Sequential Convolutional Neural Network Research Articles

A Lightweight Sequential Convolutional Neural Network for Smart Grid Stability Analysis

A Smart grid stability analysis is essential for ensuring modern power systems' reliable and secure operation. This approach helps identify potential instabilities and disturbances that can lead to blackouts or equipment failures. By analyzing the stability of the grid, operators can take proactive measures to maintain a stable and resilient power infrastructure. Monitoring smart grid data from various sources and analyzing how to control the stability of the grid are challenging tasks. A convolutional neural network (CNN) can effectively capture spatial dependencies and patterns from grid data and can help in enabling accurate prediction and classification of stability-related events in a power system. However, developing a CNN that has fewer learnable parameters and provides high accuracy is challenging. This paper presents a sequential CNN architecture to detect the stability of the Decentral Smart Grid Control (DSGC) system. A mathematical model of the 4-node start architecture of a smart grid was presented. Later, 12 parameter-based grid datasets from the UCI repository were used to validate the proposed network. The proposed CNN accepts sequential data to capture temporal dependencies in the data. The sequential process in a single dimension offers fewer learnable parameters, making the network more compact and computationally efficient. The proposed 11-layered CNN has a total of 12.7K learnable parameters. The detailed analysis of the proposed CNN using ambiguity and the t-SNE score suggested that the model can identify discriminative features for classifying data into stable and unstable classes. A comparison analysis of the quantitative parameters revealed that the model performed well, with 98.82%, 98.55%, 98.88%, and 98.77% accuracy, precision, recall, and F1 score, respectively.

An Intelligent Mechanism to Detect Multi-Factor Skin Cancer.

Deep learning utilizing convolutional neural networks (CNNs) stands out among the state-of-the-art procedures in PC-supported medical findings. The method proposed in this paper consists of two key stages. In the first stage, the proposed deep sequential CNN model preprocesses images to isolate regions of interest from skin lesions and extracts features, capturing the relevant patterns and detecting multiple lesions. The second stage incorporates a web tool to increase the visualization of the model by promising patient health diagnoses. The proposed model was thoroughly trained, validated, and tested utilizing a database related to the HAM 10,000 dataset. The model accomplished an accuracy of 96.25% in classifying skin lesions, exhibiting significant areas of strength. The results achieved with the proposed model validated by evaluation methods and user feedback indicate substantial improvement over the current state-of-the-art methods for skin lesion classification (malignant/benign). In comparison to other models, sequential CNN surpasses CNN transfer learning (87.9%), VGG 19 (86%), ResNet-50 + VGG-16 (94.14%), Inception v3 (90%), Vision Transformers (RGB images) (92.14%), and the Entropy-NDOELM method (95.7%). The findings demonstrate the potential of deep learning, convolutional neural networks, and sequential CNN in disease detection and classification, eventually revolutionizing melanoma detection and, thus, upgrading patient consideration.

Refining neural network algorithms for accurate brain tumor classification in MRI imagery

Brain tumor diagnosis using MRI scans poses significant challenges due to the complex nature of tumor appearances and variations. Traditional methods often require extensive manual intervention and are prone to human error, leading to misdiagnosis and delayed treatment. Current approaches primarily include manual examination by radiologists and conventional machine learning techniques. These methods rely heavily on feature extraction and classification algorithms, which may not capture the intricate patterns present in brain MRI images. Conventional techniques often suffer from limited accuracy and generalizability, mainly due to the high variability in tumor appearance and the subjective nature of manual interpretation. Additionally, traditional machine learning models may struggle with the high-dimensional data inherent in MRI images. To address these limitations, our research introduces a deep learning-based model utilizing convolutional neural networks (CNNs).Our model employs a sequential CNN architecture with multiple convolutional, max-pooling, and dropout layers, followed by dense layers for classification. The proposed model demonstrates a significant improvement in diagnostic accuracy, achieving an overall accuracy of 98% on the test dataset. The proposed model demonstrates a significant improvement in diagnostic accuracy, achieving an overall accuracy of 98% on the test dataset. The precision, recall, and F1-scores ranging from 97 to 98% with a roc-auc ranging from 99 to 100% for each tumor category further substantiate the model’s effectiveness. Additionally, the utilization of Grad-CAM visualizations provides insights into the model’s decision-making process, enhancing interpretability. This research addresses the pressing need for enhanced diagnostic accuracy in identifying brain tumors through MRI imaging, tackling challenges such as variability in tumor appearance and the need for rapid, reliable diagnostic tools.

WiKA: A Vision Based Sign Language Recognition from Extracted Hand Joint Features using DeepLabCut

The use of hand gesture recognition for sign language translation to address the communication gap between the hearing majority and the deaf population has had significant breakthroughs over the years. While the contact-based approach uses wearable devices, a vision-based solution is preferred owing to the convenience it offers and since it obviates the need for complicated gears. This study presents the development of WiKA, an open-source software designed to track the joints of the hands and interpret them into their corresponding sign language counterparts. DeepLabCut, a markerless pose estimation software, was employed to develop the Hand-Joint Tracking Model through the training of a sequential Convolutional Neural Network, utilizing extracted Hand-Joint features to predict the sign language alphabets (A-Z) and numbers (1-9) based on the positioning of the joints. The developed Hand-Joint tracking model exhibited a 4.92% training error and a 5.74% test error with a p-cut-off of 60%. On the other hand, the developed sign language recognition achieved a 96.44% prediction accuracy with only 0.0356% misclass. This model can be further integrated into mobile phones for seamless conversations between the signing and non-signing populations.

Generalizability of Deep Neural Networks for Vertical Cup-to-Disc Ratio Estimation in Ultra-Widefield and Smartphone-Based Fundus Images.

To develop and validate a deep learning system (DLS) for estimation of vertical cup-to-disc ratio (vCDR) in ultra-widefield (UWF) and smartphone-based fundus images. A DLS consisting of two sequential convolutional neural networks (CNNs) to delineate optic disc (OD) and optic cup (OC) boundaries was developed using 800 standard fundus images from the public REFUGE data set. The CNNs were tested on 400 test images from the REFUGE data set and 296 UWF and 300 smartphone-based images from a teleophthalmology clinic. vCDRs derived from the delineated OD/OC boundaries were compared with optometrists' annotations using mean absolute error (MAE). Subgroup analysis was conducted to study the impact of peripapillary atrophy (PPA), and correlation study was performed to investigate potential correlations between sectoral CDR (sCDR) and retinal nerve fiber layer (RNFL) thickness. The system achieved MAEs of 0.040 (95% CI, 0.037-0.043) in the REFUGE test images, 0.068 (95% CI, 0.061-0.075) in the UWF images, and 0.084 (95% CI, 0.075-0.092) in the smartphone-based images. There was no statistical significance in differences between PPA and non-PPA images. Weak correlation (r = -0.4046, P < 0.05) between sCDR and RNFL thickness was found only in the superior sector. We developed a deep learning system that estimates vCDR from standard, UWF, and smartphone-based images. We also described anatomic peripapillary adversarial lesion and its potential impact on OD/OC delineation. Artificial intelligence can estimate vCDR from different types of fundus images and may be used as a general and interpretable screening tool to improve community reach for diagnosis and management of glaucoma.

Enhancing Food Type Recognition: A Comprehensive Study on Sequential Convolutional Neural Networks for Image Classification Accuracy

Addressing the challenge of food recognition, this study investigates the effectiveness of sequential convolutional neural networks (CNNs) and their application in accurately identifying food items within images. The research introduces a novel CNN architecture, termed "sequential_2," tailored for food classification, achieving an accuracy of 89.84% on the Food Images (Food-101) dataset. Insights from the model's architecture, performance, and findings are discussed, emphasizing its potential in image classification tasks, particularly in the context of food recognition. This innovative approach aims to automate traditionally challenging and resource-intensive tasks associated with determining food attributes, creating taxonomies, and extracting nutrient information. The results highlight the potential of combining cutting-edge deep learning techniques with practical applications, showcasing a paradigm shift in the way we approach and automate the understanding of food through technology.

Sickle cell disease classification using deep learning

This paper presents a transfer and deep learning based approach to the classification of Sickle Cell Disease (SCD). Five transfer learning models such as ResNet-50, AlexNet, MobileNet, VGG-16 and VGG-19, and a sequential convolutional neural network (CNN) have been implemented for SCD classification. ErythrocytesIDB dataset has been used for training and testing the models. In order to make up for the data insufficiency of the erythrocytesIDB dataset, advanced image augmentation techniques are employed to ensure the robustness of the dataset, enhance dataset diversity and improve the accuracy of the models. An ablation experiment using Random Forest and Support Vector Machine (SVM) classifiers along with various hyperparameter tweaking was carried out to determine the contribution of different model elements on their predicted accuracy. A rigorous statistical analysis was carried out for evaluation and to further evaluate the model's robustness, an adversarial attack test was conducted. The experimental results demonstrate compelling performance across all models. After performing the statistical tests, it was observed that MobileNet showed a significant improvement (p = 0.0229), while other models (ResNet-50, AlexNet, VGG-16, VGG-19) did not (p > 0.05). Notably, the ResNet-50 model achieves remarkable precision, recall, and F1-score values of 100 % for circular, elongated, and other cell shapes when experimented with a smaller dataset. The AlexNet model achieves a balanced precision (98 %) and recall (99 %) for circular and elongated shapes. Meanwhile, the other models showcase competitive performance.

A sequential convolutional neural network for image forgery detection

A sequential convolutional neural network for image forgery detection

Spinach fungi guard: A deep learning-based software solution for swift detection and remediation of fungal diseases in spinach leaves

We have developed a software solution aimed at assisting farmers in quickly detecting and finding a cure for fungal diseases in spinach leaves. This solution utilizes Deep Learning techniques, specifically a Convolutional Neural Network (CNN), to effectively detect diseases caused by fungi in spinach leaves and suggest suitable remedies to the user. To train our model; we gathered a spinach fungi disease image dataset consisting of over 700 images categorized into six classes, including five diseases and one healthy category. Prior to model training, we resized the images and applied various image augmentation techniques to improve the robustness of the model. Using Keras, we constructed a sequential CNN model for disease classification. The model was trained on the dataset and evaluated on the validation set, achieving an impressive accuracy of 89.86 %. To provide an intuitive interface for end users, we implemented a PySide2-based GUI application that leverages the trained model to classify disease in spinach leaf images provided as input.Our software not only accurately classifies the disease but also suggests appropriate remedies or medications for the specific disease. Furthermore, it provides links to relevant products on various e-commerce sites, enabling users to conveniently purchase the required medications. This comprehensive solution empowers end users to analyze infected spinach leaf images, accurately classify diseases, and take necessary actions by applying appropriate remedies and acquiring the right medications. By swiftly detecting diseases and offering prompt remedies, our software aids in preserving the production of spinach and ensures farmers can effectively combat fungal diseases, ultimately benefiting the food, medicine, and skincare industries.

Disease Detection of Rice and Chili Based on Image Classification Using Convolutional Neural Network Android-Based

The current development of machine learning makes it easier for humans to obtain information, especially from images. The presence of processing assistance from machines can increase the accuracy of the information provided to further convince the recipient of the information. Rice and chili farmers in Indonesia have experienced many disease attacks from several types of plant diseases. Not many farmers understand and are good at guessing the diseases that attack their rice and chili plants. So many rice and chili farmers experienced crop failure. This research aims to build a disease-detection system for rice and chili plants based on Android-based image classification. The machine learning method used is Convolutional Neural Network (CNN) with the Mobile Net version one model combined with the Sequential CNN and Tensor Flow Lite models. The results of the transfer learning evaluation on the Mobile Net version 1 model and the sequential CNN model obtained training accuracy of 0.88% with a loss of 0.34%, validation accuracy of 0.84% with a loss of 0.40%, and testing accuracy of 86% with a loss of 43%. Each uses batch 69 of the total training data stopping at epoch 30 from epoch 100. The results of field testing on the application of rice and chili disease detection on 20 images of rice and chili plants can detect Rice Neck Blast disease with a probability of 75% to 100% and Rice Hispa with a probability of 97% to 100%. It can also detect chili plant diseases such as Chili Yellowish with a probability of 83%, Chili Leaf Spot with a probability of 99%, Chili Whitefly with a probability of 91% to 95, Chili Healthy with a probability of 78% to 99%, and Chili Leaf Curl with a probability 75 to 76%. The probability obtained varies according to how likely damage is to rice and chili plants. CNN with the Mobile Net version one model and the Sequential model can extract and classify images so that it has maximum information processing capabilities. This research can make it easier to help farmers identify diseases that attack their rice and chili plants.&#x0D;

Wide-baseline view synthesis for light-field display based on plane-depth-fused sweep volume

The advancements in three-dimensional (3D) display technology have led to a wide interest in light-field display. However, the need to simultaneously capture a large number of object views made content generation for light-field displays still a bottleneck. In this paper, we propose a method for light-field content generation based on plane-depth-fused sweep volume (PDFSV), focusing on handling wide-baseline views and exhibiting scene generalization when the camera array remains unchanged. Specifically, the proposed PDFSV exploits the prior depth of the images captured by a 4 × 4 spherical camera array to represent 3D information of scenes. Then two optimized sequential convolutional neural networks (CNN) are employed for implicit depth modeling and final color calculation, respectively. By doing these, the prior depth facilitates the synthesis of regions with complex textures in the target view. We produce a Wide-baseline Multi-view Image Set (WMIS) which has a field of view (FOV) angle reaching 54°and could be publicly available for access. In our experiments, we use only the 4 vertex views as input. Results demonstrate that the proposed approach can synthesize high-quality views at arbitrary positions between sparse views, outperforming existing neural-radiance-fields-based (NeRF-based) methods. Finally, we conduct autostereoscopic display experiments, achieving satisfactory results.

Traffic Violation Prediction Using Deep Learning

Smart transportation infrastructure is needed and technology is now ready to help us. Artificial intelligence (especially deep learning) can help improve the performance of existing systems in many ways. The ability to effectively identify and classify tools is critical to the success of an intelligent machine. This device can play an important role in helping us travel in a country like India where there are many people but limited space. We present an advanced framework for detecting cyclists ignoring helmet rules using deep convolutional neural networks (CNNs). The system includes motorcycle, detection, helmet and no helmet, classification and calculation using the YOLO algorithm. Convolutional Neural Network with Sequential CNN model is used in the license control process. The CNN classification model proposes to classify the permission in the image and extract the user's content. Then calculate the penalty. Finally, make an SMS service that sends reminders to users to avoid motorcycle accidents and pay within a week. Automatically block accounts and send notifications if user doesn't pay. Finally, the administrator updates the user's license after receiving the penalty. We measure the accuracy and speed of the frame.

Classification of COVID-19 X-ray images using transfer learning with visual geometrical groups and novel sequential convolutional neural networks

COVID-19 is a highly transmissible infectious disease that remains a substantial challenge. The utilization of chest radiology, particularly X-ray imaging, has proven to be highly effective, easily accessible, and cost-efficient in detecting COVID-19. A dataset named COVID-Xray-5k, consisting of imbalanced X-ray images of COVID-19-positive and normal subjects, is employed for investigation. The research introduces a novel methodology that utilizes conventional machine learning (ML), such as local binary patterns (LBP) for feature extraction and support vector machines (SVM) for classification. In addition, transfer learning is employed with the Visual Geometry Group 16-layer (VGG16) and 19-layer (VGG19) models. Besides, novel sequential convolutional neural network (CNN) architectures are presented to develop an autonomous system for classifying COVID-19. One of the proposed CNN architectures classifies the test dataset with an F1 score of 91.00% and an accuracy of 99.45% based on an empirical investigation to determine optimal hyper-parameters. The methods presented in the research show promising potential for COVID-19 classification, irrespective of class imbalance.•Employment of ML models to investigate subjective feature engineering and classification.•Transfer learning was employed for VGG16 and VGG19 with eight distinct models.•Illustration of two novel CNN sequential architectures; all the investigation is performed with and without weighted sampling.

Full-field prediction of stress and fracture patterns in composites using deep learning and self-attention

An efficient surrogate modelling framework is proposed for full-field predictions of stresses and cracks in composite material microstructures. The framework comprises two sequential convolutional neural networks (CNNs), predicting the elastic stress fields and the local crack maps, respectively. Training and test data are created from high-resolution fracture simulations of randomly generated representative volume elements (RVEs), including geometric variabilities such as fibre volume fraction and porosity. This work shows that the inclusion of a self-attention layer within the network enables the model to capture relevant local and global features, which are important in determining the heterogeneous stress distribution and crack patterns. The performance of the trained CNN models is evaluated with unseen data. The CNN models speed up the full-field predictions by 3 ∼ 4 orders of magnitude compared to the physics-based model. The surrogate model’s accuracy and efficiency are key enables for applications such as multiscale simulation, microstructure optimisation and uncertainty quantification.

Osteo-NeT: An Automated System for Predicting Knee Osteoarthritis from X-ray Images Using Transfer-Learning-Based Neural Networks Approach.

Knee osteoarthritis is a challenging problem affecting many adults around the world. There are currently no medications that cure knee osteoarthritis. The only way to control the progression of knee osteoarthritis is early detection. Currently, X-ray imaging is a central technique used for the prediction of osteoarthritis. However, the manual X-ray technique is prone to errors due to the lack of expertise of radiologists. Recent studies have described the use of automated systems based on machine learning for the effective prediction of osteoarthritis from X-ray images. However, most of these techniques still need to achieve higher predictive accuracy to detect osteoarthritis at an early stage. This paper suggests a method with higher predictive accuracy that can be employed in the real world for the early detection of knee osteoarthritis. In this paper, we suggest the use of transfer learning models based on sequential convolutional neural networks (CNNs), Visual Geometry Group 16 (VGG-16), and Residual Neural Network 50 (ResNet-50) for the early detection of osteoarthritis from knee X-ray images. In our analysis, we found that all the suggested models achieved a higher level of predictive accuracy, greater than 90%, in detecting osteoarthritis. However, the best-performing model was the pretrained VGG-16 model, which achieved a training accuracy of 99% and a testing accuracy of 92%.

DIAGNOSIS OF COLORECTAL CANCER CASES FROM TOMOGRAPHY IMAGES USING DEEP CONVOLUTIONAL NEURAL NETWORKS

Background/Aim: Tomography imaging is a valuable alternative to colonoscopy for diagnosing colorectal cancer cases especially when colonoscopy is not applicable. Therefore, processing tomography images by computer-aided diagnosis support systems is essential for helping clinicians. The aim of this study is to investigate the applicability of convolutional neural networks (CNN) for diagnosis of colorectal cancer from tomography images. This study uses CNN models to classify abdominal tomography im Methods: ages automatically. The image classication is performed using four benchmark CNN models, namely, MobileNETv2, ResNet101V2, InceptionResnetV2, EfcientNetB2, and a shallower sequential CNN model. The benchmark models are experimented with using transfer learning for two separate cases: with and without data augmentation. According to the results, the proposed sequential CNN model achieve Results: d the highest classication scores with mean accuracy, precision, recall and F1-score of 0.9803, 0.9813, 0.9793, and 0.9803, respectively. It is Conclusion: possible to achieve a better detection performance when a shallower CNN model with lower number of parameters is used. Making prediction with such a model means performing less computation to achieve the result. All in all, computer aided diagnosis of colorectal cancer is possible to help the clinicians during their daily practices

The Design and Evaluation of an Orange-Fruit Detection Model in a Dynamic Environment Using a Convolutional Neural Network

Agricultural robots play a crucial role in ensuring the sustainability of agriculture. Fruit detection is an essential part of orange-harvesting robot design. Ripe oranges need to be detected accurately in an orchard so they can be successfully picked. Accurate fruit detection in the orchard is significantly hindered by the challenges posed by the illumination and occlusion of fruit. Hence, it is important to detect fruit in a dynamic environment based on real-time data. This paper proposes a deep-learning convolutional neural network model for orange-fruit detection using a universal real-time dataset, specifically designed to detect oranges in a complex dynamic environment. Data were annotated and a dataset was prepared. A Keras sequential convolutional neural network model was prepared with a convolutional layer-activation function, maximum pooling, and fully connected layers. The model was trained using the dataset then validated by the test data. The model was then assessed using the image acquired from the orchard using Kinect RGB-D camera. The model was then run and its performance evaluated. The proposed CNN model shows an accuracy of 93.8%, precision of 98%, recall of 94.8%, and F1 score of 96.5%. The accuracy was mainly affected by the occlusion of oranges and leaves in the orchard’s trees. Varying illumination was another factor affecting the results. Overall, the orange-detection model presents good results and can effectively identify oranges in a complex real-time environment, like an orchard.

Deep Learning for Assessing Severity of Cracks in Concrete Structures

Most concrete structures suffer from degradation, where cracks are the most obvious visual sign. Concrete structures must be continuously monitored and assessed to avoid further deterioration, which may lead to a partial or total collapse. This is particularly important when constructing large structures such as towers, bridges, tunnels, and dams. This work aims to demonstrate and evaluate several deep learning approaches that can be used for monitoring and assessing the level of concrete degradation based on the cracks’ visual signs, which can then be embedded in Health Monitoring Systems (SHM). The experimental work in this study involves creating three models: Two were built using ResNet-50 and Xception transfer learning networks. In contrast, the third was built using a customized Sequential Convolutional Neural Network (SCNN) architecture. The dataset comprises 2,000 image samples sampled from a larger dataset that contains 56,000 images and which belong to four severity classes: minor, moderate, and severe, in addition to a normal class for no crack signs. The SCNN model achieved an accuracy of 90.2%, while the Xception and ResNet-50 models scored an accuracy of 86.3% and 70%, respectively.

Machine learning classification of polar sub-phases in liquid crystal MHPOBC.

Experimental polarising microscopy texture images of the fluid smectic phases and sub-phases of the classic liquid crystal MHPOBC were classified as paraelectric (SmA*), ferroelectric (SmC*), ferrielectric (SmC1/3*), and antiferroelectric (SmCA*) using convolutional neural networks, CNNs. Two neural network architectures were tested, a sequential convolutional neural network with varying numbers of layers and a simplified inception model with varying number of inception blocks. Both models are successful in binary classifications between different phases as well as classification between all four phases. Optimised architectures for the multi-phase classification achieved accuracies of (84 ± 2)% and (93 ± 1)% for sequential convolutional and inception networks, respectively. The results of this study contribute to the understanding of how CNNs may be used in classifying liquid crystal phases. Especially the inception model is of sufficient accuracy to allow automated characterization of liquid crystal phase sequences and thus opens a path towards an additional method to determine the phases of novel liquid crystals for applications in electro-optics, photonics or sensors. The outlined procedure of supervised machine learning can be applied to practically all liquid crystal phases and materials, provided the infrastructure of training data and computational power is provided.

High-Throughput Field Plant Phenotyping: A Self-Supervised Sequential CNN Method to Segment Overlapping Plants.

High-throughput plant phenotyping-the use of imaging and remote sensing to record plant growth dynamics-is becoming more widely used. The first step in this process is typically plant segmentation, which requires a well-labeled training dataset to enable accurate segmentation of overlapping plants. However, preparing such training data is both time and labor intensive. To solve this problem, we propose a plant image processing pipeline using a self-supervised sequential convolutional neural network method for in-field phenotyping systems. This first step uses plant pixels from greenhouse images to segment nonoverlapping in-field plants in an early growth stage and then applies the segmentation results from those early-stage images as training data for the separation of plants at later growth stages. The proposed pipeline is efficient and self-supervising in the sense that no human-labeled data are needed. We then combine this approach with functional principal components analysis to reveal the relationship between the growth dynamics of plants and genotypes. We show that the proposed pipeline can accurately separate the pixels of foreground plants and estimate their heights when foreground and background plants overlap and can thus be used to efficiently assess the impact of treatments and genotypes on plant growth in a field environment by computer vision techniques. This approach should be useful for answering important scientific questions in the area of high-throughput phenotyping.