A Self Regulating and Crowdsourced Indoor Positioning System through Wi-Fi Fingerprinting for Multi Storey Building

A Novel Outdoor Positioning Technique Using LTE Network Fingerprints

In recent years, wireless-based fingerprint positioning has attracted increasing research attention owing to its position-related features and applications in the Internet of Things (IoT). In this paper, by leveraging long-term evolution (LTE) signals, a novel deep-learning-based fingerprint positioning approach is proposed to solve the problem of outdoor positioning. Considering the outstanding performance of deep learning in image classification, LTE signal measurements are converted into location grayscale images to form a fingerprint database. In order to deal with the instability of LTE signals, prevent the gradient dispersion problem, and increase the robustness of the proposed deep neural network (DNN), the following methods are adopted: First, cross-entropy is used as the loss function of the DNN. Second, the learning rate of the proposed DNN is dynamically adjusted. Third, this paper adopted several data enhancement techniques. To find the best positioning fingerprint and method, three types of fingerprint and five positioning models are compared. Finally, by using a deep residual network (Resnet) and transfer learning, a hierarchical structure training method is proposed. The proposed Resnet is used to train with the united fingerprint image database to obtain a positioning model called a coarse localizer. By using the prior knowledge of the pretrained Resnet, feed-forward neural network (FFNN)-based transfer learning is used to train with the united fingerprint database to obtain a better positioning model, called a fine localizer. The experimental results convincingly show that the proposed DNN can automatically learn the location features of LTE signals and achieve satisfactory positioning accuracy in outdoor environments.

Adaptive Indoor Area Localization for Perpetual Crowdsourced Data Collection

The accuracy of fingerprinting-based indoor localization correlates with the quality and up-to-dateness of collected training data. Perpetual crowdsourced data collection reduces manual labeling effort and provides a fresh data base. However, the decentralized collection comes with the cost of heterogeneous data that causes performance degradation. In settings with imperfect data, area localization can provide higher positioning guarantees than exact position estimation. Existing area localization solutions employ a static segmentation into areas that is independent of the available training data. This approach is not applicable for crowdsoucred data collection, which features an unbalanced spatial training data distribution that evolves over time. A segmentation is required that utilizes the existing training data distribution and adapts once new data is accumulated. We propose an algorithm for data-aware floor plan segmentation and a selection metric that balances expressiveness (information gain) and performance (correctly classified examples) of area classifiers. We utilize supervised machine learning, in particular, deep learning, to train the area classifiers. We demonstrate how to regularly provide an area localization model that adapts its prediction space to the accumulating training data. The resulting models are shown to provide higher reliability compared to models that pinpoint the exact position.

Edge Computing, IoT and Social Computing in Smart Energy Scenarios

The Internet of Things (IoT) has become one of the most widely research paradigms, having received much attention from the research community in the last few years. IoT is the paradigm that creates an internet-connected world, where all the everyday objects capture data from our environment and adapt it to our needs. However, the implementation of IoT is a challenging task and all the implementation scenarios require the use of different technologies and the emergence of new ones, such as Edge Computing (EC). EC allows for more secure and efficient data processing in real time, achieving better performance and results. Energy efficiency is one of the most interesting IoT scenarios. In this scenario sensors, actuators and smart devices interact to generate a large volume of data associated with energy consumption. This work proposes the use of an Edge-IoT platform and a Social Computing framework to build a system aimed to smart energy efficiency in a public building scenario. The system has been evaluated in a public building and the results make evident the notable benefits that come from applying Edge Computing to both energy efficiency scenarios and the framework itself. Those benefits included reduced data transfer from the IoT-Edge to the Cloud and reduced Cloud, computing and network resource costs.

A Wavelet Scattering Feature Extraction Approach for Deep Neural Network Based Indoor Fingerprinting Localization

The performance of an Artificial Neural Network (ANN)-based algorithm is subject to the way the feature data is extracted. This is a common issue when applying the ANN to indoor fingerprinting-based localization where the signal is unstable. To date, there is not adequate feature extraction method that can significantly mitigate the influence of the receiver signal strength indicator (RSSI) variation that degrades the performance of the ANN-based indoor fingerprinting algorithm. In this work, a wavelet scattering transform is used to extract reliable features that are stable to small deformation and rotation invariant. The extracted features are used by a deep neural network (DNN) model to predict the location. The zero^th and the first layer of decomposition coefficients were used as features data by concatenating different scattering path coefficients. The proposed algorithm has been validated on real measurements and has achieved good performance. The experimentation results demonstrate that the proposed feature extraction method is stable to the RSSI variation.

Mobile User Indoor-Outdoor Detection Through Physical Daily Activities

An automatic, fast, and accurate switching method between Global Positioning System and indoor positioning systems is crucial to achieve current user positioning, which is essential information for a variety of services installed on smart devices, e.g., location-based services (LBS), healthcare monitoring components, and seamless indoor/outdoor navigation and localization (SNAL). In this study, we proposed an approach to accurately detect the indoor/outdoor environment according to six different daily activities of users including walk, skip, jog, stay, climbing stairs up and down. We select a number of features for each activity and then apply ensemble learning methods such as Random Forest, and AdaBoost to classify the environment types. Extensive model evaluations and feature analysis indicate that the system can achieve a high detection rate with good adaptation for environment recognition. Empirical evaluation of the proposed method has been verified on the HASC-2016 public dataset, and results show 99% accuracy to detect environment types. The proposed method relies only on the daily life activities data and does not need any external facilities such as the signal cell tower or Wi-Fi access points. This implies the applicability of the proposed method for the upper layer applications.

Signature Inspired Home Environments Monitoring System Using IR-UWB Technology

Home monitoring and remote care systems aim to ultimately provide independent living care scenarios through non-intrusive, privacy-protecting means. Their main aim is to provide care through appreciating normal habits, remotely recognizing changes and acting upon those changes either through informing the person themselves, care providers, family members, medical practitioners, or emergency services, depending on need. Care giving can be required at any age, encompassing young to the globally growing aging population. A non-wearable and unobtrusive architecture has been developed and tested here to provide a fruitful health and wellbeing-monitoring framework without interfering in a user’s regular daily habits and maintaining privacy. This work focuses on tracking locations in an unobtrusive way, recognizing daily activities, which are part of maintaining a healthy/regular lifestyle. This study shows an intelligent and locally based edge care system (ECS) solution to identify the location of an occupant’s movement from daily activities using impulse radio-ultra wide band (IR-UWB) radar. A new method is proposed calculating the azimuth angle of a movement from the received pulse and employing radar principles to determine the range of that movement. Moreover, short-term fourier transform (STFT) has been performed to determine the frequency distribution of the occupant’s action. Therefore, STFT, azimuth angle, and range calculation together provide the information to understand how occupants engage with their environment. An experiment has been carried out for an occupant at different times of the day during daily household activities and recorded with time and room position. Subsequently, these time-frequency outcomes, along with the range and azimuth information, have been employed to train a support vector machine (SVM) learning algorithm for recognizing indoor locations when the person is moving around the house, where little or no movement indicates the occurrence of abnormalities. The implemented framework is connected with a cloud server architecture, which enables to act against any abnormality remotely. The proposed methodology shows very promising results through statistical validation and achieved over 90% testing accuracy in a real-time scenario.