RESUMEN

Nuclear fusion is a potential source of energy that could supply the growing needs of the world population for millions of years. Several experimental thermonuclear fusion devices try to understand and control the nuclear fusion process. A very interesting diagnostic called Thomson scattering (TS) is performed in the Spanish fusion device TJ-II. This diagnostic takes images to measure the temperature and density profiles of the plasma, which is heated to very high temperatures to produce fusion plasma. Each image captures spectra of laser light scattered by the plasma under different conditions. Unfortunately, some images are corrupted by noise called stray light that affects the measurement of the profiles. In this work, we propose the use of deep learning models to reduce the stray light that appears in the diagnostic. The proposed approach utilizes a Pix2Pix neural network, which is an image-to-image translation based on a generative adversarial network (GAN). This network learns to translateimages affected by stray light to images without stray light. This allows for the effective removal of the noise that affects the measurements of the TS diagnostic, avoiding the need for manual image processing adjustments. The proposed method shows a better performance, reducing the noise up to 98% inimages, which surpassesprevious works that obtained 85% for the validation dataset.

RESUMEN

This paper presents the design and implementation of a spherical robot with an internal mechanism based on a pendulum. The design is based on significant improvements made, including an electronics upgrade, to a previous robot prototype developed in our laboratory. Such modifications do not significantly impact its corresponding simulation model previously developed in CoppeliaSim, so it can be used with minor modifications. The robot is incorporated into a real test platform designed and built for this purpose. As part of the incorporation of the robot into the platform, software codes are made to detect its position and orientation, using the system SwisTrack, to control its position and speed. This implementation allows successful testing of control algorithms previously developed by the authors for other robots such as Villela, the Integral Proportional Controller, and Reinforcement Learning.

RESUMEN

Recently, the scientific community has placed great emphasis on the recognition of human activity, especially in the area of health and care for the elderly. There are already practical applications of activity recognition and unusual conditions that use body sensors such as wrist-worn devices or neck pendants. These relatively simple devices may be prone to errors, might be uncomfortable to wear, might be forgotten or not worn, and are unable to detect more subtle conditions such as incorrect postures. Therefore, other proposed methods are based on the use of images and videos to carry out human activity recognition, even in open spaces and with multiple people. However, the resulting increase in the size and complexity involved when using image data requires the use of the most recent advanced machine learning and deep learning techniques. This paper presents an approach based on deep learning with attention to the recognition of activities from multiple frames. Feature extraction is performed by estimating the pose of the human skeleton, and classification is performed using a neural network based on Bidirectional Encoder Representation of Transformers (BERT). This algorithm was trained with the UP-Fall public dataset, generating more balanced artificial data with a Generative Adversarial Neural network (GAN), and evaluated with real data, outperforming the results of other activity recognition methods using the same dataset.

Asunto(s)

RESUMEN

Nowadays, there is a broad range of methods for detecting and evaluating executive dysfunction ranging from clinical interview to neuropsychological evaluation. Nevertheless, a critical issue of these assessments is the lack of correspondence of the neuropsychological test's results with real-world functioning. This paper proposes serious games as a new framework to improve the neuropsychological assessment of real-world functioning. We briefly discuss the contribution and limitations of current methods of evaluation of executive dysfunction (paper-and-pencil tests, naturalistic observation methods, and Information and Communications Technologies) to inform on daily life functioning. Then, we analyze what are the limitations of these methods to predict real-world performance: (1) A lack of appropriate instruments to investigate the complexity of real-world functioning, (2) the vast majority of neuropsychological tests assess well-structured tasks, and (3) measurement of behaviors are based on simplistic data collection and statistical analysis. This work shows how serious games offer an opportunity to develop more efficient tools to detect executive dysfunction in everyday life contexts. Serious games provide meaningful narrative stories and virtual or real environments that immerse the user in natural and social environments with social interactions. In those highly interactive game environments, the player needs to adapt his/her behavioral performance to novel and ill-structured tasks which are suited for collecting user interaction evidence. Serious games offer a novel opportunity to develop better tools to improve diagnosis of the executive dysfunction in everyday life contexts. However, more research is still needed to implement serious games in everyday clinical practice.

RESUMEN

This article presents the development of a model of a spherical robot that rolls to move and has a single point of support with the surface. The model was developed in the CoppeliaSim simulator, which is a versatile tool for implementing this kind of experience. The model was tested under several scenarios and control goals (i.e., position control, path-following and formation control) with control strategies such as reinforcement learning, and Villela and IPC algorithms. The results of these approaches were compared using performance indexes to analyze the performance of the model under different scenarios. The model and examples with different control scenarios are available online.

Asunto(s)

RESUMEN

The quality control for fruit maturity inspection is a key issue in fruit packaging and international trade. The quantification of Soluble Solids (SS) in fruits gives a good approximation of the total sugar concentration at the ripe stage, and on the other hand, SS alone or in combination with acidity is highly related to the acceptability of the fruit by consumers. The non-destructive analysis based on Visible (VIS) and Near-Infrared (NIR) spectroscopy has become a popular technique for the assessment of fruit quality. To improve the accuracy of fruit maturity inspection, VIS−NIR spectra models based on machine learning techniques are proposed for the non-destructive evaluation of soluble solids in considering a range of variations associated with varieties of stones fruit species (peach, nectarine, and plum). In this work, we propose a novel approach based on a Convolutional Neural Network (CNN) for the classification of the fruits into species and then a Feedforward Neural Network (FNN) to extract the information of VIS−NIR spectra to estimate the SS content of the fruit associated to several varieties. A classification accuracy of 98.9% was obtained for the CNN classification model and a correlation coefficient of Rc>0.7109 for the SS estimation of the FNN models was obtained. The results reported show the potential of this method for a fast and on-line classification of fruits and estimation of SS concentration.

Asunto(s)

RESUMEN

In recent years, much effort has been devoted to the development of applications capable of detecting different types of human activity. In this field, fall detection is particularly relevant, especially for the elderly. On the one hand, some applications use wearable sensors that are integrated into cell phones, necklaces or smart bracelets to detect sudden movements of the person wearing the device. The main drawback of these types of systems is that these devices must be placed on a person's body. This is a major drawback because they can be uncomfortable, in addition to the fact that these systems cannot be implemented in open spaces and with unfamiliar people. In contrast, other approaches perform activity recognition from video camera images, which have many advantages over the previous ones since the user is not required to wear the sensors. As a result, these applications can be implemented in open spaces and with unknown people. This paper presents a vision-based algorithm for activity recognition. The main contribution of this work is to use human skeleton pose estimation as a feature extraction method for activity detection in video camera images. The use of this method allows the detection of multiple people's activities in the same scene. The algorithm is also capable of classifying multi-frame activities, precisely for those that need more than one frame to be detected. The method is evaluated with the public UP-FALL dataset and compared to similar algorithms using the same dataset.

Asunto(s)

RESUMEN

Scientists and astronomers have attached great importance to the task of discovering new exoplanets, even more so if they are in the habitable zone. To date, more than 4300 exoplanets have been confirmed by NASA, using various discovery techniques, including planetary transits, in addition to the use of various databases provided by space and ground-based telescopes. This article proposes the development of a deep learning system for detecting planetary transits in Kepler Telescope light curves. The approach is based on related work from the literature and enhanced to validation with real light curves. A CNN classification model is trained from a mixture of real and synthetic data. The model is then validated only with unknown real data. The best ratio of synthetic data is determined by the performance of an optimisation technique and a sensitivity analysis. The precision, accuracy and true positive rate of the best model obtained are determined and compared with other similar works. The results demonstrate that the use of synthetic data on the training stage can improve the transit detection performance on real light curves.

Asunto(s)

RESUMEN

Human gait analysis is a standard method used for detecting and diagnosing diseases associated with gait disorders. Wearable technologies, due to their low costs and high portability, are increasingly being used in gait and other medical analyses. This paper evaluates the use of low-cost homemade textile pressure sensors to recognize gait phases. Ten sensors were integrated into stretch pants, achieving an inexpensive and pervasive solution. Nevertheless, such a simple fabrication process leads to significant sensitivity variability among sensors, hindering their adoption in precision-demanding medical applications. To tackle this issue, we evaluated the textile sensors for the classification of gait phases over three machine learning algorithms for time-series signals, namely, random forest (RF), time series forest (TSF), and multi-representation sequence learner (Mr-SEQL). Training and testing signals were generated from participants wearing the sensing pants in a test run under laboratory conditions and from an inertial sensor attached to the same pants for comparison purposes. Moreover, a new annotation method to facilitate the creation of such datasets using an ordinary webcam and a pose detection model is presented, which uses predefined rules for label generation. The results show that textile sensors successfully detect the gait phases with an average precision of 91.2% and 90.5% for RF and TSF, respectively, only 0.8% and 2.3% lower than the same values obtained from the IMU. This situation changes for Mr-SEQL, which achieved a precision of 79% for the textile sensors and 36.8% for the IMU. The overall results show the feasibility of using textile pressure sensors for human gait recognition.

Asunto(s)

RESUMEN

Resumen En el curso de la demencia, la etapa avanzada se caracteriza por un deterioro cognitivo y físico severo, definiéndola como una etapa que incluye profundos déficits de memoria, habilidades verbales mínimas, incapacidad para deambular de forma independiente, incontinencia urinaria y fecal, y necesidad de asistencia para realizar cualquier actividad de la vida diaria básica. El presente reporte tiene por objeto comunicar un caso de una usuaria con 89 años con demencia avanzada que acude a control neurológico en compañía de su familia, quienes solicitan información de cómo mejorar la calidad de vida en esa etapa. Describimos una propuesta desde el enfoque de cuidados paliativos, específicamente la concepción terapéutica activa, como una guía que permita observar a la persona no sólo desde el buen morir, sino también desde la incorporación de una actitud proactiva en función del bienestar. Este enfoque permite facilitar experiencias placenteras, definidas dentro del marco de intervenciones no farmacológicas, las cuales han demostrado en la última década importantes beneficios en personas con demencia avanzada, permitiendo individualizar las estrategias de intervención en esta etapa de la enfermedad.

In the course of dementia, the advanced stage is characterized by severe cognitive and physical impairment, defining it as a stage that includes deep memory deficits, minimal verbal skills, inability to walk independently, need of assistance to perform any basic daily life activity and urinary and fecal incontinence. The aim of this report is to describe a case of a 89-year-old woman with Advanced Dementia who goes to neurological control in the company of her family, who request information on how to improve the quality of life at this stage. We describe a proposal of palliative care approach, specifically the active therapeutic conception, as a guide that allows to observe the person not only from the good dying, but also from the incorporation of a proactive attitude in function of well-being. This approach allows to facilitate pleasurable experiences, defined within the framework of Nonpharmacological intervention, which have shown important benefits in people with advanced dementia in the last decade, allowing the identification of intervention strategies in this stage of the disease.

Asunto(s)

RESUMEN

BACKGROUND: Clinically-evaluated nutraceuticals are candidates for Alzheimer's disease (AD) prevention and treatment. Phase I studies showed biological safety of the nutraceutical BrainUp-10®, while a pilot trial demonstrated efficacy for treatment. Cell studies demonstrated neuroprotection. BrainUp-10® blocks tau self-assembly. Apathy is the most common of behavioral alterations. OBJECTIVE: The aim was to explore efficacy of BrainUp-10® in mitigating cognitive and behavioral symptoms and in providing life quality, in a cohort of Chilean patients with mild to moderate AD. METHODS: The was a multicenter, randomized, double blind, placebo-controlled phase II clinical study in mild to moderate AD patients treated with BrainUp-10® daily, while controls received a placebo. Primary endpoint was Apathy (AES scale), while secondary endpoints included Mini-Mental State Examination (MMSE), Trail Making Test (TMT A and TMT B), and Neuropsychiatry Index (NPI). AD blood biomarkers were analyzed. Laboratory tests were applied to all subjects. RESULTS: 82 patients were enrolled. The MMSE score improved significantly at week 24 compared to baseline with tendency to increase, which met the pre-defined superiority criteria. NPI scores improved, the same for caregiver distress at 12th week (p = 0.0557), and the alimentary response (p = 0.0333). Apathy tests showed a statistically significant decrease in group treated with BrainUp-10®, with p = 0.0321 at week 4 and p = 0.0480 at week 12 treatment. A marked decrease in homocysteine was shown with BrainUp-10® (p = 0.0222). CONCLUSION: Data show that BrainUp-10® produces a statistically significant improvement in apathy, ameliorating neuropsychiatric distress of patients. There were no compound-related adverse events. BrainUp-10® technology may enable patients to receive the benefits for their cognitive and behavioral problems.

Asunto(s)

RESUMEN

Across Latin American and Caribbean countries (LACs), the fight against dementia faces pressing challenges, such as heterogeneity, diversity, political instability, and socioeconomic disparities. These can be addressed more effectively in a collaborative setting that fosters open exchange of knowledge. In this work, the Latin American and Caribbean Consortium on Dementia (LAC-CD) proposes an agenda for integration to deliver a Knowledge to Action Framework (KtAF). First, we summarize evidence-based strategies (epidemiology, genetics, biomarkers, clinical trials, nonpharmacological interventions, networking, and translational research) and align them to current global strategies to translate regional knowledge into transformative actions. Then we characterize key sources of complexity (genetic isolates, admixture in populations, environmental factors, and barriers to effective interventions), map them to the above challenges, and provide the basic mosaics of knowledge toward a KtAF. Finally, we describe strategies supporting the knowledge creation stage that underpins the translational impact of KtAF.

Asunto(s)

RESUMEN

One of the major puzzles in medical research and public health systems worldwide is Alzheimer's disease (AD), reaching nowadays a prevalence near 50 million people. This is a multifactorial brain disorder characterized by progressive cognitive impairment, apathy, and mood and neuropsychiatric disorders. The main risk of AD is aging; a normal biological process associated with a continuum dynamic involving a gradual loss of people's physical capacities, but with a sound experienced view of life. Studies suggest that AD is a break from normal aging with changes in the powerful functional capacities of neurons as well as in the mechanisms of neuronal protection. In this context, an important path has been opened toward AD prevention considering that there are elements of nutrition, daily exercise, avoidance of toxic substances and drugs, an active social life, meditation, and control of stress, to achieve healthy aging. Here, we analyze the involvement of such factors and how to control environmental risk factors for a better quality of life. Prevention as well as innovative screening programs for early detection of the disease using reliable biomarkers are becoming critical to control the disease. In addition, the failure of traditional pharmacological treatments and search for new drugs has stimulated the emergence of nutraceutical compounds in the context of a "multitarget" therapy, as well as mindfulness approaches shown to be effective in the aging, and applied to the control of AD. An integrated approach involving all these preventive factors combined with novel pharmacological approaches should pave the way for the future control of the disease.

Asunto(s)

RESUMEN

BACKGROUND: Amyloid-ß peptide (Aß) deposition in Alzheimer's disease (AD) is due to an imbalance in its production/clearance rate. Aß is transported across the blood-brain barrier by LRP1 and P-gp as efflux transporters and RAGE as influx transporter. Vitamin D deficit and polymorphisms of the vitamin D receptor (VDR) gene are associated with high prevalence of mild cognitive impairment (MCI) and AD. Further, vitamin D promotes the expression of LRP1 and P-gp in AD-animal model brains. OBJECTIVE: To associate VDR polymorphisms Apa I (rs7975232), Taq I (rs731236), and Fok I (rs2228570) with the risk of developing MCI in a Chilean population, and to evaluate the relationship of these polymorphisms to the expression of VDR and Aß-transporters in peripheral blood mononuclear cells (PBMCs). METHODS: VDR polymorphisms Apa I, Taq I, and Fok I were determined in 128 healthy controls (HC) and 66 MCI patients. mRNA levels of VDR and Aß-transporters were evaluated in subgroups by qPCR. RESULTS: Alleles A of Apa I and C of Taq I were associated with a lower risk of MCI. HC with the Apa I AA genotype had higher mRNA levels of P-gp and LRP1, while the expression of VDR and RAGE were higher in MCI patients and HC. For Fok I, the TC genotype was associated with lower expression levels of Aß-transporters in both groups. CONCLUSION: We propose that the response to vitamin D treatment will depend on VDR polymorphisms, being more efficient in carriers of protective alleles of Apa I polymorphism.

Asunto(s)

RESUMEN

This work presents the development and implementation of a distributed navigation system based on object recognition algorithms. The main goal is to introduce advanced algorithms for image processing and artificial intelligence techniques for teaching control of mobile robots. The autonomous system consists of a wheeled mobile robot with an integrated color camera. The robot navigates through a laboratory scenario where the track and several traffic signals must be detected and recognized by using the images acquired with its on-board camera. The images are sent to a computer server that performs a computer vision algorithm to recognize the objects. The computer calculates the corresponding speeds of the robot according to the object detected. The speeds are sent back to the robot, which acts to carry out the corresponding manoeuvre. Three different algorithms have been tested in simulation and a practical mobile robot laboratory. The results show an average of 84% success rate for object recognition in experiments with the real mobile robot platform.

RESUMEN

Background: In relapsing-remitting multiple sclerosis, no evidence of disease activity-3 (NEDA-3) is defined as no relapses, no disability progression and no MRI activity. NEDA-4 status is defined as meeting all NEDA-3 criteria plus having an annualized brain volume loss (a-BVL) of ≤0.4%. Prospective real-world studies presenting data on NEDA-4 are scarce. Objective: To determine the proportion of patients failing to meet one or more NEDA-4 criteria and the contribution of each component to this failure. Methods: Forty-eight patients were followed for 12 months. Structural image evaluation, using normalization, of atrophy was used to assess a-BVL. Results: The patients had a mean age of 33.0 years (range 18-57), disease duration of 1.7 years (0.4-4) and Expanded Disability Status Scale score of 1.3 (0-4); 71% were women. All patients were on disease-modifying therapies. During follow-up, 21% of the patients had at least one relapse, 21% had disability progression, 8% had new T2 lesions, and 10% had gadolinium-enhanced lesions. Fifty-eight percent (28/48) achieved NEDA-3 status. a-BVL of >0.4% was observed in 52% (25/48). Only 29% (14/48) achieved NEDA-4 status. Conclusion: a-BVL is a good marker to detect subclinical disease activity. a-BVL is parameter to continue investigating for guiding clinical practice in relapsing-remitting multiple sclerosis.

RESUMEN

Alzheimer´s disease (AD) and related forms of dementia are increasingly affecting the aging population throughout the world, at an alarming rate. The World Alzheimer´s Report indicates a prevalence of 46.8 million people affected by AD worldwide. As population ages, this number is projected to triple by 2050 unless effective interventions are developed and implemented. Urgent efforts are required for an early detection of this disease. The ultimate goal is the identification of viable targets for the development of molecular markers and validation of their use for early diagnosis of AD that may improve treatment and the disease outcome in patients. The diagnosis of AD has been difficult to resolve since approaches for early and accurate detection and follow-up of AD patients at the clinical level have been reported only recently. Some proposed AD biomarkers include the detection of pathophysiological processes in the brain in vivo with new imaging techniques and novel PET ligands, and the determination of pathogenic proteins in cerebrospinal fluid showing anomalous levels of hyperphosphorylated tau and low Aß peptide. These biomarkers have been increasingly accepted by AD diagnostic criteria and are important tools for the design of clinical trials, but difficulties in accessibility to costly and invasive procedures have not been completely addressed in clinical settings. New biomarkers are currently being developed to allow determinations of multiple pathological processes including neuroinflammation, synaptic dysfunction, metabolic impairment, protein aggregation and neurodegeneration. Highly specific and sensitive blood biomarkers, using less-invasive procedures to detect AD, are derived from the discoveries of peripheric tau oligomers and amyloid variants in human plasma and platelets. We have also developed a blood tau biomarker that correlates with a cognitive decline and also with neuroimaging determinations of brain atrophy.

Asunto(s)

RESUMEN

The establishment of a molecular biomarker for early detection of Alzheimer's disease (AD) is critical for diagnosis and follow up of patients, and as a quantitative parameter in the evaluation of potential new drugs to control AD. A list of blood biomarkers has been reported but none has been validated for the Alzheimer's clinic. The changes in hyperphosphorylated tau and amyloid peptide in the cerebrospinal fluid is currently used as a tool in the clinics and for research purposes, but this method is highly invasive. Recently, we reported a non-invasive and reliable blood biomarker that correlates the increase in the ratio of heavy tau (HMWtau) and the low molecular weight tau (LMWtau) in human platelets and the decrease in the brain volume as measured by structural MRI. This molecular marker has been named Alz-tau®. Beyond the clinical trials developed with a Latin American population, the present study focuses on an evaluation of this biomarker in a Caucasian population. We examined 36 AD patients and 15 cognitively normal subjects recruited in Barcelona, Spain. Tau levels in platelets were determined by immunoreactivity and the cognitive status by using GDS and MMSE neuropsychological tests. The HMW/LMW tau ratio was statistically different between controls and AD patients. A high correlation was found between the increase in MMSE scores and HMW/LMW tau ratio. This study showed that this ratio is significantly higher in AD patients than controls. Moreover, this study on a peripheral marker of AD is valuable to understanding the AD pathogenesis.

Asunto(s)

RESUMEN

A 68-years-old Hispanic man, complained of night sweats, low grade fewer, unexplained weight loss, and memory problems over 3 months. Abdominal tomography showed multiple intra-abdominal adenopathy and biopsy confirmed classic Hodgkin's lymphoma. He commenced treatment with chemotherapy. Three months later, he had acute onset of inattention, auditory hallucinations and alterations of anterograde memory. The patient developed psychomotor agitation, unresponsive to a combination of neuroleptics and benzodiazepines. Brain MRI showed a small established cerebellar infarction. Electroencephalogram was normal. Tests for toxic metabolic encephalopathy were negative. One oligoclonal IgG bands was found in the Cerebrospinal fluid (CSF), which was not observed in corresponding serum, but cell count and protein were normal. Extensive testing for infectious encephalitis was unremarkable. CSF testing for commercially available neural and non-neural autoantibodies was negative. The patient fulfilled the Gultekin diagnostic criteria for paraneoplastic limbic encephalitis and methylprednisolone IV 1g/d for 5 days was given. He recovered rapidly, with progressive improvement in memory and psychomotor agitation. After treatment commenced, results for antibodies to mGluR5 in CSF taken prior to treatment were returned as positive. mGluR5 is found on post-synaptic terminals of neurons and microglia and is expressed primarily in the hippocampus and amygdala. This case highlights the difficulties in diagnosing this type of encephalitis: the CSF did not show pleocytosis, the MRI showed only chronic change and the electroencephalogram was normal. The dramatic recovery after methylprednisolone help to better characterized the clinical spectrum of auto-immune encephalitis. Diagnosing anti mGlutR5 encephalitis may lead to potentially highly effective treatment option and may anticipate the diagnostic of a cancer. A high index of suspicion is needed to avoid missed diagnosis. In patients with unexplained encephalitis, testing for antibodies to mGluR5 in CSF and serum should be considered. When there is a reasonable index of suspicion of auto-immune encephalitis, treatment should not be delayed for the antibody results.

Asunto(s)

RESUMEN

Proximity sensors are broadly used in mobile robots for obstacle detection. The traditional calibration process of this kind of sensor could be a time-consuming task because it is usually done by identification in a manual and repetitive way. The resulting obstacles detection models are usually nonlinear functions that can be different for each proximity sensor attached to the robot. In addition, the model is highly dependent on the type of sensor (e.g., ultrasonic or infrared), on changes in light intensity, and on the properties of the obstacle such as shape, colour, and surface texture, among others. That is why in some situations it could be useful to gather all the measurements provided by different kinds of sensor in order to build a unique model that estimates the distances to the obstacles around the robot. This paper presents a novel approach to get an obstacles detection model based on the fusion of sensors data and automatic calibration by using artificial neural networks.