2020 |
Luckner, Marcin; ł, Rafa Automatic detection of changes in signal strength characteristics in a wi-fi network for an indoor localisation system Journal Article Sensors (Switzerland), 20 (7), pp. 1–13, 2020, ISSN: 14248220. Abstract | Links | BibTeX | Tags: Fingerprinting, Indoor localisation system, Quality of Service, System deployment and maintenance, Wi-Fi network @article{Luckner2020b, title = {Automatic detection of changes in signal strength characteristics in a wi-fi network for an indoor localisation system}, author = {Marcin Luckner and Rafa{ł} Górak}, doi = {10.3390/s20071828}, issn = {14248220}, year = {2020}, date = {2020-01-01}, journal = {Sensors (Switzerland)}, volume = {20}, number = {7}, pages = {1--13}, abstract = {This paper faces the issue of changing the received signal strength (RSS) from an observed access point (AP). Such a change can reduce the Quality of Service (QoS) of a Wi-Fi-based Indoor Localisation System. We have proposed a dynamic system based on an estimator of RSS using the readings from other APs. Using an optimal threshold, the algorithm recognises an AP that has changed its characteristics. Next, the system rebuilds the localisation model excluding the changed AP to keep QoS. For the tests, we simulated a change in the analysed Wi-Fi network by replacing the measured RSS by an RSS obtained from the same AP model that lies in another place inside the same multi-floor building. The algorithm was evaluated in simulations of an isolated single-floor building, a single-floor building and a multi-floor building. The mean increase of the localisation error obtained by the system varies from 0.25 to 0.61 m after the RSS changes, whereas the error increase without using the system is between 1.21 and 1.98 m. The system can be applied to any service based on a Wi-Fi network for various kinds of changes like a reconfiguration of the network, a local malfunction or ageing of the infrastructure.}, keywords = {Fingerprinting, Indoor localisation system, Quality of Service, System deployment and maintenance, Wi-Fi network}, pubstate = {published}, tppubtype = {article} } This paper faces the issue of changing the received signal strength (RSS) from an observed access point (AP). Such a change can reduce the Quality of Service (QoS) of a Wi-Fi-based Indoor Localisation System. We have proposed a dynamic system based on an estimator of RSS using the readings from other APs. Using an optimal threshold, the algorithm recognises an AP that has changed its characteristics. Next, the system rebuilds the localisation model excluding the changed AP to keep QoS. For the tests, we simulated a change in the analysed Wi-Fi network by replacing the measured RSS by an RSS obtained from the same AP model that lies in another place inside the same multi-floor building. The algorithm was evaluated in simulations of an isolated single-floor building, a single-floor building and a multi-floor building. The mean increase of the localisation error obtained by the system varies from 0.25 to 0.61 m after the RSS changes, whereas the error increase without using the system is between 1.21 and 1.98 m. The system can be applied to any service based on a Wi-Fi network for various kinds of changes like a reconfiguration of the network, a local malfunction or ageing of the infrastructure. |
Luckner, Marcin; ł, Rafa Automatic detection of changes in signal strength characteristics in a wi-fi network for an indoor localisation system Journal Article Sensors (Switzerland), 20 (7), pp. 1–13, 2020, ISSN: 14248220. Abstract | Links | BibTeX | Tags: Fingerprinting, Indoor localisation system, Quality of Service, System deployment and maintenance, Wi-Fi network @article{Luckner2020c, title = {Automatic detection of changes in signal strength characteristics in a wi-fi network for an indoor localisation system}, author = {Marcin Luckner and Rafa{ł} Górak}, doi = {10.3390/s20071828}, issn = {14248220}, year = {2020}, date = {2020-01-01}, journal = {Sensors (Switzerland)}, volume = {20}, number = {7}, pages = {1--13}, abstract = {This paper faces the issue of changing the received signal strength (RSS) from an observed access point (AP). Such a change can reduce the Quality of Service (QoS) of a Wi-Fi-based Indoor Localisation System. We have proposed a dynamic system based on an estimator of RSS using the readings from other APs. Using an optimal threshold, the algorithm recognises an AP that has changed its characteristics. Next, the system rebuilds the localisation model excluding the changed AP to keep QoS. For the tests, we simulated a change in the analysed Wi-Fi network by replacing the measured RSS by an RSS obtained from the same AP model that lies in another place inside the same multi-floor building. The algorithm was evaluated in simulations of an isolated single-floor building, a single-floor building and a multi-floor building. The mean increase of the localisation error obtained by the system varies from 0.25 to 0.61 m after the RSS changes, whereas the error increase without using the system is between 1.21 and 1.98 m. The system can be applied to any service based on a Wi-Fi network for various kinds of changes like a reconfiguration of the network, a local malfunction or ageing of the infrastructure.}, keywords = {Fingerprinting, Indoor localisation system, Quality of Service, System deployment and maintenance, Wi-Fi network}, pubstate = {published}, tppubtype = {article} } This paper faces the issue of changing the received signal strength (RSS) from an observed access point (AP). Such a change can reduce the Quality of Service (QoS) of a Wi-Fi-based Indoor Localisation System. We have proposed a dynamic system based on an estimator of RSS using the readings from other APs. Using an optimal threshold, the algorithm recognises an AP that has changed its characteristics. Next, the system rebuilds the localisation model excluding the changed AP to keep QoS. For the tests, we simulated a change in the analysed Wi-Fi network by replacing the measured RSS by an RSS obtained from the same AP model that lies in another place inside the same multi-floor building. The algorithm was evaluated in simulations of an isolated single-floor building, a single-floor building and a multi-floor building. The mean increase of the localisation error obtained by the system varies from 0.25 to 0.61 m after the RSS changes, whereas the error increase without using the system is between 1.21 and 1.98 m. The system can be applied to any service based on a Wi-Fi network for various kinds of changes like a reconfiguration of the network, a local malfunction or ageing of the infrastructure. |
2018 |
ł, Rafa; Luckner, Marcin Automatic detection of missing access points in indoor positioning system Journal Article Sensors (Switzerland), 18 (11), 2018, ISSN: 14248220. Abstract | Links | BibTeX | Tags: Fingerprinting, Indoor localisation system, System deployment and maintenance @article{Gorak2018, title = {Automatic detection of missing access points in indoor positioning system}, author = {Rafa{ł} Górak and Marcin Luckner}, url = {https://doi.org/10.3390/s18113595}, doi = {10.3390/s18113595}, issn = {14248220}, year = {2018}, date = {2018-10-01}, journal = {Sensors (Switzerland)}, volume = {18}, number = {11}, abstract = {textlessptextgreaterThe paper presents a Wi-Fi-based indoor localisation system. It consists of two main parts, the localisation model and an Access Points (APs) detection module. The system uses a received signal strength (RSS) gathered by multiple mobile terminals to detect which AP should be included in the localisation model and whether the model needs to be updated (rebuilt). The rebuilding of the localisation model prevents the localisation system from a significant loss of accuracy. The proposed automatic detection of missing APs has a universal character and it can be applied to any Wi-Fi localisation model which was created using the fingerprinting method. The paper considers the localisation model based on the Random Forest algorithm. The system was tested on data collected inside a multi-floor academic building. The proposed implementation reduced the mean horizontal error by 5.5 m and the classification error for the floor's prediction by 0.26 in case of a serious malfunction of a Wi-Fi infrastructure. Several simulations were performed, taking into account different occupancy scenarios as well as different numbers of missing APs. The simulations proved that the system correctly detects missing and present APs in the Wi-Fi infrastructure.textless/ptextgreater}, keywords = {Fingerprinting, Indoor localisation system, System deployment and maintenance}, pubstate = {published}, tppubtype = {article} } textlessptextgreaterThe paper presents a Wi-Fi-based indoor localisation system. It consists of two main parts, the localisation model and an Access Points (APs) detection module. The system uses a received signal strength (RSS) gathered by multiple mobile terminals to detect which AP should be included in the localisation model and whether the model needs to be updated (rebuilt). The rebuilding of the localisation model prevents the localisation system from a significant loss of accuracy. The proposed automatic detection of missing APs has a universal character and it can be applied to any Wi-Fi localisation model which was created using the fingerprinting method. The paper considers the localisation model based on the Random Forest algorithm. The system was tested on data collected inside a multi-floor academic building. The proposed implementation reduced the mean horizontal error by 5.5 m and the classification error for the floor's prediction by 0.26 in case of a serious malfunction of a Wi-Fi infrastructure. Several simulations were performed, taking into account different occupancy scenarios as well as different numbers of missing APs. The simulations proved that the system correctly detects missing and present APs in the Wi-Fi infrastructure.textless/ptextgreater |
ł, Rafa; Luckner, Marcin Automatic detection of missing access points in indoor positioning system Journal Article Sensors (Switzerland), 18 (11), 2018, ISSN: 14248220. Abstract | Links | BibTeX | Tags: Fingerprinting, Indoor localisation system, System deployment and maintenance @article{Gorak2018b, title = {Automatic detection of missing access points in indoor positioning system}, author = {Rafa{ł} Górak and Marcin Luckner}, url = {https://doi.org/10.3390/s18113595}, doi = {10.3390/s18113595}, issn = {14248220}, year = {2018}, date = {2018-10-01}, journal = {Sensors (Switzerland)}, volume = {18}, number = {11}, abstract = { The paper presents a Wi-Fi-based indoor localisation system. It consists of two main parts, the localisation model and an Access Points (APs) detection module. The system uses a received signal strength (RSS) gathered by multiple mobile terminals to detect which AP should be included in the localisation model and whether the model needs to be updated (rebuilt). The rebuilding of the localisation model prevents the localisation system from a significant loss of accuracy. The proposed automatic detection of missing APs has a universal character and it can be applied to any Wi-Fi localisation model which was created using the fingerprinting method. The paper considers the localisation model based on the Random Forest algorithm. The system was tested on data collected inside a multi-floor academic building. The proposed implementation reduced the mean horizontal error by 5.5 m and the classification error for the floor's prediction by 0.26 in case of a serious malfunction of a Wi-Fi infrastructure. Several simulations were performed, taking into account different occupancy scenarios as well as different numbers of missing APs. The simulations proved that the system correctly detects missing and present APs in the Wi-Fi infrastructure. },keywords = {Fingerprinting, Indoor localisation system, System deployment and maintenance}, pubstate = {published}, tppubtype = {article} } <p>The paper presents a Wi-Fi-based indoor localisation system. It consists of two main parts, the localisation model and an Access Points (APs) detection module. The system uses a received signal strength (RSS) gathered by multiple mobile terminals to detect which AP should be included in the localisation model and whether the model needs to be updated (rebuilt). The rebuilding of the localisation model prevents the localisation system from a significant loss of accuracy. The proposed automatic detection of missing APs has a universal character and it can be applied to any Wi-Fi localisation model which was created using the fingerprinting method. The paper considers the localisation model based on the Random Forest algorithm. The system was tested on data collected inside a multi-floor academic building. The proposed implementation reduced the mean horizontal error by 5.5 m and the classification error for the floor's prediction by 0.26 in case of a serious malfunction of a Wi-Fi infrastructure. Several simulations were performed, taking into account different occupancy scenarios as well as different numbers of missing APs. The simulations proved that the system correctly detects missing and present APs in the Wi-Fi infrastructure.</p> |
Publications
2020 |
Automatic detection of changes in signal strength characteristics in a wi-fi network for an indoor localisation system Journal Article Sensors (Switzerland), 20 (7), pp. 1–13, 2020, ISSN: 14248220. |
Automatic detection of changes in signal strength characteristics in a wi-fi network for an indoor localisation system Journal Article Sensors (Switzerland), 20 (7), pp. 1–13, 2020, ISSN: 14248220. |
2018 |
Automatic detection of missing access points in indoor positioning system Journal Article Sensors (Switzerland), 18 (11), 2018, ISSN: 14248220. |
Automatic detection of missing access points in indoor positioning system Journal Article Sensors (Switzerland), 18 (11), 2018, ISSN: 14248220. |