Brain tumor is one of the most aggressive diseases nowadays, resulting in a very short life span if it is diagnosed at an advanced stage. The treatment planning phase is thus essential for enhancing the quality of life for patients. The use of Magnetic Resonance Imaging (MRI) in the diagnosis of brain tumors is extremely widespread, but the manual interpretation of large amounts of images requires considerable effort and is prone to human errors. Hence, an automated method is necessary to identify the most common brain tumors. Convolutional Neural Network (CNN) architectures are successful in image classification due to their high layer count, which enables them to conceive the features effectively on their own. The tuning of CNN hyperparameters is critical in every dataset since it has a significant impact on the efficiency of the training model. Given the high dimensionality and complexity of the data, manual hyperparameter tuning would take an inordinate amount of time, with the possibility of failing to identify the optimal hyperparameters. In this paper, we proposed a Bayesian Optimization-based efficient hyperparameter optimization technique for CNN. This method was evaluated by classifying 3064 T-1-weighted CE-MRI images into three types of brain tumors (Glioma, Meningioma, and Pituitary). Based on Transfer Learning, the performance of five well-recognized deep pre-trained models is compared with that of the optimized CNN. After using Bayesian Optimization, our CNN was able to attain 98.70% validation accuracy at best without data augmentation or cropping lesion techniques, while VGG16, VGG19, ResNet50, InceptionV3, and DenseNet201 achieved 97.08%, 96.43%, 89.29%, 92.86%, and 94.81% validation accuracy, respectively. Moreover, the proposed model outperforms state-of-the-art methods on the CE-MRI dataset, demonstrating the feasibility of automating hyperparameter optimization.

The next generation’s sensor nodes will be more intelligent, energy conservative, and perpetual lifetime in the set-up of wireless sensor networks (WSNs). These sensors nodes are facing the overwhelming challenge of energy consumption which gradually decreases the lifetime of overall network. The wireless power transfer (WPT) is one of the most emerging technologies of energy harvesting that deploys at the heart of sensor nodes for efficient lifetime solution. A wireless portable charging device (WPCD) is drifting inside the WSN to recharge all the nodes which are questing for the eternal life. In this paper, we aspire to optimize a multi-objective function for charging trail of WPCD, and self-learning algorithm for data routing jointly. We formulated that the objective functions can optimize the fair energy consumption as well as maximize the routing efficiency of WPCD. The fundamental challenge of the problem is, to integrate the novel path for WPCD by applying the Nodal A* algorithm. We proposed a novel method of sensor node’s training for intellectual data transmission by using of clustering and reinforcement learning (SARSA) defined as clustering SARSA (C-SARSA) along with an optimal solution of objective functions. The whole mechanism outperforms in terms of trade-off between energy consumption and stability (fair energy consumption among all nodes) of the WSN; moreover, it prolongs the lifetime of the WSN. The simulated results demonstrate that our proposed method did better than compared literature in terms of energy consumption, stability, and lifetime of the WSN.

An app store (i.e., Google Play) is a platform for mobile apps for almost every software and service. App stores allow users to browse and download apps and facilitate developers to keep an eye on their apps by providing ratings and reviews of the apps. App reviews may include the user’s experience, information about bugs, request for new features, or rating of the app in word. The manual categorization of app reviews is critical and time-consuming for developers. Automatic classification of app reviews may help developers especially for fixing bugs on time. In this perspective, several approaches have been proposed for the automatic classification of reviews. However, none of them exploits the non-textual information of app reviews. In this paper, we propose a deep learning based approach for the classification of app reviews. It does not only leverage non-textual information of app reviews but also exploits a deep learning technique that has proved more accurate for the text classification in various domains. The approach first extracts textual and nontextual information of each app review, preprocesses the textual information, computes the sentiment of app reviews using Senti4SD, and determines the history of the reviewer includes the total number of reviews posted by the reviewer, and his submission rate (i.e., what percentages of his review have been submitted for the associated app). Second, we create a digital vector against each app review. Finally, we train a deep learning based multi-class classifier to classify app reviews. The proposed approach is evaluated on a public dataset, and the results suggest that it significantly improves the state of the art. It improves average precision from 75.72% to 95.49%, average recall from 69.40% to 93.94%, and f-measure from 72.41% to 94.71%, respectively.

Pattern synthesis is a significant research focus in smart antennas due to its extensive use in several radar and communication systems. To improve the optimization performance of pattern synthesis of uniform and sparse linear antenna array, this paper presents an optimization method for solving the antenna array synthesis problem using the Mayfly Algorithm (MA). MA is a new heuristic algorithm inspired by the flight behavior as well as the mating process of mayflies, it has a unique velocity update system with great convergence. In this work, the MA was applied to linear antenna arrays (LAA) for optimal pattern synthesis in the following ways: by optimizing the antenna current amplitudes while maintaining uniform spacing and by optimizing the antenna positions while assuming a uniform excitation. Constraints of inter-element spacing and aperture length are imposed in the synthesis of sparse LAA. Sidelobe level (SLL) suppression with the placement of nulls in the specified directions is also implemented. The results gotten from this novel algorithm are validated by benchmarking with results obtained using other intelligent algorithms. In the synthesis of uniform 20-element LAA with nulls, MA achieved an SLL of −31.27 dB and the deepest null of −101.60 dB. Also, for sparse 20-element LAA, an SLL of −18.85 dB was attained alongside the deepest null of −87.37 dB. MA obtained an SLL of −35.73 dB and −23.68 dB for the synthesis of uniform and sparse 32-element LAA respectively. Finally, electromagnetism simulations are conducted using ANSYS Electromagnetics (HFSS) software, to evaluate the performance of MA for the beam pattern optimizations, taking into consideration the mutual coupling effects. The results prove that optimization of LAA using MA provides considerable enhancements in peak SLL suppression, null control, and convergence rate with respect to the uniform array and the synthesis obtained from other existing optimization techniques.