Cognitive Internet Of Things Research Articles

Efficient multichannel energy harvesting with dedicated energy transmitters in CR-IoT networks

Radio Frequency (RF) energy harvesting is strongly believed to be a sustainable solution to the power depletion problem in battery powered IoT devices. In addition to harvesting energy from ambient RF signals, the use of dedicated energy transmitters (ETs) that transmit energy to nearby IoT devices via RF signals has recently been proposed. In this paper, we study the problem of designing an energy harvesting policy for a group of cognitive radio-enabled IoT (CR-IoT) devices served by a number of ETs to maximize the minimum of their charging rates. With the help of cognitive radios, a CR-IoT node is capable of changing its frequency channel of operation allowing for multi-channel energy harvesting. Frequency channels are assumed to be opportunistically accessible depending on the activity of wireless users that are licensed to use those channels. The problem entails the design of the ET’s transmission policy (to what CR-IoT device, and over what channel) and the design of an ambient harvesting policy for every CR-IoT device (when it is not served by ETs). The problem is formulated as a mixed integer linear program (MILP). The objective is to maximize a lower bound on the total harvested energy in a given time frame per CR-IoT node. This optimization is subject to scheduling, total energy budget, and maximum transmit power constraints. Given the intractability of MILP formulations, a sub-optimal algorithm is proposed. Extensive experimentation is carried out to assess the effectiveness of the proposed sub-optimal algorithm by comparing it to the MILP’s solution obtained using IBM CPLEX solver with a limit on the execution time. We also combine our sub-optimal algorithm withe the CPLEX solver to produce a new two-stages algorithm that improves the original one by around 47%. Finally, we investigate the effect of multiple parameters including number of ETs, number of channels, and channel availability probability on the minimum charging rate.

Relational regression: a cognitively-inspired method for prediction system in cognitive IoT

Relational regression: a cognitively-inspired method for prediction system in cognitive IoT

Anti-Jamming Resource-Allocation Method in the EH-CIoT Network through LWDDPG Algorithm.

In the Energy-Harvesting (EH) Cognitive Internet of Things (EH-CIoT) network, due to the broadcast nature of wireless communication, the EH-CIoT network is susceptible to jamming attacks, which leads to a serious decrease in throughput. Therefore, this paper investigates an anti-jamming resource-allocation method, aiming to maximize the Long-Term Throughput (LTT) of the EH-CIoT network. Specifically, the resource-allocation problem is modeled as a Markov Decision Process (MDP) without prior knowledge. On this basis, this paper carefully designs a two-dimensional reward function that includes throughput and energy rewards. On the one hand, the Agent Base Station (ABS) intuitively evaluates the effectiveness of its actions through throughput rewards to maximize the LTT. On the other hand, considering the EH characteristics and battery capacity limitations, this paper proposes energy rewards to guide the ABS to reasonably allocate channels for Secondary Users (SUs) with insufficient power to harvest more energy for transmission, which can indirectly improve the LTT. In the case where the activity states of Primary Users (PUs), channel information and the jamming strategies of the jammer are not available in advance, this paper proposes a Linearly Weighted Deep Deterministic Policy Gradient (LWDDPG) algorithm to maximize the LTT. The LWDDPG is extended from DDPG to adapt to the design of the two-dimensional reward function, which enables the ABS to reasonably allocate transmission channels, continuous power and work modes to the SUs, and to let the SUs not only transmit on unjammed channels, but also harvest more RF energy to supplement the battery power. Finally, the simulation results demonstrate the validity and superiority of the proposed method compared with traditional methods under multiple jamming attacks.

Sequential detection with feedback information for two‐way cooperative spectrum sensing in cognitive internet of things

Sequential detection with feedback information for two‐way cooperative spectrum sensing in cognitive internet of things

Interference management of cognitive IoT based on interference steering and alignment

Interference management of cognitive IoT based on interference steering and alignment

Conscious points and patterns extraction: a high-performance computing model for knowledge discovery in cognitive IoT

Conscious points and patterns extraction: a high-performance computing model for knowledge discovery in cognitive IoT

Intelligent Health Surveillance: Cognitive IoT Enhanced by Rapid Machine Learning

Abstract: The quality of life for diabetic patients is significantly improved through continuous monitoring. Integrating various technologies such as the Internet of Things (IoT), embedded software, communication technologies, artificial intelligence, and smart devices helps reduce the financial burden on the healthcare system. Advances in communication technologies have facilitated personalized and remote healthcare. To meet the growing demand for advanced e-health applications, developing intelligent healthcare systems and increasing the number of applications connected to the network is essential. Consequently, to achieve critical needs like high bandwidth and energy efficiency, the 5G network must support smart healthcare applications. This research proposes an intelligent infrastructure for monitoring diabetes patients using machine learning methods. The architecture incorporates smart devices, sensors, and mobile phones to provide comprehensive coverage of the patient's body. Data collected from the patient is analyzed and classified using machine learning to produce a diagnosis. Several machine learning methods were tested to evaluate the proposed prediction system, and simulation results indicated that the Sequential Minimum Optimization (SMO) method provides higher classification accuracy, sensitivity, and precision than other techniques.

Inductive reasoning for significant concept and pattern discovery in cognitive IoT

Inductive reasoning for significant concept and pattern discovery in cognitive IoT

Hybrid intelligent system for channel allocation and packet transmission in CR-IoT networks

The proliferation of interconnected devices is driving a surge in the demand for wireless spectrum. Meeting the need for wireless channel access for every device, while also ensuring consistent quality of service (QoS), poses significant challenges. This is particularly true for resource-limited heterogeneous devices within Internet of Things (IoT) networks. Cognitive radio (CR) technology addresses the shortcomings of traditional fixed channel allocation policies by enabling unlicensed users to opportunistically access unused spectrum belonging to licensed users. This facilitates timely and reliable transmission of mission-critical data packets. A cognitive radio-enabled IoT (CR-IoT) network is poised to better accommodate the growing demands of diverse applications and services within the smart city framework, spanning areas such as healthcare, agriculture, manufacturing, logistics, transportation, environment, public safety, and pharmaceuticals. To minimize switching delays and ensure energy and spectral efficiency, this study proposes a hybrid intelligent system for efficient channel allocation and packet transmission in CR-IoT networks. Leveraging Support Vector Machine (SVM) and Adaptive Neuro-Fuzzy Inference System (ANFIS), the system dynamically manages spectrum resources to minimize handoffs while upholding QoS. A Java-based simulation integrates system outputs with interference temperature data to accommodate service demands across 2G–4G spectrums. Evaluation reveals SVM’s 98.8% accuracy in detecting spectrum holes and ANFIS’s 90.4% accuracy in channel allocation. These results demonstrate significant potential for enhancing spectrum utilization in various IoT applications.

Using Cognitive IOT In Vehicle System for On Actual Time Monitoring of CO2 Emission with Temperature and Alcohol Detector

One of the pressing environmental challenges we face today is the phenomenon of global warming, primarily driven by the release of greenhouse gases. Among these gases, carbon dioxide stands out as a significant contributor, with its emissions leading to a warming effect on the Earth's surface. Protecting our environment requires us to address and manage these changes effectively, presenting a considerable challenge. For long-term control of carbon dioxide emissions at their source, there is a growing recognition of the need for preventive and control technologies. This paper aims to employ IoT technology, utilizing Raspberry Pi's CO2 sensitivity, to monitor emissions from various sources such as public transportation, industries, and forest fires. Continuous monitoring of carbon dioxide levels within a city will help identify areas with the highest pollution levels. Additionally, this initiative seeks to implement an intelligent system for early detection of forest fires, also known as wildfires. These uncontrolled fires in natural areas pose significant threats to both ecosystems and human resources. It's noteworthy that wildfires emit more CO2 gas than initially assumed, impacting state climate targets. Integrating these efforts with IoT enhances security and enables various services, including the deployment of a Simple Notification Service (SNS) to alert mobile users about high CO2 levels in specific areas. Furthermore, this model aims to extend its capabilities to include the detection of temperature in heated vehicle components, such as engines, using temperature detectors. Moreover, alcohol detectors will be utilized to monitor alcohol consumption by vehicle drivers, enhancing safety measures on the road. Keywords: SNS (Simple Notification Service), IoT (Internet of Things), GPS (Global Positioning System), GVG (Green Vehicle Guide), MAQUMON (Mobile Air Quality Monitoring Network).

Multiple hypothesis testing in cognitive IoT sensor network

Recent Internet of Things (IoT) research aims to develop generic objects to learn, reason, and perceive their environment. Therefore, a new area has emerged known as cognitive IoT (CIoT). The cognitive Internet of Things integrates IoT with intelligence and behaves as well as humans through intelligent functionality. Several inferential tasks in CIoT require multiple hypothesis testing. The situation becomes cumbersome when the data is massive and heterogeneous. Thus, this research suggests a novel technique for multiple-hypothesis testing that uses a copula function to deal effectively with massive heterogeneous data. In addition, these data may contain missing or corrupted entries. Hence, it introduced probabilistic clustering, which reduces model inefficiency and takes control over the false discovery rate (FDR). Most of the variance from each cluster was extracted using kernel principal component analysis (KPCA) to reduce the processing burden at the fusion centre. Subsequently, it computes the p-value of each cluster's first principal component data and employs the Bonferroni method for multiple hypothesis testing. Finally, this research study evaluates the performance of the proposed algorithm on six-month environmental data, revealing that the proposed technique is efficient in terms of accuracy and computation time compared to other methods in the presence of massive heterogeneous data.

Plausible reasoning and knowledge extraction in Cognitive IoT

Plausible reasoning and knowledge extraction in Cognitive IoT

Multi-Channel Cooperative Spectrum Sensing and Scheduling for Cognitive IoT Networks

This paper presents a novel multi-channel cooperative spectrum sensing and scheduling (MC$_2$S$_3$) framework for spectrum and energy harvesting cognitive Internet of Things (IoT) networks. We address the challenge of maximizing network throughput by formulating a combinatorial problem that jointly optimizes the sensing scheduling of primary channels (PCs), the assignment of IoT devices for sensing scheduled PCs, and the clustering and allocation of IoT nodes to efficiently use discovered idle PCs; subject to spectrum utilization and collision avoidance constraints. Recognizing the inherent complexity of the underlying NP-hard mixed-integer non-linear programming (MINLP) problem, we propose a decomposition strategy that decouples the master problem into PC exploration and exploitation sub-problems. In the exploration phase, we derive closed-form solutions for optimal sensing durations and detection thresholds that satisfies spectrum utilization and collision avoidance constraints, which are then used to develop a priority metric to rank PCs. The proposed PC ranking informs a sequential PC scheduling and IoT sensing assignment approach that exploits a linear bottleneck assignment (LBA) strategy, proceeding until further scheduling does not enhance network utility. For the exploitation phase, we leverage a non-orthogonal multiple access (NOMA) strategy to multiplex multiple IoT nodes on a single PC, employing an iterative linear sum assignment (LSA) method for efficient allocation to maximize utilization of idle PCs. Numerical results validate the efficacy of our proposed methodologies, reaching an accuracy of approximately 99% in the order of milliseconds, significantly outperforming time complexity of brute-force benchmarks.

Attacking Modulation Recognition With Adversarial Federated Learning in Cognitive-Radio-Enabled IoT

Attacking Modulation Recognition With Adversarial Federated Learning in Cognitive-Radio-Enabled IoT

Physical-Layer Security Enhancement in Energy-Harvesting-Based Cognitive Internet of Things: A GAN-Powered Deep Reinforcement Learning Approach

Physical-Layer Security Enhancement in Energy-Harvesting-Based Cognitive Internet of Things: A GAN-Powered Deep Reinforcement Learning Approach

ASSOCIATE: A simulator for assessing soft security in the Cognitive Internet of Things

By augmenting the Internet of Things (IoT) with Artificial Intelligence (AI), the Cognitive Internet of Things (CIoT) has emerged, where intelligent objects autonomously sense, perceive, make decisions, and collaborate with minimal initial knowledge. Ensuring trust and security in such a cognitive society poses significant challenges. Soft security approaches, which leverage behavioral norms, have arisen as a promising solution to address these challenges. In this paper, we introduce ASSOCIATE, a modular and multi-layered tool designed for simulating and evaluating soft security models in the CIoT domain. ASSOCIATE applies a trust model to CIoT simulations and assesses the society’s soft security. The evaluation process encompasses society preparation, generation, trust model preparation, execution, and report generation. Input configuration files in the JSON format define simulation parameters, allowing the simulator to generate the requested society and conduct simulations. Evaluation results are presented through charts and graphs and saved in image and CSV formats. We demonstrate the tool’s functionality by enhancing the Santander dataset using the society generation module and analyzing various trust profiles. The proposed tool provides a valuable means of assessing the efficacy of soft security models in CIoT simulations, facilitating a comprehensive analysis of trust and security in CIoT systems.

Distributed Sequential Detection for Cooperative Spectrum Sensing in Cognitive Internet of Things.

The rapid development of wireless communication technology has led to an increasing number of internet of thing (IoT) devices, and the demand for spectrum for these devices and their related applications is also increasing. However, spectrum scarcity has become an increasingly serious problem. Therefore, we introduce a collaborative spectrum sensing (CSS) framework in this paper to identify available spectrum resources so that IoT devices can access them and, meanwhile, avoid causing harmful interference to the normal communication of the primary user (PU). However, in the process of sensing the PUs signal in IoT devices, the issue of sensing time and decision cost (the cost of determining whether the signal state of the PU is correct or incorrect) arises. To this end, we propose a distributed cognitive IoT model, which includes two IoT devices independently using sequential decision rules to detect the PU. On this basis, we define the sensing time and cost functions for IoT devices and formulate an average cost optimization problem in CSS. To solve this problem, we further regard the optimal sensing time problem as a finite horizon problem and solve the threshold of the optimal decision rule by person-by-person optimization (PBPO) methodology and dynamic programming. At last, numerical simulation results demonstrate the correctness of our proposal in terms of the global false alarm and miss detection probability, and it always achieves minimal average cost under various costs of each observation taken and thresholds.

Deep Learning approach for Co-operative Spectrum Sensing under Congested Cognitive IoT networks

Deep Learning approach for Co-operative Spectrum Sensing under Congested Cognitive IoT networks

A decentralised federated learning scheme for heterogeneous devices in cognitive IoT

Cognitive Internet of Things (IoT) technologies typically rely on substantial data collected from edge devices for data analysis and decision-making. However this reliance often leads to the inadvertent exposure of private data from smart edge devices. Federated learning (FL) is a distributed machine learning framework that protects user privacy by performing collaborative training without uploading private data. Nevertheless, applying classical FL to cognitive IoT systems to preserve privacy preservation faces significant challenges, such as central server failure and communication burden. Furthermore, when edge devices with heterogeneous data and systems participate in federated training, the learning process becomes slow and the performance of edge devices is compromised. To address these challenges, we propose a decentralised FL framework for cognitive IoT, termed DFL–MKF. In DFL– MKF, the centralised server is eliminated and each edge device is dynamically connected. We initialised models for edge devices based on computational and storage capabilities to accommodate system heterogeneity. Edge devices learned from the knowledge of multiple neighbours via knowledge transfer, and knowledge fusion was employed to aggregate the knowledge of multiple neighbours, thereby improving the performance of local models, and addressing data heterogeneity. Comprehensive experiments were performed on three image classification tasks. The results of these experiments demonstrate that the proposed method achieved superior performance compared to various baselines and improved communication efficiency.

Distributed private preserving learning based chaotic encryption framework for cognitive healthcare IoT systems

In the field of cognitive healthcare Internet of Things (CH-IoT), there is a strong demand for reliable and minimally intrusive smart gadgets that consistently acquire, analyse, and obtain the confidential health details of the individual. In fact, CH-IoT is empowered with artificial intelligence (AI) to transmute a fewer operational inputs into actionable, intelligent actions through the digitization of medical healthcare data. However, these systems consume more network complexity, interaction, and overhead costs, while inducing a blend of susceptibility and confidentiality issues. In support of this complexity, these cognitive systems need centralised data collection and to be gathered and analysed, which affects scalability issues and adds fuel to privacy and security breaches. Even though it possesses greater intricacy in its potential application, a substantial factor is maintaining the private preservation of healthcare data against the growing attacks. Thus, this paper presents a distributed privacy-preserving, chaotic encryption-based framework that can be deployed for CH-IoT systems to safeguard sensitive data against message modification, denial of service (DoS), and man-in-the-middle attacks (MIM), guaranteeing privacy and data integrity. The proposed framework integrated the federated learning layered hybrid chaotic encryption strategies by investigating through examination the learning infrastructure of convolutional neural networks (CNN). In the examination, the complete framework was carried out in the Tensorflow Federated Learning Libraries (FLL), and numerous performance metrics such as accuracy, precision, recall, f1-score, transmission efficiency, and overhead ratio were measured and contrasted with the various existing frameworks. For the intensive analysis, formal and informal security experiments were also conducted by NIST (National Institute of Science and Technology). The analytical results illustrate the importance of the proposed framework by achieving better security performance and outperforming the other existing models. Lastly, the proposed framework has more potential than the other existing frameworks and finds its place in real-time healthcare systems, but it needs to be improvised for real-time datasets.