RESUMEN

Recent decades have witnessed substantial changes in freshwater biodiversity worldwide. Although research has shown that freshwater biodiversity can be shaped by changes in habitat diversity and human-induced pressure, the potentials for interaction between these drivers and freshwater biodiversity at large spatial extents remain unclear. To address these issues, we employed a spatially extensive multitrophic fish and insect database from 3323 stream sites across the United States, to investigate the ability of habitat diversity to modulate the effect of human pressure on the richness and abundance of fish and insects. We found evidence that high levels of habitat diversity were associated with increased richness and abundance of fish and insects (including whole-assemblage and individual trophic guilds). We also show that the effects of human pressure on the richness and abundance of fish and insects tend to become positive at high levels of habitat diversity. Where habitat diversity is low, human pressure strongly reduces insect richness and abundance, whereas these reductions are attenuated at high levels of habitat diversity. Structural equation modeling revealed that human pressure reduced habitat diversity, indirectly negatively affecting the richness and abundance of fish and insects. These findings illustrate that, in addition to promoting greater fish and insect biodiversity, habitat diversity may mitigate the deleterious effects of human pressures on these two stream assemblages. Overall, our study suggests that maintaining high levels of habitat diversity is a useful way to protect freshwater biodiversity from ongoing increases in human pressure. However, if human pressures continue to increase, this will reduce habitat diversity, further threatening stream assemblages.

Asunto(s)

Biodiversidad , Ecosistema , Peces , Insectos , Ríos , Animales , Insectos/fisiología , Peces/fisiología , Estados Unidos , Humanos , Actividades Humanas

RESUMEN

Human activities are altering the existing patterns of Land Use Land Cover (LULC) and Land Surface Temperature (LST) on a global scale. However, long-term trends of LULC and LST are largely unknown in many remote mountain areas such as the Karakorum. . The objective of our study therefore was to evaluate the historical changes in land use and land cover (LULC) in an alpine environment located in Islamabad Capital Territory, Pakistan. We used Landsat satellite pictures (namely Landsat 5 TM and Landsat 8 OLI) from the years 1988, 2002, and 2016 and applied the Maximum Likelihood Classification (MLC) approach to categorize land use classes. Land Surface Temperatures (LST) were calculated using the thermal bands (6, 10, and 11) of Landsat series data. The correlation between the Human Modification Index (HMI) and LULC as well as LST was evaluated by utilizing data from Google Earth Engine (GEE). Over the study period, the urbanized area increased by 9.94%, whilst the agricultural and bare soil areas decreased by 3.81% and 3.94%, respectively. The findings revealed a significant change in the LULC with a decrease of 1.99% in vegetation. The highest LST class exhibited a progressive trend, with an increase from 12.27% to 48.48%. Based on the LST analysis, the built-up area shows the highest temperature, followed by the barren, agricultural, and vegetation categories. Similarly, the HMI for different LST categories indicates that higher LST categories have higher levels of human alteration compared to lower LST categories, with a strong correlation (R-value = 0.61) between HMI and LST. The findings can be utilized to promote sustainable urban management and for biodiversity conservation efforts. The work also has the potential of utilizing it to protect delicate ecosystems from human interference and to formulate strategies and regulations for sustainable urban growth, including aspects of land utilization and zoning, reduction of urban heat stress, and urban infrastructure.

Asunto(s)

Temperatura , Pakistán , Humanos , Agricultura , Monitoreo del Ambiente/métodos , Urbanización , Actividades Humanas , Imágenes Satelitales

RESUMEN

Coastal ecosystems are facing increasing anthropogenic stressors, including rapid urbanization rates and extensive fossil fuel usage. Nevertheless, the distribution of hydrocarbons in the Brazilian semi-arid region remains relatively uncharacterized. In this study, we analyzed ten surface sediment samples (0-2 cm) along the banks of the Acaraú River to assess the chronic contributions of aliphatic and aromatic hydrocarbons. The Acaraú River is a crucial riverine-estuarine area in the semi-arid region of Northeast Brazil. Ultrasound-assisted extraction and gas chromatograph coupled to a mass spectrometer were used to identify target compounds: 45 PAHs, 27 n-alkanes (C10-C38), and two isoprenoids. At most stations, the predominant grain size was sand, and the organic carbon content was less than 1%. The total n-alkanes concentration ranged from 14.1 to 170.0 µg g-1, while individual pristane and phytane concentrations ranged from not detected (nd) to 0.4 µg g-1 and nd to 0.7 µg g-1, respectively. These concentrations resemble those found in unpolluted sediments and are lower compared to samples from urbanized coastal areas. The total USEPA PAHs concentration varied from 157.8 to 1364 ng g-1, leading to the characterization of sediment samples as moderately polluted. Based on diagnostic ratios calculated from both alkane and PAH concentrations, the sediment samples were predominantly deriving from pyrolytic sources, with some contribution from petrogenic sources. The most abundant group was 5-ring PAHs (mean: 47.3 ± 36.7%), followed by 3-ring PAHs (mean: 17.9 ± 13.7%). This predominance indicates a pyrolytic origin of hydrocarbons in the Acaraú River. The concentrations reported here were representative of the level of background hydrocarbons in the region. Regarding the sediment quality assessment, BaP TPE calculated for the Acaraú River ranged from 13.2 to 1258.4 ng g-1 (mean: 409.3 ± 409.4 ng g-1). When considering site-specific sediment quality values for the coast of the state of Ceará, half of the stations are classified as strongly contaminated, and toxic effects are expected to occur (SQGq >0.25) for the ∑16 PAHs measured in the samples, especially due to dibenz [a,h]anthracene concentrations.

Asunto(s)

Hidrocarburos Policíclicos Aromáticos , Contaminantes Químicos del Agua , Humanos , Brasil , Ríos/química , Ecosistema , Sedimentos Geológicos/química , Contaminantes Químicos del Agua/análisis , Hidrocarburos , Hidrocarburos Policíclicos Aromáticos/análisis , Alcanos/análisis , Monitoreo del Ambiente , Actividades Humanas

RESUMEN

Adaptive AI for context and activity recognition remains a relatively unexplored field due to difficulty in collecting sufficient information to develop supervised models. Additionally, building a dataset for human context activities "in the wild" demands time and human resources, which explains the lack of public datasets available. Some of the available datasets for activity recognition were collected using wearable sensors, since they are less invasive than images and precisely capture a user's movements in time series. However, frequency series contain more information about sensors' signals. In this paper, we investigate the use of feature engineering to improve the performance of a Deep Learning model. Thus, we propose using Fast Fourier Transform algorithms to extract features from frequency series instead of time series. We evaluated our approach on the ExtraSensory and WISDM datasets. The results show that using Fast Fourier Transform algorithms to extract features performed better than using statistics measures to extract features from temporal series. Additionally, we examined the impact of individual sensors on identifying specific labels and proved that incorporating more sensors enhances the model's effectiveness. On the ExtraSensory dataset, the use of frequency features outperformed that of time-domain features by 8.9 p.p., 0.2 p.p., 39.5 p.p., and 0.4 p.p. in Standing, Sitting, Lying Down, and Walking activities, respectively, and on the WISDM dataset, the model performance improved by 1.7 p.p., just by using feature engineering.

Asunto(s)

Algoritmos , Caminata , Humanos , Actividades Humanas , Movimiento , Factores de Tiempo

RESUMEN

Due to its capacity to gather vast, high-level data about human activity from wearable or stationary sensors, human activity recognition substantially impacts people's day-to-day lives. Multiple people and things may be seen acting in the video, dispersed throughout the frame in various places. Because of this, modeling the interactions between many entities in spatial dimensions is necessary for visual reasoning in the action recognition task. The main aim of this paper is to evaluate and map the current scenario of human actions in red, green, and blue videos, based on deep learning models. A residual network (ResNet) and a vision transformer architecture (ViT) with a semi-supervised learning approach are evaluated. The DINO (self-DIstillation with NO labels) is used to enhance the potential of the ResNet and ViT. The evaluated benchmark is the human motion database (HMDB51), which tries to better capture the richness and complexity of human actions. The obtained results for video classification with the proposed ViT are promising based on performance metrics and results from the recent literature. The results obtained using a bi-dimensional ViT with long short-term memory demonstrated great performance in human action recognition when applied to the HMDB51 dataset. The mentioned architecture presented 96.7 ± 0.35% and 41.0 ± 0.27% in terms of accuracy (mean ± standard deviation values) in the train and test phases of the HMDB51 dataset, respectively.

Asunto(s)

Aprendizaje Profundo , Humanos , Redes Neurales de la Computación , Aprendizaje Automático Supervisado , Actividades Humanas , Movimiento (Física)

RESUMEN

Given the ecological and socioeconomic importance of the mangroves of the Brazilian Amazon coast, RapidEye satellite images were analyzed to recognize mangrove forest and salt flat changes to different land use through human activities. Results show that mangroves are still very well preserved, with less than 1% of the total converted to other uses, primarily urban areas and roads. These human activities have been the principal causes of use in the mangrove forest, driven by local anthropogenic pressures resulting from human settlements in the transition zone between the mainland and tidal flats. In contrast, aquaculture, the principal driver of the loss of mangroves in other regions of South America and in Asian countries, plays only a secondary role in habitat conversion on the Amazon coast. However, these human activities demand more attention and policies need to be supported by Brazilian legislation.

Asunto(s)

Ecosistema , Humedales , Humanos , Brasil , Acuicultura , Actividades Humanas

RESUMEN

Human Activity Recognition (HAR) is a complex problem in deep learning, and One-Dimensional Convolutional Neural Networks (1D CNNs) have emerged as a popular approach for addressing it. These networks efficiently learn features from data that can be utilized to classify human activities with high performance. However, understanding and explaining the features learned by these networks remains a challenge. This paper presents a novel eXplainable Artificial Intelligence (XAI) method for generating visual explanations of features learned by one-dimensional CNNs in its training process, utilizing t-Distributed Stochastic Neighbor Embedding (t-SNE). By applying this method, we provide insights into the decision-making process through visualizing the information obtained from the model's deepest layer before classification. Our results demonstrate that the learned features from one dataset can be applied to differentiate human activities in other datasets. Our trained networks achieved high performance on two public databases, with 0.98 accuracy on the SHO dataset and 0.93 accuracy on the HAPT dataset. The visualization method proposed in this work offers a powerful means to detect bias issues or explain incorrect predictions. This work introduces a new type of XAI application, enhancing the reliability and practicality of CNN models in real-world scenarios.

Asunto(s)

Inteligencia Artificial , Redes Neurales de la Computación , Humanos , Reproducibilidad de los Resultados , Actividades Humanas , Bases de Datos Factuales

RESUMEN

Falling events are a global health concern with short- and long-term physical and psychological implications, especially for the elderly population. This work aims to monitor human activity in an indoor environment and recognize falling events without requiring users to carry a device or sensor on their bodies. A sensing platform based on the transmission of a continuous wave (CW) radio-frequency (RF) probe signal was developed using general-purpose equipment. The CW probe signal is similar to the pilot subcarriers transmitted by commercial off-the-shelf WiFi devices. As a result, our methodology can easily be integrated into a joint radio sensing and communication scheme. The sensing process is carried out by analyzing the changes in phase, amplitude, and frequency that the probe signal suffers when it is reflected or scattered by static and moving bodies. These features are commonly extracted from the channel state information (CSI) of WiFi signals. However, CSI relies on complex data acquisition and channel estimation processes. Doppler radars have also been used to monitor human activity. While effective, a radar-based fall detection system requires dedicated hardware. In this paper, we follow an alternative method to characterize falling events on the basis of the Doppler signatures imprinted on the CW probe signal by a falling person. A multi-class deep learning framework for classification was conceived to differentiate falling events from other activities that can be performed in indoor environments. Two neural network models were implemented. The first is based on a long-short-term memory network (LSTM) and the second on a convolutional neural network (CNN). A series of experiments comprising 11 subjects were conducted to collect empirical data and test the system's performance. Falls were detected with an accuracy of 92.1% for the LSTM case, while for the CNN, an accuracy rate of 92.1% was obtained. The results demonstrate the viability of human fall detection based on a radio sensing system such as the one described in this paper.

Asunto(s)

Aprendizaje Profundo , Humanos , Anciano , Redes Neurales de la Computación , Radar , Actividades Humanas

RESUMEN

Funções executivas (FE) referem-se ao conjunto de habilidades que, de forma integrada, coordenam o comportamento e a cognição. Assim, o comprometimento no desenvolvimento das FE está ligado a vários desfechos negativos ao longo da vida. Portanto, a avaliação dessas habilidades na infância é essencial para identificar e prevenir prejuízos na vida adulta. Este estudo teve como objetivo investigar evidências de validade do Teste Informatizado para Avaliação das Funções Executivas (Tafe) pelo critério de idade e pelo padrão de correlação entre medidas do TAFE e outras medidas de FE. Para isso, foi utilizada uma amostra de 51 crianças, entre 4 e 10 anos de idade, matriculadas em uma escola privada na cidade de Goiânia (GO), da pré-escola ao 4º ano do ensino fundamental. Como instrumentos, foram utilizados, além do Tafe, as tarefas de Bloco de Corsi, Teste de Trilhas A e B, Teste de Trilhas Pré-Escolares, Teste de Stroop Pré-Escolares e Subteste Dígitos da Escala Wechsler de Inteligência. Foram conduzidas análises estatísticas Kruskal Wallis para verificar a evidência de validade por relação com idade e análises de correlação não paramétrica de Spearman para avaliar as evidências de validade convergente. O instrumento investigado mostrou-se efetivo para discriminar entre as diferentes faixas etárias, assim, sensível ao desenvolvimento das FE. Os resultados obtidos no Tafe correlacionaram-se aos obtidos em outros testes que também avaliaram FE, mostrando claros padrões de convergência. Logo, as análises dos resultados fornecem evidências de validade ao Tafe, derivadas a partir de diferentes estratégias de investigação.(AU)

---

Executive functions (EF) refer to the set of skills that, in an integrated way, coordinate behavior and cognition. Thus, the commitment in developing EF is linked to several negative outcomes throughout life. Therefore, the assessment of these abilities in childhood is essential to identify and prevent possible harm in adult life. This study aimed to investigate evidences of validity of the Computerized Test for Evaluation of Executive Functions (TAFE) by the age criterion and by the pattern of correlation between TAFE measures and other EF measures. To this end, a sample of 51 children, between 4 and 10 years old, enrolled in a private school in the municipality of Goiânia (GO), from preschool to the 4th year of elementary school, was used. As instruments, in addition to TAFE, the tasks of Corsi Block, Trails Test A and B, Preschool Trails Test, Preschool Stroop Test and the Digits Subtest of the Wechsler Intelligence Scale were used. Kruskal Wallis statistical analyzes were conducted to verify the evidence of validity by age criteria and Spearman's nonparametric correlation analysis to assess evidence of convergent validation. The instrument investigated was effective to discriminate between different age groups, thus being sensitive to the development of EF. The results obtained in TAFE were correlated with those obtained in other tests that also assess FE, showing patterns of convergence. Therefore, the analysis of the results provides validation evidence to TAFE, derived from different investigation methods.(AU)

---

Las funciones ejecutivas (FE) se refieren al conjunto de habilidades que coordinan la conducta y la cognición. Así, el deterioro en el desarrollo de FE está relacionado con varios resultados negativos durante la vida. Por tanto, la valoración de estas habilidades en la infancia es fundamental para identificar y prevenir posibles daños en la vida adulta. Este estudio tuvo como objetivo investigar la evidencia de validez de la Prueba Computarizada para Evaluación de Funciones Ejecutivas (Tafe) por el criterio de edad y convergencia entre las medidas Tafe y otras medidas de FE. Para ello, se utilizó una muestra de 51 niños, de entre 4 y 10 años de edad, matriculados en un colegio privado de Goiânia (Goiás, Brasil) desde la preescolar hasta 4.º de primaria. Como instrumentos, además del Tafe, se utilizaron las tareas de Bloque de Corsi, el Test de los senderos A y B, el Test de los Senderos Preescolares, el Test de Stroop Preescolar y la Subprueba de Dígitos de la Escala Wechsler de Inteligencia. Se realizaron análisis estadísticos de Kruskal Wallis para verificar la validez por criterios de edad y análisis de correlación no-paramétrica de Spearman para evaluar la evidencia de validez convergente. Tafe demostró ser efectivo para discriminar entre diferentes grupos de edad, así es sensible al desarrollo de FE. Los resultados en Tafe se correlacionaron con los obtenidos en otras pruebas de FE, lo que muestra claros patrones de convergencia. Por tanto, el análisis aporta evidencias de validez para Tafe, derivadas de diferentes estrategias de investigación.(AU)

Asunto(s)

Humanos , Masculino , Femenino , Preescolar , Niño , Cognición , Docilidad , Inhibición Psicológica , Memoria a Corto Plazo , Percepción , Pruebas de Aptitud , Juego e Implementos de Juego , Ludoterapia , Atención Primaria de Salud , Solución de Problemas , Fenómenos Psicológicos , Pruebas Psicológicas , Psicología , Recuerdo Mental , Recreación , Retención en Psicología , Atención , Instituciones Académicas , Percepción Auditiva , Ajuste Social , Apoyo Social , Percepción del Habla , Estrés Psicológico , Análisis y Desempeño de Tareas , Tecnología , Terapéutica , Pensamiento , Escalas de Wechsler , Conducta , Ciencias de la Conducta , Neurociencias , Adaptación Psicológica , Niño , Cuidado del Niño , Preescolar , Monitoreo del Ambiente , Organizaciones , Salud Infantil , Disonancia Cognitiva , Estadísticas no Paramétricas , Estado de Conciencia , Intuición , Manifestaciones Neuroconductuales , Disciplinas y Actividades Conductuales , Autoeficacia , Creatividad , Reconocimiento en Psicología , Autonomía Personal , Acceso a la Información , Comprensión , Crecimiento y Desarrollo , Discriminación en Psicología , Educación , Emociones , Planificación , Cerebro , Resiliencia Psicológica , Función Ejecutiva , Test de Stroop , Atención Plena , Memoria Espacial , Autocontrol , Metacognición , Escala de Memoria de Wechsler , Pruebas de Memoria y Aprendizaje , Automanejo , Mentalización , Frustación , Revisión Sistemática , Regulación Emocional , Análisis de Escalamiento Multidimensional , Autoevaluación , Estado Funcional , Interacción Social , Entrenamiento Cognitivo , Velocidad de Procesamiento , Crecimiento Psicológico , Actividad Nerviosa Superior , Actividades Humanas , Imaginación , Desarrollo del Lenguaje , Trastornos del Desarrollo del Lenguaje , Aprendizaje , Procesos Mentales , Actividad Motora , Pruebas Neuropsicológicas , Neuropsicología

RESUMEN

Este estudo propõe analisar as relações e os processos de subjetivação de mulheres quebradeiras de coco babaçu decorrentes das intervenções de políticas desenvolvimentistas em seus territórios de vida e reverberações no Movimento Interestadual de Quebradeiras de Coco Babaçu (MIQCB). Sob a perspectiva ético-estético-política da Cartografia, acompanhamos as narrativas das histórias de vida de 24 mulheres, suas atividades cotidianas e eventos do MIQCB, também analisamos os documentos das políticas. Entendemos que, ao passo que tais políticas de desenvolvimento rural contribuem para a melhoria das condições de vida, em termos materiais e simbólicos, elas também produzem ressonâncias relacionadas ao modo de subjetivação do tipo "empresário de si", que agenciam seus modos de viver, de produzir e de se relacionar consigo e com os outros na lógica capitalista neoliberal. A resistência às capturas neoliberais também estão presentes ao ampliarem as mobilizações coletivas do próprio movimento, articulando com outros na produção de um "comum".(AU)

---

This study proposes to analyze the relations and the processes of subjectivation of babassu coconut-breaker women arising from developmental policy interventions in their territories of life and reverberations in the Babassu Coconut-breaker Interstate Movement (MIQCB). From the ethical-aesthetic-political perspective of Cartography, we followed the narratives of the life stories of 24 women, their daily activities and promoted events by MIQCB, we also analyzed the policy documents. We understand that while these policies of rural development contribute to improve the living conditions, in material and symbolic terms, they also produce resonances related to the "self-entrepreneur" mode of subjectivation, which has been handling their ways of living, producing, and relating to themselves and others in the neoliberal capitalist logic. Resistance to neoliberal captures is also present as they expand the collective mobilizations of the movement itself, articulating with others, in the production of a "common."(AU)

---

Este estudio tiene como objetivo analizar los procesos de subjetivación de las mujeres que rompen coco babaçu que surgen de las intervenciones de las políticas de desarrollo en sus territorios de vida y las reverberaciones en el Movimiento Interestadual de las Mujeres que Rompen Coco Babaçu (MIQCB). Desde la perspectiva ético-estético-política de la Cartografía, seguimos las narraciones de las historias de vida de 24 mujeres, sus actividades diarias y eventos del MIQCB, y también analizamos los documentos de las políticas. Si bien estas políticas han contribuido a mejorar las condiciones de vida de las mujeres, en términos materiales y simbólicos, también han producido resonancias del modo de subjetivación "autoempresarial", que ha agenciado sus formas de vivir, producir y relacionarse consigo mismas y con los demás en la lógica capitalista neoliberal. La resistencia a las capturas neoliberales también está presente cuando amplían las movilizaciones colectivas del propio movimiento, articulándose con otros en la producción de un "común".(AU)

Asunto(s)

Humanos , Femenino , Crecimiento y Desarrollo , Economía , Gobierno , Política , Pobreza , Psicología , Psicología Social , Política Pública , Jubilación , Población Rural , Deseabilidad Social , Justicia Social , Problemas Sociales , Ciencias Sociales , Suelo , Derechos de la Mujer , Madera , Políticas, Planificación y Administración en Salud , Planificación Socioeconómica , Políticas de Control Social , Legislación Ambiental , Brasil , Agua , Ejercicio Físico , Etnicidad , Desarrollo Económico , Áreas de Pobreza , Usos del Suelo , Medio Rural , Bosques , Organizaciones , Salud Ambiental , Conflicto de Intereses , Carga de Trabajo , Política de Planificación Familiar , Emprendimiento , Agroquímicos , Entrevista , Negociación Colectiva , Comercio , Productos Agrícolas , Gestión Ambiental , Explotación de Recursos Naturales , Recursos Naturales , Recursos Renovables , Reservas Naturales , Flora , Conservación de los Recursos Naturales , Diversidad Cultural , Naturaleza , Feminismo , Industria Procesadora y de Extracción , Administración de Recursos Naturales , Economía Rural , Capitalismo , Estado , Poder Público , Biodiversidad , Agricultura , Eficiencia , Ambiente , Medio Ambiente y Salud Pública , Gestión de Ciencia, Tecnología e Innovación en Salud , Proyectos , Mercado de Trabajo , Vigilancia Sanitaria de Productos , Control y Fiscalización de Alimentos y Bebidas , Alimentos de Coco , Maquinaria , Agricultura Sostenible , Recursos no Renovables , Agroindustria , Comunicación Ambiental , Feminidad , Política Ambiental , Pequeña Empresa , Violencia Étnica , Factores Sociológicos , Alimentos , Equilibrio entre Vida Personal y Laboral , Activismo Político , Participación de los Interesados , Derechos Socioeconómicos , Territorio Ocupado , Desarrollo Sostenible , Programas Sociales , Pueblos Indígenas , Derecho al Trabajo , Empoderamiento , Inclusión Social , Equidad de Género , Rol de Género , Vulnerabilidad Social , Responsabilidad Ambiental , Responsabilidad Socioambiental , Diversidad, Equidad e Inclusión , Condiciones de Trabajo , Comercio de Vida Silvestre , Necesidades y Demandas de Servicios de Salud , Vivienda , Actividades Humanas , Derechos Humanos , Sindicatos , Acontecimientos que Cambian la Vida , Antropología , Minería , Grupos Profesionales

RESUMEN

Research into assisted living environments -within the area of Ambient Assisted Living (ALL)-focuses on generating innovative technology, products, and services to provide medical treatment and rehabilitation to the elderly, with the purpose of increasing the time in which these people can live independently, whether they suffer from neurodegenerative diseases or disabilities. This key area is responsible for the development of activity recognition systems (ARS) which are a valuable tool to identify the types of activities carried out by the elderly, and to provide them with effective care that allows them to carry out daily activities normally. This article aims to review the literature to outline the evolution of the different data mining techniques applied to this health area, by showing the metrics used by researchers in this area of knowledge in recent experiments.

Asunto(s)

Actividades Humanas , Aprendizaje Automático , Anciano , Minería de Datos , Humanos , Tecnología

RESUMEN

Due to wearables' popularity, human activity recognition (HAR) plays a significant role in people's routines. Many deep learning (DL) approaches have studied HAR to classify human activities. Previous studies employ two HAR validation approaches: subject-dependent (SD) and subject-independent (SI). Using accelerometer data, this paper shows how to generate visual explanations about the trained models' decision making on both HAR and biometric user identification (BUI) tasks and the correlation between them. We adapted gradient-weighted class activation mapping (grad-CAM) to one-dimensional convolutional neural networks (CNN) architectures to produce visual explanations of HAR and BUI models. Our proposed networks achieved 0.978 and 0.755 accuracy, employing both SD and SI. The proposed BUI network achieved 0.937 average accuracy. We demonstrate that HAR's high performance with SD comes not only from physical activity learning but also from learning an individual's signature, as in BUI models. Our experiments show that CNN focuses on larger signal sections in BUI, while HAR focuses on smaller signal segments. We also use the grad-CAM technique to identify database bias problems, such as signal discontinuities. Combining explainable techniques with deep learning can help models design, avoid results overestimation, find bias problems, and improve generalization capability.

Asunto(s)

Identificación Biométrica , Redes Neurales de la Computación , Bases de Datos Factuales , Actividades Humanas , Humanos

RESUMEN

Hydrological and erosion dynamics are prone to change due to natural factors, human activities, or climate change. These changes are mainly related to modifications of land use and cover and can be assessed through the concept of connectivity, which analyzes how the spatial distribution of the elements facilitates runoff and sediment transport. The objective of this study was to evaluate changes in hydrological and sediment connectivity over 42 years and projected under a climate change scenario in the tropical Santa Cruz catchment in Aquismón, S.L.P., Mexico. The index of connectivity (IC) was computed using SedInConnect version 2.3 and the ArcSWAT model to estimate runoff. Hydrological connectivity and runoff were projected for 2027 using the MPI ECHAM 5 in the A2 climate change scenario. The results indicated that spatio-temporal changes in land use/cover, in conjunction with geomorphological features and expected climate change, would modify hydrological and sediment connectivity, especially in flat areas, where conversion of natural vegetation to cropland was steadily increasing over the years. Under future conditions, runoff and sediment transport are likely to increase, which will impact soil erosion and vulnerability to flooding but will not necessarily be negative. The study shows how spatial-temporal integration of runoff, sediments, landforms, land use cover and change, and connectivity can improve our understanding of catchment dynamics and the importance of analyses that characterize their evolution. The results can subsequently be applied and replicated in other catchments for management and restoration purposes.

Asunto(s)

Cambio Climático , Hidrología , Inundaciones , Actividades Humanas , Humanos , México

RESUMEN

Selective logging is one of the main human activities that are drastically modifying tropical forests around the world. Reduced-impact logging emerged as a rational model of timber harvesting that reduces the impacts on the ecosystems and contributes to the conservation of natural resources. Nevertheless, this type of activity may still alter the forest structure, nutrient cycling, soil drainage, and other important ecosystem processes. Here, we aimed at testing the effects of selective logging on litter deposition in central Brazilian Amazonia. We estimated litter production during one dry and one rainy season in 11 sites logged between 2003 and 2017 and one unlogged site. Mean litter deposition was greater during the dry season. Although litter deposition rates varied between a few study sites, this variation was independent of the time after logging. The results suggest that the low logging intensity in the study site (16.8 m³/ha) had no intense impacts on litter deposition. Reduced-impact logging may be an alternative for the use of forest resources in Amazonian forests without compromising nutrient cycles.

Asunto(s)

Ecosistema , Agricultura Forestal , Brasil , Conservación de los Recursos Naturales/métodos , Bosques , Actividades Humanas , Humanos , Árboles

RESUMEN

Humans frequently interact with Pacific harbor seals (Phoca vitulina richardii) at Punta Banda Estuary, Baja California, Mexico, due to the high incidence of recreational activities people undertake there. The immediate effect of these interactions is that seals flush to the water, reducing their time on land and, probably, increasing their energy expenditure. On-land observations were used to study the impact of different sources of disturbance on seal behavior and evaluate their effect on the amount of time dedicated to nursing over three pupping seasons, (2015-2017), with 0.58-0.81 disturbance events/hour recorded over the entire sampling period. Terrestrial vehicles were the source with the highest disturbance rate (number of disturbance events/h), followed closely by pedestrians. However, the proportion of seals affected was highest when pedestrians were the disturbance source. Recovery events (seals hauling out after flushing) occurred after 34% of disturbance events, after less than half of which the same number of hauled-out seals as there were prior to the disturbance were observed. Recovery time varied among the years studied, of which 2017 saw the longest recovery time. In addition, pedestrians were the disturbance source with the longest recovery time. Given that resting on land is essential for pup survival, which depends on both the establishment of the mother-pup bond from birth and its maintenance throughout nursing, flushing behavior may have significant implications for the entire colony during the nursing season. We recorded a decrease in nursing duration, which did not return to the same level even after recovery and the resumption of nursing. Terrestrial vehicles were found to be the disturbance source that shortened nursing events most significantly.

Asunto(s)

Phoca , Animales , Estuarios , Actividades Humanas , Humanos , México , Estaciones del Año

RESUMEN

Global biodiversity loss by anthropogenic impacts is an under-recognized form of global environmental change. Global defaunation is still poorly documented in the case of insects, showing a significant decrease in populations and diversity. The blowfly Neta chilensis (Walker 1837) is poorly known and presumed to be confined to southern-South America, with an unclear distributional pattern. It was last collected in 1984. We aimed, through Ecological Niche Models, to identify regions highly suitable for N. chilensis; to test the suitability of regions with doubtful records; to understand the impact that climatic change and human activities have had; and to identify regions with high chances to find it. We compiled 130 presence records from Argentina and Chile and 117 localities where it was sought but not found between 1987 and 2018. Results indicate that suitable conditions are restricted to southern and central Chile and to southwestern Argentina, that doubtful records are predicted in unsuitable areas, that N. chilensis occupies a narrow niche and that its decline is not mainly caused by climate changes but more probably to habitat loss and to the biological invasion. We identified two regions where the chances of finding the species are higher in the case that it is not extinct already.

Asunto(s)

Cambio Climático , Ecosistema , Biodiversidad , Chile , Actividades Humanas , Humanos

RESUMEN

Demersal fisheries are one of the top anthropic stressors in marine environments. In the long term, some species are more vulnerable to fishery impacts than others, which can lead to permanent changes on the food web. The trophic relationships between predator and prey constitute the food web and it represents a network of the energy channels in an ecosystem. In turn, the network structure influences ecosystem diversity and stability. The first aim of this study was to describe for the first time the food web of the San Jorge Gulf (Patagonia Argentina) with high resolution, i.e. to the species level when information is available. The San Jorge Gulf was subject to intense fisheries thus our second aim is to analyse the food web structure with and without fishery to evaluate if the bottom-trawl industrial fishery altered the network structure and stability. We used several network metrics like: mean trophic level, omnivory, modularity and quasi-sign stability. We included these metrics because they are related to stability and can be evaluated using predator diets that can weight the links between predators and prey. The network presented 165 species organized in almost five trophic levels. The inclusion of a fishery node adds 69 new trophic links. All weighted and unweighted metrics showed differences between the two networks, reflecting a decrease in stability when fishery was included in the system. Thus, our results suggested a probable change of state of the system. The observed changes in species abundances since the fishery was established, could represent the state change predicted by network analysis. Our results suggests that changes in the stability of food webs can be used to evaluate the impacts of human activity on ecosystems.

Asunto(s)

Explotaciones Pesqueras , Cadena Alimentaria , Dieta , Ecosistema , Actividades Humanas , Humanos

RESUMEN

Oceanic islands support unique biotas but often lack ecological redundancy, so that the removal of a species can have a large effect on the ecosystem. The larger islands of the Galápagos Archipelago once had one or two species of giant tortoise that were the dominant herbivore. Using paleoecological techniques, we investigate the ecological cascade on highland ecosystems that resulted from whalers removing many thousands of tortoises from the lowlands. We hypothesize that the seasonal migration of a now-extinct tortoise species to the highlands was curtailed by decreased intraspecific competition. We find the trajectory of plant community dynamics changed within a decade of the first whaling vessels visiting the islands. Novel communities established, with a previously uncommon shrub, Miconia, replacing other shrubs of the genera Alternanthera and Acalypha. It was, however, the introduction of cattle and horses that caused the local extirpation of plant species, with the most extreme impacts being evident after c. 1930. This modified ecology is considered the natural state of the islands and has shaped subsequent conservation policy and practice. Restoration of El Junco Crater should emphasize exclusion of livestock, rewilding with tortoises, and expanding the ongoing plantings of Miconia to also include Acalypha and Alternanthera.

Asunto(s)

Ecosistema , Extinción Biológica , Tortugas , Animales , Evolución Biológica , Bovinos , Ecología , Ecuador , Herbivoria , Actividades Humanas , Humanos

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)

Algoritmos , Actividades Humanas , Anciano , Humanos , Esqueleto

RESUMEN

Indoor localization and human activity recognition are two important sources of information to provide context-based assistance. This information is relevant in ambient assisted living (AAL) scenarios, where older adults usually need supervision and assistance in their daily activities. However, indoor localization and human activity recognition have been mostly considered isolated problems. This work presents and evaluates a framework that takes advantage of the relationship between location and activity to simultaneously perform indoor localization, mapping, and human activity recognition. The proposed framework provides a non-intrusive configuration, which fuses data from an inertial measurement unit (IMU) placed in the person's shoe, with proximity and human activity-related data from Bluetooth low energy beacons (BLE) deployed in the indoor environment. A variant of the simultaneous location and mapping (SLAM) framework was used to fuse the location and human activity recognition (HAR) data. HAR was performed using data streaming algorithms. The framework was evaluated in a pilot study, using data from 22 people, 11 young people, and 11 older adults (people aged 65 years or older). As a result, seven activities of daily living were recognized with an F1 score of 88%, and the in-door location error was 0.98 ± 0.36 m for the young and 1.02 ± 0.24 m for the older adults. Furthermore, there were no significant differences between the groups, indicating that our proposed method works adequately in broad age ranges.

Asunto(s)

Inteligencia Ambiental , Actividades Cotidianas , Adolescente , Anciano , Algoritmos , Actividades Humanas , Humanos , Proyectos Piloto