A5011996470- Indoor and Outdoor Localization Technologies
- Speech and Audio Processing
- Millimeter-Wave Propagation and Modeling
- Wireless Networks and Protocols
- Machine Learning and ELM
- Radio Wave Propagation Studies
- Machine Learning and Data Classification
- Smart Parking Systems Research
- Artificial Intelligence in Healthcare and Education
- Scientific Computing and Data Management
- GNSS positioning and interference
- Context-Aware Activity Recognition Systems
- Underwater Vehicles and Communication Systems
- Inertial Sensor and Navigation
- Mobile Crowdsensing and Crowdsourcing
- Robotics and Sensor-Based Localization
- RFID technology advancements
- IoT and Edge/Fog Computing
- IoT Networks and Protocols
- Interactive and Immersive Displays
- Face and Expression Recognition
- Energy Efficient Wireless Sensor Networks
- Time Series Analysis and Forecasting
- Music and Audio Processing
- Video Analysis and Summarization
Universitat Jaume I
2020-2024
Tampere University
2020-2023
Technology is continually undergoing a constituent development caused by the appearance of billions new interconnected "things" and their entrenchment in our daily lives. One underlying versatile technologies, namely wearables, able to capture rich contextual information produced such devices use it deliver legitimately personalized experience. The main aim this paper shed light on history wearable provide state-of-the-art review market. Moreover, provides an extensive diverse classification...
Every year, for ten years now, the IPIN competition has aimed at evaluating real-world indoor localisation systems by testing them in a realistic environment, with movement, using EvAAL framework. The provided unique overview of state-of-the-art systems, technologies, and methods positioning navigation purposes. Through fair comparison performance achieved each system, was able to identify most promising approaches pinpoint critical working conditions. In 2020, included 5 diverse off-site...
The technological solutions and communication capabilities offered by the Internet of Things paradigm, in terms raising availability wearable devices, ubiquitous internet connection, presence on market service-oriented solutions, have allowed a wide proposal Location Based Services (LBS). In close future, we foresee that companies service providers will developed reliable to address indoor positioning, as basis for useful location based services. These be different from each other they adopt...
Indoor positioning based on IEEE 802.11 wireless LAN (Wi-Fi) fingerprinting needs a reference data set, also known as radio map, in order to match the incoming fingerprint operational phase with most similar set and then estimate device position indoors. Scalability problems may arise when map is large, e.g., providing large geographical areas or involving crowdsourced collection. Some researchers divide into smaller independent clusters, such that search area reduced less dense groups than...
Modern IoT devices, that include smartphones and wearables, usually have limited resources. They require efficient methods to optimize the use of internal storage, provide computational efficiency, reduce energy consumption. Device resources should be used appropriately, especially when employed for time-consuming energy-intensive computations such as positioning or localization. However, reducing costs degrades methods. Therefore, goal this article is propose compare compression mechanisms...
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...
Wearable and IoT devices requiring positioning localisation services grow in number exponentially every year. This rapid growth also produces millions of data entries that need to be pre-processed prior being used any indoor system ensure the quality provide a high Quality Service (QoS) end-user. In this paper, we offer novel straightforward cleansing algorithm for WLAN fingerprinting radio maps. is based on correlation among fingerprints using Received Signal Strength (RSS) values Access...
Indoor Positioning based on Machine Learning has drawn increasing attention both in the academy and industry as meaningful information from reference data can be extracted. Many researchers are using supervised, semi-supervised, unsupervised models to reduce positioning error offer reliable solutions end-users. In this article, we propose a new architecture by combining Convolutional Neural Network (CNN), Long short-term memory (LSTM) Generative Adversarial (GAN) order increase training thus...
The evaluation of Indoor Positioning Systems (IPSs) mostly relies on local deployments in the researchers' or partners' facilities. complexity preparing comprehensive experiments, collecting data, and considering multiple scenarios usually limits area and, therefore, assessment proposed systems. requirements features controlled experiments cannot be generalized since use same sensors anchors density guaranteed. dawn datasets is pushing IPS to a similar level as machine-learning models, where...
The localization speed and accuracy in the indoor scenario can greatly impact Quality of Experience user. While many individual machine learning models achieve comparable positioning performance, their prediction mechanisms offer different complexity to system. In this work, we propose a fingerprinting method for multi-building multi-floor deployments, composed cascade three building classification, floor 2D regression. We conduct an exhaustive search optimally performing one each step while...
Indoor positioning based on machine-learning (ML) models has attracted widespread interest in the last few years, given its high performance and usability. Supervised, semisupervised, unsupervised have thus been widely used this field, not only to estimate user position, but also compress, clean, denoise fingerprinting datasets. Some scholars focused developing, improving, optimizing ML provide accurate solutions end user. This article introduces a novel method initialize input weights...
Nowadays, several indoor positioning solutions sup-port Wi-Fi and use this technology to estimate the user position. It is characterized by its low cost, availability in outdoor environments, a wide variety of devices support technology. However, technique suffers from scalability problems when radio map has large number reference fingerprints because might increase time response operational phase. In order minimize response, many have been proposed along time. The most common solution...
Machine learning models have become an essential tool in current indoor positioning solutions, given their high capa-bilities to extract meaningful information from the environment. Convolutional neural networks (CNNs) are one of most used (NNs) due that they capable complex patterns input data. Another model solutions is Extreme Learning (ELM), which provides acceptable generalization performance as well a fast speed learning. In this paper, we offer lightweight combination CNN and ELM,...
Microsoft proposed RADAR in 2000, the first indoor positioning system based on Wi-Fi fingerprinting. Since then, research community has worked not only to improve base estimator but also finding an optimal RSS data representation. The long-term objective is find a that minimises mean error. Despite relevant advances last 23 years, disruptive solution been reached yet. evaluation with non-open datasets and comparisons non-optimized baselines make analysis of current status fingerprinting for...
IoT devices and wearables may rely on Wi-Fi finger-printing to estimate the position indoors. The limited resources of these make it necessary provide adequate methods reduce operational computational load without degrading positioning error. Thus, aim this article is improve error dimensionality radio map by using an enhanced DBSCAN. Moreover, we additional analysis combining DBSCAN + PCA for further reduction. Thereby, implement a postprocessing method based correlation coefficient join...
Improving the performance of Artificial Neural Network (ANN) regression models on small or scarce datasets, such as wireless network positioning data, can be realized by simplifying task. One approach includes implementing model a classifier, followed probabilistic mapping algorithm that transforms class probabilities into multi-dimensional output. In this work, we propose so-called c2r, novel ANN-based architecture classification robust regressor, while enabling end-to-end training. The...
Fingerprint-based indoor positioning is widely used in many contexts, including pedestrian and autonomous vehicles navigation. Many approaches have traditional Machine Learning models to deal with fingerprinting, being k-NN the most common one. However, reference data (or radio map) generally limited, as collection a very demanding task, which degrades overall accuracy. In this work, we propose novel approach add random noise map will be combination an ensemble model. Instead of augmenting...
Machine learning models have become an essential tool in current indoor positioning solutions, given their high capabilities to extract meaningful information from the environment. Convolutional neural networks (CNNs) are one of most used (NNs) due that they capable complex patterns input data. Another model solutions is Extreme Learning (ELM), which provides acceptable generalization performance as well a fast speed learning. In this paper, we offer lightweight combination CNN and ELM,...
Wearable and IoT devices requiring positioning localisation services grow in number exponentially every year. This rapid growth also produces millions of data entries that need to be pre-processed prior being used any indoor system ensure the quality provide a high Quality Service (QoS) end-user. In this paper, we offer novel straightforward cleansing algorithm for WLAN fingerprinting radio maps. is based on correlation among fingerprints using Received Signal Strength (RSS) values Access...