ISSN / EISSN : 14248220 / 14248220
Current Publisher: MDPI (10.3390)
Total articles ≅ 23,355
Google Scholar h5-index: 84
Latest articles in this journal
Sensors, Volume 20; doi:10.3390/s20020540
Abstract:It is of great significance for the global navigation satellite system (GNSS) service to detect the polar ionospheric total electron content (TEC) and its variations, particularly under disturbed ionosphere conditions, including different phases of solar activity, the polar day and night alternation, the Weddell Sea anomaly (WSA) as well as geomagnetic storms. In this paper, four different models are utilized to map the ionospheric TEC over the Arctic and Antarctic for about one solar cycle: the polynomial (POLY) model, the generalized trigonometric series function (GTSF) model, the spherical harmonic (SH) model, and the spherical cap harmonic (SCH) model. Compared to other models, the SCH model has the best performance with ±0.8 TECU of residual mean value and 1.5–3.5 TECU of root mean square error. The spatiotemporal distributions and variations of the polar ionospheric TEC are investigated and compared under different ionosphere conditions in the Arctic and Antarctic. The results show that the solar activity significantly affects the TEC variations. During polar days, the ionospheric TEC is more active than it is during polar nights. In polar days over the Antarctic, the maximum value of TEC always appears at night in the Antarctic Peninsula and Weddell Sea area affected by the WSA. In the same year, the ionospheric TEC of the Antarctic has a larger amplitude of annual variation than that of the TEC in the Arctic. In addition, the evolution of the ionization patch during a geomagnetic storm over the Antarctic can be clearly tracked employing the SCH model, which appears to be adequate for mapping the polar TEC, and provides a sound basis for further automatic identification of ionization patches.
Sensors, Volume 20; doi:10.3390/s20020542
Abstract:Nowadays, in modern elite sport, the identification of the best training strategies which are useful in obtaining improvements during competitions requires an accurate measure of the physiologic and biomechanical parameters that affect performance. The goal of this pilot study was to investigate the capabilities of the e-Kayak system, a multichannel digital acquisition system specifically tailored for flatwater sprint kayaking application. e-Kayak allows the synchronous measure of all the parameters involved in kayak propulsion, both dynamic (including forces acting on the paddle and footrest) and kinematic (including stroke frequency, displacement, velocity, acceleration, roll, yaw, and pitch of the boat). After a detailed description of the system, we investigate its capability in supporting coaches to evaluate the performance of elite athletes’ trough-specific measurements. This approach allows for a better understanding of the paddler’s motion and the relevant effects on kayak behavior. The system allows the coach to carry out a wide study of kayak propulsion highlighting, and, at the same time, the occurrences of specific technical flaws in the paddling technique. In order to evaluate the correctness of the measurement results acquired in this pilot study, these results were compared with others which are available in the literature and which were obtained from subjects with similar characteristics.
Sensors, Volume 20; doi:10.3390/s20020541
Abstract:Disk-shaped torque sensors are widely used in robotic joints and wheel driving. However, in terms of conventional spoke-type geometries, there is always a trade-off between sensitivity and stiffness, because their strain exposure depends upon a bending deformation mode which causes strain nonuniformity. This paper presents a lever-type method of strain exposure that performs a uniaxial tension and compression deformation mode to optimize the strain uniformity and improve the trade-off. Moreover, on the basis of this approach, the proposed disk F-shaped torque sensor enjoys has axial thinness, easy installation of strain gauges and flexible customization. The simulation and experimental results have validated the basic design idea.
Sensors, Volume 20; doi:10.3390/s20020543
Abstract:This paper describes a low-cost, robust, and accurate remote eye-tracking system that uses an industrial prototype smartphone with integrated infrared illumination and camera. Numerous studies have demonstrated the beneficial use of eye-tracking in domains such as neurological and neuropsychiatric testing, advertising evaluation, pilot training, and automotive safety. Remote eye-tracking on a smartphone could enable the significant growth in the deployment of applications in these domains. Our system uses a 3D gaze-estimation model that enables accurate point-of-gaze (PoG) estimation with free head and device motion. To accurately determine the input eye features (pupil center and corneal reflections), the system uses Convolutional Neural Networks (CNNs) together with a novel center-of-mass output layer. The use of CNNs improves the system’s robustness to the significant variability in the appearance of eye-images found in handheld eye trackers. The system was tested with 8 subjects with the device free to move in their hands and produced a gaze bias of 0.72°. Our hybrid approach that uses artificial illumination, a 3D gaze-estimation model, and a CNN feature extractor achieved an accuracy that is significantly (400%) better than current eye-tracking systems on smartphones that use natural illumination and machine-learning techniques to estimate the PoG.
Sensors, Volume 20; doi:10.3390/s20020544
Abstract:In China, traditional techniques for measuring structural subsidence cannot keep pace with the rapid development of critical national infrastructure such as the growing network of high-speed railways. Traditional monitoring methods using leveling instruments are inefficient and time consuming when monitoring structures like bridges and tunnels. Thus, a fast, economical, and more accurate and precise way to survey building subsidence is urgently needed to address this problem. This paper introduces a new close-range photogrammetry technique that deploys a fixed camera with tilt compensator to measure changes in height over small areas. A barcode subsidence mark that can be identified automatically during digital image processing replaces the leveling points used in traditional methods. Four experiments at different locations verified that results from the new method were stable and consistent with total station measurements. This approach is simple, inexpensive, and produces accurate and precise results as our evaluation results show.
Sensors, Volume 20; doi:10.3390/s20020528
Abstract:Gesture spotting is an essential task for recognizing finger gestures used to control in-car touchless interfaces. Automated methods to achieve this task require to detect video segments where gestures are observed, to discard natural behaviors of users’ hands that may look as target gestures, and be able to work online. In this paper, we address these challenges with a recurrent neural architecture for online finger gesture spotting. We propose a multi-stream network merging hand and hand-location features, which help to discriminate target gestures from natural movements of the hand, since these may not happen in the same 3D spatial location. Our multi-stream recurrent neural network (RNN) recurrently learns semantic information, allowing to spot gestures online in long untrimmed video sequences. In order to validate our method, we collect a finger gesture dataset in an in-vehicle scenario of an autonomous car. 226 videos with more than 2100 continuous instances were captured with a depth sensor. On this dataset, our gesture spotting approach outperforms state-of-the-art methods with an improvement of about 10% and 15% of recall and precision, respectively. Furthermore, we demonstrated that by combining with an existing gesture classifier (a 3D Convolutional Neural Network), our proposal achieves better performance than previous hand gesture recognition methods.
Sensors, Volume 20; doi:10.3390/s20020529
Abstract:In recent years, we have seen significant interest in the use of permanently deployed resident robotic vehicles for commercial inspection, maintenance and repair (IMR) activities. This paper presents a concept and demonstration, through offshore trials, of a low-cost, low-maintenance, navigational marker that can eliminate drift in vehicle INS solution when the vehicle is close to the IMR target. The subsea localisation marker system is fixed on location on the resident field asset and is used in on-vehicle machine vision algorithms for pose estimation and facilitation of a high-resolution world coordinate frame registration with a high refresh rate. This paper presents evaluation of the system during trials in the North Atlantic Ocean during January 2019. System performances and propagation of position error is inspected and estimated, and the effect of intermittent visual based position update to Kalman filter and onboard INS solution is discussed. The paper presents experimental results of the commercial state-of-the-art inertial navigation system operating in the pure inertial mode for comparison.
Sensors, Volume 20; doi:10.3390/s20020530
Abstract:Open-ended coaxial probes can be used as tissue characterization devices. However, the technique suffers from a high error rate. To improve this technology, there is a need to decrease the measurement error which is reported to be more than 30% for an in vivo measurement setting. This work investigates the machine learning (ML) algorithms’ ability to decrease the measurement error of open-ended coaxial probe techniques to enable tissue characterization devices. To explore the potential of this technique as a tissue characterization device, performances of multiclass ML algorithms on collected in vivo rat hepatic tissue and phantom dielectric property data were evaluated. Phantoms were used for investigating the potential of proliferating the data set due to difficulty of in vivo data collection from tissues. The dielectric property measurements were collected from 16 rats with hepatic anomalies, 8 rats with healthy hepatic tissues, and in house phantoms. Three ML algorithms, k-nearest neighbors (kNN), logistic regression (LR), and random forests (RF) were used to classify the collected data. The best performance for the classification of hepatic tissues was obtained with 76% accuracy using the LR algorithm. The LR algorithm performed classification with over 98% accuracy within the phantom data and the model generalized to in vivo dielectric property data with 48% accuracy. These findings indicate first, linear models, such as logistic regression, perform better on dielectric property data sets. Second, ML models fitted to the data collected from phantom materials can partly generalize to in vivo dielectric property data due to the discrepancy between dielectric property variability.
Sensors, Volume 20; doi:10.3390/s20020531
Abstract:Lower back pain is an extremely common health problem and globally causes more disability than any other condition. Among other rehabilitation approaches, back schools are interventions comprising both an educational component and exercises. Normally, the main outcome evaluated is pain reduction. The aim of this study was to evaluate not only the efficacy of back school therapy in reducing pain, but also the functional improvement. Patients with lower back pain were clinically and functionally evaluated; in particular, the timed “up and go” test with inertial movement sensor was studied before and after back school therapy. Forty-four patients completed the program, and the results showed not only a reduction of pain, but also an improvement in several parameters of the timed up and go test, especially in temporal parameters (namely duration and velocity). The application of the inertial sensor measurement in evaluating functional aspects seems to be useful and promising in assessing the aspects that are not strictly correlated to the specific pathology, as well as in rehabilitation management.
Sensors, Volume 20; doi:10.3390/s20020532
Abstract:In core computer vision tasks, we have witnessed significant advances in object detection, localisation and tracking. However, there are currently no methods to detect, localize and track objects in road environments, and taking into account real-time constraints. In this paper, our objective is to develop a deep learning multi object detection and tracking technique applied to road smart mobility. Firstly, we propose an effective detector-based on YOLOv3 which we adapt to our context. Subsequently, to localize successfully the detected objects, we put forward an adaptive method aiming to extract 3D information, i.e., depth maps. To do so, a comparative study is carried out taking into account two approaches: Monodepth2 for monocular vision and MADNEt for stereoscopic vision. These approaches are then evaluated over datasets containing depth information in order to discern the best solution that performs better in real-time conditions. Object tracking is necessary in order to mitigate the risks of collisions. Unlike traditional tracking approaches which require target initialization beforehand, our approach consists of using information from object detection and distance estimation to initialize targets and to track them later. Expressly, we propose here to improve SORT approach for 3D object tracking. We introduce an extended Kalman filter to better estimate the position of objects. Extensive experiments carried out on KITTI dataset prove that our proposal outperforms state-of-the-art approches.