Brain tumor is a severe cancer and a life-threatening disease. Thus, early detection is crucial in the process of treatment. Recent progress in the field of deep learning has contributed enormously to the health industry medical diagnosis. Convolutional neural networks (CNNs) have been intensively used as a deep learning approach to detect brain tumors using MRI images. Due to the limited dataset, deep learning algorithms and CNNs should be improved to be more efficient. Thus, one of the most known techniques used to improve model performance is Data Augmentation. This paper presents a detailed review of various CNN architectures and highlights the characteristics of particular models such as ResNet, AlexNet, and VGG. After that, we provide an efficient method for detecting brain tumors using magnetic resonance imaging (MRI) datasets based on CNN and data augmentation. Evaluation metrics values of the proposed solution prove that it succeeded in being a contribution to previous studies in terms of both deep architectural design and high detection success.

As the paradigm shift toward Software as a Service (SaaS) continues to gain the interest of companies and the scientific community, performances must be optimal. Indeed, cloud providers must provide an optimal quality of service (QoS) for their users in order to survive in such a competitive cloud market. Workload forecasting techniques have been proposed in order to improve capacity planning, ensure efficient management of resources and, hence, maintain SLA contracts with end users. In this context, we propose a new approach to predict the number of requests arriving at a SaaS service in order to prepare the virtualized resources necessary to respond to user requests. The method will be implemented in order to simultaneously achieve a twofold benefit: obtain precise forecast results while optimizing response time. In this regard, we have chosen to control the computation time by dynamizing the size of the sliding window associated to the recent history to be analyzed, since the larger the size of the entry in the prediction model, the more the algorithmic complexity increases. Then, the prediction will be established based on the temporal locality principle and the dynamic assignment of weights to different data points in recent history. Moreover, the proposed method can be extended to cover other uses in prediction. Experiments were carried out to assess the performance of the proposed method using two real workload traces and compared to state-of-the-art methods. The proposed method offers a compromise between the execution time and the accuracy of the prediction.

The last years witnessed an explosive progress in networking, storage, and processing technologies resulting in an unprecedented amount of digitalization of data. Hence, there has been a considerable need for tools or techniques to delve and efficien