Network Of IoT Devices Research Articles

Optimal method to monitor network for IoT devices based on anomaly detection

Many challenges have been identified to monitor, manage, process, and store the big data that accumulates from different sources in the IoT concept. The focus of this paper is very significant and limited to solving the problem of monitoring classified big data. Detection of anomalies in a grouping of classified data made it easy to monitor and help to make decisions for action to operate. There is no need to store, process, or manage the redundant data further that is already within the range of the group. So, the main concern is abnormal values in the groups that need to be processed further and require focus. The method proposed in this paper serves as an optimal solution designed to address the visualization challenges associated with dense and high-volume datasets. Our approach involves a strategic process of categorizing data into groups and pinpointing anomalies within these groups. This systematic classification not only enhances data organization but also plays a pivotal role in simplifying the visualization of intricate data patterns. Additionally, this method brings about significant cost efficiencies by strategically optimizing the expenses incurred in processing operations and the allocation of storage space for the equipment.

Optimized Resource Allocation in IoT Using Fuzzy Logic and Bio-Inspired Algorithms

IoT smart devices are a confluence of microprocessors, sensors, power source and transceiver modules to effectively sense, communicate and transfer data. Energy efficiency is a key governing value of the network performance of smart devices in distributed IoT networks. Low and discrete power and limited amount of memory and finite number of resources form some major bottlenecks in the workflow. Dynamic load balancing, reliability and flexibility are heavily relied upon by cloud computing for its accessibility. Resources are dynamically provided to the end client in an as-come on-demand fashion with the global network that is the Internet. Proportionally the need for services is increasing at a rate that is astonishing compared to any other forms of development. Load balancing seems a major challenge faced due to the architecture and the modular nature of our cloud environment. Loads need to be distributed dynamically to all the nodes. In this paper, we have introduced a technique that combines fuzzy logic with various nature inspired algorithms—grey wolf algorithm and firefly algorithm to effectively balance the load in a network of IoT devices. The performances of various nature inspired algorithms are compared with a brute force approach based on energy efficiency, network lifetime maximization, node failure rate and packet delivery ratio.

IoTDevID: A Behavior-Based Device Identification Method for the IoT

Device identification is one way to secure a network of IoT devices, whereby devices identified as suspicious can subsequently be isolated from a network. In this study, we present a machine learning-based method, IoTDevID, that recognizes devices through characteristics of their network packets. As a result of using a rigorous feature analysis and selection process, our study offers a generalizable and realistic approach to modelling device behavior, achieving high predictive accuracy across two public datasets. The model's underlying feature set is shown to be more predictive than existing feature sets used for device identification, and is shown to generalize to data unseen during the feature selection process. Unlike most existing approaches to IoT device identification, IoTDevID is able to detect devices using non-IP and low-energy protocols.

A blockchain security scheme to support fog-based internet of things

This paper proposes a fog-based secure data sharing framework for IoT devices that uses blockchain mechanism for this purpose. Fog computation is a popular paradigm that facilitates computation/storage facilities closer to the users and placed in between cloud environment and the users. Here, the IoT devices share data among each other through a secure mechanism. We propose two software agents: Software agent for Network formation and Monitoring (SAN) and Software agent for Blockchain formation and monitoring (SAB) placed in the fog node where SAN forms/monitors the network of IoT devices and SAB implements the security framework for blockchain implementation. Here, three different versions of AES (128/192/256) are used for group key sharing. Group key is used for encryption/decryption of the data present in a block of a blockchain. An AES 128 based Proof of Work (PoW) is used for block addition by an authorized IoT device. SHA 256 is used for implementing hashing in blockchain. Three different systems namely System 1, 2, and 3 are considered for the experiment under different settings of design parameters. A comparison between different settings is depicted in the result section. The execution time (in seconds) is used as an evaluation parameter. The performance is found to be best in case of System 3 configuration. The time requirement is found to be a monotonically increasing function of block size and AES key length.

Machine Learning in AWS for IoT-based Oil Pipeline Monitoring System

The world's economy is dominate by the oil export business, which is heavily reliant on oil pipelines. Due to the length of the pipes and the harsh environment through which they pass, continuous structural health monitoring of pipelines using normal methods is difficult and expensive. In this paper, an IoT system integrated with cloud services is propose for oil pipeline structure monitoring. The system is based on collecting data from sensor nodes attached to the pipeline structure, which collectively form a network of IoT devices connected to the AWS cloud. Measurements from sensor nodes are collect, stored, and filtered in AWS cloud. Measurements are also make accessible to users through the internet in real-time using Python web framework, Flask, and sending alarms via email in real-time. The performance of the system is evaluate by applying damaging events (hard knocking) on the oil pipeline at several distances. Analysis of IoT data by machine learning classification algorithms, apply and comparison between SVM, Random Forest Classifier, and Decision Tree to determine the best one, and then built in EC2 Linux in AWS to analyses the measurements and classify new events according to their distances from the sensor nodes. The proposed system is test on field measurements that were collect in Al-Mussaib Gas Turbine Power Station in Baghdad. Among the three classifiers, Random Forest achieved 90% classification rate.

IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices.

Two main approaches exist when deploying a Convolutional Neural Network (CNN) on resource-constrained IoT devices: either scale a large model down or use a small model designed specifically for resource-constrained environments. Small architectures typically trade accuracy for computational cost by performing convolutions as depth-wise convolutions rather than standard convolutions like in large networks. Large models focus primarily on state-of-the-art performance and often struggle to scale down sufficiently. We propose a new model, namely IoTNet, designed for resource-constrained environments which achieves state-of-the-art performance within the domain of small efficient models. IoTNet trades accuracy with computational cost differently from existing methods by factorizing standard 3 × 3 convolutions into pairs of 1 × 3 and 3 × 1 standard convolutions, rather than performing depth-wise convolutions. We benchmark IoTNet against state-of-the-art efficiency-focused models and scaled-down large architectures on data sets which best match the complexity of problems faced in resource-constrained environments. We compare model accuracy and the number of floating-point operations (FLOPs) performed as a measure of efficiency. We report state-of-the-art accuracy improvement over MobileNetV2 on CIFAR-10 of 13.43% with 39% fewer FLOPs, over ShuffleNet on Street View House Numbers (SVHN) of 6.49% with 31.8% fewer FLOPs and over MobileNet on German Traffic Sign Recognition Benchmark (GTSRB) of 5% with 0.38% fewer FLOPs.

A UAV-assisted CH election framework for secure data collection in wireless sensor networks

With the advance of UAV-related technologies, UAV-assisted wireless communications such as UAV-assisted coverage extension, UAV-assisted relaying and UAV-assisted data distribution and collection are gathering a lot of interests from government and industry fields. More specifically, the UAV-assisted data distribution and collection is implemented as a UAV-based WSN (Wireless Sensor Network). In the UAV-based WSN, a CH (Cluster Head) plays a crucial role such as data collection from members, data transfer toward a UAV and data distribution from the UAV to its members. Due to the role of a CH, many attackers try to make their compromised nodes CHs. In the general CH election framework, since each node determines a CH role by itself, compromised nodes declare themselves as a CH regardless of their disqualification. Generally, a compromised CH consumes much more energy than a normal CH because it keeps fulfilling the CH role to deliver corrupted messages to the sink greedily. Inspired by this phenomenon, we propose a UAV-assisted CH election framework which collects residual energy of nodes, and employs them for electing new CHs and excluding the lowest energy nodes from CH candidates. Simulation results show that our framework outperforms the general CH election framework even when the number of compromised nodes is large. Concerning the CH election period, our framework provides better security and performance than the general CH election framework with a short CH election period. Besides, the variation of node compromise time had no impact on our framework’s superiority to the general CH election framework. Another simulation results show that the increase of UAV tour frequency enhances both security and performance of our framework. Our CH election framework is easily applied to a network of IoT devices because the IoT network also demands clustering for energy and data management efficiency. Our future work item is applying as many other CH election schemes as possible to our framework and comparing their security and performance.

The Network of IoT Devices for Realize Smart Home

The Network of IoT Devices for Realize Smart Home