IoT

While a variety of image processing studies have been performed to quantify the potential performance of neural network-based models using high-quality still images, relatively few studies seek to apply those models to a real-time operational context. This paper seeks to extend prior work in neural-network-based mask detection algorithms to a real-time, low-power deployable context that is conducive to immediate installation and use. Particularly relevant in the COVID-19 era with varying rules on mask mandates, this work applies two neural network models to inference of mask detection in both live (mobile) and recorded scenarios. Furthermore, an experimental dataset was collected where individuals were encouraged to use presentation attacks against the algorithm to quantify how perturbations negatively impact model performance. The results from evaluation on the experimental dataset are further investigated to identify the degradation caused by poor lighting and image quality, as well as to test for biases within certain demographics such as gender and ethnicity. In aggregate, this work validates the immediate feasibility of a low-power and low-cost real-time mask recognition system. Full article

This paper focuses on a block cipher adaptation of the Galois Extension Fields (GEF) combination technique for PRNGs and targets application in the Internet of Things (IoT) space, an area where the combination technique was concluded as a quality stream cipher. Electronic Codebook (ECB) and Cipher Feedback (CFB) variations of the cryptographic algorithm are discussed. Both modes offer computationally efficient, scalable cryptographic algorithms for use over a simple combination technique like XOR. The cryptographic algorithm relies on the use of quality PRNGs, but adds an additional layer of security while preserving maximal entropy and near-uniform distributions. The use of matrices with entries drawn from a Galois field extends this technique to block size chunks of plaintext, increasing diffusion, while only requiring linear operations that are quick to perform. The process of calculating the inverse differs only in using the modular inverse of the determinant, but this can be expedited by a look-up table. We validate this GEF block cipher with the NIST test suite. Additional statistical tests indicate the condensed plaintext results in a near-uniform distributed ciphertext across the entire field. The block cipher implemented on an MSP430 offers a faster, more power-efficient alternative to the Advanced Encryption Standard (AES) system. This cryptosystem is a secure, scalable option for IoT devices that must be mindful of time and power consumption. Full article

Time Slotted Channel Hopping (TSCH) is a medium access protocol defined in the IEEE 802.15.4 standard. It has proven to be one of the most reliable options when it comes to industrial applications. TSCH offers a degree of high flexibility and can be tailored to the requirements of specific applications. Several performance aspects of TSCH have been investigated so far, such as the energy consumption, reliability, scalability and many more. However, mobility in TSCH networks remains an aspect that has not been thoroughly explored. In this paper, we examine how TSCH performs under mobility situations. We define two mobile scenarios: one where autonomous agriculture vehicles move on a predefined trail, and a warehouse logistics scenario, where autonomous robots/vehicles and workers move randomly. We examine how different TSCH scheduling approaches perform on these mobility patterns and when a different number of nodes are operating. The results show that the current TSCH scheduling approaches are not able to handle mobile scenarios efficiently. Moreover, the results provide insights on how TSCH scheduling can be improved for mobile applications. Full article

This paper proposes a policy management framework which we call the SANIJO framework. This framework comprises three different types of policy rules that are applicable to smart devices for managing their multiuser–multidevice interactions in IoT collectives, from a socio-ethical perspective. We developed a policy language to help regulate and manage the interaction behaviors of smart internet-connected devices that are being deployed at an increasing rate around the world. The policy rules are classified into Authorization, Obligation, and Prohibition rules and are prototyped in the SANIJO system. We implemented our framework as a collection of mobile apps (running on smartphones) and a robot app (running on the robot). We then illustrate its operation based on an aged care center scenario. Full article

The scale of Internet of Things (IoT) systems has expanded in recent times and, in tandem with this, IoT solutions have developed symbiotic relationships with technologies, such as edge Computing. IoT has leveraged edge computing capabilities to improve the capabilities of IoT solutions, such as facilitating quick data retrieval, low latency response, and advanced computation, among others. However, in contrast with the benefits offered by edge computing capabilities, there are several detractors, such as centralized data storage, data ownership, privacy, data auditability, and security, which concern the IoT community. This study leveraged blockchain’s inherent capabilities, including distributed storage system, non-repudiation, privacy, security, and immutability, to provide a novel, advanced edge computing architecture for IoT systems. Specifically, this blockchain-based edge computing architecture addressed centralized data storage, data auditability, privacy, data ownership, and security. Following implementation, the performance of this solution was evaluated to quantify performance in terms of response time and resource utilization. The results show the viability of the proposed and implemented architecture, characterized by improved privacy, device data ownership, security, and data auditability while implementing decentralized storage. Full article

The Fourth Industrial Revolution has led to the adoption of novel technologies and methodologies in factories, making these more efficient and productive. Among the new services which are changing industry, there are those based on machine learning algorithms, which enable machines to learn from their past observations and hence possibly forecast future states. Specifically, predictive maintenance represents the opportunity to understand in advance possible machine outages due to broken parts and schedule the necessary maintenance operations. However, in real scenarios predictive maintenance struggles to be adopted due to a multitude of variables and the heavy customization it requires. In this work, we propose a novel framework for predictive maintenance, which is trained online to recognize new issues reported by the operators. Our framework, tested on different scenarios and with a varying number and several kinds of sensors, shows recall levels above 0.85, demonstrating its effectiveness and adaptability. Full article

CultivData proposes the convergence of technologies, such as IoT, big data, HPC, open data and artificial intelligence, to apply HPDA (High Performance Data Analytics) to the cultivation of agricultural data and improve the efficiency and effectiveness of farms. An information system has been developed as an IT platform for the cultivation of open data to extract knowledge and to support the decision making of stakeholders in the agricultural sector, so that it is possible to improve product quality and farm productivity. The resulting system integrates access to data provided by IoT devices that sensorize farms and public and open data sources (Open Data). The platform was designed to make precision agriculture a reality and to be useful not only to farmers, but also to agricultural decision-makers who plan species and crops based on data such as available water; expected weather; prices and market demands, and so forth. In addition, the platform provides to agricultural producers access to historical climate data; climate forecasts to anticipate times of drought or disasters; pest situations or monitoring of their plantations with sensorization and orthophotographs. Full article

This paper assesses the relative performance of the MQTT protocol in comparison to the Secure Remote Update Protocol (SRUP) in a number of simulated real-world conditions, and describes an experiment that has been conducted to measure the processing delay associated with the use of the more secure protocol. Experimental measurements for power consumption of the devices and the size of comparable TCP packets were also made. Analysis shows that the use of the SRUP protocol added an additional processing delay of between 42.92 ms and 51.60 ms—depending on the specific hardware in use. There was also shown to be a 55.47% increase in power consumption when running the secure SRUP protocol, compared with an MQTT implementation. Full article

Pervasive collaborative computing within the Internet of Things (IoT) has progressed rapidly over the last decade. Nevertheless, emerging architectural models and their applications still suffer from limited capacity in areas like power, efficient computing, memory, connectivity, latency and bandwidth. Technological development is still in progress in the fields of hardware, software and wireless communications. Their communication is usually done via the Internet and wireless via base stations. However, these models are sometimes subject to connectivity failures and limited coverage. The models that incorporate devices with peer-to-peer (P2P) communication technologies are of great importance, especially in harsh environments. Nevertheless, their power-limited devices are randomly distributed on the periphery where their availability can be limited and arbitrary. Despite these limitations, their capabilities and efficiency are constantly increasing. Accelerating development in these areas can be achieved by improving architectures and technologies of pervasive collaborative computing, which refers to the collaboration of mobile and embedded computing devices. To enhance mobile collaborative computing, especially in the models acting at the network’s periphery, we are interested in modernizing and strengthening connectivity using wireless technologies and P2P communication. Therefore, the main goal of this paper is to enhance and maintain connectivity and improve the performance of these pervasive systems while performing the required and expected services in a challenging environment. This is especially important in catastrophic situations and harsh environments, where connectivity is used to facilitate and enhance rescue operations. Thus, we have established a resilient mobile collaborative architectural model comprising a peripheral autonomous network of pervasive devices that considers the constraints of these resources. By maintaining the connectivity of its devices, this model can operate independently of wireless base stations by taking advantage of emerging P2P connection technologies such as Wi-Fi Direct and those enabled by LoPy4 from Pycom such as LoRa, BLE, Sigfox, Wi-Fi, Radio Wi-Fi and Bluetooth. Likewise, we have designed four algorithms to construct a group of devices, calculate their scores, select a group manager, and exchange inter- and intra-group messages. The experimental study we conducted shows that this model continues to perform efficiently, even in circumstances like the breakdown of wireless connectivity due to an extreme event or congestion from connecting a huge number of devices. Full article

Digitization is the emerging process in the current transformation of industry. Understanding the role and socio-economic consequences of digitalization is crucial for the way technology is being deployed in each sector. One of the affected sectors is dentistry. This study highlights the current advances and challenges in integrating and merging artificial intelligence (AI), intelligence augmentation (IA), and machine learning (ML) in dentistry. We conduct a comparative analysis to give an overview of which technology is being currently deployed and what role IA and AI will play in dentistry, as AI plays an assistive role in advancing human capabilities. We find that challenges range from AI finding its way into routine medical practice to qualitative challenges of retrieving adequate data input. Other challenges lie in the yet unanswered questions of liability in how to reduce deployment costs of new technology. Given these challenges, we provide an outlook of how future technology can be deployed in daily-life dentistry and how robots and humans will interact, given the current technology developments. The aim of this paper is to discuss the future of dentistry and whether it is AI or IA conquering the modern dentistry era. Full article

The Internet of Things (IoT) is transforming the world into an ecosystem of objects that communicate with each other to enrich our lives. The devices’ collaboration allows the creation of complex applications, where each object can provide one or more services needed for global benefit. The information moves to nodes in a peer-to-peer network, in which the concept of trustworthiness is essential. Trust and Reputation Models (TRMs) are developed with the goal of guaranteeing that actions taken by entities in a system reflect their trustworthiness values and to prevent these values from being manipulated by malicious entities. The cornerstone of any TRM is the ability to generate a coherent evaluation of the information received. Indeed, the feedback generated by the consumers of the services has a vital role as the source of any trust model. In this paper, we focus on the generation of the feedback and propose different metrics to evaluate it. Moreover, we illustrate a new collusive attack that influences the evaluation of the received services. Simulations with a real IoT dataset show the importance of feedback generation and the impact of the new proposed attack. Full article

The European Agency for Safety and Health at Work considers Smart Personal Protective Equipment as “Intelligent Protection For The Future”. It mainly consists of electronic components that collect data about their use, the workers who wear them, and the working environment. This paper proposes a distributed solution of Smart Personal Protective Equipment for the safety monitoring of Lone Workers by adopting low-cost electronic devices. In addition to the same hazards as anyone else, Lone Workers need additional and specific systems due to the higher risk they run on a work site. To this end, the Edge-Computing paradigm can be adopted to deploy an architecture embedding wearable devices, which alerts safety managers when workers do not wear the prescribed Personal Protective Equipment and supports a fast rescue when a worker seeks help or an accidental fall is automatically detected. The proposed system is a work-in-progress which provides an architecture design to accommodate different requirements, namely the deployment difficulties at temporary and large working sites, the maintenance and connectivity recurring cost issues, the respect for the workers’ privacy, and the simplicity of use for workers and their supervisors. Full article

Classifying fluctuating operating wireless environments can be crucial for successfully delivering authentic and confidential packets and for identifying legitimate signals. This study utilizes raw in-phase (I) and quadrature-phase (Q) samples, exclusively, to develop a low-order statistical feature set for wireless signal classification. Edge devices making decentralized decisions from I/Q sample analysis is beneficial. Implementing appropriate security and transmitting mechanisms, reducing retransmissions and increasing energy efficiency are examples. Wireless sensor networks (WSNs) and their Internet of Things (IoT) utilization emphasize the significance of this time series classification problem. Here, I/Q samples of typical WSN and industrial, scientific and medical band transmissions are collected in a live operating environment. Analog Pluto software-defined radios and Raspberry Pi devices are utilized to achieve a low-cost yet high-performance testbed. Features are extracted from Matlab-based statistical analysis of the I/Q samples across time, frequency (fast Fourier transform) and space (probability density function). Noise, ZigBee, continuous wave jamming, WiFi and Bluetooth signal data are examined. Supervised machine learning approaches, including support vector machines, Random Forest, XGBoost, k nearest neighbors and a deep neural network (DNN), evaluate the developed feature set. The optimal approach is determined as an XGBoost/SVM classifier. This classifier achieves similar accuracy and generalization results, on unseen data, to the DNN, but for a fraction of time and computation requirements. Compared to existing approaches, this study’s principal contribution is the developed low-order feature set that achieves signal classification without prior network knowledge or channel assumptions and is validated in a real-world wireless operating environment. The feature set can extend the development of resource-constrained edge devices as it is widely deployable due to only requiring received I/Q samples and these features are warranted as IoT devices become widely used in various modern applications. Full article

The tremendous number of Internet of Things (IoT) applications, with their ubiquity, has provided us with unprecedented productivity and simplified our daily life. At the same time, the insecurity of these technologies ensures that our daily lives are surrounded by vulnerable computers, allowing for the launch of multiple attacks via large-scale botnets through the IoT. These attacks have been successful in achieving their heinous objectives. A strong identification strategy is essential to keep devices secured. This paper proposes and implements a model for anomaly-based intrusion detection in IoT networks that uses a convolutional neural network (CNN) and gated recurrent unit (GRU) to detect and classify binary and multiclass IoT network data. The proposed model is validated using the BoT-IoT, IoT Network Intrusion, MQTT-IoT-IDS2020, and IoT-23 intrusion detection datasets. Our proposed binary and multiclass classification model achieved an exceptionally high level of accuracy, precision, recall, and F1 score. Full article

The Internet of Things is emerging as a vast, inter-connected space of devices and things surrounding people, many of which are increasingly capable of autonomous action, from automatically sending data to cloud servers for analysis, changing the behaviour of smart objects, to changing the physical environment. A wide range of ethical concerns has arisen in their usage and development in recent years. Such concerns are exacerbated by the increasing autonomy given to connected things. This paper reviews, via examples, the landscape of ethical issues, and some recent approaches to address these issues concerning connected things behaving autonomously as part of the Internet of Things. We consider ethical issues in relation to device operations and accompanying algorithms. Examples of concerns include unsecured consumer devices, data collection with health-related Internet of Things, hackable vehicles, behaviour of autonomous vehicles in dilemma situations, accountability with Internet of Things systems, algorithmic bias, uncontrolled cooperation among things, and automation affecting user choice and control. Current ideas towards addressing a range of ethical concerns are reviewed and compared, including programming ethical behaviour, white-box algorithms, black-box validation, algorithmic social contracts, enveloping IoT systems, and guidelines and code of ethics for IoT developers; a suggestion from the analysis is that a multi-pronged approach could be useful based on the context of operation and deployment. Full article

This paper explores the security of a single-stage residue number system (RNS) pseudorandom number generator (PRNG), which has previously been shown to provide extremely high-quality outputs when evaluated through available RNG statistical test suites or in using Shannon and single-stage Kolmogorov entropy metrics. In contrast, rather than blindly performing statistical analyses on the outputs of the single-stage RNS PRNG, this paper provides both white box and black box analyses that facilitate reverse engineering of the underlying RNS number generation algorithm to obtain the residues, or equivalently key, of the RNS algorithm. We develop and demonstrate a conditional entropy analysis that permits extraction of the key given a priori knowledge of state transitions as well as reverse engineering of the RNS PRNG algorithm and parameters (but not the key) in problems where the multiplicative RNS characteristic is too large to obtain a priori state transitions. We then discuss multiple defenses and perturbations for the RNS system that fool the original attack algorithm, including deliberate noise injection and code hopping. We present a modification to the algorithm that accounts for deliberate noise, but rapidly increases the search space and complexity. Lastly, we discuss memory requirements and time required for the attacker and defender to maintain these defenses. Full article

The rapid adoption of Android devices comes with the growing prevalence of mobile malware, which leads to serious threats to mobile phone security and attacks private information on mobile devices. In this paper, we designed and implemented a model for malware detection on Android devices to protect private and financial information, for the mobile applications of the ATISCOM project. This model is based on client/server architecture, to reduce the heavy computations on a mobile device by sending data from the mobile device to the server for remote processing (i.e., offloading) of the predictions. We then gradually optimized our proposed model for better classification of the newly installed applications on Android devices. We at first adopted Naive Bayes to build the model with 92.4486% accuracy, then the classification method that gave the best accuracy of 93.85% for stochastic gradient descent (SGD) with binary class (i.e., malware and benign), and finally the regression method with numerical values ranging from −100 to 100 to manage the uncertainty predictions. Therefore, our proposed model with random forest regression gives a good accuracy in terms of performance, with a good correlation coefficient, minimum computation time and the smallest number of errors for malware detection. Full article

With the rapid development of the autonomous world, local decision making between devices is becoming important. This article provides a new paradigm (Rock-Paper-Scissors-Hammer: RPSH) that can reduce the number of conflicts or decision draws and thus increase the throughput of autonomous devices while reducing the kept number of records or transactions. The paradigm requires a sealed envelope protocol and sequential message passing between both parties to decide unanimously a winner between the two participants without a third-party mediation. The message passing proposes a detailed record in a blockchain-like format that is not corruptible and is verifiable for conflict resolution. A simulated IoT environment is created to show the advantage of the proposed protocol and it shows significant reduction in mean efforts due to the elimination of draws or undecided situations. Autonomous devices, such as cars, need to maintain meticulous, lightweight, but blockchain-like record keeping for insurance settlements or conflict resolutions; that archival data size is significantly reduced by the RPSH protocol. Full article

The Internet of Things offers a wide range of possibilities that can be exploited more or less explicitly for user authentication, ranging from specifically designed systems including biometric devices to environmental sensors that can be opportunistically used to feed behavioural authentication systems. How to integrate all this information in a reliable way to get a continuous authentication service presents several open challenges. Among these: how to combine semi-trusted information coming from non-tamper-proof sensors, where to store such data avoiding a single point of failure, how to analyse data in a distributed way, which interface to use to provide an authentication service to a multitude of different services and applications. In this paper, we present a Blockchain-based architectural solution of a distributed system able to transform IoT interactions into useful data for an authentication system. The design includes: (i) a security procedure to certify users’ positions and identities, (ii) a secure storage to hold this information, and (iii) a service to dynamically assign a trust level to a user’s position. We call this system “Secure Path”. Full article