With the growing advancement of wireless communication technologies,WiFi-based human sensing has gained increasing attention as a non-intrusive and device-free solution.Among the available signal types,Channel State I...With the growing advancement of wireless communication technologies,WiFi-based human sensing has gained increasing attention as a non-intrusive and device-free solution.Among the available signal types,Channel State Information(CSI)offers fine-grained temporal,frequency,and spatial insights into multipath propagation,making it a crucial data source for human-centric sensing.Recently,the integration of deep learning has significantly improved the robustness and automation of feature extraction from CSI in complex environments.This paper provides a comprehensive review of deep learning-enhanced human sensing based on CSI.We first outline mainstream CSI acquisition tools and their hardware specifications,then provide a detailed discussion of preprocessing methods such as denoising,time–frequency transformation,data segmentation,and augmentation.Subsequently,we categorize deep learning approaches according to sensing tasks—namely detection,localization,and recognition—and highlight representative models across application scenarios.Finally,we examine key challenges including domain generalization,multi-user interference,and limited data availability,and we propose future research directions involving lightweight model deployment,multimodal data fusion,and semantic-level sensing.展开更多
Human Activity Recognition(HAR)is a novel area for computer vision.It has a great impact on healthcare,smart environments,and surveillance while is able to automatically detect human behavior.It plays a vital role in ...Human Activity Recognition(HAR)is a novel area for computer vision.It has a great impact on healthcare,smart environments,and surveillance while is able to automatically detect human behavior.It plays a vital role in many applications,such as smart home,healthcare,human computer interaction,sports analysis,and especially,intelligent surveillance.In this paper,we propose a robust and efficient HAR system by leveraging deep learning paradigms,including pre-trained models,CNN architectures,and their average-weighted fusion.However,due to the diversity of human actions and various environmental influences,as well as a lack of data and resources,achieving high recognition accuracy remain elusive.In this work,a weighted average ensemble technique is employed to fuse three deep learning models:EfficientNet,ResNet50,and a custom CNN.The results of this study indicate that using a weighted average ensemble strategy for developing more effective HAR models may be a promising idea for detection and classification of human activities.Experiments by using the benchmark dataset proved that the proposed weighted ensemble approach outperformed existing approaches in terms of accuracy and other key performance measures.The combined average-weighted ensemble of pre-trained and CNN models obtained an accuracy of 98%,compared to 97%,96%,and 95%for the customized CNN,EfficientNet,and ResNet50 models,respectively.展开更多
Understanding the impacts of human activities on the plateau’s living environment is essential for advancing modernization pathways that promote harmony between humanity and nature.However,studies on the dynamic inte...Understanding the impacts of human activities on the plateau’s living environment is essential for advancing modernization pathways that promote harmony between humanity and nature.However,studies on the dynamic interactions between human activities and the living environment on the Qinghai-Xizang Plateau(QXP)remain limited,with a paucity of quantitative relationship analyses.This study established an assessment framework to evaluate human influences on the living environment in QXP,using data on typical human activities,ecological conditions,and human settlements.Within this framework,the spatial analysis methods and the coupling coordination model were used to examine the spatio-temporal characteristics and relationship of human activities and living environment on the QXP from 2000 to 2020.The geographical detector model was then applied to identify the key factors influencing the plateau’s human living environment.Subsequently,the four-quadrant analysis model was adopted to assess human influences on the living environment.The results indicate that the human activity intensity(HAI)on the QXP remained relatively low yet increased by 15.41%from 2000 to 2020.Spatially,the human living environment quality(LEQ)improved from northwest to southeast,with 61.14%of the areas remaining stable and 18.47%experiencing slight improvement.The analysis of coupling coordination revealed a continuous improvement between the HAI and LEQ,with the areas of high and relatively high coordinated types increasing by more than 9%.Precipitation and urban-rural construction were identified as the primary factors influencing changes in the LEQ.The interaction between the HAI and LEQ was strengthening,with 40.44%classified as coordinated development type and 38.35%as development-environment conflict type.These findings provide valuable insights for enhancing the resilience of human settlements and promoting green development across the plateau.展开更多
Prevention of biological invasion requires understanding how alien species invade native communities.Although studies have identified mechanisms that underlie plant invasion in some habitats,limited attention has focu...Prevention of biological invasion requires understanding how alien species invade native communities.Although studies have identified mechanisms that underlie plant invasion in some habitats,limited attention has focused on invasion patterns along elevational gradients.In this study,we asked which factors drive the global and regional distribution of the invasive plant Galinsoga quadriradiata along elevational gradients.To answer this question,we examined whether human activities(i.e.,roads)promote G.quadriradiata invasion,how seed dispersal-related traits of G.quadriradiata change along elevation gradients,and whether G.quadriradiata has adapted to high-elevation environments through phenotypic plasticity or genetic variation.On the global scale,we found that human activities and road density positively contribute to the G.quadriradiata expansion in mountainous areas.Field surveys in China revealed significant elevational differences in the seed dispersal traits of G.quadriradiata,with higher-elevation populations exhibiting lower dispersal ability and generally lower genetic diversity.Under common conditions,high-elevation populations showed higher leaf mass ratio but lower root mass ratio and reproductive allocation.This suggests that high-elevation environments create a barrier to dispersal for G.quadriradiata,and that G.quadriradiata has adapted phenotypically to these conditions.Our study indicates that the elevational invasion pattern of G.quadriradiata is shaped by multiple factors,particularly human activities and phenotypic adaptability.In addition,our finding that G.quadriradiata invasion at high elevations is not constrained by low genetic diversity indicates that monitoring and management of G.quadriradiata in mountainous areas should be strengthened.展开更多
Human activity recognition(HAR)is a method to predict human activities from sensor signals using machine learning(ML)techniques.HAR systems have several applications in various domains,including medicine,surveillance,...Human activity recognition(HAR)is a method to predict human activities from sensor signals using machine learning(ML)techniques.HAR systems have several applications in various domains,including medicine,surveillance,behavioral monitoring,and posture analysis.Extraction of suitable information from sensor data is an important part of the HAR process to recognize activities accurately.Several research studies on HAR have utilizedMel frequency cepstral coefficients(MFCCs)because of their effectiveness in capturing the periodic pattern of sensor signals.However,existing MFCC-based approaches often fail to capture sufficient temporal variability,which limits their ability to distinguish between complex or imbalanced activity classes robustly.To address this gap,this study proposes a feature fusion strategy that merges time-based and MFCC features(MFCCT)to enhance activity representation.The merged features were fed to a convolutional neural network(CNN)integrated with long shortterm memory(LSTM)—DeepConvLSTM to construct the HAR model.The MFCCT features with DeepConvLSTM achieved better performance as compared to MFCCs and time-based features on PAMAP2,UCI-HAR,and WISDM by obtaining an accuracy of 97%,98%,and 97%,respectively.In addition,DeepConvLSTM outperformed the deep learning(DL)algorithms that have recently been employed in HAR.These results confirm that the proposed hybrid features are not only practical but also generalizable,making them applicable across diverse HAR datasets for accurate activity classification.展开更多
Understanding the complex interactions between human activities and ecosystem functions is a prerequisite for achieving sustainable development.Since the implementation of the“Grain for Green”Project in 1999,ecosyst...Understanding the complex interactions between human activities and ecosystem functions is a prerequisite for achieving sustainable development.Since the implementation of the“Grain for Green”Project in 1999,ecosystem functions in China’s Loess Plateau have significantly improved.However,intensified human activities have also exacerbated the pressures on the region’s fragile ecological environment.This study investigates the spatiotemporal variations in the human activity intensity index(HAI)and net ecosystem benefits(NEB)from 2000 to 2020,using expert-based assessments and an enhanced cost-benefit evaluation framework.Results indicate that HAI increased by 16.7% and 16.6% at the grid and county levels,respectively.NEB exhibited pronounced spatial heterogeneity,with a total increase of USD 36.2 trillion at the grid scale.At the county level,the average NEB rose by 75%.The degree of trade-off was higher at the grid scale than at the county scale,while the synergistic areas initially expanded and then declined at both scales.Key areas for improvement and regions of lagging development were identified as priority zones for ecological management and spatial planning at both spatial resolutions.This study offers scientific insights and practical guidance for harmonizing ecological conservation with high-quality development in ecologically vulnerable regions.展开更多
Human activities have significantly impacted the land surface temperature(LST),endangering human health;however,the relationship between these two factors has not been adequately quantified.This study comprehensively ...Human activities have significantly impacted the land surface temperature(LST),endangering human health;however,the relationship between these two factors has not been adequately quantified.This study comprehensively constructs a Human Activity Intensity(HAI)index and employs the Maximal Information Coefficient,four-quadrant model,and XGBoostSHAP model to investigate the spatiotemporal relationship and influencing factors of HAI-LST in the Yellow River Basin(YRB)from 2000 to 2020.The results indicated that from 2000 to 2020,as HAI and LST increased,the static HAI-LST relationship in the YRB showed a positive correlation that continued to strengthen.This dynamic relationship exhibited conflicting development,with the proportion of coordinated to conflicting regions shifting from 1:4 to 1:2,indicating a reduction in conflict intensity.Notably,only the degree of conflict in the source area decreased significantly,whereas it intensified in the upper and lower reaches.The key factors influencing the HAI-LST relationship include fractional vegetation cover,slope,precipitation,and evapotranspiration,along with region-specific factors such as PM_(2.5),biodiversity,and elevation.Based on these findings,region-specific ecological management strategies have been proposed to mitigate conflict-prone areas and alleviate thermal stress,thereby providing important guidance for promoting harmonious development between humans and nature.展开更多
To address the deficiencies in comprehensive surface contamination prevention strategies within China's nitrate-affected regions,this research innovatively proposes the DITAPH model-a systematic framework integrat...To address the deficiencies in comprehensive surface contamination prevention strategies within China's nitrate-affected regions,this research innovatively proposes the DITAPH model-a systematic framework integrating groundwater nitrate vulnerability assessment and Nitrate Vulnerable Zones(NVZs)delineation through optimization of hydrogeological parameters.Based on detailed hydrogeological and hydrochemical investigations,the DITAPH model was applied in the plain areas of Quanzhou to evaluate its applicability.The model selected hydrogeological parameters(depth of groundwater,lithology of the vadose zone,topographic slope,aquifer water yield property),one climatic parameter(precipitation),and two anthropogenic parameters(land use type and population density)as assessment indicators.The results of the groundwater nitrate vulnerability assessment showed that the low,relatively low,relatively high,and high groundwater nitrate vulnerability zones in the study area accounted for 5.96%,35.44%,53.74%and 4.86%of the total area,respectively.Groundwater nitrate vulnerability was most strongly influenced by human activities,followed by groundwater depth and topographic slope.The high vulnerability zone is mainly affected by domestic and industrial wastewater,whereas the relatively high groundwater nitrate vulnerability zone is primarily influenced by agricultural activities.Validation of the DITAPH model revealed a significant positive correlation between the DITAPH index(DI)and nitrate concentration(ρ(NO3−)).The results of the NVZs delineated by the DITAPH model are reliable and can serve as a tool for water resource management planning,guiding the development of targeted measures in the NVZs to prevent groundwater contamination.展开更多
Carbon fluxes are essential indicators assessing vegetation carbon cycle functions.However,the extent and mechanisms by which climate change and human activities influence the spatiotemporal dynamics of carbon fluxes ...Carbon fluxes are essential indicators assessing vegetation carbon cycle functions.However,the extent and mechanisms by which climate change and human activities influence the spatiotemporal dynamics of carbon fluxes in arid oasis and non-oasis area remains unclear.Here,we assessed and predicted the future effects of climate change and human activities on carbon fluxes in the Hexi Corridor.The results showed that the annual average gross primary productivity(GPP),net ecosystem productivity(NEP),and ecosystem respiration(Reco)in the Hexi Corridor oasis increased by 263.91 g C·m^(-2)·yr^(-1),118.45 g C·m^(-2)·yr^(-1)and 122.46 g C·m^(-2)·yr^(-1),respectively,due to the expansion of the oasis area by 3424.84 km^(2) caused by human activities from 2000 to 2022.Both oasis and non-oasis arid ecosystems in the Hexi Corridor acted as carbon sinks.Compared to the non-oasis area,the carbon fluxes contributions of oasis area increased,ranging from 10.21%to 13.99%for GPP,8.50%to11.68%for NEP,and 13.34%to 17.13%for Reco.The contribution of the carbon flux from the oasis expansion area to the total carbon flux change in the Hexi Corridor was 30.96%(7.09 Tg C yr^(-1))for GPP,29.57%(3.39 Tg C yr^(-1))for NEP and 32.40%(3.58 Tg C yr^(-1))for Reco.The changes in carbon fluxes in the oasis area were mainly attributed to human activities(oasis expansion)and temperature,whereas non-oasis area was mainly due to climate factors.Moreover,the future increasing trends were observed for GPP(64.99%),NEP(66.29%)and Reco(82.08%)in the Hexi Corridor.This study provides new insights into the regulatory mechanisms of carbon cycle in the arid oasis and non-oasis area.展开更多
The Turpan-Hami(Tuha)Basin of China,a critical region on the Silk Road Economic Belt and a major national energy base,occupies a significant position in energy security and in the major industrial clusters in Xinjiang...The Turpan-Hami(Tuha)Basin of China,a critical region on the Silk Road Economic Belt and a major national energy base,occupies a significant position in energy security and in the major industrial clusters in Xinjiang Uygur Autonomous Region,China.Understanding spatial and temporal evolution of human activities in this area is essential for harmonizing ecological protection with energy development,safeguarding the ecological security of the Silk Road Economic Belt,and promoting the sustainable development of the area.However,despite rapid socioeconomic advances,the trajectories of human activity intensity and the principal driving mechanisms over the past three decades remain inadequately understood.To address these gaps,this study constructed a land use dataset for the Tuha Basin from 1990 to 2020,utilizing Google Earth Engine(GEE)and random forest classification algorithm.We assessed the intensity of human activities and their spatial autocorrelation patterns and further identified key drivers influencing spatial and temporal variations using the Geodetector model.Our findings indicated that the intensity of human activities in the Tuha Basin has exhibited a"first decline and then recovery"trend over the past 30 a,accompanied by significant spatial clustering.In recent years,the aggregation of hot spots has diminished,while clustering of cold spots has intensified,suggesting a dispersion of human activity centers.Nevertheless,urban areas in the Hami and Turpan cities,along with their surrounding areas,continued to serve as core areas of human activities.Topographic features(slope gradient and aspect)and their interactions with economic variables emerged as dominant determinants shaping the spatial patterns and temporal dynamics of human activity intensity.This result provides critical insights into fostering sustainable regional development and ecological conservation in the Tuha Basin and offers valuable methodological and empirical references for studies on land use dynamics and human activity intensity in similar arid areas.展开更多
The Liaohe River Valley was one of the key centers of the origination and development of agriculture in northern China during the Holocene.To understand the long-term interaction among the evolutions of climate,agricu...The Liaohe River Valley was one of the key centers of the origination and development of agriculture in northern China during the Holocene.To understand the long-term interaction among the evolutions of climate,agriculture,and human activities,it is essential to quantitatively reconstruct the spatiotemporal changes in regional prehistoric human land use.In this study,known archaeological sites and a prehistoric land use model(PLUM)were combined to reconstruct changes in land use in the Liaohe River Valley during 8-2 ka BP from a quantitative perspective.The land use area experienced two stages of increase(during 8-5 ka BP and after 4 ka BP)and one stage of decrease(during 5-4 ka BP);these periods were characterized by spatial expansions and contractions.The land use intensity level differed significantly in the western and eastern parts of the valley before 4 ka BP,but the situation changed as the distribution center of the human activity shifted to the southern part of the valley around 5-4 ka BP.Overall,the spatial and temporal changes in the land use areas in both the western and eastern parts of the valley responded well to variations in precipitation during 8-2 ka BP,which potentially provides useful insights into understanding the responses of human activity to future climate change.展开更多
Based on regional paleoclimate sequences,records of human activities,paleoclimate simulations,and detailed environmental historical records,we discuss the impacts of Holocene climate change and human activities on the...Based on regional paleoclimate sequences,records of human activities,paleoclimate simulations,and detailed environmental historical records,we discuss the impacts of Holocene climate change and human activities on the evolution of the Shule River in the western Qilian Mountains,China.The results indicate that during the early to mid-Holocene,the river evolution of the Shule River alluvial fan was closely related to regional climate fluctuations.In the late Holocene,flood agriculture began to emerge along the Shule River.During the historical period,population growth and the expansion of arable land led to increased river water usage,resulting in decreased access to the expected distribution of water resources in other regions,which in turn has caused imbalances in the regional hydrological ecosystem.展开更多
Activity recognition is a challenging topic in the field of computer vision that has various applications,including surveillance systems,industrial automation,and human-computer interaction.Today,the demand for automa...Activity recognition is a challenging topic in the field of computer vision that has various applications,including surveillance systems,industrial automation,and human-computer interaction.Today,the demand for automation has greatly increased across industries worldwide.Real-time detection requires edge devices with limited computational time.This study proposes a novel hybrid deep learning system for human activity recognition(HAR),aiming to enhance the recognition accuracy and reduce the computational time.The proposed system combines a pretrained image classification model with a sequence analysis model.First,the dataset was divided into a training set(70%),validation set(10%),and test set(20%).Second,all the videos were converted into frames and deep-based features were extracted from each frame using convolutional neural networks(CNNs)with a vision transformer.Following that,bidirectional long short-term memory(BiLSTM)-and temporal convolutional network(TCN)-based models were trained using the training set,and their performances were evaluated using the validation set and test set.Four benchmark datasets(UCF11,UCF50,UCF101,and JHMDB)were used to evaluate the performance of the proposed HAR-based system.The experimental results showed that the combination of ConvNeXt and the TCN-based model achieved a recognition accuracy of 97.73%for UCF11,98.81%for UCF50,98.46%for UCF101,and 83.38%for JHMDB,respectively.This represents improvements in the recognition accuracy of 4%,2.67%,3.67%,and 7.08%for the UCF11,UCF50,UCF101,and JHMDB datasets,respectively,over existing models.Moreover,the proposed HAR-based system obtained superior recognition accuracy,shorter computational times,and minimal memory usage compared to the existing models.展开更多
Existing through-wall human activity recognition methods often rely on Doppler information or reflective signal characteristics of the human body.However,static individuals,lacking prominent motion features,do not gen...Existing through-wall human activity recognition methods often rely on Doppler information or reflective signal characteristics of the human body.However,static individuals,lacking prominent motion features,do not generate Doppler information.Moreover,radar signals experience significant attenuation due to absorption and scattering effects as they penetrate walls,limiting recognition performance.To address these challenges,this study proposes a novel through-wall human activity recognition method based on MIMO radar.Utilizing a MIMO radar operating at 1–2 GHz,we capture activity data of individuals through walls and process it into range-angle maps to represent activity features.To tackle the issue of minimal variation in reflection areas caused by static individuals,a multi-scale activity feature extraction module is designed,capable of extracting effective features from radar signals across multiple scales.Simultaneously,a temporal attention mechanism is employed to extract keyframe information from sequential signals,focusing on critical moments of activity.Furthermore,this study introduces an activity recognition network based on a Deformable Transformer,which efficiently extracts both global and local features from radar signals,delivering precise human posture and activity sequences.In experimental scenarios involving 24 cm-thick brick walls,the proposed method achieves an impressive 97.1%accuracy in activity recognition classification.展开更多
Central Asia(CA)faces escalating threats from increasing temperature,glacier retreat,biodiversity loss,unsustainable water use,terminal lake shrinkage,and soil salinization,all of which challenge the balance between e...Central Asia(CA)faces escalating threats from increasing temperature,glacier retreat,biodiversity loss,unsustainable water use,terminal lake shrinkage,and soil salinization,all of which challenge the balance between ecological integrity and socio-economic development essential for achieving Sustainable Development Goals.However,a comprehensive understanding of priority areas from a multi-dimensional perspective is lacking,hindering effective conservation and development strategies.To address this,we developed a comprehensive assessment framework with a tailored indicator system,enabling a spatial evaluation of CA’s priority areas by integrating biodiversity,ecosystem services(ESs),and human activities.Combining zonation and geographical detectors,this approach facilitates spatial prioritization and examines ecological and socio-economic heterogeneity.Our findings reveal a heterogeneous distribution of priority areas across CA,with significant concentrations in eastern mountainous regions,river valleys,and oasis agricultural lands.We identified 184 key districts crucial for ecological and societal sustainability.Attribution analysis shows that natural factors like soil types,precipitation,and evapotranspiration significantly shape these areas,influencing human activities and the distribution of biodiversity and ESs.Multi-dimensional analysis indicates existing protected areas cover only 15%of the top 30%priority areas,revealing substantial conservation gaps.Additionally,a 38%overlap between ESs and human activities,along with 63.25%congruence in integrated areas,underscores significant human impacts on ecological systems and their dependency on ESs.Given CA’s limited resources,it is crucial to implement measures that strengthen conservation efforts,align ecological preservation with socio-economic demands,and enhance resource efficiency through sustainable integrated land and water resource management.展开更多
Human activity recognition is a significant area of research in artificial intelligence for surveillance,healthcare,sports,and human-computer interaction applications.The article benchmarks the performance of You Only...Human activity recognition is a significant area of research in artificial intelligence for surveillance,healthcare,sports,and human-computer interaction applications.The article benchmarks the performance of You Only Look Once version 11-based(YOLOv11-based)architecture for multi-class human activity recognition.The article benchmarks the performance of You Only Look Once version 11-based(YOLOv11-based)architecture for multi-class human activity recognition.The dataset consists of 14,186 images across 19 activity classes,from dynamic activities such as running and swimming to static activities such as sitting and sleeping.Preprocessing included resizing all images to 512512 pixels,annotating them in YOLO’s bounding box format,and applying data augmentation methods such as flipping,rotation,and cropping to enhance model generalization.The proposed model was trained for 100 epochs with adaptive learning rate methods and hyperparameter optimization for performance improvement,with a mAP@0.5 of 74.93%and a mAP@0.5-0.95 of 64.11%,outperforming previous versions of YOLO(v10,v9,and v8)and general-purpose architectures like ResNet50 and EfficientNet.It exhibited improved precision and recall for all activity classes with high precision values of 0.76 for running,0.79 for swimming,0.80 for sitting,and 0.81 for sleeping,and was tested for real-time deployment with an inference time of 8.9 ms per image,being computationally light.Proposed YOLOv11’s improvements are attributed to architectural advancements like a more complex feature extraction process,better attention modules,and an anchor-free detection mechanism.While YOLOv10 was extremely stable in static activity recognition,YOLOv9 performed well in dynamic environments but suffered from overfitting,and YOLOv8,while being a decent baseline,failed to differentiate between overlapping static activities.The experimental results determine proposed YOLOv11 to be the most appropriate model,providing an ideal balance between accuracy,computational efficiency,and robustness for real-world deployment.Nevertheless,there exist certain issues to be addressed,particularly in discriminating against visually similar activities and the use of publicly available datasets.Future research will entail the inclusion of 3D data and multimodal sensor inputs,such as depth and motion information,for enhancing recognition accuracy and generalizability to challenging real-world environments.展开更多
Due to the lack of human avoidance analysis,the orthosis cannot accurately apply orthopedic force during orthopedic,resulting in poor orthopedic effect.Therefore,the relationship between the human body’s active avoid...Due to the lack of human avoidance analysis,the orthosis cannot accurately apply orthopedic force during orthopedic,resulting in poor orthopedic effect.Therefore,the relationship between the human body’s active avoidance ability and force application is studied to achieve accurate loading of orthopedic force.First,a high-precision scoliosis model was established based on computed tomography data,and the relationship between orthopedic force and Cobb angle was analyzed.Then 9 subjects were selected for avoidance ability test grouped by body mass index calculation,and the avoidance function of different groups was fitted.The avoidance function corrected the application of orthopedic forces.The results show that the optimal correction force calculated by the finite element method was 60 N.The obese group had the largest avoidance ability,followed by the standard group and the lean group.When the orthopedic force was 60 N,the Cobb angle was reduced from 33.77°to 20°,the avoidance ability of the standard group at 50 N obtained from the avoidance function was 20.28%and 10.14 N was actively avoided.Therefore,when 50 N was applied,60.14 N was actually generated,which can achieve the orthopedic effect of 60 N numerical simulation analysis.The avoidance effect can take the active factors of the human body into consideration in the orthopedic process,so as to achieve a more accurate application of orthopedic force,and provide data reference for clinicians in the orthopedic process.展开更多
Human Activity Recognition(HAR)has become increasingly critical in civic surveillance,medical care monitoring,and institutional protection.Current deep learning-based approaches often suffer from excessive computation...Human Activity Recognition(HAR)has become increasingly critical in civic surveillance,medical care monitoring,and institutional protection.Current deep learning-based approaches often suffer from excessive computational complexity,limited generalizability under varying conditions,and compromised real-time performance.To counter these,this paper introduces an Active Learning-aided Heuristic Deep Spatio-Textural Ensemble Learning(ALH-DSEL)framework.The model initially identifies keyframes from the surveillance videos with a Multi-Constraint Active Learning(MCAL)approach,with features extracted from DenseNet121.The frames are then segmented employing an optimized Fuzzy C-Means clustering algorithm with Firefly to identify areas of interest.A deep ensemble feature extractor,comprising DenseNet121,EfficientNet-B7,MobileNet,and GLCM,extracts varied spatial and textural features.Fused characteristics are enhanced through PCA and Min-Max normalization and discriminated by a maximum voting ensemble of RF,AdaBoost,and XGBoost.The experimental results show that ALH-DSEL provides higher accuracy,precision,recall,and F1-score,validating its superiority for real-time HAR in surveillance scenarios.展开更多
The Songhua River Basin(SRB),ranking third largest in China in terms of both runoff volume and basin area,has experi-enced frequent disasters and drastic changes in runoff since the early 20th century.Many studies hav...The Songhua River Basin(SRB),ranking third largest in China in terms of both runoff volume and basin area,has experi-enced frequent disasters and drastic changes in runoff since the early 20th century.Many studies have analyzed the causes of runoff re-duction;however,the spatiotemporal differences in runoff contributions and their underlying mechanisms remain poorly understood,which are crucial for regional water resources management and effective utilization.This study used the Mann-Kendall rank correlation trend test,continuous wavelet analysis,cumulative anomaly,and the slope change ratio of cumulative quantities(SCRCQ)method to explore the runoff changes characteristics and spatiotemporal differences of the contributions of climate change and human activities to runoff changes across three sub-basins of the SRB.The results show that:1)runoff from 1955 to 2022 in all the three sub-basins exhibit a statistically significant decreasing trend at 0.05 significant level.2)Four abrupt change points in runoff were detected in Nenjiang River Basin(NRB)and the mainstream of the SRB(MSRB),whereas only two change points in the Second Songhua River(SSRB).3)Runoff and precipitation series of the NRB and MSRB exhibit similar multi-timescale cycle characteristics with the most dominated cycles of 45-58 yr.In contrast,it is 12-18 yr for SSRB.4)Anthropogenic activities are the primary factor leading to in the reduction of runoff in NRB(74.33%-91.67%)and MSRB(50.11%-102.12%),whereas it is only 5.38%-33.12%in SSRB.This is attributed to the uneven distribution of regional climate and human activities in the entire SRB.5)With the growing demand for water diversion for agri-cultural irrigation,anthropogenic activities in the NRB and MSRB have increased.However,the opposite is found in SSR,where the in-creased influence of precipitation on runoff and water conservation policies are identified.展开更多
This research investigates the application of multisource data fusion using a Multi-Layer Perceptron (MLP) for Human Activity Recognition (HAR). The study integrates four distinct open-source datasets—WISDM, DaLiAc, ...This research investigates the application of multisource data fusion using a Multi-Layer Perceptron (MLP) for Human Activity Recognition (HAR). The study integrates four distinct open-source datasets—WISDM, DaLiAc, MotionSense, and PAMAP2—to develop a generalized MLP model for classifying six human activities. Performance analysis of the fused model for each dataset reveals accuracy rates of 95.83 for WISDM, 97 for DaLiAc, 94.65 for MotionSense, and 98.54 for PAMAP2. A comparative evaluation was conducted between the fused MLP model and the individual dataset models, with the latter tested on separate validation sets. The results indicate that the MLP model, trained on the fused dataset, exhibits superior performance relative to the models trained on individual datasets. This finding suggests that multisource data fusion significantly enhances the generalization and accuracy of HAR systems. The improved performance underscores the potential of integrating diverse data sources to create more robust and comprehensive models for activity recognition.展开更多
基金supported by National Natural Science Foundation of China(NSFC)under grant U23A20310.
文摘With the growing advancement of wireless communication technologies,WiFi-based human sensing has gained increasing attention as a non-intrusive and device-free solution.Among the available signal types,Channel State Information(CSI)offers fine-grained temporal,frequency,and spatial insights into multipath propagation,making it a crucial data source for human-centric sensing.Recently,the integration of deep learning has significantly improved the robustness and automation of feature extraction from CSI in complex environments.This paper provides a comprehensive review of deep learning-enhanced human sensing based on CSI.We first outline mainstream CSI acquisition tools and their hardware specifications,then provide a detailed discussion of preprocessing methods such as denoising,time–frequency transformation,data segmentation,and augmentation.Subsequently,we categorize deep learning approaches according to sensing tasks—namely detection,localization,and recognition—and highlight representative models across application scenarios.Finally,we examine key challenges including domain generalization,multi-user interference,and limited data availability,and we propose future research directions involving lightweight model deployment,multimodal data fusion,and semantic-level sensing.
基金supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2026R765),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Human Activity Recognition(HAR)is a novel area for computer vision.It has a great impact on healthcare,smart environments,and surveillance while is able to automatically detect human behavior.It plays a vital role in many applications,such as smart home,healthcare,human computer interaction,sports analysis,and especially,intelligent surveillance.In this paper,we propose a robust and efficient HAR system by leveraging deep learning paradigms,including pre-trained models,CNN architectures,and their average-weighted fusion.However,due to the diversity of human actions and various environmental influences,as well as a lack of data and resources,achieving high recognition accuracy remain elusive.In this work,a weighted average ensemble technique is employed to fuse three deep learning models:EfficientNet,ResNet50,and a custom CNN.The results of this study indicate that using a weighted average ensemble strategy for developing more effective HAR models may be a promising idea for detection and classification of human activities.Experiments by using the benchmark dataset proved that the proposed weighted ensemble approach outperformed existing approaches in terms of accuracy and other key performance measures.The combined average-weighted ensemble of pre-trained and CNN models obtained an accuracy of 98%,compared to 97%,96%,and 95%for the customized CNN,EfficientNet,and ResNet50 models,respectively.
基金The Second Tibetan Plateau Scientific Expedition and Research Program,No.2019QZKK0608。
文摘Understanding the impacts of human activities on the plateau’s living environment is essential for advancing modernization pathways that promote harmony between humanity and nature.However,studies on the dynamic interactions between human activities and the living environment on the Qinghai-Xizang Plateau(QXP)remain limited,with a paucity of quantitative relationship analyses.This study established an assessment framework to evaluate human influences on the living environment in QXP,using data on typical human activities,ecological conditions,and human settlements.Within this framework,the spatial analysis methods and the coupling coordination model were used to examine the spatio-temporal characteristics and relationship of human activities and living environment on the QXP from 2000 to 2020.The geographical detector model was then applied to identify the key factors influencing the plateau’s human living environment.Subsequently,the four-quadrant analysis model was adopted to assess human influences on the living environment.The results indicate that the human activity intensity(HAI)on the QXP remained relatively low yet increased by 15.41%from 2000 to 2020.Spatially,the human living environment quality(LEQ)improved from northwest to southeast,with 61.14%of the areas remaining stable and 18.47%experiencing slight improvement.The analysis of coupling coordination revealed a continuous improvement between the HAI and LEQ,with the areas of high and relatively high coordinated types increasing by more than 9%.Precipitation and urban-rural construction were identified as the primary factors influencing changes in the LEQ.The interaction between the HAI and LEQ was strengthening,with 40.44%classified as coordinated development type and 38.35%as development-environment conflict type.These findings provide valuable insights for enhancing the resilience of human settlements and promoting green development across the plateau.
基金supported by the National Natural Science Foundation of China(32271584 and 31600445)the Natural Science Basic Research Plan in Shaanxi Province of China(2020JM-286)+2 种基金the Fundamental Research Funds for the Central Universities(GK202103072,GK202103073)the National College Students'Innovative Entrepreneurial Training Plan Program(202310718085)Special Research Project in Philosophy and Social Sciences of Shaanxi Province(2022HZ1795).
文摘Prevention of biological invasion requires understanding how alien species invade native communities.Although studies have identified mechanisms that underlie plant invasion in some habitats,limited attention has focused on invasion patterns along elevational gradients.In this study,we asked which factors drive the global and regional distribution of the invasive plant Galinsoga quadriradiata along elevational gradients.To answer this question,we examined whether human activities(i.e.,roads)promote G.quadriradiata invasion,how seed dispersal-related traits of G.quadriradiata change along elevation gradients,and whether G.quadriradiata has adapted to high-elevation environments through phenotypic plasticity or genetic variation.On the global scale,we found that human activities and road density positively contribute to the G.quadriradiata expansion in mountainous areas.Field surveys in China revealed significant elevational differences in the seed dispersal traits of G.quadriradiata,with higher-elevation populations exhibiting lower dispersal ability and generally lower genetic diversity.Under common conditions,high-elevation populations showed higher leaf mass ratio but lower root mass ratio and reproductive allocation.This suggests that high-elevation environments create a barrier to dispersal for G.quadriradiata,and that G.quadriradiata has adapted phenotypically to these conditions.Our study indicates that the elevational invasion pattern of G.quadriradiata is shaped by multiple factors,particularly human activities and phenotypic adaptability.In addition,our finding that G.quadriradiata invasion at high elevations is not constrained by low genetic diversity indicates that monitoring and management of G.quadriradiata in mountainous areas should be strengthened.
基金supported by Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia through the Researchers Supporting Project PNURSP2025R333.
文摘Human activity recognition(HAR)is a method to predict human activities from sensor signals using machine learning(ML)techniques.HAR systems have several applications in various domains,including medicine,surveillance,behavioral monitoring,and posture analysis.Extraction of suitable information from sensor data is an important part of the HAR process to recognize activities accurately.Several research studies on HAR have utilizedMel frequency cepstral coefficients(MFCCs)because of their effectiveness in capturing the periodic pattern of sensor signals.However,existing MFCC-based approaches often fail to capture sufficient temporal variability,which limits their ability to distinguish between complex or imbalanced activity classes robustly.To address this gap,this study proposes a feature fusion strategy that merges time-based and MFCC features(MFCCT)to enhance activity representation.The merged features were fed to a convolutional neural network(CNN)integrated with long shortterm memory(LSTM)—DeepConvLSTM to construct the HAR model.The MFCCT features with DeepConvLSTM achieved better performance as compared to MFCCs and time-based features on PAMAP2,UCI-HAR,and WISDM by obtaining an accuracy of 97%,98%,and 97%,respectively.In addition,DeepConvLSTM outperformed the deep learning(DL)algorithms that have recently been employed in HAR.These results confirm that the proposed hybrid features are not only practical but also generalizable,making them applicable across diverse HAR datasets for accurate activity classification.
基金National Natural Science Foundation of China(Grant No.U2243225)the Strategic Priority Research Program of the Chinese Academy of Sciences(Grant No.XDB40000000)+2 种基金the Natural Science Basic Research Program of Shaanxi(Grant No.Z2024-ZYFS-0065)the Funding of Top Young talents of Ten Thousand talents Plan in China(2021)the Fundamental Research Funds for the Central Universities(Grants No.2452023071 and 2023HHZX002).
文摘Understanding the complex interactions between human activities and ecosystem functions is a prerequisite for achieving sustainable development.Since the implementation of the“Grain for Green”Project in 1999,ecosystem functions in China’s Loess Plateau have significantly improved.However,intensified human activities have also exacerbated the pressures on the region’s fragile ecological environment.This study investigates the spatiotemporal variations in the human activity intensity index(HAI)and net ecosystem benefits(NEB)from 2000 to 2020,using expert-based assessments and an enhanced cost-benefit evaluation framework.Results indicate that HAI increased by 16.7% and 16.6% at the grid and county levels,respectively.NEB exhibited pronounced spatial heterogeneity,with a total increase of USD 36.2 trillion at the grid scale.At the county level,the average NEB rose by 75%.The degree of trade-off was higher at the grid scale than at the county scale,while the synergistic areas initially expanded and then declined at both scales.Key areas for improvement and regions of lagging development were identified as priority zones for ecological management and spatial planning at both spatial resolutions.This study offers scientific insights and practical guidance for harmonizing ecological conservation with high-quality development in ecologically vulnerable regions.
基金Shanxi Province Graduate Research Practice Innovation Project,No.2023KY465Project on the Reform of Graduate Education and Teaching in Shanxi Province,No.2021YJJG146+1 种基金Research Project of Shanxi Provincial Cultural Relics Bureau,No.22-8-14-1400-119National Key R&D Program of China,No.2021YFB3901300。
文摘Human activities have significantly impacted the land surface temperature(LST),endangering human health;however,the relationship between these two factors has not been adequately quantified.This study comprehensively constructs a Human Activity Intensity(HAI)index and employs the Maximal Information Coefficient,four-quadrant model,and XGBoostSHAP model to investigate the spatiotemporal relationship and influencing factors of HAI-LST in the Yellow River Basin(YRB)from 2000 to 2020.The results indicated that from 2000 to 2020,as HAI and LST increased,the static HAI-LST relationship in the YRB showed a positive correlation that continued to strengthen.This dynamic relationship exhibited conflicting development,with the proportion of coordinated to conflicting regions shifting from 1:4 to 1:2,indicating a reduction in conflict intensity.Notably,only the degree of conflict in the source area decreased significantly,whereas it intensified in the upper and lower reaches.The key factors influencing the HAI-LST relationship include fractional vegetation cover,slope,precipitation,and evapotranspiration,along with region-specific factors such as PM_(2.5),biodiversity,and elevation.Based on these findings,region-specific ecological management strategies have been proposed to mitigate conflict-prone areas and alleviate thermal stress,thereby providing important guidance for promoting harmonious development between humans and nature.
基金supported by the National Key Research and Development Program of China(No.2022YFF1301301)the Natural Science Foundation of Xiamen Municipality(No.3502Z202472047)the Geological Survey Program of China Geological Survey(DD20190303).
文摘To address the deficiencies in comprehensive surface contamination prevention strategies within China's nitrate-affected regions,this research innovatively proposes the DITAPH model-a systematic framework integrating groundwater nitrate vulnerability assessment and Nitrate Vulnerable Zones(NVZs)delineation through optimization of hydrogeological parameters.Based on detailed hydrogeological and hydrochemical investigations,the DITAPH model was applied in the plain areas of Quanzhou to evaluate its applicability.The model selected hydrogeological parameters(depth of groundwater,lithology of the vadose zone,topographic slope,aquifer water yield property),one climatic parameter(precipitation),and two anthropogenic parameters(land use type and population density)as assessment indicators.The results of the groundwater nitrate vulnerability assessment showed that the low,relatively low,relatively high,and high groundwater nitrate vulnerability zones in the study area accounted for 5.96%,35.44%,53.74%and 4.86%of the total area,respectively.Groundwater nitrate vulnerability was most strongly influenced by human activities,followed by groundwater depth and topographic slope.The high vulnerability zone is mainly affected by domestic and industrial wastewater,whereas the relatively high groundwater nitrate vulnerability zone is primarily influenced by agricultural activities.Validation of the DITAPH model revealed a significant positive correlation between the DITAPH index(DI)and nitrate concentration(ρ(NO3−)).The results of the NVZs delineated by the DITAPH model are reliable and can serve as a tool for water resource management planning,guiding the development of targeted measures in the NVZs to prevent groundwater contamination.
基金The Foundation for Distinguished Young Scholars of Gansu Province,No.22JR5RA046Key Research Program of Gansu Province,No.23ZDKA0004+2 种基金The Joint Funds of the National Natural Science Foundation of China,No.U22A202690Interdisciplinary Youth Team Project from the Key Laboratory of Cryospheric Science and Frozen Soil Engineering,No.CSFSE-ZQ-2408The Youth Innovation Promotion Association CAS to X.W.,No.2020422。
文摘Carbon fluxes are essential indicators assessing vegetation carbon cycle functions.However,the extent and mechanisms by which climate change and human activities influence the spatiotemporal dynamics of carbon fluxes in arid oasis and non-oasis area remains unclear.Here,we assessed and predicted the future effects of climate change and human activities on carbon fluxes in the Hexi Corridor.The results showed that the annual average gross primary productivity(GPP),net ecosystem productivity(NEP),and ecosystem respiration(Reco)in the Hexi Corridor oasis increased by 263.91 g C·m^(-2)·yr^(-1),118.45 g C·m^(-2)·yr^(-1)and 122.46 g C·m^(-2)·yr^(-1),respectively,due to the expansion of the oasis area by 3424.84 km^(2) caused by human activities from 2000 to 2022.Both oasis and non-oasis arid ecosystems in the Hexi Corridor acted as carbon sinks.Compared to the non-oasis area,the carbon fluxes contributions of oasis area increased,ranging from 10.21%to 13.99%for GPP,8.50%to11.68%for NEP,and 13.34%to 17.13%for Reco.The contribution of the carbon flux from the oasis expansion area to the total carbon flux change in the Hexi Corridor was 30.96%(7.09 Tg C yr^(-1))for GPP,29.57%(3.39 Tg C yr^(-1))for NEP and 32.40%(3.58 Tg C yr^(-1))for Reco.The changes in carbon fluxes in the oasis area were mainly attributed to human activities(oasis expansion)and temperature,whereas non-oasis area was mainly due to climate factors.Moreover,the future increasing trends were observed for GPP(64.99%),NEP(66.29%)and Reco(82.08%)in the Hexi Corridor.This study provides new insights into the regulatory mechanisms of carbon cycle in the arid oasis and non-oasis area.
基金supported by the Third Xinjiang Scientific Expedition Program(2022xjkk1205)the National Natural Science Foundation of China(42377461).
文摘The Turpan-Hami(Tuha)Basin of China,a critical region on the Silk Road Economic Belt and a major national energy base,occupies a significant position in energy security and in the major industrial clusters in Xinjiang Uygur Autonomous Region,China.Understanding spatial and temporal evolution of human activities in this area is essential for harmonizing ecological protection with energy development,safeguarding the ecological security of the Silk Road Economic Belt,and promoting the sustainable development of the area.However,despite rapid socioeconomic advances,the trajectories of human activity intensity and the principal driving mechanisms over the past three decades remain inadequately understood.To address these gaps,this study constructed a land use dataset for the Tuha Basin from 1990 to 2020,utilizing Google Earth Engine(GEE)and random forest classification algorithm.We assessed the intensity of human activities and their spatial autocorrelation patterns and further identified key drivers influencing spatial and temporal variations using the Geodetector model.Our findings indicated that the intensity of human activities in the Tuha Basin has exhibited a"first decline and then recovery"trend over the past 30 a,accompanied by significant spatial clustering.In recent years,the aggregation of hot spots has diminished,while clustering of cold spots has intensified,suggesting a dispersion of human activity centers.Nevertheless,urban areas in the Hami and Turpan cities,along with their surrounding areas,continued to serve as core areas of human activities.Topographic features(slope gradient and aspect)and their interactions with economic variables emerged as dominant determinants shaping the spatial patterns and temporal dynamics of human activity intensity.This result provides critical insights into fostering sustainable regional development and ecological conservation in the Tuha Basin and offers valuable methodological and empirical references for studies on land use dynamics and human activity intensity in similar arid areas.
基金Global Change Program of National Key Research and Development Program of China,No.2020YFA0607700National Natural Science Foundation of China,No.T2192954,No.42488201,No.42177180。
文摘The Liaohe River Valley was one of the key centers of the origination and development of agriculture in northern China during the Holocene.To understand the long-term interaction among the evolutions of climate,agriculture,and human activities,it is essential to quantitatively reconstruct the spatiotemporal changes in regional prehistoric human land use.In this study,known archaeological sites and a prehistoric land use model(PLUM)were combined to reconstruct changes in land use in the Liaohe River Valley during 8-2 ka BP from a quantitative perspective.The land use area experienced two stages of increase(during 8-5 ka BP and after 4 ka BP)and one stage of decrease(during 5-4 ka BP);these periods were characterized by spatial expansions and contractions.The land use intensity level differed significantly in the western and eastern parts of the valley before 4 ka BP,but the situation changed as the distribution center of the human activity shifted to the southern part of the valley around 5-4 ka BP.Overall,the spatial and temporal changes in the land use areas in both the western and eastern parts of the valley responded well to variations in precipitation during 8-2 ka BP,which potentially provides useful insights into understanding the responses of human activity to future climate change.
基金The National Natural Science Foundation of China(Grant 42371159)。
文摘Based on regional paleoclimate sequences,records of human activities,paleoclimate simulations,and detailed environmental historical records,we discuss the impacts of Holocene climate change and human activities on the evolution of the Shule River in the western Qilian Mountains,China.The results indicate that during the early to mid-Holocene,the river evolution of the Shule River alluvial fan was closely related to regional climate fluctuations.In the late Holocene,flood agriculture began to emerge along the Shule River.During the historical period,population growth and the expansion of arable land led to increased river water usage,resulting in decreased access to the expected distribution of water resources in other regions,which in turn has caused imbalances in the regional hydrological ecosystem.
基金funded by the Ongoing Research Funding Program(ORF-2025-890),King Saud University,Riyadh,Saudi Arabia.
文摘Activity recognition is a challenging topic in the field of computer vision that has various applications,including surveillance systems,industrial automation,and human-computer interaction.Today,the demand for automation has greatly increased across industries worldwide.Real-time detection requires edge devices with limited computational time.This study proposes a novel hybrid deep learning system for human activity recognition(HAR),aiming to enhance the recognition accuracy and reduce the computational time.The proposed system combines a pretrained image classification model with a sequence analysis model.First,the dataset was divided into a training set(70%),validation set(10%),and test set(20%).Second,all the videos were converted into frames and deep-based features were extracted from each frame using convolutional neural networks(CNNs)with a vision transformer.Following that,bidirectional long short-term memory(BiLSTM)-and temporal convolutional network(TCN)-based models were trained using the training set,and their performances were evaluated using the validation set and test set.Four benchmark datasets(UCF11,UCF50,UCF101,and JHMDB)were used to evaluate the performance of the proposed HAR-based system.The experimental results showed that the combination of ConvNeXt and the TCN-based model achieved a recognition accuracy of 97.73%for UCF11,98.81%for UCF50,98.46%for UCF101,and 83.38%for JHMDB,respectively.This represents improvements in the recognition accuracy of 4%,2.67%,3.67%,and 7.08%for the UCF11,UCF50,UCF101,and JHMDB datasets,respectively,over existing models.Moreover,the proposed HAR-based system obtained superior recognition accuracy,shorter computational times,and minimal memory usage compared to the existing models.
基金supported by National Natural Science Foundation of China(No.62272242)Postgraduate Research&Practice Innovation Program of Jiangsu Province(Nos.KYCX21_0800,KYCX23_1082).
文摘Existing through-wall human activity recognition methods often rely on Doppler information or reflective signal characteristics of the human body.However,static individuals,lacking prominent motion features,do not generate Doppler information.Moreover,radar signals experience significant attenuation due to absorption and scattering effects as they penetrate walls,limiting recognition performance.To address these challenges,this study proposes a novel through-wall human activity recognition method based on MIMO radar.Utilizing a MIMO radar operating at 1–2 GHz,we capture activity data of individuals through walls and process it into range-angle maps to represent activity features.To tackle the issue of minimal variation in reflection areas caused by static individuals,a multi-scale activity feature extraction module is designed,capable of extracting effective features from radar signals across multiple scales.Simultaneously,a temporal attention mechanism is employed to extract keyframe information from sequential signals,focusing on critical moments of activity.Furthermore,this study introduces an activity recognition network based on a Deformable Transformer,which efficiently extracts both global and local features from radar signals,delivering precise human posture and activity sequences.In experimental scenarios involving 24 cm-thick brick walls,the proposed method achieves an impressive 97.1%accuracy in activity recognition classification.
基金funded by the Joint CAS-MPG Research Project(HZXM20225001MI)this research was also supported partly by the key program of National Natural Science Foundation of China(42230708)the Tianshan Talent Project of Xinjiang Uygur Autonomous Region,China(2022TSYCLJ0056).
文摘Central Asia(CA)faces escalating threats from increasing temperature,glacier retreat,biodiversity loss,unsustainable water use,terminal lake shrinkage,and soil salinization,all of which challenge the balance between ecological integrity and socio-economic development essential for achieving Sustainable Development Goals.However,a comprehensive understanding of priority areas from a multi-dimensional perspective is lacking,hindering effective conservation and development strategies.To address this,we developed a comprehensive assessment framework with a tailored indicator system,enabling a spatial evaluation of CA’s priority areas by integrating biodiversity,ecosystem services(ESs),and human activities.Combining zonation and geographical detectors,this approach facilitates spatial prioritization and examines ecological and socio-economic heterogeneity.Our findings reveal a heterogeneous distribution of priority areas across CA,with significant concentrations in eastern mountainous regions,river valleys,and oasis agricultural lands.We identified 184 key districts crucial for ecological and societal sustainability.Attribution analysis shows that natural factors like soil types,precipitation,and evapotranspiration significantly shape these areas,influencing human activities and the distribution of biodiversity and ESs.Multi-dimensional analysis indicates existing protected areas cover only 15%of the top 30%priority areas,revealing substantial conservation gaps.Additionally,a 38%overlap between ESs and human activities,along with 63.25%congruence in integrated areas,underscores significant human impacts on ecological systems and their dependency on ESs.Given CA’s limited resources,it is crucial to implement measures that strengthen conservation efforts,align ecological preservation with socio-economic demands,and enhance resource efficiency through sustainable integrated land and water resource management.
基金supported by King Saud University,Riyadh,Saudi Arabia,under Ongoing Research Funding Program(ORF-2025-951).
文摘Human activity recognition is a significant area of research in artificial intelligence for surveillance,healthcare,sports,and human-computer interaction applications.The article benchmarks the performance of You Only Look Once version 11-based(YOLOv11-based)architecture for multi-class human activity recognition.The article benchmarks the performance of You Only Look Once version 11-based(YOLOv11-based)architecture for multi-class human activity recognition.The dataset consists of 14,186 images across 19 activity classes,from dynamic activities such as running and swimming to static activities such as sitting and sleeping.Preprocessing included resizing all images to 512512 pixels,annotating them in YOLO’s bounding box format,and applying data augmentation methods such as flipping,rotation,and cropping to enhance model generalization.The proposed model was trained for 100 epochs with adaptive learning rate methods and hyperparameter optimization for performance improvement,with a mAP@0.5 of 74.93%and a mAP@0.5-0.95 of 64.11%,outperforming previous versions of YOLO(v10,v9,and v8)and general-purpose architectures like ResNet50 and EfficientNet.It exhibited improved precision and recall for all activity classes with high precision values of 0.76 for running,0.79 for swimming,0.80 for sitting,and 0.81 for sleeping,and was tested for real-time deployment with an inference time of 8.9 ms per image,being computationally light.Proposed YOLOv11’s improvements are attributed to architectural advancements like a more complex feature extraction process,better attention modules,and an anchor-free detection mechanism.While YOLOv10 was extremely stable in static activity recognition,YOLOv9 performed well in dynamic environments but suffered from overfitting,and YOLOv8,while being a decent baseline,failed to differentiate between overlapping static activities.The experimental results determine proposed YOLOv11 to be the most appropriate model,providing an ideal balance between accuracy,computational efficiency,and robustness for real-world deployment.Nevertheless,there exist certain issues to be addressed,particularly in discriminating against visually similar activities and the use of publicly available datasets.Future research will entail the inclusion of 3D data and multimodal sensor inputs,such as depth and motion information,for enhancing recognition accuracy and generalizability to challenging real-world environments.
基金the Applied Basic Research Program of Educational Department of Liaoning Province(No.LJKZZ20220058)。
文摘Due to the lack of human avoidance analysis,the orthosis cannot accurately apply orthopedic force during orthopedic,resulting in poor orthopedic effect.Therefore,the relationship between the human body’s active avoidance ability and force application is studied to achieve accurate loading of orthopedic force.First,a high-precision scoliosis model was established based on computed tomography data,and the relationship between orthopedic force and Cobb angle was analyzed.Then 9 subjects were selected for avoidance ability test grouped by body mass index calculation,and the avoidance function of different groups was fitted.The avoidance function corrected the application of orthopedic forces.The results show that the optimal correction force calculated by the finite element method was 60 N.The obese group had the largest avoidance ability,followed by the standard group and the lean group.When the orthopedic force was 60 N,the Cobb angle was reduced from 33.77°to 20°,the avoidance ability of the standard group at 50 N obtained from the avoidance function was 20.28%and 10.14 N was actively avoided.Therefore,when 50 N was applied,60.14 N was actually generated,which can achieve the orthopedic effect of 60 N numerical simulation analysis.The avoidance effect can take the active factors of the human body into consideration in the orthopedic process,so as to achieve a more accurate application of orthopedic force,and provide data reference for clinicians in the orthopedic process.
文摘Human Activity Recognition(HAR)has become increasingly critical in civic surveillance,medical care monitoring,and institutional protection.Current deep learning-based approaches often suffer from excessive computational complexity,limited generalizability under varying conditions,and compromised real-time performance.To counter these,this paper introduces an Active Learning-aided Heuristic Deep Spatio-Textural Ensemble Learning(ALH-DSEL)framework.The model initially identifies keyframes from the surveillance videos with a Multi-Constraint Active Learning(MCAL)approach,with features extracted from DenseNet121.The frames are then segmented employing an optimized Fuzzy C-Means clustering algorithm with Firefly to identify areas of interest.A deep ensemble feature extractor,comprising DenseNet121,EfficientNet-B7,MobileNet,and GLCM,extracts varied spatial and textural features.Fused characteristics are enhanced through PCA and Min-Max normalization and discriminated by a maximum voting ensemble of RF,AdaBoost,and XGBoost.The experimental results show that ALH-DSEL provides higher accuracy,precision,recall,and F1-score,validating its superiority for real-time HAR in surveillance scenarios.
基金Under the auspices of National Natural Science Foundation of China(No.42271125)Jilin Province Foreign Expert Project(No.L202322)Doctoral Research Initiation Project of Jilin Normal University(No.0420237)。
文摘The Songhua River Basin(SRB),ranking third largest in China in terms of both runoff volume and basin area,has experi-enced frequent disasters and drastic changes in runoff since the early 20th century.Many studies have analyzed the causes of runoff re-duction;however,the spatiotemporal differences in runoff contributions and their underlying mechanisms remain poorly understood,which are crucial for regional water resources management and effective utilization.This study used the Mann-Kendall rank correlation trend test,continuous wavelet analysis,cumulative anomaly,and the slope change ratio of cumulative quantities(SCRCQ)method to explore the runoff changes characteristics and spatiotemporal differences of the contributions of climate change and human activities to runoff changes across three sub-basins of the SRB.The results show that:1)runoff from 1955 to 2022 in all the three sub-basins exhibit a statistically significant decreasing trend at 0.05 significant level.2)Four abrupt change points in runoff were detected in Nenjiang River Basin(NRB)and the mainstream of the SRB(MSRB),whereas only two change points in the Second Songhua River(SSRB).3)Runoff and precipitation series of the NRB and MSRB exhibit similar multi-timescale cycle characteristics with the most dominated cycles of 45-58 yr.In contrast,it is 12-18 yr for SSRB.4)Anthropogenic activities are the primary factor leading to in the reduction of runoff in NRB(74.33%-91.67%)and MSRB(50.11%-102.12%),whereas it is only 5.38%-33.12%in SSRB.This is attributed to the uneven distribution of regional climate and human activities in the entire SRB.5)With the growing demand for water diversion for agri-cultural irrigation,anthropogenic activities in the NRB and MSRB have increased.However,the opposite is found in SSR,where the in-creased influence of precipitation on runoff and water conservation policies are identified.
基金supported by the Royal Golden Jubilee(RGJ)Ph.D.Programme(Grant No.PHD/0079/2561)through the National Research Council of Thailand(NRCT)and Thailand Research Fund(TRF).
文摘This research investigates the application of multisource data fusion using a Multi-Layer Perceptron (MLP) for Human Activity Recognition (HAR). The study integrates four distinct open-source datasets—WISDM, DaLiAc, MotionSense, and PAMAP2—to develop a generalized MLP model for classifying six human activities. Performance analysis of the fused model for each dataset reveals accuracy rates of 95.83 for WISDM, 97 for DaLiAc, 94.65 for MotionSense, and 98.54 for PAMAP2. A comparative evaluation was conducted between the fused MLP model and the individual dataset models, with the latter tested on separate validation sets. The results indicate that the MLP model, trained on the fused dataset, exhibits superior performance relative to the models trained on individual datasets. This finding suggests that multisource data fusion significantly enhances the generalization and accuracy of HAR systems. The improved performance underscores the potential of integrating diverse data sources to create more robust and comprehensive models for activity recognition.
