“…The extreme learning machine (ELM), fuzzy system and modified swarm intelligence is used to develop hybrid optimized fuzzy threshold ELM (HOFTELM) algorithm for the localization of elderly persons in smart cities. The algorithm outperforms the existing algorithms in terms of average location error ratio (ALER) and is computationally efficient [93].…”
With exponential growth in the deployment of Internet of Things (IoT) devices, many new innovative and real-life applications are being developed. IoT supports such applications with the help of resource-constrained fixed as well as mobile nodes. These nodes can be placed in anything from vehicles to the human body to smart homes to smart factories. Mobility of the nodes enhances the network coverage and connectivity. One of the crucial requirements in IoT systems is the accurate and fast localization of its nodes with high energy efficiency and low cost. The localization process has several challenges. These challenges keep changing depending on the location and movement of nodes such as outdoor, indoor, with or without obstacles and so on. The performance of localization techniques greatly depends on the scenarios and conditions from which the nodes are traversing. Precise localization of nodes is very much required in many unique applications. Although several localization techniques and algorithms are available, there are still many challenges for the precise and efficient localization of the nodes. This paper classifies and discusses various state-of-the-art techniques proposed for IoT node localization in detail. It includes the different approaches such as centralized, distributed, iterative, ranged based, range free, device-based, device-free and their subtypes. Furthermore, the different performance metrics that can be used for localization, comparison of the different techniques, some prominent applications in smart cities and future directions are also covered.
“…The extreme learning machine (ELM), fuzzy system and modified swarm intelligence is used to develop hybrid optimized fuzzy threshold ELM (HOFTELM) algorithm for the localization of elderly persons in smart cities. The algorithm outperforms the existing algorithms in terms of average location error ratio (ALER) and is computationally efficient [93].…”
With exponential growth in the deployment of Internet of Things (IoT) devices, many new innovative and real-life applications are being developed. IoT supports such applications with the help of resource-constrained fixed as well as mobile nodes. These nodes can be placed in anything from vehicles to the human body to smart homes to smart factories. Mobility of the nodes enhances the network coverage and connectivity. One of the crucial requirements in IoT systems is the accurate and fast localization of its nodes with high energy efficiency and low cost. The localization process has several challenges. These challenges keep changing depending on the location and movement of nodes such as outdoor, indoor, with or without obstacles and so on. The performance of localization techniques greatly depends on the scenarios and conditions from which the nodes are traversing. Precise localization of nodes is very much required in many unique applications. Although several localization techniques and algorithms are available, there are still many challenges for the precise and efficient localization of the nodes. This paper classifies and discusses various state-of-the-art techniques proposed for IoT node localization in detail. It includes the different approaches such as centralized, distributed, iterative, ranged based, range free, device-based, device-free and their subtypes. Furthermore, the different performance metrics that can be used for localization, comparison of the different techniques, some prominent applications in smart cities and future directions are also covered.
“…w . (23) The Conv-1 processes a radio image with the size of W × W × H = 60 × 60 × 3, by using convolutional kernel with stride of S (1) = 1, quantity of E (1) = 30, and size of F (1) × F (1) = 1 × 1. The size of Conv-1 layer output isW (1) × W (1) × H (1) , where…”
Section: Cnn-based Model For Localizationmentioning
confidence: 99%
“…The rapidly growing artificial intelligence, Internet of things (IoT), and wireless communication technologies have greatly facilitated the applications of location-based services, such as object navigation, healthcare management, smart life, and the applications of IoT [1][2][3][4]. Nearly all of these applications require an accurate location of indoors.…”
The intelligent indoor localization based on WIFI is increasingly concerned for its universality. However, in practical applications, its indoor localization accuracy is limited by noises, diffractions and multipath effects. To overcome these drawbacks, we design a new intelligence indoor localization system based on Channel State Information (CSI) of the wireless signal from Multiple Input Multiple Output (MIMO), named IILC. In IILC, the initial amplitude information is first processed in the measured CSI data, which can effectively suppress the impact from noise and other interference. Next, we explore a method to construct radio image. It can make full use of space-frequency information and time-frequency information from CSI-MIMO to obtain more location information. Then, we design a new deep learning network to obtain the optimal effective of radio image classification. Moreover, a mixed-norm is proposed to impose sparsity penalty and overfit constraint on the loss function, which makes the valuable feature units active and the others inactive. The experimental results verify that IILC system has excellent performance. The overall localization accuracy of IILC in the office scene can reach 97.10%, and the probability of localization error within 1.2m is 86.21%.
“…They proposed a hybrid optimized fuzzy threshold ELM (HOFTELM) algorithm by combining extreme learning machine (ELM), fuzzy system, and modified swarm intelligence. They also employed particle-swarm gray-wolf optimization to determine the motion of the sensor node [ 37 ].…”
The widespread use of the internet and the exponential growth in small hardware diversity enable the development of Internet of things (IoT)-based localization systems. We review machine-learning-based approaches for IoT localization systems in this paper. Because of their high prediction accuracy, machine learning methods are now being used to solve localization problems. The paper’s main goal is to provide a review of how learning algorithms are used to solve IoT localization problems, as well as to address current challenges. We examine the existing literature for published papers released between 2020 and 2022. These studies are classified according to several criteria, including their learning algorithm, chosen environment, specific covered IoT protocol, and measurement technique. We also discuss the potential applications of learning algorithms in IoT localization, as well as future trends.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.