Search

Ultrasound images are corrupted by a type of signal-dependent noise, called speckle, difficult to remove or attenuate with the classical denoising methods. On the contrary, structural Magnetic Resonance Imaging (MRI) is usually a high resolution low noise image modality that involves complex and expensive equipment and long acquisition times. Herein, a deep learning-based pipeline for speckle removal in B-mode ultrasound medical images, based on cross modality transfer learning, is proposed. The architecture of the system is based on a pix2pix Generative Adversarial Network (GAN), $D$ , able to denoise real B-mode ultrasound images by generating synthetic MRI-like versions by an image-to-image translation manner. The GAN $D$ was trained using two classes of image pairs: i) a set consisting of authentic MRI images paired with synthetic ultrasound images generated through a dedicated ultrasound simulator based on another GAN, $S$ , designed specifically for this purpose, and ii) a set comprising natural images paired with their corresponding noisy counterparts corrupted by Rayleigh noise. The denoising GAN proposed in this study demonstrates effective removal of speckle noise from B-mode ultrasound images. It successfully preserves the integrity of anatomical structures and avoids reconstruction artifacts, producing outputs that closely resemble typical MRI images. Comparative tests against other state-of-the-art methods reveal superior performance of the proposed denoising strategy across various reconstruction quality metrics.

Over the last decade several machine learning (ML) based data-driven approaches have been used for Electromyography (EMG) based control of prosthetic hands. However, the performance of EMG-based frameworks can be affected by: i) the onset of fatigue due to long data collection sessions, ii) musculoskeletal differences between individuals, and iii) sensor position drifting between different sessions with the same user. To evaluate these aspects, in this work, we compare the performance of EMG-based hand gesture decoding models developed using three approaches. This comparison allows for future works in EMG-based Human-Machine Interfaces development to make more informed ML decisions. First, we trained from scratch a Transformer-based architecture, called Temporal Multi-Channel Vision Transformer (TMC-ViT). For our second approach, we utilized a pre-trained and fine-tuned TMC-ViT model (a transfer learning approach). Finally, for our third approach, we developed a Prototypical Network (a few-shot learning approach). The models are trained in a subject-specific and subject-generic manner for eight subjects and validated employing the 10-fold cross-validation procedure. This study shows that training a deep learning decoding model from scratch in a subject-specific manner leads to higher decoding accuracies when a larger dataset is available. For smaller datasets, subject-generic models, or inter-session models, the few-shot learning approach produces more robust results with better performance, and is more suited to applications where long data collection scenarios are not possible, or where multiple users are intended for the interface. Our findings show that the few-shot learning approach can outperform training a model from scratch in different scenarios.

6G networks are expected to use the terahertz (THz) frequency spectrum in some way. However, relatively little is known about the transmission channel in this part of the spectrum. In this article, we propose a novel and accurate channel loss model that considers both molecular and water vapor continuum absorptions for THz networks based on the frequency range between 100 GHz and 600 GHz. The proposed channel model assumes that the atmospheric absorption is accurately accounted for by the molecular absorption coefficient and the water vapor continuum absorption coefficient. The new model is based on equations developed to accurately match the channel response given by a spectroscopic database. This makes the channel model robust and useful for evaluating the performance of THz networks. The model is validated against a spectroscopic database defined as a benchmark. The performance of the new channel loss model is evaluated against different models, including several error metrics. Numerical results show the new channel model is as accurate as the spectroscopic database by correctly reproducing the provided experimental dataset. Therefore, the proposed channel model is a reliable, robust and simple tool that can be successfully used to carry out performance evaluation of THz networks with accuracy.

Depressive disorders are a leading cause of morbility and disability in the working population worldwide. Psychiatric assessment and treatment of depressive disorders may be improved by using objective behavioral and physiological biomarkers. In this work we present a psychiatry telemedicine platform where two important biomarkers of depression, eye-blinking rate and heart rate variability, are computed from the video stream and shown to the clinician in real time during teleconsultation. In order to validate our video processing methods, we use a public annotated dataset with image and photoplethysmography information, complemented by us with eye blinking information. For the eye-blinking detection, we obtained 94%±16% precision in the best scenario. For the estimation of %LF and LF/HF, the mean errors obtained are 16.9NU and 1.1, respectively, outperforming the state of the art. These results show the potential of the proposed telemedicine platform.

The optimal power flow (OPF) problem is a widely studied subject in the literature that has been solved through classical and metaheuristic optimization techniques. Nowadays, significant advances in computational resources and commercial optimization solvers allow solving complex optimization problems by combining the best of both worlds in approaches that are known as matheuristics, however, in order to solve the OPF problem, matheuristic approaches have been little explored. In this regard, this paper presents a novel Variable Neighborhood Descent (VND) matheuristic approach to solve the OPF problem for large-scale systems. The proposed algorithm combines the classic OPF model and the VND heuristic algorithm. The OPF problem is formulated as a mixed-integer nonlinear programming (MINLP) model, in which the objective function aims to minimize the fuel generation costs, subject to the physical and operational constraints of the power system. The integer variables of this MINLP model represent the control of taps positions of the on-load tap changers and the reactive shunt compensation equipment. To validate the proposed methodology, 17 power systems of specialized literature were tested with sizes from 14 to 4661 buses, and the obtained solutions are compared with the solutions provided by the commercial optimization solver Knitro. Results show the superiority of the proposed matheuristic algorithm compared with Knitro to solve the MINLP-OPF model for large-scale systems.

Given the necessity of developing more efficient electric distribution systems (EDSs) and providing a continuous energy service for active and passive users, distribution system planners are constantly seeking for more robust planning strategies that can address the complexities of large-scale EDSs. In this regard, the proposed work investigates the implementation of a novel strategy that is based on two stages to tackle the short-term planning problem in large-scale EDSs. In the first stage, a system reduction technique is developed to remove all non-desired buses and circuits from the original large-scale EDS, while in the second stage an optimization model is formulated to represent the EDS expansion planning problem. The planning stage is designed using a multi-period formulation, which defines, in the most cost-effective way, actions such as the allocation of voltage regulators (VRs) and capacitor banks (CBs) to improve the EDS operation, considering the demand growth and new requests for distributed generation (DG) connections. The objective function of this optimization model minimizes the expected cost of energy purchased from the market and charges due to carbon emission taxes, while the energy purchased from DG developers is maximized. For simulation purposes, a real 1080-bus EDS is reduced to an equivalent 54-bus system and implementing the developed optimization model, results show that a set of planning actions can be obtained to improve the EDS operation. These obtained planning actions are projected to the 1080-bus EDS and using an optimal power flow tool, the accuracy of the proposed planning strategy is estimated.

In this manuscript, a method for designing Takagi-Sugeno (T-S) fuzzy discrete-time regulators based on linear matrix inequalities (LMIs) is proposed to control the variation of the knee joint angle movement of paraplegic patients through electrical stimulation. A simple method for discretizing nonlinear systems described by T-S fuzzy models is used. The control strategy is applied for a paraplegic volunteer and a healthy one. The results and analysis show that the controlled system attended the design specifications for small values of the sample time considered for the discretization.

Machine learning algorithms have been applied to numerous transcript datasets to identify Long non-coding RNAs (lncRNAs). Nevertheless, before these algorithms are applied to RNA data, features must be extracted from the original sequences. As many of these features can be redundant or irrelevant, the predictive performance of the algorithms can be improved by performing feature selection. However, the most current approaches usually select features independently, ignoring possible relations. In this paper, we propose a new model, which identifies the best subsets, removing unnecessary, irrelevant, and redundant predictive features, taking the importance of their co-occurrence into account. The proposed model is based on decomposing solutions and is called $k$ -rounds of decomposition features. In this model, the least relevant features are suppressed according to their contribution to a classification task. To evaluate our proposal, we extract from 5 plant species datasets, a set of features based on sequence structures, using GC content, k-mer (1-6), sequence length, and Open Reading Frame. Next, we apply 5 metaheuristics approaches (Genetic Algorithm, ($\mu + \lambda $ ) Evolutionary Algorithm, Artificial Bee Colony, Ant Colony Optimization, and Particle Swarm Optimization) to select the best feature subsets. The main contribution of this work was to include in each metaheuristic a decomposition model that uses round and voting scheme. To investigate its relevance, we select the REPTree classifier to assess the predictive capacity of each subset of features selected in 8 plant species. We identified that the inclusion of the proposed decomposition model significantly reduces the dimensions of the datasets and improves predictive performance, regardless of the metaheuristic. Furthermore, the resulting pipeline has been compared with five approaches in the literature, for lncRNA, when it also showed superior predictive performance. Finally, this study generated a new pipeline to find a minimum number of features in lncRNAs and biological sequences.

Transmission systems are the basis of the communication systems process. This paper on the operationalization of its stages is little or rarely updated. Currently, interests are focused on global discussions on topics such as 5G networks, different types of modulation, data transfer rates, and the possibility of services focused mainly on offering quality to the end user. As technology changes, operating companies invest hundreds of millions in infrastructure and equipment, but almost always, the entire operating system from previous generations remains operative for years and does not receive proper attention, development of technologies, or improvements in the control of its operational efficiency, mainly from the point of view of automation technology upgrades. Therefore, it is important to reassess and optimize this infrastructure and its modus operandi in order to guarantee an extension of the useful life and to provide an economy to the operators. The main aim of the paper is to discuss the main aspects of a multipoint transmission system through a graphic technique called leveling diagram. It was applied based on a real scenario, in the city of Curitiba, a metropolis with more than two million inhabitants located in the Southern region of Brazil. The combination of this graphical technique and numerical analysis resulted in new modeling. Therefore, the main contribution of this paper is to provide a new alternative of visual analysis for transmission systems.

In this paper, new analytical formalisms to evaluate the packet throughput of multiservice multirate slotted ALOHA optical code-division multiple-access (OCDMA) networks are proposed. The proposed formalisms can be successfully applied to 1-D and 2-D OCDMA networks with any number of user classes in the system. The bit error rate (BER) and packet correct probability expressions are derived, considering the multiple-access interference as binomially distributed. Packet throughput expressions, on the other hand, are derived considering Poisson, binomial, and Markov chain approaches for the composite packet arrivals distributions, with the latter defined as benchmark. A throughput performance evaluation is carried out for two distinct user code sequences separately, namely, 1-D and 2-D multiweight multilength optical orthogonal code (MWML-OOC). Numerical results show that the Poisson approach underestimates the throughput performance in unacceptable levels and incorrectly predicts the number of successfully received packets for most offered load values even in favorable conditions, such as for the 2-D MWML-OOC OCDMA network with a considerably large number of simultaneous users. On the other hand, the binomial approach proved to be more straightforward, computationally more efficient, and just as accurate as the Markov chain approach.