Accurate real time localization tracking in a clinical environment using Bluetooth Low Energy and deep learning

Wearable Systems for Unveiling Collective Intelligence in Clinical Settings

Nowadays, there is an ever-growing interest in assessing the collective intelligence (CI) of a team in a wide range of scenarios, thanks to its potential in enhancing teamwork and group performance. Recently, special attention has been devoted on the clinical setting, where breakdowns in teamwork, leadership, and communication can lead to adverse events, compromising patient safety. So far, researchers have mostly relied on surveys to study human behavior and group dynamics; however, this method is ineffective. In contrast, a promising solution to monitor behavioral and individual features that are reflective of CI is represented by wearable technologies. To date, the field of CI assessment still appears unstructured; therefore, the aim of this narrative review is to provide a detailed overview of the main group and individual parameters that can be monitored to evaluate CI in clinical settings, together with the wearables either already used to assess them or that have the potential to be applied in this scenario. The working principles, advantages, and disadvantages of each device are introduced in order to try to bring order in this field and provide a guide for future CI investigations in medical contexts.

MHSA-EC: An Indoor Localization Algorithm Fusing the Multi-Head Self-Attention Mechanism and Effective CSI

Channel state information (CSI) provides a fine-grained description of the signal propagation process, which has attracted extensive attention in the field of indoor positioning. The CSI signals collected by different fingerprint points have a high degree of discrimination due to the influence of multi-path effects. This multi-path effect is reflected in the correlation between subcarriers and antennas. However, in mining such correlations, previous methods are difficult to aggregate non-adjacent features, resulting in insufficient multi-path information extraction. In addition, the existence of the multi-path effect makes the relationship between the original CSI signal and the distance not obvious, and it is easy to cause mismatching of long-distance points. Therefore, this paper proposes an indoor localization algorithm that combines the multi-head self-attention mechanism and effective CSI (MHSA-EC). This algorithm is used to solve the problem where it is difficult for traditional algorithms to effectively aggregate long-distance CSI features and mismatches of long-distance points. This paper verifies the stability and accuracy of MHSA-EC positioning through a large number of experiments. The average positioning error of MHSA-EC is 0.71 m in the comprehensive office and 0.64 m in the laboratory.

Automated Calibration of RSS Fingerprinting Based Systems Using a Mobile Robot and Machine Learning

This paper describes an automated method for the calibration of RSS-fingerprinting-based positioning systems. The method assumes using a robotic platform to gather fingerprints in the system environment and using them for training machine learning models. The obtained models are used for positioning purposes during the system operation. The presented calibration method covers all steps of the system calibration, from mapping the system environment using a GraphSLAM based algorithm to training models for radio map calibration. The study analyses four different models: fitting a log-distance path loss model, Gaussian Process Regression, Artificial Neural Network and Random Forest Regression. The proposed method was tested in a BLE-based indoor localisation system set up in a fully furnished apartment. The results have shown that the tested models allow for localisation with accuracy comparable to those reported in the literature. In the case of the Neural Network regression, the median error of robot positioning was 0.87 m. The median of trajectory error in a walking person localisation scenario was 0.4 m.

C-GCN: A Flexible CSI Phase Feature Extraction Network for Error Suppression in Indoor Positioning

Channel state information (CSI) provides a fine-grained description of the signal propagation process, which has attracted extensive attention in the field of indoor positioning. However, considering the influence of environment and hardware, the phase of CSI is distorted in most cases. It is difficult to extract effective location features in multiple scenes only through the determined artificial experience model. Graph neural network has performed well in many fields in recent years, but there is still a lot of room to explore in the field of indoor positioning. In this paper, a phase feature extraction network based on multi-dimensional correlation is proposed, named Cooperation-Graph Convolution Network (C-GCN). The purpose of C-GCN is to extract new features of multiple correlation and to mine the relationship between antenna and subcarrier as much as possible. C-GCN is composed of convolution layer and graph convolution layer. In the graph convolution layer, C-GCN regards each subcarrier of each antenna as a node in the graph network, constructs the connection by the correlation between the antenna and the subcarrier, and aggregates the node vectors by graph convolution. In the convolution layer, there is a natural corresponding structure between data packets, C-GCN extracts the fluctuation with convolution in Euclidean space. C-GCN combines these two layers, and applies end-to-end supervised training to obtain effective features. Extensive experiments are conducted in typical indoor environments to verify the superior performance of C-GCN in restraining error tailing. The average positioning error of C-GCN is 1.29 m in comprehensive office and 1.71 m in garage. Combined with the amplitude feature, the average positioning error is 0.99 m in comprehensive office and 1.14 m in garage.

Beacon-Based Remote Measurement of Social Behavior in ASD Clinical Trials: A Technical Feasibility Assessment

In this work, we propose a Bluetooth low energy (BLE) beacon-based algorithm to enable remote measurement of the social behavior of the participants of an observational Autism Spectrum Disorder (ASD) clinical trial (NCT03611075). We have developed a mobile application for a smartphone and a smartwatch to collect beacon signals from BLE beacon sensors as well as to store information about the participants’ household rooms. Our goal is to collect beacon information about the time the participants spent in different rooms of their household to infer sociability information. We applied the same technology and setup in an internal experiment with healthy volunteers to evaluate the accuracy of the proposed algorithm in 10 different home setups, and we observed an average accuracy of 97.2%. Moreover, we show that it is feasible for the clinical study participants/caregivers to set up the BLE beacon sensors in their homes without any technical help, with 96% of them setting up the technology on the first day of data collection. Next, we present results from one-week location data from study participants collected through the proposed technology. Finally, we provide a list of good practice guidelines for optimally applying beacon technology for indoor location monitoring. The proposed algorithm enables us to estimate time spent in different rooms of a household that can pave the development of objective sociability features and eventually support decisions regarding drug efficacy in ASD.

Received Signal Strength Fingerprinting-Based Indoor Location Estimation Employing Machine Learning

The fingerprinting technique is a popular approach to reveal location of persons, instruments or devices in an indoor environment. Typically based on signal strength measurement, a power level map is created first in the learning phase to align with measured values in the inference. Second, the location is determined by taking the point for which the recorded received power level is closest to the power level actually measured. The biggest limit of this technique is the reliability of power measurements, which may lack accuracy in many wireless systems. To this end, this work extends the power level measurement by using multiple anchors and multiple radio channels and, consequently, considers different approaches to aligning the actual measurements with the recorded values. The dataset is available online. This article focuses on the very popular radio technology Bluetooth Low Energy to explore the possible improvement of the system accuracy through different machine learning approaches. It shows how the accuracy-complexity trade-off influences the possible candidate algorithms on an example of three-channel Bluetooth received signal strength based fingerprinting in a one dimensional environment with four static anchors and in a two dimensional environment with the same set of anchors. We provide a literature survey to identify the machine learning algorithms applied in the literature to show that the studies available can not be compared directly. Then, we implement and analyze the performance of four most popular supervised learning techniques, namely k Nearest Neighbors, Support Vector Machines, Random Forest, and Artificial Neural Network. In our scenario, the most promising machine learning technique being the Random Forest with classification accuracy over 99%.

Developing a Solution for Mobility and Distribution Analysis Based on Bluetooth and Artificial Intelligence

The purpose of this research was to develop a simple, cost-effective, but enough efficient solution for locating, tracking and distribution analysis of people and/or vehicle flowing, based on non-intrusive Bluetooth sensing and selective filtering algorithms employing artificial intelligence components. The solution provides a tool for analyzing density of targets in a specific area, useful when checking contact proximities of a target along a route. The principle consists of the detection of mobile devices that use active Bluetooth connections, such as personal notebooks, smartphones, smartwatches, Bluetooth headphones, etc. to locate and track their movement in the dedicated area. For this purpose, a specific configuration of three BT sensors is used and RSSI levels compared, based on a combination of differential location estimates. The solution may also be suited for indoor localization where GPS signals are usually weak or missing; for example, in public places such as subway stations or trains, hospitals, airport terminals and so on. The applicability of this solution is estimated to be vast, ranging from travel and transport information services, route guidance, passenger flows tracking, and path recovery for persons suspected to have SARS-COV2 or other contagious viruses, serving epidemiologic enquiries. The specific configuration of Bluetooth detectors may be installed either in a fixed location, or in a public transport vehicle. A set of filters and algorithms for triangulation-based location of detected targets and movement tracking, based on artificial intelligence is employed. When applied in the public transport field, this setup can be also developed to extract additional information on traffic, such as private traffic flowing, or passenger movement patterns along the vehicle route, improved location in absence of GPS signals, etc. Field tests have been carried out for determining different aspects concerning indoor location accuracy, reliability, selection of targets and filtering. Results and possible applications are also presented in the final section of the paper.

BLE-GSpeed: A New BLE-Based Dataset to Estimate User Gait Speed

To estimate the user gait speed can be crucial in many topics, such as health care systems, since the presence of difficulties in walking is a core indicator of health and function in aging and disease. Methods for non-invasive and continuous assessment of the gait speed may be key to enable early detection of cognitive diseases such as dementia or Alzheimer’s disease. Wearable technologies can provide innovative solutions for healthcare problems. Bluetooth Low Energy (BLE) technology is excellent for wearables because it is very energy efficient, secure, and inexpensive. In this paper, the BLE-GSpeed database is presented. The dataset is composed of several BLE RSSI measurements obtained while users were walking at a constant speed along a corridor. Moreover, a set of experiments using a baseline algorithm to estimate the gait speed are also presented to provide baseline results to the research community.

Multi-Slot BLE Raw Database for Accurate Positioning in Mixed Indoor/Outdoor Environments

The technologies and sensors embedded in smartphones have contributed to the spread of disruptive applications built on top of Location Based Services (LBSs). Among them, Bluetooth Low Energy (BLE) has been widely adopted for proximity and localization, as it is a simple but efficient positioning technology. This article presents a database of received signal strength measurements (RSSIs) on BLE signals in a real positioning system. The system was deployed on two buildings belonging to the campus of the University of Extremadura in Badajoz. the database is divided into three different deployments, changing in each of them the number of measurement points and the configuration of the BLE beacons. the beacons used in this work can broadcast up to six emission slots simultaneously. Fingerprinting positioning experiments are presented in this work using multiple slots, improving positioning accuracy when compared with the traditional single slot approach.

Indoor Localization System Based on Bluetooth Low Energy for Museum Applications

In the last few years, indoor localization has attracted researchers and commercial developers. Indeed, the availability of systems, techniques and algorithms for localization allows the improvement of existing communication applications and services by adding position information. Some examples can be found in the managing of people and/or robots for internal logistics in very large warehouses (e.g., Amazon warehouses, etc.). In this paper, we study and develop a system allowing the accurate indoor localization of people visiting a museum or any other cultural institution. We assume visitors are equipped with a Bluetooth Low Energy (BLE) device (commonly found in modern smartphones or in a small chipset), periodically transmitting packets, which are received by geolocalized BLE receivers inside the museum area. Collected packets are provided to the locator server to estimate the positions of the visitors inside the museum. The position estimation is based on a feed-forward neural network trained by a measurement campaign in the considered environment and on a non-linear least square algorithm. We also provide a strategy for deploying the BLE receivers in a given area. The performance results obtained from measurements show an achievable position estimate accuracy below 1 m.

Development of a real-time indoor location system using bluetooth low energy technology and deep learning to facilitate clinical applications

PURPOSE

An indoor, real-time location system (RTLS) can benefit both hospitals and patients by improving clinical efficiency through data-driven optimization of procedures. Bluetooth-based RTLS systems are cost-effective but lack accuracy because Bluetooth signal is subject to significant fluctuation. We aim to improve the accuracy of RTLS using the deep learning technique.

METHODS

We installed a Bluetooth sensor network in a three-floor clinic building to track patients, staff, and devices. The Bluetooth sensors measured the strength of the signal broadcasted from Bluetooth tags, which was fed into a deep neural network to calculate the location of the tags. The proposed deep neural network consists of a long short-term memory (LSTM) network and a deep classifier for tracking moving objects. Additionally, a spatial-temporal constraint algorithm was implemented to further increase the accuracy and stability of the results. To train the neural network, we divided the building into 115 zones and collected training data in each zone. We further augmented the training data to generate cross-zone trajectories, mimicking the real-world scenarios. We tuned the parameters for the proposed neural network to achieve relatively good accuracy.

RESULTS

The proposed deep neural network achieved an overall accuracy of about 97% for tracking objects in each individual zone in the whole three-floor building, 1.5% higher than the baseline neural network that was proposed in an earlier paper, when using 10 s of signals. The accuracy increased with the density of Bluetooth sensors. For tracking moving objects, the proposed neural network achieved stable and accurate results. When latency is less of a concern, we eliminated the effect of latency from the accuracy and gained an accuracy of 100% for our testing trajectories, significantly improved from the baseline method.

CONCLUSIONS

The proposed deep neural network composed of a LSTM, a deep classifier and a posterior constraint algorithm significantly improved the accuracy and stability of RTLS for tracking moving objects.

Applying Movement Constraints to BLE RSSI-Based Indoor Positioning for Extracting Valid Semantic Trajectories

Indoor positioning techniques, owing to received signal strength indicator (RSSI)-based sensors, can provide useful trajectory-based services. These services include user movement analytics, next-to-visit recommendation, and hotspot detection. However, the value of RSSI is often disturbed due to obstacles in indoor environment, such as doors, walls, and furnitures. Therefore, many indoor positioning techniques still extract an invalid trajectory from the disturbed RSSI. An invalid trajectory contains distant or impossible consecutive positions within a short time, which is unlikely in a real-world scenario. In this study, we enhanced indoor positioning techniques with movement constraints on BLE (Bluetooth Low Energy) RSSI data to prevent an invalid semantic indoor trajectory. The movement constraints ensure that a predicted semantic position cannot be far apart from the previous position. Furthermore, we can extend any indoor positioning technique using these movement constraints. We conducted comprehensive experimental studies on real BLE RSSI datasets from various indoor environment scenarios. The experimental results demonstrated that the proposed approach effectively extracts valid indoor semantic trajectories from the RSSI data.

Hybrid Wireless Fingerprint Indoor Localization Method Based on a Convolutional Neural Network

In the indoor location field, the quality of received-signal-strength-indicator (RSSI) fingerprints plays a key role in the performance of indoor location services. However, changes in an indoor environment may lead to the decline of location accuracy. This paper presents a localization method employing a Hybrid Wireless fingerprint (HW-fingerprint) based on a convolutional neural network (CNN). In the proposed scheme, the Ratio fingerprint was constructed by calculating the ratio of different RSSIs from important contribution access points (APs). The HW-fingerprint combined the Ratio fingerprint and the RSSI to enhance the expression of indoor environment characteristics. Moreover, a CNN architecture was constructed to learn important features from the complex HW-fingerprint for indoor locations. In the experiment, the HW-fingerprint was tested in an actual indoor scene for 15 days. Results showed that the average daily location accuracy of the K-Nearest Neighbor (KNN), Support Vector Machines (SVMs), and CNN was improved by 3.39%, 8.03% and 9.03%, respectively, when using the HW-fingerprint. In addition, the deep-learning method was 4.19% and 16.37% higher than SVM and KNN in average daily location accuracy, respectively.

Wireless Indoor Localization Using Convolutional Neural Network and Gaussian Process Regression

This paper presents a localization model employing convolutional neural network (CNN) and Gaussian process regression (GPR) based on Wi-Fi received signal strength indication (RSSI) fingerprinting data. In the proposed scheme, the CNN model is trained by a training dataset. The trained model adapts to complex scenes with multipath effects or many access points (APs). More specifically, the pre-processing algorithm makes the RSSI vector which is formed by considerable RSSI values from different APs readable by the CNN algorithm. The trained CNN model improves the positioning performance by taking a series of RSSI vectors into account and extracting local features. In this design, however, the performance is to be further improved by applying the GPR algorithm to adjust the coordinates of target points and offset the over-fitting problem of CNN. After implementing the hybrid model, the model is experimented with a public database that was collected from a library of Jaume I University in Spain. The results show that the hybrid model has outperformed the model using k-nearest neighbor (KNN) by 61.8%. While the CNN model improves the performance by 45.8%, the GPR algorithm further enhances the localization accuracy. In addition, the paper has also experimented with the three kernel functions, all of which have been demonstrated to have positive effects on GPR.

Intelligent inverse treatment planning via deep reinforcement learning, a proof-of-principle study in high dose-rate brachytherapy for cervical cancer

Inverse treatment planning in radiation therapy is formulated as solving optimization problems. The objective function and constraints consist of multiple terms designed for different clinical and practical considerations. Weighting factors of these terms are needed to define the optimization problem. While a treatment planning optimization engine can solve the optimization problem with given weights, adjusting the weights to yield a high-quality plan is typically performed by a human planner. Yet the weight-tuning task is labor intensive, time consuming, and it critically affects the final plan quality. An automatic weight-tuning approach is strongly desired. The procedure of weight adjustment to improve the plan quality is essentially a decision-making problem. Motivated by the tremendous success in deep learning for decision making with human-level intelligence, we propose a novel framework to adjust the weights in a human-like manner. This study used inverse treatment planning in high-dose-rate brachytherapy (HDRBT) for cervical cancer as an example. We developed a weight-tuning policy network (WTPN) that observes dose volume histograms of a plan and outputs an action to adjust organ weighting factors, similar to the behaviors of a human planner. We trained the WTPN via end-to-end deep reinforcement learning. Experience replay was performed with the epsilon greedy algorithm. After training was completed, we applied the trained WTPN to guide treatment planning of five testing patient cases. It was found that the trained WTPN successfully learnt the treatment planning goals and was able to guide the weight tuning process. On average, the quality score of plans generated under the WTPN's guidance was improved by ~8.5% compared to the initial plan with arbitrarily set weights, and by 10.7% compared to the plans generated by human planners. To our knowledge, this was the first time that a tool was developed to adjust organ weights for the treatment planning optimization problem in a human-like fashion based on intelligence learnt from a training process, which was different from existing strategies based on pre-defined rules. The study demonstrated potential feasibility to develop intelligent treatment planning approaches via deep reinforcement learning.

A Deep Learning Approach to Position Estimation from Channel Impulse Responses

Radio-based locating systems allow for a robust and continuous tracking in industrial environments and are a key enabler for the digitalization of processes in many areas such as production, manufacturing, and warehouse management. Time difference of arrival (TDoA) systems estimate the time-of-flight (ToF) of radio burst signals with a set of synchronized antennas from which they trilaterate accurate position estimates of mobile tags. However, in industrial environments where multipath propagation is predominant it is difficult to extract the correct ToF of the signal. This article shows how deep learning (DL) can be used to estimate the position of mobile objects directly from the raw channel impulse responses (CIR) extracted at the receivers. Our experiments show that our DL-based position estimation not only works well under harsh multipath propagation but also outperforms state-of-the-art approaches in line-of-sight situations.

BLE RSS Measurements Dataset for Research on Accurate Indoor Positioning

RSS-based indoor positioning is a consolidated research field for which several techniques have been proposed. Among them, Bluetooth Low Energy (BLE) beacons are a popular option for practical applications. This paper presents a new BLE RSS database that was created to aid in the development of new BLE RSS-based positioning methods and to encourage their reproducibility and comparability. The measurements were collected in two university zones: an area among bookshelves in a library and an area of an office space. Each zone had its own batch of deployed iBKS 105 beacons, configured to broadcast advertisements every 200 ms. The collection in the library zone was performed using three Android smartphones of different brands and models, with beacons broadcasting at −12 dBm transmission power, while in the other zone the collection was performed using of one those smartphones with beacons configured to advertise at the −4 dBm, −12 dBm and −20 dBm transmission powers. Supporting materials and scripts are provided along with the database, which annotate the BLE readings, provide details on the collection, the environment, and the BLE beacon deployments, ease the database usage, and introduce the reader to BLE RSS-based positioning and its challenges. The BLE RSS database and its supporting materials are available at the Zenodo repository under the open-source MIT license.