基于CEEMDAN-VMD-TCN-lightGBM模型的水质预测研究

针对目前水质预测模型中因为数据本身的复杂性、在信号处理过程中存在的噪声干扰以及分解深度不够导致单一分解难以全面捕捉信号非线性特征的问题,提出了一种基于二次分解的水质预测模型。该模型采用完全自适应噪声集合经验模态分解(CEEMDAN)对原始数据进行分解,再利用变分模态分解(VMD)对熵值最高的模态分量进行二次分解,最终将处理后的时间序列输入到TCN-lightGBM多特征预测模型中。同时,采用麻雀算法(SSA)对预测模型进行优化。以山东省玉符河水质为例,本模型的均方根误差(RMSE)是0.1053,平均绝对误差(MAE)是0.0815,决定系数(R2)是0.9471,与GRU、LSTM、LightGBM、TCN等当下较为流行的模型的预测指标进行比较。结果显示,在R2上本模型提升了53.04%、70.41%、66.07%、65.20%等,在RMSE上减少了62.76%、65.50%、64.93%、64.80%等,在MAE上降低了62.76%、66.24%、63.80%、65.24%等。由此可知,基于CEEMDAN-VMD-TCN-lightGBM的模型具有更好的预测性能、泛化能力和捕捉信号非线性特征的能力。

Effects of thinning on the understory light environment of different stands and the photosynthetic performance and growth of the reforestation species Phoebe bournei

Light levels determine regeneration in stands and a key concern is how to regulate the light environment of different stand types to the requirements of the understory.In this study,we selected three stands typical in south China(a Cryptomeria japonica plantation,a Quercus acutissima plantation,and a mixed stand of both)and three thinning intensities to determine the best understory light environ-ment for 3-year-old Phoebe bournei seedlings.The canopy structure,understory light environment,and photosynthe-sis and growth indicators were assessed following thin-ning.Thinning improved canopy structure and understory light availability of each stand;species composition was the reason for differences in the understory light environ-ment.Under the same thinning intensity,the mixed stand had the greatest light radiation and most balanced spectral composition.P.bournei photosynthesis and growth were closely related to the light environment;all three stands required heavy thinning to create an effective and sustained understory light environment.In a suitable understory light environment,the efficiency of light interception,absorption,and use by seedlings was enhanced,resulting in a higher carbon assimilation the main limiting factor was stomatal conductance.As a shade-avoidance signal,red/far-red radia-tion is a critical factor driving changes in photosynthesis and growth of P.bournei seedlings,and a reduction increased light absorption and use capacity and height:diameter ratios.The growth advantage transformed from diameter to height,enabling seedlings to access more light.Our findings suggest that the regeneration of shade-tolerant species such as P.bournei could be enhanced if a targeted approach to thinning based on stand type was adopted.

基于LightGBM的智能可穿戴设备用户行为预测

智能可穿戴设备产生的大量数据是人类宝贵的数字资源。使用开放数据集和主流数据分析工具,如可进行快速模型开发的PyCaret模块,有助于人们进行数据挖掘工作,且不被细节所困扰。作为Kaggle竞赛爱好者的常用工具,LightGBM分类器对用户行为的预测表现优异,对此文中的研究结果也得到验证。

A Workable Solution for Reducing the Large Number of Vehicle and Pedestrian Accidents Occurring on a Yellow Light

Traffic intersections are incredibly dangerous for drivers and pedestrians. Statistics from both Canada and the U.S. show a high number of fatalities and serious injuries related to crashes at intersections. In Canada, during 2019, the National Collision Database shows that 28% of traffic fatalities and 42% of serious injuries occurred at intersections. Likewise, the U.S. National Highway Traffic Administration (NHTSA) found that about 40% of the estimated 5,811,000 accidents in the U.S. during the year studied were intersection-related crashes. In fact, a major survey by the car insurance industry found that nearly 85% of drivers could not identify the correct action to take when approaching a yellow traffic light at an intersection. One major reason for these accidents is the “yellow light dilemma,” the ambiguous situation where a driver should stop or proceed forward when unexpectedly faced with a yellow light. This situation is even further exacerbated by the tendency of aggressive drivers to inappropriately speed up on the yellow just to get through the traffic light. A survey of Canadian drivers conducted by the Traffic Injury Research Foundation found that 9% of drivers admitted to speeding up to get through a traffic light. Another reason for these accidents is the increased danger of making a left-hand turn on yellow. According to the National Highway Traffic Safety Association (NHTSA), left turns occur in approximately 22.2% of collisions—as opposed to just 1.2% for right turns. Moreover, a study by CNN found left turns are three times as likely to kill pedestrians than right turns. The reason left turns are so much more likely to cause an accident is because they take a driver against traffic and in the path of oncoming cars. Additionally, most of these left turns occur at the driver’s discretion—as opposed to the distressingly brief left-hand arrow at busy intersections. Drive Safe Now proposes a workable solution for reducing the number of accidents occurring during a yellow light at intersections. We believe this fairly simple solution will save lives, prevent injuries, reduce damage to public and private property, and decrease insurance costs.

Photoperiod Mediates the Effects of Temperature and Light Intensity on the Proliferation of Ulva prolifera

In order to study the complex effects of photoperiod,temperature,and light intensity on the spore maturation and release number of Ulva prolifera,we cultured thalli segment(2–3 mm)under three different photoperiods(L:D=12:12,14:10 and 10:14),temperature(15℃(LT),25℃(MT)and 30℃(HT))and light intensity(100,200 and 400μmol m^(−2)s^(−1),noted as LL,ML and HL,respectively)conditions.Then the maturation time,spore release number and chlorophyll fluorescence were analyzed.The results suggested that:1)The spore maturation time was accelerated by higher temperature or higher light intensity from 62 h to 36 h,and changes in day length accelerated the spore maturation to a certain extent as compared with 12:12 light/dark cycle;2)Higher light intensity significantly decreased the chlorophyll fluorescence(Fv′/Fm′,NPQ,rETRmax andα)of the mature reproductive segment under 30℃with 12:12 light/dark cycle.But when in the other photoperiods(10:14 and 14:10 conditions),the inhibitory effects of high light intensity were alleviated significantly;3)The optimum condition for the spore maturation and release was 12:12 light/dark cycle,25℃,400μmol m^(−2)s^(−1),with both shorter and longer photoperiod reducing the spore release number;4)Higher light intensity significantly increased the spore release number under 25℃,but these effects were alleviated by 30℃treatment.This study is the first attempt to elucidate the coincidence effects of photoperiod,temperature and light intensity on the reproduction of Ulva,which would help to reveal the mechanism of the rapid proliferation of green tide.

Effect of artificial natural light on the development of myopia among primary school-age children in China:a three-year longitudinal study

AIM:To assess the efficacy of artificial natural light in preventing incident myopia in primary school-age children.METHODS:This is a prospective,randomized control,intervention study.A total of 1840 students from 39 classes in 4 primary schools in Foshan participated in this study.The whole randomization method was adopted to include classes as a group according to 1:1 randomized control.Classrooms in the control group were illuminated by usual light,and classrooms in the intervention group were illuminated by artificial natural light.All students received uncorrected visual acuity and best-corrected visual acuity measurement,non-cycloplegic autorefraction,ocular biometric examination,slit lamp and strabismus examination.Three-year follow-up,the students underwent same procedures.Myopia was defined as spherical equivalent refraction≤-0.50 D and uncorrected visual acuity<20/20.RESULTS:There were 894 students in the control group and 946 students in the intervention group with a mean±SD age of 7.50±0.53y.The three-year cumulative incidence rate of myopia was 26.4%(207 incident cases among 784 eligible participants at baseline)in the control group and 21.2%(164 incident cases among 774 eligible participants at baseline)in the intervention group[difference of 5.2%(95%CI,3.7%to 10.1%);P=0.035].There was also a significant difference in the three-year change in spherical equivalent refraction for the control group(-0.81 D)compared with the intervention group[-0.63 D;difference of 0.18 D(95%CI,0.08 to 0.28 D);P<0.001].Elongation of axial length was significantly different between in the control group(0.77 mm)and the intervention group[0.72 mm;difference of 0.05 mm(95%CI,0.01 to 0.09 mm);P=0.003].CONCLUSION:Artificial natural light in the classroom of primary schools can result in reducing incidence rate of myopia during a period of three years.

Identifying drivers of urban landuse changes in the Wenchuan earthquake- affected area by using night-time light data

To learn the process of urban land evolution before and after an earthquake is vital to formulate the urban reconstruction control policies and recovery measures in the earthquake-stricken areas.However,spatiotemporal evolution and its driving factors of urban land in earthquake-prone areas remains limited due to the scarcity of ground observation data.This research,leveraging night-time light remote sensing imagery and land cover data,conducted a comprehensive analysis of the long-term evolution characteristics of urban land in earthquake-prone areas.It introduced methodologies for assessing the socio-economic impact and the primary natural environmental factors driving urban land evolution in these regions.To validate the proposed methods,the 2008 Wenchuan earthquake-affected area in China was selected as a representative study area.The results indicated that the average Digital Number(DN)values in socio-economically impacted areas showed a trend of rising,falling,and then rising again after the earthquake.DN values in three types of damaged areas including Type Ⅱ,Type Ⅲ,and Type Ⅳ exceeded pre-earthquake levels.The analysis of determinative factors influencing urban land evolution revealed that slope and elevation were key elements in controlling urban land expansion before the earthquake,whereas factors such as slope,elevation,lithology,and faults had a stronger influence on urban land expansion after the earthquake.It can be seen that,in view of the differences in the natural conditions of regions for post-disaster reconstruction,the local government need to actively adjust and adapt to urban spatial planning,so as to leverage the scale effect of large-scale inputs of funds,facilities,human resources and other factors after the disaster,thus enhancing resilience and recovery efficiency in response to disaster impacts.

Model prediction of inactivation of Aeromonas salmonicida grown on poultry in situ by intense pulsed light

The aim of this study was to evaluate the factors influencing the inactivation effect of intense pulsed light(IPL)on Aeromonas salmonicida grown on chicken meat and skin,and to further develop prediction models of inactivation.In this work,chicken meat and skin inoculated with meat-borne A.salmonicida isolates were subjected to IPL treatments under different conditions.The results showed that IPL had obvious bactericidal effect in the chicken skin and thickness groups when the treatment voltage and time were 7 V combined with 5 s.In addition,the lethality curves of A.salmonicida were fitted under IPL conditions of 3.5-7.5 V.The comparison of statistical parameters revealed that the Weibull model could best fit the mortality curves and could accurately predict the mortality dynamic of A.salmonicida grown on chicken skin.And further a secondary model between the scale factor b and the treatment voltage in Weibull model was established using linear equations,which determined that the secondary model could accurately predict the inactivation of A.salmonicida.This study provides a theoretical basis for future prediction models of Aeromonas,and also provides new ideas for sterilization approaches of meat-borne Aeromonas.

一种基于随机森林和Light GBM的房产估价模型

针对商品房评估方法中存在数据源单一,考虑影响因素理想化,特征工程过分依赖主观经验等问题,结合随机森林和Light GBM模型,提出了一种RF_LightGBM模型用于房产价值评估。首先,通过随机森林对特征进行重要度排序,将影响房产价格因素较小的特征排除,使用网格搜索算法对模型进行优化,最后将该方法用于房产价值评估。在真实的房价数据集上进行的实验表明,相较于随即森林,XGBoost等传统模型,RF_LightGBM模型的评估精度提高了1.7%,且百分误差在0%~10%以内的评估结果占比88.38%。说明所用模型可以很好地应用于房产价值评估,得到的评估结果更加准确。

Design and tailoring of patterned ZnO nanostructures for perovskite light absorption modulation

Lithography is a pivotal micro/nanomanufacturing technique,facilitating performance enhancements in an extensive array of devices,encompassing sensors,transistors,and photovoltaic devices.The key to creating highly precise,multiscale-distributed patterned structures is the precise control of the lithography process.Herein,high-quality patterned ZnO nanostructures are constructed by systematically tuning the exposure and development times during lithography.By optimizing these parameters,ZnO nanorod arrays with line/hole arrangements are successfully prepared.Patterned ZnO nanostructures with highly controllable morphology and structure possess discrete three-dimensional space structure,enlarged surface area,and improved light capture ability,which achieve highly efficient energy conversion in perovskite solar cells.The lithography process management for these patterned ZnO nanostructures provides important guidance for the design and construction of complex nanostructures and devices with excellent performance.

Regulation of different light conditions for efficient biomass production and protein accumulation of Spirulina platensis

Light plays an important role in the photosynthesis and metabolic process of microalgae.However,how different light conditions regulate the biomass production and protein accumulation of microalgae is mostly unknown.In this study,the influence of different light conditions,including light colors,densities,and light:dark cycles on the cell growth and biochemical composition of Spirulina platensis was symmetrically characterized.Under different colored lights,S.platensis all shows an increase trend within the increased light intensity ranges;however,each showing different optimal light intensities.At the same light intensity,different colored lights show different growth rate of S.platensis following the sequence of red>white>green>yellow>blue.The maximum growth rate and protein accumulation were determined as 21.88 and 5.10 mg/(L·d)when illuminated under red LED.The energy efficiency of different light sources was calculated and ranked as red>white>blue≈green>yellow.Transcriptomic analysis suggests that red light can promote cell growth and protein accumulation by upregulating genes related to photosynthesis,carbon fixation,and C-N metabolism pathways.This study provides a conducive and efficient way to promote biomass production and protein accumulation of S.platensis by regulating light conditions.

Robust Facial Biometric Authentication System Using Pupillary Light Reflex for Liveness Detection of Facial Images

Pupil dynamics are the important characteristics of face spoofing detection.The face recognition system is one of the most used biometrics for authenticating individual identity.The main threats to the facial recognition system are different types of presentation attacks like print attacks,3D mask attacks,replay attacks,etc.The proposed model uses pupil characteristics for liveness detection during the authentication process.The pupillary light reflex is an involuntary reaction controlling the pupil’s diameter at different light intensities.The proposed framework consists of two-phase methodologies.In the first phase,the pupil’s diameter is calculated by applying stimulus(light)in one eye of the subject and calculating the constriction of the pupil size on both eyes in different video frames.The above measurement is converted into feature space using Kohn and Clynes model-defined parameters.The Support Vector Machine is used to classify legitimate subjects when the diameter change is normal(or when the eye is alive)or illegitimate subjects when there is no change or abnormal oscillations of pupil behavior due to the presence of printed photograph,video,or 3D mask of the subject in front of the camera.In the second phase,we perform the facial recognition process.Scale-invariant feature transform(SIFT)is used to find the features from the facial images,with each feature having a size of a 128-dimensional vector.These features are scale,rotation,and orientation invariant and are used for recognizing facial images.The brute force matching algorithm is used for matching features of two different images.The threshold value we considered is 0.08 for good matches.To analyze the performance of the framework,we tested our model in two Face antispoofing datasets named Replay attack datasets and CASIA-SURF datasets,which were used because they contain the videos of the subjects in each sample having three modalities(RGB,IR,Depth).The CASIA-SURF datasets showed an 89.9%Equal Error Rate,while the Replay Attack datasets showed a 92.1%Equal Error Rate.

I-DCGAN and TOPSIS-IFP:A simulation generation model for radiographic flaw detection images in light alloy castings and an algorithm for quality evaluation of generated images

The intelligent detection technology driven by X-ray images and deep learning represents the forefront of advanced techniques and development trends in flaw detection and automated evaluation of light alloy castings.However,the efficacy of deep learning models hinges upon a substantial abundance of flaw samples.The existing research on X-ray image augmentation for flaw detection suffers from shortcomings such as poor diversity of flaw samples and low reliability of quality evaluation.To this end,a novel approach was put forward,which involves the creation of the Interpolation-Deep Convolutional Generative Adversarial Network(I-DCGAN)for flaw detection image generation and a comprehensive evaluation algorithm named TOPSIS-IFP.I-DCGAN enables the generation of high-resolution,diverse simulated images with multiple appearances,achieving an improvement in sample diversity and quality while maintaining a relatively lower computational complexity.TOPSIS-IFP facilitates multi-dimensional quality evaluation,including aspects such as diversity,authenticity,image distribution difference,and image distortion degree.The results indicate that the X-ray radiographic images of magnesium and aluminum alloy castings achieve optimal performance when trained up to the 800th and 600th epochs,respectively.The TOPSIS-IFP value reaches 78.7%and 73.8%similarity to the ideal solution,respectively.Compared to single index evaluation,the TOPSIS-IFP algorithm achieves higher-quality simulated images at the optimal training epoch.This approach successfully mitigates the issue of unreliable quality associated with single index evaluation.The image generation and comprehensive quality evaluation method developed in this paper provides a novel approach for image augmentation in flaw recognition,holding significant importance for enhancing the robustness of subsequent flaw recognition networks.

Hepatomegaly and jaundice as the presenting symptoms of systemic light-chain amyloidosis: A case report

BACKGROUND Light chain(AL)amyloidosis is a plasma cell dyscrasia characterized by the pathologic production and extracellular tissue deposition of fibrillar proteins derived from immunoglobulin AL fragments secreted by a clone of plasma cells,which leads to progressive dysfunction of the affected organs.The two most commonly affected organs are the heart and kidneys,and liver is rarely the dominant affected organ with only 3.9%of cases,making them prone to misdia-gnosis and missed diagnosis.CASE SUMMARY A 65-year-old woman was admitted with a 3-mo history of progressive jaundice and marked hepatomegaly.Initially,based on enhanced computed tomography scan and angiography,Budd-Chiari syndrome was considered and balloon dilatation of significant hepatic vein stenoses was performed.However,addi-tional diagnostic procedures,including liver biopsy and bone marrow-exami-nation,revealed immunoglobulin kapa AL amyloidosis with extensive liver involvement and hepatic vascular compression.The disease course was progre-ssive and fatal,and the patient eventually died 5 mo after initial presentation of symptoms.CONCLUSION AL amyloidosis with isolated liver involvement is very rare,and can be easily misdiagnosed as a vascular disease.

Machine Learning-based Identification of Contaminated Images in Light Curve Data Preprocessing

Attitude is one of the crucial parameters for space objects and plays a vital role in collision prediction and debris removal.Analyzing light curves to determine attitude is the most commonly used method.In photometric observations,outliers may exist in the obtained light curves due to various reasons.Therefore,preprocessing is required to remove these outliers to obtain high quality light curves.Through statistical analysis,the reasons leading to outliers can be categorized into two main types:first,the brightness of the object significantly increases due to the passage of a star nearby,referred to as“stellar contamination,”and second,the brightness markedly decreases due to cloudy cover,referred to as“cloudy contamination.”The traditional approach of manually inspecting images for contamination is time-consuming and labor-intensive.However,we propose the utilization of machine learning methods as a substitute.Convolutional Neural Networks and SVMs are employed to identify cases of stellar contamination and cloudy contamination,achieving F1 scores of 1.00 and 0.98 on a test set,respectively.We also explore other machine learning methods such as ResNet-18 and Light Gradient Boosting Machine,then conduct comparative analyses of the results.

A Novel Sensing Imaging Equipment Under Extremely Dim Light for Blast Furnace Burden Surface:Starlight High-Temperature Industrial Endoscope

Blast furnace(BF)burden surface contains the most abundant,intuitive and credible smelting information and acquiring high-definition and high-brightness optical images of which is essential to realize precise material charging control,optimize gas flow distribution and improve ironmaking efficiency.It has been challengeable to obtain high-quality optical burden surface images under high-temperature,high-dust,and extremelydim(less than 0.001 Lux)environment.Based on a novel endoscopic sensing detection idea,a reverse telephoto structure starlight imaging system with large field of view and large aperture is designed.Combined with a water-air dual cooling intelligent self-maintenance protection device and the imaging system,a starlight high-temperature industrial endoscope is developed to obtain clear optical burden surface images stably under the harsh environment.Based on an endoscope imaging area model,a material flow trajectory model and a gas-dust coupling distribution model,an optimal installation position and posture configuration method for the endoscope is proposed,which maximizes the effective imaging area and ensures large-area,safe and stable imaging of the device in a confined space.Industrial experiments and applications indicate that the proposed method obtains clear and reliable large-area optical burden surface images and reveals new BF conditions,providing key data support for green iron smelting.

Light-modulated graphene-based φ_(0) Josephson junction and -φ_(0) to φ_(0) transition

We investigate the chiral edge states-induced Josephson current–phase relation in a graphene-based Josephson junction modulated by the off-resonant circularly polarized light and the staggered sublattice potential.By solving the Bogoliubov–de Gennes equation,a φ_(0) Josephson junction is induced in the coaction of the off-resonant circularly polarized light and the staggered sublattice potential,which arises from the fact that the center of-mass wave vector of Cooper pair becomes finite and the opposite center of-mass wave vector to compensate is lacking in the nonsuperconducting region.Interestingly,when the direction of polarization of light is changed,-φ_(0) to φ_(0) transition generates,which generalizes the concept of traditional 0–πtransition.Our findings provide a purely optical way to manipulate a phase-controllable Josephson device and guidelines for future experiments to confirm the presence of graphene-based φ_(0)Josephson junction.

Artificial night light and thyroid cancer

BACKGROUND The occurrence of thyroid cancer(TC)has increased in recent decades.Exposure to outdoor artificial light at night(ALN)is associated with an increased risk of cancer.AIM To investigated the impact of ALN,as a significant environmental pollutant,on TC incidence worldwide.METHODS The assessment involved analyzing satellite ALN data in conjunction with TC incidence data[adjusted standardized rate(ASR)],while considering the quality of cancer registries(QCR),gross domestic product(GDP)per person,and health expenditure per person(HEP)for each country.RESULTS Results indicated a correlation between higher ASR and ALN exposure percentages,particularly in countries with higher GDP or HEP quartiles(all P<0.05).Significant differences in ASR were observed across QCR levels,both high and low quality(all P<0.05),but not in countries without registry activity.However,when evaluating ASR against ALN exposure percentages while considering GDP/HEP quartiles or QCR levels,no significant associations were found(all P>0.10).CONCLUSION The findings suggest a potential link between higher GDP and adverse health conditions,serving as possible risk factors for TC,rather than a direct association with ALN.Limitations include the use of cross-sectional data,temporal misalign ment,and reliance on ALN as a socioeconomic proxy.It is proposed that light pollution might be connected to a lifestyle conducive to carcinogenesis.Additionally,the presence of higher GDP/HEP could enhance access to diagnostic resources,potentially facilitating TC diagnosis and inclusion in cancer registries.

A Light and Simplified Branch Bending Method for Young Pear Trees

Aiming at high cost and low efficiency of conventional branch bending method in the modern intensive planting and labor-saving cultivation mode of young pear trees,this paper provides a new branch bending method with wide source of raw materials,cheap price and simple operation,which is also suitable for the management of low-age branches in the process of high grafting and upgrading of traditional big trees.

Electrically-driven ultrafast out-of-equilibrium light emission from hot electrons in suspended graphene/hBN heterostructures

Nanoscale light sources with high speed of electrical modulation and low energy consumption are key components for nanophotonics and optoelectronics.The record-high carrier mobility and ultrafast carrier dynamics of graphene make it promising as an atomically thin light emitter which can be further integrated into arbitrary platforms by van der Waals forces.However,due to the zero bandgap,graphene is difficult to emit light through the interband recombination of carriers like conventional semiconductors.Here,we demonstrate ultrafast thermal light emitters based on suspended graphene/hexagonal boron nitride(Gr/hBN)heterostructures.Electrons in biased graphene are significantly heated up to 2800 K at modest electric fields,emitting bright photons from the near-infrared to the visible spectral range.By eliminating the heat dissipation channel of the substrate,the radiation efficiency of the suspended Gr/hBN device is about two orders of magnitude greater than that of graphene devices supported on SiO2or hBN.Wefurther demonstrate that hot electrons and low-energy acoustic phonons in graphene are weakly coupled to each other and are not in full thermal equilibrium.Direct cooling ofhigh-temperature hot electrons to low-temperature acoustic phonons is enabled by the significant near-field heat transfer at the highly localized Gr/hBN interface,resulting in ultrafast thermal emission with up to 1 GHz bandwidth under electrical excitation.It is found thatsuspending the Gr/hBN heterostructures on the SiO2trenches significantly modifies the light emission due to the formation of the optical cavity and showed a~440%enhancement inintensity at the peak wavelength of 940 nm compared to the black-body thermal radiation.The demonstration of electrically driven ultrafast light emission from suspended Gr/hBNheterostructures sheds the light on applications of graphene heterostructures in photonicintegrated circuits,such as broadband light sources and ultrafast thermo-optic phase modulators.