Description:
Industrial Internet of Things (IIoT) deploys edge devices to act as intermediaries between sensors and actuators and application servers or cloud services. Machine learning models have been widely used to thwart malware attacks in such edge devices. However, these models are vulnerable to adversarial attacks where attackers craft adversarial samples by introducing small perturbations to malware samples to fool a classifier to misclassify them as benign applications. Literature on deep learning networks proposes adversarial retraining as a defense mechanism where adversarial samples are combined with legitimate samples to retrain the classifier. However, existing works select such adversarial samples in a random fashion which degrades the classifier's performance. This work proposes two novel approaches for selecting adversarial samples to retrain a classifier. One, based on the distance from malware cluster center, and the other, based on a probability measure derived from a kernel based learning (KBL). Our experiments show that both of our sample selection methods outperform the random selection method and the KBL selection method improves detection accuracy by 6%. Also, while existing works focus on deep neural networks with respect to adversarial retraining, we additionally assess the impact of such adversarial samples on other classifiers and our proposed selective adversarial retraining approaches show similar performance improvement for these classifiers as well. The outcomes from the study can assist in designing robust security systems for IIoT applications.
Description:
Industrial Internet of Things (IIoT) deploys edge devices to act as intermediaries between sensors and actuators and application servers or cloud services. Machine learning models have been widely used to thwart malware attacks in such edge devices. However, these models are vulnerable to adversarial attacks where attackers craft adversarial samples by introducing small perturbations to malware samples to fool a classifier to misclassify them as benign applications. Literature on deep learning networks proposes adversarial retraining as a defense mechanism where adversarial samples are combined with legitimate samples to retrain the classifier. However, existing works select such adversarial samples in a random fashion which degrades the classifier's performance. This work proposes two novel approaches for selecting adversarial samples to retrain a classifier. One, based on the distance from malware cluster center, and the other, based on a probability measure derived from a kernel based learning (KBL). Our experiments show that both of our sample selection methods outperform the random selection method and the KBL selection method improves detection accuracy by 6%. Also, while existing works focus on deep neural networks with respect to adversarial retraining, we additionally assess the impact of such adversarial samples on other classifiers and our proposed selective adversarial retraining approaches show similar performance improvement for these classifiers as well. The outcomes from the study can assist in designing robust security systems for IIoT applications.
Description:
The number of IoT sensors and physical objects accommodated on the Internet is increasing day by day, and traditional Cloud Computing would not be able to host IoT data because of its high latency. Being challenged of processing all IoT big data on Cloud facilities, there is not enough study on automating components to deal with the big data and real-time tasks in the IoT–Fog–Cloud ecosystem. For instance, designing automatic data transfer from the fog layer to cloud layer, which contains enormous distributed devices is challenging. Considering fog as the supporting processing layer, dealing with decentralized devices in the IoT and fog layer leads us to think of other automatic mechanisms to manage the existing heterogeneity. The big data and heterogeneity challenges also motivated us to design other automatic components for Fog resiliency, which we address as the third challenge in the ecosystem. Fog resiliency makes the processing of IoT tasks independent to the Cloud layer. This survey aims to review, study, and analyze the automatic functions as a taxonomy to help researchers, who are implementing methods and algorithms for different IoT applications. We demonstrated the automatic functions through our research in accordance to each challenge. The study also discusses and suggests automating the tasks, methods, and processes of the ecosystem that still process the data manually.
Description:
In many application scenarios, wireless sensors are deployed deterministically throughout a wide area to detect and report specific events or monitor environmental parameters. To cover a large area with minimal number of sensors, it is important to determine sensing radius of the operating sensors. Since the emitted energy of a random event is neither predictable nor fixed, accurate sensing radius modelling is a challenging problem. To the best of our knowledge, no work has considered how the event intensity factor reduces probability of event detection while assuming a sensing radius despite its high significance in important areas such as coverage, detection, localization, etc. In this paper, we have proposed a novel stochastic model of the maximum sensing radius to guarantee a user-defined event detection probability from the pdf of average event intensity and the quality of sensors. Comprehensive theoretical and numerical analyses are presented to evaluate the event detection performance of this model against different relevant parameters and these are also verified by simulation. Provision for event location trajectory computation is analysed for high-intensity events.
Description:
Accurate estimation of the in situ strength of concrete at early age is very important as it provides the necessary information required to start subsequent construction operations. Overestimation of the strength may cause serious safety hazards and underestimation may lead to unnecessary costly delays. This study investigates the performance of the maturity method in estimating the strength of in situ concrete subjected to cold weather at early age. Instrumented concrete slabs were subjected to cold weather conditions at early ages and their strengths were measured using drilled core samples from the slab. Sensors embedded in the slabs measured the temperature in the concrete which was used to estimate the strength using the maturity method. The measured core strengths at 24 and 72 h after casting are then compared with the estimated strengths using the maturity method and its performance is evaluated. The core strengths are also compared with the strength of standard cylinders cured at the same condition as the slabs. More than 250 cylinders from two slab thicknesses and four batches of concrete were used in the experiments to obtain statistically significant experimental data. The results show that the maturity method performed much better than the standard cylinder strength. On average the standard cylinder strength underestimated the core strength by more than 40% while the maturity method overestimated the strength by less than 10% with a lower variation.
Description:
Obfuscated Memory Malware (OMM) presents significant threats to interconnected systems, including smart city applications, for its ability to evade detection through concealment tactics. Existing OMM detection methods primarily focus on binary detection. Their multiclass versions consider a few families only and, thereby, fail to detect much existing and emerging malware. Moreover, their large memory size makes them unsuitable to be executed in resource-constrained embedded/IoT devices. To address this problem, in this paper, we propose a multiclass but lightweight malware detection method capable of identifying recent malware and is suitable to execute in embedded devices. For this, the method considers a hybrid model by combining the feature-learning capabilities of convolutional neural networks with the temporal modeling advantage of bidirectional long short-term memory. The proposed architecture exhibits compact size and fast processing speed, making it suitable for deployment in IoT devices that constitute the major components of smart city systems. Extensive experiments with the recent CIC-Malmem-2022 OMM dataset demonstrate that our method outperforms other machine learning-based models proposed in the literature in both detecting OMM and identifying specific attack types. Our proposed method thus offers a robust yet compact model executable in IoT devices for defending against obfuscated malware.
Description:
Obfuscated Memory Malware (OMM) presents significant threats to interconnected systems, including smart city applications, for its ability to evade detection through concealment tactics. Existing OMM detection methods primarily focus on binary detection. Their multiclass versions consider a few families only and, thereby, fail to detect much existing and emerging malware. Moreover, their large memory size makes them unsuitable to be executed in resource-constrained embedded/IoT devices. To address this problem, in this paper, we propose a multiclass but lightweight malware detection method capable of identifying recent malware and is suitable to execute in embedded devices. For this, the method considers a hybrid model by combining the feature-learning capabilities of convolutional neural networks with the temporal modeling advantage of bidirectional long short-term memory. The proposed architecture exhibits compact size and fast processing speed, making it suitable for deployment in IoT devices that constitute the major components of smart city systems. Extensive experiments with the recent CIC-Malmem-2022 OMM dataset demonstrate that our method outperforms other machine learning-based models proposed in the literature in both detecting OMM and identifying specific attack types. Our proposed method thus offers a robust yet compact model executable in IoT devices for defending against obfuscated malware.
Description:
Summary Wireless sensor networks (WSNs) consist of resource‐starving miniature sensor nodes deployed in a remote and hostile environment. These networks operate on small batteries for days, months, and even years depending on the requirements of monitored applications. The battery‐powered operation and inaccessible human terrains make it practically infeasible to recharge the nodes unless some energy‐scavenging techniques are used. These networks experience threats at various layers and, as such, are vulnerable to a wide range of attacks. The resource‐constrained nature of sensor nodes, inaccessible human terrains, and error‐prone communication links make it obligatory to design lightweight but robust and secured schemes for these networks. In view of these limitations, we aim to design an extremely lightweight payload‐based mutual authentication scheme for a cluster‐based hierarchical WSN. The proposed scheme, also known as payload‐based mutual authentication for WSNs, operates in 2 steps. First, an optimal percentage of cluster heads is elected, authenticated, and allowed to communicate with neighboring nodes. Second, each cluster head, in a role of server, authenticates the nearby nodes for cluster formation. We validate our proposed scheme using various simulation metrics that outperform the existing schemes.
Description:
Cognitive radio network (CRN) users are inherently expected to experience widely-varied delays due to the uncertainty in wireless channel availability. Supporting delay sensitive real-time services through CRNs, so that visitors are allowed to experience full-scale networking services by opportunistically sharing the spectrum from a number of existing networks without impacting on the primary users, thus remains a challenging task. This paper presents a novel technique to provision QoS guarantee for delay-sensitive services in CRNs having secondary users equipped with multiple radio interfaces. The technique relies on modeling spectrums holes from multiple primary networks through a resultant channel to enable implementing a single server queuing model with random service interruption. Simulation results using ns-2.33 show that using multiple radio interfaces has sheer strength to reduce CRN delay with fewer number of primary channel sensing.
Description:
Traditional packaging systems are refused since these systems do not provide any information about the quality of food products to the consumers and manufacturers at any stage of supply chain. The essence of a new technology to monitor the food spoilage from farm to fork is emerged to reduce hazards such as food borne diseases. Moreover, the food quality monitoring systems clarify the main factors in food wastage during supply chain. Intelligent packaging is employed to provide information about the history of food handling and storage to enhance food products quality and meet consumer satisfactions. Meat is one of the most perishable foods which causes sever illnesses in the case of spoilage. Variety of indicators and sensors have been proposed to warn about meat spoilage in meat industry. In this paper an overview of proposed approaches as well as commercial technologies to monitor the quality of meat during storage and transportation is presented. Furthermore, the existing technologies are compared in the sense of advantages and disadvantages in meat packaging applications.
Description:
Traditional packaging systems are refused since these systems do not provide any information about the quality of food products to the consumers and manufacturers at any stage of supply chain. The essence of a new technology to monitor the food spoilage from farm to fork is emerged to reduce hazards such as food borne diseases. Moreover, the food quality monitoring systems clarify the main factors in food wastage during supply chain. Intelligent packaging is employed to provide information about the history of food handling and storage to enhance food products quality and meet consumer satisfactions. Meat is one of the most perishable foods which causes sever illnesses in the case of spoilage. Variety of indicators and sensors have been proposed to warn about meat spoilage in meat industry. In this paper an overview of proposed approaches as well as commercial technologies to monitor the quality of meat during storage and transportation is presented. Furthermore, the existing technologies are compared in the sense of advantages and disadvantages in meat packaging applications.
Description:
Peptide receptors with Zn(ii)-DPA units and a covalently bound fluorescent coumarin indicator on an oxazole-containing scaffold are shown to function as more selective pyrophosphate sensors than the analogous chemosensing ensembles in indicator displacement assays.
Description:
Estimating various properties of soil, including moisture, carbon, and nitrogen, is crucial for studying their correlation with plant health and food production. However, conventional methods such as oven-drying and chemical analysis are laborious, expensive, and only feasible for a limited land area. With the advent of remote sensing technologies like multi/hyperspectral imaging, it is now possible to predict soil properties non-invasive and cost-effectively for a large expanse of bare land. Recent research shows the possibility of predicting those soil contents from a wide range of hyperspectral data using good prediction algorithms. However, these kinds of hyperspectral sensors are expensive and not widely available. Therefore, this paper investigates different machine and deep learning techniques to predict soil nutrient properties using only the red (R), green (G), and blue (B) bands data to propose a suitable machine/deep learning model that can be used as a rapid soil test. Another objective of this research is to observe and compare the prediction accuracy in three cases i. hyperspectral band ii. full spectrum of the visual band, and iii. three-channel of RGB band and provide a guideline to the user on which spectrum information they should use to predict those soil properties. The outcome of this research helps to develop a mobile application that is easy to use for a quick soil test. This research also explores learning-based algorithms with significant feature combinations and their performance comparisons in predicting soil properties from visual band data. For this, we also explore the impact of dimensional reduction (i.e., principal component analysis) and transformations (i.e., empirical mode decomposition) of features. The results show that the proposed model can comparably predict the soil contents from the three-channel RGB data.
Description:
Estimating various properties of soil, including moisture, carbon, and nitrogen, is crucial for studying their correlation with plant health and food production. However, conventional methods such as oven-drying and chemical analysis are laborious, expensive, and only feasible for a limited land area. With the advent of remote sensing technologies like multi/hyperspectral imaging, it is now possible to predict soil properties non-invasive and cost-effectively for a large expanse of bare land. Recent research shows the possibility of predicting those soil contents from a wide range of hyperspectral data using good prediction algorithms. However, these kinds of hyperspectral sensors are expensive and not widely available. Therefore, this paper investigates different machine and deep learning techniques to predict soil nutrient properties using only the red (R), green (G), and blue (B) bands data to propose a suitable machine/deep learning model that can be used as a rapid soil test. Another objective of this research is to observe and compare the prediction accuracy in three cases i. hyperspectral band ii. full spectrum of the visual band, and iii. three-channel of RGB band and provide a guideline to the user on which spectrum information they should use to predict those soil properties. The outcome of this research helps to develop a mobile application that is easy to use for a quick soil test. This research also explores learning-based algorithms with significant feature combinations and their performance comparisons in predicting soil properties from visual band data. For this, we also explore the impact of dimensional reduction (i.e., principal component analysis) and transformations (i.e., empirical mode decomposition) of features. The results show that the proposed model can comparably predict the soil contents from the three-channel RGB data.
Description:
Acoustic Emission (AE) has become a powerful tool for Non-Destructive Testing (NDT) and Structural Health Monitoring (SHM) to identify and locate damage in engineering structures. Propagation cracks and other damages emit stress waves which can be detected by suitable sensors mounted on the structures surface. AE is becoming more and more popular for composite structures since it is not only able to monitor a relative large area at a time and without scanning but also because it is able to detect and potentially discriminate all different failure types such as matrix cracking, delamination and fibre breakage. In order to identify the location of AE sources in large plate-like structures it typically requires the use of at least three widely spaced sensors. The distance between these sensors is defined by, for example, expected AE intensity and attenuation of the signals. This paper presents AE monitoring results from a tensile test on a composite plate. The origin of each AE event was located using a novel configuration of the three sensors, which were installed in a closely arranged triangular array with the sensors just 45 mm apart. The algorithm locates AE sources by determining the direction from which the wave approaches the array using the time of arrival and the distance the wave has travelled using the wave mode separation. The test was conducted on a carbon fibre reinforced composite (CFRP) plate with anisotropic lay-up. The technique is particularly suitable for NDT and SHM applications where the close positioning of the sensors allows the array to be installed in one housing to simplify mounting and wiring.
Description:
The increasing attacks on traffic signals worldwide indicate the importance of intrusion detection. The existing traffic signal Intrusion Detection Systems (IDSs) that rely on inputs from connected vehicles and image analysis techniques can only detect intrusions created by spoofed vehicles. However, these approaches fail to detect intrusion from attacks on in-road sensors, traffic controllers, and signals. In this paper, we proposed an IDS based on detecting anomalies associated with flow rate, phase time, and vehicle speed, which is a significant extension of our previous work using additional traffic parameters and statistical tools. We theoretically modelled our system using the Dempster-Shafer decision theory, considering the instantaneous observations of traffic parameters and their relevant historical normal traffic data. We also used Shannon's entropy to determine the uncertainty associated with the observations. To validate our work, we developed a simulation model based on the traffic simulator called SUMO using many real scenarios and the data recorded by the Victorian Transportation Authority, Australia. The scenarios for abnormal traffic conditions were generated considering attacks such as jamming, Sybil, and false data injection attacks. The results show that the overall detection accuracy of our proposed system is 79.3% with fewer false alarms.
Description:
The increasing attacks on traffic signals worldwide indicate the importance of intrusion detection. The existing traffic signal Intrusion Detection Systems (IDSs) that rely on inputs from connected vehicles and image analysis techniques can only detect intrusions created by spoofed vehicles. However, these approaches fail to detect intrusion from attacks on in-road sensors, traffic controllers, and signals. In this paper, we proposed an IDS based on detecting anomalies associated with flow rate, phase time, and vehicle speed, which is a significant extension of our previous work using additional traffic parameters and statistical tools. We theoretically modelled our system using the Dempster-Shafer decision theory, considering the instantaneous observations of traffic parameters and their relevant historical normal traffic data. We also used Shannon's entropy to determine the uncertainty associated with the observations. To validate our work, we developed a simulation model based on the traffic simulator called SUMO using many real scenarios and the data recorded by the Victorian Transportation Authority, Australia. The scenarios for abnormal traffic conditions were generated considering attacks such as jamming, Sybil, and false data injection attacks. The results show that the overall detection accuracy of our proposed system is 79.3% with fewer false alarms.
Description:
Emergency Management System (EMS) is an important component of Intelligent transportation systems, and its primary objective is to send Emergency Vehicles (EVs) to the location of a reported incident. However, the increasing traffic in urban areas, especially during peak hours, results in the delayed arrival of EVs in many cases, which ultimately leads to higher fatality rates, increased property damage, and higher road congestion. Existing literature addressed this issue by giving higher priority to EVs while traveling to an incident place by changing traffic signals (e.g., making the signals green) on their travel path. A few works have also attempted to find the best route for an EV using traffic information (e.g., number of vehicles, flow rate, and clearance time) at the beginning of the journey. However, these works did not consider congestion or disruption faced by other non-emergency vehicles adjacent to the EV travel path. The selected travel paths are also static and do not consider changing traffic parameters while EVs are en route. To address these issues, this article proposes an Unmanned Aerial Vehicle (UAV) guided priority-based incident management system to assist EVs in obtaining a better clearance time in intersections and thus achieve a lower response time. The proposed model also considers disruption faced by other surrounding non-emergency vehicles adjacent to the EVs' travel path and selects an optimal solution by controlling the traffic signal phase time to ensure that EVs can reach the incident place on time while causing minimal disruption to other on-road vehicles. Simulation results indicate that the proposed model achieves an 8% lower response time for EVs while the clearance time surrounding the incident place is improved by 12%.
Description:
Emergency Management System (EMS) is an important component of Intelligent transportation systems, and its primary objective is to send Emergency Vehicles (EVs) to the location of a reported incident. However, the increasing traffic in urban areas, especially during peak hours, results in the delayed arrival of EVs in many cases, which ultimately leads to higher fatality rates, increased property damage, and higher road congestion. Existing literature addressed this issue by giving higher priority to EVs while traveling to an incident place by changing traffic signals (e.g., making the signals green) on their travel path. A few works have also attempted to find the best route for an EV using traffic information (e.g., number of vehicles, flow rate, and clearance time) at the beginning of the journey. However, these works did not consider congestion or disruption faced by other non-emergency vehicles adjacent to the EV travel path. The selected travel paths are also static and do not consider changing traffic parameters while EVs are en route. To address these issues, this article proposes an Unmanned Aerial Vehicle (UAV) guided priority-based incident management system to assist EVs in obtaining a better clearance time in intersections and thus achieve a lower response time. The proposed model also considers disruption faced by other surrounding non-emergency vehicles adjacent to the EVs' travel path and selects an optimal solution by controlling the traffic signal phase time to ensure that EVs can reach the incident place on time while causing minimal disruption to other on-road vehicles. Simulation results indicate that the proposed model achieves an 8% lower response time for EVs while the clearance time surrounding the incident place is improved by 12%.