Search

Based on orbital angular momentum (OAM) properties of Laguerre-Gaussian beams LG(p,ℓ), a robust optical encoding model for efficient data transmission applications is designed. This paper presents an optical encoding model based on an intensity profile generated by a coherent superposition of two OAM-carrying Laguerre-Gaussian modes and a machine learning detection method. In the encoding process, the intensity profile for data encoding is generated based on the selection of p and ℓ indices, while the decoding process is performed using a support vector machine (SVM) algorithm. Two different decoding models based on an SVM algorithm are tested to verify the robustness of the optical encoding model, finding a BER =10-9 for 10.2 dB of signal-to-noise ratio in one of the SVM models.

Accurate dynamic model is critical for collaborative robots to achieve satisfactory performance in model-based control or other applications such as dynamic simulation and external torque estimation. Such dynamic models are frequently restricted to identifying important system parameters and compensating for nonlinear terms. Friction, as a primary nonlinear element in robotics, has a significant impact on model accuracy. In this paper, a reliable dynamic friction model, which incorporates the influence of temperature fluctuation on the robot joint friction, is utilized to increase the accuracy of identified dynamic parameters. First, robot joint friction is investigated. Extensive test series are performed in the full velocity operating range at temperatures ranging from 19 °C to 51 °C to investigate friction dependency on joint module temperature. Then, dynamic parameter identification is performed using an inverse dynamics identification model and weighted least squares regression constrained to the feasible space, guaranteeing the optimal solution. Using the identified friction model parameters, the friction torque is computed for measured robot joint velocity and temperature. Friction torque is subtracted from the measured torque, and a non-friction torque is used to identify dynamic parameters. Finally, the proposed notion is validated experimentally on the Indy7 collaborative robot manipulator, and the results show that the dynamic model with parameters identified using the proposed method outperforms the dynamic model with parameters identified using the conventional method in tracking measured torque, with a relative improvement of up to 70.37%.

The quadrature angular diversity aperture (QADA) receiver, consisting of a quadrant photodiode (QPD) and an aperture placed above the QPD, has been investigated for pose estimation for visible light systems. Current work on pose estimation for the QADA receiver uses classical camera sensor algorithms well known in computer vision. To this end, however, the light spot center first has to be obtained based on the RSS. However, this is less straightforward than for camera sensors, as in contrast to such sensors where the relationships are linear, the RSS output from the QADA is a non-linear function of the light spot position. When applying closed form solutions or iterative methods for cameras on a QADA, the non-linearity will degrade their performance. Furthermore, since in practice the aperture is not always perfectly aligned with the QPD, a procedure to calibrate the receiver is needed. Current work on calibration requires additional sophisticated equipment to measure the pose during calibration, which increases the difficulty of implementation. In this paper, we target the above problems for pose estimation and calibration of the QADA receiver. To this end, we first study the effect of the strategy of differencing and normalization on the probability density function (PDF), a commonly applied strategy for the QPD's robustness against RSS variation, and it is shown that the applied strategy results in a complex PDF, which makes an effective and efficient estimation hard to achieve. Therefore, we derive an approximated PDF in a simple closed-form, based on which the calibration and the pose estimation algorithms using the least squares principle are proposed. The proposed calibration does not require any information about the pose of the receiver and is robust to variation of the received power and imperfect knowledge of the radiation pattern of the LED, making it easy to implement. We also derive the corresponding Cramér-Rao lower bound on the misalignment to benchmark the performance of the misalignment and to serve as an indicator to determine the required signal-to-noise ratio (SNR) or number of LEDs to obtain a desired accuracy. The calibration and pose estimation are evaluated by means of a Monte Carlo simulation. Computer simulations show that this theoretical bound is close to the RMSE of the proposed estimator and that the proposed pose estimator outperforms the PnP algorithm.

This paper presents a transfer domain strategy to tackle the limitations of low-resolution thermal sensors and generate higher-resolution images of reasonable quality. The proposed technique employs a CycleGAN architecture and uses a ResNet as an encoder in the generator along with an attention module and a novel loss function. The network is trained on a multi-resolution thermal image dataset acquired with three different thermal sensors. Results report better performance benchmarking results on the 2nd CVPR-PBVS-2021 thermal image super-resolution challenge than state-of-the-art methods. The code of this work is available online., Competing Interests: The authors declare no conflicts of interest.

Recent engineering and neuroscience applications have led to the development of brain-computer interface (BCI) systems that improve the quality of life of people with motor disabilities. In the same area, a significant number of studies have been conducted in identifying or classifying upper-limb movement intentions. On the contrary, few works have been concerned with movement intention identification for lower limbs. Notwithstanding, lower-limb neurorehabilitation is a major topic in medical settings, as some people suffer from mobility problems in their lower limbs, such as those diagnosed with neurodegenerative disorders, such as multiple sclerosis, and people with hemiplegia or quadriplegia. Particularly, the conventional pattern recognition (PR) systems are one of the most suitable computational tools for electroencephalography (EEG) signal analysis as the explicit knowledge of the features involved in the PR process itself is crucial for both improving signal classification performance and providing more interpretability. In this regard, there is a real need for outline and comparative studies gathering benchmark and state-of-art PR techniques that allow for a deeper understanding thereof and a proper selection of a specific technique. This study conducted a topical overview of specialized papers covering lower-limb motor task identification through PR-based BCI/EEG signal analysis systems. To do so, we first established search terms and inclusion and exclusion criteria to find the most relevant papers on the subject. As a result, we identified the 22 most relevant papers. Next, we reviewed their experimental methodologies for recording EEG signals during the execution of lower limb tasks. In addition, we review the algorithms used in the preprocessing, feature extraction, and classification stages. Finally, we compared all the algorithms and determined which of them are the most suitable in terms of accuracy.

Structural health monitoring for offshore wind turbine foundations is paramount to the further development of offshore fixed wind farms. At present time there are a limited number of foundation designs, the jacket type being the preferred one in large water depths. In this work, a jacket-type foundation damage diagnosis strategy is stated. Normally, most or all the available data are of regular operation, thus methods that focus on the data leading to failures end up using only a small subset of the available data. Furthermore, when there is no historical precedent of a type of fault, those methods cannot be used. In addition, offshore wind turbines work under a wide variety of environmental conditions and regions of operation involving unknown input excitation given by the wind and waves. Taking into account the aforementioned difficulties, the stated strategy in this work is based on an autoencoder neural network model and its contribution is two-fold: (i) the proposed strategy is based only on healthy data, and (ii) it works under different operating and environmental conditions based only on the output vibration data gathered by accelerometer sensors. The proposed strategy has been tested through experimental laboratory tests on a scaled model.

This paper presents a solution to support service discovery for edge choreography based distributed embedded systems. The Internet of Things (IoT) edge architectural layer is composed of Raspberry Pi machines. Each machine hosts different services organized based on the choreography collaborative paradigm. The solution adds to the choreography middleware three messages passing models to be coherent and compatible with current IoT messaging protocols. It is aimed to support blind hot plugging of new machines and help with service load balance. The discovery mechanism is implemented as a broker service and supports regular expressions (Regex) in message scope to discern both publishing patterns offered by data providers and client services necessities. Results compare Control Process Unit (CPU) usage in a request-response and datacentric configuration and analyze both regex interpreter latency times compared with a traditional message structure as well as its impact on CPU and memory consumption.

Current CNN-based stereo depth estimation models can barely run under real-time constraints on embedded graphic processing unit (GPU) devices. Moreover, state-of-the-art evaluations usually do not consider model optimization techniques, being that it is unknown what is the current potential on embedded GPU devices. In this work, we evaluate two state-of-the-art models on three different embedded GPU devices, with and without optimization methods, presenting performance results that illustrate the actual capabilities of embedded GPU devices for stereo depth estimation. More importantly, based on our evaluation, we propose the use of a U-Net like architecture for postprocessing the cost-volume, instead of a typical sequence of 3D convolutions, drastically augmenting the runtime speed of current models. In our experiments, we achieve real-time inference speed, in the range of 5-32 ms, for 1216 × 368 input stereo images on the Jetson TX2, Jetson Xavier, and Jetson Nano embedded devices.

This article presents a comprehensive study of human physiology to determine the impact of body mass index (BMI) on human gait. The approach followed in this study consists of a mathematical model based on the centre of mass of the human body, the inertia of a person in motion and the human gait speed. Moreover, the study includes the representation of a building using graph theory and emulates the presence of a person inside the building when an emergency takes place. The optimal evacuation route is obtained using the breadth-first search (BFS) algorithm, and the evacuation time prediction is calculated using a Gaussian process model. Then, the risk of the building is quantified by using a non-sequential Monte Carlo simulation. The results open up a new horizon for developing a more realistic model for the assessment of civil safety.

In this work, we explore the use of images from different spectral bands to classify defects in melamine faced panels, which could appear through the production process. Through experimental evaluation, we evaluate the use of images from the visible (VS), near-infrared (NIR), and long wavelength infrared (LWIR), to classify the defects using a feature descriptor learning approach together with a support vector machine classifier. Two descriptors were evaluated, Extended Local Binary Patterns (E-LBP) and SURF using a Bag of Words (BoW) representation. The evaluation was carried on with an image set obtained during this work, which contained five different defect categories that currently occurs in the industry. Results show that using images from beyond the visual spectrum helps to improve classification performance in contrast with a single visible spectrum solution.

Understanding tourism related behavior and traveling patterns is an essential element of transportation system planning and tourism management at tourism destinations. Traditionally, tourism market segmentation is conducted to recognize tourist's profiles for which personalized services can be provided. Today, the availability of wearable sensors, such as smartphones, holds the potential to tackle data collection problems of paper-based surveys and deliver relevant mobility data in a timely and cost-effective way. In this paper, we develop and implement a hierarchical clustering approach for smartphone geo-localized data to detect meaningful tourism related market segments. For these segments, we provide detailed insights into their characteristics and related mobility behavior. The applicability of the proposed approach is demonstrated on a use case in the Province of Zeeland in the Netherlands. We collected data from 1505 users during five months using the Zeeland app. The proposed approach resulted in two major clusters and four sub-clusters which we were able to interpret based on their spatio-temporal patterns and the recurrence of their visiting patterns to the region.

Multi-spectral RGB-NIR sensors have become ubiquitous in recent years. These sensors allow the visible and near-infrared spectral bands of a given scene to be captured at the same time. With such cameras, the acquired imagery has a compromised RGB color representation due to near-infrared bands (700⁻1100 nm) cross-talking with the visible bands (400⁻700 nm). This paper proposes two deep learning-based architectures to recover the full RGB color images, thus removing the NIR information from the visible bands. The proposed approaches directly restore the high-resolution RGB image by means of convolutional neural networks. They are evaluated with several outdoor images; both architectures reach a similar performance when evaluated in different scenarios and using different similarity metrics. Both of them improve the state of the art approaches.

Due to the massive insertion of embedded cameras in a wide variety of devices and the generalized use of LED lamps, Optical Camera Communication (OCC) has been proposed as a practical solution for future Internet of Things (IoT) and smart cities applications. Influence of mobility, weather conditions, solar radiation interference, and external light sources over Visible Light Communication (VLC) schemes have been addressed in previous works. Some authors have studied the spatial intersymbol interference from close emitters within an OCC system; however, it has not been characterized or measured in function of the different transmitted wavelengths. In this work, this interference has been experimentally characterized and the Normalized Power Signal to Interference Ratio (NPSIR) for easily determining the interference in other implementations, independently of the selected system devices, has been also proposed. A set of experiments in a darkroom, working with RGB multi-LED transmitters and a general purpose camera, were performed in order to obtain the NPSIR values and to validate the deduced equations for 2D pixel representation of real distances. These parameters were used in the simulation of a wireless sensor network scenario in a small office, where the Bit Error Rate (BER) of the communication link was calculated. The experiments show that the interference of other close emitters in terms of the distance and the used wavelength can be easily determined with the NPSIR. Finally, the simulation validates the applicability of the deduced equations for scaling the initial results into real scenarios., Competing Interests: The authors declare no conflict of interest. The founding sponsors had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, and in the decision to publish the results.

This paper presents a novel CNN-based architecture, referred to as Q-Net, to learn local feature descriptors that are useful for matching image patches from two different spectral bands. Given correctly matched and non-matching cross-spectral image pairs, a quadruplet network is trained to map input image patches to a common Euclidean space, regardless of the input spectral band. Our approach is inspired by the recent success of triplet networks in the visible spectrum, but adapted for cross-spectral scenarios, where, for each matching pair, there are always two possible non-matching patches: one for each spectrum. Experimental evaluations on a public cross-spectral VIS-NIR dataset shows that the proposed approach improves the state-of-the-art. Moreover, the proposed technique can also be used in mono-spectral settings, obtaining a similar performance to triplet network descriptors, but requiring less training data.

Sustainable mobility and smart mobility management play important roles in achieving smart cities' goals. In this context we investigate the role of smartphones as mobility behavior sensors and evaluate the responsivity of different attitudinal profiles towards personalized route suggestion incentives delivered via mobile phones. The empirical results are based on mobile sensed data collected from more than 3400 people's real life over a period of six months. The findings show which user profiles are most likely to accept such incentives and how likely they are to result in more sustainable mode choices. In addition we provide insights into tendencies towards accepting more sustainable route options for different trip purposes and illustrate smart city platform potential (for collection of mobility behavior data and delivery of incentives) as a tool for development of personalized mobility management campaigns and policies.

This paper evaluates different wavelet-based cross-spectral image fusion strategies adopted to merge visible and infrared images. The objective is to find the best setup independently of the evaluation metric used to measure the performance. Quantitative performance results are obtained with state of the art approaches together with adaptations proposed in the current work. The options evaluated in the current work result from the combination of different setups in the wavelet image decomposition stage together with different fusion strategies for the final merging stage that generates the resulting representation. Most of the approaches evaluate results according to the application for which they are intended for. Sometimes a human observer is selected to judge the quality of the obtained results. In the current work, quantitative values are considered in order to find correlations between setups and performance of obtained results; these correlations can be used to define a criteria for selecting the best fusion strategy for a given pair of cross-spectral images. The whole procedure is evaluated with a large set of correctly registered visible and infrared image pairs, including both Near InfraRed (NIR) and Long Wave InfraRed (LWIR).

This manuscript evaluates the behavior of classical feature point descriptors when they are used in images from long-wave infrared spectral band and compare them with the results obtained in the visible spectrum. Robustness to changes in rotation, scaling, blur, and additive noise are analyzed using a state of the art framework. Experimental results using a cross-spectral outdoor image data set are presented and conclusions from these experiments are given.