tissues in real time. Therefore, it may be inferred to suggest that brain tumor detection in patients using PGGAN augmentation with the proposed modulated CNN technique generates the optimum performance using the soft voting approach.

Quantifying the Potential Contribution of Submerged Aquatic Vegetation to Coastal Carbon Capture in a Delta System from Field and Landsat 8/9-Operational Land Imager (OLI) Data with Deep Convolutional Neural Network

Submerged aquatic vegetation (SAV) are highly efficient at carbon sequestration and, despite their relatively small distribution globally, are recognized as a potentially valuable component of climate change mitigation. However, SAV mapping in tidal marshes presents a challenge due to optically complex constituents in the water. The emergence and advancement of deep learning-based techniques in the field of habitat mapping with remote sensing imagery provides an opportunity to address this challenge. In this study, an analytical framework was developed to quantify the carbon sequestration of SAV habitats in the Atchafalaya River Delta Estuary from field and remote sensing observations using deep convolutional neural network (DCNN) techniques. A U-Net-based model, Wetland-SAV Network, was trained to identify the SAV percent cover (high, medium, and low) as well as other estuarine habitat types from Landsat 8/9-OLI data. The areal extent of SAV was up to 8% of the total area (47,000 ha). The habitat areas and habitat-specific carbon fluxes were then used to quantify the net greenhouse gas (GHG) flux of the study area for with/without SAV scenarios in a carbon balance model. The total net GHG flux was in the range of −0.13 ± 0.06 to −0.86 ± 0.37 × 105 tonne CO2e y−1 and increased up to 40% (−0.23 ± 0.10 to −0.90 ± 0.39 × 105 tonne CO2e y−1) when SAV was accounted for within the calculation. At the hectare scale, the inclusion of SAV resulted in an increase of ~60% for the net GHG sink in shallow areas adjacent to the emergent marsh where SAV was abundant. This is the first attempt at remotely mapping SAV in coastal Louisiana as well as a first quantification of net GHG flux at the scale of hectares to thousands of hectares, accounting for SAV within these sub-tropical coastal delta marshes. Remote sensing and deep learning models have high potential for mapping and monitoring SAV in turbid sub-tropical coastal deltas as a component of the increasing accuracy of net GHG flux estimates at small (hectare) and large (coastal basin) scales.

An Efficient Combination of Convolutional Neural Network and LightGBM Algorithm for Lung Cancer Histopathology Classification.

The most dangerous disease in recent decades is lung cancer. The most accurate method of cancer diagnosis, according to research, is through the use of histopathological images that are acquired by a biopsy. Deep learning techniques have achieved success in bioinformatics, particularly medical imaging. In this paper, we present an innovative method for rapidly identifying and classifying histopathology images of lung tissues by combining a newly proposed Convolutional Neural Networks (CNN) model with a few total parameters and the enhanced Light Gradient Boosting Model (LightGBM) classifier. After the images have been pre-processed in this study, the proposed CNN technique is provided for feature extraction. Then, the LightGBM model with multiple threads has been used for lung tissue classification. The simulation result, applied to the LC25000 dataset, demonstrated that the novel technique successfully classifies lung tissue with 99.6% accuracy and sensitivity. Furthermore, the proposed CNN model has achieved the lowest training parameters of only one million parameters, and it has also achieved the shortest processing time of just one second throughout the feature extraction process. When this result is compared with the most recent state-of-the-art approaches, the suggested approach has increased effectiveness in the areas of both disease classification accuracy and processing time.

Addressing Geological Challenges in Mineral Resource Estimation: A Comparative Study of Deep Learning and Traditional Techniques

Spatial prediction of orebody characteristics can often be challenging given the commonly complex geological structure of mineral deposits. For example, a high nugget effect can strongly impact variogram modelling. Geological complexity can be caused by the presence of structural geological discontinuities combined with numerous lithotypes, which may lead to underperformance of grade estimation with traditional kriging. Deep learning algorithms can be a practical alternative in addressing these issues since, in the neural network, calculation of experimental variograms is not necessary and nonlinearity can be captured globally by learning the underlying interrelationships present in the dataset. Five different methods are used to estimate an unsampled 2D dataset. The methods include the machine learning techniques Support Vector Regression (SVR) and Multi-Layer Perceptron (MLP) neural network; the conventional geostatistical methods Simple Kriging (SK) and Nearest Neighbourhood (NN); and a deep learning technique, Convolutional Neural Network (CNN). A comparison of geologic features such as discontinuities, faults, and domain boundaries present in the results from the different methods shows that the CNN technique leads in terms of capturing the inherent geological characteristics of given data and possesses high potential to outperform other techniques for various datasets. The CNN model learns from training images and captures important features of each training image based on thousands of calculations and analyses and has good ability to define the borders of domains and to construct its discontinuities.

A Computer Vision-Based Automatic System for Egg Grading and Defect Detection.

Defective eggs diminish the value of laying hen production, particularly in cage-free systems with a higher incidence of floor eggs. To enhance quality, machine vision and image processing have facilitated the development of automated grading and defect detection systems. Additionally, egg measurement systems utilize weight-sorting for optimal market value. However, few studies have integrated deep learning and machine vision techniques for combined egg classification and weighting. To address this gap, a two-stage model was developed based on real-time multitask detection (RTMDet) and random forest networks to predict egg category and weight. The model uses convolutional neural network (CNN) and regression techniques were used to perform joint egg classification and weighing. RTMDet was used to sort and extract egg features for classification, and a Random Forest algorithm was used to predict egg weight based on the extracted features (major axis and minor axis). The results of the study showed that the best achieved accuracy was 94.8% and best R2 was 96.0%. In addition, the model can be used to automatically exclude non-standard-size eggs and eggs with exterior issues (e.g., calcium deposit, stains, and cracks). This detector is among the first models that perform the joint function of egg-sorting and weighing eggs, and is capable of classifying them into five categories (intact, crack, bloody, floor, and non-standard) and measuring them up to jumbo size. By implementing the findings of this study, the poultry industry can reduce costs and increase productivity, ultimately leading to better-quality products for consumers.

An intelligent network monitoring approach for online classification of Darknet traffic

The Internet plays a crucial role in supporting global applications and businesses, but security remains a major challenge. Within the Internet, there exists a parallel network known as the Darknet, where malicious activities and traffic are present and require real-time classification. Many methods aim to classify this Darknet traffic in real-time due to its significant volume within Internet traffic. However, online Darknet traffic classification faces challenges, particularly in determining the optimal packet sampling amount for achieving a high classification rate in high-performance networks. To address this, our paper presents a novel approach that combines Convolutional Neural Network (CNN) and Reinforcement Learning (RL) techniques for intelligent and adaptive packet sampling rates in high-performance network interfaces. This method reduces overhead on monitored entities, especially in high-speed networks with a high bit rate. Our findings demonstrate a TOR traffic prediction accuracy of 99.84% and successful classification tasks in high-throughput networks using our method.

Resource-Efficient Convolutional Networks: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques

Convolutional neural networks (CNNs) are used in our daily life, including self-driving cars, virtual assistants, social network services, healthcare services, and face recognition, among others. However, deep CNNs demand substantial compute resources during training and inference. The machine learning community has mainly focused on model-level optimizations such as architectural compression of CNNs, whereas the system community has focused on implementation-level optimization. In between, various arithmetic-level optimization techniques have been proposed in the arithmetic community. This article provides a survey on resource-efficient CNN techniques in terms of model-, arithmetic-, and implementation-level techniques, and identifies the research gaps for resource-efficient CNN techniques across the three different level techniques. Our survey clarifies the influence from higher- to lower-level techniques based on our resource efficiency metric definition and discusses the future trend for resource-efficient CNN research.

Classification of Brain Tumours in MRI Images using a Convolutional Neural Network.

Recent advances in deep learning have aided the well-being business in Medical Imaging of numerous disorders like brain tumours, a serious malignancy caused by unregulated and aberrant cell portioning. The most frequent and widely used machine learning algorithm for visual learning and image identification is CNN. In this article, the convolutional neural network (CNN) technique is used. Augmentation of data and processing of images is used to classify scan imagery of brain MRI as malignant or benign. The performance of the proposed CNN model is compared with pre-trained models: VGG-16, ResNet-50, and Inceptionv3 using the technique which is transfer learning. Even though the experiment was conducted on a relatively limited dataset, the experimental results reveal that the suggested scratched CNN model accuracy achieved is 94 percent, VGG-16 was extremely effective and had a very low complexity rate with an accuracy of 90 percent, whereas ResNet- 50 reached 86 percent and Inception v3 obtained 64 percent accuracy. When compared to previous pre-trained models, the suggested model consumes significantly less processing resources and achieves significantly higher accuracy outcomes and reduction in losses.

ECG Heartbeat classification using deep transfer learning with Convolutional Neural Network and STFT technique

Electrocardiogram (ECG) is a simple non-invasive measure to identify heart-related issues such as irregular heartbeats known as arrhythmias. While artificial intelligence and machine learning is being utilized in a wide range of healthcare related applications and datasets, many arrhythmia classifiers using deep learning methods have been proposed in recent years. However, sizes of the available datasets from which to build and assess machine learning models is often very small and the lack of well-annotated public ECG datasets is evident. In this paper, we propose a deep transfer learning framework that is aimed to perform classification on a small size training dataset. The proposed method is to fine-tune a general-purpose image classifier ResNet-18 with MIT-BIH arrhythmia dataset in accordance with the AAMI EC57 standard. This paper further investigates many existing deep learning models that have failed to avoid data leakage against AAMI recommendations. We compare how different data split methods impact the model performance. This comparison study implies that future work in arrhythmia classification should follow the AAMI EC57 standard when using any including MIT-BIH arrhythmia dataset.