Coupling Analysis of Multiple Machine Learning Models for Human Activity Recognition

Artificial intelligence(AI)technology has become integral in the realm of medicine and healthcare,particularly in human activity recognition(HAR)applications such as fitness and rehabilitation tracking.This study introduces a robust coupling analysis framework that integrates four AI-enabled models,combining both machine learning(ML)and deep learning(DL)approaches to evaluate their effectiveness in HAR.The analytical dataset comprises 561 features sourced from the UCI-HAR database,forming the foundation for training the models.Additionally,the MHEALTH database is employed to replicate the modeling process for comparative purposes,while inclusion of the WISDM database,renowned for its challenging features,supports the framework’s resilience and adaptability.The ML-based models employ the methodologies including adaptive neuro-fuzzy inference system(ANFIS),support vector machine(SVM),and random forest(RF),for data training.In contrast,a DL-based model utilizes one-dimensional convolution neural network(1dCNN)to automate feature extraction.Furthermore,the recursive feature elimination(RFE)algorithm,which drives an ML-based estimator to eliminate low-participation features,helps identify the optimal features for enhancing model performance.The best accuracies of the ANFIS,SVM,RF,and 1dCNN models with meticulous featuring process achieve around 90%,96%,91%,and 93%,respectively.Comparative analysis using the MHEALTH dataset showcases the 1dCNN model’s remarkable perfect accuracy(100%),while the RF,SVM,and ANFIS models equipped with selected features achieve accuracies of 99.8%,99.7%,and 96.5%,respectively.Finally,when applied to the WISDM dataset,the DL-based and ML-based models attain accuracies of 91.4%and 87.3%,respectively,aligning with prior research findings.In conclusion,the proposed framework yields HAR models with commendable performance metrics,exhibiting its suitability for integration into the healthcare services system through AI-driven applications.

Influence of Human Activity Intensity on Habitat Quality in Hainan Tropical Rainforest National Park,China

Due to long-term human activity interference,the Hainan Tropical Rainforest National Park(HTRNP)of China has experienced ecological problems such as habitat fragmentation and biodiversity loss,and with the expanding scope and intensity of human activity impact,the regional ecological security is facing serious challenges.A scientific assessment of the interrelationship between human activity intensity and habitat quality in the HTRNP is a prerequisite for achieving effective management of ecological disturbances caused by human activities and can also provide scientific strategies for the sustainable development of the region.Based on the land use change data in 2000,2010,and 2020,the spatial and temporal variations and the relationship between habitat quality(HQ)and human activity intensity(HAI)in the HTRNP were explored using the integrated valuation of ecosystem services and trade-offs(InVEST)model.System dynamics and land use simulation models were also combined to conduct multi-scenario simulations of their relationships.The results showed that during 2000–2020,the habitat quality of the HTRNP improved,the intensity of human activities decreased each year,and there was a negative correlation between the two.Second,the system dynamic model could be well coupled with the land use simulation model by combining socio-economic and natural factors.The simulation scenarios of the coupling model showed that the harmonious development(HD)scenario is effective in curbing the increasing trend of human activity intensity and decreasing trend of habitat quality,with a weaker trade-off between the two compared with the baseline development(BD)and investment priority oriented(IPO)scenarios.To maintain the authenticity and integrity of the HTRNP,effective measures such as ecological corridor construction,ecological restoration,and the implementation of ecological compensation policies need to be strengthened.

Quantitative contributions of climate change and human activities to vegetation dynamics in the Zoige Plateau from 2001 to 2020

Climate change and human activities such as overgrazing and rapid development of tourism simultaneously affected the vegetation of the Zoige Plateau.However,the spatiotemporal variations of vegetation and the relative contributions of climate change and human activities to these vegetation dynamics remain unclear.Therefore,clarifying how and why the vegetation on the Zoige Plateau changed can provide a scientific basis for the sustainable development of the region.Here,we investigate NDVI trends using the Normalized Difference Vegetation Index(NDVI)as an indicator of vegetation greenness and distinguish the relative effects of climate changes and human activities on vegetation changes by utilizing residual trend analysis and the Geodetector.We find a tendency of vegetation greening from 2001 to 2020,with significant greening accounting for 21.44%of the entire region.However,browning area expanded rapidly after 2011.Warmer temperatures are the primary driver of vegetation changes in the Zoige Plateau.Climatic variations and human activities were responsible for 65.57%and 34.43%of vegetation greening,and 39.14%and 60.86%of vegetation browning,respectively,with browning concentrated along the Yellow,Black and White Rivers.Compared to 2001-2010,the inhibitory effect of human activity and climate fluctuations on vegetation grew dramatically between 2011 and 2020.

Spatial distribution of soil salinization under the influence of human activities in arid areas,China

The Hotan Prefecture of Xinjiang Uygur Autonomous Region,China belongs to arid desert climate,with significant soil salinization issues.The study selected six rivers in Hotan Prefecture(Pishan,Qaraqash,Yurungqash,Celle,Kriya,and Niya rivers)to explore the spatial distribution of soil salinization in this area and its underlying mechanisms.Sampling was conducted along each river's watershed,from the Gobi in the upper reaches,through the anthropogenic impact area in the middle reaches,to the desert area in the lower reaches.Soil physical-chemical indicators,including total soluble salts,pH,K+,Na+,Ca2+,Mg2+,SO42-,Cl-,CO32-,HCO3-,organic matter,available nitrogen,available phosphorus,and available potassium,were tested,along with the total dissolved solids of surface water and groundwater.The results revealed that the soil water and nutrient contents in anthropogenic impact area were higher than those in Gobi and desert areas,while the pH and total soluble salts were lower than those in Gobi and desert areas.The ions in the soil of the study area were primarily Cl-,SO42-,K+,and Na+,and the ion concentration of soil salt were positively correlated with surface water and groundwater.Overall,the study area exhibited low soil water content,low clay content,infertile soil,and high soil salinization,dominated by weak to moderate chloride-sulfate types.Compared with Gobi and desert areas,the soil in anthropogenic impact area had higher soil water content,lower pH,lower soluble salts,and higher nutrients,indicating that human farming activities help mitigate salinization.These findings have practical implications for guiding the scientific prevention and control of soil salinization in the arid areas and for promoting sustainable agricultural development.

Responses of runoff to changes in climate and human activities in the Liuhe River Basin, China

Since the 1950s,numerous soil and water conservation measures have been implemented to control severe soil erosion in the Liuhe River Basin(LRB),China.While these measures have protected the upstream soil and water ecological environment,they have led to a sharp reduction in the downstream flow and the deterioration of the river ecological environment.Therefore,it is important to evaluate the impact of soil and water conservation measures on hydrological processes to assess long-term runoff changes.Using the Soil and Water Assessment Tool(SWAT)models and sensitivity analyses based on the Budyko hypothesis,this study quantitatively evaluated the effects of climate change,direct water withdrawal,and soil and water conservation measures on runoff in the LRB during different periods,including different responses to runoff discharge,hydrological regime,and flood processes.The runoff series were divided into a baseline period(1956-1969)and two altered periods,i.e.,period 1(1970-1999)and period 2(2000-2020).Human activities were the main cause of the decrease in runoff during the altered periods,contributing 86.03%(-29.61 mm),while the contribution of climate change was only 13.70%(-4.70 mm).The impact of climate change manifests as a decrease in flood volume caused by a reduction in precipitation during the flood season.Analysis of two flood cases indicated a 66.00%-84.00%reduction in basin runoff capacity due to soil and water conservation measures in the upstream area.Soil and water conservation measures reduced the peak flow and total flood volume in the upstream runoff area by 77.98%and 55.16%,respectively,even with nearly double the precipitation.The runoff coefficient in the reservoir area without soil and water conservation measures was 4.0 times that in the conservation area.These results contribute to the re-evaluation of soil and water conservation hydrological effects and provide important guidance for water resource planning and water conservation policy formulation in the LRB.

Coupled effects of climate change and human activities on vegetation dynamics in the Southwestern Alpine Canyon Region of China

The driving effects of climate change and human activities on vegetation change have always been a focal point of research.However,the coupling mechanisms of these driving factors across different temporal and spatial scales remain controversial.The Southwestern Alpine Canyon Region of China(SACR),as an ecologically fragile area,is highly sensitive to the impacts of climate change and human activities.This study constructed a vegetation cover dataset for the SACR based on the Enhanced Vegetation Index(EVI)from 2000 to 2020.Spatial autocorrelation,Theil-Sen trend,and Mann-Kendall tests were used to analyze the spatiotemporal characteristics of vegetation cover changes.The main drivers of spatial heterogeneity in vegetation cover were identified using the optimal parameter geographic detector,and an improved residual analysis model was employed to quantify the relative contributions of climate change and human activities to interannual vegetation cover changes.The main findings are as follows:Spatially,vegetation cover exceeds 60%in most areas,especially in the southern part of the study area.However,the border area between Linzhi and Changdu exhibits lower vegetation cover.Climate factors are the primary drivers of spatial heterogeneity in vegetation cover,with temperature having the most significant influence,as indicated by its q-value,which far exceeds that of other factors.Additionally,the interaction q-value between the two factors significantly increases,showing a relationship of bivariate enhancement and nonlinear enhancement.In terms of temporal changes,vegetation cover shows an overall improving trend from 2000 to 2020,with significant increases observed in 68.93%of the study area.Among these,human activities are the main factors driving vegetation cover change,with a relative contribution rate of 41.31%,while climate change and residual factors contribute 35.66%and 23.53%,respectively.By thoroughly exploring the coupled mechanisms of vegetation change,this study provides important references for the sustainable management and conservation of the vegetation ecosystem in the SACR.

Study on the spatial and temporal evolutionary characteristics of ozone concentration and the impact of human activities in China in 2019

Ozone(O_(3))pollution has a profound impact on human health,vegetation development,and the ecological environment,making it a critical focus of global academic research.In recent years,O_(3)pollution in China has been on a steady rise,with ozone emerging as the sole conventional pollutant to consistently increase in concentration without any decline.This study conducted a quantitative analysis of O_(3)concentrations across 367 Chinese cities in 2019,examining spatial autocorrelation and local clustering of O_(3)levels,and investigated the diverse relationships between human activity factors and O_(3)concentration.The seasonal fluctuation of O_(3)exhibited the“M-type”pattern,with peak concentrations in winter and the lowest levels in summer.The center of O_(3)pollution migrated southeastward,with the area of highest concentration progressively shifting south along the eastern coast.Moreover,O_(3)concentration showed a strong positive correlation with population density,road freight volume,and industrial emissions,suggesting that human activities,vehicle emissions,and industrial operations are significant contributors to O_(3)production.The results provide comprehensive information on the characteristics,causes,and occurrence mechanism of O_(3)in Chinese cities that can be utilized by global government departments to formulate strategies to prevent and control O_(3)pollution.

The Crested Ibises expanding to plain areas exhibit a higher tolerance of human proximity

Animals must strike a balance between anti-predation behavior and other essential behaviors,such as foraging.Within the same species,strategies may vary on individuals’risk-taking preferences,and in this process the environment is a determinant,in addition to predator regime.The Crested Ibis(Nipponia nippon)exhibits such tendency.This is an endangered species,once inhabiting exclusively in China’s Qinling Mountain.This used to be the sole remaining wild population.However,over recent decades,this population has expanded.A portion has relocated to breed in the lower plain area,which is characterized by elevated level of human activities and landscape complexity.We used flight initiation distance(FID)as an indicator of the ibises’risk-taking preference,particularly their response to human proximity.Additionally,we examined the environmental factors influencing their foraging site selection,including altitude,terrain openness,human activity intensity and human construction.Our findings revealed a significantly shorter FID among individuals relocating to plain habitats,indicating a higher tolerance of human proximity.The results showed that FID decreased with distance to the nearest human settlement.Another finding is that FID was independent of instant human activity intensity and environmental factors(altitude and terrain openness).These different may arise from various combinations of human activity,predation risk,and food abundance within the two habitats.These results provide insights into the in situ conservation of the threatened species within the context of global urbanization.

Impacts of climate change and human activities on vegetation dynamics on the Mongolian Plateau, East Asia from 2000 to 2023

The Mongolian Plateau in East Asia is one of the largest contingent arid and semi-arid areas of the world.Under the impacts of climate change and human activities,desertification is becoming increasingly severe on the Mongolian Plateau.Understanding the vegetation dynamics in this region can better characterize its ecological changes.In this study,based on Moderate Resolution Imaging Spectroradiometer(MODIS)images,we calculated the kernel normalized difference vegetation index(kNDVI)on the Mongolian Plateau from 2000 to 2023,and analyzed the changes in kNDVI using the Theil-Sen median trend analysis and Mann-Kendall significance test.We further investigated the impact of climate change on kNDVI change using partial correlation analysis and composite correlation analysis,and quantified the effects of climate change and human activities on kNDVI change by residual analysis.The results showed that kNDVI on the Mongolian Plateau was increasing overall,and the vegetation recovery area in the southern region was significantly larger than that in the northern region.About 50.99%of the plateau showed dominant climate-driven effects of temperature,precipitation,and wind speed on kNDVI change.Residual analysis showed that climate change and human activities together contributed to 94.79%of the areas with vegetation improvement.Appropriate human activities promoted the recovery of local vegetation,and climate change inhibited vegetation growth in the northern part of the Mongolian Plateau.This study provides scientific data for understanding the regional ecological environment status and future changes and developing effective ecological protection measures on the Mongolian Plateau.

Changes of coastline and tidal flat and its implication for ecological protection under human activities: Take China’s Bohai Bay as an example

The change processes and trends of shoreline and tidal flat forced by human activities are essential issues for the sustainability of coastal area,which is also of great significance for understanding coastal ecological environment changes and even global changes.Based on field measurements,combined with Linear Regression(LR)model and Inverse Distance Weighing(IDW)method,this paper presents detailed analysis on the change history and trend of the shoreline and tidal flat in Bohai Bay.The shoreline faces a high erosion chance under the action of natural factors,while the tidal flat faces a different erosion and deposition patterns in Bohai Bay due to the impact of human activities.The implication of change rule for ecological protection and recovery is also discussed.Measures should be taken to protect the coastal ecological environment.The models used in this paper show a high correlation coefficient between observed and modeling data,which means that this method can be used to predict the changing trend of shoreline and tidal flat.The research results of present study can provide scientific supports for future coastal protection and management.

Hydrochemical characteristics of surface water in Hengduan mountain region of Eastern Tibet and its response to human activities:A case study of Duoqu Basin,Jinsha River

The analysis of hydrochemical characteristics and influencing factors of surface river on plateau is helpful to study water hydrological cycle and environmental evolution,which can scientifically guide rational development and utilization of water resources and planning of ecological environment protection.With the expansion and diversification of human activities,the quality of surface rivers will be more directly affected.Therefore,it is of great significance to pay attention to the hydrochemical characteristics of plateau surface rivers and the influence of human activities on their circulation and evolution.In this study,surface water in the Duoqu basin of Jinsha River located in Hengduan mountain region of Eastern Tibet was selected as the representative case.Twenty-three groups of surface water samples were collected to analyze the hydrochemical characteristics and ion sources based on correlation analysis,piper trigram,gibbs model,hydrogen and oxygen isotopic techniques.The results suggest the following:(1)The pH showed slight alkalinity with the value ranged from 7.25 to 8.62.Ca^(2+),Mg^(2+)and HCO_(3)^(–)were the main cations and anions.HCO_(3)^(-)Ca and HCO_(3)^(-)Ca·Mg were the primary hydrochemical types for the surface water of Duoqu River.The correlation analysis showed that TDS had the most significant correlation with Ca^(2+),Mg^(2+)and HCO_(3)^(–).Analysis on hydrogen and oxygen isotopes indicated that the surface rivers were mainly recharged by atmospheric precipitation and glacial melt water in this study area.(2)The surface water had a certain reverse cation alternating adsorption,and surface water ions were mainly derived from rock weathering,mainly controlled by weathering and dissolution of carbonates,and secondly by silicates and sodium rocks.(3)The influence of human activities was weak,while the development of cinnabar minerals had a certain impact on the hydrochemistry characteristics,which was the main factor for causing the increase of SO_(4)^(2–).The densely populated county towns and temples with frequent incense burning activities may cause some anomalies of surface water quality.At present,the Duoqu River watershed had gone through a certain influence of mineral exploitation,so the hydrological cycle and river eco-environment at watershed scale will still bound to be change.The results could provide basic support for better understanding water balance evolution as well as the ecological protection of Duoqu River watershed.

TransTM:A device-free method based on time-streaming multiscale transformer for human activity recognition

RFID-based human activity recognition(HAR)attracts attention due to its convenience,noninvasiveness,and privacy protection.Existing RFID-based HAR methods use modeling,CNN,or LSTM to extract features effectively.Still,they have shortcomings:1)requiring complex hand-crafted data cleaning processes and 2)only addressing single-person activity recognition based on specific RF signals.To solve these problems,this paper proposes a novel device-free method based on Time-streaming Multiscale Transformer called TransTM.This model leverages the Transformer's powerful data fitting capabilities to take raw RFID RSSI data as input without pre-processing.Concretely,we propose a multiscale convolutional hybrid Transformer to capture behavioral features that recognizes singlehuman activities and human-to-human interactions.Compared with existing CNN-and LSTM-based methods,the Transformer-based method has more data fitting power,generalization,and scalability.Furthermore,using RF signals,our method achieves an excellent classification effect on human behaviorbased classification tasks.Experimental results on the actual RFID datasets show that this model achieves a high average recognition accuracy(99.1%).The dataset we collected for detecting RFID-based indoor human activities will be published.

Centennial Analysis of Human Activity Intensity and Associated Historical Events in Heilongjiang River Sino-Russo Watershed

Human activities in a transborder watershed are complex under the influence of domestic policies,international relations,and global events.Understanding the forces driving human activity change is important for the development of transborder watershed.In this study,we used global historical land cover data,the hemeroby index model,and synthesized major historical events to analyze how human activity intensity changed in the Heilongjiang River(Amur River in Russia)watershed(HLRW).The results showed that there was a strong spatial heterogeneity in the variation of human activity intensity in the HLRW over the past century(1900-2016).On the Chinese side,the human activity intensity change shifted from the plain areas for agricultural reclamation to the mountainous areas for timber extraction.On the Russian side,human activity intensity changes mostly concentrated along the Trans-Siberian Railway and the Baikal-Amur Mainline.Localized variation of human activity intensity tended to respond to regional events while regionalized variation tends to reflect national policy change or broad international events.The similarities and differences between China and Russia in policies and positions in international events resulted in synchronous and asynchronous changes in human activity intensity.Meanwhile,policy shifts were often confined by the natural features of the watershed.These results reveal the historical origins and fundamental connotations of watershed development and contribute to formulating regional management policies that coordinate population,eco-nomic,social,and environmental activities.

An Investigation of Frequency-Domain Pruning Algorithms for Accelerating Human Activity Recognition Tasks Based on Sensor Data

The rapidly advancing Convolutional Neural Networks(CNNs)have brought about a paradigm shift in various computer vision tasks,while also garnering increasing interest and application in sensor-based Human Activity Recognition(HAR)efforts.However,the significant computational demands and memory requirements hinder the practical deployment of deep networks in resource-constrained systems.This paper introduces a novel network pruning method based on the energy spectral density of data in the frequency domain,which reduces the model’s depth and accelerates activity inference.Unlike traditional pruning methods that focus on the spatial domain and the importance of filters,this method converts sensor data,such as HAR data,to the frequency domain for analysis.It emphasizes the low-frequency components by calculating their energy spectral density values.Subsequently,filters that meet the predefined thresholds are retained,and redundant filters are removed,leading to a significant reduction in model size without compromising performance or incurring additional computational costs.Notably,the proposed algorithm’s effectiveness is empirically validated on a standard five-layer CNNs backbone architecture.The computational feasibility and data sensitivity of the proposed scheme are thoroughly examined.Impressively,the classification accuracy on three benchmark HAR datasets UCI-HAR,WISDM,and PAMAP2 reaches 96.20%,98.40%,and 92.38%,respectively.Concurrently,our strategy achieves a reduction in Floating Point Operations(FLOPs)by 90.73%,93.70%,and 90.74%,respectively,along with a corresponding decrease in memory consumption by 90.53%,93.43%,and 90.05%.

Impact of climate change and human activities on the spatiotemporal dynamics of surface water area in Gansu Province, China

Understanding the dynamics of surface water area and their drivers is crucial for human survival and ecosystem stability in inland arid and semi-arid areas.This study took Gansu Province,China,a typical area with complex terrain and variable climate,as the research subject.Based on Google Earth Engine,we used Landsat data and the Open-surface Water Detection Method with Enhanced Impurity Control method to monitor the spatiotemporal dynamics of surface water area in Gansu Province from 1985 to 2022,and quantitatively analyzed the main causes of regional differences in surface water area.The findings revealed that surface water area in Gansu Province expanded by 406.88 km2 from 1985 to 2022.Seasonal surface water area exhibited significant fluctuations,while permanent surface water area showed a steady increase.Notably,terrestrial water storage exhibited a trend of first decreasing and then increasing,correlated with the dynamics of surface water area.Climate change and human activities jointly affected surface hydrological processes,with the impact of climate change being slightly higher than that of human activities.Spatially,climate change affected the'source'of surface water to a greater extent,while human activities tended to affect the'destination'of surface water.Challenges of surface water resources faced by inland arid and semi-arid areas like Gansu Province are multifaceted.Therefore,we summarized the surface hydrology patterns typical in inland arid and semi-arid areas and tailored surface water'supply-demand'balance strategies.The study not only sheds light on the dynamics of surface water area in Gansu Province,but also offers valuable insights for ecological protection and surface water resource management in inland arid and semi-arid areas facing water scarcity.

Combined CNN-LSTM Deep Learning Algorithms for Recognizing Human Physical Activities in Large and Distributed Manners:A Recommendation System

Recognizing human activity(HAR)from data in a smartphone sensor plays an important role in the field of health to prevent chronic diseases.Daily and weekly physical activities are recorded on the smartphone and tell the user whether he is moving well or not.Typically,smartphones and their associated sensing devices operate in distributed and unstable environments.Therefore,collecting their data and extracting useful information is a significant challenge.In this context,the aimof this paper is twofold:The first is to analyze human behavior based on the recognition of physical activities.Using the results of physical activity detection and classification,the second part aims to develop a health recommendation system to notify smartphone users about their healthy physical behavior related to their physical activities.This system is based on the calculation of calories burned by each user during physical activities.In this way,conclusions can be drawn about a person’s physical behavior by estimating the number of calories burned after evaluating data collected daily or even weekly following a series of physical workouts.To identify and classify human behavior our methodology is based on artificial intelligence models specifically deep learning techniques like Long Short-Term Memory(LSTM),stacked LSTM,and bidirectional LSTM.Since human activity data contains both spatial and temporal information,we proposed,in this paper,to use of an architecture allowing the extraction of the two types of information simultaneously.While Convolutional Neural Networks(CNN)has an architecture designed for spatial information,our idea is to combine CNN with LSTM to increase classification accuracy by taking into consideration the extraction of both spatial and temporal data.The results obtained achieved an accuracy of 96%.On the other side,the data learned by these algorithms is prone to error and uncertainty.To overcome this constraint and improve performance(96%),we proposed to use the fusion mechanisms.The last combines deep learning classifiers tomodel non-accurate and ambiguous data to obtain synthetic information to aid in decision-making.The Voting and Dempster-Shafer(DS)approaches are employed.The results showed that fused classifiers based on DS theory outperformed individual classifiers(96%)with the highest accuracy level of 98%.Also,the findings disclosed that participants engaging in physical activities are healthy,showcasing a disparity in the distribution of physical activities between men and women.

Identification and distribution of 13003 landslides in the northwest margin of Qinghai-Tibet Plateau based on human-computer interaction remote sensing interpretation

The periphery of the Qinghai-Tibet Plateau is renowned for its susceptibility to landslides.However,the northwestern margin of this region,characterised by limited human activities and challenging transportation,remains insufficiently explored concerning landslide occurrence and dispersion.With the planning and construction of the Xinjiang-Tibet Railway,a comprehensive investigation into disastrous landslides in this area is essential for effective disaster preparedness and mitigation strategies.By using the human-computer interaction interpretation approach,the authors established a landslide database encompassing 13003 landslides,collectively spanning an area of 3351.24 km^(2)(36°N-40°N,73°E-78°E).The database incorporates diverse topographical and environmental parameters,including regional elevation,slope angle,slope aspect,distance to faults,distance to roads,distance to rivers,annual precipitation,and stratum.The statistical characteristics of number and area of landslides,landslide number density(LND),and landslide area percentage(LAP)are analyzed.The authors found that a predominant concentration of landslide origins within high slope angle regions,with the highest incidence observed in intervals characterised by average slopes of 20°to 30°,maximum slope angle above 80°,along with orientations towards the north(N),northeast(NE),and southwest(SW).Additionally,elevations above 4.5 km,distance to rivers below 1 km,rainfall between 20-30 mm and 30-40 mm emerge as particularly susceptible to landslide development.The study area’s geological composition primarily comprises Mesozoic and Upper Paleozoic outcrops.Both fault and human engineering activities have different degrees of influence on landslide development.Furthermore,the significance of the landslide database,the relationship between landslide distribution and environmental factors,and the geometric and morphological characteristics of landslides are discussed.The landslide H/L ratios in the study area are mainly concentrated between 0.4 and 0.64.It means the landslides mobility in the region is relatively low,and the authors speculate that landslides in this region more possibly triggered by earthquakes or located in meizoseismal area.

Impacts of Human Activities and Season on Species Diversity and Abundance of Butterflies in Mpanga Kipengere Game Reserve and Surrounding Farmlands, Tanzania

Maintaining natural habitats is crucial for the preservation of insects and other species that indicate environmental changes. However, the Mpanga/Kipengere Game Reserve and its surrounding farmlands are facing disturbance due to human activities, which is putting many wildlife species, particularly larger mammals, at risk. To determine the impact of human activities on butterfly species diversity and abundance in the reserve and its surrounding areas, we conducted a study from November 2021 to October 2023. We collected butterfly data using transect walks and baited traps in two habitat types. Our study yielded 2799 butterfly Individuals ranging in 124 species divided into five families habitat, season, and anthropogenic factors are significant environmental variables influencing species diversity and abundance of butterflies. Therefore, it’s important to protect habitat and dry-season water for the conservation of invertebrates such as butterflies. Our study findings provide essential information for ecological monitoring and future assessment of the Mpanga/Kipengere Game Reserve ecosystem health.

Evaluating the Impacts of Human Activities on Diversity, Abundance, and Distribution of Large Mammals in Nimule National Park, South Sudan

Globally, human activities have a significant impact on the diversity, abundance, and distribution of large mammals in Protected Areas (PAs). These disturbances increase human pressure on biodiversity and species habitats, highlighting the need for conservation. This study aimed to assess the abundance and distribution of large mammals in different habitat types within Nimule National Park (NNP) and understand the impacts of human activities on them. Data on the abundance and distribution of large mammals and their respective habitat types were collected through line transect surveys. Human activity signs were observed and recorded along the transect lines. To estimate the impacts of human activities on the diversity, abundance, and distribution of large mammal species, as well as to identify any significant differences between them and their habitat types, the study utilized the Kruskal Wallis test, Polynomial multiple regressions, and diversity indices. The findings from the Shannon-Weiner and Simpson indices indicated that large mammal species were more diverse inside the park (H’ = 1.136;D = 0.570) compared to the buffer zone (H’ = 0.413;D = 0.171), with 85% (443 out of 510 samples) recorded within Nimule National Park. The species abundance showed a semi-balanced status (0.58). The diversity results among different habitat types revealed that large mammals were more diverse and highly distributed in both open woodlands (244) and dense woodlands (192), while riverine vegetation had the lowest diversity (8). Statistical tests demonstrated a highly significant difference at a 99% confidence interval (p-value = 0.01) between habitat types and identified species of large mammals. Additionally, the results highlighted the high abundance of Uganda kob (274), baboons (141), and warthog (57) across most habitat types, accounting for at least 75% of their distribution. The most prevalent human activities observed were cattle footprints (27%) and cattle dung (14%). Human footprints and tree cutting combined accounted for 9%, indicating the practice of livestock grazing, poaching, encroachment, and fuelwood collection by local communities. However, these activities did not appear to significantly impact the diversity, abundance, and distribution of large mammals in Nimule National Park. Therefore, it is crucial to foster shared responsibilities and engage relevant stakeholders in the management and conservation of large wildlife species. Regular community awareness programs should be implemented to cultivate a sense of ownership. Moreover, it is recommended that a comprehensive survey be conducted on the population status of all mammal species in Nimule National Park, including its surrounding Buffer Zone. Monitoring the impact of human activities on their behavior and habitats using satellite images should also be carried out at least every five to ten years.

A Novel Method for Cross-Subject Human Activity Recognition with Wearable Sensors

Human Activity Recognition (HAR) is an important way for lower limb exoskeleton robots to implement human-computer collaboration with users. Most of the existing methods in this field focus on a simple scenario recognizing activities for specific users, which does not consider the individual differences among users and cannot adapt to new users. In order to improve the generalization ability of HAR model, this paper proposes a novel method that combines the theories in transfer learning and active learning to mitigate the cross-subject issue, so that it can enable lower limb exoskeleton robots being used in more complex scenarios. First, a neural network based on convolutional neural networks (CNN) is designed, which can extract temporal and spatial features from sensor signals collected from different parts of human body. It can recognize human activities with high accuracy after trained by labeled data. Second, in order to improve the cross-subject adaptation ability of the pre-trained model, we design a cross-subject HAR algorithm based on sparse interrogation and label propagation. Through leave-one-subject-out validation on two widely-used public datasets with existing methods, our method achieves average accuracies of 91.77% on DSAD and 80.97% on PAMAP2, respectively. The experimental results demonstrate the potential of implementing cross-subject HAR for lower limb exoskeleton robots.