Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 4.100
Filtrar
1.
Sensors (Basel) ; 24(11)2024 May 24.
Artigo em Inglês | MEDLINE | ID: mdl-38894162

RESUMO

Composite indoor human activity recognition is very important in elderly health monitoring and is more difficult than identifying individual human movements. This article proposes a sensor-based human indoor activity recognition method that integrates indoor positioning. Convolutional neural networks are used to extract spatial information contained in geomagnetic sensors and ambient light sensors, while transform encoders are used to extract temporal motion features collected by gyroscopes and accelerometers. We established an indoor activity recognition model with a multimodal feature fusion structure. In order to explore the possibility of using only smartphones to complete the above tasks, we collected and established a multisensor indoor activity dataset. Extensive experiments verified the effectiveness of the proposed method. Compared with algorithms that do not consider the location information, our method has a 13.65% improvement in recognition accuracy.


Assuntos
Acelerometria , Algoritmos , Atividades Humanas , Redes Neurais de Computação , Smartphone , Humanos , Acelerometria/instrumentação , Acelerometria/métodos , Monitorização Fisiológica/instrumentação , Monitorização Fisiológica/métodos
2.
Ying Yong Sheng Tai Xue Bao ; 35(5): 1312-1320, 2024 May.
Artigo em Chinês | MEDLINE | ID: mdl-38886430

RESUMO

Understanding the influences of climate change and human activities on vegetation change is the foundation for effective ecosystem management. Based on the 250 m MODIS-NDVI data from 2002 to 2020, we employed Theil-Sen Median trend analysis and the Mann-Kendall test to quantify vegetation change in Hunan Province. By combining with meteorological, nighttime light index, land cover and other data, residual analysis and correlation analysis, we examined the impacts of human activities and climate change on vegetation dynamics at both the pixel level and the county level. The results showed that the normalized difference vegetation index (NDVI) in Hunan Province exhibited a spatial pattern of "overall improvement with localized degradation" during 2002-2020. Approximately 64.9% of the study area experienced significant vegetation improvement, mainly occurring in the western and central-southern parts of Hunan Province. 1.4% of the study area experienced significant vegetation degradation, mostly in the newly developed urban areas and the farmland in the Dongting Lake Plain. Human activities and climate change jointly promoted vegetation improvement in 67.9% of the study area. Human activities and climate contributed to 96% and 4% of the NDVI change, respectively. At the county level, human activities contributed to over 80% of the NDVI change in each district or county. The impacts of human activities on vegetation change exhibited significant spatial heterogeneity. Urban expansion led to vegetation degradation in the newly developed areas, while vegetation growth appeared in the old developed urban areas. The ecological restoration projects promoted vegetation restoration in the western part of Hunan Province. This study could help us better understand the spatiotemporal variations of vegetation and their responses to climate change and human activities, which would offer scientific basis for effective ecological restoration policy.


Assuntos
Mudança Climática , Ecossistema , Monitoramento Ambiental , China , Monitoramento Ambiental/métodos , Conservação dos Recursos Naturais , Imagens de Satélites , Atividades Humanas , Desenvolvimento Vegetal , Árvores/crescimento & desenvolvimento
3.
Sci Rep ; 14(1): 13574, 2024 06 12.
Artigo em Inglês | MEDLINE | ID: mdl-38866833

RESUMO

Microplastic pollution is a significant global environmental issue, and impacts span from individual organisms to the entire ecosystems. This study investigated the properties of microplastics in amphibian larvae, shedding light on their environmental interactions and potential ecological consequences. We examined microplastics extracted from amphibian larvae of 10 taxa, sampled from sites experiencing different levels of human impact. Our findings revealed a predominance of blue microplastics and fibres, each comprising 53% of the total microplastics in amphibian larvae. Microplastic fibres were also notably longer than other morphological types of microplastics. Furthermore, we observed variations in the surface area of microplastics among different amphibian families. An interesting observation from our research is the apparent positive relationship between the size of amphibian larvae and the length of granular and flake-shaped microplastics. Conversely, we observed a negative relationship between the length of these microplastics and human environmental impact. These insights significantly contribute to the understanding of microplastic pollution in freshwater environments, highlighting its complexities beyond marine ecosystems. Our research emphasises the intricate relationships between microplastics and freshwater organisms, underscoring the need for comprehensive strategies to mitigate microplastic pollution.


Assuntos
Anfíbios , Larva , Microplásticos , Microplásticos/análise , Animais , Humanos , Anfíbios/metabolismo , Poluentes Químicos da Água/análise , Ecossistema , Monitoramento Ambiental/métodos , Atividades Humanas
4.
J Environ Manage ; 362: 121335, 2024 Jun.
Artigo em Inglês | MEDLINE | ID: mdl-38833934

RESUMO

Transitional features of desert environments partially determine the risks associated with ecosystems. Influenced by climate change and human activities, the variability and uncertainty of desertification levels and ecological risks in the Qinghai Area of Qilian Mountain National Park (QMNPQA) has become increasingly prominent. As a critical ecological barrier in northwest China, monitoring desertification dynamics and ecological risks is crucial for maintaining ecosystem stability. This study identifies the optimal monitoring model from four constructed desertification monitoring models and analyzes spatiotemporal changes in desertification. The spatial and temporal changes in ecological risks and their primary driving factors were analyzed using methods such as raster overlay calculation, geographic detector, cloud model, and trend analysis. The main conclusions are as follows: The desertification feature spatial model based on GNDVI-Albedo demonstrates better applicability in the study area, with an inversion accuracy of 81.24%. The levels of desertification and ecological risks in QMNPQA exhibit significant spatial heterogeneity, with a gradual decrease observed from northwest to southeast. From 2000 to 2020, there is an overall decreasing trend in desertification levels and ecological risks, with the decreasing trend area accounting for 89.82% and 85.71% respectively, mainly concentrated in the southeastern and northwestern parts of the study area. The proportion of areas with increasing trends is 4.49% and 7.05% respectively, scattered in patches in the central and southern edge areas. Surface temperature (ST), Digital Elevation Map (DEM), and Green normalized difference vegetation index (GNDVI) are the most influential factors determining the spatial distribution of ecological risks in QMNPQA. The effects of management and climatic factors on ecological risks demonstrate a significant antagonistic effect, highlighting the positive contributions of human activities in mitigating the driving effects of climate change on ecological risks. The research results can provide reference for desertification prevention and ecological quality improvement in QMNPQA.


Assuntos
Mudança Climática , Conservação dos Recursos Naturais , Ecossistema , Atividades Humanas , Parques Recreativos , China , Humanos , Ecologia
5.
Mar Pollut Bull ; 204: 116533, 2024 Jul.
Artigo em Inglês | MEDLINE | ID: mdl-38833949

RESUMO

Coastal waters face significant anthropogenic stress, particularly from tourism, exacerbating pollution, especially in areas like touristic islands. Ischia, the largest island in the Gulf of Naples and part of the Regno di Nettuno Marine Protected Area, suffers from pollution due to tourism and maritime traffic. During the initial SARS-CoV-2 lockdown from March to June 2020, Ischia was isolated, providing a unique opportunity to study pollutant release and its impact on coastal ecosystems. Adult Mytilus galloprovincialis mussels were transplanted to three sites on the island for active biomonitoring. Accumulation of chemicals in tissues and biomarkers related to metabolism, detoxification, and oxidative stress were measured. Results indicated that pollutants from daily activities entered the sea, affecting filter feeders. Translocated organisms showed modulated metabolic functions and biochemical changes, highlighting coastal vulnerability and calling for conservation efforts.


Assuntos
Monitoramento Biológico , Mytilus , Animais , Humanos , COVID-19 , Turismo , Monitoramento Ambiental , Poluentes Químicos da Água/análise , Ilhas , Atividades Humanas , Itália , SARS-CoV-2
6.
Sci Total Environ ; 943: 173741, 2024 Sep 15.
Artigo em Inglês | MEDLINE | ID: mdl-38857808

RESUMO

The Tibetan Plateau (TP) is one of the most challenging areas for human long-term settlement due to its extreme living environment. Understanding the relationship between human activities and environmental changes in this extreme environment is important and can provide a historical reference for adapting to future climate change. In this study, we took the Angren Basin in the southern TP as a case study to elucidate the relationship since Little Ice Age (LIA). Using fecal stanol in feces, lake and river surface sediments, surface soils, and sediment core, we found that specific indices S1 and S2 from the composition of coprostanol, epicoprostanol, 5ß-ethylcoprostanol and 5ß-ethylepicoprostanol can reflect changes in human population and herbivores, respectively. Through the comparison between environmental changes determined by grain size, elements, sedimentation rate, and other climate records, the relationship between human activities and environmental changes was interpreted. Our results indicate that: (i) during 1480-1820 CE, the fecal stanols in lake sediments mainly originated from livestock, and the human population was low. In contrast, during 1820-2021 CE, the proportion and flux of S1 have been continuously increasing, indicating significant population growth. (ii) During the middle LIA, the cold-dry climate inhibited the development of agriculture and farming. However, the increased precipitation during the late LIA promoted that development, resulting in an increase in human population and livestock in a short term. (iii) Since 1951, people have reclaimed wasteland and developed husbandry, leading to increased soil erosion. (iv) Over the past 40 years, with a warm-humid climate and good policy support, human activities, such as agriculture and husbandry, have rapidly increased, but soil erosion has declined in the recent 20 years due to good soil-water conservation efforts. This study sheds light on the relationship between human activities and environmental changes and provides insights into future climate change responses.


Assuntos
Mudança Climática , Monitoramento Ambiental , Atividades Humanas , Tibet , Humanos , Lagos/química , Sedimentos Geológicos/química , Fezes/química , Solo/química
7.
Ying Yong Sheng Tai Xue Bao ; 35(4): 1092-1100, 2024 Apr 18.
Artigo em Chinês | MEDLINE | ID: mdl-38884244

RESUMO

To explore the influence of climate change and human activities on grassland phenology in Anhui Pro-vince, and quantify the contribution rate of climate change and human activities to phenology, we extracted the phenology of grassland, including the start of growing season (SOS) and the end of growing season (EOS), based on the normalized difference vegetation index (NDVI) dataset of Anhui Province from 2003 to 2020. The temporal and spatial characteristics and future evolution trends of phenological changes were analyzed using slope trend ana-lysis, Mann-Kendall non-parametric test, and Hurst index. We further conducted correlation analysis and residual analysis based on the datasets of mean annual temperature and mean annual precipitation to explore the responses of phenology to climate change and human activities, and quantify their contribution rate. The results showed that SOS and EOS showed an advancing trend with a rate of 0.8 and 0.7 days per year from 2003 to 2020. SOS in the sou-thern part of the study area was significantly earlier than in the central and northern regions, while EOS gradually advanced from south to north. Both SOS and EOS in the future showed an advancing trend. SOS was negatively correlated with annual average temperature, while positively correlated with annual precipitation. EOS was negatively correlated with both annual average temperature and annual precipitation. The proportion of the area where SOS was advanced driven by both climate change and human activities was 56.9%, and the value was 48.3% for EOS. Human activities were the main driving factor for phenology, and climate change was the secondary driving factor. The relative contributions of human activities and climate change to SOS were 66.4% and 33.6%, and to EOS were 61.2% and 38.8%, respectively. Human activities had stronger impact on SOS and EOS than climate change, resulting in earlier phenology.


Assuntos
Mudança Climática , Pradaria , Atividades Humanas , China , Estações do Ano , Humanos , Ecossistema , Poaceae/crescimento & desenvolvimento
8.
Opt Express ; 32(10): 16645-16656, 2024 May 06.
Artigo em Inglês | MEDLINE | ID: mdl-38858865

RESUMO

Single-Photon Avalanche Diode (SPAD) direct Time-of-Flight (dToF) sensors provide depth imaging over long distances, enabling the detection of objects even in the absence of contrast in colour or texture. However, distant objects are represented by just a few pixels and are subject to noise from solar interference, limiting the applicability of existing computer vision techniques for high-level scene interpretation. We present a new SPAD-based vision system for human activity recognition, based on convolutional and recurrent neural networks, which is trained entirely on synthetic data. In tests using real data from a 64×32 pixel SPAD, captured over a distance of 40 m, the scheme successfully overcomes the limited transverse resolution (in which human limbs are approximately one pixel across), achieving an average accuracy of 89% in distinguishing between seven different activities. The approach analyses continuous streams of video-rate depth data at a maximal rate of 66 FPS when executed on a GPU, making it well-suited for real-time applications such as surveillance or situational awareness in autonomous systems.


Assuntos
Fótons , Humanos , Atividades Humanas , Redes Neurais de Computação , Reconhecimento Automatizado de Padrão/métodos , Desenho de Equipamento
9.
Environ Geochem Health ; 46(7): 218, 2024 Jun 07.
Artigo em Inglês | MEDLINE | ID: mdl-38849659

RESUMO

Human activity factors have a significant impact on changes in ammonia nitrogen (NH3-N) content in rivers. Existing research mainly focuses on human activity factors as type factors, and lacks research on the key factors affecting river NH3-N among human activity factors. Therefore, this paper aims to study the key factors affecting human activities on NH3-N in the Huaihe River through various statistical analysis methods. The study found that changes in NH3-N content in the Huaihe River are mainly affected by land use patterns in the basin. There are two different ways in which land use affects NH3-N in rivers: direct effects and indirect effects. We also studied the main pathways through which changes in key factors in human activities affect NH3-N in the Huaihe River by constructing a structural equation model. The results showed that crop sowing area and afforestation area have a significant direct effect on NH3-N in the Huaihe River. In addition, crop sowing area and afforestation area can also affect river NH3-N by regulating the amount of nitrogen fertilizer and human excrement. This study is of great significance for understanding how human activities regulate NH3-N content in rivers.


Assuntos
Amônia , Rios , Rios/química , China , Humanos , Amônia/análise , Atividades Humanas , Monitoramento Ambiental , Agricultura , Poluentes Químicos da Água/análise , Nitrogênio/análise , Fertilizantes
10.
Science ; 384(6701): 1191-1195, 2024 Jun 14.
Artigo em Inglês | MEDLINE | ID: mdl-38815088

RESUMO

Rivers and streams contribute to global carbon cycling by decomposing immense quantities of terrestrial plant matter. However, decomposition rates are highly variable and large-scale patterns and drivers of this process remain poorly understood. Using a cellulose-based assay to reflect the primary constituent of plant detritus, we generated a predictive model (81% variance explained) for cellulose decomposition rates across 514 globally distributed streams. A large number of variables were important for predicting decomposition, highlighting the complexity of this process at the global scale. Predicted cellulose decomposition rates, when combined with genus-level litter quality attributes, explain published leaf litter decomposition rates with high accuracy (70% variance explained). Our global map provides estimates of rates across vast understudied areas of Earth and reveals rapid decomposition across continental-scale areas dominated by human activities.


Assuntos
Atividades Humanas , Folhas de Planta , Rios , Rios/química , Humanos , Celulose , Ciclo do Carbono , Plantas/metabolismo
11.
Sci Rep ; 14(1): 12411, 2024 05 30.
Artigo em Inglês | MEDLINE | ID: mdl-38816446

RESUMO

Knowledge distillation is an effective approach for training robust multi-modal machine learning models when synchronous multimodal data are unavailable. However, traditional knowledge distillation techniques have limitations in comprehensively transferring knowledge across modalities and models. This paper proposes a multiscale knowledge distillation framework to address these limitations. Specifically, we introduce a multiscale semantic graph mapping (SGM) loss function to enable more comprehensive knowledge transfer between teacher and student networks at multiple feature scales. We also design a fusion and tuning (FT) module to fully utilize correlations within and between different data types of the same modality when training teacher networks. Furthermore, we adopt transformer-based backbones to improve feature learning compared to traditional convolutional neural networks. We apply the proposed techniques to multimodal human activity recognition and compared with the baseline method, it improved by 2.31% and 0.29% on the MMAct and UTD-MHAD datasets. Ablation studies validate the necessity of each component.


Assuntos
Atividades Humanas , Aprendizado de Máquina , Redes Neurais de Computação , Humanos , Algoritmos , Atenção
12.
Philos Trans R Soc Lond B Biol Sci ; 379(1905): 20230185, 2024 Jul 08.
Artigo em Inglês | MEDLINE | ID: mdl-38768208

RESUMO

Acoustic communication plays an important role in coordinating group dynamics and collective movements across a range of taxa. However, anthropogenic disturbance can inhibit the production or reception of acoustic signals. Here, we investigate the effects of noise and light pollution on the calling and collective behaviour of wild jackdaws (Corvus monedula), a highly social corvid species that uses vocalizations to coordinate collective movements at winter roosting sites. Using audio and video monitoring of roosts in areas with differing degrees of urbanization, we evaluate the influence of anthropogenic disturbance on vocalizations and collective movements. We found that when levels of background noise were higher, jackdaws took longer to settle following arrival at the roost in the evening and also called more during the night, suggesting that human disturbance may cause sleep disruption. High levels of overnight calling were, in turn, linked to disruption of vocal consensus decision-making and less cohesive group departures in the morning. These results raise the possibility that, by affecting cognitive and perceptual processes, human activities may interfere with animals' ability to coordinate collective behaviour. Understanding links between anthropogenic disturbance, communication, cognition and collective behaviour must be an important research priority in our increasingly urbanized world. This article is part of the theme issue 'The power of sound: unravelling how acoustic communication shapes group dynamics'.


Assuntos
Corvos , Ruído , Comportamento Social , Vocalização Animal , Animais , Corvos/fisiologia , Efeitos Antropogênicos , Atividades Humanas
13.
Sensors (Basel) ; 24(10)2024 May 09.
Artigo em Inglês | MEDLINE | ID: mdl-38793858

RESUMO

Inertial signals are the most widely used signals in human activity recognition (HAR) applications, and extensive research has been performed on developing HAR classifiers using accelerometer and gyroscope data. This study aimed to investigate the potential enhancement of HAR models through the fusion of biological signals with inertial signals. The classification of eight common low-, medium-, and high-intensity activities was assessed using machine learning (ML) algorithms, trained on accelerometer (ACC), blood volume pulse (BVP), and electrodermal activity (EDA) data obtained from a wrist-worn sensor. Two types of ML algorithms were employed: a random forest (RF) trained on features; and a pre-trained deep learning (DL) network (ResNet-18) trained on spectrogram images. Evaluation was conducted on both individual activities and more generalized activity groups, based on similar intensity. Results indicated that RF classifiers outperformed corresponding DL classifiers at both individual and grouped levels. However, the fusion of EDA and BVP signals with ACC data improved DL classifier performance compared to a baseline DL model with ACC-only data. The best performance was achieved by a classifier trained on a combination of ACC, EDA, and BVP images, yielding F1-scores of 69 and 87 for individual and grouped activity classifications, respectively. For DL models trained with additional biological signals, almost all individual activity classifications showed improvement (p-value < 0.05). In grouped activity classifications, DL model performance was enhanced for low- and medium-intensity activities. Exploring the classification of two specific activities, ascending/descending stairs and cycling, revealed significantly improved results using a DL model trained on combined ACC, BVP, and EDA spectrogram images (p-value < 0.05).


Assuntos
Acelerometria , Algoritmos , Aprendizado de Máquina , Fotopletismografia , Humanos , Fotopletismografia/métodos , Acelerometria/métodos , Masculino , Adulto , Processamento de Sinais Assistido por Computador , Feminino , Atividades Humanas , Resposta Galvânica da Pele/fisiologia , Dispositivos Eletrônicos Vestíveis , Adulto Jovem
14.
Sensors (Basel) ; 24(10)2024 May 16.
Artigo em Inglês | MEDLINE | ID: mdl-38794015

RESUMO

WiFi Channel State Information (CSI)-based human action recognition using convolutional neural networks (CNNs) has emerged as a promising approach for non-intrusive activity monitoring. However, the integrity and reliability of the reported performance metrics are susceptible to data leakage, wherein information from the test set inadvertently influences the training process, leading to inflated accuracy rates. In this paper, we conduct a critical analysis of a notable IEEE Sensors Journal study on WiFi CSI-based human action recognition, uncovering instances of data leakage resulting from the absence of subject-based data partitioning. Empirical investigation corroborates the lack of exclusivity of individuals across dataset partitions, underscoring the importance of rigorous data management practices. Furthermore, we demonstrate that employing data partitioning with respect to humans results in significantly lower precision rates than the reported 99.9% precision, highlighting the exaggerated nature of the original findings. Such inflated results could potentially discourage other researchers and impede progress in the field by fostering a sense of complacency.


Assuntos
Redes Neurais de Computação , Humanos , Tecnologia sem Fio , Algoritmos , Atividades Humanas , Reprodutibilidade dos Testes
15.
Sci Rep ; 14(1): 10560, 2024 05 08.
Artigo em Inglês | MEDLINE | ID: mdl-38720020

RESUMO

The research on video analytics especially in the area of human behavior recognition has become increasingly popular recently. It is widely applied in virtual reality, video surveillance, and video retrieval. With the advancement of deep learning algorithms and computer hardware, the conventional two-dimensional convolution technique for training video models has been replaced by three-dimensional convolution, which enables the extraction of spatio-temporal features. Specifically, the use of 3D convolution in human behavior recognition has been the subject of growing interest. However, the increased dimensionality has led to challenges such as the dramatic increase in the number of parameters, increased time complexity, and a strong dependence on GPUs for effective spatio-temporal feature extraction. The training speed can be considerably slow without the support of powerful GPU hardware. To address these issues, this study proposes an Adaptive Time Compression (ATC) module. Functioning as an independent component, ATC can be seamlessly integrated into existing architectures and achieves data compression by eliminating redundant frames within video data. The ATC module effectively reduces GPU computing load and time complexity with negligible loss of accuracy, thereby facilitating real-time human behavior recognition.


Assuntos
Algoritmos , Compressão de Dados , Gravação em Vídeo , Humanos , Compressão de Dados/métodos , Atividades Humanas , Aprendizado Profundo , Processamento de Imagem Assistida por Computador/métodos , Reconhecimento Automatizado de Padrão/métodos
16.
Environ Sci Technol ; 58(19): 8510-8517, 2024 May 14.
Artigo em Inglês | MEDLINE | ID: mdl-38695484

RESUMO

Anthropogenic activities have fundamentally changed the chemistry of the Baltic Sea. According to results reported in this study, not even the thallium (Tl) isotope cycle is immune to these activities. In the anoxic and sulfidic ("euxinic") East Gotland Basin today, Tl and its two stable isotopes are cycled between waters and sediments as predicted based on studies of other redox-stratified basins (e.g., the Black Sea and Cariaco Trench). The Baltic seawater Tl isotope composition (ε205Tl) is, however, higher than predicted based on the results of conservative mixing calculations. Data from a short sediment core from East Gotland Basin demonstrates that this high seawater ε205Tl value originated sometime between about 1940 and 1947 CE, around the same time other prominent anthropogenic signatures begin to appear in the same core. This juxtaposition is unlikely to be coincidental and suggests that human activities in the surrounding area have altered the seawater Tl isotope mass-balance of the Baltic Sea.


Assuntos
Sedimentos Geológicos , Oceanos e Mares , Água do Mar , Tálio , Água do Mar/química , Sedimentos Geológicos/química , Atividades Humanas , Humanos , Monitoramento Ambiental , Poluentes Químicos da Água , Isótopos
17.
Sensors (Basel) ; 24(9)2024 Apr 23.
Artigo em Inglês | MEDLINE | ID: mdl-38732771

RESUMO

Human activity recognition (HAR) technology enables continuous behavior monitoring, which is particularly valuable in healthcare. This study investigates the viability of using an ear-worn motion sensor for classifying daily activities, including lying, sitting/standing, walking, ascending stairs, descending stairs, and running. Fifty healthy participants (between 20 and 47 years old) engaged in these activities while under monitoring. Various machine learning algorithms, ranging from interpretable shallow models to state-of-the-art deep learning approaches designed for HAR (i.e., DeepConvLSTM and ConvTransformer), were employed for classification. The results demonstrate the ear sensor's efficacy, with deep learning models achieving a 98% accuracy rate of classification. The obtained classification models are agnostic regarding which ear the sensor is worn and robust against moderate variations in sensor orientation (e.g., due to differences in auricle anatomy), meaning no initial calibration of the sensor orientation is required. The study underscores the ear's efficacy as a suitable site for monitoring human daily activity and suggests its potential for combining HAR with in-ear vital sign monitoring. This approach offers a practical method for comprehensive health monitoring by integrating sensors in a single anatomical location. This integration facilitates individualized health assessments, with potential applications in tele-monitoring, personalized health insights, and optimizing athletic training regimes.


Assuntos
Dispositivos Eletrônicos Vestíveis , Humanos , Adulto , Masculino , Feminino , Pessoa de Meia-Idade , Adulto Jovem , Atividades Humanas , Orelha/fisiologia , Algoritmos , Atividades Cotidianas , Aprendizado de Máquina , Aprendizado Profundo , Monitorização Fisiológica/instrumentação , Monitorização Fisiológica/métodos , Movimento (Física) , Caminhada/fisiologia
18.
Sensors (Basel) ; 24(9)2024 Apr 25.
Artigo em Inglês | MEDLINE | ID: mdl-38732841

RESUMO

Shadow, a natural phenomenon resulting from the absence of light, plays a pivotal role in agriculture, particularly in processes such as photosynthesis in plants. Despite the availability of generic shadow datasets, many suffer from annotation errors and lack detailed representations of agricultural shadows with possible human activity inside, excluding those derived from satellite or drone views. In this paper, we present an evaluation of a synthetically generated top-down shadow segmentation dataset characterized by photorealistic rendering and accurate shadow masks. We aim to determine its efficacy compared to real-world datasets and assess how factors such as annotation quality and image domain influence neural network model training. To establish a baseline, we trained numerous baseline architectures and subsequently explored transfer learning using various freely available shadow datasets. We further evaluated the out-of-domain performance compared to the training set of other shadow datasets. Our findings suggest that AgroSegNet demonstrates competitive performance and is effective for transfer learning, particularly in domains similar to agriculture.


Assuntos
Agricultura , Atividades Humanas , Redes Neurais de Computação , Agricultura/métodos , Humanos
19.
PLoS One ; 19(5): e0300577, 2024.
Artigo em Inglês | MEDLINE | ID: mdl-38728344

RESUMO

To quantitatively analyze the impact of climate variability and human activities on grassland productivity of China's Qilian Mountain National Park, this study used Carnegic-Ames-Stanford Approach model (CASA) and Integrated Vegetation model improved by the Comprehensive and Sequential Classification System (CSCS) to assess the trends of grassland NPP from 2000 to 2015, the residual trend analysis method was used to quantify the impact of human activities and climate change on the grassland based on the NPP changes. The actual grassland NPP accumulation mainly occurred in June, July and August (autumn); the actual NPP showed a fluctuating upward trend with an average increase of 2.2 g C·m-2 a-1, while the potential NPP increase of 1.6 g C·m-2 a-1 and human-induced NPP decreased of 0.5 g C·m-2 a-1. The annual temperature showed a fluctuating upward trend with an average increase of 0.1°C 10a-1, but annual precipitation showed a fluctuating upward trend with an average annual increase of 1.3 mm a-1 from 2000 to 2015. The area and NPP of grassland degradation caused by climate variability was significantly greater than that caused by human activities and mainly distributed in the northwest and central regions, but area and NPP of grassland restored caused by human activities was significantly greater than that caused by climate variability and mainly distributed in the southeast regions. In conclusion, grassland in Qilian Mountain National Park showed a trend of degradation based on distribution area, but showed a trend of restoration based on actual NPP. Climate variability was the main cause of grassland degradation in the northwestern region of study area, and restoration of grassland in the eastern region was the result of the combined effects of human activities and climate variability. Under global climate change, the establishment of Qilian Mountain National Park was of great significance to the grassland's protection and the grasslands ecological restoration that have been affected by humans.


Assuntos
Mudança Climática , Pradaria , Atividades Humanas , Parques Recreativos , China , Humanos , Conservação dos Recursos Naturais , Clima , Ecossistema , Temperatura
20.
Mol Ecol ; 33(11): e17353, 2024 Jun.
Artigo em Inglês | MEDLINE | ID: mdl-38613250

RESUMO

Effective population size (Ne) is a particularly useful metric for conservation as it affects genetic drift, inbreeding and adaptive potential within populations. Current guidelines recommend a minimum Ne of 50 and 500 to avoid short-term inbreeding and to preserve long-term adaptive potential respectively. However, the extent to which wild populations reach these thresholds globally has not been investigated, nor has the relationship between Ne and human activities. Through a quantitative review, we generated a dataset with 4610 georeferenced Ne estimates from 3829 populations, extracted from 723 articles. These data show that certain taxonomic groups are less likely to meet 50/500 thresholds and are disproportionately impacted by human activities; plant, mammal and amphibian populations had a <54% probability of reaching N ̂ e = 50 and a <9% probability of reaching N ̂ e = 500. Populations listed as being of conservation concern according to the IUCN Red List had a smaller median N ̂ e than unlisted populations, and this was consistent across all taxonomic groups. N ̂ e was reduced in areas with a greater Global Human Footprint, especially for amphibians, birds and mammals, however relationships varied between taxa. We also highlight several considerations for future works, including the role that gene flow and subpopulation structure plays in the estimation of N ̂ e in wild populations, and the need for finer-scale taxonomic analyses. Our findings provide guidance for more specific thresholds based on Ne and help prioritise assessment of populations from taxa most at risk of failing to meet conservation thresholds.


Assuntos
Anfíbios , Conservação dos Recursos Naturais , Genética Populacional , Mamíferos , Densidade Demográfica , Animais , Anfíbios/genética , Anfíbios/classificação , Mamíferos/genética , Mamíferos/classificação , Fluxo Gênico , Aves/genética , Aves/classificação , Humanos , Endogamia , Deriva Genética , Plantas/genética , Plantas/classificação , Atividades Humanas
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...