RESUMEN

This paper presents a comprehensive approach to detect violent events in videos by combining CrimeNet, a Vision Transformer (ViT) model with structured neural learning and adversarial regularization, with an adaptive threshold sliding window model based on the Transformer architecture. CrimeNet demonstrates exceptional performance on all datasets (XD-Violence, UCF-Crime, NTU-CCTV Fights, UBI-Fights, Real Life Violence Situations, MediEval, RWF-2000, Hockey Fights, Violent Flows, Surveillance Camera Fights, and Movies Fight), achieving high AUC ROC and AUC PR values (up to 99% and 100%, respectively). However, the generalization of CrimeNet to cross-dataset experiments posed some problems, resulting in a 20-30% decrease in performance, for instance, training in UCF-Crime and testing in XD-Violence resulted in 70.20% in AUC ROC. The sliding window model with adaptive thresholding effectively solves these problems by automatically adjusting the violence detection threshold, resulting in a substantial improvement in detection accuracy. By applying the sliding window model as post-processing to CrimeNet results, we were able to improve detection accuracy by 10% to 15% in cross-dataset experiments. Future lines of research include improving generalization, addressing data imbalance, exploring multimodal representations, testing in real-world applications, and extending the approach to complex human interactions.

RESUMEN

Sign language serves as the primary mode of communication for the deaf community. With technological advancements, it is crucial to develop systems capable of enhancing communication between deaf and hearing individuals. This paper reviews recent state-of-the-art methods in sign language recognition, translation, and production. Additionally, we introduce a rule-based system, called ruLSE, for generating synthetic datasets in Spanish Sign Language. To check the usefulness of these datasets, we conduct experiments with two state-of-the-art models based on Transformers, MarianMT and Transformer-STMC. In general, we observe that the former achieves better results (+3.7 points in the BLEU-4 metric) although the latter is up to four times faster. Furthermore, the use of pre-trained word embeddings in Spanish enhances results. The rule-based system demonstrates superior performance and efficiency compared to Transformer models in Sign Language Production tasks. Lastly, we contribute to the state of the art by releasing the generated synthetic dataset in Spanish named synLSE.

Asunto(s)

RESUMEN

BACKGROUND: Only 5% of the molecules tested in oncology phase 1 trials reach the market after an average of 7.5 years of waiting and at a cost of tens of millions of dollars. To reduce the cost and shorten the time of discovery of new treatments, "drug repurposing" (research with molecules already approved for another indication) and the use of secondary data (not collected for the purpose of research) have been proposed. Due to advances in informatics in clinical care, secondary data can, in some cases, be of equal quality to primary data generated through prospective studies. OBJECTIVE: The objective of this study is to identify drugs currently marketed for other indications that may have an effect on the prognosis of patients with cancer. METHODS: We plan to monitor a cohort of patients with high-lethality cancers treated in the public health system of Catalonia between 2006 and 2012, retrospectively, for survival for 5 years after diagnosis or until death. A control cohort, comprising people without cancer, will also be retrospectively monitored for 5 years. The following study variables will be extracted from different population databases: type of cancer (patients with cancer cohort), date and cause of death, pharmacological treatment, sex, age, and place of residence. During the first stage of statistical analysis of the patients with cancer cohort, the drugs consumed by the long-term survivors (alive at 5 years) will be compared with those consumed by nonsurvivors. In the second stage, the survival associated with the consumption of each relevant drug will be analyzed. For the analyses, groups will be matched for potentially confounding variables, and multivariate analyses will be performed to adjust for residual confounding variables if necessary. The control cohort will be used to verify whether the associations found are exclusive to patients with cancer or whether they also occur in patients without cancer. RESULTS: We anticipate discovering multiple significant associations between commonly used drugs and the survival outcomes of patients with cancer. We expect to publish the initial results in the first half of 2024. CONCLUSIONS: This retrospective study may identify several commonly used drugs as candidates for repurposing in the treatment of various cancers. All analyses are considered exploratory; therefore, the results will have to be confirmed in subsequent clinical trials. However, the results of this study may accelerate drug discovery in oncology. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/48925.

RESUMEN

PURPOSE: Information and Communication Technologies have transformed our lives in different social areas, facilitating interpersonal relationships thanks to technological tools. In the specific case of people with disabilities, Assistive Technologies (ATs) break down barriers and increase opportunities to become active members of society with equal opportunities. MATERIALS AND METHODS: This paper presents a systematic mapping study that analyzes the current state-of-the-art of ATs proposed in the literature to support the empowering of people with disability. Specifically, this paper focuses on (1) describing a global vision of the scientific literature published in the last 20 years about ATs in the computer science field and (2) identifying research needs, gaps, and trends. RESULTS: For this purpose, an in-depth analysis of 389 primary studies is presented. The information obtained from the mapping process is also constrained. Concretely, 35 ATs versus 22 disabilities are compared, obtaining striking peaks for some disabilities described in the discussion. CONCLUSIONS: Finally, the findings show that several areas have been covered only lightly, revealing interesting future directions and challenges for junior researchers.

• ATs have the potential to break down barriers for people with disabilities, enabling them to participate more fully in society. This implies a need for rehabilitation programs to incorporate ATs into their strategies to enhance social inclusion.• Given the transformative role of ICT, rehabilitation programs should focus on helping people with disabilities develop the necessary technological skills to utilize ATs effectively.• This work highlights the diversity of ATs and disabilities, suggesting a need for personalized rehabilitation plans that match specific ATs to individual disabilities.• Rehabilitation professionals should be trained to assess and recommend appropriate ATs for each case. Rehabilitation programs should consider incorporating cutting-edge ATs and staying involved in research to contribute to future developments to cover gaps and challenges identified.

RESUMEN

MS SPIDOC is a novel sample delivery system designed for single (isolated) particle imaging at X-ray Free-Electron Lasers that is adaptable towards most large-scale facility beamlines. Biological samples can range from small proteins to MDa particles. Following nano-electrospray ionization, ionic samples can be m/z-filtered and structurally separated before being oriented at the interaction zone. Here, we present the simulation package developed alongside this prototype. The first part describes how the front-to-end ion trajectory simulations have been conducted. Highlighted is a quadrant lens; a simple but efficient device that steers the ion beam within the vicinity of the strong DC orientation field in the interaction zone to ensure spatial overlap with the X-rays. The second part focuses on protein orientation and discusses its potential with respect to diffractive imaging methods. Last, coherent diffractive imaging of prototypical T = 1 and T = 3 norovirus capsids is shown. We use realistic experimental parameters from the SPB/SFX instrument at the European XFEL to demonstrate that low-resolution diffractive imaging data (q < 0.3 nm-1) can be collected with only a few X-ray pulses. Such low-resolution data are sufficient to distinguish between both symmetries of the capsids, allowing to probe low abundant species in a beam if MS SPIDOC is used as sample delivery.

Asunto(s)

RESUMEN

Pump-probe experiments at X-ray free-electron laser (XFEL) facilities are a powerful tool for studying dynamics at ultrafast and longer timescales. Observing the dynamics in diverse scientific cases requires optical laser systems with a wide range of wavelength, flexible pulse sequences and different pulse durations, especially in the pump source. Here, the pump-probe instrumentation available for measurements at the Single Particles, Clusters, and Biomolecules and Serial Femtosecond Crystallography (SPB/SFX) instrument of the European XFEL is reported. The temporal and spatial stability of this instrumentation is also presented.

Asunto(s)

RESUMEN

Object detectors have improved in recent years, obtaining better results and faster inference time. However, small object detection is still a problem that has not yet a definitive solution. The autonomous weapons detection on Closed-circuit television (CCTV) has been studied recently, being extremely useful in the field of security, counter-terrorism, and risk mitigation. This article presents a new dataset obtained from a real CCTV installed in a university and the generation of synthetic images, to which Faster R-CNN was applied using Feature Pyramid Network with ResNet-50 resulting in a weapon detection model able to be used in quasi real-time CCTV (90 ms of inference time with an NVIDIA GeForce GTX-1080Ti card) improving the state of the art on weapon detection in a two stages training. In this work, an exhaustive experimental study of the detector with these datasets was performed, showing the impact of synthetic datasets on the training of weapons detection systems, as well as the main limitations that these systems present nowadays. The generated synthetic dataset and the real CCTV dataset are available to the whole research community.

Asunto(s)

RESUMEN

The number of connected sensors and devices is expected to increase to billions in the near future. However, centralised cloud-computing data centres present various challenges to meet the requirements inherent to Internet of Things (IoT) workloads, such as low latency, high throughput and bandwidth constraints. Edge computing is becoming the standard computing paradigm for latency-sensitive real-time IoT workloads, since it addresses the aforementioned limitations related to centralised cloud-computing models. Such a paradigm relies on bringing computation close to the source of data, which presents serious operational challenges for large-scale cloud-computing providers. In this work, we present an architecture composed of low-cost Single-Board-Computer clusters near to data sources, and centralised cloud-computing data centres. The proposed cost-efficient model may be employed as an alternative to fog computing to meet real-time IoT workload requirements while keeping scalability. We include an extensive empirical analysis to assess the suitability of single-board-computer clusters as cost-effective edge-computing micro data centres. Additionally, we compare the proposed architecture with traditional cloudlet and cloud architectures, and evaluate them through extensive simulation. We finally show that acquisition costs can be drastically reduced while keeping performance levels in data-intensive IoT use cases.

RESUMEN

The European X-ray Free-Electron Laser (FEL) became the first operational high-repetition-rate hard X-ray FEL with first lasing in May 2017. Biological structure determination has already benefitted from the unique properties and capabilities of X-ray FELs, predominantly through the development and application of serial crystallography. The possibility of now performing such experiments at data rates more than an order of magnitude greater than previous X-ray FELs enables not only a higher rate of discovery but also new classes of experiments previously not feasible at lower data rates. One example is time-resolved experiments requiring a higher number of time steps for interpretation, or structure determination from samples with low hit rates in conventional X-ray FEL serial crystallography. Following first lasing at the European XFEL, initial commissioning and operation occurred at two scientific instruments, one of which is the Single Particles, Clusters and Biomolecules and Serial Femtosecond Crystallography (SPB/SFX) instrument. This instrument provides a photon energy range, focal spot sizes and diagnostic tools necessary for structure determination of biological specimens. The instrumentation explicitly addresses serial crystallography and the developing single particle imaging method as well as other forward-scattering and diffraction techniques. This paper describes the major science cases of SPB/SFX and its initial instrumentation - in particular its optical systems, available sample delivery methods, 2D detectors, supporting optical laser systems and key diagnostic components. The present capabilities of the instrument will be reviewed and a brief outlook of its future capabilities is also described.

RESUMEN

BACKGROUND: The US mainland is experiencing an epidemic of opioid overdoses. Unfortunately, the US Territories (Guam, Puerto Rico, and the Virgin Islands) have often been overlooked in opioid pharmacoepidemiology research. This study examined common prescription opioids over the last decade. METHODS: The United States Drug Enforcement Administration's Automation of Reports and Consolidated Orders System (ARCOS) was used to report on ten medical opioids: buprenorphine, codeine, fentanyl, hydrocodone, hydromorphone, meperidine, methadone, morphine, oxycodone, and oxymorphone, by weight from 2006 to 2017. Florida and Hawaii were selected as comparison areas. RESULTS: Puerto Rico had the greatest Territorial oral morphine mg equivalent (MME) per capita (421.5) which was significantly higher (p < .005) than the Virgin Islands (139.2) and Guam (118.9) but significantly lower than that of Hawaii (794.6) or Florida (1,509.8). Methadone was the largest opioid by MMEs in 2017 in most municipalities, accounting for 41.1% of the total in the Virgin Islands, 37.9% in Florida, 36.6% in Hawaii but 80.8% in Puerto Rico. Puerto Rico and Florida showed pronounced differences in the distribution patterns by pharmacies, hospitals, and narcotic treatment programs for opioids. CONCLUSIONS: Continued monitoring of the US Territories is needed to provide a balance between appropriate access to these important agents for cancer related and acute pain while also minimizing diversion and avoiding the opioid epidemic which has adversely impacted the US mainland.

RESUMEN

This paper presents a Deep Learning approach for traffic sign recognition systems. Several classification experiments are conducted over publicly available traffic sign datasets from Germany and Belgium using a Deep Neural Network which comprises Convolutional layers and Spatial Transformer Networks. Such trials are built to measure the impact of diverse factors with the end goal of designing a Convolutional Neural Network that can improve the state-of-the-art of traffic sign classification task. First, different adaptive and non-adaptive stochastic gradient descent optimisation algorithms such as SGD, SGD-Nesterov, RMSprop and Adam are evaluated. Subsequently, multiple combinations of Spatial Transformer Networks placed at distinct positions within the main neural network are analysed. The recognition rate of the proposed Convolutional Neural Network reports an accuracy of 99.71% in the German Traffic Sign Recognition Benchmark, outperforming previous state-of-the-art methods and also being more efficient in terms of memory requirements.

Asunto(s)

RESUMEN

BACKGROUND: In this paper a new approach is applied to the area of marketing research. The aim of this paper is to recognize how brain activity responds during the visualization of short video advertisements using discrete classification techniques. By means of low cost electroencephalography devices (EEG), the activation level of some brain regions have been studied while the ads are shown to users. We may wonder about how useful is the use of neuroscience knowledge in marketing, or what could provide neuroscience to marketing sector, or why this approach can improve the accuracy and the final user acceptance compared to other works. METHODS: By using discrete techniques over EEG frequency bands of a generated dataset, C4.5, ANN and the new recognition system based on Ameva, a discretization algorithm, is applied to obtain the score given by subjects to each TV ad. RESULTS: The proposed technique allows to reach more than 75 % of accuracy, which is an excellent result taking into account the typology of EEG sensors used in this work. Furthermore, the time consumption of the algorithm proposed is reduced up to 30 % compared to other techniques presented in this paper. CONCLUSIONS: This bring about a battery lifetime improvement on the devices where the algorithm is running, extending the experience in the ubiquitous context where the new approach has been tested.

Asunto(s)

RESUMEN

An innovative approach to physical activity recognition based on the use of discrete variables obtained from accelerometer sensors is presented. The system first performs a discretization process for each variable, which allows efficient recognition of activities performed by users using as little energy as possible. To this end, an innovative discretization and classification technique is presented based on the χ2 distribution. Furthermore, the entire recognition process is executed on the smartphone, which determines not only the activity performed, but also the frequency at which it is carried out. These techniques and the new classification system presented reduce energy consumption caused by the activity monitoring system. The energy saved increases smartphone usage time to more than 27 h without recharging while maintaining accuracy.

Asunto(s)

RESUMEN

OBJECTIVE: To determine the 1-year point prevalence of migraine among residents > or =15 years old in 12 Latin American urban communities, and record medical consultation preferences of the identified migraineurs. BACKGROUND: Prevalence of migraine with or without aura in Latin American urban communities has not been established by large-scale population studies. METHODS: A validated face-to-face interview questionnaire based on International Headache Society criteria was completed for all headache sufferers within selected households, in a cross-sectional study. The randomly selected populations were representative of urban communities from the six participating Latin American countries. The questionnaire used was identical in each of the six participating countries. RESULTS: Of the 8618 people available for screening, 62% reported headache and 2637 completed interview questionnaires. Age-adjusted 1-year prevalence of migraine with or without aura for each country was (female/male, %): Argentina 6.1/3.8, Brazil 17.4/7.8, Colombia 13.8/4.8, Ecuador 13.5/2.9, Mexico 12.1/3.9, and Venezuela 12.2/4.7. Migraine prevalence was highest in women aged 30 to 50 years. In the year prior to the study, 42% of individuals interviewed and identified with migraine reported consulting a health professional about their headaches, most frequently (14%) a general practitioner. No previous diagnosis of migraine was reported by 65% of individuals with headache. CONCLUSIONS: In agreement with previous epidemiologic reports, migraine is also a common disorder in Latin American urban communities and predominantly affects women aged 30 to 50 years. Consultation preferences are also similar to those of previous reports.

Asunto(s)

RESUMEN

OBJECTIVE: The objective of this study was to document the clinical characteristics of migraine and patterns of medication use in residents > or =15 years old in 12 Latin American urban communities. BACKGROUND: Few large-scale population studies have established the symptoms and disability associated with migraine with or without aura in Latin American urban communities or the pattern of medication use in these regions. METHODS: In this study, subjects in 12 urban communities, from 6 Latin American countries, were surveyed with a validated face-to-face interview questionnaire based on International Headache Society criteria for migraine. The questionnaire was completed during face-to-face interviews with headache sufferers within selected households and included questions about migraine symptoms, migraine-related disability, and the use of health-care resources and medications to treat migraines. RESULTS: Of the 8618 people available for screening, 62% suffered from headaches. Of individuals with migraine, 42% reported consulting a health-care professional about their headaches. Of the migraineurs, 94.2% reported moderate to severe pain. Associated symptoms of nausea or vomiting, photophobia, phonophobia, and osmophobia were common during migraine attacks in 30.3, 76.4, 85.1, and 47.7% of subjects, respectively. The majority of subjects suffered between one and eight migraines each month. Although no previous diagnosis of migraine was reported by 65% of headache sufferers, migraineurs lost an average of 8 days in the preceding 3 months in any of the following areas: school, work, household chores, and/or social, family, or leisure activities. The agents used most widely to treat migraine were paracetamol and salicylates, while nonsteroidal anti-inflammatory drugs, dypirone, and ergotamines were also commonly used. Medication use varied widely among countries, but was predominantly nonprescription. CONCLUSIONS: Migraine is a common disorder in Latin American urban communities imposing significant burden on individuals, families, and communities. The magnitude of the impact and the range of activities affected by migraine are similar to those of previous reports in other regions. The preponderance of nonprescription medications and the scarcity of migraine-specific triptans from the study findings are especially striking.

Asunto(s)

Asunto(s)

RESUMEN

OBJETIVO: Determinar la prevalencia de ocho problemas neurológicos -migraña, enfermedad cerebrovascular, enfermedad de Parkinson, neuropatía periférica, trastornos del desarrollo neurológico, epilepsia, demencia y secuelas de traumatismo craneoencefálico- en Colombia como parte del estudio neuroepidemiológico nacional (EPINEURO). MÉTODOS: Se realizó una encuesta transversal en dos fases entre septiembre de 1995 y gosto de 1996. En la primera fase se identificó a las personas que podían estar padeciendo alguna enfermedad neurológica y en la segunda se hizo el diagnóstico específico. Se xaminó una muestra de 8 910 personas distribuidas en proporción con la población de cada una de las cinco zonas geográficas de Colombia, que son las regiones entral, sudoccidental, noroccidental, oriental y la costa caribe. La evaluación se realizó según una versión odificada del protocolo de neuroepidemiología de la Organización Mundial de la Salud, además de un examen físico simplificado. A los posibles pacientes de demencia identificados se les aplicó un examen neuropsicológico, diseñado para este estudio, con el fin de profundizar en los aspectos cognoscitivos. Se aplicaron las escalas de Hachinski, Yesavage y Blessed y los criterios iagnósticos del NINCDS-ADRDA para la enfermedad de Alzheimer, los del NINDS-AIREN para la demencia de origen vascular y los del DSM-IV para todo tipo de demencia. Se realizó una ncuesta para determinar si había secuelas de traumatismo craneoencefálico. Las personas mayores de 12 años fueron evaluadas por neurólogos de adultos y los menores de 12 años por un neuropediatra. Se calcularon las prevalencias de trastornos neurológicos por edad y sexo, tanto por egión como para el país en su totalidad, y sus intervalos de confianza de 95 por ciento. RESULTADOS: La prevalencia por 1 000 habitantes de los trastornos investigados ueron las siguientes: migraña, 71,2 (intervalo de confianza de 95 por ciento [IC95 por ciento]: 65,5 a 76,8); trastornos del desarrollo neurológico, 46,1 (IC95 por ciento: 35,5 a 58,9); enfermedad cerebrovascular, 19,9 (IC95 por ciento: 14,3 a 27,4); demencia, 13,1 (IC95 por ciento: 8,5 a 9,3); epilepsia, 10,3 (IC95 por ciento: 8,5 a 13,0); neuropatía periférica, 8,5 (IC95 por ciento: 6,8 a 10,7); secuelas de traumatismo craneoencefálico, 6,4 (IC95 por ciento: 5,0 a 7,8) y enfermedad de Parkinson 4,7 (IC95 or ciento: 2,2 a 8,9). En todos los casos, menos en el de traumatismos craneoencefálicos, la prevalencia fue mayor en mujeres. Conclusiones. Estos resultados permiten diseñar políticas de salud más actuales dirigidas a lograr una prevención más eficaz, un mejor control y un tratamiento más adecuado de los trastornos neurológicos en Colombia. La fácil aplicación de las encuestas y el bajo costo de este tipo de investigaciones hacen que esta metodología sea ideal para países con carencia de recursos humanos especializados

Objective. To determine the prevalence of eight neurological problems­migraine, cerebrovascular disease, Parkinson's disease, peripheral neuropathy, disorders of neurological development, epilepsy, dementia, and sequelae of head trauma­in Colombia as a part of the National Neuroepidemiological Study (EPINEURO). Methods. A cross-sectional survey was carried out in two phases between September 1995 and August 1996. In the first phase persons who might be suffering from a neurological disease were identified, and in the second phase a specific diagnosis was made. A sample of 8 910 people were examined, distributed in proportion to the population in each of the five geographical areas of Colombia (central, southwest, northwest, eastern, and Caribbean coast). The evaluation was done using a modified version of the neuroepidemiology protocol of the World Health Organization, along with a simplified physical examination. With the patients with possible dementia a neuropsychological examination designed for this study was used in order to thoroughly examine the cognitive aspects analyzed in the initial mental screening. The scales of Hachinski, Yesavage, and Blessed and the diagnostic criteria of the NINCDSADRDA were used for Alzheimer's disease; the NINDS-AIREN criteria for dementia of vascular origin; and the DSM-IV criteria for all types of dementia. A survey was conducted in order to determine if there were sequelae of head trauma. Persons 12 years old or older were evaluated by an adult neurologist and those under 12 years old by a pediatric neurologist. The prevalences of neurological disorders were calculated by age and sex, for each region and also for the entire country, with 95% confidence intervals (CIs). Results. The prevalence per 1 000 population for the disorders investigated was: migraine, 71.2 (95% CI: 65.5 to 76.8); disorders of neurological development, 46.1 (95% CI: 35.5 to 58.9); cerebrovascular disease, 19.9 (95% CI: 14.3 to 27.4); dementia, 13.1 (95% CI: 8.5 to 19.3); epilepsy, 10.3 (95% CI: 8.5 to 13.0); peripheral neuropathy, 8.5 (95% CI: 6.8 to 10.7); sequelae of head trauma, 6.4 (95% CI: 5.0 to 7.8); and Parkinson's disease, 4.7 (95% CI: 2.2 to 8.9). In all those cases except head trauma the prevalence was higher among women than among men. Conclusions. These results make it possible to design more up-to-date health policies aimed at achieving more effective prevention, better control, and more adequate treatment of neurological disorders in Colombia. The easy application of these surveys and the low cost of this type of research make this methodology ideal for countries with shortages of specialized personnel

Asunto(s)

Asunto(s)

Asunto(s)

Asunto(s)