The coronavirus disease (COVID-19) is rapidly spreading around the world. Early diagnosis and isolation of COVID-19 patients has proven crucial in slowing the disease’s spread. One of the best options for detecting COVID-19 reliably and easily is to use deep learning (DL) strategies. Two different DL approaches based on a pertained neural network model (ResNet-50) for COVID-19 detection using chest X-ray (CXR) images are proposed in this study. Augmenting, enhancing, normalizing, and resizing CXR images to a fixed size are all part of the preprocessing stage. This research proposes a DL method for classifying CXR images based on an ensemble employing multiple runs of a modified version of the Resnet-50. The proposed system is evaluated against two publicly available benchmark datasets that are frequently used by several researchers: COVID-19 Image Data Collection (IDC) and CXR Images (Pneumonia). The proposed system validates its dominance over existing methods such as VGG or Densnet, with values exceeding 99.63% in many metrics, such as accuracy, precision, recall, F1-score, and Area under the curve (AUC), based on the performance results obtained.

Monkeypox (MPX) is a disease caused by monkeypox virus (MPXV). It is a contagious disease and has associated symptoms of skin lesions, rashes, fever, and respiratory distress lymph swelling along with numerous neurological distresses. This can be a deadly disease, and the latest outbreak of it has shown its spread to Europe, Australia, the United States, and Africa. Typically, diagnosis of MPX is performed through PCR, by taking a sample of the skin lesion. This procedure is risky for medical staff, as during sample collection, transmission and testing, they can be exposed to MPXV, and this infectious disease can be transferred to medical staff. In the current era, cutting-edge technologies such as IoT and artificial intelligence (AI) have made the diagnostics process smart and secure. IoT devices such as wearables and sensors permit seamless data collection while AI techniques utilize the data in disease diagnosis. Keeping in view the importance of these cutting-edge technologies, this paper presents a non-invasive, non-contact, computer-vision-based method for diagnosis of MPX by analyzing skin lesion images that are more smart and secure compared to traditional methods of diagnosis. The proposed methodology employs deep learning techniques to classify skin lesions as MPXV positive or not. Two datasets, the Kaggle Monkeypox Skin Lesion Dataset (MSLD) and the Monkeypox Skin Image Dataset (MSID), are used for evaluating the proposed methodology. The results on multiple deep learning models were evaluated using sensitivity, specificity and balanced accuracy. The proposed method has yielded highly promising results, demonstrating its potential for wide-scale deployment in detecting monkeypox. This smart and cost-effective solution can be effectively utilized in underprivileged areas where laboratory infrastructure may be lacking.

Social networks such as twitter have emerged as social platforms that can impart a massive knowledge base for people to share their unique ideas and perspectives on various topics and issues with friends and families. Sentiment analysis based on machine learning has been successful in discovering the opinion of the people using redundantly available data. However, recent studies have pointed out that imbalanced data can have a negative impact on the results. In this paper, we propose a framework for improved sentiment analysis through various ordered preprocessing steps with the combination of resampling of minority classes to produce greater performance. The performance of the technique can vary depending on the dataset as its initial focus is on feature selection and feature combination. Multiple machine learning algorithms are utilized for the classification of tweets into positive, negative, or neutral. Results have revealed that random minority oversampling can provide improved performance and it can tackle the issue of class imbalance.

The Internet of Things (IoT) refers to a system of interconnected, internet-connected devices and sensors that allows the collection and dissemination of data. The data provided by these sensors may include outliers or exhibit anomalous behavior as a result of attack activities or device failure, for example. However, the majority of existing outlier detection algorithms rely on labeled data, which is frequently hard to obtain in the IoT domain. More crucially, the IoT’s data volume is continually increasing, necessitating the requirement for predicting and identifying the classes of future data. In this study, we propose an unsupervised technique based on a deep Variational Auto-Encoder (VAE) to detect outliers in IoT data by leveraging the characteristic of the reconstruction ability and the low-dimensional representation of the input data’s latent variables of the VAE. First, the input data are standardized. Then, we employ the VAE to find a reconstructed output representation from the low-dimensional representation of the latent variables of the input data. Finally, the reconstruction error between the original observation and the reconstructed one is used as an outlier score. Our model was trained only using normal data with no labels in an unsupervised manner and evaluated using Statlog (Landsat Satellite) dataset. The unsupervised model achieved promising and comparable results with the state-of-the-art outlier detection schemes with a precision of ≈90% and an F1 score of 79%.

Security and performance (SAP) are two critical NFRs that affect the successful completion of software projects. Organizations need to follow the practices that are vital to SAP verification. These practices must be incorporated into the software development process to identify SAP-related defects and avoid failures after deployment. This can only be achieved if organizations are fully aware of SAP verification activities and appropriately include them in the software development process. However, there is a lack of awareness of the factors that influence SAP verification, which makes it difficult for businesses to improve their verification efforts and ensure that the released software meets these requirements. To fill this gap, this research study aimed to identify the mediating factors (MFs) influencing SAP verification and the actions to promote them. Ten MFs and their corresponding actions were identified after thoroughly reviewing the existing literature. The mapping of MFs and their corresponding actions were initially evaluated with the help of a pilot study. Mathematical modeling was utilized to model these MFs and examine each MF’s unique effect on software SAP verification. In addition, two case studies with a small- and a medium-sized organization were used to better understand the function these MFs play in the process of SAP verification. The research findings suggested that MFs assist software development organizations in their efforts to integrate SAP verification procedures into their standard software systems. Further investigation is required to support the understanding of these MFs when building modern software systems.