Consumer electronics such as smart home devices, smartphones and smart wearables rely on accurate collection and sharing of data for massive user interaction. These form essential components of next ...generation Internet-of-Things (IoT) which require connected support. But owing to the limited battery life, these consumer nodes suffer from power limitations requiring frequent battery charging or replacements. This paper presents digital twin enabled wireless powering scheme for a massive IoT network. Digital twin creates a virtual replica of communication network involving large number of sensor nodes and access points (APs). This network is tested for energy deficient consumer IoT nodes and energy harvesting is enabled for the sensor nodes to harness the RF energy transmitted by the APs. Minimum Interference AP Clustering (MIAC), an energy conservation scheme for wireless powering of cell-free massive IoT is proposed which forms subsets of APs or AP clusters for each active node. In this paper, the performance of a digital twin IoT network is evaluated with energy harvesting and AP clustering for different transmission schemes. The amount of energy harvested and the spectral efficiency achieved is obtained along with the mathematical formulations. It is shown that the coherent transmission with linear energy harvesting achieves maximum average spectral efficiency of 2.659 bits/s/Hz. Further, the impact of incorporating AP clustering in the network transmission model suggests that the spectral efficiency achieved with AP clustering is 12% higher than the transmission scheme with no AP clustering. In the end, the proposed network is compared with two other network models for performance evaluation. A use case scenario of digital twin in consumer health for enabling smart healthcare ecosystem is also provided.
In the past few years, numerous methods of attack against recommendation systems have been developed. Cellphones, smart devices, and self-driving cars are instances of distributed IoT consumer ...devices that generate massive amounts of data on a daily basis and pose security threats to the cloud server. Due to the higher exchange of data, the challenges in this domain lead to increased security issues. Therefore, intrusion detection systems are important for the security and privacy of IoT consumer devices and hence to the cloud server. Due to the prediction, classification of attacks and recommendation of malware devices, the accuracy of machine learning and deep learning approaches for research in security for IoT consumer devices has gained tremendous popularity. Federated learning (FL), is a privacy-preserving decentralized learning technique that does not transport data but instead trains the model locally before sending the parameters to a cloud server, which helps in ensuring the security of data. However, communication channels can still be attacked by hackers, so blocking malicious data is a major requirement for the cloud server. In this paper, a federated learning recommender hybrid intrusion detection system (FRHIDS) model has been proposed that detects the attacks on the SDN network incoming from the IoT consumer devices and recommends that the safety devices transmit the decrypted data to the federated cloud server. In this model, the preservation of the security and privacy model parameters by utilizing the process of testing and training has been implemented. Simulation shows that the proposed approach's well-designed recommender system has outperformed state-of-the-art models. The performance of the proposed technique is evaluated based on its computational complexity and validation, which have shown 12% improvement over the already existing techniques.
Consumer electronics has witnessed rapid proliferation owing to the tremendous adoption of Internet-of-Things (IoT) technologies. The growing interaction between cyber world and the physical world ...demands intelligent and connected consumer products for ubiquitous information exchange. But the vulnerability to lack of coordinated connections, energy aware network solutions and regulated technology integrations is the main challenge. Thus it is very important to have new and sustainable support paradigm for next generation (next-gen) IoT based consumer electronics. This paper presents a robust resource control mechanism for consumer electronics based IoT network that offers communication support and reduced energy overhead. An intelligent reflecting surface (IRS) aided network model is proposed in which the consumer nodes or devices connect to the access points using various multiple IRSs. To foster the connected devices network in sustainable manner, resource control algorithm is proposed which enables the selection of optimal IRS against all IRSs. The performance of the network is evaluated for achievable sum rate for different transmit powers, different IRS phase shifts and number of IRS passive elements. It is observed that introduction of resource control scheme improves the achievable sum rate of the system by 9% using IRS with more reflecting elements with optimal phase shifts. Further, the energy efficiency analysis is carried out by proposing a power consumption model taking the power consumed by the circuit components into account. The proposed resource control enables the network model to attain maximum energy efficiency at lower signal-to-noise ratio (SNR) regime.
The emerging consumer electronic products and sensor devices are involved in data driven consumer applications. E-commerce is an important service application based on sensor Web technology. It ...involves networks of intelligent objects or sensor nodes for data collection and data sharing for e-commerce systems. But these massive devices involved in the huge data collection are battery limited. This puts huge energy burden on the Internet-of-Things (IoT) based wireless network. Thus, energy sustainability is very important in energy constrained IoT networks for next generation sustainable IoT support. This paper presents a wireless powered IoT network aided by self-sustainable intelligent reflecting surfaces (IRSs). The energy is harvested by the user nodes as well as the IRSs by tuning the IRS reflection coefficients. An algorithm is proposed which associates a set of IoT nodes to each IRS such that the energy requirements and sum rate of the network are met. It is observed that the IRS-aided system with energy harvesting capabilities achieve maximum average sum rate of 20 bits/s/Hz with the proposed algorithm at base station (BS) transmit power <inline-formula> <tex-math notation="LaTeX">P_{t} </tex-math></inline-formula> of 40 dBm. Further, the impact of energy harvesting on the tradeoff between required power and achieved sum rate is evaluated. The IRS-aided wireless powered system is compared with system model with no IRS and no energy harvesting case for performance evaluation. In the end, the use-case scenarios of energy efficient wireless network in e-commerce consumer electronic systems are also discussed.
Energy is vital parameter for communication in Internet of Things (IoT) applications via Wireless Sensor Networks (WSN). Genetic algorithms with dynamic clustering approach are supposed to be very ...effective technique in conserving energy during the process of network planning and designing for IoT. Dynamic clustering recognizes the cluster head (CH) with higher energy for the data transmission in the network. In this paper, various applications, like smart transportation, smart grid, and smart cities, are discussed to establish that implementation of dynamic clustering computing-based IoT can support real-world applications in an efficient way. In the proposed approach, the dynamic clustering-based methodology and frame relay nodes (RN) are improved to elect the most preferred sensor node (SN) amidst the nodes in cluster. For this purpose, a Genetic Analysis approach is used. The simulations demonstrate that the proposed technique overcomes the dynamic clustering relay node (DCRN) clustering algorithm in terms of slot utilization, throughput and standard deviation in data transmission.
Summary
With the advancements in the technology, Internet of Things (IoT)‐based wireless sensor networks (WSNs) have shown a tremendous growth in rendering a huge number of applications across the ...globe. However, it is observed that IoT‐based sensor nodes suffer from energy limitations. To resolve this, cluster‐based topology is adapted by the various researchers for rendering green energy‐efficient solution for communication of IoT devices. In this paper, the dynamic and energy‐efficient clustering for energy hole mitigation (DECEM) is proposed. The proposed framework is composed of the following proposed attributes; network is divided in two halves of regions, in each half, a gateway node (GN) is selected that collects data from their corresponding half region. Further, in each cluster, two cluster heads (CHs) are selected among whom one is made active at a moment (remains active until 60% of its energy is consumed) and other stays in sleep mode. First, the GN is selected in each side of the network (divided into two halves), and later, clustering is done, and selection of two CHs in each cluster is performed. The parameters for the selection of GN and CHs include residual energy, separation between the node and the sink, the number of neighbour nodes and network's residual energy. The simulation experiments reveal that DECEM has enhanced stability period by 5% and 31% as compared to the MEEC and IDHR protocols, respectively. The network lifetime is gigantically improved by 56% as compared to MEEC protocol.
The dynamic clustering is proposed to alleviate energy hole problem. As the sink is placed outside the network, the one gateway node (GN) is located in each half of the network area. In each cluster, two CHs are selected, only one is active at one moment. However, when the energy of active CH drops by 60% of its initial energy, it goes to sleep mode. This process is repeated till both nodes come to the same level of energy. Thereafter, only one CH becomes active and other becomes cluster member. The selection of CH and GN is done based on energy, distance, number of neighbour nodes and network's residual energy.
One of the most ubiquitous cause of worldwide deforestation and devastation of wildlife is fire. To control fire and reach the forest area in time is not always possible. Consequently, the level of ...destruction is often high. Therefore, predicting fires well in time and taking immediate action is of utmost importance. However, traditional fire prediction approaches often fail to detect fire in time. Therefore, a more reliable approach like the Internet of Things (IoT) needs to be adopted. IoT sensors can not only observe the real-time conditions of an area, but it can also predict fire when combined with Machine learning. This paper provides an insight into the use of Machine Learning models towards the occurrence of forest fires. In this context, eight Machine Learning algorithms: Boosted Decision Trees, Decision Forest Classifier, Decision Jungle Classifier, Averaged Perceptron, 2-Class Bayes Point Machine, Local Deep Support Vector Machine (SVM), Logistic Regression and Binary Neural Network model have been implemented. Results suggest that the Boosted decision tree model with the Area Under Curve (AUC) value of 0.78 is the most suitable candidate for a fire prediction model. Based on the results, we propose a novel IoT-based smart Fire prediction system that would consider both meteorological data and images for early fire prediction.
Among the key challenges with wireless sensor networks (WSNs) is that most sensor nodes are fueled by energy-constrained batteries, which has a significant impact on the network’s efficiency, ...reliability, and durability. As a result, many clustering approaches have been developed to enhance the energy efficiency of WSNs. Meanwhile, fifth-generation (5G) transmissions necessitate the usage of multiple-input multiple-output (MIMO) multiple antennas in numerous Internet of Things (IoT) applications to furnish increased capacity in a multipath spectrum environment. Instead of a single senor that can facilitate better load balancing utilization, we believe to balance the energy utilization per unit area. The devices in IoT are submerged with various transmission interfaces known as MIMO in 5G networks. With MIMO being more commonly accessible on IoT devices, an effective clustering approach for rapidly evolving IoT systems is both lacking and urgently needed to support a variety of user scenarios. In this paper, we proposed the intelligent MIMO-based 5G balanced energy-efficient protocol which focuses to achieve Quality of Experience (QoE) for transmitting in clusters for IoT networks. The proposed protocol enhances the utilization of energy and lifetime of the network in which it shows 30% less energy utilized in comparison to the existing protocols.
Recently, incredible growth in communication technology has given rise to the hot topic, big data. Distributed wireless sensor networks (WSNs) are the key provider of big data and can generate a ...significant amount of data. Various technical challenges exist in gathering the real-time data. Energy-efficient routing algorithms can overcome these challenges. The signal transmission features have been obtained by analyzing the experiments. According to these experiments, an energy-efficient big data algorithm (big data efficient gathering, BDEG) for a WSN is proposed for real-time data collection. Clustering communication is established on the basis of a received signal strength indicator and residual energy of sensor nodes. Experimental simulations show that BDEG is stable in terms of the network lifetime and the data transmission time because of the load-balancing scheme. The effectiveness of the proposed scheme is verified through numerical results obtained in MATLAB.
Alzheimer’s disease (AD) is the most generally known neurodegenerative disorder, leading to a steady deterioration in cognitive ability. Deep learning models have shown outstanding performance in the ...diagnosis of AD, and these models do not need any handcrafted feature extraction over conventional machine learning algorithms. Since the 2012 AlexNet accomplishment, the convolutional neural network (CNN) has been progressively utilized by the medical community to assist practitioners to early diagnose AD. This paper explores the current cutting edge applications of CNN on single and multimodality (combination of two or more modalities) neuroimaging data for the classification of AD. An exhaustive systematic search is conducted on four notable databases: Google Scholar, IEEE Xplore, ACM Digital Library, and PubMed in June 2021. The objective of this study is to examine the effectiveness of classification approaches on AD to analyze different kinds of datasets, neuroimaging modalities, preprocessing techniques, and data handling methods. However, CNN has achieved great success in the classification of AD; still, there are a lot of challenges particularly due to scarcity of medical imaging data and its possible scope in this field.
PDF