A leading cause of mortality globally, skin cancer is deadly. Early skin cancer diagnosis reduces mortality. Visual inspection is the main skin cancer diagnosis tool; however, it is imprecise. Researchers propose deep-learning techniques to assist physicians identify skin tumors fast and correctly. Deep convolutional neural networks (CNNs) can identify distinct objects in complex tasks. We train a CNN on photos with merely pixels and illness labels to classify skin lesions. We train on HAM-10000 using a CNN. On the HAM10000 dataset, the suggested model scored 95.23% efficiency, 95.30% sensitivity, and 95.91% specificity.

Acute Lymphoblastic Leukemia (ALL) is a malignant neoplasm defined by the rapid proliferation of early lymphoid progenitors (lymphoblasts) within the bone marrow and peripheral blood. Due to its aggressive course, prompt and accurate diagnosis is essential and has a profound impact on patient outcomes. This study proposes an integrative deep learning method for ALL detection using the Acute Lymphoblastic Leukemia Image Database (ALL-IDB). This is accomplished by fusing one modified clinical data CNN integrated through an attention mechanism with another modified pre-trained CNN for image analysis. The performance of the proposed model was evaluated using the ALL-IDB1 and ALL-IDB2 datasets, achieving 99.2% accuracy with AUC at 0.998%. By incorporating clinical with image data, an overall increase of 2.3% in accuracy and 0.007 in AUC was observed. The results show that using deep learning to detect ALL is accurate and possible, laying the foundations for AI-based diagnoses of hematological cancers to be more accurate.

Microservices are being used by businesses to split monolithic software into a set of small services whose instances run independently in containers. Load balancing and auto-scaling are important cloud features for cloud-based container microservices because they control the number of resources available. The current issues concerning load balancing and auto-scaling techniques in Cloud-based container microservices were investigated in this paper. Server overloaded, service failure and traffic spikes were the key challenges faced during the microservices communication phase, making it difficult to provide better Quality of Service (QoS) to users. The aim is to critically investigate the addressed issues related to Load balancing and Auto-scaling in Cloud-based Container Microservices (CBCM) in order to enhance performance for better QoS to the users.

The rapid expansion of the use of the Internet of Things (IoT) has encouraged many attackers to exploit the vulnerabilities in these networks to violate data privacy or disrupt service; they are easy targets due to the diversity of devices within the network, which has led to the loss of unified security standards. intrusion detection system (IDS) play a pivotal role in securing IoT networks by monitoring inbound and outbound traffic to these networks and issuing a security alarm when there is an attack; moreover, they respond directly to these security threats to prevent them from harming the network and violating data privacy. To design an IDS capable of performing work with high efficiency, an appropriate dataset must be chosen to train and evaluate the designed model. This dataset works as a fundamental task in the success of these systems because it plays a major role in training the system, feature engineering, evaluating the performance of the model, and other tasks. This paper focused on one of the modern datasets used in training and evaluating IDS models, that is, the CICIOT2023 dataset. The CICIOT2023 dataset is distinguished from other datasets, such as CICIDS2017, UNSW-NB15, and KDD1999. It focuses on the IoT environment, unlike other datasets that focus on data traffic in traditional networks, and it uses a variety of devices and protocols; moreover, it contains modern and complex attacks and a balance between the data of those attacks and normal traffic. This paper discusses the structure of the dataset, the kinds of attacks it contains, the applications and fields in which it is used, the strengths that distinguish it from other datasets, its role in developing cybersecurity research, the most important studies that have been written and dealt with this dataset, and finally, the future visions for developing the dataset.

With the modern invention of high-quality sensors and smart chips with high computational power, smart devices like smartphones and smart wearable devices are becoming primary computing sources for routine life. These devices, collectively, might possess an enormous amount of valuable data but due to privacy concerns and privacy laws like General Data Protection Regulation (GDPR), this enormous amount of very valuable data is not available to train models for more accurate and efficient AI applications. Federated Learning (FL) has emerged as a very prominent collaborative learning technique to learn from such decentralized private data while reasonably satisfying the privacy constraints. To learn from such decentralized and massively distributed data, federated learning needs to overcome some unique challenges like system heterogeneity, statistical heterogeneity, communication, model heterogeneity, privacy, and security. In this article, to begin with, we explain some fundamentals of federated learning along with the definition and applications of FL. Subsequently, we further explain the unique challenges of FL while critically covering recently proposed approaches to handle them. Furthermore, this paper also discusses some relatively novel challenges for federated learning. To conclude, we discuss some future research directions in the domain of federated learning.