A5039322222- Indoor and Outdoor Localization Technologies
- Millimeter-Wave Propagation and Modeling
- Mobile Crowdsensing and Crowdsourcing
- Scientific Computing and Data Management
- Speech and Audio Processing
- Wireless Networks and Protocols
- Robotics and Sensor-Based Localization
- RFID technology advancements
- Advanced MIMO Systems Optimization
- Underwater Vehicles and Communication Systems
- Smart Parking Systems Research
- E-commerce and Technology Innovations
- Power Systems and Technologies
- Artificial Intelligence in Healthcare and Education
- Ultra-Wideband Communications Technology
- Energy Efficient Wireless Sensor Networks
- Inertial Sensor and Navigation
- Bluetooth and Wireless Communication Technologies
- Online Learning and Analytics
- Big Data and Digital Economy
- Water Systems and Optimization
- Machine Learning and Data Classification
- Target Tracking and Data Fusion in Sensor Networks
- Distributed Sensor Networks and Detection Algorithms
- Machine Learning in Healthcare
Universitat Jaume I
2016-2021
WiFi fingerprinting, one of the most popular methods employed in indoor positioning, currently faces two major problems: lack robustness to short and long time signal changes difficult reproducibility new presented relevant literature. This paper presents a RSS (Received Signal Strength) database created foster ease research works that address above-mentioned problems. A trained professional took several consecutive fingerprints while standing at specific positions facing directions. The may...
In recent years, indoor localization systems have been the object of significant research activity and growing interest for their great expected social impact impressive business potential. Application areas include tracking navigation, monitoring, personalized advertising, Active Assisted Living (AAL), traceability, Internet Things (IoT) networks, Home-land Security. spite numerous advances industrial interest, no canned solutions yet defined. The diversity heterogeneity applications,...
The Indoor Positioning and Navigation (IPIN) conference holds an annual competition in which indoor localization systems from different research groups worldwide are evaluated empirically. objective of this is to establish a systematic evaluation methodology with rigorous metrics both for real-time (on-site) post-processing (off-site) situations, realistic environment unfamiliar the prototype developers. For IPIN 2018 conference, was held on September 22nd, 2018, Atlantis, large shopping...
This paper presents the analysis and discussion of off-site localization competition track, which took place during Seventh International Conference on Indoor Positioning Navigation (IPIN 2016). Five international teams proposed different strategies for smartphone-based indoor positioning using same reference data. The competitors were provided with several smartphone-collected signal datasets, some used training (known trajectories), others evaluating (unknown trajectories). permits a...
The development of indoor positioning solutions using smartphones is a growing activity with an enormous potential for everyday life and professional applications. research activities on this topic concentrate the new that are tested in specific environments under their own evaluation metrics. To explore real quality smartphone-based capabilities seamlessly adapting to different scenarios, it needed find fair frameworks. design competitions extensive pre-recorded datasets valid way generate...
IPIN 2019 Competition, sixth in a series of competitions, was held at the CNR Research Area Pisa (IT), integrated into program Conference. It included two on-site real-time Tracks and three off-site Tracks. The four presented this paper were set same environment, made buildings close together for total usable area 1000 m <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> outdoors 6000 indoors over floors, with path length exceeding 500 m....
RSS-based indoor positioning is a consolidated research field for which several techniques have been proposed. Among them, Bluetooth Low Energy (BLE) beacons are popular option practical applications. This paper presents new BLE RSS database that was created to aid in the development of methods and encourage their reproducibility comparability. The measurements were collected two university zones: an area among bookshelves library office space. Each zone had its own batch deployed iBKS 105...
Wi-Fi fingerprinting is a well-known technique used for indoor positioning. It relies on pattern recognition method that compares the captured operational fingerprint with set of previously collected reference samples (radio map) using similarity function. The matching algorithms suffer from scalability problem in large deployments huge density fingerprints, where number radio map prohibitively large. This paper presents comprehensive comparative study existing methods to reduce complexity...
Localization is one of the main pillars for indoor services. However, it still very difficult mobile sensing community to compare state-of-the-art positioning systems due scarcity publicly available databases. To make fair and meaningful comparisons between systems, they must be evaluated in same situation, or sets situations. In this paper, two databases are introduced studying performance magnetic field Wi-Fi fingerprinting based environment (i.e., area). The “magnetic” database contains...
Data enrichment through interpolation or regression is a common approach to deal with sample collection for Indoor Localization WiFi fingerprinting. This paper provides guidelines on where collect samples and proposes new model received signal strength regression. The creates vectors that describe the presence of obstacles between an access point collected samples. vectors, distance positions samples, collected, are used train Support Vector Regression. experiments included some relevant...
Wi-Fi fingerprinting is a popular technique for Indoor Positioning Systems (IPSs) thanks to its low complexity and the ubiquity of WLAN infrastructures. However, this may present scalability issues when reference dataset (radio map) very large. To reduce computational costs, k-Means Clustering has been successfully applied in past. it general-purpose algorithm unsupervised classification. This paper introduces three variants that apply heuristics based on radio propagation knowledge coarse...
Selecting the appropriate parameters for an indoor positioning system may be a difficult task due to large number of parameter combinations. It is more complex in realistic multi-building multi-floor environments, where severe wrong building and floor errors occur but they are not highlighted main evaluation metric. Moreover, selected configuration, that seem validation, have expected behaviour real deployment. In order address these issues, ensemble systems introduced. A base estimator with...
Wi-Fi Fingerprinting is widely adopted for smartphone-based indoor positioning systems due to the availability of already deployed infrastructure communications. The UJIIndoorLoc database contains data in a large environment covering three multi-tier buildings collected with multiple devices. Since evaluation set private, developers and researchers can still be evaluated under same conditions than participants 2015 EvAAL-ETRI competition. This paper shows results experiences such kind...
The accuracy of indoor positioning systems is commonly computed as a metric based on the Euclidean distance from estimated locations to actual locations. This paper suggests that error distances should be lengths paths person may follow when going wrongly positions real positions. proposes method calculates floor plan and obstacles information using visibility graphs offsetting techniques, which are used in robotics CAD/CAM for navigation manufacturing, respectively. Demonstration proposed...
Indoor positioning systems (IPSs) suffer from a lack of standard evaluation procedures enabling credible comparisons: this is one the main challenges hindering their widespread market adoption. Traditionally, accuracy based on errors defined as Euclidean distance between true positions and estimated positions. While simple, it ignores obstacles floor transitions. In article, we describe that measure error length pedestrian path connects position to position. The apply pathfinding maps using...
This paper presents the development of a parking occupancy simulator to support smart system. The uses an agent-based approach model drivers who follow activity plans and may or not use We illustrate how process developing our helped in design implementation system components. also shows was used study possible usage university campus, foreseeing (1) for system’s overall suitability, (2) reservation guarantee violation problems, (3) value using total traveled distance as metric evaluation....
Wi-Fi fingerprinting is a popular technique for smartphone-based indoor positioning. However, well-known RF propagation issues create signal fluctuations that translate into large positioning errors. Large errors limit the usage of in industrial environments, where reliability position estimates key requirement. One successful approach to deal with average signals collected simultaneously through independent interfaces. Another provided by models built on radio maps. This paper explores...
Fingerprinting is widely used for indoor positioning, where pattern matching techniques are usually applied to signals from APs or Beacons. However, the real-time monitoring of emitters not an easy task in most cases. When alteration detected properly fixed, it might have a severe impact accuracy positioning algorithm. Simple but common alterations energy failure, emitter replacement, wrong placement after maintenance and AP displacement. This paper explores how be automatically by computing...