The Internet of Things (IoT) concept has emerged to improve people’s lives by providing a wide range of smart and connected devices and applications in several domains, such as green IoT-based agriculture, smart farming, smart homes, smart transportation, smart health, smart grid, smart cities, and smart environment. However, IoT devices are at risk of cyber attacks. The use of deep learning techniques has been adequately adopted by researchers as a solution in securing the IoT environment. Deep learning has also successfully been implemented in various fields, proving its superiority in tackling intrusion detection attacks. Due to the limitation of signature-based detection for unknown attacks, the anomaly-based Intrusion Detection System (IDS) gains advantages to detect zero-day attacks. In this paper, a systematic literature review (SLR) is presented to analyze the existing published literature regarding anomaly-based intrusion detection, using deep learning techniques in securing IoT environments. Data from the published studies were retrieved from five databases (IEEE Xplore, Scopus, Web of Science, Science Direct, and MDPI). Out of 2116 identified records, 26 relevant studies were selected to answer the research questions. This review has explored seven deep learning techniques practiced in IoT security, and the results showed their effectiveness in dealing with security challenges in the IoT ecosystem. It is also found that supervised deep learning techniques offer better performance, compared to unsupervised and semi-supervised learning. This analysis provides an insight into how the use of data types and learning methods will affect the performance of deep learning techniques for further contribution to enhancing a novel model for anomaly intrusion detection and prediction.

Metaverse is a vast term that can contain every digital thing in the future. Therefore, life domains, such as learning and education, should have their systems redirected to adopt this topic to keep their availability and longevity. Many papers have discussed the metaverse, the applications to run on, and the historical progress to have the metaverse the way it is today. However, the framework of the metaverse itself is still unclear, and its components cannot be exactly specified. Although E-Learning systems are a need that has developed over the years along with technology, the structures of the available E-Learning systems based on the metaverse are either not well described or are adopted, in their best case, as just a 3D environment. In this paper, we examine some previous works to find out the special technologies that should be provided by the metaverse framework, then we discuss the framework of the metaverse if applied as an E-Learning environment framework. This will make it easy to develop future metaverse-based applications, as the proposed framework will make the virtual learning environments work smoothly on the metaverse. In addition, E-Learning will be a more interactive and pleasant process.

The concept of molecular similarity has been commonly used in rational drug design, where structurally similar molecules are examined in molecular databases to retrieve functionally similar molecules. The most used conventional similarity methods used two-dimensional (2D) fingerprints to evaluate the similarity of molecules towards a target query. However, these descriptors include redundant and irrelevant features that might impact the performance of similarity searching methods. Thus, this study proposed a new approach for identifying the important features of molecules in chemical datasets based on the representation of the molecular features using Autoencoder (AE), with the aim of removing irrelevant and redundant features. The proposed approach experimented using the MDL Data Drug Report standard dataset (MDDR). Based on experimental findings, the proposed approach performed better than several existing benchmark similarity methods such as Tanimoto Similarity Method (TAN), Adapted Similarity Measure of Text Processing (ASMTP), and Quantum-Based Similarity Method (SQB). The results demonstrated that the performance achieved by the proposed approach has proven to be superior, particularly with the use of structurally heterogeneous datasets, where it yielded improved results compared to other previously used methods with the similar goal of improving molecular similarity searching.

The rise of the Internet of things (IoT) provides an intelligent environment. However, it demands a higher security effort due to its vulnerabilities. A number of studies have emphasized the area of anomaly intrusion detection and its use in various types of applications. The development of a robust anomaly intrusion detection system relies heavily on understanding complex structures from noisy data, identifying dynamic anomaly patterns, and detecting anomalies with insufficient labels. Therefore, an advanced approach of deep learning techniques is required for the purpose of achieving improved performance of anomaly detection rather than the unconventional approaches of shallow learning. However, the immense adaptations of IoT in major devices result in an increase in data usage and higher computational requirements. Hence, this work highlights a review on anomaly intrusion detection utilizing deep learning approaches with a focus on resource-constrained devices’ application within the domain of IoT in real-world challenges. Based on findings, the performance of deep learning in anomaly detection is proven to be superior in regard to accuracy detection and false alarm rate. However, further work on deep learning techniques should be carried out to ensure the robustness of IDS.

No abstract