Search

Drones/unmanned aerial vehicles (UAVs) have recently grown in popularity due to their inexpensive cost and widespread commercial use. The increased use of drones raises the possibility that they may be employed in illicit activities such as drug smuggling and terrorism. Thus, drone monitoring and automated detection are critical for protecting restricted areas or special zones from illicit drone operations. One of the most challenging difficulties in drone detection in surveillance videos is the apparent likeness of drones against varied backdrops. This paper introduces an automated image-based drone-detection system that uses an enhanced deep-learning-based object-detection algorithm known as you only look once (YOLOv5) to defend restricted territories or special zones from unauthorized drone incursions. The transfer learning to pretrain the model is employed for improving performance due to an insufficient number of samples in our dataset. Furthermore, the model can recognize the detected object in the images and mark the object’s bounding box by joining the results across the region. The experiments show outstanding results for the loss value, drone location detection, precision and recall.

Internet of things (IoT) devices and applications are dramatically increasing worldwide, resulting in more cybersecurity challenges. Among these challenges are malicious activities that target IoT devices and cause serious damage, such as data leakage, phishing and spamming campaigns, distributed denial-of-service (DDoS) attacks, and security breaches. In this paper, a stacked deep learning method is proposed to detect malicious traffic data, particularly malicious attacks targeting IoT devices. The proposed stacked deep learning method is bundled with five pretrained residual networks (ResNets) to deeply learn the characteristics of the suspicious activities and distinguish them from normal traffic. Each pretrained ResNet model consists of 10 residual blocks. We used two large datasets to evaluate the performance of our detection method. We investigated two heterogeneous IoT environments to make our approach deployable in any IoT setting. Our proposed method has the ability to distinguish between benign and malicious traffic data and detect most IoT attacks. The experimental results show that our proposed stacked deep learning method can provide a higher detection rate in real time compared with existing classification techniques.

Blood cancer, or leukemia, has a negative impact on the blood and/or bone marrow of children and adults. Acute lymphocytic leukemia (ALL) and acute myeloid leukemia (AML) are two sub-types of acute leukemia. The Internet of Medical Things (IoMT) and artificial intelligence have allowed for the development of advanced technologies to assist in recently introduced medical procedures. Hence, in this paper, we propose a new intelligent IoMT framework for the automated classification of acute leukemias using microscopic blood images. The workflow of our proposed framework includes three main stages, as follows. First, blood samples are collected by wireless digital microscopy and sent to a cloud server. Second, the cloud server carries out automatic identification of the blood conditions—either leukemias or healthy—utilizing our developed generative adversarial network (GAN) classifier. Finally, the classification results are sent to a hematologist for medical approval. The developed GAN classifier was successfully evaluated on two public data sets: ALL-IDB and ASH image bank. It achieved the best accuracy scores of 98.67% for binary classification (ALL or healthy) and 95.5% for multi-class classification (ALL, AML, and normal blood cells), when compared with existing state-of-the-art methods. The results of this study demonstrate the feasibility of our proposed IoMT framework for automated diagnosis of acute leukemia tests. Clinical realization of this blood diagnosis system is our future work.

Nowadays, cloud computing is one of the important and rapidly growing services; its capabilities and applications have been extended to various areas of life. Cloud computing systems face many security issues, such as scalability, integrity, confidentiality, unauthorized access, etc. An illegitimate intruder may gain access to a sensitive cloud computing system and use the data for inappropriate purposes, which may lead to losses in business or system damage. This paper proposes a hybrid unauthorized data handling (HUDH) scheme for big data in cloud computing. The HUDH scheme aims to restrict illegitimate users from accessing the cloud and to provide data security provisions. The proposed HUDH consists of three steps: data encryption, data access, and intrusion detection. The HUDH scheme involves three algorithms: advanced encryption standards (AES) for encryption, attribute-based access control (ABAC) for data access control, and hybrid intrusion detection (HID) for unauthorized access detection. The proposed scheme is implemented using the Python and Java languages. The testing results demonstrated that the HUDH scheme can delegate computation overhead to powerful cloud servers. User confidentiality, access privilege, and user secret key accountability can be attained with more than 97% accuracy.

Porous carbons are highly attractive and demanding materials which could be prepared using biomass waste; thus, they are promising for enhanced electrochemical capacitive performance in capacitors and cycling efficiency in Li-ion batteries. Herein, biomass (rice husk)-derived activated carbon was synthesized via a facile chemical route and used as anode materials for Li-ion batteries. Various characterization techniques were used to study the structural and morphological properties of the prepared activated carbon. The prepared activated carbon possessed a carbon structure with a certain degree of amorphousness. The morphology of the activated carbon was of spherical shape with a particle size of ~40–90 nm. Raman studies revealed the characteristic peaks of carbon present in the prepared activated carbon. The electrochemical studies evaluated for the fabricated coin cell with the activated carbon anode showed that the cell delivered a discharge capacity of ~321 mAhg−1 at a current density of 100 mAg−1 for the first cycle, and maintained a capacity of ~253 mAhg−1 for 400 cycles. The capacity retention was found to be higher (~81%) with 92.3% coulombic efficiency even after 400 cycles, which showed excellent cyclic reversibility and stability compared to commercial activated carbon. These results allow the waste biomass-derived anode to overcome the problem of cyclic stability and capacity performance. This study provides an insight for the fabrication of anodes from the rice husk which can be redirected into creating valuable renewable energy storage devices in the future, and the product could be a socially and ethically acceptable product.

The Dark Web is known as a place triggering a variety of criminal activities. Anonymization techniques enable illegal operations, leading to the loss of confidential information and its further use as bait, a trade product or even a crime tool. Despite technical progress, there is still not enough awareness of the Dark Web and its secret activity. In this study, we introduced the Dark Web Enhanced Analysis (DWEA), in order to analyze and gather information about the content accessed on the Dark Net based on data characteristics. The research was performed to identify how the Dark Web has been influenced by recent global events, such as the COVID-19 epidemic. The research included the usage of a crawler, which scans the network and collects data for further analysis with machine learning. The result of this work determines the influence of the COVID-19 epidemic on the Dark Net.

Online social networks (OSNs) play an integral role in facilitating social interaction, however, these social networks increase antisocial behavior, such as cyberbullying, hate speech, and trolling. Aggression or hate speech that takes place through short message service (SMS) or the Internet (e.g., in social media platforms) is known as cyberbullying. Therefore, automatic detection utilizing natural language processing (NLP) is a necessary first step that helps prevent cyberbullying. This research proposes an automatic cyberbullying method to detect aggressive behavior using a consolidated deep learning model. This technique utilizes multichannel deep learning based on three models, namely, the bidirectional gated recurrent unit (BiGRU), transformer block, and convolutional neural network (CNN), to classify Twitter comments into two categories: aggressive and not aggressive. Three well-known hate speech datasets were combined to evaluate the performance of the proposed method. The proposed method achieved promising results. The accuracy of the proposed method was approximately 88%.

The Internet of Things (IoT) is a wide network consisting of Internet-connected objects using installed software, such as home appliances, vehicles, and other entities embedded with sensors, actuators, radio-frequency identification (RFID), and electronics to exchange data. In the last two decades, numerous IoT solutions have been developed by small, medium-sized, and large enterprises to make our lives easier. Furthermore, private and academic researchers have extensively investigated some practical IoT solutions. The rapid expansion of IoT solutions accompanies numerous security concerns because the underlying IoT protocols and communication technologies have not considered security. Recently, blockchain has emerged to become one of the promising technologies that might overcome some of the IoT limitations (security limitations, in particular). Blockchain technology is a database ledger that uses a peer-to-peer (P2P) network and stores transactions and asset registries. Blockchain can be described as a mounting list of records (i.e., blocks) with the following properties: distributed, decentralized, immutable, and shared. This paper surveyed recent security advances to overcome IoT limitations using blockchain. In this article, the blockchain attempts to overcome IoT limitations that are related to cyber security have been classified into four categories: end-to-end traceability; data privacy and anonymity; identity verification and authentication; and confidentiality, data integrity, and availability (CIA). Intended as a guideline for future research, this paper also explores systematic processes.

One of the most challenging topics in the field of intelligent transportation systems is the automatic interpretation of the driver’s behavior. This research investigates distracted driver posture recognition as a part of the human action recognition framework. Numerous car accidents have been reported that were caused by distracted drivers. Our aim was to improve the performance of detecting drivers’ distracted actions. The developed system involves a dashboard camera capable of detecting distracted drivers through 2D camera images. We use a combination of three of the most advanced techniques in deep learning, namely the inception module with a residual block and a hierarchical recurrent neural network to enhance the performance of detecting the distracted behaviors of drivers. The proposed method yields very good results. The distracted driver behaviors include texting, talking on the phone, operating the radio, drinking, reaching behind, fixing hair and makeup, and talking to the passenger.

Cloud computing has become a prominent technology due to its important utility service, this service concentrates on outsourcing data to organizations and individual consumers. Cloud computing has considerably changed the manner in which individuals or organizations store, retrieve, and organize their personal information. Despite the manifest development in cloud computing, there are still some concerns regarding the level of security and issues related to adopting cloud computing that prevent users from fully trusting this useful technology. Hence, for the sake of reinforcing the trust between cloud clients (CC) and cloud service providers (CSP), as well as safeguarding the CC’s data in the cloud, several security paradigms of cloud computing based on a third-party auditor (TPA) have been introduced. The TPA, as a trusted party, is responsible for checking the integrity of the CC’s data and all the critical information associated with it. However, the TPA could become an adversary and could aim to deteriorate the privacy of the CC’s data by playing a malicious role. In this paper, we present the state of the art of cloud computing’s privacy-preserving models (PPM) based on a TPA. Three TPA factors of paramount significance are discussed: TPA involvement, security requirements, and security threats caused by vulnerabilities. Moreover, TPA’s privacy preserving models are comprehensively analyzed and categorized into different classes with an emphasis on their dynamicity. Finally, we discuss the limitations of the models and present our recommendations for their improvement.

Currently, life cannot be imagined without the use of bank cards for purchases or money transfers, however, their use provides new opportunities for money launderers and terrorist organizations. This paper proposes a blockchain-enabled transaction scanning (BTS) method for the detection of anomalous actions. The BTS method specifies the rules for outlier detection and rapid movements of funds, which restrict anomalous actions in transactions. The specified rules determine the specific patterns of malicious activities in the transactions. Furthermore, the rules of the BTS method scan the transaction history and provide a list of entities that receive money suspiciously. Finally, the blockchain-enabled process is used to restrict money laundering. To validate the performance of the proposed BTS method, a Spring Boot application is built based on the Java programming language. Based on experimental results, the proposed BTS method automates the process of investigating transactions and restricts money laundering incidents.

Remote sensing technologies have been widely used in the contexts of land cover and land use. The image classification algorithms used in remote sensing are of paramount importance since the reliability of the result from remote sensing depends heavily on the classification accuracy. Parametric classifiers based on traditional statistics have successfully been used in remote sensing classification, but the accuracy is greatly impacted and rather constrained by the statistical distribution of the sensing data. To eliminate those constraints, new variants of support vector machine (SVM) are introduced. In this paper, we propose and implement land use classification based on improved SVM-enabled radial basis function (RBF) and SVM-Linear for image sensing. The proposed variants are applied for the cross-validation to determine how the optimization of parameters can affect the accuracy. The accuracy assessment includes both training and test sets, addressing the problems of overfitting and underfitting. Furthermore, it is not trivial to determine the generalization problem merely based on a training dataset. Thus, the improved SVM-RBF and SVM-Linear also demonstrate the outstanding generalization performance. The proposed SVM-RBF and SVM-Linear variants have been compared with the traditional algorithms (Maximum Likelihood Classifier (MLC) and Minimum Distance Classifier (MDC)), which are highly compatible with remote sensing images. Furthermore, the MLC and MDC are mathematically modeled and characterized with new features. Also, we compared the proposed improved SVM-RBF and SVM-Linear with the current state-of-the-art algorithms. Based on the results, it is confirmed that proposed variants have higher overall accuracy, reliability, and fault-tolerance than traditional as well as latest state-of-the-art algorithms.

Wireless Local Area Networks (WLANs) are increasingly integrated into our daily lives. Access Points (APs) are an integral part of the WLAN infrastructure, as they are responsible for coordinating wireless users and connecting them to the wired side of the network and, eventually, to the Internet. APs are deployed everywhere, from airports and shopping malls to coffee shops and hospitals, to provide Internet connectivity. One of the most serious security problems encountered by WLAN users is the existence of Rogue Access Points (RAPs). This article classifies existing solutions, identifies vulnerabilities, and suggests future directions for research into these RAPs. The ultimate objective is to classify existing detection techniques and find new RAP types that have not been classified by the research community. The literature typically categorizes Evil-twin, Unauthorized, Compromised, and Improperly Configured RAPs. Two other types have largely been abandoned by researchers, but can be classified as Denial of Service RAP attacks. These are deauthentication/disassociation attacks targeting wireless users, and the forging of the first message in a four-way handshake.

Investigation of the reliable operation of AlGaN/GaN HFETs at elevated temperatures is attempted. In this paper, a Monte Carlo-based temperature-dependent mobility model, with incorporation of steady-state velocity overshoot, is employed in modeling the drain current-voltage characteristics of AlGaN/GaN HFETs at 300, 400, and 500 K. One of the major merits of this model is that it employs a very small set of fitting parameters. The modeled drain current-voltage characteristics have been successfully matched to the experimental characteristics at the aforementioned temperatures. While confirming that a brief measurement at these temperatures is of no reliability concern on the quality of the metal-semiconductor contacts, this matching proves that the temperature dependency of the electron drift velocity is the cause of the degradation of drain current within the aforementioned range of temperature. In producing the aforementioned match for the long-gate AlGaN/GaN HFETs, it is also shown that the accurate modeling of the temperature dependency of the low-field drift transport is more consequential than the accurate representation of the transport in the medium-to-high electric fields.

The effects of the variation of the size of isolation mesa of AlGaN/GaN heterojunction field-effect transistors (HFETs) on the device characteristics are presented for the first time. Studies on the direct current and pulsed drain and gate current-voltage characteristics demonstrate a correlation between the pinchoff voltage and the size of the isolation mesa. In this paper, devices fabricated on narrow mesas (i.e., 16 × 40 μm2 fins) and also a device fabricated on an array of very small size mesas (i.e., 16 × 7 μm2 islands) are compared with AlGaN/GaN HFETs of traditionally sized mesas (i.e., 70 × 100 μm2). All these devices show maximum extrinsic gate transconductance greater than 220 mS/mm, whereas the pinchoff voltage is observed to become less negative by reducing the size of the individual mesas. The island-isolated HFETs also enjoy a relatively higher gate transconductance.

Quantum dot (QD) sensitized TiO2 is considered as a highly promising photoanode material for photoelectrochemical (PEC) solar hydrogen production. However, due to its limited stability, the photoan ...

We have studied the photoelectrochemical properties of both undoped and Si-doped GaN nanowire arrays in 1 mol l 1 solutions of hydrogen bromide and potassium bromide, which were used separately as electrolytes. It is observed that variations of the photocurrent with bias voltage depend strongly on the n-type doping in GaN nanowires in both electrolytes, which are analyzed in the context of GaN surface band bending and its variation with the incorporation of Si-doping. Maximum incident-photon-to-current-conversion efficiencies of 15% and 18% are measured for undoped and Si-doped GaN nanowires under 350 nm light illumination, respectively. Stable hydrogen generation is also observed at a zero bias potential versus the counter-electrode. (Some figures may appear in colour only in the online journal)

Media access control (MAC) addresses in wireless networks can be trivially spoofed using off-the-shelf devices. The aim of this research is to detect MAC address spoofing in wireless networks using a hard-to-spoof measurement that is correlated to the location of the wireless device, namely the received signal strength (RSS). We developed a passive solution that does not require modification for standards or protocols. The solution was tested in a live test-bed (i.e., a wireless local area network with the aid of two air monitors acting as sensors) and achieved 99.77%, 93.16% and 88.38% accuracy when the attacker is 8–13 m, 4–8 m and less than 4 m away from the victim device, respectively. We implemented three previous methods on the same test-bed and found that our solution outperforms existing solutions. Our solution is based on an ensemble method known as random forests.