DIABETIC RETINOPATHY DIAGNOSIS USING KERNEL FUZZY C MEANS WITH CONVOLUTIONAL NEURAL NETWORK BASED RESIDUAL MODEL

In this paper, an unsupervised image segmentation algorithm is proposed, which combines spatial constraints with a kernel fuzzy c-means (KFCM) clustering algorithm. Conventional KFCM clustering segmentation algorithm does not incorporate the spatial context information of image, which makes it sensitive to the noise and intensity variations. In order to overcome the shortcomings, the contents of image is characterized by Gaussian mixture model, and the parameters of model are estimated by modified expectation maximization (EM) algorithm, which overcomes the classical EM algorithm drawbacks that easily trap in local maxima and be susceptible to initial value. According to the maximum a posterior theorem, we can get the pixel maximum posterior probability. We redefine the objective function of the KFCM algorithm which incorporates the pixel maximum posteriori probability, by minimizing the fuzzy objective function, the fuzzy segmentation algorithm is derived. The experimental results on a synthetic image and a real magnetic resonance image show that the proposed algorithm is more effective than the conventional FCM algorithm without local spatial constraints.

The study presents the results of the development and testing of deep learning neural network architectures, which demonstrate high accuracy rates in classifying neurophysiological data, in particular hemodynamic brain activation patterns obtained by functional near-infrared spectroscopy, during solving mathematical problems on spatial-numerical associations. The analyzed signal represents a multidimensional time series of oxyhemoglobin and deoxyhemoglobin dynamics. Taking the specificity of the fNIRS signal into account, a comparative analysis of 2 types of neural network architectures was carried out: (1) architectures based on recurrent neural networks: recurrent neural network with long short-term memory, recurrent neural network with long short-term memory with fully connected layers, bidirectional recurrent neural network with long short-term memory, convolutional recurrent neural network with long short-term memory; (2) architectures based on convolutional neural networks with 1D convolutions: convolutional neural network, fully convolutional neural network, residual neural network. Trained long short-term memory recurrent neural network architectures showed worse results in accuracy in comparison with 1D convolutional neural network architectures. Residual neural network (model_Resnet) demonstrated the highest accuracy rates in three experimental conditions more than 88% in detecting age-related differences in brain activation during spatial-numerical association tasks considering the individual characteristics of the respondents’ signal.

Designing and developing automated systems to detect and grade Diabetic Retinopathy (DR) is one of the recent research areas in the world of medical image applications since it is considered one of the main causes of total blindness for people who have diabetes in the mid-age. In this paper, a complete pipeline for retinal fundus images processing and analysis has been described, implemented and evaluated. This pipeline has three main stages: (i) image pre-processing, (ii) features extraction and (iii) classification. In the first stage, the image has been pre-processed using different transformations to standardize the images and to enhance the images quality. It has been proven that Gaussian filtering is quite effective in this context to enhance the images contrast. In the second and third stage, the convolution neural network (CNN), one of the best neural network architecture for image analysis applications, has been used. The concept of transfer learning and fine tuning have been advocated in this paper and applied for ResNet18 using the publicly available Kaggle dataset. The problem of DR diagnosis has been handled as a multi-class classification problem where there are five levels of the disease severity (0 – No DR, 1 – Mild, 2 – Moderate, 3 – Severe, 4 – Proliferative DR). The final model has achieved accuracy of 70 %, recall of 50% and specificity of 88% outperforming other models built from scratch with less training time and proving the efficiency of transfer learning in this context. The training process has considered the problem of imbalanced dataset using two different ways and it has been discovered that using imbalanced dataset sampler is a very efficient solution. The final model developed in this research could be used as the main unit for a computer aided system to be hosted online for DR detection and diagnosis.

In recent times, Internet of Things (IoT) and Deep Learning (DL) models have revolutionized the diagnostic procedures of Diabetic Retinopathy (DR) in its early stages that can save the patient from vision loss. At the same time, the recent advancements made in Machine Learning (ML) and DL models help in developing Computer Aided Diagnosis (CAD) models for DR recognition and grading. In this background, the current research works designs and develops an IoT-enabled Effective Neutrosophic based Segmentation with Optimal Deep Belief Network (ODBN) model i.e., NS-ODBN model for diagnosis of DR. The presented model involves Interval Neutrosophic Set (INS) technique to distinguish the diseased areas in fundus image. In addition, three feature extraction techniques such as histogram features, texture features, and wavelet features are used in this study. Besides, Optimal Deep Belief Network (ODBN) model is utilized as a classification model for DR. ODBN model involves Shuffled Shepherd Optimization (SSO) algorithm to regulate the hyperparameters of DBN technique in an optimal manner. The utilization of SSO algorithm in DBN model helps in increasing the detection performance of the model significantly. The presented technique was experimentally evaluated using benchmark DR dataset and the results were validated under different evaluation metrics. The resultant values infer that the proposed INS-ODBN technique is a promising candidate than other existing techniques.

The Internet of Things (IoT) has transformed various sectors by enabling connectivity and automation through smart devices. However, the expansion of IoT networks has introduced new security challenges, particularly concerning the detection and prevention of cyber threats. This study explores the application of machine learning (ML) models for enhancing network security in IoT-enabled smart systems. The primary objective was to evaluate the performance of different ML algorithms, including Convolutional Neural Networks (CNN), Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT), K-Means, and Autoencoder, in detecting and mitigating security threats in IoT environments. The study also aimed to identify the most effective model in terms of accuracy, precision, recall, and F1-score. The research methodology involved training and testing these models on publicly available IoT security datasets, followed by performance evaluation based on the key metrics. Statistical analysis, including One-Way ANOVA and post-hoc testing, was used to assess the significance of the performance differences across the models. The results revealed that CNN outperformed all other models, achieving the highest accuracy (96.7%), precision (95.8%), recall (97.2%), and F1-score (96.5%). Random Forest also demonstrated strong performance with an accuracy of 95.6% and a balanced evaluation across all metrics. In contrast, traditional models like SVM and DT showed comparatively lower performance, while Autoencoder struggled with classification tasks, particularly in real-time threat detection. Statistical analysis confirmed the significant differences in model performance. In conclusion, the study demonstrates the effectiveness of deep learning and ensemble models, particularly CNN and Random Forest, in enhancing IoT network security. The research highlights the importance of selecting the appropriate ML model based on the specific requirements of the IoT environment and computational constraints, and suggests that hybrid models and model optimization strategies may offer promising solutions for resource-constrained IoT systems.

With the rapid development of 5G and the Internet of Things, video has gained broad application space as a carrier of information, and video codec technology can reduce video storage space, save transmission bandwidth, and provide the possibility for the promotion of video applications. Versatile Video Coding (VVC), the latest generation of video coding standard today, still uses block-based coding, which inevitably introduces coding artifacts, and deblocking filters can effectively reduce artifacts and improve the quality of compressed video. The deblocking filter in VVC still adopts the method based on empirical threshold when making the filtering decision, but the actual video scene changes variously, and it is obviously impossible to obtain the optimal filtering effect with a fixed threshold. The decision of the filtering mode is essentially a classification problem. Existing research shows that the convolutional neural network (CNN) has a strong ability in classification tasks, and its feature extraction and nonlinear fitting ability can greatly improve the learning ability of the target, so as to obtain better classification accuracy. Therefore, we improves the deblocking filter in VVC based on CNN. Experimental results show that, compared with the original filtering method of VVC, our method can better improve the quality of compressed video.

Diabetic retinopathy (DR) is a complication of prolonged diabetic mellitus causing damage to the micro-vascular system in retina. Computer-aided detection of DR can significantly reduce time, effort, and cost in early diagnosis and thereby restrict further complications. In this paper, we present a deep learning based framework for automated DR stage classification from fundus retinal images.We design and develop a custom build Convolutional Neural Network (CNN) model named Model-IVS to extract meaningful and discriminative features from the retinal fundus images. The proposed hybrid-CNN combines the multi-scale pyramidal feature processing concept of inception model with the convolutional pipeline based feature extraction concept of VGG-Nets and adopts multi-scale feature concatenation based short-cut connections of DenseNet with learnable convolutions. For the binary classification tasks, we employ Model-IVS as a feature extractor and use Support Vector Machine (SVM) classifier on the reduced features obtained through principal component analysis. The proposed hybrid model is end-to-end trained incrementally on a class-balanced dataset curated from the train set of EyePACS dataset. The cross-dataset generalization of the proposed hybrid CNN based DR classification framework is evaluated on APTOS, MESSIDOR-1 and MESSIDOR-2 datasets. Experimental results demonstrate that our model has outperformed all the existing state-of-the-art methods for DR severity grading task on APTOS dataset. The proposed Model-IVS has achieved best accuracy, AUC-ROC, and kappa score of 84.33%, 0.978 and 0.899, respectively in DR severity grading task. In binary classification tasks like DR screening and referable DR predictions, our Model-IVS feature extraction network with SVM classifier on PCA features has also achieved comparable performance results w.r.t. the state-of-the-art methods. In DR screening task, we recorded an accuracy of 97.84%, 87.42%, and 89.67% on APTOS, MESSIDOR-1, and MESSIDOR-2 datasets, respectively. In referable DR prediction, we achieved AUC-ROC score of 0.987, 0.928, and 0.873 on APTOS, MESSIDOR-1, and MESSIDOR-2 datasets, respectively.

Convolutional neural networks (CNNs) have shown great advantages in computer vision fields, and loss functions are of great significance to their gradient descent algorithms. Softmax loss, a combination of cross-entropy loss and Softmax function, is the most commonly used one for CNNs. Hence, it can continuously increase the discernibility of sample features in classification tasks. Intuitively, to promote the discrimination of CNNs, the learned features are desirable when the inter-class separability and intra-class compactness are maximized simultaneously. Since Softmax loss hardly motivates this inter-class separability and intra-class compactness simultaneously and explicitly, we propose a new method to achieve this simultaneous maximization. This method minimizes the distance between features of homogeneous samples along with Softmax loss and thus improves CNNs' performance on vision-related tasks. Experiments on both visual classification and face verification datasets validate the effectiveness and advantages of our method.

Intrusion Detection System (IDS) has been a challenging area to be developed in recent years since there are so many kinds of network attacks that are difficult to be classified by system. Moreover, there is always the possibility of the upcoming new attack. Therefore, Intrusion detection system must be improved by new classifiers to obtain the best results not only for classifying attack but also recognizing a new type of attack in an advanced way. These developments will be beneficial for managing security systems in an upcoming era. There are several classifier algorithms for Intrusion Detection System such as Support Vector Machine (SVM) and Fuzzy Kernel C-Means (FKCM). SVM classifier is known as one of the techniques to improve efficiency in attack detection while FKCM is famous because it provides better results to reduce the number of selected data features. Each of classifiers is using kernel trick to improve the classifying matter. In this study, we will compare proposed model which are FKCM with rbf, FKCM with polynomial kernel, SVM with rbf, and SVM with polynomial kernel to find a better result that could increase the accuracy of classifying network attacks. KDD Cup 1999 will be used to evaluate each model. In this study, the use of SVM with polynomial kernel brings the best result with 100 % accuracy can be obtained in 1.9 second.

<span id="docs-internal-guid-94842888-7fff-2ae1-cd5c-026943b95b7f"><span>Cancer is one of the diseases with the highest mortality rate in the world. Cancer is a disease when abnormal cells grow out of control that can attack the body's organs side by side or spread to other organs. Lung cancer is a condition when malignant cells form in the lungs. To diagnose lung cancer can be done by taking x-ray images, CT scans, and lung tissue biopsy. In this modern era, technology is expected to help research in the field of health. Therefore, in this study feature extraction from CT images was used as data to classify lung cancer. We used CT scan image data from SPIE-AAPM Lung CT challenge 2015. Fuzzy C-Means and fuzzy kernel C-Means were used to classify the lung nodule from the patient into benign or malignant. Fuzzy C-Means is a soft clustering method that uses Euclidean distance to calculate the cluster center and membership matrix. Whereas fuzzy kernel C-Means uses kernel distance to calculate it. In addition, the support vector machine was used in another study to obtain 72% average AUC. Simulations were performed using different k-folds. The score showed fuzzy kernel C-Means had the highest accuracy of 74%, while fuzzy C-Means obtained 73% accuracy. </span></span>

Artificial intelligence using deep learning to screen for referable and vision-threatening diabetic retinopathy in Africa: a clinical validation study

This paper aims to introduce a novel approach that includes three steps, namely Energy efficient clustering, Disease diagnosis, and an Alert system. Initially, energy-efficient clustering of nodes was conducted, and to render the clustering more optimal, its centroid was optimally selected by a new hybrid algorithm. In addition, this cluster formation was conducted based on constraints such as distance and energy. Further, the disease diagnosis in IoT was performed under two phases namely, “feature extraction and classification”. During feature extraction, the statistical and higher-order features were extracted. These extracted features were then classified via Optimized Deep Convolutional Neural Network (DCNN). To make the classification more precise, the weights of the DCNN were optimally tuned by a new hybrid algorithm referred to as Hybrid Elephant and Moth Flame with Adaptive Learning (HEM-AL). Finally, an alert system was enabled via proposed severity level estimation, which determined the severity of the disease, suggesting patients to visit the hospital. Lastly, the supremacy of the developed approach was examined via evaluation over the other extant techniques. Accordingly, the proposed model attained an accuracy of 0.99 for test case 1, and was 7.41%, 17.34%, and 13.41% better than traditional NN, CNN, and DCNN models.

Machine learning (ML) within the edge internet of things (IoT) is instrumental in making significant shifts in various industrial domains, including smart farming. To increase the efficiency of farming operations and ensure ML accessibility for both small and large-scale farming, the need for a low-cost ML-enabled framework is more pressing. In this paper, we present an end-to-end solution that utilizes tiny ML (TinyML) for the low-cost adoption of ML in classification tasks with a focus on the post-harvest process of olive fruits. We performed dataset collection to build a dataset that consists of several varieties of olive fruits, with the aim of automating the classification and sorting of these fruits. We employed simple image segmentation techniques by means of morphological segmentation to create a dataset that consists of more than 16,500 individually labeled fruits. Then, a convolutional neural network (CNN) was trained on this dataset to classify the quality and category of the fruits, thereby enhancing the efficiency of the olive post-harvesting process. The goal of this study is to show the feasibility of compressing ML models into low-cost edge devices with computationally constrained settings for tasks like olive fruit classification. The trained CNN was efficiently compressed to fit into a low-cost edge controller, maintaining a small model size suitable for edge computing. The performance of this CNN model on the edge device, focusing on metrics like inference time and memory requirements, demonstrated its feasibility with an accuracy of classification of more than 97.0% and minimal edge inference delays ranging from 6 to 55 inferences per second. In summary, the results of this study present a framework that is feasible and efficient for compressing CNN models on edge devices, which can be utilized and expanded in many agricultural applications and also show the practical insights for implementing the used CNN architectures into edge IoT devices and show the trade-offs for employing them using TinyML.

This dissertation aims to explore Internet of Things (IoT) sensor nodes in various application scenarios with different design requirements. The research provides a comprehensive exploration of all the IoT layers composing an advanced device, from transducers to on-board processing, through low power hardware schemes and wireless protocols for wide area networks. Nowadays, spreading and massive utilization of wireless sensor nodes pushes research and industries to overcome the main limitations of such constrained devices, aiming to make them easily deployable at a lower cost. Significant challenges involve the battery lifetime that directly affects the device operativity and the wireless communication bandwidth. Factors that commonly contrast the system scalability and the energy per bit, as well as the maximum coverage. This thesis aims to serve as a reference and guideline document for future IoT projects, where results are structured following a conventional development pipeline. They usually consider communication standards and sensing as project requirements and low power operation as a necessity. A detailed overview of five leading IoT wireless protocols, together with custom solutions to overcome the throughput limitations and decrease the power consumption, are some of the topic discussed. Low power hardware engineering in multiple applications is also introduced, especially focusing on improving the trade-off between energy, functionality, and on-board processing capabilities. To enhance these features and to provide a bottom-top overview of an IoT sensor node, an innovative and low-cost transducer for structural health monitoring is presented. Lastly, the high-performance computing at the extreme edge of the IoT framework is addressed, with special attention to image processing algorithms running on state of the art RISC-V architecture. As a specific deployment scenario, an OpenCV-based stack, together with a convolutional neural network, is assessed on the octa-core PULP SoC.

Diabetic retinopathy (DR) is a leading cause of blindness worldwide, affecting millions of dia- betic patients. Early detection and accurate classification of DR stages are crucial for preventing vision loss and improving patient outcomes. This survey paper presents a comprehensive anal- ysis of deep learning approaches for automatic detection and classification of diabetic retinopa- thy from fundus images. The proposed system utilizes Faster Region-based Convolutional Neural Networks (Faster R-CNN) architecture to accurately identify and categorize the sever- ity of DR in retinal images. The methodology encompasses image acquisition using fundus cameras, preprocessing for quality enhancement, deep feature learning for data-driven char- acterizations, and classification into various DR stages including No DR, Mild DR, Moderate DR, Proliferative DR, and Severe DR. This automated approach offers significant advantages over traditional manual screening methods, providing faster, more consistent, and cost-effective diagnosis capabilities. The technical implementation focuses on developing robust algorithms for fundus image analysis, including preprocessing techniques for image enhancement, feature extraction using convolutional neural networks, and classification models optimized for medical imaging appli- cations. The system addresses challenges such as image quality variations, lighting conditions, and anatomical differences across patients. Performance evaluation encompasses accuracy met- rics, sensitivity, specificity, and area under the ROC curve (AUC) to ensure clinical reliability. The proposed Faster R-CNN architecture demonstrates superior performance compared to tra- ditional methods, achieving high accuracy in DR detection while maintaining computational efficiency suitable for clinical deployment. This automated screening system has the potential to significantly improve early detection rates, reduce healthcare costs, and enhance patient care quality in diabetic retinopathy management.