Search

The extensive growth in Industrial Internet of Things (IIoT) applications have tremendously increased the demands for low latency and resource sensitive computing to accomplish critical industrial automations. This has leveraged the use of some proficient computing paradigms like Multi-access Edge Computing (MEC) which facilitates a low latency and scalable solution for execution of industrial workloads. However, continual generation of industrial data has imposed a substantial amount of stress on the resource constrained MEC systems. In this perspective, our study proposes a Consolidated Stochastic Computation Offloading (CSCO) framework to address the increasing computational demands of MEC-based IIoT systems. The proposed framework efficiently handles industrial workloads by modeling them as stochastic processes to observe the number of data packets denied service due to finite number of busy MEC servers. We provide an analytical solution corresponding to the loss probability of data packets denied service at the MEC servers. This leads to the development of a computation offloading mechanism for time-critical tasks. Further, we provide the expression for Conditional Waiting Time (CWT) and Unconditional Waiting Time (UWT) of the data packets waiting to be offloaded to the remote cloud servers. Through extensive numerical simulations it is inferred that the proposed CSCO framework provides promising results in characterizing the stochastic behavior of MEC-based IIoT systems, thereby providing a low-latency, and resource sensitive solution for the considered system.

The enormous growth in Internet of Things (IoT) has caused large-scale transformation in data acquisition and communication mechanism for conventional IoT systems. The continuously increasing requirements for delay-tolerant delivery of services in IoT applications has led to the emergence of more scalable and energy-efficient computing platforms like edge computing. However, the massive growth in volume of data being offloaded from low-powered IoT devices to the edge has imposed challenges on edge servers in terms of traffic bottlenecks, latency, and wastage of energy. In this view, a Local Data Reduction (LDR) framework is proposed which addresses the latency issues and cost constraints to facilitate energy-efficient processing of IoT data. We exploit the Markovian birth-death process to model edge-based IoT systems and derive performance metrics for the proposed LDR model. We also provide explicit analytical solution for the total expected cost function incurred pertaining to the LDR and without LDR (WLDR) models. Through extensive numerical illustrations we validate our findings and observe that the proposed LDR model outperforms the WLDR model. Hence, the LDR model operates well to meet the Quality of Service (QoS) requirements for real-time IoT systems by favouring green computing paradigms.

The wide use of internet-enabled devices has not left the healthcare sector untouched. The health status of each individual is being monitored irrespective of his/her medical conditions. The advent of such medical devices is beneficial not only for patients but also for physicians, hospitals, and insurance companies. It makes healthcare fast, reliable, and hassle-free. People can keep an eye on their blood pressure, pulse rate, etc., and thus take preventive measures on their own. In hospitals, too, the Internet of Things (IoT) is being deployed for various tasks such as monitoring oxygen and blood sugar levels, electrocardiograms (ECGs), etc. The IoT in healthcare also reduces the cost of various ailments through fast and rigorous data analysis. The prediction of diseases through machine-learning techniques based on symptoms has become a promising concept. There may also be a situation where real-time analysis is required. In such a latency-sensitive situation, fog computing plays a vital role. Establishing communication every time with the cloud is not required with the introduction of fog and thus the latency is reduced. Healthcare is a latency-sensitive application area. So, the deployment of fog computing in this area is of vital importance. Our work focuses on improving the efficiency of the system for the precise diagnosis of and recommendations for heart disease. It evaluates the system using a machine-learning module.

Cloud computing delivers services through the Internet and enables the deployment of a diversity of apps to provide services to many businesses. At present, the low scalability of these cloud frameworks is their primary obstacle. As a result, they are unable to satisfy the demands of centralized computer systems, which are based on the Internet of Things (IoT). Applications such as disease surveillance and tracking and monitoring systems, which are highly latency sensitive, demand the computation of the Big Data communicated to centralized databases and from databases to cloud data centers, resulting in system performance loss. Recent concepts, such as fog and edge computing, offer novel approaches to data processing by relocating the processing power and other resources closer to the end user, thereby reducing latency and maximizing energy efficiency. Existing fog models, on the other hand, have a number of limitations and tend to prioritize either the precision of their findings or a faster response time, but not both. For the purpose of applying a healthcare solution in the real world, we developed and implemented a one-of-a-kind architecture that integrates quartet deep learning with edge computing devices. The paradigm that has been developed delivers health management as a fog service through the Internet of Things (IoT) devices and efficiently organizes the data from patients based on the requirements of the user. FogBus, a fog-enabled cloud framework, is used to measure the effectiveness of the proposed structure in regards to resource usage, network throughput, congestion, precision, and runtime. To maximize the QoS or forecast the accuracy in different fog computing settings and for different user requirements, the suggested technique can be set up to run in a number of different modes.

In recent times, several strategies to minimize the spread of 2019 novel coronavirus disease (COVID-19) have been adopted. Some recent technological breakthroughs like the drone-based tracking systems have focused on devising specific dynamical approaches for administering public mobility and providing early detection of symptomatic patients. In this paper, a smart real-time image processing framework converged with a non-contact thermal temperature screening module was implemented. The proposed framework comprised of three modules

In today’s era, the exponential growth of data and its management is a matter of concern. Machine learning has shown its efficacy in multiple application areas. But machine learning on decentralized data was a hectic task since last decade. A novel technology has gained much importance in recent days i.e., federated learning which deals with training on decentralized and distributed data along with preservation of its privacy. Smartphone data being privacy-sensitive is used for locally training a global model which further is aggregated to generate an updated global model which again is distributed among multiple clients. This paper focuses on presenting the efficacy of federated learning by epitomizing an architecture showing the working mechanism of the technology. Further, this paper exhibits an intersection of on-device machine learning, privacy preservation technology and edge computing i.e., federated learning. Also, we have used TensorFlow Federated, an open source platform to simulate federated learning tasks for MNIST and extended MNIST (E-MNIST) datasets. Further, the results contain the loss and accuracy parameters for ten iterations repeated for six optimizer states (Opt st ) for each dataset. The peak accuracy that we achieved for MNIST and E-MNIST datasets are 0.843 and 0.853 respectively by using federated averaging algorithm. Further, the minimum loss value that we obtained for MNIST and E-MNIST datasets are 0.652 and 0.646 respectively. The execution time for implementing the algorithm for each dataset is presented in a graphical manner. Finally, certain application areas where federated learning technology has aided are scrutinized.

The massive growth in the popularity of Internet of Things (IoT) and hence expansion in the number of IoT devices has led to network control issues. The heterogeneity observed in the generated data from each device has further contributed to latency delays and network traffic concerns. An integral part of current network research encompasses the monitoring of network activities, device identification, and secure exchange of information between different devices. The recognition and administration of these persistently increasing IoT devices have posed major challenges in various fields of their application, like Cyber-Physical Systems (CPSs). Hence, the management of network traffic flow between these devices has become a concerning issue. The prolonged inconsistency in cybersecurity systems and constrained computational capabilities have further made IoT devices more vulnerable to adversarial threats. To this end, the preservation and administration of network activities become crucial to manage. In this chapter, we address the network traffic administration issue for different IoT devices. We focus on the efficient characterization of inter-arrival rates of data generated from IoT devices for packet-level and flow-level analysis. Thus, making identification and management of IoT devices exceedingly significant for securing stable functioning of network activities. We also discuss some influential works conjectured to IoT devices and network analysis. The empirical results obtained from real-world network flows have been reported to provide a precise understanding of our observations. Finally, the strengths and weaknesses of some state-of-the-art technologies are discussed along with relevant future scopes.

The advent of information communication technologies (ICTs) has contributed enormously to the expansion of healthcare amenities worldwide. The retrieval and delivery of healthcare information over digital platforms have increased scope for inter- and intracare facilities among the healthcare industry. This comprises exchanging hypersensitive information pertinent to the patients’ health records. Thus a highly risk-free approach is required to transmit the information over several remotely distributed platforms. In this chapter, we provide a secure architecture for acquisition and distribution of healthcare information (possibly acquired through sensory devices) over a large scenario to facilitate inter- and intracare health facilities to the patients. We address some of the pitfalls of existing healthcare services and provide schemes for bridging the inconsistencies observed between these services. We address the issues of electronic health records (EHRs) in adaptively handling the patients’ health details, thus providing more interoperability to physicians, caregivers, healthcare clinics, and insurance agencies. We also provide an in-depth discussion regarding several enabling technologies that have led to the success of these smart healthcare services. Through our study, we introduce a blockchain-based architecture, which can address some of the critical care services by adding more ubiquity, reliability, and traceability to healthcare sector that conventional healthcare services failed to achieve.

With the outbreak of COVID-19 pandemic, several educational and business organizations have adopted online video conferencing platforms to facilitate their smooth functioning. These platforms have largely favored educational institutions for remotely conducting virtual classes over various electronic learning (e-learning) platforms. This has imposed challenges on existing Internet platforms for efficiently managing network performance generated from the extensive use of these platforms. In this paper, a framework for monitoring the effect of different network parameters, while using some well-known e-learning platforms is provided. The different LTE network performance parameters like uplink speed, downlink speed, network latency, and jitter are considered. We observed that the LTE network performance parameters obtained while using Microsoft Teams is optimum. Since, we observed that Microsoft Teams provided an optimal performance, we further perform analysis on Microsoft Teams. We further obtain the empirical distribution pertaining to the LTE network communication features by employing Gamma distribution. From our analysis, it is observed that the network throughput, latency, and jitter can be optimized to enhance the users' quality of experience by employing the proposed strategy.

The massive technological expansions in modern healthcare solutions have substantially influenced the development of several unfolding research fields. One such interesting area involves the therapeutic prognosis of pathological conditions in patients by using knowledge engineering techniques. These techniques have inevitably assisted in the growth of healthcare systems. In this paper, we provide a comprehensive classification framework for identification of pathological disorders in children. We consider a real dataset to study the accuracy in prediction of different classification algorithms for the identification of seven different pathological conditions. We then present an experimental analysis corresponding to the performance of each algorithm. This framework can be used for the early detection of diseases and for suggesting appropriate precautionary measures. Further a more stratified understanding of the demographics of a patient’s pathological conditions can be determined and appropriate treatment can be recommended.

The deployment of sensor nodes (SNs) in smart homes induces multipath transmission of signals in indoor environments (IEs). These paths occur due to the presence of household utility objects, which produce several reflected communication paths between the sender and the receiver. In order to determine the effective position of a target SN in a wireless sensor network (WSN), certain localization schemes are required in conjunction with trilateration methods. Therefore, it is worthwhile to estimate the uncertainties in the range for time of arrival (TOA) localization of SNs subjected to non-line of sight (NLOS) conditions. In this article, we provide a technique to characterize the variations in the range corresponding to the TOA based on the well-known Tsallis’ entropy framework. In this model, the non-extensive parameter q characterizes the variations in the localization range caused due to multipath components. In this context, we optimize the Tsallis entropy subject to the two moment constraints (i.e., mean and variance) along with the normalization constraint. Our proposed model is in excellent agreement with the synthetic data in contrast to the mixture model. This paper also provides a new approach for estimating the parameters corresponding to the mixture model and the proposed \(q-\)Gaussian model by minimizing the Jensen–Shannon (JS) symmetric measure between the two models and the synthetic data.

The advent of geographic information system has proven its efficiency in many relevant domains but still needs some more explorations. In this paper, a novel architecture towards the convergence of machine learning and GIS technology is presented. The enabling technologies associated to the implementations performed are well-defined and presented in this paper. Further, relevant works in the domain of the merger technology of machine learning and GIS technology is epitomized. This paper considered three relevant datasets viz., Indian census data, Zomato restaurants data and COVID-19 data for India for practically realizing the proposed framework. The proficiency of the proposed framework is presented through various results generated in this paper. Furthermore, the limitations posed by the proposed framework and ways to tackle the challenges are presented. Various geospatial visualization operations along with statistical plots are shown in this paper to epitomize the overlay analysis, point-cluster generation, heatmap analysis and spatial clustering approaches. Further, wherever required a Microsoft Bing map is provided to epitomize the performed risk analysis along with zonal classification. Finally, concluding remarks are summarized with the presentation of recent techniques like deep learning, serverless computing paradigm and so on to improve the proposed framework with diminished limitations.

The ability of the Internet of things (IoT) to incorporate anything and everything has induced and it is revolutionary applications in spheres of smart healthcare, smart living, smart cities, smart governance, and many more. A more general illustration for the IoT-based administration is the smart waste monitoring and management scheme for the smart cities. The smart waste management comprises of certain information and communication technologies (ICT) which support the tracking and management of the garbage bins. In this paper, we present a strategy for the garbage bin detection problem based on the thresholding scheme and also present a real-time waste management algorithm for the dynamic selection of optimal paths by the garbage collection vans. We also provide an optimal cost model subject to the threshold-based constraints which falls under the time complexity \(O\left( {p + n\;\log \;n} \right)\), (where \(p\) and \(n\) denote the path and the location of the smart dustbins), for our proposed algorithm.