Abstract

A large-scale model of brain dynamics, as it is manifested in functional neuroimaging data, is presented in this study. The model is built around a general trainable network of Hopf oscillators, the dynamics of which are described in the complex domain. It was shown earlier that when a pair of Hopf oscillators are coupled by power coupling with a complex coupling strength, it is possible to stabilize the normal phase difference at a value related to the angle of the complex coupling strength. In the present model, the magnitudes of the complex coupling weights are set using the Structural Connectivity information obtained from Diffusion Tensor Imaging (DTI). The complex-valued outputs of the oscillator network are transformed by a complex-valued feedforward network with a single hidden layer. The entire model is

Abstract

The innate ability to recognize facial expressions and associated emotions is fundamental to human communication. Technology advancements have enabled computers to perform similar tasks to a considerable extent, opening versatile applications in diverse domains. In particular, Facial Emotion Recognition (FER) technology has recently been widely explored for investigating student engagement in classroom settings. While previous research studies mainly captivated the FER practice in engagement detection, far too little attention has been paid to the real-time emotional states of students during classroom interactions. In this regard, this paper introduces the In-Class Student Emotion and Engagement Detection System (iSEEDS), a novel AI-based approach for pinpointing learners' emotional states during classroom lectures. The iSEEDS employs Convo-lutional Neural Network (CNN) models for emotion detection and corresponding eye movement analysis. The system can help educators respond in real-time to students' emotional states and engagement levels. It can support responsive teaching by initiating remedial feedback in accordance with students' current emotions and engagement. A detailed literature review of existing emotion recognition models is presented as a background of iSEEDS development. Then the initial prototype model

Abstract

Leishmania donovani causes the neglected tropical disease visceral leishmaniasis. There is currently no vaccine available to combat the disease. Therefore, chemotherapy is the only treatment option available. However, the available drugs have various adverse effects on the host. As a result, new drugs are needed to treat the disease; natural compounds can be used as an alternative to traditional drugs. This study examined apigenin, diosmin, and naringin as prospective inhibitors against the Leishmania donovani Sterol 24-C- methyltransferase enzyme (LdSMT). All three compounds have a high affinity for the LdSMT and remain stable for 100 ns during the molecular dynamics simulation. In the cell viability assays, these compounds showed excellent IC50 values, with apigenin having the best IC50 value of 16.11 µM against Leishmania donovani promastigote. The findings of this study showed that all three flavonoids could be used as a safe alternative to conventional anti-leishmanial drugs.

Abstract

The Internet of Things (IoT)-enabled ride sharing is one of the most transforming and innovative technologies in the transportation industry. It has myriads of advantages, but with increasing demands there are security concerns as well. Traditionally, cryptographic methods are used to address the security and privacy concerns in a ride sharing system. Unfortunately, due to the emergence of quantum algorithms, these cryptographic protocols may not remain secure. Hence, there is a necessity for privacy-preserving ride sharing protocols which can resist various attacks against quantum computers. In the domain of privacy preserving ride sharing, a threshold private set intersection (TPSI) can be adopted as a viable solution because it enables the users to determine the intersection of private data sets if the set intersection cardinality is greater than or equal to a threshold value. Although TPSI can help to alleviate privacy concerns, none of the existing TPSI is quantum secure. Furthermore, the existing TPSI faces the issue of long-term security. In contrast to classical and post quantum cryptography, quantum cryptography (QC) provides a more robust solution, where QC is based on the postulates of quantum physics (e.g., Heisenberg uncertainty principle, no cloning theorem, etc.) and it can handle the prevailing issues of quantum threat and long-term security. Herein, we propose the first QC based TPSI protocol which has a direct application in privacy preserving ride sharing. Due to the use of QC, our IoT-enabled ride sharing scheme remains quantum secure and achieves long-term security as well.

Abstract

The objective of Advanced Persistent Threat (APT) attacks is to exploit Cyber-Physical Systems (CPSs) in combination with the Industrial Internet of Things (I-IoT) by using fast attack methods. Machine learning (ML) techniques have shown potential in identifying APT attacks in autonomous and malware detection systems. However, detecting hidden APT attacks in the I-IoT-enabled CPS domain and achieving real-time accuracy in detection present significant challenges for these techniques. To overcome these issues, a new approach is suggested that is based on the Graph Attention Network (GAN), a multi- dimensional algorithm that captures behavioral features along with the relevant information that other methods do not deliver. This approach utilizes masked self-attentional layers to address the limitations of prior Deep Learning (DL) methods that rely on convolutions. Two datasets, the DAPT2020 malware, and Edge I-IoT datasets are used to evaluate the approach, and it attains the highest detection accuracy of 96.97% and 95.97%, with prediction time of 20.56 seconds and 21.65 seconds, respectively. The GAN approach is compared to conventional ML algorithms, and simulation results demonstrate a significant performance improvement over these algorithms in the I-IoT-enabled CPS realm.

Abstract

A persistent, targeted cyber attack is called an advanced persistent threat (APT) attack. The attack is mainly launched to gain sensitive information, take over the system, and for financial gain, which creates nowadays more hurdles and challenges for the organization in preventing, detecting, and recovering from such attacks. Due to the nature of APT attacks, it is difficult to detect them quickly. Therefore machine learning techniques come into these research areas. This study uses deep and machine learning models such as random forest, decision tree, convolutional neural network, multilayer perceptron and so forth to categorize and effectively detect APT attacks by utilizing publicly accessible datasets. The datasets used in this study are CSE-CIC-IDS2018, CIC-IDS2017, NSL-KDD, and UNSW-NB15. This study proposes the hybrid ensemble machine learning model, a mixed approach of random forest and XGBoost classifiers. It has obtained the maximum prediction accuracy of 98.92%, 99.91%, 99.24%, and 97.11% for datasets CSE-CIC-IDS2018, CIC-IDS2017, NSL-KDD, and UNSW-NB15, with a false positive rate of 0.52%, 0.12%, 0.62%, and 5.29% respectively. These results are compared to other closely related recent studies in the literature. Our experiment's findings show that our model has performed significantly better for all datasets.

Abstract

The most significant and critical infrastructures, such as the electricity utilities, clean water facilities, nuclear plants and manufacturing industries are controlled and supervised by the industrial control systems. These systems undergo through a metamorphosis as a result of the Industry 4.0 revolution, which emphasises enhanced connectivity and flexibility with the Internet of Things (IoT) and cloud computing technologies. As the data is transferred across the Internet, Industry 4.0 communication can be easily attacked by launching different potential attacks. As a consequence, we attempt to propose a novel certificate-based access control and key establishment scheme for securing Industry 4.0 communication, called ACKS-IA. It offers access control and key establishment between smart industrial devices, as well as between a smart device and its associated cloud server. A formal security analysis of ACKS-IA through the broadly-accepted Burrows–Abadi– Needham (BAN) logic is provided. It confirms that ACKS-IA is secured and provides secure mutual authentication among the communication entities. The detailed informal security analysis and comparative study with the existing related schemes reveal that the proposed ACKS-IA is secured and efficient in terms of communication cost, computation cost, and security and functionality features including anonymity and untraceability as compared to other competing schemes. Finally, a real testbed implementation of ACKS-IA is provided to measure its effect on important performance attributes.

Abstract

This paper discusses the development of autopilot hardware for small fixed-wing air vehicles. Weight constraint is the critical factor in developing such hardware. The sensors and communication devices are selected based on the requirements and constraints of these air vehicles. The sensors used in the hardware are calibrated using a three-axis rotating platform. The software written in the autopilot hardware is flexible enough to incorporate complex estimation and control algorithms along with the hardware-in-loop simulations. Linear output feedback controllers are designed for fixed wing micro and nano air vehicles. Successful flight trials are conducted to demonstrate the utility of the autopilot hardware for small fixed-wing air vehicles

Abstract

The epidemic growth of the Internet of Things (IoT) objects have revolutionized Maritime Transportation Systems (MTS). Though, it becomes challenging for the centralized cloud-centric framework to fulfil the application requirements such as low latency and power utilization. The introduction of the distributed edge-centric framework has recently helped the IoT-enabled MTS to meet these requirements by manipulating the tasks at the edge of the networks. Despite the fact that MTS leverages mobile subscribers by overcoming inherent cloud computing limitations, data security and user privacy requirements in establishing the MTS setup are still non-trivial challenges. In this article, we develop a key agreement solution for mobile users to realize mutual authentication in a single round. Our protocol offers user anonymity to maintain user privacy, and it can prevent physical attacks by physically unclonable functions. Initially, the security analysis is conferred to substantiate our protocol’s security persistence or strength. Later, its performance correlation is observed under the assumption of diverse metrics in a predefined empirical setup. The meticulous performance correlation endorses the precedence of our protocol over specified related protocols.

Abstract

In recent years there has been rampant growth in the field of ML, AI, Big Data, IoT, cyber security, and cloud computing. These technologies have also integrated into the field of smart healthcare. The Internet of Medical Things (IoMT)-driven e-health is one such domain, which utilizes these modern technologies to provide cost-effective and secure healthcare care services to the patients [1]. It contain sensors, devices, actuators, etc. All the raw data is collected from these devices, which is prepossessed and refined to give useful insights. The medical professional can analyze and visualize critical health parameters such as ‘‘blood pressure (BP), heart rate, temperature, etc Based on the current status of the patient, alerts can be generated to doctors or the nursing staff in case of any eventuality. The integration of IoMT with e-health can enhance live tracking, monitoring and health services of patients [2], [3]. This data is regularly shared by the integrated devices and stored over the cloud server, where the healthcare professional can get all the diagnostics of patients. With the benefits of the technology, there are some security challenges. It can be architectural design flaws, a software bug, or a hardware backdoor that can lead to the compromise of the security of the systems. The cyber threat actor can gain authorized access to the system and paralyze all the networks at once. Weak control access, authentication and authorization protocols in the network may compromise the systems to the cyber attackers [4]. Attacks such as ransomware, rootkit, malware, denial of service (DoS), etc., can cause harm to the devices and tamper the healthcare data. Attackers can remotely access the smart healthcare devices and can use them as the botnet devices. With remote access, the attackers can redirect the network somewhere else and can huge network flooding [5], [6]. There have been a lot of high-impact cyber attacks happening to the e-health infrastructure. For example, a patient with the smart pacemaker monitors heart rate, temperature, and blood flow rate that can be critical to a heart alignment patient. Imagine this device gets compromised by a threat actor, it can create panic even worse and can cause death to the patient [7]. For mitigation of the cyber-attacks on all the critical infrastructure (i.e., e-health), cyber security comes into action. With threat modeling and hunting, we can actively search for any threat in the network, its source, and the severity of the threats. Once threats are found in the network, all the mitigation techniques can be used to secure the network from any intrusion. Cyber security provides a strong mechanism (i.e., authentication and key agreement) with all the tools and techniques to safeguard the e-health system [5], [6], [8]. Therefore, proper registration, authentication, authorization and intrusion detection schemes can be used to mitigate the various cyber attacks, i.e., ‘‘replay attempts, man-in-themiddle (MiTM) attacks, replay attacks, illegal session key computation, stolen verifier, etc., [8]