Heterogeneous Smart Research Articles

An Index Policy Based on Sarsa and Q -Learning for Heterogeneous Smart Target Tracking

An Index Policy Based on Sarsa and Q -Learning for Heterogeneous Smart Target Tracking

Data governance challenges on smart home involving multiple research sites

Abstract Background The development of Ambient Assisted Living (AAL) technology has great potential for ubiquitous health monitoring through collaboration between multiple research sites, but its use poses significant challenges to data governance. This study aims to investigate data governance challenges arising when smart home data flows across different research sites. Methods A four-analytic-dimension method was used to identify potential data-related issues that may occur when heterogeneous smart home data moves around multiple research sites. These dimensions include data domain, stakeholders, value, and governance goal. Results Data domain has difficulty in categorizing new data types generated by analytical models without a specified agreement, and determining the regulations for varying levels of anonymization and privacy protection is unclear in the AAL research field. Stakeholders in the AAL project may hold have different norms and practices for data use. Although some common values may be shared, such as improving the quality of homecare, conflicts may still arise and need to be regulated by data governance. Shifting AAL data between stakeholders may reduce its value, as different stakeholders may have varying interests. For instance, removing identifiable information from data to preserve privacy may reduce its value for researchers exploring individuals’ activity patterns. Governance goals are objectives for maintaining and facilitating data. While some governance goals can be widely acknowledged and shared, such as ensuring data security and privacy, conflicts may still exist over others, such as data access. Conclusions The big data generated by smart home technology highlights the need to develop proper data governance models to regulate data. This study’s implications include a better understanding of potential data-related challenges when data flows around multiple research sites, helping policymakers set up suitable data governance models. Key messages • AAL tech for health monitoring poses data governance challenges due to varying stakeholder norms and values. • Proper data governance models need to be developed for AAL data as it remains challenges in data domain, stakeholders, value, and governance goal.

A multiple-input fluid queue model for performance evaluation of fog server in an intelligent vehicular network

Nowadays, there is a growing trend towards fog computing which is a relatively new concept that has been introduced as an extension of cloud computing. It is considered as a promising paradigm for intelligent vehicular networks due to its ability to reduce delays and enhance network efficiency. The utilization of fog computing plays a crucial role in tackling the distinct obstacles encountered in vehicular computing, including issues like real-time data processing, and limitations on bandwidth. By relocating computational resources closer to the network’s edge, it enhances the effectiveness, dependability, and safety of vehicular applications while simultaneously boosting privacy and security measures. In addition, fog offloading has played a pivotal role in fog computing and edge computing structures. Its objective is to efficaciously allocate the data and assign the processing of tasks among edge devices, fog nodes, and cloud resources. Efficient fog offloading strategies are adaptable, scalable, and are able to handle faults, making them indispensable for optimizing these architectures. Although efficiency and quality of service are crucial objectives in a fog computing based intelligent vehicular network environment, performance remains a significant concern that cannot be overlooked. In light of this, to evaluate the efficacy of the probabilistic offloading approach on a fog server, a thorough performance evaluation is necessary. This research proposes a fluid queue approach that accounts for the constant flow of data packets while evaluating a fog server’s performance. For a fog computing-based intelligent vehicular network (FCIVN) with numerous heterogeneous smart vehicles (SVs), we construct a multiple-input fluid queue to model the tasks handed over to the fog server in order to evaluate its performance. In an FCIVN, the arrivals are drawn from various sources at the fog server. Accordingly, in the proposed model the fluid queue is modulated by more than one independent and distinct finite-state birth–death processes (BDPs) which control the variable inflow, and another BDP which controls the variable outflow. We present the details concerning an intermediate fog server’s buffer occupancy distribution within an FCIVN. Further, we assess the performance measures in terms of the offered load, expected buffer-level, average throughput and average latency of the tasks in an FCIVN. Finally, quantitative illustrations are presented to demonstrate the appropriateness of the fluid queue model developed in this study. The results are found to be in consistence with the expected behaviour of these performance indicators.

AC-DNN: An Adaptive Compact DNNs Architecture for Collaborative Learning Among Heterogeneous Smart Devices

AC-DNN: An Adaptive Compact DNNs Architecture for Collaborative Learning Among Heterogeneous Smart Devices

Impact of consumer preferences in a cournot duopoly market with heterogeneous smart sustainable supply chains

Impact of consumer preferences in a cournot duopoly market with heterogeneous smart sustainable supply chains

An expert system for hybrid edge to cloud computational offloading in heterogeneous MEC–MCC environments

Mobile Cloud Computing (MCC) integrates cloud computing into the mobile environment, effectively tackling performance, environmental, and security constraints. However, the proliferation of clouds and applications introduces complexities in offloading decisions. Mobile Edge Computing (MEC) has emerged as a solution to bolster MCC performance, capitalizing on the proximity to edge devices. However, optimizing computation offloading remains paramount for heterogeneous smart (mobile phones, wearables, and IoT) devices, necessitating efficient utilization of network resources and computational offloading. To address these challenges, this paper introduces NSANNOM (Network and Device Resources Utilization through Smart ANN-based Offloading Mechanism), an expert system designed for optimal computational offloading decision-making and efficient network resource allocation mechanisms. NSANNOM employs Artificial Neural Networks (ANN) for precise decision-making by validating real-world datasets, underscoring ANN’s superiority over existing algorithms, and showcasing enhanced energy savings, cost efficiency, and latency response. Experimental evaluations demonstrate that the proposed ANN model for the offloading decision-making algorithm achieves a training accuracy of 97% and a validation accuracy of 99%. The system consumes minimal energy (10 MJ) for task scheduling and exhibits remarkable accuracy in resource utilization across multiple tasks (10–50) ranging in size (from 1 to 16 GB). Additionally, it minimizes time delays (in milliseconds) during the offloading process.

Impact of consumer preferences on pricing and strategic decisions in a triopoly with heterogeneous smart sustainable supply chains

In the face of escalating environmental concerns, an expanding consumer base actively seeks authentic and transparent information traceability to reinforce their dedication to sustainable practices. This research aims to examine the impact of consumer preferences for product traceability, environmental sustainability, and brand on the optimal decisions and pricing strategies of firms within heterogeneous smart sustainable supply chains (SSCs). Employing both centralized and decentralized scenarios, the study develops differentiated triopoly models in which the participating players are categorized as boundedly rational, naive, and adaptive. Utilizing a differential game approach, the research analyzes the optimal decisions of entities and the performance of products under various scenarios. Subsequently, a Bertrand triopoly game is employed to scrutinize the pricing strategies of differentiated SSCs. The findings underscore the substantial influence of consumer sustainability and traceability preferences on information transparency for sustainable products, impacting both manufacturers and suppliers, while brand reputation positively shapes decision-making. The study reveals intricate effects of these preferences on the adjustment speed of boundedly rational supply chains, directly influencing market stability.

Asymmetric two-dimensional poroelastic analysis of heterogeneous smart discs considering hygrothermal loading

The objective of this study is to examine through the finite element method the impacts of employing two-dimensional (2D) properties grading on the behaviors of piezoelectric sensors/actuators due to their significance. These structures are modeled as variable thickness discs and are assumed to be exposed to simultaneous asymmetric loading conditions (thermal, hygral, electrical, and mechanical loads). Results demonstrate that the 2D grading is superior compared to the conventional one-dimensional grading for reducing the von Mises stress. The reduction reached, for instance, 8.3% allowing further increase of loading and/or safety. Also, the change of the displacement is varied between −4.5% and 31% depending on the considered grading pattern, and thus can be controlled to a desired value which helps to improve the sensing and actuating functionality for certain requirements. The study also examines the effects of porosity, and the results are compared to nonporous discs. Reductions of the maximum compressive tangential stress and von Mises stress reached 79.75% and 33.6%, respectively at specific porosity distribution patterns and volume fractions. These findings have significant implications for the manufacturing of smart structures, enabling them to operate in severe working conditions with better sensing and actuating capabilities than previously possible.

Multidimensional data processing and tensor analysis for large-scale power grids in a parallel computing framework

Abstract Grid data is compressed and stored without processing. There are problems of large compression errors and long running time, which affect the compression and storage effect. Therefore, this paper proposes a method for storing grid data using parallel computing frameworks. While drawing on the task scheduling strategy of MapReduce distributed computing framework, combined with the current situation of centralized deployment of data in the information system of the State Grid Corporation, an efficient tensor-based parallel computing method is proposed. The massive multivariate and heterogeneous smart grid data is compressed using the Tucker decomposition method for big data compression of smart grids. This method’s line resistance and reactance dynamic parameters have average values of 0.033 and 0.520, respectively, which are very close to the actual values. The method used in this paper has a high degree of accuracy in estimating resistance dynamic parameters. It possesses certain practical application performance. By predicting the daily average load of the North China Power Grid, the accuracy of the prediction data of the gridded load analysis is close to the actual value, indicating the superiority of the grid multidimensional data processing method designed in this paper.

Reinforcement Learning-Based Adaptive Feature Boosting for Smart Grid Intrusion Detection

Intrusion detection systems (IDSs) are crucial in the security monitoring for the smart grid with increasing machine-to-machine communications and cyber threats thereafter. However, the multi-sourced, correlated, and heterogeneous smart grid data pose significant challenges to the accurate attack detection by IDSs. To improve the attack detection, this paper proposes Reinforcement Learning-based Adaptive Feature Boosting, which aims to leverage a series of AutoEncoders (AEs) to capture critical features from the multi-sourced smart grid data for the classification of normal, fault, and attack events. Multiple AEs are utilized to extract representative features from different feature sets that are automatically generated through a weighted feature sampling process; each AE-extracted feature set is then applied to build a Random Forest (RF) base classifier. In the feature sampling process, Deep Deterministic Policy Gradient (DDPG) is introduced to dynamically determine the feature sampling probability based on the classification accuracy. The critical features that improve the classification accuracy are assigned larger sampling probabilities and increasingly participate in the training of next AE. The presence of critical features is increased in the event classification over the multi-sourced smart grid data. Considering potential different alarms among base classifiers, an ensemble classifier is further built to distinguish normal, fault, and attack events. Our proposed approach is evaluated on the two realistic datasets collected from Hardware-In-the-Loop (HIL) and WUSTIL-IIOT-2021 security testbeds, respectively. The evaluation on the HIL security dataset shows that our proposed approach achieves the classification accuracy with 97.28%, an effective 5.5% increase over the vanilla Adaptive Feature Boosting. Moreover, the proposed approach not only accurately and stably selects critical features on the WUSTIL-IIOT-2021 dataset based on the significant difference of feature sampling probabilities between critical and uncritical features, i.e., the probabilities greater than 0.08 and less than 0.01, but also outperforms the other best-performing approaches with the increasing Matthew Correlation Coefficient (MCC) of 8.03%.

Graph Learning for Interactive Threat Detection in Heterogeneous Smart Home Rule Data

The interactions among automation configuration rule data have led to undesired and insecure issues in smart homes, which are known as interactive threats. Most existing solutions use program analysis to identify interactive threats among automation rules, which is not suitable for closed-source platforms. Meanwhile, security policy-based solutions suffer from low detection accuracy because the pre-defined security policies in a single platform can hardly cover diverse interactive threat types across heterogeneous platforms. In this paper, we propose Glint, the first graph learning-based system for interactive threat detection in smart homes. We design a multi-scale graph representation learning model, called ITGNN, for both homogeneous and heterogeneous interaction graph pattern learning. To facilitate graph learning, we build large interaction graph training datasets by multi-domain data fusion from five different platforms. Moreover, Glint detects drifting samples with contrastive learning and improves the generalization ability with transfer learning across heterogeneous platforms. Our evaluation shows that Glint achieves 95.5% accuracy in detecting interactive threats across the five platforms. Besides, we examine a set of user-designed blueprints in the Home Assistant platform and reveal four new types of real-world interactive threats, called "action block", "action ablation", "trigger intake", and "condition duplicate", which are cross-platform interactive threats captured by Glint.

Secured gateway based communication in heterogeneous SM –neighbourhood area network in smart grid using FPGA design

Usage of the gateway in smart Grid (SG) makes the Grid more flexible, Making Sure the best interoperability in heterogeneous network architecture. The purpose of this gateway in SG will be to handle two communicating standards. In this paper, an FPGA layout for gateway has been presented that ensures the safety and manages heterogeneous Smart meters (SMs) in the Neighbourhood area of the smart Grid. The proposed work solves the Integration of two distinct communication standard Kinds of the smart meter (SM), PRIME and 6LoWPAN, which can be wired and wireless type Criteria. The integration of the SMs was performed using a multiplexer (2:1) and De-multiplexer (1:2) architecture in the SM to Data Concentrator Unit (DCU), and the hardware is executed through Xilinx RTL Simulation. The two MUX which is a wired SM type. The next input is just 6 LoWPAN (IPv6 Low power. The gateway architecture was created, including a Security algorithm AES-128,to provide data security for your 2 SMs data. Simulations are conducted MR-OFDM under distinct constellation sizes are compared to 6LoW PAN protocol, and the results promise a good performance in terms of hardware utilization, delay, and power. Comparison of this work provides better performance concerning hardware utilization. The Proposed architecture introduces a delay of the five ns time delay for its Procedure. The system mentioned above description is verified in the target device xc5vlx330-2ff1760 in the Xilinx ISE14.2. Hence the suggested gateway architecture is proved as an acceptable design for heterogeneous SMs to DCU communication in SG.

FLDID: Federated Learning Enabled Deep Intrusion Detection in Smart Manufacturing Industries.

The rapid development in manufacturing industries due to the introduction of IIoT devices has led to the emergence of Industry 4.0 which results in an industry with intelligence, increased efficiency and reduction in the cost of manufacturing. However, the introduction of IIoT devices opens up the door for a variety of cyber threats in smart industries. The detection of cyber threats against such extensive, complex, and heterogeneous smart manufacturing industries is very challenging due to the lack of sufficient attack traces. Therefore, in this work, a Federated Learning enabled Deep Intrusion Detection framework is proposed to detect cyber threats in smart manufacturing industries. The proposed FLDID framework allows multiple smart manufacturing industries to build a collaborative model to detect threats and overcome the limited attack example problem with individual industries. Moreover, to ensure the privacy of model gradients, Paillier-based encryption is used in communication between edge devices (representative of smart industries) and the server. The deep learning-based hybrid model, which consists of a Convolutional Neural Network, Long Short Term Memory, and Multi-Layer Perceptron is used in the intrusion detection model. An exhaustive set of experiments on the publically available dataset proves the effectiveness of the proposed framework for detecting cyber threats in smart industries over the state-of-the-art approaches.

Toward a Heterogeneous Smart Electromagnetic Environment for Millimeter-Wave Communications: An Industrial Viewpoint

Fifth generation (5G) and beyond communication systems open the door to millimeter Wave (mmWave) frequency bands to leverage the extremely large operating bandwidths and deliver unprecedented network capacity. These frequency bands are affected by high propagation losses that severely limit the achievable coverage. The simplest way to address this problem would be to increase the number of installed mmWave base stations (BSs), at the same time augmenting the overall network cost, power consumption and ElectroMagnetic Field (EMF) levels. As alternative direction, here we propose to complement the macro-layer of mmWave BSs with a heterogeneous deployment of Smart Electromagnetic (Smart EM) Entities - namely IAB nodes, Smart Repeaters, Reconfigurable Intelligent Surfaces (RISs) and passive surfaces - that is judiciously planned to minimize the total installation costs while at the same time optimizing the network spectral efficiency. Initial network planning results underline the effectiveness of the proposed approach. The available technologies and the key research directions for achieving this view are thoroughly discussed by accounting for issues ranging from system-level design to the development of new materials.

A flexible Compilation-as-a-Service and Remote-Programming-as-a-Service platform for IoT devices

The Internet-of-Things (IoT) presents itself as an emerging technology, which is able to interconnect a massive number of heterogeneous smart objects. Several complex data-driven applications, such as smart cities applications, home automation, health monitoring, etc., have been realized through the existence of these ubiquitous networks of smart objects. The ability to remotely update the devices forming an IoT network is of paramount importance, as it enables adding new functionality in their firmware, either for resolving software bugs and security vulnerabilities or for application re-purposing, without the need to physically access them. In this work, we present a flexible Compilation-as-a-Service and Remote-Programming-as-a-Service platform that jointly offers cloud-based compilation and Firmware-Over-The-Air (FOTA) update functionalities for deployed IoT devices, in a reliable and secure manner. Our system is capable of easily supporting various embedded operating systems and heterogeneous hardware platforms. We describe the system architecture and elaborate on the implementation details of all system components. In addition, we perform an extensive performance evaluation of a Proof-of-Concept (PoC) deployment of our system and discuss results in terms of system response, scalability and resource utilization.

Stress concentration in shape memory alloy sheets with circular cavities: Effects of transformation, saturation, and plasticity

The analysis of stress concentration in geometrically heterogeneous smart structures is of great importance. In this study, by utilizing a recent constitutive model which considered both transformation and plasticity of shape memory alloys (SMAs), the stress concentration factor (SCF) in plates with circular cavities is investigated and the effect of phase transformation, saturation, and plasticity which may occur locally is studied. The results show that the conversion of the austenitic phase to the martensite leads to a reduction in SCF. After saturation of phase transformation at the stress concentration point, the SCF increases until the entire sheet enters the martensite phase. In the example under study, the SCF reaches 5.8 which is greatly higher than the elastic SCF. By entering the plastic region locally, the SCF reduces. Also, the modeling of sheets with more than one cavity has been done. It is concluded that extra hole, as a stress relief method, has a stronger effect on decreasing maximum stress concentration of shape memory alloys (considering transformation and plasticity) compared to purely elastic stress concentration studies.

A signature-based data security and authentication framework for internet of things applications

<span>Internet of things (IoT) is the next big revolution in modernized network technologies connecting a massive number of heterogeneous smart appliances and physical objects. Owing to these technologies' novelty, various issues are characterized by security concerns are the most prioritized issue. A review of existing security approaches highlights that they are very particular about the solution towards a specific attack and cannot resist any unknown attacker. Therefore, this manuscript presents a novel computational model that introduces a unique authentication process using a simplified encryption strategy. The simulated study outcome shows that the proposed system offers efficient security and efficient data transmission performance in the presence of an unknown adversary. Hence, the study outcome exhibits better effects than frequently used security solutions when implemented in a vulnerable IoT environment.</span>

A resilient Trust Management framework towards trust related attacks in the Social Internet of Things

As a huge number of heterogeneous smart things in the Social Internet of Things (SIoT) paradigm are connected to exchange services, security principles are needed to ensure safe communication in the network. From this perspective, various Trust Management models have been set forward in the literature in order to assess nodes trustworthiness and therefore to avoid malicious connections in the SIoT network. However, these models still lack practical solutions to address SIoT trust related attacks performed towards the trust evaluation process. In this regard, the present work stands for an in-depth study on the effectiveness of the trust attack management, as it is integrated into the trust model, with the aim of classifying the nodes behaviors more accurately in order to ensure secure connections in the network. For this reason, nodes behaviors analysis, based on Machine Learning (ML) algorithms, is carried out within our trust assessment process. Our objective lies in limiting interactions with not only poor service provider, but also with attacker nodes. The proposed trust method’s acquired outcome reveals that our introduced TM model demonstrates an improved efficiency in identifying malicious nodes compared to a trust classification algorithm without nodes behaviors evaluation. Experimentation conducted within a simulated dataset based on real social data through Cooja; corroborates the efficiency of our proposed solution in terms of coping with simulated trust related attacks performed by malicious nodes.

Features-Aware DDoS Detection in Heterogeneous Smart Environments based on Fog and Cloud Computing

Nowadays, urban environments are deploying smart environments (SEs) to evolve infrastructures, resources, and services. SEs are composed of a huge amount of heterogeneous devices, i.e., the SEs have both personal devices (smartphones, notebooks, tablets, etc) and Internet of Things (IoT) devices (sensors, actuators, and others). One of the existing problems of the SEs is the detection of Distributed Denial of Service (DDoS) attacks, due to the vulnerabilities of IoT devices. In this way, it is necessary to deploy solutions that can detect DDoS in SEs, dealing with issues like scalability, adaptability, and heterogeneity (distinct protocols, hardware capacity, and running applications). Within this context, this article presents an Intelligent System for DDoS detection in SEs, applying Machine Learning (ML), Fog, and Cloud computing approaches. Additionally, the article presents a study about the most important traffic features for detecting DDoS in SEs, as well as a traffic segmentation approach to improve the accuracy of the system. The experiments performed, using real network traffic, suggest that the proposed system reaches 99% of accuracy, while reduces the volume of data exchanged and the detection time.

A Fog-Based Multi-Purpose Internet of Things Analytics Platform

Data analytics is an important component for the benefit and growth of the Internet of Things (IoT). The utilization of data generated by a variety of heterogeneous smart devices offers the possibility of gaining meaningful insights into various aspects of the daily lives of end consumers, the environment and weather, but also into value-added processes of business and industry. The potential benefits derived from analyzing IoT data can be further enhanced by advancing developments in streaming and machine learning technologies. A critical factor in the application of these technologies are the underlying analytics architectures. These must overcome a variety of different challenges that are influenced by technical, but also legal or personal constraints and differ in importance and impact depending on the IoT application domain in which such an architecture is to be deployed. Solutions presented by previous research address only a handful of these challenges. An important capability to address the variety of challenges that arise from this situation is the ability to support the hybrid deployment of analytics pipelines at different network layers. Consequently, in this work, we propose an architectural solution that enables hybrid analytics pipeline deployments, addresses the challenges described in previous scientific literature and can be deployed in various IoT application domains. Finally, we experimentally evaluate the proposed solution.