Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
6,856
result(s) for
"Ala"
Sort by:
A Multi-Layer Classification Approach for Intrusion Detection in IoT Networks Based on Deep Learning
The security of IoT networks is an important concern to researchers and business owners, which is taken into careful consideration due to its direct impact on the availability of the services offered by IoT devices and the privacy of the users connected with the network. An intrusion detection system ensures the security of the network and detects malicious activities attacking the network. In this study, a deep multi-layer classification approach for intrusion detection is proposed combining two stages of detection of the existence of an intrusion and the type of intrusion, along with an oversampling technique to ensure better quality of the classification results. Extensive experiments are made for different settings of the first stage and the second stage in addition to two different strategies for the oversampling technique. The experiments show that the best settings of the proposed approach include oversampling by the intrusion type identification label (ITI), 150 neurons for the Single-hidden Layer Feed-forward Neural Network (SLFN), and 2 layers and 150 neurons for LSTM. The results are compared to well-known classification techniques, which shows that the proposed technique outperforms the others in terms of the G-mean having the value of 78% compared to 75% for KNN and less than 50% for the other techniques.
Journal Article
Competing Endogenous RNAs, Non-Coding RNAs and Diseases: An Intertwined Story
MicroRNAs (miRNAs), a class of small non-coding RNA molecules, are responsible for RNA silencing and post-transcriptional regulation of gene expression. They can mediate a fine-tuned crosstalk among coding and non-coding RNA molecules sharing miRNA response elements (MREs). In a suitable environment, both coding and non-coding RNA molecules can be targeted by the same miRNAs and can indirectly regulate each other by competing for them. These RNAs, otherwise known as competing endogenous RNAs (ceRNAs), lead to an additional post-transcriptional regulatory layer, where non-coding RNAs can find new significance. The miRNA-mediated interplay among different types of RNA molecules has been observed in many different contexts. The analyses of ceRNA networks in cancer and other pathologies, as well as in other physiological conditions, provide new opportunities for interpreting omics data for the field of personalized medicine. The development of novel computational tools, providing putative predictions of ceRNA interactions, is a rapidly growing field of interest. In this review, I discuss and present the current knowledge of the ceRNA mechanism and its implications in a broad spectrum of different pathologies, such as cardiovascular or autoimmune diseases, cancers and neurodegenerative disorders.
Journal Article
Can Exposure to Celebrities Reduce Prejudice? The Effect of Mohamed Salah on Islamophobic Behaviors and Attitudes
Can exposure to celebrities from stigmatized groups reduce prejudice? To address this question, we study the case of Mohamed Salah, a visibly Muslim, elite soccer player. Using data on hate crime reports throughout England and 15 million tweets from British soccer fans, we find that after Salah joined Liverpool F.C., hate crimes in the Liverpool area dropped by 16% compared with a synthetic control, and Liverpool F.C. fans halved their rates of posting anti-Muslim tweets relative to fans of other top-flight clubs. An original survey experiment suggests that the salience of Salah’s Muslim identity enabled positive feelings toward Salah to generalize to Muslims more broadly. Our findings provide support for the parasocial contact hypothesis—indicating that positive exposure to out-group celebrities can spark real-world behavioral changes in prejudice.
Journal Article
Compact wideband antenna for wireless capsule endoscopy system
This paper proposes an implantable antenna to be used in either planar or conformal arrangements for implanted biomedical devices. The proposed antenna has a wide bandwidth characteristic. When it is in a conformal shape, the antenna can be used for wireless capsule endoscopy applications. In addition, the antenna can be a good candidate for biotelemetry applications while it is planar. A cubic phantom model was adopted in simulations for the initial design and optimization of the conformal antenna structure. The antenna was designed on the outer wall of the capsule to provide more space for other electronics inside. Implanted antennas are subject to detuning effects due to the proximity of various tissues in the gastrointestinal tract, presence of the electronic module in the capsule, different biocompatible coating thicknesses, and different bending conditions. Having a wide bandwidth makes this antenna less sensitive to these detuning effects. Performance of the proposed antenna was experimentally validated in the planar and conformal forms by using a solid muscle-mimicking phantom. Based on measurements, antenna exhibits wide impedance bandwidths, from 170 to 3500 MHz for the conformal antenna, and from 650 to 3600 MHz for the planar antenna inside muscle tissue phantom.
Journal Article
An Adaptive Security Framework for Internet of Things Networks Leveraging SDN and Machine Learning
The Internet of Things (IoT) is expanding rapidly with billions of connected devices worldwide, necessitating robust security solutions to protect these systems. This paper proposes a comprehensive and adaptive security framework called Enhanced Secure Channel Authentication using random forests and software-defined networking (SCAFFOLD), tailored for IoT environments. The framework establishes secure communication channels between IoT nodes using software-defined networking (SDN) and machine learning techniques. The key components include encrypted channels using session keys, continuous traffic monitoring by the SDN controller, ensemble machine-learning for attack detection, precision mitigation via SDN reconfiguration, and periodic reauthentication for freshness. A mathematical model formally defines the protocol. Performance evaluations via extensive simulations demonstrate Enhanced SCAFFOLD’s ability to reliably detect and rapidly mitigate various attacks with minimal latency and energy consumption overheads across diverse IoT network scenarios and traffic patterns. The multidimensional approach combining encryption, intelligent threat detection, surgical response, and incremental hardening provides defense-in-depth to safeguard availability, integrity, and privacy within modern IoT systems while preserving quality of service.
Journal Article