Improving the Performance of RSSI Based Indoor Localization Techniques Using Neural Networks
01 Mar 2018-
TL;DR: In this paper, error reduction in a RSSI based localization algorithm using neural networks is discussed about and results show significant improvement in localization performance with the error correction mechanism.
Abstract: Node localization is an essential part of Wireless sensor network and has a good scope for research and development. Many revolutionary ideas like driverless cars, augmented reality and instant emergency response systems are dependent on precise localization. Localization in an indoor environment is not generic and simple as in outdoors due to the increased randomness, attenuation, heterogeneity and interference. These factors reduce the precision of popular localization algorithms in an indoor environment. This paper discusses about error reduction in a RSSI based localization algorithm using neural networks. Parallel computational capabilities and non-linearity of neural networks would come in handy with the constraints in indoor localization. In-depth discussion has been made in this paper about the procedure followed for localization, sources of error and error controlling mechanisms applied. Simulation results are also discussed towards the end, which show significant improvement in localization performance with the error correction mechanism.
Citations
More filters
TL;DR: In this paper, an adaptive power control algorithm for a transmitter, as a reference emitter, operating in power-saving mode is presented, which adjusts the localization system accuracy at the assumed level of energy radiated by radio emitters based on the RSSI signal received power estimation.
Abstract: In localization systems based on the emission of reference radio signals, an important issue related to the reliability of sensor operation is the problem of operating time and power of the emitted reference radio signal. There are many localization methods that have proven useful in practice and that use a reference radio signal for this purpose. In the issue of determining the location of radio emitters, various radio signal propagation models are used to determine the effective range and distance of the sensor-receiver from the radio emitter. This paper presents an adaptive power control algorithm for a transmitter, as a reference emitter, operating in power-saving mode. An important advantage of the presented solution is the adjustment of the localization system accuracy at the assumed level of energy radiated by radio emitters based on the RSSI signal received power estimation.
7 citations
TL;DR: A comprehensive survey of the applicability of machine learning and deep learning to achieve seamless navigation can be found in this paper , where the authors systematically discuss the application perspectives, research challenges and the framework of ML (mostly) and DL (a few) based positioning approaches.
3 citations
09 Dec 2022
TL;DR: In this article , a weighted Gaussian hybrid filter algorithm is applied to received RSSI to obtain reference value and construct a RSSI database and then construct an environmental adaptive neural network localization model to achieve highprecision localization of target nodes in complex indoor environments.
Abstract: Low-cost ranging techniques, such as received signal strength indicator(RSSI), often lead to inaccurate location estimation in wireless sensor networks. To reduce the errors caused by ranging techniques, this paper uses a non-ranging method based on RSSI. We arrange several access points(APs) with known coordinates in the indoor environment, and then select a large number of reference points(RPs) to collect RSSI. A weighted Gaussian hybrid filter algorithm is applied to received RSSI to obtain reference value and construct a RSSI database. We use the DBSCAN clustering algorithm to pre-process the database for classification, and then construct an environmental adaptive neural network localization model to achieve high-precision localization of target nodes in complex indoor environments.
16 Feb 2022
TL;DR: In this article , an indoor localization system is developed through Zigbee wireless modules by acquiring RSSI values from fixed nodes and processing them through 3D trilateration algorithm to locate multiple unknown nodes, and subsequently, determine distances between them.
Abstract: An indoor localization system is developed through Zigbee wireless modules by acquiring RSSI values from fixed nodes and processing them through 3D trilateration algorithm to locate multiple unknown nodes, and subsequently, determine distances between them. Kalman filtering is applied for refining RSSI values for localization. The experimental setup focuses on optimization of antenna orientation and reader altitude as well as calibration of signal propagation loss constants for the log-distance path loss model to best characterize the indoor test environment. Optimal results were obtained when both reader's and tag's antennas were positioned perpendicular to the ground and reader is placed at higher altitudes. In testing the accuracy of the indoor localization system, three reader altitude setups were done, specifically 1.5m, 2m, and 2.5m, to determine how it can affect the system. The results of the study show a significant improvement in localization accuracy when the readers were placed at 2.5m. Overall, the localization error was lessened to an averaged value of 0.16m from 0.6389m and 0.35m when the readers were placed at the highest optimal altitude. The accuracy in determining distances between tags was found to significantly increase as distance between the tags increased. From a range of error of 3.23% to 32.02% for 0.5m distance, it decreased to 0.82% to 9.29% for distances 1.5m and above. The findings of this study exhibit positive outputs in using an RSSI-based Zigbee indoor localization system for locating multiple stationary tags and determining distances of tags that are farther apart.
09 Dec 2022
TL;DR: In this article , a weighted Gaussian hybrid filter algorithm is applied to received RSSI to obtain reference value and construct a RSSI database and then construct an environmental adaptive neural network localization model to achieve highprecision localization of target nodes in complex indoor environments.
Abstract: Low-cost ranging techniques, such as received signal strength indicator(RSSI), often lead to inaccurate location estimation in wireless sensor networks. To reduce the errors caused by ranging techniques, this paper uses a non-ranging method based on RSSI. We arrange several access points(APs) with known coordinates in the indoor environment, and then select a large number of reference points(RPs) to collect RSSI. A weighted Gaussian hybrid filter algorithm is applied to received RSSI to obtain reference value and construct a RSSI database. We use the DBSCAN clustering algorithm to pre-process the database for classification, and then construct an environmental adaptive neural network localization model to achieve high-precision localization of target nodes in complex indoor environments.
References
More filters
TL;DR: A survey of state-of-the-art routing techniques in WSNs is presented and the design trade-offs between energy and communication overhead savings in every routing paradigm are studied.
Abstract: Wireless sensor networks consist of small nodes with sensing, computation, and wireless communications capabilities. Many routing, power management, and data dissemination protocols have been specifically designed for WSNs where energy awareness is an essential design issue. Routing protocols in WSNs might differ depending on the application and network architecture. In this article we present a survey of state-of-the-art routing techniques in WSNs. We first outline the design challenges for routing protocols in WSNs followed by a comprehensive survey of routing techniques. Overall, the routing techniques are classified into three categories based on the underlying network structure: flit, hierarchical, and location-based routing. Furthermore, these protocols can be classified into multipath-based, query-based, negotiation-based, QoS-based, and coherent-based depending on the protocol operation. We study the design trade-offs between energy and communication overhead savings in every routing paradigm. We also highlight the advantages and performance issues of each routing technique. The article concludes with possible future research areas.
4,701 citations
"Improving the Performance of RSSI B..." refers background in this paper
...Recent technological advances have made manufacture of small, low cost sensors nodes technologically and economically feasible [1]....
[...]
23 Apr 2013
TL;DR: An RSSI model that estimates the distance between sensor nodes in WSNs is presented and shows that there is less error in distance estimation in an outdoor environment compared to indoor environment.
Abstract: Research has revealed that the correlation between distance and RSSI (Received Signal Strength Indication) values is the key of ranging and localization technologies in wireless sensor networks (WSNs). In this paper, an RSSI model that estimates the distance between sensor nodes in WSNs is presented. The performance of this model is evaluated and analyzed in a real system deployment in an indoor and outdoor environment by performing an empirical measurement using Crossbow IRIS wireless sensor motes. Our result shows that there is less error in distance estimation in an outdoor environment compared to indoor environment. The results of these evaluations would contribute towards obtaining accurate locations of wireless sensor nodes.
120 citations
"Improving the Performance of RSSI B..." refers background in this paper
...RSSI based localization is more popular because it is simple and does not require any sophisticated hardware [5]....
[...]
01 Aug 2017
TL;DR: A multiplicative distance-correction factor (MDCF) is proposed to counteract the inaccuracy of estimated distance to improve localisation accuracy in indoor wireless sensor localisation.
Abstract: As a low-cost distance measurement method, received signal strength (RSS) is often used for indoor wireless sensor localisation. However, RSS values can be easily influenced by multi-path fading, noise and other environmental parameters. This decreases the accuracy and stability of estimated distance. To improve localisation accuracy, this study proposes a multiplicative distance-correction factor (MDCF) to counteract the inaccuracy of estimated distance. In the same indoor environment, the product of this CF and estimated distance is regarded as a good approximation of real distance between unknown node and an anchor node. Then, two location estimated methods based on MDCF (MDCF-grid and MDCF-particle swarm optimisation) are proposed. The experimental results confirm that the proposed location estimation methods can significantly improve localisation accuracy without extra hardware in practical indoor scenarios.
26 citations
"Improving the Performance of RSSI B..." refers methods in this paper
...To reduce the error, feedback error control using multiplicative distance-correction factor, Time Window Statistics, UWB Ranging and other techniques are used [7-9]....
[...]
25 Jun 2006
TL;DR: Simulated results showed that efficiency is improved for network structures whose profiles are cuboid or cone shaped, and whose node distributions are layered or random, while a large scale sensor network is analyzed to verify the propagating trend of localization.
Abstract: Localization of sensor nodes is important for many sensor network applications such as distance-based routing and target tracking. This paper presents a localization approach for sensor networks in constrained 3-D space. By assuming that all the original beacon nodes are on the bottom plane, the localization procedure for the entire network is primarily from the bottom to the top and at the same time the localization process is carried out in all directions from the regions where the original beacon nodes are clustered. Simulated results showed that efficiency is improved for network structures whose profiles are cuboid or cone shaped, and whose node distributions are layered or random. The effects of the number of original beacon nodes as well as the node density on the localizing errors and/or the localizing successful rate are explored. Finally, a large scale sensor network is analyzed to verify the propagating trend of localization.
23 citations
"Improving the Performance of RSSI B..." refers background in this paper
...by multipath error, diffraction, attenuation, the direction of antennas and other factors more severely in an indoor environment [6]....
[...]
24 Apr 2015
TL;DR: A method for using the UWB ranging & communication modules (RCM) and designing ARM9 controllers to set up Self-organized WSN indoor localization system that can apply in large indoor range and the positioning error is less than 0.2m.
Abstract: This paper presents a method for using the UWB ranging aamp, communication modules (RCM) and designing ARM9 controllers to set up Self-organized WSN indoor localization system It is the mobile target that measure the distance at the same time, so it needn't to synchronize the clock of the base station and can obtain real-time position information The most advantage is that the mobile tag can detect the base stations nearby automatically and along with these base stations to form a self-organized wireless sensor network The localization system can apply in large indoor range and the positioning error is less than 02m
12 citations
"Improving the Performance of RSSI B..." refers methods in this paper
...To reduce the error, feedback error control using multiplicative distance-correction factor, Time Window Statistics, UWB Ranging and other techniques are used [7-9]....
[...]