RESUMO
Putting sensors on the bodies of animals to automate animal activity recognition and gain insight into their behaviors can help improve their living conditions. Although previous hard-coded algorithms failed to classify complex time series obtained from accelerometer data, recent advances in deep learning have improved the task of animal activity recognition for the better. However, a comparative analysis of the generalizing capabilities of various models in combination with different input types has yet to be addressed. This study experimented with two techniques for transforming the segmented accelerometer data to make them more orientation-independent. The methods included calculating the magnitude of the three-axis accelerometer vector and calculating the Discrete Fourier Transform for both sets of three-axis data as the vector magnitude. Three different deep learning models were trained on this data: a Multilayer Perceptron, a Convolutional Neural Network, and an ensemble merging both called a hybrid Convolutional Neural Network. Besides mixed cross-validation, every model and input type combination was assessed on a goat-wise leave-one-out cross-validation set to evaluate its generalizing capability. Using orientation-independent data transformations gave promising results. A hybrid Convolutional Neural Network with L2-norm as the input combined the higher classification accuracy of a Convolutional Neural Network with the lower standard deviation of a Multilayer Perceptron. Most of the misclassifications occurred for behaviors that display similar accelerometer traces and minority classes, which could be improved in future work by assembling larger and more balanced datasets.
RESUMO
Although wireless devices continuously gain communication capabilities, even state-of-the-art Industrial Internet of Things (IIoT) architectures, such as Internet Protocol version 6 over the Time-Slotted Channel Hopping (TSCH) mode of IEEE 802.15.4 (6TiSCH), continue to use network-wide, fixed link configurations. This presents a missed opportunity to (1) forego the need for rigorous manual setup of new deployments; and (2) provide full coverage of particularly heterogeneous and/or dynamic industrial sites. As such, we devised the Multi-Modal Minimal Scheduling Function (3MSF) for the TSCH link layer, which, combined with previous work on the routing layer, results in a 6TiSCH architecture able to dynamically exploit modern multi-modal hardware on a per-link basis through variable-duration timeslots, simultaneous transmission, and routing metric normalization. This paper describes, in great detail, its design and discusses the rationale behind every choice made. Finally, we evaluate three basic scenarios through simulations, showcasing both the functionality and flexibility of our 6TiSCH implementation.
RESUMO
ECG classification or heartbeat classification is an extremely valuable tool in cardiology. Deep learning-based techniques for the analysis of ECG signals assist human experts in the timely diagnosis of cardiac diseases and help save precious lives. This research aims at digitizing a dataset of images of ECG records into time series signals and then applying deep learning (DL) techniques on the digitized dataset. State-of-the-art DL techniques are proposed for the classification of the ECG signals into different cardiac classes. Multiple DL models, including a convolutional neural network (CNN), a long short-term memory (LSTM) network, and a self-supervised learning (SSL)-based model using autoencoders are explored and compared in this study. The models are trained on the dataset generated from ECG plots of patients from various healthcare institutes in Pakistan. First, the ECG images are digitized, segmenting the lead II heartbeats, and then the digitized signals are passed to the proposed deep learning models for classification. Among the different DL models used in this study, the proposed CNN model achieves the highest accuracy of â¼92%. The proposed model is highly accurate and provides fast inference for real-time and direct monitoring of ECG signals that are captured from the electrodes (sensors) placed on different parts of the body. Using the digitized form of ECG signals instead of images for the classification of cardiac arrhythmia allows cardiologists to utilize DL models directly on ECG signals from an ECG machine for the real-time and accurate monitoring of ECGs.
Assuntos
Arritmias Cardíacas , Aprendizado Profundo , Eletrocardiografia , Redes Neurais de Computação , Humanos , Eletrocardiografia/métodos , Arritmias Cardíacas/diagnóstico , Arritmias Cardíacas/fisiopatologia , Arritmias Cardíacas/classificação , Processamento de Sinais Assistido por Computador , Algoritmos , Frequência Cardíaca/fisiologiaRESUMO
Ultra-wideband (UWB) has gained increasing interest for providing real-time positioning to robots in GPS-denied environments. For a robot to act on this information, it also requires its heading. This is, however, not provided by UWB. To overcome this, either multiple tags are used to create a local reference frame connected to the robot or a single tag is combined with ego-motion estimation from odometry or Inertial Measurement Unit (IMU) measurements. Both odometry and the IMU suffer from drift, and it is common to use a magnetometer to correct the drift on the heading; however, magnetometers tend to become unreliable in typical GPS-denied environments. To overcome this, a lightweight particle filter was designed to run in real time. The particle filter corrects the ego-motion heading and location drift using the UWB measurements over a moving horizon time frame. The algorithm was evaluated offline using data sets collected from a ground robot that contains line-of-sight (LOS) and non-line-of-sight conditions. An RMSE of 13 cm and 0.12 (rad) was achieved with four anchors in the LOS condition. It is also shown that it can be used to provide the robot with real-time position and heading information for the robot to act on it in LOS conditions, and it is shown to be robust in both experimental conditions.
RESUMO
The Routing Protocol for Low-power and Lossy Networks (RPL) is a popular routing layer protocol for multi-hop Wireless Sensor Networks (WSNs). However, typical RPL configurations are based on decade-old assumptions, leading to a mismatch with: (1) advances in wireless hardware; and (2) growing wireless contention. To soften the impact of external stressors (i.e., jamming and interference), we extended RPL to exploit the capabilities of modern multi-interfaced wireless devices. More specifically, our main contribution is the design, development, and evaluation of a novel RPL Objective Function (OF) which, through simulations, is compared to traditional single-interface approaches and a state-of-the-art multi-interface approach. We examine two scenarios, with and without the injection of jamming, respectively. Our proposed OF is shown to outperform, or otherwise perform similar to, all alternatives considered. In normal conditions, it auto-selects the best interface whilst incurring negligible protocol overhead. In our jamming simulations, it provides stable end-to-end delivery ratios exceeding 90%, whereas the closest alternative averages 65% and is considerably less stable. Given we have open-sourced our development codebase, our solution is an ideal candidate for adoption by RPL deployments that expect to suffer interference from competing technologies or are unable to select the best radio technology a priori.
RESUMO
Equine training activity detection will help to track and enhance the performance and fitness level of riders and their horses. Currently, the equestrian world is eager for a simple solution that goes beyond detecting basic gaits, yet current technologies fall short on the level of user friendliness and detection of main horse training activities. To this end, we collected leg accelerometer data of 14 well-trained horses during jumping and dressage trainings. For the first time, 6 jumping training and 25 advanced horse dressage activities are classified using specifically developed models based on a neural network. A jumping training could be classified with a high accuracy of 100 %, while a dressage training could be classified with an accuracy of 96.29%. Assigning the dressage movements to 11, 6 or 4 superclasses results in higher accuracies of 98.87%, 99.10% and 100%, respectively. Furthermore, during dressage training, the side of movement could be identified with an accuracy of 97.08%. In addition, a velocity estimation model was developed based on the measured velocities of seven horses performing the collected, working, and extended gaits during a dressage training. For the walk, trot, and canter paces, the velocities could be estimated accurately with a low root mean square error of 0.07 m/s, 0.14 m/s, and 0.42 m/s, respectively.
RESUMO
While IEEE 802.15.4e Time-Slotted Channel Hopping (TSCH) networks should be equipped to deal with the hard wireless challenges of industrial environments, the sensor networks are often still limited by the characteristics of the used physical (PHY) layer. Therefore, the TSCH community has recently started shifting research efforts to the support of multiple PHY layers, to overcome this limitation. On the one hand, integrating such multi-PHY support implies dealing with the PHY characteristics to fit the resource allocation in the TSCH schedule, and on the other hand, defining policies on how to select the appropriate PHY for each network link. As such, first a heuristic is proposed that is a step towards a distributed PHY and parent selection mechanism for slot bonding multi-PHY TSCH sensor networks. Additionally, a proposal on how this heuristic can be implemented in the IPv6 over the TSCH mode of IEEE 802.15.4e (6TiSCH) protocol stack and its Routing Protocol for Low-power and Lossy network (RPL) layer is also presented. Slot bonding allows the creation of different-sized bonded slots with a duration adapted to the data rate of each chosen PHY. Afterwards, a TSCH slot bonding implementation is proposed in the latest version of the Contiki-NG Industrial Internet of Things (IIoT) operating system. Subsequently, via extensive simulation results, and by deploying the slot bonding implementation on a real sensor node testbed, it is shown that the computationally efficient parent and PHY selection mechanism approximates the packet delivery ratio (PDR) results of a near-optimal, but computationally complex, centralized scheduler.
RESUMO
Currently, gathering statistics and information for ice hockey training purposes mostly happens by hand, whereas the automated systems that do exist are expensive and difficult to set up. To remedy this, in this paper, we propose and analyse a wearable system that combines player localisation and activity classification to automatically gather information. A stick-worn inertial measurement unit was used to capture acceleration and rotation data from six ice hockey activities. A convolutional neural network was able to distinguish the six activities from an unseen player with a 76% accuracy at a sample frequency of 100 Hz. Using unseen data from players used to train the model, a 99% accuracy was reached. With a peak detection algorithm, activities could be automatically detected and extracted from a complete measurement for classification. Additionally, the feasibility of a time difference of arrival based ultra-wideband system operating at a 25 Hz update rate was determined. We concluded that the system, when the data were filtered and smoothed, provided acceptable accuracy for use in ice hockey. Combining both, it was possible to gather useful information about a wide range of interesting performance measures. This shows that our proposed system is a suitable solution for the analysis of ice hockey.
Assuntos
Hóquei , Aceleração , RotaçãoRESUMO
A mechanically flexible textile antenna-backed sensor node is designed and manufactured, providing accurate personal localization functionality by application of Decawave's DW1000 Impulse Radio Ultra-Wideband (IR-UWB) Integrated Circuit (IC). All components are mounted on a flexible polyimide foil, which is integrated on the backplane of a wearable cavity-backed slot antenna designed for IR-UWB localization in Channels 2 and 3 of the IEEE 802.15.4-2011 standard (3744 MHz-4742.4 MHz). The textile antenna's radiation pattern is optimized to mitigate body effects and to minimize absorption by body tissues. Furthermore, its time-domain characteristics are measured to be adequate for localization. By combining the antenna and the bendable Printed Circuit Board (PCB), a mechanically supple sensor system is realized, for which the performance is validated by examining it as a node used in a complete localization system. This shows that six nodes around the body must be deployed to provide system coverage in all directions around the wearer. Even without using sleep mode functionalities, the measurements indicate that the system's autonomy is 13.3 h on a 5 V 200 mAh battery. Hence, this system acts as a proof of concept for the joining of localization electronics and other sensors with a full-textile antenna into a mechanically flexible sensor system.
RESUMO
A thorough analysis of sports is becoming increasingly important during the training process of badminton players at both the recreational and professional level. Nowadays, game situations are usually filmed and reviewed afterwards in order to analyze the game situation, but these video set-ups tend to be difficult to analyze, expensive, and intrusive to set up. In contrast, we classified badminton movements using off-the-shelf accelerometer and gyroscope data. To this end, we organized a data capturing campaign and designed a novel neural network using different frame sizes as input. This paper shows that with only accelerometer data, our novel convolutional neural network is able to distinguish nine activities with 86% precision when using a sampling frequency of 50 Hz. Adding the gyroscope data causes an increase of up to 99% precision, as compared to, respectively, 79% and 88% when using a traditional convolutional neural network. In addition, our paper analyses the impact of different sensor placement options and discusses the impact of different sampling frequenciess of the sensors. As such, our approach provides a low cost solution that is easy to use and can collect useful information for the analysis of a badminton game.
Assuntos
Acelerometria , Esportes com Raquete , Movimento , Redes Neurais de ComputaçãoRESUMO
Aside from vast deployment cost reduction, Industrial Wireless Sensor and Actuator Networks (IWSAN) introduce a new level of industrial connectivity. Wireless connection of sensors and actuators in industrial environments not only enables wireless monitoring and actuation, it also enables coordination of production stages, connecting mobile robots and autonomous transport vehicles, as well as localization and tracking of assets. All these opportunities already inspired the development of many wireless technologies in an effort to fully enable Industry 4.0. However, different technologies significantly differ in performance and capabilities, none being capable of supporting all industrial use cases. When designing a network solution, one must be aware of the capabilities and the trade-offs that prospective technologies have. This paper evaluates the technologies potentially suitable for IWSAN solutions covering an entire industrial site with limited infrastructure cost and discusses their trade-offs in an effort to provide information for choosing the most suitable technology for the use case of interest. The comparative discussion presented in this paper aims to enable engineers to choose the most suitable wireless technology for their specific IWSAN deployment.
RESUMO
Ultra-wideband (UWB) localization is one of the most promising approaches for indoor localization due to its accurate positioning capabilities, immunity against multipath fading, and excellent resilience against narrowband interference. However, UWB researchers are currently limited by the small amount of feasible open source hardware that is publicly available. We developed a new open source hardware platform, Wi-PoS, for precise UWB localization based on Decawave's DW1000 UWB transceiver with several unique features: support of both long-range sub-GHz and 2.4 GHz back-end communication between nodes, flexible interfacing with external UWB antennas, and an easy implementation of the MAC layer with the Time-Annotated Instruction Set Computer (TAISC) framework. Both hardware and software are open source and all parameters of the UWB ranging can be adjusted, calibrated, and analyzed. This paper explains the main specifications of the hardware platform, illustrates design decisions, and evaluates the performance of the board in terms of range, accuracy, and energy consumption. The accuracy of the ranging system was below 10 cm in an indoor lab environment at distances up to 5 m, and accuracy smaller than 5 cm was obtained at 50 and 75 m in an outdoor environment. A theoretical model was derived for predicting the path loss and the influence of the most important ground reflection. At the same time, the average energy consumption of the hardware was very low with only 81 mA for a tag node and 63 mA for the active anchor nodes, permitting the system to run for several days on a mobile battery pack and allowing easy and fast deployment on sites without an accessible power supply or backbone network. The UWB hardware platform demonstrated flexibility, easy installation, and low power consumption.
RESUMO
Current inventory-taking methods (counting stocks and checking correct placements) in large vertical warehouses are mostly manual, resulting in (i) large personnel costs, (ii) human errors and (iii) incidents due to working at large heights. To remedy this, the use of autonomous indoor drones has been proposed. However, these drones require accurate localization solutions that are easy to (temporarily) install at low costs in large warehouses. To this end, we designed a Ultra-Wideband (UWB) solution that uses infrastructure anchor nodes that do not require any wired backbone and can be battery powered. The resulting system has a theoretical update rate of up to 2892 Hz (assuming no hardware dependent delays). Moreover, the anchor nodes have an average current consumption of only 27 mA (compared to 130 mA of traditional UWB infrastructure nodes). Finally, the system has been experimentally validated and is available as open-source software.
RESUMO
LoRaWAN is one of the low power wide area network (LPWAN) technologies that have received significant attention by the research community in the recent years. It offers low-power, low-data rate communication over a wide range of covered area. In the past years, the number of publications regarding LoRa and LoRaWAN has grown tremendously. This paper provides an overview of research work that has been published from 2015 to September 2018 and that is accessible via Google Scholar and IEEE Explore databases. First, a detailed description of the technology is given, including existing security and reliability mechanisms. This literature overview is structured by categorizing papers according to the following topics: (i) physical layer aspects; (ii) network layer aspects; (iii) possible improvements; and (iv) extensions to the standard. Finally, a strengths, weaknesses, opportunities and threats (SWOT) analysis is presented along with the challenges that LoRa and LoRaWAN still face.
RESUMO
Radio frequency (RF) technologies are often used to track assets in indoor environments. Among others, ultra-wideband (UWB) has constantly gained interest thanks to its capability to obtain typical errors of 30 cm or lower, making it more accurate than other wireless technologies such as WiFi, which normally can predict the location with several meters accuracy. However, mainly due to technical requirements that are part of the standard, conventional medium access strategies such as clear channel assessment, are not straightforward to implement. Since most scientific papers focus on UWB accuracy improvements of a single user, it is not clear to which extend this limitation and other design choices impact the scalability of UWB indoor positioning systems. We investigated the scalability of indoor localization solutions, to prove that UWB can be used when hundreds of tags are active in the same system. This paper provides mathematical models that calculate the theoretical supported user density for multiple localization approaches, namely Time Difference of Arrival (TDoA) and Two-Way Ranging (TWR) with different MAC protocol combinations, i.e., ALOHA and TDMA. Moreover, this paper applies these formulas to a number of realistic UWB configurations to study the impact of different UWB schemes and settings. When applied to the 802.15.4a compliant Decawave DW1000 chip, the scalability dramatically degrades if the system operates with uncoordinated protocols and two-way communication schemes. In the best case scenario, UWB DW1000 chips can actively support up to 6171 tags in a single domain cell (no handover) with well-selected settings and choices, i.e., when adopting the combination of TDoA (one-way link) and TDMA. As a consequence, UWB can be used to simultaneously localize thousands of nodes in a dense network. However, we also show that the number of supported devices varies greatly depending on the MAC and PHY configuration choices.
RESUMO
Radio frequency (RF)-based indoor positioning systems (IPSs) use wireless technologies (including Wi-Fi, Zigbee, Bluetooth, and ultra-wide band (UWB)) to estimate the location of persons in areas where no Global Positioning System (GPS) reception is available, for example in indoor stadiums or sports halls. Of the above-mentioned forms of radio frequency (RF) technology, UWB is considered one of the most accurate approaches because it can provide positioning estimates with centimeter-level accuracy. However, it is not yet known whether UWB can also offer such accurate position estimates during strenuous dynamic activities in which moves are characterized by fast changes in direction and velocity. To answer this question, this paper investigates the capabilities of UWB indoor localization systems for tracking athletes during their complex (and most of the time unpredictable) movements. To this end, we analyze the impact of on-body tag placement locations and human movement patterns on localization accuracy and communication reliability. Moreover, two localization algorithms (particle filter and Kalman filter) with different optimizations (bias removal, non-line-of-sight (NLoS) detection, and path determination) are implemented. It is shown that although the optimal choice of optimization depends on the type of movement patterns, some of the improvements can reduce the localization error by up to 31%. Overall, depending on the selected optimization and on-body tag placement, our algorithms show good results in terms of positioning accuracy, with average errors in position estimates of 20 cm. This makes UWB a suitable approach for tracking dynamic athletic activities.
Assuntos
Postura , Algoritmos , Humanos , Reprodutibilidade dos Testes , Esportes , Tecnologia sem FioRESUMO
So far, existing sub-GHz wireless communication technologies focused on low-bandwidth, long-range communication with large numbers of constrained devices. Although these characteristics are fine for many Internet of Things (IoT) applications, more demanding application requirements could not be met and legacy Internet technologies such as Transmission Control Protocol/Internet Protocol (TCP/IP) could not be used. This has changed with the advent of the new IEEE 802.11ah Wi-Fi standard, which is much more suitable for reliable bidirectional communication and high-throughput applications over a wide area (up to 1 km). The standard offers great possibilities for network performance optimization through a number of physical- and link-layer configurable features. However, given that the optimal configuration parameters depend on traffic patterns, the standard does not dictate how to determine them. Such a large number of configuration options can lead to sub-optimal or even incorrect configurations. Therefore, we investigated how two key mechanisms, Restricted Access Window (RAW) grouping and Traffic Indication Map (TIM) segmentation, influence scalability, throughput, latency and energy efficiency in the presence of bidirectional TCP/IP traffic. We considered both high-throughput video streaming traffic and large-scale reliable sensing traffic and investigated TCP behavior in both scenarios when the link layer introduces long delays. This article presents the relations between attainable throughput per station and attainable number of stations, as well as the influence of RAW, TIM and TCP parameters on both. We found that up to 20 continuously streaming IP-cameras can be reliably connected via IEEE 802.11ah with a maximum average data rate of 160 kbps, whereas 10 IP-cameras can achieve average data rates of up to 255 kbps over 200 m. Up to 6960 stations transmitting every 60 s can be connected over 1 km with no lost packets. The presented results enable the fine tuning of RAW and TIM parameters for throughput-demanding reliable applications (i.e., video streaming, firmware updates) on one hand, and very dense low-throughput reliable networks with bidirectional traffic on the other hand.
RESUMO
Driven by the fast growth of wireless communication, the trend of sharing spectrum among heterogeneous technologies becomes increasingly dominant. Identifying concurrent technologies is an important step towards efficient spectrum sharing. However, due to the complexity of recognition algorithms and the strict condition of sampling speed, communication systems capable of recognizing signals other than their own type are extremely rare. This work proves that multi-model distribution of the received signal strength indicator (RSSI) is related to the signals' modulation schemes and medium access mechanisms, and RSSI from different technologies may exhibit highly distinctive features. A distinction is made between technologies with a streaming or a non-streaming property, and appropriate feature spaces can be established either by deriving parameters such as packet duration from RSSI or directly using RSSI's probability distribution. An experimental study shows that even RSSI acquired at a sub-Nyquist sampling rate is able to provide sufficient features to differentiate technologies such as Wi-Fi, Long Term Evolution (LTE), Digital Video Broadcasting-Terrestrial (DVB-T) and Bluetooth. The usage of the RSSI distribution-based feature space is illustrated via a sample algorithm. Experimental evaluation indicates that more than 92% accuracy is achieved with the appropriate configuration. As the analysis of RSSI distribution is straightforward and less demanding in terms of system requirements, we believe it is highly valuable for recognition of wideband technologies on constrained devices in the context of dynamic spectrum access.
RESUMO
Data science or "data-driven research" is a research approach that uses real-life data to gain insight about the behavior of systems. It enables the analysis of small, simple as well as large and more complex systems in order to assess whether they function according to the intended design and as seen in simulation. Data science approaches have been successfully applied to analyze networked interactions in several research areas such as large-scale social networks, advanced business and healthcare processes. Wireless networks can exhibit unpredictable interactions between algorithms from multiple protocol layers, interactions between multiple devices, and hardware specific influences. These interactions can lead to a difference between real-world functioning and design time functioning. Data science methods can help to detect the actual behavior and possibly help to correct it. Data science is increasingly used in wireless research. To support data-driven research in wireless networks, this paper illustrates the step-by-step methodology that has to be applied to extract knowledge from raw data traces. To this end, the paper (i) clarifies when, why and how to use data science in wireless network research; (ii) provides a generic framework for applying data science in wireless networks; (iii) gives an overview of existing research papers that utilized data science approaches in wireless networks; (iv) illustrates the overall knowledge discovery process through an extensive example in which device types are identified based on their traffic patterns; (v) provides the reader the necessary datasets and scripts to go through the tutorial steps themselves.
RESUMO
BACKGROUND: The combination of an aging population and nursing staff shortages implies the need for more advanced systems in the healthcare industry. Many key enablers for the optimization of healthcare systems require provisioning of location awareness for patients (e.g. with dementia), nurses, doctors, assets, etc. Therefore, many Indoor Positioning Systems (IPSs) will be indispensable in healthcare systems. However, although many IPSs have been proposed in literature, most of these have been evaluated in non-representative environments such as office buildings rather than in a hospital. METHODS: To remedy this, the paper evaluates the performance of existing IPSs in an operational modern healthcare environment: the "Sint-Jozefs kliniek Izegem" hospital in Belgium. The evaluation (data-collecting and data-processing) is executed using a standardized methodology and evaluates the point accuracy, room accuracy and latency of multiple IPSs. To evaluate the solutions, the position of a stationary device was requested at 73 evaluation locations. By using the same evaluation locations for all IPSs the performance of all systems could objectively be compared. RESULTS: Several trends can be identified such as the fact that Wi-Fi based fingerprinting solutions have the best accuracy result (point accuracy of 1.21 m and room accuracy of 98%) however it requires calibration before use and needs 5.43 s to estimate the location. On the other hand, proximity based solutions (based on sensor nodes) are significantly cheaper to install, do not require calibration and still obtain acceptable room accuracy results. CONCLUSION: As a conclusion of this paper, Wi-Fi based solutions have the most potential for an indoor positioning service in case when accuracy is the most important metric. Applying the fingerprinting approach with an anchor installed in every two rooms is the preferred solution for a hospital environment.