Nowadays, brain tumors have become a leading cause of mortality worldwide. The brain cells in the tumor grow abnormally and badly affect the surrounding brain cells. These cells could be either cancerous or non-cancerous types, and their symptoms can vary depending on their location, size, and type. Due to its complex and varying structure, detecting and classifying the brain tumor accurately at the initial stages to avoid maximum death loss is challenging. This research proposes an improved fine-tuned model based on CNN with ResNet50 and U-Net to solve this problem. This model works on the publicly available dataset known as TCGA-LGG and TCIA. The dataset consists of 120 patients. The proposed CNN and fine-tuned ResNet50 model are used to detect and classify the tumor or no-tumor images. Furthermore, the U-Net model is integrated for the segmentation of the tumor regions correctly. The model performance evaluation metrics are accuracy, intersection over union, dice similarity coefficient, and similarity index. The results from fine-tuned ResNet50 model are IoU: 0.91, DSC: 0.95, SI: 0.95. In contrast, U-Net with ResNet50 outperforms all other models and correctly classified and segmented the tumor region.

Cancer associated with the nervous system and brain tumors ranks among the leading causes of death in various countries. Magnetic resonance imaging (MRI) and computed tomography (CT) capture brain images. MRI is pivotal in diagnosing brain tumors and analyzing other brain disorders. Typically, radiologists or experts manually assess MRI images to detect brain tumors and abnormalities in the early stages for appropriate treatment. However, early brain tumor diagnosis is complex, necessitating computerized methods. This research introduces a novel approach for the automated segmentation of brain tumors and a framework for classifying brain tumor regions. The proposed methods comprise several stages: preprocessing, enhancing the coherence of MRI brain images using Contrast Limited Adaptive Histogram Equalization (CLAHE) and diffusion filtering in the first two steps, followed by the segmentation of the region of interest using the Fuzzy C-Means (FCM) clustering technique in the third step. The last step involves classification using the Support Vector Machine (SVM) classifier. The classifier is applied to different brain tumor types, from meningioma to pituitary tumors, utilizing the CE-MRI database. The proposed method exhibits significantly improved contrast and proves the effectiveness of the classification framework, achieving an average sensitivity of 0.977, specificity of 0.979, accuracy of 0.982, and a Dice score (DSC) of 0.961. Furthermore, this method demonstrates a shorter processing time of 0.42 seconds compared to existing approaches. The performance of this method underscores its significance when compared to state-of-the-art methods in terms of sensitivity, specificity, accuracy, and DSC. For future enhancements, it is possible to standardize the approach by incorporating a set of classifiers to increase the robustness of the brain classification method.

A brain tumor is a significant health concern that directly or indirectly affects thousands of people worldwide. The early and accurate detection of brain tumors is vital to the successful treatment of brain tumors and the improved quality of life of the patient. There are several imaging techniques used for brain tumor detection. Among these techniques, the most common are MRI and CT scans. To overcome the limitations associated with these traditional techniques, computer-aided analysis of brain images has gained attention in recent years as a promising approach for accurate and reliable brain tumor detection. In this study, we proposed a fine-tuned vision transformer model that uses advanced image processing and deep learning techniques to accurately identify the presence of brain tumors in the input data images. The proposed model FT-ViT involves several stages, including the processing of data, patch processing, concatenation, feature selection and learning, and fine tuning. Upon training the model on the CE-MRI dataset containing 5712 brain tumor images, the model could accurately identify the tumors. The FT-Vit model achieved an accuracy of 98.13%. The proposed method offers high accuracy and can significantly reduce the workload of radiologists, making it a practical approach in medical science. However, further research can be conducted to diagnose more complex and rare types of tumors with more accuracy and reliability.

Privacy-preserving techniques allow private information to be used without compromising privacy. Most encryption algorithms, such as the Advanced Encryption Standard (AES) algorithm, cannot perform computational operations on encrypted data without first applying the decryption process. Homomorphic encryption algorithms provide innovative solutions to support computations on encrypted data while preserving the content of private information. However, these algorithms have some limitations, such as computational cost as well as the need for modifications for each case study. In this paper, we present a comprehensive overview of various homomorphic encryption tools for Big Data analysis and their applications. We also discuss a security framework for Big Data analysis while preserving privacy using homomorphic encryption algorithms. We highlight the fundamental features and tradeoffs that should be considered when choosing the right approach for Big Data applications in practice. We then present a comparison of popular current homomorphic encryption tools with respect to these identified characteristics. We examine the implementation results of various homomorphic encryption toolkits and compare their performances. Finally, we highlight some important issues and research opportunities. We aim to anticipate how homomorphic encryption technology will be useful for secure Big Data processing, especially to improve the utility and performance of privacy-preserving machine learning.

Significant yield challenges are posed by biotic stress on coffee leaves, which has a negative effect on the revenue generation of this highly utilized commodity. Numerous studies have proposed techniques for the early detection and classification of biotic stress in coffee leaves. In this study, we propose a technique called extracted feature ensemble (EFE) for classifying healthy and infected classes. Transfer learning-based convolutional neural networks (CNNs) and custom-designed features are used to improve classification performance. Under the concept of EFE, three methodologies are proposed for evaluating various extracted feature combinations and determining the effect of dimensionality on the performance of the model. In addition, a semi-segmentation approach is used to guide the extraction of informative foreground details, while non-segmented inputs are used to improve the model’s robustness against complex background noise. By improving three open-source datasets for biotic stress categorization in coffee leaves, a new dataset was created and employed. The first proposed method, ECNN, focused on the effective concatenation of five CNNs and obtained a classification accuracy of 93.45% using a decision tree classifier, exceeding the maximum individual accuracy of 86.07% from Mobile-Net v3 features. In addition, the HLGGM method was investigated, which demonstrated an enhanced accuracy of 99.16% by combining dimension-reduced Mobile-Net v3 features with handcrafted features. HLGCM, the final approach represented, aimed at extracting features from dimensionality-reduced handmade and CNN-based data, and ultimately succeeded in accomplishing an accuracy of 99.49 percent by using decision tree model. The obtained results demonstrate the efficacy of feature concatenation in enhancing the classification model’s discriminative capabilities and classification accuracy. The appropriate combination of hand-made and CNN-based features gives better accuracy and interesting insights into the effect of feature reduction on model classification efficiency. The article offers dimensionality reduction, directed learning, and feature concatenation techniques for identifying coffee leaf diseases. This work can aid in the development of computationally efficient and accurate disease control and coffee plant sustainability strategies.

The amazing fusion of the internet of things (IoT) into traditional health monitoring systems has produced remarkable advances in the field of e-health. Different wireless body area network devices and sensors are providing real-time health monitoring services. As the number of IoT devices is rapidly booming, technological and security challenges are also rising day by day. The data generated from sensor-based devices need confidentiality, integrity, authenticity, and end-to-end security for safe communication over the public network. IoT-based health monitoring systems work in a layered manner, comprising a perception layer, a network layer, and an application layer. Each layer has some security, and privacy concerns that need to be addressed accordingly. A lot of research has been conducted to resolve these security issues in different domains of IoT. Several frameworks for the security of IoT-based e-health systems have also been developed. This paper introduces a security framework for real-time health monitoring systems to ensure data confidentiality, integrity, and authenticity by using two common IoT protocols, namely constrained application protocol (CoAP) and message query telemetry transports (MQTT). This security framework aims to defend sensor data against the security loopholes while it is continuously transmitting over the layers and uses hypertext transfer protocols (HTTPs) for this purpose. As a result, it shields from the breach with a very low ratio of risk. The methodology of this paper focuses on how the security framework of IoT-based real-time health systems is protected under the tiers of CoAP and HTTPs. CoAP works alongside HTTPs and is responsible for providing end-to-end security solutions.