Brain tumors (BT) represent a severe and potentially life-threatening cancer. Failing to promptly diagnose these tumors can significantly shorten a person’s life. Therefore, early and accurate detection of brain tumors is essential, allowing for appropriate treatment and improving the chances of a patient’s survival. Due to the different characteristics and data limitations of brain tumors is challenging problems to classify the three different types of brain tumors. A convolutional neural networks (CNNs) learning algorithm integrated with data augmentation techniques was used to improve the model performance. CNNs have been extensively utilized in identifying brain tumors through the analysis of Magnetic Resonance Imaging (MRI) images The primary aim of this research is to propose a novel method that achieves exceptionally high accuracy in classifying the three distinct types of brain tumors. This paper proposed a novel Stack Ensemble Transfer Learning model called “SETL_BMRI”, which can recognize brain tumors in MRI images with elevated accuracy. The SETL_BMRI model incorporates two pre-trained models, AlexNet and VGG19, to improve its ability to generalize. Stacking combined outputs from these models significantly improved the accuracy of brain tumor detection as compared to individual models. The model’s effectiveness is evaluated using a public brain MRI dataset available on Kaggle, containing images of three types of brain tumors (meningioma, glioma, and pituitary). The experimental findings showcase the robustness of the SETL_BMRI model, achieving an overall classification accuracy of 98.70%. Additionally, it delivers an average precision, recall, and F1-score of 98.75%, 98.6%, and 98.75%, respectively. The evaluation metric values of the proposed solution indicate that it effectively contributed to previous research in terms of achieving high detection accuracy.

In the therapy of Coronavirus, the drug target is a demanding task to find novel medicine. A bunch of pharmaceutics procedures are employed to recognize these mutual actions. But they are exhausting and high-priced. Keeping this in view, computational procedures are widely approached to determine the mutual action of the medicine and their respective proteins. Many scientists have applied ML approaches to deduce attributes from simplified molecular-input line systems (for medicine) and protein sequences. Such approaches dropped the proteins' chemical, physical, and structural characteristics and the respective medicine. Our job is to undertake deep learning approaches to detect coronavirus enzyme correspondence with the validated Chembl database medicine. The representation of the molecular structure of proteins, medically known as fingerprints, will be done scientifically. Then, a deep learning model will be given training on the pulled-out fingerprints and the properties of molecules to determine the interplay of the medicine with the respective catalyst. The suggested approach will be proficient in recognizing the catalyst's interactivity with the approved database medicine.

The current world revolves around data. Internet predicts that there are currently 2.8 million devices connected to the Internet. It spans the largest web with almost six connected devices per person. Cloud infrastructure is reaching its maximum capacity and hence needs upgrading. Fog Computing is a viable addition. This infrastructure upgrade also includes a suitable routing algorithm and its complement switching topologies. Adding self-learning capabilities to such a network implies the notion of Zero-Touch Networks. A pivotal point in Zero-Touch Networks is the selection of an optimal machine-learning algorithm. One such algorithm is Federated learning which relies on local updates of a global model. This paper revolves around, the analysis of energy consumption of a Federated learning-based utility supervision architecture for Zero-Touch Networks, by comparing it to a Cloud-Fog architecture. The initial test results were obtained through simulation on ‘iFogSim’. The analysis utilizes linear regression for prediction. The results depict lower initial values and less variation in a Federated learning-based architecture, as compared to Cloud-Fog architecture.

Ubiquitous computing is the most dominant technology using in the all of kind of businesses now a days. Mobile computing plays a key role in Ubiquitous computing due to data management as mobile computing creating a lot of challenged for data management. In the 21 st century, people are preferring to move towards mobile devices and this creating more data ever before. Researchers and institutions are working hard to secure and manage the increasing volume of data smart tablet, smartphones and mobile gadget. To make data effective and efficient then the information should be transferred from one mobile device to another device with less security hazards and loss of data. Entity aware data management on Mobile devices (EDMD) is a new research area for providing better solution in term of intelligence, efficiency and scalability for management of data on smart or mobile devices. Traditionally data management is limited to structured data due to predefined system of organization and process but by the introduction of EDMD for unstructured data the researcher and industry now can solve most complicated problem of computation. As a result, mobile devices are now enabling new computing application in term of social networking to real time information processing. To get maximum benefits

In our research study spanning 2015-2021, we analyzed Software Engineering (SE) across 15 Knowledge Areas (KAs) outlined by SWEBoK. Using Web of Science (WoS) database, we examined 32,232 articles (2015-2017), 31,459 articles (2018-2020), and 6,919 articles (2021). Collaborative and co-word networks were generated using VOS Viewer. Our findings reveal SE's influence in 81 research areas. English dominated, but Spanish and Portuguese were notable. Europe led in publications, with USA and China prominent. Stronger collaboration networks, especially in the USA and China, correlated with increased research output. Asian countries' rise was evident from 2018-2021. Top 10 highly cited papers and co-word analysis were included, aiding researchers and educators. SE's impact crossed domains, enabling cross-disciplinary research and informing educators' course designs. Institutional and country productivity influenced partnerships and academia-industry collaborations. Multinational companies gauged research potential through active countries. Analyzing co-words depicted trends, and highly cited papers set industry standards. Bibliometric analysis offered qualitative and quantitative research evaluation.

A critical aspect of the widespread adoption of data science is the availability of low-cost processors for data mining and analysis. Since they focus on wearable devices, they can provide real-time features through multiple connections via ubiquitous data science. With increased features associated with wireless device convergence and current technological advancements, ubiquitous hardware and architecture innovations must be considered. Moreover, the hardware utilized in ubiquitous systems must be capable of decision-making, high-speed processing, information convergence, sociability, reduced visual clutter, and goal-oriented design. The objective of effective data analysis may be accomplished via the combination of fuzzy model approaches, effective artificial neural networks, reinforcement learning models, convolutional neural networks, and deep learning models. Data marts may be used to improve the design of ubiquitous systems. Specifically, data marts offer an enhanced mechanism for accessing server-side data that are updated frequently. Additionally, the data mart incorporates the capability that has been introduced to the location-based business analysis data depending on the geographic location of the device and collected data. Indeed, data marts might be used in conjunction with data visualization approaches, depending on the data management requirements. Visualization of the data allows for interfaces with data sources irrespective of the type of data format and the geographical location.