A Participatory Service Platform for Indoor Location-Based Services

Shin, Hyun-Jun; Chon, Yohan; Kim, Yungeun; Cha, Hojung

doi:10.1109/mprv.2015.1

Cited by 30 publications

(21 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If we compare the values and reliability intervals obtained in this second test for the metric "relative accuracy" we can see a significant improvement as compared to when all locations were used. The increases/decreases in percentage points in those cases where we did not execute our algorithm to delete unstable WAPs are as follows (we take all the WAPs from the initial set, as indicated in the first row of combined Tables 2-4 and combined Tables 5-7 When we compare the results published for the WASP and Redpin algorithms with noise filtering and 5 access points [11] with the ones we get when we run our algorithm to delete unstable WAPs (and also take 5 WAPs) we can see that we get significant improvements for the following [12]. This is an improvement of +4.50 percentage points when using the Random Forest algorithm.…”

Section: Results From the Linear Configurationmentioning

confidence: 99%

“…This paper focuses on fingerprinting smartphone-based algorithms which are employed to locate users at room level (the exact location of the user inside a room is not that relevant but knowing the exact room the user is in with the highest accuracy is crucial). Using room level granularity will allow us to overcome one of the crucial aspects of indoor location systems when the areas to cover are big: scalability [12]. Training indoor locations systems with a complete grid of training points is time consuming and does not scale on computational resources required for estimating user locations.…”

Section: Mobile Information Systemsmentioning

confidence: 99%

“…Training indoor locations systems with a complete grid of training points is time consuming and does not scale on computational resources required for estimating user locations. Some research proposals such as [12] overcome this limitation by using crowdsourcing-based place learning. However, this approach requires the manual involvement of volunteer collaborating users to improve the accuracy of the system and collateral aspects such as data quality should be taken into account.…”

Section: Mobile Information Systemsmentioning

confidence: 99%

See 2 more Smart Citations

Improving Accuracy and Simplifying Training in Fingerprinting-Based Indoor Location Algorithms at Room Level

Muñoz-Organero

Brito-Pacheco²

2016

Mobile Information Systems

View full text Add to dashboard Cite

Fingerprinting-based algorithms are popular in indoor location systems based on mobile devices. Comparing the RSSI (Received Signal Strength Indicator) from different radio wave transmitters, such as Wi-Fi access points, with prerecorded fingerprints from located points (using different artificial intelligence algorithms), fingerprinting-based systems can locate unknown points with a few meters resolution. However, training the system with already located fingerprints tends to be an expensive task both in time and in resources, especially if large areas are to be considered. Moreover, the decision algorithms tend to be of high memory and CPU consuming in such cases and so does the required time for obtaining the estimated location for a new fingerprint. In this paper, we study, propose, and validate a way to select the locations for the training fingerprints which reduces the amount of required points while improving the accuracy of the algorithms when locating points at room level resolution. We present a comparison of different artificial intelligence decision algorithms and select those with better results. We do a comparison with other systems in the literature and draw conclusions about the improvements obtained in our proposal. Moreover, some techniques such as filtering nonstable access points for improving accuracy are introduced, studied, and validated.

show abstract

Section: Results From the Linear Configurationmentioning

confidence: 99%

Section: Mobile Information Systemsmentioning

confidence: 99%

Section: Mobile Information Systemsmentioning

confidence: 99%

See 1 more Smart Citation

Improving Accuracy and Simplifying Training in Fingerprinting-Based Indoor Location Algorithms at Room Level

Muñoz-Organero

Brito-Pacheco²

2016

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

“…For instance, [16] proposed an store recommendation systems by mining the context of decision-making behaviour using eye-tracking data, [17] proposed a POI discovery approach by matching the user profile and the semantic-enhanced POIs, [18] proposed a recommended system to help users in shopping for technical products by considering user preference and technical product attributes, and [19] proposed an automatic mobile assistant for museum visiting based on WiFi-based indoor positioning. Additionally, Shin et al [20] constructed an indoor database platform for indoor location-based services.…”

Section: Indoor Poi Recommendationmentioning

confidence: 99%

Location-Aware POI Recommendation for Indoor Space by Exploiting WiFi Logs

Zheng

Chen

et al. 2017

Mobile Information Systems

View full text Add to dashboard Cite

Indoor shopping trajectories provide us with a new approach to understanding user's behaviour pattern in urban shopping mall, which can be derived from user-generated WiFi logs using indoor localization technology. In this paper, we propose a locationaware Point-of-Interest (POI) recommendation service in urban shopping mall that offers a user a set of indoor POIs by considering both personal interest and location preference. The POI recommendation service cannot only improve user's shopping experience but also help the store owner better understand user's shopping preference and intent. Specifically, the proposed method consists of two phases: offline modelling and online recommendation. The offline modelling phase is designed to learn user preference by mining his/her historical shopping trajectories. The online recommendation phase automatically produces top-recommended POIs based on the learnt preference. To demonstrate the utility of our proposed approach, we have performed a comprehensive experiment evaluation on a real-world dataset collected by 468 users over 33 days. The experimental results show that the proposed recommendation service achieves much better recommendation performance than several existing benchmark methods.

show abstract

“…Rai et al [13] proposed an automatic calibration method utilizing an acceleration sensor, a compass sensor and a gyro sensor, which are installed in smartphones and floor maps. In addition to Rai et al [13], not a few researchers such as Shin et al [17] and Kawajiri et al [9] have developed methods that utilize crowds' cooperation. However, except for Kawajiri et al [9] their methods don't consider which label to get new data and Kawajiri et al is not enough.…”

Section: Related Work Indoor Localization Calibrationmentioning

confidence: 99%

Efficient calibration for rssi-based indoor localization by bayesian experimental design on multi-task classification

Shimosaka

Saisho

2016

Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing

View full text Add to dashboard Cite

RSSI-based indoor localization is getting much attention. Thanks to a number of researchers, the localization accuracy has already reached a sufficient level. However, it is still not easy-to-use technology because of its heavy installation cost. When an indoor localization system is installed, it needs to collect RSSI data for training classifiers. Existing techniques need to collect enough data at each location. This is why the installation cost is very heavy. We propose a technique to gather data efficiently by using machine learning techniques. Our proposed algorithm is based on multi-task learning and Bayesian optimization. This algorithm can remove the need to collect data of all location labels and select location labels to acquire new data efficiently. We verify this algorithm by using a Wi-Fi RSSI dataset collected in a building. The empirical results suggest that the algorithm is superior to an existing algorithm applying single-task learning and Active Class Selection.

show abstract

A Participatory Service Platform for Indoor Location-Based Services

Cited by 30 publications

References 10 publications

Improving Accuracy and Simplifying Training in Fingerprinting-Based Indoor Location Algorithms at Room Level

Improving Accuracy and Simplifying Training in Fingerprinting-Based Indoor Location Algorithms at Room Level

Location-Aware POI Recommendation for Indoor Space by Exploiting WiFi Logs

Efficient calibration for rssi-based indoor localization by bayesian experimental design on multi-task classification

Contact Info

Product

Resources

About