Convolutional Neural Network Classifier Research Articles

Automated Description Generation of Cytologic Findings for Lung Cytological Images Using a Pretrained Vision Model and Dual Text Decoders: Preliminary Study.

Cytology plays a crucial role in lung cancer diagnosis. Pulmonary cytology involves cell morphological characterisation in the specimen and reporting the corresponding findings, which are extremely burdensome tasks. In this study, we propose a technique to generate cytologic findings from for cytologic images to assist in the reporting of pulmonary cytology. For this study, 801 patch images were retrieved using cytology specimens collected from 206 patients; the findings were assigned to each image as a dataset for generating cytologic findings. The proposed method consists of a vision model and dual text decoders. In the former, a convolutional neural network (CNN) is used to classify a given image as benign or malignant, and the features related to the image are extracted from the intermediate layer. Independent text decoders for benign and malignant cells are prepared for text generation, and the text decoder switches according to the CNN classification results. The text decoder is configured using a transformer that uses the features obtained from the CNN for generating findings. The sensitivity and specificity were 100% and 96.4%, respectively, for automated benign and malignant case classification, and the saliency map indicated characteristic benign and malignant areas. The grammar and style of the generated texts were confirmed correct, achieving a BLEU-4 score of 0.828, reflecting high degree of agreement with the gold standard, outperforming existing LLM-based image-captioning methods and single-text-decoder ablation model. Experimental results indicate that the proposed method is useful for pulmonary cytology classification and generation of cytologic findings.

Efficacies of the CNN Algorithm in Predicting Lung Cancer

Lung cancer is the leading cause of cancer-related death in the 21st century, and is highly expected to remain so in the future ages. It is possible to diagnose and treat the lung cancer if the proper symptoms of the diseases are detected in the early phases. A convolutional neural network (CNN)-based machine learning model is a recently emerged network design that has been functionalizing since the last decade mainly to optimize the detection processes of the lung cancer in the pre-collected medical examinations and the closely associated lung cancer datasets. Through the CNN classifier, the lung cancer patients are majorly classified based on their symptoms while the Python programming script drives the detection schemes as a whole through the effective implementation of the entire model. In fact, the CNN model enables the medical practitioners and hospital professionals to build the sustainable prototype mechanisms for the effective treatment of the lung cancer via the computational intelligence without any negative impacts on the societal environment. As it can reduce the amount of wasted resources and the amount of work required to complete the manual diagnosis tasks, the lung cancer patients can get the real-time treatment in a cost-effective manner with the minimal effort and latency from any location at any time. In this article, we overviews the performances of the CNN model designed by us, and assess its accuracy regimes in detecting the cancerous and noncancerous Lung cells. We believe that our model could mark the future prototype medical diagnosis scheme for the efficient lung cancer cells investigations, their progressive growing stages, and the timely assessments of the medical treatments.

Mode recognition in a kerosene-fueled scramjet combustor by a Swin Transformer neural network

Recognizing the combustion mode in scramjet engines is critical for suppressing oscillations and stabilizing the combustion process in hypersonic aircrafts. Current accesses mainly depend on mechanical measurement and dominant frequencies based on image analysis methods, such as proper orthogonal decomposition and dynamic mode decomposition. However, these traditional methods either lack of precision or fall short of the need for prior knowledge, poor generalization, and low efficiency, posing challenges in practical implementations, especially when online controlling is highlighted in the scramjet combustions. Recently, machine learning (ML) has been introduced to the combustion community due to its superiority in high flexibility and efficiency in addressing complex problems. The classical convolutional neural network (CNN) architectures have been reported to achieve efficient combustion mode recognition in furnace combustion, swirling combustor, and rotating detonation engines. However, those CNN-based models are incapable of utilizing the global flame features and the coherences of local areas, resulting in insufficient accuracy and robustness in scramjet combustions with high inflow speed and distinct mode variations. To address this problem, this paper reports a Swin (shifted window) Transformer model, an advanced ML structure outstanding in capturing both global and local features by its self-attention mechanism with high computational efficiency, to identify combustion modes in scramjet engines. The Swin-T was trained and validated in a kerosene-fueled cavity-based scramjet combustor, and results show that it can achieve a considerable accuracy of 95.28%. Comparisons with CNN-based models further indicate that Swin-T outperforms in accuracy, efficiency, and robustness by around 0.7%, 80%, and 3%, respectively.

Two-step convolutional neural network classification of plant disease

Two-step convolutional neural network classification of plant disease

Optimizing Skin Cancer Diagnosis: A Modified Ensemble Convolutional Neural Network for Classification.

Skin cancer is recognized as one of the most harmful cancers worldwide. Early detection of this cancer is an effective measure for treating the disease efficiently. Traditional skin cancer detection methods face scalability challenges and overfitting issues. To address these complexities, this study proposes a random cat swarm optimization (CSO)with an ensemble convolutional neural network (RCS-ECNN) method to categorize the different stages of skin cancer. In this study, two deep learning classifiers, deep neural network (DNN) and Keras DNN (KDNN), are utilized to identify the stages of skin cancer. In this method, an effective preprocessing phase is presented to simplify the classification process. The optimal features are selected using the feature extraction phase. Then, the GrabCut algorithm is employed to carry out the segmentation process. Also, the CSO is employed to enhance the effectiveness of the method. The HAM10000 and ISIC datasets are utilized to evaluate the RCS-ECNN method. The RCS-ECNN method achieved an accuracy of 99.56%, a recall of 99.66%, a specificity value of 99.254%, a precision value of 99.18%, and an F1-score value of 98.545%, respectively. The experimental results demonstrated that the RCS-ECNN method outperforms the existing techniques.

Chaotic gradient based optimization with fuzzy temporal optimized CNN for heart failure prediction

Heart failure is a leading cause of premature death, especially among individuals with a sedentary lifestyle. Early and accurate detection is essential to prevent the progression of this situation. However, many existing prediction systems failed to detect early and accurately, also taking more time to detect. To address these issues, we propose an advanced heart failure detection model that combines one-dimensional chaotic maps and a Gradient-Based Optimizer (GBO) called Chaotic Gradient-Based Optimizer (CGBO). This approach improves feature selection by effectively selecting the most crucial features related to the risk of heart failure. Additionally, we introduce the Fuzzy Temporal Optimized Convolutional Neural Network (FTOCNN) classifier that incorporates CGBO and fuzzy temporal rules to enhance detection accuracy. The proposed model is evaluated using the UCI heart dataset and Electronic Health Records (EHRs) and its performance is assessed through statistical measures, classification metrics, and a Wilcoxon rank-sum p-test. Furthermore, a tenfold cross-validation process ensures a comprehensive evaluation and the proposed method outperforms different Machine Learning (ML) / Deep Learning (DL) classifiers. The experimental findings reveal that CGBO significantly improves the predictive performance of the FTOCNN classifier by achieving 94% accuracy in EHR and enhances the reliability of heart failure detection compared to existing systems.

Adaptive Thermal History De-Identification for Privacy-Preserving Data Sharing of Directed Energy Deposition Processes

Abstract In collaborative additive manufacturing (AM), sharing process data across multiple users can provide small- to medium-sized manufacturers (SMMs) with enlarged training data for part certification, facilitating accelerated adoption of metal-based AM technologies. The aggregated data can be used to develop a process-defect model that is more precise, reliable, and adaptable. However, the AM process data often contains printing path trajectory information that can significantly jeopardize intellectual property (IP) protection when shared among different users. In this study, a new adaptive AM data de-identification method is proposed that aims to mask the printing trajectory information in the AM process data in the form of melt pool images. This approach integrates stochastic image augmentation (SIA) and adaptive surrogate image generation (ASIG) via tracking melt pool geometric changes to achieve a trade-off between AM process data privacy and utility. As a result, surrogate melt pool images are generated with perturbed printing directions. In addition, a convolutional neural network (CNN) classifier is used to evaluate the proposed method regarding privacy gain (i.e., changes in the accuracy of identifying printing orientations) and utility loss (i.e., changes in the ability to detect process anomalies). The proposed method is validated using data collected from two cylindrical specimens using the directed energy deposition (DED) process. The case study results show that the de-identified dataset significantly improved privacy preservation while sacrificing little data utility, once shared on the cloud-based AM system for collaborative process-defect modeling.

Optimizing Convolutional Neural Network Architectures with Optimal Activation Functions for Pediatric Pneumonia Diagnosis Using Chest X-rays

Pneumonia remains a significant cause of morbidity and mortality among pediatric patients worldwide. Accurate and timely diagnosis is crucial for effective treatment and improved patient outcomes. Traditionally, pneumonia diagnosis has relied on a combination of clinical evaluation and radiologists’ interpretation of chest X-rays. However, this process is time-consuming and prone to inconsistencies in diagnosis. The integration of advanced technologies such as Convolutional Neural Networks (CNNs) into medical diagnostics offers a potential to enhance the accuracy and efficiency. In this study, we conduct a comprehensive evaluation of various activation functions within CNNs for pediatric pneumonia classification using a dataset of 5856 chest X-ray images. The novel Mish activation function was compared with Swish and ReLU, demonstrating superior performance in terms of accuracy, precision, recall, and F1-score in all cases. Notably, InceptionResNetV2 combined with Mish activation function achieved the highest overall performance with an accuracy of 97.61%. Although the dataset used may not fully represent the diversity of real-world clinical cases, this research provides valuable insights into the influence of activation functions on CNN performance in medical image analysis, laying a foundation for future automated pneumonia diagnostic systems.

Rapid Identification of Plastic Beverage Bottles by Using Raman Spectroscopy Combined With Machine Learning Algorithm

ABSTRACTRapid and accurate identification of plastic beverage bottles is of great importance because plastic beverage bottles can be encountered as physical evidence in cases involving assaults, thefts, and homicides. In this experiment, 40 commercially available plastic beverage bottles were collected as experimental samples, and their Raman spectral data were collected. Initially, the samples were classified into two categories of polyethylene terephthalate (PET) and polyethylene (PE), and the 35 PET samples were further clustered into three categories by K‐means clustering. Savitzky–Golay algorithm smoothing, standard normal variate, multiple scattering correction, and first‐order derivatives were utilized to improve the quality of the Raman spectra. A convolutional neural network (CNN) model was constructed for the classification and identification, and four evaluation indexes, such as accuracy, precision, recall, and F1‐score, were utilized to compare the model's performance under the four types of preprocessing. The results show that the spectral data preprocessing combining SG and MSC has higher accuracy than other preprocessing methods, and the CNN classification model has the best performance, with 100% correct classification rate in both the training set and the test set, respectively. In conclusion, the results show that convolutional neural networks, when used in combination with Raman spectroscopy, can quickly detect the type of plastic beverage bottle, which is crucial for solving crimes.

Multi-Scale Analysis of Knee Joint Acoustic Signals for Cartilage Degeneration Assessment

This study focuses on the diagnostic analysis of cartilage damage in the knee joint based on acoustic signals generated by the joint. The research utilizes a combination of advanced signal processing techniques, specifically empirical mode decomposition (EEMD) and detrended fluctuation analysis (DFA), alongside convolutional neural networks (CNNs) for classification and detection tasks. Acoustic signals, often reflecting the mechanical behavior of the joint during movement, serve as a non-invasive diagnostic tool for assessing the cartilage condition. EEMD is applied to decompose the signals into intrinsic mode functions (IMFs), which are then analyzed using DFA to quantify the scaling properties and detect irregularities indicative of cartilage damage. The separation of individual frequency components allows for multi-scale analysis of the signals, with each of the functions resulting from the analysis reflecting local variations in the amplitude and frequency over time and allowing for effective removal of noise present in the signal. The CNN model is trained on features extracted from these signals to accurately classify different stages of cartilage degeneration. The proposed method demonstrates the potential for early detection of knee joint pathology, providing a valuable tool for preventive healthcare and reducing the need for invasive diagnostic procedures. The results suggest that the combination of EEMD-DFA for feature extraction and CNN for classification offers a promising approach for the non-invasive assessment of cartilage damage.

Integration of Grey Wolf Optimization Framework with Convolutional Neural Network for Kidney Tumor Classification from Ct Images

Integration of Grey Wolf Optimization Framework with Convolutional Neural Network for Kidney Tumor Classification from Ct Images

Bilinear Interpolation Augmented Deep Feature Extraction with an Improved Remora Optimization-Based Deep Convolutional Neural Network for Skin Lesion Classification

Bilinear Interpolation Augmented Deep Feature Extraction with an Improved Remora Optimization-Based Deep Convolutional Neural Network for Skin Lesion Classification

Fast and accurate deep learning scans for signatures of natural selection in genomes using FASTER-NN

Deep learning classification models based on Convolutional Neural Networks (CNNs) are increasingly used in population genetic inference for detecting signatures of natural selection. Prevailing detection methods treat the design of the classifier as a discrete phase, assuming that high classification accuracy is the sole prerequisite for precise detection. This frequently steers method development toward classification-driven optimizations that can inadvertently impede detection. We present FASTER-NN, a CNN classifier designed specifically for the precise detection of natural selection. It has higher sensitivity than state-of-the-art CNN classifiers while only processing allele frequencies and genomic positions through dilated convolutions to maximize data reuse. As a result, execution time is invariant to the sample size and the chromosome length, creating a highly suitable solution for large-scale, whole-genome scans. Furthermore, FASTER-NN can accurately identify selective sweeps in recombination hotspots, which is a highly challenging detection problem with very limited theoretical treatment to date.

Vision Transformers for Image Classification: A Comparative Survey

Transformers were initially introduced for natural language processing, leveraging the self-attention mechanism. They require minimal inductive biases in their design and can function effectively as set-based architectures. Additionally, transformers excel at capturing long-range dependencies and enabling parallel processing, which allows them to outperform traditional models, such as long short-term memory (LSTM) networks, on sequence-based tasks. In recent years, transformers have been widely adopted in computer vision, driving remarkable advancements in the field. Previous surveys have provided overviews of transformer applications across various computer vision tasks, such as object detection, activity recognition, and image enhancement. In this survey, we focus specifically on image classification. We begin with an introduction to the fundamental concepts of transformers and highlight the first successful Vision Transformer (ViT). Building on the ViT, we review subsequent improvements and optimizations introduced for image classification tasks. We then compare the strengths and limitations of these transformer-based models against classic convolutional neural networks (CNNs) through experiments. Finally, we explore key challenges and potential future directions for image classification transformers.

A New Approach to COVID-19 Detection Using Alexnet From Chest CT Images

Background: At the beginning of 2020, the pneumonia-like COVID-19 virus spread rapidly worldwide. With the emergence of this dangerous virus, work, and daily life have become very difficult. To control this virus, all the centers are closed and quarantined by the government and the countries of the world. Every day, many people from all over the world die due to COVID-19. Many efforts are being made in all fields to diagnose and treat people infected with this virus. For this reason, many researchers started working on identifying this virus and its types. The Scientifics, in computer science, did not sit idle either. Method: In some studies, different image processing methods and algorithms have been used to extract the edge features of the Computed Tomography (CT) images of the lung. In this clinical-computerized study, lung CT images of non-infected and infected people from different hospitals in Lorestan province were used. This collection has 90 stereotypes of images in jpg format of CT scans of people's lungs, each file has more than 200 images from different angles of lung imaging. The preprocessing methods were the first step of the research. In the second phase, edge detection was applied to the dataset to get the highest accuracy rate. Consequently, a classification Convolutional Neural Network (CNN)-AlexNet architecture was used to reach the final aim. Results: The results show that the average accuracy rate of image edge extraction with a threshold value of 0.1 is 93% and the accuracy rate of AlexNet architecture classification is 100%. The proposed method helps physicians to improve disease diagnosis from lung CT images to achieve a more accurate detection rate. Conclusion: This study shows that the CNN-AlexNet architecture effectively increases the diagnosis accuracy rate than the other methods. It is suggested that educational programs for researchers in the field of disease detection from radiology images be provided and that the effectiveness of different types of deep learning methods be compared in future studies.

Seed Protein Content Estimation with Bench-Top Hyperspectral Imaging and Attentive Convolutional Neural Network Models.

Wheat is a globally cultivated cereal crop with substantial protein content present in its seeds. This research aimed to develop robust methods for predicting seed protein concentration in wheat seeds using bench-top hyperspectral imaging in the visible, near-infrared (VNIR), and shortwave infrared (SWIR) regions. To fully utilize the spectral and texture features of the full VNIR and SWIR spectral domains, a computer-vision-aided image co-registration methodology was implemented to seamlessly align the VNIR and SWIR bands. Sensitivity analyses were also conducted to identify the most sensitive bands for seed protein estimation. Convolutional neural networks (CNNs) with attention mechanisms were proposed along with traditional machine learning models based on feature engineering including Random Forest (RF) and Support Vector Machine (SVM) regression for comparative analysis. Additionally, the CNN classification approach was used to estimate low, medium, and high protein concentrations because this type of classification is more applicable for breeding efforts. Our results showed that the proposed CNN with attention mechanisms predicted wheat protein content with R2 values of 0.70 and 0.65 for ventral and dorsal seed orientations, respectively. Although, the R2 of the CNN approach was lower than of the best performing feature-based method, RF (R2 of 0.77), end-to-end prediction capabilities with CNN hold great promise for the automation of wheat protein estimation for breeding. The CNN model achieved better classification of protein concentrations between low, medium, and high protein contents, with an R2 of 0.82. This study's findings highlight the significant potential of hyperspectral imaging and machine learning techniques for advancing precision breeding practices, optimizing seed sorting processes, and enabling targeted agricultural input applications.

Small Metal Objects Classification Based on The Deep Learning Approach

Classification of small metal objects plays a crucial role in various engineering fields, including manufacturing, robotics, and security. With advancements in deep learning techniques, the use of Convolutional Neural Networks (CNNs) has emerged as a powerful tool for image classification tasks. The methodology begins by collecting diverse datasets consisting of images of small metal objects. The datasets are labelled with corresponding object classes to facilitate supervised learning. Preprocessing techniques like re-sizing, normalization, and augmentation are used to improve the quality and diversity of the datasets. The use of CNNs in classification can be a better option compared to commonly used machine learning approaches. The CNN architecture is designed and trained to learn the distinguishing features of small metal objects. The main objective of this study is to assess the accuracy of this classification and explain how CNNs can enhance classification accuracy. The results of this study also show the effect of the optimizer on the classification process, which changes when different types of optimizers such as RMSprop, Adam, and SGD are used. While some optimizers yield slightly lower accuracy results, the Adam optimizer with the CNN ResNet-50 module proves suitable for use with this dataset, achieving a high classification accuracy of 86%.

Melanoma Skin Cancer Detection Using Deep Learning Methods and Binary GWO Algorithm

Melanoma is one of the most aggressive types of skin cancer, and its early detection is critical to improving survival rates and treatment outcomes for patients. Conventional diagnostic methods often suffer from high computational costs and low accuracy, primarily due to inadequate feature selection and classification strategies. The goal of this research is to combine state-of-the-art deep learning techniques with optimization algorithms to develop a precise and efficient predictive system for melanoma detection. In this work, we propose a novel framework that integrates Convolutional Neural Networks (CNNs) for image classification and a binary Grey Wolf Optimization (GWO) algorithm for feature selection. The binary GWO algorithm identifies the most relevant features from dermatological images, eliminating redundancy and reducing the computational burden. The CNN is then trained on the refined feature subset to enhance classification efficiency. Extensive experiments on publicly available skin lesion datasets demonstrate that the proposed model significantly outperforms traditional machine learning models. Improvements in sensitivity, specificity, and overall classification accuracy highlight the effectiveness of combining deep learning with optimization techniques. Our results show that deep learning and optimization methods, such as the binary GWO algorithm, can be successfully applied to melanoma diagnosis. This strategy not only improves detection efficiency and accuracy but also supports early diagnosis and treatment planning, leading to better patient outcomes. By leveraging the binary GWO algorithm to optimize the feature selection process and CNNs for image classification, the proposed approach reduces computational costs while increasing classification accuracy. When trained and evaluated on publicly available skin lesion datasets, the model demonstrates significant improvements in sensitivity, specificity, and overall accuracy compared to conventional machine learning models.

A Hybrid Deep Learning Model Combining AgresNet, YOLO, and CNN for Lung Tumor Segmentation and Classification

Lung cancer is a malicious tumor that originates in the respiratory tissues when the cells lining the airways of the lungs proliferate and expand uncontrollably. While computed tomography (CT) scans are capable of illuminating problematic areas, they are not proficient at independently diagnosing lung tumors. The task of accurately determining the nodule distribution within the lung CT scans through automatic identification is challenging. As a consequence, the delineation of lung CT images facilitates the identification and classification of lung tumors. This study involved the acquisition of 1097 lung CT image datasets from the Iraq-Oncology Teaching Hospital/National Centre for Cancer Diseases (IQ-OTH/NCCD). In the initial stage of the work, lung CT images are segmented to find malignancies utilizing the U-Net and Attention Gate Residual U-Net (AGRes U-Net) algorithms. The Intersection over Union (IoU) and binary focal loss metrics are applied to evaluate the segmented lung images. AGRes U-Net achieves 97% greater accuracy than the standard U-Net architecture, as determined by performance evaluation. Subsequently, a YOLOv5 network is implemented to annotate the segmented lung CT images with lesions. Thus, the segmented lung CT outputs are labelled for tumors by the YOLOv5 network are fed into the VGG-19 architecture. With an accuracy of 94.8%, this VGG-19 framework distinguishes the lung tumors as normal, benign, and malignant. To compare the performance of the segmented lung output to that of the classified output by means of a convolutional neural network (CNN), the labelled lung CT images are fed as input to a CNN model in the second phase of the work. In conjunction with the Adaptive Moment Estimation (Adam) optimizer, the CNN model is implemented. The Adam optimizer demonstrates a 98% accuracy rate for the classified tumor outputs. The study illustrates that the accuracy of AGResU-Net segmentation for lung cancer detection and classification, at 97%, is nearly equivalent to that of the CNN model, which achieves 98% accuracy.

Design and realization of compressor data abnormality safety monitoring and inducement traceability expert system.

Centrifugal compressors are widely used in the oil and natural gas industry for gas compression, reinjection, and transportation. Fault diagnosis and identification of centrifugal compressors are crucial. To promptly monitor abnormal changes in compressor data and trace the causes leading to these data anomalies, this paper proposes a security monitoring and root cause tracing method for compressor data anomalies. Additionally, it presents an intelligent system design method for fault tracing in compressors and localization of faults from different sources. This method starts from petrochemical big data and consists of three parts: fault dynamic knowledge graph construction, instrument data sliding fault-tolerant filtering, and the fusion and reasoning of fault dynamic knowledge graph and instrument data variation monitoring. The results show that this method effectively overcomes the problems of false alarms and missed alarms based on fixed threshold alarm methods, and achieves 100% classification of two types of faults: non starting of the drive machine and low oil pressure by constructing a PCA (Principal Component Analysis)-SPE (Square Prediction Error)-CNN (Convolutional Neural Network) classifier. Combined with dynamic knowledge graph and NLP (Natural Language Processing) inference, it achieves good diagnostic results.