A Unified Model Fusing Region of Interest Detection and Super Resolution for Video Compression

High-resolution video transmission requires a substantial amount of bandwidth.In this paper,we present a novel video processing methodology that innovatively integrates region of interest(ROI)identification and super-resolution enhancement.Our method commences with the accurate detection of ROIs within video sequences,followed by the application of advanced super-resolution techniques to these areas,thereby preserving visual quality while economizing on data transmission.To validate and benchmark our approach,we have curated a new gaming dataset tailored to evaluate the effectiveness of ROI-based super-resolution in practical applications.The proposed model architecture leverages the transformer network framework,guided by a carefully designed multi-task loss function,which facilitates concurrent learning and execution of both ROI identification and resolution enhancement tasks.This unified deep learning model exhibits remarkable performance in achieving super-resolution on our custom dataset.The implications of this research extend to optimizing low-bitrate video streaming scenarios.By selectively enhancing the resolution of critical regions in videos,our solution enables high-quality video delivery under constrained bandwidth conditions.Empirical results demonstrate a 15%reduction in transmission bandwidth compared to traditional super-resolution based compression methods,without any perceivable decline in visual quality.This work thus contributes to the advancement of video compression and enhancement technologies,offering an effective strategy for improving digital media delivery efficiency and user experience,especially in bandwidth-limited environments.The innovative integration of ROI identification and super-resolution presents promising avenues for future research and development in adaptive and intelligent video communication systems.

A New Method to Locate the Region of Interest( ROI) of Palmprint

Biometric identification was a kind of identity recognition technology by making use of the human's unique physiological or behavioral characteristics,it provided a high reliability and stability way for the identification. Global threshold binarization palmprint image is used in this paper,and the bio-morphological methods are used to get the sensitive area of palmprint image's positioning point,so as to extract the region of interest. The palmprint collection is realized on the FPGA chip,and this kind of collection method uses the DSP Builder toolbox to realize visual programming in Matlab / Simulink and achieve fast modeling and development. The practice proves that this method is simple,flexible and its equipment is portable and fast.

A mathematical morphological approach for region of interest coding of microscopy image compression

A novel mathematical morphological approach for region of interest(ROI) automatic determination and JPEG2000-based coding of microscopy image compression is presented.The algorithm is very fast and requires lower computing power,which is particularly suitable for some irregular region-based cell microscopy images with poor qualities.Firstly,an active threshold-based method is discussed to create a rough mask of regions of interest(cells).And then some morphological operations are designed and applied to achieve the segmentation of cells.In addition,an extra morphological operation,dilation,is applied to create the final mask with some redundancies to avoid the"edge effect"after removing false cells.Finally,ROI and region of background(ROB) are obtained and encoded individually in different compression ratio flexibly based on the JPEG2000,which can adjust the quality between ROI and ROB without coding for ROI shape.The experimental results certify the effectiveness of the proposed algorithm,and compared with JPEG2000,the proposed algorithm has better performance in both subjective quality and objective quality at the same compression ratios.

Autonomous Lane Keeping Solution Based on Adaptive Gray Threshold and Region of Interest

Autonomous lane keeping is an important technology in intelligent transportation,which is used to avoid unnecessary traffic accidents caused by lane departure.To adapt different lighting environment,and make up ordinary Hough transform’s shortcomings of tardiness and poor immunity,we propose an improved algorithm by using adaptive gray threshold and setting Region of interest(ROI),to do the quick Hough transform for tracking lane line,implementing autonomous lane keeping. The dynamic adaptive threshold method can be suitable with different lighting conditions and quickly,accurately remove most of the information not relative to lane line.Meanwhile setting ROI can let the program only care about the specific region which can provide useful information and further reduce the processing data.And then on the basic of identification,we put forward some efficient innovation strategy about the control logic of straight state,curve state and the transition state.The experiment proves that this solution greatly raises efficiency.

Construction and Application of a Regional Kilometer-Scale Carbon Source and Sink Assimilation Inversion System(CCMVS-R)

CO_(2)is one of the most important greenhouse gases(GHGs)in the earth’s atmosphere.Since the industrial era,anthropogenic activities have emitted excessive quantities of GHGs into the atmosphere,resulting in climate warming since the 1950s and leading to an increased frequency of extreme weather and climate events.In 2020,China committed to striving for carbon neutrality by 2060.This commitment and China’s consequent actions will result in significant changes in global and regional anthropogenic carbon emissions and therefore require timely,comprehensive,and objective monitoring and verification support(MVS)systems.The MVS approach relies on the top-down assimilation and inversion of atmospheric CO_(2)concentrations,as recommended by the Intergovernmental Panel on Climate Change(IPCC)Inventory Guidelines in 2019.However,the regional high-resolution assimilation and inversion method is still in its initial stage of development.Here,we have constructed an inverse system for carbon sources and sinks at the kilometer level by coupling proper orthogonal decomposition(POD)with four-dimensional variational(4DVar)data assimilation based on the weather research and forecasting-greenhouse gas(WRF-GHG)model.Our China Carbon Monito ring and Verification Support at the Regional level(CCMVS-R)system can continuously assimilate information on atmospheric CO_(2)and other related information and realize the inversion of regional and local anthropogenic carbon emissions and natural terrestrial ecosystem carbon exchange.Atmospheric CO_(2)data were collected from six ground-based monito ring sites in Shanxi Province,China to verify the inversion effect of regio nal anthropogenic carbon emissions by setting ideal and real experiments using a two-layer nesting method(at 27 and 9 km).The uncertainty of the simulated atmospheric CO_(2)decreased significantly,with a root-mean-square error of CO_(2)concentration values between the ideal value and the simulated after assimilation was close to 0.The total anthropogenic carbon emissions in Shanxi Province in 2019 from the assimilated inversions were approximately 28.6%(17%-38%)higher than the mean of five emission inventories using the bottomup method,showing that the top-down CCMVS-R system can obtain more comprehensive information on anthropogenic carbon emissions.

A core-satellite self-assembled SERS aptasensor containing a“biological-silent region”Raman tag for the accurate and ultrasensitive detection of histamine

Herein,a novel interference-free surface-enhanced Raman spectroscopy(SERS)strategy based on magnetic nanoparticles(MNPs)and aptamer-driven assemblies was proposed for the ultrasensitive detection of histamine.A core-satellite SERS aptasensor was constructed by combining aptamer-decorated Fe_(3)O_(4)@Au MNPs(as the recognize probe for histamine)and complementary DNA-modified silver nanoparticles carrying 4-mercaptobenzonitrile(4-MBN)(Ag@4-MBN@Ag-c-DNA)as the SERS signal probe for the indirect detection of histamine.Under an applied magnetic field in the absence of histamine,the assembly gave an intense Raman signal at“Raman biological-silent”region due to 4-MBN.In the presence of histamine,the Ag@4-MBN@Ag-c-DNA SERS-tag was released from the Fe_(3)O_(4)@Au MNPs,thus decreasing the SERS signal.Under optimal conditions,an ultra-low limit of detection of 0.65×10^(-3)ng/mL and a linear range 10^(-2)-10^5 ng/mL on the SERS aptasensor were obtained.The histamine content in four food samples were analyzed using the SERS aptasensor,with the results consistent with those determined by high performance liquid chromatography.The present work highlights the merits of indirect strategies for the ultrasensitive and highly selective SERS detection of small biological molecules in complex matrices.

Diagnostic Study of an Extreme Explosive Cyclone over the Kuroshio/Kuroshio Extension Region

Explosive cyclones(ECs)occur frequently over the Kuroshio/Kuroshio Extension region.The most rapidly intensified EC over the Kuroshio/Kuroshio Extension region during the 42 years(1979-2020)of cold seasons(October-April)was studied to reveal the variations of the key factors at different explosive-developing stages.This EC had weak low-level baroclinicity,mid-level cyclonic-vorticity advection,and strong low-level water vapor convergence at the initial explosive-developing stage.The low-level baroclinicity and mid-level cyclonic-vorticity advection increased substantially during the maximum-deepening-rate stage.The diagnostic analyses using the Zwack-Okossi equation showed that diabatic heating was the main contributor to the initial rapid intensification of this EC.The cyclonic-vorticity advection and warm-air advection enhanced rapidly in the middle and upper troposphere and contributed to the maximum rapid intensification,whereas the diabatic heating weakened slightly in the mid-low troposphere.The relative contribution of the diabatic heating decreased from the initial explosive-developing stage to the maximum-deepening-rate stage due to the enhancement of other factors(the cyclonic-vorticity advection and warm-air advection).Furthermore,the physical factors contributing to this EC varied with the explosive-developing stage.The non-key factors at the initial explosive-developing stage need attention to forecast the rapid intensification.

Interdecadal variability of summer precipitation in the Three River Source Region: Influences of SST and zonal shifts of the East Asian subtropical westerly jet

Summer precipitation in the Three Rivers Source Region(TRSR)of China is vital for the headwaters of the Yellow,Yangtze,and Lancang rivers and exhibits significant interdecadal variability.This study investigates the influence of the East Asian westerly jet(EAWJ)on TRSR rainfall.A strong correlation is found between TRSR summer precipitation and the Jet Zonal Position Index(JZPI)of the EAWJ from 1961 to 2019(R=0.619,p<0.01).During periods when a positive JZPI indicates a westward shift in the EAWJ,enhanced water vapor anomalies,warmer air,and low-level convergence anomalies contribute to increased TRSR summer precipitation.Using empirical orthogonal function and regression analyses,this research identifies the influence of large-scale circulation anomalies associated with the Atlantic–Eurasian teleconnection(AEA)from the North Atlantic(NA).The interdecadal variability between the NA and central tropical Pacific(CTP)significantly affects TRSR precipitation.This influence is mediated through the AEA via a Rossby wave train extending eastward along the EAWJ,and another south of 45°N.Moreover,the NA–CTP Opposite Phase Index(OPI),which quantifies the difference between the summer mean sea surface temperatures of the NA and the CTP,is identified as a critical factor in modulating the strength of this teleconnection and influencing the zonal position of the EAWJ.

Spatiotemporal variability of rain-on-snow events in the arid region of Northwest China

Rain-on-snow(ROS)events involve rainfall on snow surfaces,and the occurrence of ROS events can exacerbate water scarcity and ecosystem vulnerability in the arid region of Northwest China(ARNC).In this study,using daily snow depth data and daily meteorological data from 68 meteorological stations provided by the China Meteorological Administration National Meteorological Information Centre,we investigated the spatiotemporal variability of ROS events in the ARNC from 1978 to 2015 and examined the factors affecting these events and possible changes of future ROS events in the ARNC.The results showed that ROS events in the ARNC mainly occurred from October to May of the following year and were largely distributed in the Qilian Mountains,Tianshan Mountains,Ili River Valley,Tacheng Prefecture,and Altay Prefecture,with the Ili River Valley,Tacheng City,and Altay Mountains exhibiting the most occurrences.Based on the intensity of ROS events,the areas with the highest risk of flooding resulting from ROS events in the ARNC were the Tianshan Mountains,Ili River Valley,Tacheng City,and Altay Mountains.The number and intensity of ROS events in the ARNC largely increased from 1978 to 2015,mainly influenced by air temperature and the number of rainfall days.However,due to the snowpack abundance in areas experiencing frequent ROS events in the ARNC,snowpack changes exerted slight impact on ROS events,which is a temporary phenomenon.Furthermore,elevation imposed lesser impact on ROS events in the ARNC than other factors.In the ARNC,the start time of rainfall and the end time of snowpack gradually advanced from the spring of the current year to the winter of the previous year,while the end time of rainfall and the start time of snowpack gradually delayed from autumn to winter.This may lead to more ROS events in winter in the future.These results could provide a sound basis for managing water resources and mitigating related disasters caused by ROS events in the ARNC.

Assessment of plant diversity of endemic species of the Saharo-Arabian region in Egypt

Savanna, semi-deserts, and hot deserts characterize the Saharo-Arabian region, which includes Morocco, Mauretania, Algeria, Tunisia, Libya, Egypt, Palestine, Kuwait, Saudi Arabia, Qatar, Bahrain, the United Arab Emirates, Oman, Yemen, southern Jordan, Syria, Iraq, Iran, Afghanistan, Pakistan, and northern India. Its neighboring regions, the Sudano-Zambezian region belonging to the Paleotropical Kingdom and the Mediterranean and Irano-Turanian regions included in the Holarctic Kingdom, share a large portion of their flora with the Saharo-Arabian region. Despite the widespread acknowledgment of the region's global importance for plant diversity, an up to date list of the Saharo-Arabian endemics is still unavailable. The available data are frequently insufficient or out of date at both the whole global and the national scales. Therefore, the present study aims at screening and verifying the Saharo-Arabian endemic plants and determining the phytogeographical distribution of these taxa in the Egyptian flora. Hence, a preliminary list of 429 Saharo-Arabian endemic plants in Egypt was compiled from the available literature. Indeed, by excluding the species that were recorded in any countries or regions outside the Saharo-Arabian region based on different literature, database reviews, and websites, the present study has reduced this number to 126 taxa belonging to 87 genera and 37 families. Regarding the national geographic distribution, South Sinai is the richest region with 83 endemic species compared with other eight phytogeographic regions in Egypt, followed by the Isthmic Desert(the middle of Sinai Peninsula, 53 taxa). Sahara regional subzone(SS1) distributes all the 126 endemic species, Arabian regional subzone(SS2) owns 79 taxa, and Nubo-Sindian subzone(SS3) distributes only 14 endemics. Seven groups were recognized at the fourth level of classification as a result of the application of the two-way indicator species analysis(TWINSPAN) to the Saharo-Arabian endemic species in Egypt, i.e., Ⅰ Asphodelus refractus group, Ⅱ Agathophora alopecuroides var. papillosa group, Ⅲ Anvillea garcinii group, Ⅳ Reseda muricata group, V Agathophora alopecuroides var. alopecuroides group, Ⅵ Scrophularia deserti group, and Ⅶ Astragalus schimperi group. It's crucial to clearly define the Saharo-Arabian endemics and illustrate an updated verified database of these taxa for a given territory for providing future management plans that support the conservation and sustainable use of these valuable species under current thought-provoking devastating impacts of rapid anthropogenic and climate change in this region.

Surface and Deep Structure of the Hanshan-Wuwei Basins in the Lower Yangtze Region:Implications for Mesozoic Tectonic Evolution of the South China Block

Indicating the tectonic features of the Hanshan-Wuwei basin can reconstruct the framework of the basins formed in Mesozoic and further understand the Mesozoic tectonic evolution of the South China Block.Studies on surface structure,regional stress field and deep geophysical characteristics of the Mesozoic Hanshan-Wuwei basin in Lower Yangtze region were carried out.NE-NNE trending folds and faults developed in the northern margin of the basins.The reconstruction of tectonic stress fields indicates four stress stages dominating the basins'evolution including NW-SE compression,N-S compression,NW-SE extension and NWW-SEE compression.2D seismic profiles reveal coexistence of thrust,strike-slip and normal faults in the basin.Combined with regional geological studies,the geodynamic processes for the formation of the Hanshan-Wuwei basin can be divided into five stages:1)During the Late Triassic,EW trending foreland basin was formed by N-S compression;2)From Mid-Jurassic to Late Jurassic,continuous compression strengthened the foreland deformation and formed thrust nappes.In this stage,the integrated foreland basin was compartmentalized or fragmented,and transferred to the broken foreland basin;3)NE-trending sinistral strike-slip movement at the beginning of the Early Cretaceous;4)Regional extension resulted in normal faults and rift basins developing in the Late Cretaceous;5)The NWW-SEE compression at the end of the Late Cretaceous caused NW sinistral strike-slip faults to form,which partly transformed the rift basin.

Land use change and its driving factors in the ecological function area:A case study in the Hedong Region of the Gansu Province,China

Land use and cover change(LUCC)is important for the provision of ecosystem services.An increasing number of recent studies link LUCC processes to ecosystem services and human well-being at different scales recently.However,the dynamic of land use and its drivers receive insufficient attention within ecological function areas,particularly in quantifying the dynamic roles of climate change and human activities on land use based on a long time series.This study utilizes geospatial analysis and geographical detectors to examine the temporal dynamics of land use patterns and their underlying drivers in the Hedong Region of the Gansu Province from 1990 to 2020.Results indicated that grassland,cropland,and forestland collectively accounted for approximately 99% of the total land area.Cropland initially increased and then decreased after 2000,while grassland decreased with fluctuations.In contrast,forestland and construction land were continuously expanded,with net growth areas of 6235.2 and 455.9 km^(2),respectively.From 1990 to 2020,cropland was converted to grassland,and both of them were converted to forestland as a whole.The expansion of construction land primarily originated from cropland.From 2000 to 2005,land use experienced intensified temporal dynamics and a shift of relatively active zones from the central to the southeastern region.Grain yield,economic factors,and precipitation were the major factors accounting for most land use changes.Climatic impacts on land use changes were stronger before 1995,succeeded by the impact of animal husbandry during 1995-2000,followed by the impacts of grain production and gross domestic product(GDP)after 2000.Moreover,agricultural and pastoral activities,coupled with climate change,exhibited stronger enhancement effects after 2000 through their interaction with population and economic factors.These patterns closely correlated with ecological restoration projects in China since 1999.This study implies the importance of synergy between human activity and climate change for optimizing land use via ecological patterns in the ecological function area.

Uncertainties of ENSO-related Regional Hadley Circulation Anomalies within Eight Reanalysis Datasets

El Nino-Southern Oscillation(ENSO),the leading mode of global interannual variability,usually intensifies the Hadley Circulation(HC),and meanwhile constrains its meridional extension,leading to an equatorward movement of the jet system.Previous studies have investigated the response of HC to ENSO events using different reanalysis datasets and evaluated their capability in capturing the main features of ENSO-associated HC anomalies.However,these studies mainly focused on the global HC,represented by a zonal-mean mass stream function(MSF).Comparatively fewer studies have evaluated HC responses from a regional perspective,partly due to the prerequisite of the Stokes MSF,which prevents us from integrating a regional HC.In this study,we adopt a recently developed technique to construct the three-dimensional structure of HC and evaluate the capability of eight state-of-the-art reanalyses in reproducing the regional HC response to ENSO events.Results show that all eight reanalyses reproduce the spatial structure of HC responses well,with an intensified HC around the central-eastern Pacific but weakened circulations around the Indo-Pacific warm pool and tropical Atlantic.The spatial correlation coefficient of the three-dimensional HC anomalies among the different datasets is always larger than 0.93.However,these datasets may not capture the amplitudes of the HC responses well.This uncertainty is especially large for ENSO-associated equatorially asymmetric HC anomalies,with the maximum amplitude in Climate Forecast System Reanalysis(CFSR)being about 2.7 times the minimum value in the Twentieth Century Reanalysis(20CR).One should be careful when using reanalysis data to evaluate the intensity of ENSO-associated HC anomalies.

Artificial ground freezing of underground mines in cold regions using thermosyphons with air insulation

Current practice of underground artificial ground freezing(AGF)typically involves huge refrigeration systems of large economic and environmental costs.In this study,a novel AGF technique is proposed deploying available cold wind in cold regions.This is achieved by a static heat transfer device called thermosyphon equipped with an air insulation layer.A refrigeration unit can be optionally integrated to meet additional cooling requirements.The introduction of air insulation isolates the thermosyphon from ground zones where freezing is not needed,resulting in:(1)steering the cooling resources(cold wind or refrigeration)towards zones of interest;and(2)minimizing refrigeration load.This design is demonstrated using well-validated mathematical models from our previous work based on two-phase enthalpy method of the ground coupled with a thermal resistance network for the thermosyphon.Two Canadian mines are considered:the Cigar Lake Mine and the Giant Mine.The results show that our proposed design can speed the freezing time by 30%at the Giant Mine and by two months at the Cigar Lake Mine.Further,a cooling load of 2.4 GWh can be saved at the Cigar Lake Mine.Overall,this study provides mining practitioners with sustainable solutions of underground AGF.

Seasonal Characteristics of Forecasting Uncertainties in Surface PM_(2.5)Concentration Associated with Forecast Lead Time over the Beijing-Tianjin-Hebei Region

Forecasting uncertainties among meteorological fields have long been recognized as the main limitation on the accuracy and predictability of air quality forecasts.However,the particular impact of meteorological forecasting uncertainties on air quality forecasts specific to different seasons is still not well known.In this study,a series of forecasts with different forecast lead times for January,April,July,and October of 2018 are conducted over the Beijing-Tianjin-Hebei(BTH)region and the impacts of meteorological forecasting uncertainties on surface PM_(2.5)concentration forecasts with each lead time are investigated.With increased lead time,the forecasted PM_(2.5)concentrations significantly change and demonstrate obvious seasonal variations.In general,the forecasting uncertainties in monthly mean surface PM_(2.5)concentrations in the BTH region due to lead time are the largest(80%)in spring,followed by autumn(~50%),summer(~40%),and winter(20%).In winter,the forecasting uncertainties in total surface PM_(2.5)mass due to lead time are mainly due to the uncertainties in PBL heights and hence the PBL mixing of anthropogenic primary particles.In spring,the forecasting uncertainties are mainly from the impacts of lead time on lower-tropospheric northwesterly winds,thereby further enhancing the condensation production of anthropogenic secondary particles by the long-range transport of natural dust.In summer,the forecasting uncertainties result mainly from the decrease in dry and wet deposition rates,which are associated with the reduction of near-surface wind speed and precipitation rate.In autumn,the forecasting uncertainties arise mainly from the change in the transport of remote natural dust and anthropogenic particles,which is associated with changes in the large-scale circulation.

Energy conversion due to non-ideal electric field in separatrix region of magnetotail reconnection

A recent satellite observation has revealed the presence of energy conversion in the separatrix region(SR)of magnetotail reconnection,driven by perpendicular components.We investigated this phenomenon by means of particle-in-cell simulations in two-dimensional(2D)and three-dimensional(3D)systems.Our result indicates that in the 2D simulation,energy conversion in the SR is dominated by parallel components,with the main influencing factor being the parallel electric field,which is not consistent with the observation.However,a case that is similar to the observation is found in the 3D simulation,suggesting that the observation result may be attributed to the 3D characteristics.Our findings provide a potential explanation for the satellite observation.

Regional economic assessment of a novel place-based model for sustainable food systems

Several actions from both the environmental and human viewpoints have already been made to meet the sustainability goals targeted at food systems.Still,new place-based ideas to improve sustainability are needed.Agroecological symbiosis(AES),a novel food system model,is an example of a suggested system-level change to attain sustainability targets;it is a symbiosis of food production and processing using renewable energy that uses its own feedstock.AES has already been found advantageous from the ecological and biophysical viewpoints,but a regional economic evaluation of the model is still lacking.Thus,the aim of our paper is to assess the regional economic impact of a possible systemic change in the food system using the network of agroecological symbiosis(NAES)as an example.We applied scenarios representing different ways of moving towards envisioned NAES models in Mäntsälä,Finland,and a computable general equilibrium model to evaluate the regional economic impact.According to our results,both regional economy and employment would increase,and the regional production base would diversify with NAES implementation applied to the region,but the extent of the benefits varies between scenarios.The scenario that includes change in both public and private food demand,production of bioenergy and utilization of by-products would cause the largest impacts.However,realizing NAES requires investments that may influence the actual implementation of such models.Nonetheless,a change towards NAES can promote an economically and spatially just transition to sustainability,as NAES seems to be economically most beneficial for rural areas.

Suitable region of dynamic optimal interpolation for efficiently altimetry sea surface height mapping

The dynamic optimal interpolation(DOI)method is a technique based on quasi-geostrophic dynamics for merging multi-satellite altimeter along-track observations to generate gridded absolute dynamic topography(ADT).Compared with the linear optimal interpolation(LOI)method,the DOI method can improve the accuracy of gridded ADT locally but with low computational efficiency.Consequently,considering both computational efficiency and accuracy,the DOI method is more suitable to be used only for regional applications.In this study,we propose to evaluate the suitable region for applying the DOI method based on the correlation between the absolute value of the Jacobian operator of the geostrophic stream function and the improvement achieved by the DOI method.After verifying the LOI and DOI methods,the suitable region was investigated in three typical areas:the Gulf Stream(25°N-50°N,55°W-80°W),the Japanese Kuroshio(25°N-45°N,135°E-155°E),and the South China Sea(5°N-25°N,100°E-125°E).We propose to use the DOI method only in regions outside the equatorial region and where the absolute value of the Jacobian operator of the geostrophic stream function is higher than1×10^(-11).

A Dual-Task Learning Approach for Bearing Anomaly Detection and State Evaluation of Safe Region

Predictive maintenance has emerged as an effective tool for curbing maintenance costs,yet prevailing research predominantly concentrates on the abnormal phases.Within the ostensibly stable healthy phase,the reliance on anomaly detection to preempt equipment malfunctions faces the challenge of sudden anomaly discernment.To address this challenge,this paper proposes a dual-task learning approach for bearing anomaly detection and state evaluation of safe regions.The proposed method transforms the execution of the two tasks into an optimization issue of the hypersphere center.By leveraging the monotonicity and distinguishability pertinent to the tasks as the foundation for optimization,it reconstructs the SVDD model to ensure equilibrium in the model’s performance across the two tasks.Subsequent experiments verify the proposed method’s effectiveness,which is interpreted from the perspectives of parameter adjustment and enveloping trade-offs.In the meantime,experimental results also show two deficiencies in anomaly detection accuracy and state evaluation metrics.Their theoretical analysis inspires us to focus on feature extraction and data collection to achieve improvements.The proposed method lays the foundation for realizing predictive maintenance in a healthy stage by improving condition awareness in safe regions.

Effectiveness of hybrid ensemble machine learning models for landslide susceptibility analysis:Evidence from Shimla district of North-west Indian Himalayan region

The Indian Himalayan region is frequently experiencing climate change-induced landslides.Thus,landslide susceptibility assessment assumes greater significance for lessening the impact of a landslide hazard.This paper makes an attempt to assess landslide susceptibility in Shimla district of the northwest Indian Himalayan region.It examined the effectiveness of random forest(RF),multilayer perceptron(MLP),sequential minimal optimization regression(SMOreg)and bagging ensemble(B-RF,BSMOreg,B-MLP)models.A landslide inventory map comprising 1052 locations of past landslide occurrences was classified into training(70%)and testing(30%)datasets.The site-specific influencing factors were selected by employing a multicollinearity test.The relationship between past landslide occurrences and influencing factors was established using the frequency ratio method.The effectiveness of machine learning models was verified through performance assessors.The landslide susceptibility maps were validated by the area under the receiver operating characteristic curves(ROC-AUC),accuracy,precision,recall and F1-score.The key performance metrics and map validation demonstrated that the BRF model(correlation coefficient:0.988,mean absolute error:0.010,root mean square error:0.058,relative absolute error:2.964,ROC-AUC:0.947,accuracy:0.778,precision:0.819,recall:0.917 and F-1 score:0.865)outperformed the single classifiers and other bagging ensemble models for landslide susceptibility.The results show that the largest area was found under the very high susceptibility zone(33.87%),followed by the low(27.30%),high(20.68%)and moderate(18.16%)susceptibility zones.The factors,namely average annual rainfall,slope,lithology,soil texture and earthquake magnitude have been identified as the influencing factors for very high landslide susceptibility.Soil texture,lineament density and elevation have been attributed to high and moderate susceptibility.Thus,the study calls for devising suitable landslide mitigation measures in the study area.Structural measures,an immediate response system,community participation and coordination among stakeholders may help lessen the detrimental impact of landslides.The findings from this study could aid decision-makers in mitigating future catastrophes and devising suitable strategies in other geographical regions with similar geological characteristics.