J. Sens. Actuator Netw., Volume 11, Issue 3 (September 2022) – 26 articles

Wireless networks have continued to evolve to offer connectivity between users and smart devices such as drones and wireless sensor nodes. In this environment, insecure public channels are deployed to link the users to their remote smart devices. Some of the application areas of these smart devices include military surveillance and healthcare monitoring. Since the data collected and transmitted to the users are highly sensitive and private, any leakages can have adverse effects. As such, strong entity authentication should be implemented before any access is granted in these wireless networks. Although numerous protocols have been developed for this purpose, the simultaneous attainment of robust security and privacy at low latencies, execution time and bandwidth remains a mirage. In this paper, a session-dependent token-based payload enciphering scheme for integrity enhancements in wireless networks is presented. This protocol amalgamates fuzzy extraction with extended Chebyshev chaotic maps to boost the integrity of the exchanged payload. The security analysis shows that this scheme offers entity anonymity and backward and forward key secrecy. In addition, it is demonstrated to be robust against secret ephemeral leakage, side-channeling, man-in-the-middle and impersonation attacks, among other security threats. From the performance perspective, the proposed scheme requires the least communication overheads and a relatively low execution time during the authentication process. Full article

Phishing is still a major security threat in cyberspace. In phishing, attackers steal critical information from victims by presenting a spoofing/fake site that appears to be a visual clone of a legitimate site. Several Unicode characters are visually identical to ASCII characters. This similarity in characters is generally known as homoglyphs. Malicious adversaries utilize homoglyphs in URLs and DNS domains to target organizations. To reduce the risks caused by phishing attacks, effective ways of detecting phishing websites are urgently required. This paper proposes a homoglyph attack detection model that combines a hash function and machine learning. There are two phases to the model approach. The machine was being trained during the development phase. The deployment phase involved deploying the model with a Java interface and testing the outcomes through actual user interaction. The results are more accurate when the URL is hashed, as any little changes to the URL can be recognized. The homoglyph detector can be developed as a stand-alone software that is used as the initial step in requesting a webpage as it enhances browser security and protects websites from phishing attempts. To verify the effectiveness, we compared the proposed model on several criteria to existing phishing detection methods. By using the hash function, the proposed security features increase the overall security of the homoglyph attack detection in terms of accuracy, integrity, and availability. The experiment results showed that the model can detect phishing sites with an accuracy of 99.8% using Random Forest, and the hash function improves the accuracy of homoglyph attack detection. Full article

The opportunistic fog radio access network (OF-RAN) expands its offloading computation capacity on-demand by establishing virtual fog access points (v-FAPs), comprising user devices with idle resources recruited opportunistically to execute the offloaded tasks in a distributed manner. OF-RAN is attractive for providing computation offloading services to resource-limited Internet-of-Things (IoT) devices from vertical industrial applications such as smart transportation, tourism, mobile healthcare, and public safety. However, the current OF-RAN design is lacking a trusted and distributed mechanism for automating its processes such as v-FAP formation and service execution. Motivated by the recent emergence of blockchain, with smart contracts as an enabler of trusted and distributed systems, we propose an automated mechanism for OF-RAN processes using smart contracts. To demonstrate how our smart-contract-based automation for OF-RAN could apply in real life, a federated deep learning (DL) use-case where a resource-limited client offloads the resource-intensive training of its DL model to a v-FAP is implemented and evaluated. The results validate the DL and blockchain performances of the proposed smart-contract-enabled OF-RAN. The appropriate setting of process parameters to meet the often competing requirements is also demonstrated. Full article

The traditional Long-Range Wide-Area Network (LoRaWAN) uses an Advanced Encryption Standard (AES) 128 bit symmetric key to secure entities and data against several attacks. However, due to the existence of heterogeneous applications, designing a globally accepted and resilient LoRaWAN security model is challenging. Although several security models to maximize the security efficiency in LoRaWAN exist using the trusted key server to securely manage the keys, designing an optimum LoRaWAN security model is yet to be fully realized. Therefore, in this paper, we proposed two LoRaWAN security algorithms, A and B, for a trusted key management server (TKMS) to securely manage and distribute the keys amongst the entities. Algorithm B is an enhanced version of Algorithm A, which utilizes the security shortcomings of Algorithm A. We employed two formal analysis methods in the modelling, results analysis, and verification. The Scyther security verification tool was used for algorithm modelling and analysis against all possible attacks, while BAN logic was used to prove the logical correctness of the proposed algorithms. The results indicate that BAN logic feasibly proves the model logic correctness and the security claims employed in Scyther are reliable metrics for assessing the algorithms’ security efficiency. The security claims proved that the security algorithm is more secure and reliable as no attacks were detected across all entities in the enhanced-Algorithm B, unlike in Algorithm A. Moreover, the application of hashing minimizes computation cost and time for authentication and message integrity as compared to symmetric and asymmetric encryption. However, the proposed algorithm is yet to be verified as completely lightweight. Full article

Vehicle to everything (V2X) technology allows the broader development of driving safety, efficiency, and comfort. Because the vehicles can quickly send and receive frequent messages from other vehicles and nearby devices, e.g., cooperative awareness message applications on the intelligent transport system (ITS), V2X requires a good security and privacy protection system to make the messages reliable for the ITS requirements. The existing standards developed in the US and Europe use many short valid period pseudonym certificates to meet the security and privacy requirements. However, this method has difficulty ensuring that revoked pseudonym certificates are treated as revoked by any vehicles because distributing revocation information on a wireless vehicular network with intermittent and rapidly changing topology is demanding. A promising approach to solving this problem is the periodic activation of released pseudonym certificates. Initially, it releases all required pseudonym certificates for a certain period to the vehicle, and pseudonym certificates can be used only after receiving an activation code. Such activation-code-based schemes have a common problem in the inefficient use of network resources between the road-side unit (RSU) and vehicles. This paper proposes an efficient and privacy-preserving activation code distribution strategy solving the problem. By adopting the unicast distribution model of modified activation code for pseudonym certificate (ACPC), our scheme can obtain benefits of efficient activation code distribution. The proposed scheme provides small communication resource usage in the V2X network with various channel options for delivering activation codes in a privacy preserved manner. Full article

Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine capable of responding in a manner similar to human intelligence. Research in this area includes robotics, language recognition, image identification, natural language processing, and expert systems. In recent years, the availability of large datasets, the development of effective algorithms, and access to powerful computers have led to unprecedented success in artificial intelligence. This powerful tool has been used in numerous scientific and engineering fields including mineral identification. This paper summarizes the methods and techniques of artificial intelligence applied to intelligent mineral identification based on research, classifying the methods and techniques as artificial neural networks, machine learning, and deep learning. On this basis, visualization analysis is conducted for mineral identification of artificial intelligence from field development paths, research hot spots, and keywords detection, respectively. In the end, based on trend analysis and keyword analysis, we propose possible future research directions for intelligent mineral identification. Full article

The last decade witnessed remarkable growth in the number of global road accidents. To minimize road accidents, transportation systems need to become more intelligent. Multiple detection of target vehicles under adverse weather conditions is one of the primary challenges of autonomous vehicles. Photonic radar sensors may become the promising technology to detect multiple targets to realize autonomous vehicles. In this work, high-speed photonic radar is designed to detect multiple targets by incorporating a cost-effective wavelength division multiplexing (WDM) scheme. Numerical simulations of the proposed WDM-based photonic radar is demonstrated in terms of received power and signal to noise (SNR) ratio. The performance of the proposed photonic radar is also investigated under diverse weather conditions, particularly low, medium, and thick fog. The proposed photonic radar demonstrated a significant range resolution of 7 cm when the target was placed at 80 m distance from the photonic radar sensor-equipped vehicle. In addition to this, traditional microwave radar is demonstrated to prove the effectiveness of the proposed photonic radar. Full article

Knee osteoarthritis is one of the most prevalent chronic diseases. It leads to pain, stiffness, decreased participation in activities of daily living and problems with balance recognition. Force platforms have been one of the tools used to analyse balance in patients. However, identification in early stages and assessing the severity of osteoarthritis using parameters derived from a force plate are yet unexplored to the best of our knowledge. Combining artificial intelligence with medical knowledge can provide a faster and more accurate diagnosis. The aim of our study is to present a novel algorithm to classify the occurrence and severity of knee osteoarthritis based on the parameters derived from a force plate. Forty-four sway movements graphs were measured. The different machine learning algorithms, such as K-Nearest Neighbours, Logistic Regression, Gaussian Naive Bayes, Support Vector Machine, Decision Tree Classifier and Random Forest Classifier, were implemented on the dataset. The proposed method achieves 91% accuracy in detecting sway variation and would help the rehabilitation specialist to objectively identify the patient’s condition in the initial stage and educate the patient about disease progression. Full article

The rapid development of new information and communication technologies (ICTs) and the deployment of advanced Internet of Things (IoT)-based devices has led to the study and implementation of edge computing technologies in smart grid (SG) systems. In addition, substantial work has been expended in the literature to incorporate artificial intelligence (AI) techniques into edge computing, resulting in the promising concept of edge intelligence (EI). Consequently, in this article, we provide an overview of the current state-of-the-art in terms of EI-based SG adoption from a range of angles, including architectures, computation offloading, and cybersecurity concerns. The basic objectives of this article are fourfold. To begin, we discuss EI and SGs separately. Then we highlight contemporary concepts closely related to edge computing, fundamental characteristics, and essential enabling technologies from an EI perspective. Additionally, we discuss how the use of AI has aided in optimizing the performance of edge computing. We have emphasized the important enabling technologies and applications of SGs from the perspective of EI-based SGs. Second, we explore both general edge computing and architectures based on EI from the perspective of SGs. Thirdly, two basic questions about computation offloading are discussed: what is computation offloading and why do we need it? Additionally, we divided the primary articles into two categories based on the number of users included in the model, either a single user or a multiple user instance. Finally, we review the cybersecurity threats with edge computing and the methods used to mitigate them in SGs. Therefore, this survey comes to the conclusion that most of the viable architectures for EI in smart grids often consist of three layers: device, edge, and cloud. In addition, it is crucial that computation offloading techniques must be framed as optimization problems and addressed effectively in order to increase system performance. This article typically intends to serve as a primer for emerging and interested scholars concerned with the study of EI in SGs. Full article

Recent advances have allowed the monitoring of several volatile organic compounds (VOCs) in human exhaled breath, and many of them are being utilized as a biomarker to diagnose several diseases, including diabetes. Among several VOCs, isopropanol (IPA) has been reported as a common volatile compound in the exhaled breath of patients with type 1 and type 2 diabetes. In this article, an experimental approach is discussed to develop a highly selective and sensitive IPA vapor sensor system. The fabricated sensor is comprised of a small and portable glass slide coated with molecularly imprinted polymer containing specific binding sites compatible with IPA molecules. The developed sensor is based on the wavelength interrogation technique. The fabricated device is analyzed for the detection of IPA vapor with different concentrations varying from 50% to 100%. The sensor exhibits maximum sensitivities of 0.37, 0.30, and 0.62 nm/%IPA, respectively, for 30, 60, and 90 min, respectively, and an excellent sensitivity of 0.63 nm/%IPA for 120 min exposure along with good selectivity among a similar class of VOCs. The major features of the sensor i.e., small size, portability, cost-effectiveness, high sensitivity, and good selectivity, make it a potential candidate for diabetes monitoring. The promising results of the sensor illustrate its potential in diabetes monitoring applications. Full article

This paper studies the gradient-based adversarial attacks on cluster-based, heterogeneous, multi-agent, deep reinforcement learning (MADRL) systems with time-delayed data transmission. The structure of the MADRL system consists of various clusters of agents. The deep Q-network (DQN) architecture presents the first cluster’s agent structure. The other clusters are considered as the environment of the first cluster’s DQN agent. We introduce two novel observations in data transmission, termed on-time and time-delay observations. The proposed observations are considered when the data transmission channel is idle, and the data is transmitted on time or delayed. By considering the distance between the neighboring agents, we present a novel immediate reward function by appending a distance-based reward to the previously utilized reward to improve the MADRL system performance. We consider three types of gradient-based attacks to investigate the robustness of the proposed system data transmission. Two defense methods are proposed to reduce the effects of the discussed malicious attacks. We have rigorously shown the system performance based on the DQN loss and the team reward for the entire team of agents. Moreover, the effects of the various attacks before and after using defense algorithms are demonstrated. The theoretical results are illustrated and verified with simulation examples. Full article

Telecare medical information system (TMIS) is a technology used in a wireless body area network (WBAN), which has a crucial role in healthcare services. TMIS uses wearable devices with sensors to collect patients’ data and transmit the data to the controller node via a public channel. Then, the medical server obtains the data from the controller node and stores it in the database to be analyzed. Unfortunately, an attacker can try to perform attacks via a public channel. Thus, establishing a secure mutual authentication protocol is essential for secure data transfer. Several authentication schemes have been presented to achieve mutual authentication, but there are performance limitations and security problems. Therefore, this study aimed to propose two secure and efficient WBAN authentication protocols between sensors and a mobile device/controller: authentication protocol-I for emergency medical reports and authentication protocol-II for periodic medical reports. To analyze the proposed authentication protocols, we conducted an informal security analysis, implemented BAN logic analysis, validated our proposed authentication protocol using the AVISPA simulation tool, and conducted a performance analysis. Consequently, we showed that our proposed protocols satisfy all security requirements in this study, attain mutual authentication, resist active and passive attacks, and have suitable computation and communication costs for a WBAN. Full article

Over the past decade, new technologies have driven the rise of what is being termed as the fourth industrial revolution. The introduction of this new revolution is amalgamating the cyber and physical worlds, bringing with it many benefits, such as the advent of industry 4.0, the internet of things, cloud technologies and smart homes and cities. These new and exciting areas are poised to have significant advantages for society; they can increase the efficiency of many systems and increase the quality of life of people. However, these emerging technologies can potentially have downsides, if used incorrectly or maliciously by bad entities. The rise of the widespread use of sensor networks to allow the mentioned systems to function has brought with it many security vulnerabilities that conventional “hard security” measures cannot mitigate. It is for this reason that a new “soft security” approach is being taken in conjunction with the conventional security means. Trust models offer an efficient way of mitigating the threats posed by malicious entities in networks that conventional security methods may not be able to combat. This paper discusses the general structure of a trust model, the environments they are used in and the attack types they are used to defend against. The work aims to provide a comprehensive review of the wide assortment of trust parameters and methods used in trust models. The work discusses which environments and network types each of these parameters and calculation methods would be suited to. Finally, a design study is provided to demonstrate how a trust model design will differ between two different industry 4.0 networks. Full article

Location prediction in an indoor environment is a challenge, and this has been a research trend for recent years, with many potential applications. In this paper, machine-learning-based regression algorithms and Received Signal Strength Indicator (RSSI) fingerprint data from Wireless Access Points (WAPs) with dual Service set IDentifiers (SSIDs) are used, and positioning prediction and location accuracy are compared with single SSIDs. It is found that using Wi-Fi RSSI data from dual-frequency SSIDs improves the location prediction accuracy by up to 19%. It is also found that Support Vector Regression (SVR) gives the best prediction among classical machine-learning algorithms, followed by K-Nearest Neighbour (KNN) and Linear Regression (LR). Moreover, we analyse the effect of fingerprint grid size, coverage of the Reference Points (RPs) and location of the Test Points (TPs) on the positioning prediction and location accuracy using these three best algorithms. It is found that the prediction accuracy depends upon the fingerprint grid size and the boundary of the RPs. Experimental results demonstrates that reducing fingerprint grid size improves the positioning prediction and location accuracy. Further, the result also shows that when all the TPs are inside the boundary of RPs, the prediction accuracy increases. Full article

With the huge proliferation of mobile Internet of Things (IoT) devices such as connected vehicles, drones, and healthcare wearables, IoT networks are promising mobile connectivity capacity far beyond the conventional computing platforms. The success of this service provisioning is highly dependent on the flexibility offered by such enabling technologies to support IoT mobility using different devices and protocol stacks. Many of the connected mobile IoT devices are autonomous, and resource constrained, which poses additional challenges for mobile IoT communication. Therefore, given the unique mobility requirements of IoT devices and applications, many challenges are still to be addressed. This paper presents a global mobility management solution for IoT networks that can handle both micro and macro mobility scenarios. The solution exploits a path-based forwarding fabric together with mechanisms from Information-Centric Networking. The solution is equally suitable for legacy session-based mobile devices and emerging information-based IoT devices such as mobile sensors. Simulation evaluations have shown minimum overhead in terms of packet delivery and signalling costs to support macro mobility handover across different IoT domains. Full article

Calibrating intrinsic and extrinsic camera parameters is a fundamental problem that is a preliminary task for a wide variety of applications, from robotics to computer vision to surveillance and industrial tasks. With the advent of Internet of Things (IoT) technology and edge computing capabilities, the ability to track motion activities in large outdoor areas has become feasible. The proposed work presents a network of IoT camera nodes and a dissertation on two possible approaches for automatically estimating their poses. One approach follows the Structure from Motion (SfM) pipeline, while the other is marker-based. Both methods exploit the correspondence of features detected by cameras on synchronized frames. A preliminary indoor experiment was conducted to assess the performance of the two methods compared to ground truth measurements, employing a commercial tracking system of millimetric precision. Outdoor experiments directly compared the two approaches on a larger setup. The results show that the proposed SfM pipeline more accurately estimates the pose of the cameras. In addition, in the indoor setup, the same methods were used for a tracking application to show a practical use case. Full article

In present times, the largest amount of data is being controlled in a centralized manner. However, as the data are in essence the fuel of any application and service, there is a need to make the data more findable and accessible. Another problem with the data being centralized is the limited storage as well as the uncertainty of their authenticity. In the Internet of Things (IoT) sector specifically, data are the key to develop the most powerful and reliable applications. For these reasons, there is a rise on works that present decentralized marketplaces for IoT data with many of them exploiting blockchain technology to offer security advantages. The main contribution of this work is to review the existing works on decentralized IoT data marketplaces and discuss important design aspects and options so as to guide (a) the prospective user to select the IoT data marketplace that matches their needs and (b) the potential designer of a new marketplace to make insightful decisions. Full article

Recent developments in communication and information technologies, especially in the internet of things (IoT), have greatly changed and improved the human lifestyle. Due to the easy access to, and increasing demand for, smart devices, the IoT system faces new cyber-physical security and privacy attacks, such as denial of service, spoofing, phishing, obfuscations, jamming, eavesdropping, intrusions, and other unforeseen cyber threats to IoT systems. The traditional tools and techniques are not very efficient to prevent and protect against the new cyber-physical security challenges. Robust, dynamic, and up-to-date security measures are required to secure IoT systems. The machine learning (ML) technique is considered the most advanced and promising method, and opened up many research directions to address new security challenges in the cyber-physical systems (CPS). This research survey presents the architecture of IoT systems, investigates different attacks on IoT systems, and reviews the latest research directions to solve the safety and security of IoT systems based on machine learning techniques. Moreover, it discusses the potential future research challenges when employing security methods in IoT systems. Full article

Day by day, the demand for wireless systems is increasing while the available spectrum resources are not sufficient. To fulfil the demand for wireless systems, the spectrum hole (spectrum vacant) should be found and utilised very effectively. Cognitive radio (CR) is a device which intelligently senses the spectrum through various spectrum-sensing detectors. Based on the complexity and licensed user’s information present with CR, the appropriate detector should be utilised for spectrum sensing. In this paper, a hybrid detector (HD) is proposed to determine the spectrum hole from the available spectrum resources. HD is designed based on an energy detector (ED) and matched detector (MD). Unlike a single detector such as ED or MD, HD can sense the signal more precisely. Here, HD can work on both conditions whether the primary user (PU) information is available or not. HD is analysed under heterogeneous environments with and without cooperative spectrum sensing (CSS). For CSS, four users were used to implement OR, AND, and majority schemes under low SNR walls. To design the HD, specifications were chosen based on the IEEE Wireless Regional Area Network (WRAN) 802.22 standard for accessing TV spectrum holes. For the HD model, we achieved the best results through OR rule. Under the low SNR circumstances at −20 dB SNR, the probability of detection (P_D) is maximised to 1 and the probability of a false alarm (P_FA) is reduced to 0 through the CSS environment. Full article

The increased interest in autonomous vehicles has led to the development of novel networking protocols in VANETs In such a widespread safety-critical application, security is paramount to the implementation of the networks. We view new autonomous vehicle edge networks as opportunistic networks that bridge the gap between fully distributed vehicular networks based on short-range vehicle-to-vehicle communication and cellular-based infrastructure for centralized solutions. Experiments are conducted using opportunistic networking protocols to provide data to autonomous trams and buses in a smart city. Attacking vehicles enter the city aiming to disrupt the network to cause harm to the general public. In the experiments the number of vehicles and the attack length is altered to investigate the impact on the network and vehicles. Considering different measures of success as well as computation expense, measurements are taken from all nodes in the network across different lengths of attack. The data gathered from each node allow exploration into how different attacks impact metrics including the delivery probability of a message, the time taken to deliver and the computation expense to each node. The novel multidimensional analysis including geospatial elements provides evidence that the state-of-the-art MaxProp algorithm outperforms the benchmark as well as other, more complex routing protocols in most of the categories. Upon the introduction of attacking nodes however, PRoPHET provides the most reliable delivery probability when under attack. Two different attack methods (black and grey holes) are used to disrupt the flow of messages throughout the network and the more basic protocols show that they are less consistent. In some metrics, the PRoPHET algorithm performs better when under attack due to the benefit of reduced network traffic. Full article

A compromised Smart Grid, or its components, can have cascading effects that can affect lives. This has led to numerous cybersecurity-centric studies focusing on the Smart Grid in research areas such as encryption, intrusion detection and prevention, privacy and trust. Even though trust is an essential component of cybersecurity research; it has not received considerable attention compared to the other areas within the context of Smart Grid. As of the time of this study, we observed that there has neither been a study assessing trust within the Smart Grid nor were there trust models that could detect malicious attacks within the substation. With these two gaps as our objectives, we began by presenting a mathematical formalization of trust within the context of Smart Grid devices. We then categorized the existing trust-based literature within the Smart Grid under the NIST conceptual domains and priority areas, multi-agent systems and the derived trust formalization. We then proposed a novel substation-based trust model and implemented a Modbus variation to detect final-phase attacks. The variation was tested against two publicly available Modbus datasets (EPM and ATENA H2020) under three kinds of tests, namely external, internal, and internal with IP-MAC blocking. The first test assumes that external substation adversaries remain so and the second test assumes all adversaries within the substation. The third test assumes the second test but blacklists any device that sends malicious requests. The tests were performed from a Modbus server’s point of view and a Modbus client’s point of view. Aside from detecting the attacks within the dataset, our model also revealed the behaviour of the attack datasets and their influence on the trust model components. Being able to detect all labelled attacks in one of the datasets also increased our confidence in the model in the detection of attacks in the other dataset. We also believe that variations of the model can be created for other OT-based protocols as well as extended to other critical infrastructures. Full article

Background: the increasing adoption of smart and wearable sensors in the healthcare domain empowers the development of cutting-edge medical applications. Smart hospitals can employ sensors and applications for critical decision-making based on real-time monitoring of patients and equipment. In this context, quality of service (QoS) is essential to ensure the reliability of application data. Methods: we developed a QoS-aware sensor middleware for healthcare 4.0 that orchestrates data from several sensors in a hybrid operating room. We deployed depth imaging sensors and real-time location tags to monitor surgeries in real-time, providing data to medical applications. Results: an experimental evaluation in an actual hybrid operating room demonstrates that the solution can reduce the jitter of sensor samples up to 90.3%. Conclusions: the main contribution of this article relies on the QoS Service Elasticity strategy that aims to provide QoS for applications. The development and installation were demonstrated to be complex, but possible to achieve. Full article

The Internet of Things (IoT) is a promising technology that allows numerous devices to be connected for ease of communication. The heterogeneity and ubiquity of the various connected devices, openness to devices in the network, and, importantly, the increasing number of connected smart objects (or devices) have exposed the IoT network to various security challenges and vulnerabilities which include manipulative data injection and cyberattacks such as a denial of service (DoS) attack. Any form of intrusive data injection or attacks on the IoT networks can create devastating consequences on the individual connected device or the entire network. Hence, there is a crucial need to employ modern security measures that can protect the network from various forms of attacks and other security challenges. Intrusion detection systems (IDS) and intrusion prevention systems have been identified globally as viable security solutions. Several traditional machine learning methods have been deployed as IoT IDS. However, the methods have been heavily criticized for poor performances in handling voluminous datasets, as they rely on domain expertise for feature extraction among other reasons. Thus, there is a need to devise better IDS models that can handle the IoT voluminous datasets efficiently, cater to feature extraction, and perform reasonably well in terms of overall performance. In this paper, an IDS based on redefined long short-term memory deep learning approach is proposed for detecting DoS attacks in IoT networks. The model was tested on benchmark datasets; CICIDS-2017 and NSL-KDS datasets. Three pre-processing procedures, which include encoding, dimensionality reduction, and normalization were deployed for the datasets. Using key classification metrics, experimental results obtained show that the proposed model can effectively detect DoS attacks in IoT networks as it performs better compared to other methods including models from related works. Full article

In the study of human mobility, gait analysis is a well-recognized assessment methodology. Despite its widespread use, doubts exist about its clinical utility, i.e., its potential to influence the diagnostic-therapeutic practice. Gait analysis evaluates the walking pattern (normal/abnormal) based on the gait cycle. Based on the analysis obtained, various applications can be developed in the medical, security, sports, and fitness domain to improve overall outcomes. Wearable sensors provide a convenient, efficient, and low-cost approach to gather data, while machine learning methods provide high accuracy gait feature extraction for analysis. The problem is to identify gait abnormalities and if present, subsequently identify the locations of impairments that lead to the change in gait pattern of the individual. Proper physiotherapy treatment can be provided once the location/landmark of the impairment is known correctly. In this paper, classification of multiple anatomical regions and their combination on a large scale highly imbalanced dataset is carried out. We focus on identifying 27 different locations of injury and formulate it as a multi-class classification approach. The advantage of this method is the convenience and simplicity as compared to previous methods. In our work, a benchmark is set to identify the gait disorders caused by accidental impairments at multiple anatomical regions using the GaitRec dataset. In our work, machine learning models are trained and tested on the GaitRec dataset, which provides Ground Reaction Force (GRF) data, to analyze an individual’s gait and further classify the gait abnormality (if present) at the specific lower-region portion of the body. The design and implementation of machine learning models are carried out to detect and classify the gait patterns between healthy controls and gait disorders. Finally, the efficacy of the proposed approach is showcased using various qualitative accuracy metrics. The achieved test accuracy is 96% and an F1 score of 95% is obtained in classifying various gait disorders on unseen test samples. The paper concludes by stating how machine learning models can help to detect gait abnormalities along with directions of future work. Full article

Industry 4.0, or the Fourth Industrial Revolution, is driven by innovative technologies that have profound effects on both production systems and business models. This revolution is characterized by the addition of disruptive technologies and methods. These aspects of Industry 4.0 have a significant impact on marketing, and have led to an evolution to ensure that marketing activities align with technological advancements and address consumers’ current needs. The purpose of this paper is to formulate and discuss future research avenues for marketing considering the changes brought about by Industry 4.0. The approach taken in the paper is to review the relevant literature and focus on the key themes which are most important for future research on Industry 4.0 and marketing. Therefore, a Systematic Bibliometric Literature Review was conducted based on the SCOPUS indexing online database of scientific articles, the most important peer-reviewed journal database in the academic world. The paper finds that there are a number of research avenues for marketing researchers to conduct investigations in, but the most important areas are five marketing principles in Industry 4.0: cooperation, conversation, co-creation, cognitivity, and connectivity. Future research should focus on the quantitative study of these five principles. Full article