Physics Guided Deep Learning-Based Model for Short-Term Origin–Destination Demand Prediction in Urban Rail Transit Systems Under Pandemic

Accurate origin–destination(OD)demand prediction is crucial for the efficient operation and management of urban rail transit(URT)systems,particularly during a pandemic.However,this task faces several limitations,including real-time availability,sparsity,and high-dimensionality issues,and the impact of the pandemic.Consequently,this study proposes a unified framework called the physics-guided adaptive graph spatial–temporal attention network(PAG-STAN)for metro OD demand prediction under pandemic conditions.Specifically,PAG-STAN introduces a real-time OD estimation module to estimate real-time complete OD demand matrices.Subsequently,a novel dynamic OD demand matrix compression module is proposed to generate dense real-time OD demand matrices.Thereafter,PAG-STAN leverages various heterogeneous data to learn the evolutionary trend of future OD ridership during the pandemic.Finally,a masked physics-guided loss function(MPG-loss function)incorporates the physical quantity information between the OD demand and inbound flow into the loss function to enhance model interpretability.PAG-STAN demonstrated favorable performance on two real-world metro OD demand datasets under the pandemic and conventional scenarios,highlighting its robustness and sensitivity for metro OD demand prediction.A series of ablation studies were conducted to verify the indispensability of each module in PAG-STAN.

RESEARCH ON MUNICIPAL WATER DEMANDS FORECAST

Based on the changing law of municipal water demand,a trigonometric function model for short-term water demand forecast is established using the time-series analysis approach.The method for forecasting water demand during holidays and under unexpected events is also presented.Meanwhile,a computer software is developed.Through actual application,this method performs well and has high accuracy,so it can be applied to the daily operation of a water distribution system and lay a foundation for on-line optimal operation.

以患者需求为导向的临床护理路径在卒中后偏瘫患者中的应用效果

目的:观察以患者需求为导向的临床护理路径在卒中后偏瘫患者中的应用效果。方法:选取2020年1月至2022年3月该院收治的75例卒中后偏瘫患者进行前瞻性研究,按随机数字表法将其分为对照组37例与观察组38例。对照组采用常规护理,观察组采用以患者需求为导向的临床护理路径。比较两组护理前后肢体运动能力[Fugl-Meyer运动功能评估量表(FMA)]评分、日常生活能力[Barthel指数(BI)]评分、焦虑情绪[焦虑自评量表(SAS)]评分、神经功能缺损程度[美国国立卫生研究院卒中量表(NIHSS)]评分,以及护理满意度[纽卡斯尔护理服务满意度量表(NSNS)]评分。结果:护理后,两组FMA、BI评分均高于护理前,且观察组高于对照组,差异有统计学意义(P<0.05);两组SAS评分均低于护理前,且观察组低于对照组,差异有统计学意义(P<0.05);两组NHISS评分均低于护理前,且观察组低于对照组,差异有统计学意义(P<0.05);观察组NSNS评分高于对照组,差异有统计学意义(P<0.05)。结论:以患者需求为导向的临床护理路径可提高卒中后偏瘫患者肢体运动功能、日常生活能力和护理满意度评分,以及降低焦虑情绪和神经缺损程度评分的效果优于常规护理。

Spatial Characteristics and Influencing Factors of Urban Resilience from the Perspective of Daily Activity:A Case Study of Nanjing,China

Based on the connotation of urban resilience and the main contradictions of China's urbanization,urban resilience is placed within the main daily activities contradictory scene of the urban man-land system to build a theoretical framework of urban activity resilience.Relying on geographic big data,this study identifies the spatial characteristics of activity resilience,reveals the impact of activity environment on activity resilience in Nanjing,and proposes countermeasures.The main conclusions are as follows.1)Activity resilience presents a composite spatial structure of circles and clusters,and most areas are resilient but at a low level.2)There are significantly positive and negative global autocorrelation between activity resilience and activity scale,and activity stability.Simultaneously,there also exists a local spatial autocorrelation with the opposite positive and negative trends.3)Activity environment has a significant effect on activity resilience,and the degree and direction of influence among different dimensions and regions are heterogeneous.4)For activity resilience,it is necessary to increase the matching degree between the scale and stability of activities,and reduce the excessive concentration and flow of activities.For the activity environment,it is necessary to improve the accessibility of the ecological environment,strengthen the high-quality supply of the infrastructure environment,optimize the balance of the location environment,and promote the inclusiveness of the social environment.

Short-term intravenous interferon therapy for chronic hepatitis B

AIM:To investigate the therapeutic efficacy of short- term, multiple daily dosing of intravenous interferon (IFN) in patients with hepatitis B e antigen (HBeAg)-positive chronic hepatitis B. METHODS:IFN-β was intravenously administered at a total dose of 102 million international units (MIU) over a period of 28 d in 26 patients positive for HBeAg and HBV-DNA. IFN-beta was administered at doses of 2 MIU and 1 MIU on d 1, 3 MIU twice daily from d 2 to d 7, and 1 MIU thrice daily from d 8 to d 28. Patients were followed up for 24 wk after the end of treatment. RESULTS:Six months after the end of the treatment, loss of HBV-DNA occurred in 13 (50.0%) of the 26 patients, loss of HBeAg in 9 (34.6%), development of anti-HBe in 10 (38.5%), HBeAg seroconversion in 8 (30.8%), and normalization of alanine aminotransferase (ALT) levels in 11 (42.0%). CONCLUSION:This 4-wk long IFN-β therapy, which was much shorter than conventional therapy lasting 12 wk or even more than 1 year, produced therapeutic effects similar to those achieved by IFN-α or pegylated- IFN-α (peg-IFN). Fewer adverse effects, greater efficacy, and a shorter treatment period led to an improvement in patients’ quality of life. IFN-β is administered intravenously, whereas IFN-α is administered intramuscularly or subcutaneously. Because both interferons are known to bind to an identical receptor and exert antiviral effects through intracellular signal transduction, the excellent results of IFN-β found in this study may be attributed to the multiple doses allowed by the intravenous route.

Estimating daily actual evapotranspiration of a rice–wheat rotation system in typical farmland in the Huai River Basin using a two-step model and two one-step models

The objective of this study is to evaluate the performance of three models for estimating daily evapotranspiration(ET) by employing flux observation data from three years(2007, 2008 and 2009) during the growing seasons of winter wheat and rice crops cultivated in a farmland ecosystem(Shouxian County) located in the Huai River Basin(HRB), China. The first model is a two-step model(PM-Kc);the other two are one-step models(e.g., Rana-Katerji(R-K) and advection-aridity(AA)). The results showed that the energy closure degrees of eddy covariance(EC) data during winter wheat and rice-growing seasons were reasonable in the HRB, with values ranging from 0.84 to 0.91 and R2 of approximately 0.80. Daily ET of winter wheat showed a slow decreasing trend followed by a rapid increase, while that of rice presented a decreasing trend after an increase. After calibrating the crop coefficient(Kc), the PM–Kc model performed better than the model using the Kc recommended by the Food and Agricultural Organization(FAO). The calibrated key parameters of the R-K model and AA model showed better universality. After calibration, the simulation performance of the PM-Kc model was satisfactory. Both the R-K model and AA model underestimated the daily ET of winter wheat and rice. Compared with that of the R-K model, the simulation result of the AA model was better, especially in the simulation of daily ET of rice. Overall, this research highlighted the consistency of the PM-Kc model to estimate the water demand for rice and wheat crops in the HRB and in similar climatic regions in the world.

Tail Quantile Estimation of Heteroskedastic Intraday Increases in Peak Electricity Demand

Modelling of intraday increases in peak electricity demand using an autoregressive moving average-exponential generalized autoregressive conditional heteroskedastic-generalized single Pareto (ARMA-EGARCH-GSP) approach is discussed in this paper. The developed model is then used for extreme tail quantile estimation using daily peak electricity demand data from South Africa for the period, years 2000 to 2011. The advantage of this modelling approach lies in its ability to capture conditional heteroskedasticity in the data through the EGARCH framework, while at the same time estimating the extreme tail quantiles through the GSP modelling framework. Empirical results show that the ARMA-EGARCH-GSP model produces more accurate estimates of extreme tails than a pure ARMA-EGARCH model.

大都市数字化日常消费的时空特征——以杭州市外卖O2O消费为例

移动互联网的普及催生了以外卖O2O消费为代表的数字化消费模式,日常消费供给与需求的时空格局正在发生变革。以杭州市主城区外卖O2O消费为研究对象,基于高精度的消费数据,运用数理统计、核密度空间分析以及可视化方法,刻画大都市数字化日常消费单日内高峰时段的时空特征,并对供给与需求的时空特征进行关联性分析。研究发现,①大都市数字化日常消费存在午、晚两个高峰,午高峰的规模更大、瞬时变化率更高。②需求空间在数字化日常消费高峰时期呈现显著的集聚态势,午高峰的空间集聚度较晚高峰高,且空间范围更小、边界更清晰;需求空间用地类型由单一的生产性服务用地转为居住、生产和文教等多元用地。③供给空间高密集聚形成多中心格局,供给空间分布与传统商业空间格局总体一致,局部存在差异——关键供给中心多数与社区级商圈重叠,少量位于非商业空间。④数字化日常消费形成午晚高峰错位和供需高峰错位两个特征:客观环境的时空约束影响潜在消费者决策,导致午晚高峰错位;数字时代店铺仍旧受集聚效应支配形成多中心格局,骑行配送拓宽供给中心的服务半径,扩大消费与供给的地理不邻近,从而形成供需高峰错位。

农村公共文化服务供给失配及其“适老化”路径——基于老龄人口日常生活方式的研究

让农村老年人享受高质量的公共文化生活,是新时代积极应对农村老龄化的基本要求。以农村老龄人口日常生活方式为依据,精准识别农村老龄公共文化服务需求侧结构,有利于推动其迈向“适老化”发展新阶段。农村低龄、高龄与失能老龄人因养老模式不同,其生活方式呈现各不相同的特点,进而共同塑造了农村多元老龄公共文化服务需求侧结构。但是,农村公共文化服务供给侧由于供给分配不平衡、供给使用率相对较低、供给形式主义滋生、供给主体能力不足等原因,使农村老龄公共文化服务供需失配较为突出。推动农村公共文化服务“适老化”发展,亟须强化农村老龄公共文化服务需求导向原则,建立农村老龄公共文化服务需求反馈机制,激活村庄新乡贤老龄公共文化服务购买功能,提高购买市场性老龄公共文化服务供给灵活性,增加村财老龄公共文化服务投入力度。

Comparative study of univariate and multivariate strategy for short-term forecasting of heat demand density:Exploring single and hybrid deep learning models

Accurate short-term forecasting of heating energy demand is needed for achieving optimal building energy management,cost savings,environmental sustainability,and responsible energy consumption.Furthermore,short-term heating energy prediction contributes to zero-energy building performance in cold climates.Given the critical importance of short-term forecasting in heating energy management,this study evaluated six prevalent deep-learning algorithms to predict energy load,including single and hybrid models.The overall best-performing predictors were hybrid models using Convolutional Neural Networks,regardless of whether they were multivariate or univariate.Nevertheless,while the multivariate models performed better in the first hour,the univariate models often were more accurate in the final 24 h.Thus,the best-performing predictor of the first timestep was a multivariate hybrid Convolutional Neural Network–Recurrent Neural Network model with a coefficient of determination(R^(2))of 0.98 and the lowest mean absolute error.Yet,the best-performing predictor of the final timestep was the univariate hybrid model Convolutional Neural Network–Long Short-Term Memory with an R^(2)of 0.80.Also,the prediction accuracy of the best-performing multivariate hybrid models reduced faster per hour compared to the univariate models.These findings suggest that multivariate models may be better suited for early timestep predictions,while univariate models may be better suited for later time steps.Hence,combining the models can enhance accuracy at various timesteps for achieving high fidelity in forecasting and offering a comprehensive tool for energy management.

基于GA-ACO-BP神经网络的日用消费品物流需求预测

针对日用消费品的物流需求,从宏观经济发展水平、相关产业水平、消费能力、物流供应能力、互联网发展水平、贸易水平6个方面,采用灰色关联度分析法对影响因素的灰色关联度进行计算及排序,构建预测指标体系。考虑物流相关数据样本较少,其影响因素之间存在非线性,结合遗传算法的全局寻优能力和蚁群算法的并行计算能力,构建了基于遗传算法-蚁群优化-反向传播神经网络(genetic algorithm-ant colony optimization-back propagation neural network,GA-ACO-BP)的日用消费品物流需求预测模型。分别采用GA-ACO-BP模型、GA-BP模型和BP模型对全国日用消费品物流需求进行预测,结果表明,GA-ACO-BP模型更能拟合日用消费品物流需求变化,预测精度较高,为物流需求预测研究提供一种模型参考,具有一定的实用价值。

城市居民日常活动与环境供需匹配特征及影响关系研究

城市居民日常活动与环境供需关系与城市生活品质息息相关。在新旧供需矛盾交织叠加,城市治理新理念、技术迅速发展的背景下,其匹配特征及影响关系需要并可以进一步理清。借鉴时空间行为及流空间理论搭建日常活动与环境供需理论框架及指标体系,并依托地理大数据支撑,基于ANP-CV主客观赋权法、随机森林非线性回归模型等技术手段,以南京市中心城区为例进行实证分析。研究发现,日常活动与环境供需匹配关系呈现以“中心—外围”为主,“圈层递变”为辅的复合型空间结构,极化特征较显著。日常活动与环境供需相互影响作用表现为不对称、不持续的非线性特征。具体地,日常活动更受活动环境塑造,又以支撑生计和多元包容的社会环境起主要作用,同时供需之间往往不具有持续的相互促进作用。因此,应促进日常活动与环境供需双向良性互动,提高供需网络要素集聚与扩散效益,根据日常活动与环境供需演进的阶段性,灵活选择多样路径,以促进供需关系的高质量可持续发展。

基于SVR-ARMA组合模型的日旅游需求预测

短期微观旅游需求具有强非线性特征,单一的模型很难做出准确预测。针对此问题,本文分析了著名风景区黄山2010年旅游旺季(4-10月)相关日数据的特征,在此基础上建立SVR-ARMA组合模型,用SVR模型先对原始非线性数据预测,再对SVR模型预测所产生的线性残差用ARMA模型预测,将两部分预测值几何相加得最终的预测值。最后分别与单一的SVR和ARMA模型对比,结果表明该组合模型有更高更稳健的预测精度,很适合短期微观旅游需求。

杭州公共设施调研与分析——基于日常生活服务需求的视角

面对新形势下基本公共服务设施配置的新要求,杭州市开展了公共服务设施基本配套规定的评估与修订。有别于传统的"自上而下"制定各类设施配套标准的思路,此次评估与修订工作采用基于日常生活服务需求视角的"自下而上"的创新型思路,问卷与访谈相结合并将调研设施从公益性设施拓展到商业性设施,了解居民使用设施的频率、步行容忍时间等特征及对设施集中设置的意愿,以此为依据,对杭州市公共设施基本配套规定中设施类型的确定、设施功能的复合设置、服务半径的选取等方面提出建议。

农村老年人日常生活照料需求及影响因素研究

目的:了解农村地区老年人日常生活照料需求现况,分析其影响因素。方法:分层随机抽取威海市文登区农村老年人300人进行问卷调查,通过日常生活照料方式评估老年人的照料需求。结果:日常生活为自己照料者占87.7%,需要家庭照料者为12.0%;单因素分析显示,不同年龄、经济收入、ADL、IADL与抑郁状况的老年人日常生活照料需求存在显著性差异(P<0.05);多因素logistic回归分析显示,性别、经济收入、日常生活自理能力与抑郁是老年人日常生活照料需求的主要影响因素(P<0.05)。结论:自我照料和家庭照料仍是农村老年人日常生活照料的主要资源,且大部分老年人选择自我照料。日常生活自理能力缺陷与抑郁的高龄男性贫困老年人对家庭照料的需求更大。

基于时间序列模型ARMA的水厂逐日需水量过程预测方法

水厂逐日需水量预测作为城市供水优化调度的基础,满足水厂需水量是供水系统调度的基本目标,因此准确预测需水量过程是进行供水系统优化调度的前提条件。通过分析深圳市主要水厂日需水量的变化规律,提取影响水厂逐日需水量关键因素,以时间序列模型ARMA(1,1)为基础,嵌入自适应机制进行滚动预测,提出水厂逐日需水量过程预测方法。实例应用表明ARMA模型能够适用于深圳市水厂逐日需水量预测,预测平均相对误差小于10%,预测值与实测值分布规律基本一致,预测精度较高。

武汉市周年逐日电力指标对气温的非线性响应

为了建立电力因子与气象要素的关系,利用2005—2007年武汉市电网日电量、日最大负荷、日最小负荷及相应的气温资料,分析气温对各电力指标的影响,建立了各电力指标与气温的非线性统计模型,并与线性模型进行比较。结果表明,非线性模型比线性模型能更好地反映电力指标与气温的关系,日最大负荷、日电量、日最小负荷最不敏感的平均温度临界点分别是15～16℃、14～15℃、13～14℃,低于该温度时气温下降或高于该温度时气温上升,电力指标均呈非线性增加,与最不敏感的平均气温偏离越大,电力指标增加越快。

利用特高压输电技术提高全球能源使用效率

为探讨基于时差实现全球范围内电力负荷削峰填谷的可行性,研究了位于北纬45°附近不同时区的中国济南、欧洲法国、北美加利福尼亚3个区域电网的日负荷需求数据;基于不同时区区域电网的用电负荷特性,计算了通过特高压输电技术实现北美、欧洲、中国三大区域电网互联的可行性和基于区域时差实现削峰填谷的经济效益。研究结果表明:时差导致了人类自然生产和生活规律的差异,不同时区电力负荷需求的波动具有很强的互补性,利用这种互补性实现全球范围内电力负荷的削峰填谷是可行的;利用特高压输电技术实现不同区域电网互联的综合经济效益优于建设抽水蓄能电站。

“增益”还是“损耗”?挑战性工作要求对工作-家庭增益的“双刃剑”影响

基于资源保存理论和不确定管理理论,采用日记研究法收集81个样本10个工作日的数据,从静态和动态两个视角,通过明晰挑战性工作要求的不同属性(每日水平、平均水平、日间变动、波动变化),全面检验了挑战性工作要求对工作-家庭增益的影响。研究结果表明:(1)在静态模型中,挑战性工作要求通过工作专注度(增益路径)和放松(损耗路径)作用于工作-家庭增益,且在个体间的平均水平模型中,放松的中介作用更为显著;(2)在动态模型中,挑战性工作要求的日间变动和波动变化,均通过减少员工工作专注度和放松,进而降低工作-家庭增益。最后,本研究讨论了管理者应重视挑战性工作要求的双刃剑作用等实践启示。

基于气温的城市燃气短期日负荷预测模型——以四川省成都地区为例

随着城市燃气用气规模的不断增长,加上近年来冬季长期低温、气温骤降等极端天气屡屡出现,因气温变化导致的日用气峰谷差有扩大的趋势,采用中长期数据进行趋势预测可能存在较大误差。而利用短期的气温、用气负荷数据,结合较为准确的一周内气象预报对未来几天内的城市燃气日负荷进行预测,对上游供气企业、城市燃气公司合理安排销售计划和日调峰等具有重要的现实意义。为此,通过分析气温对城市燃气短期日负荷的影响机理,利用统计学和化学动力学理论,基于阿累尼乌斯方程反应的温度—化学反应速率关系,考虑气温突变、低温累积等因素构建了气温对城市燃气短期日负荷的预测模型,并利用成都地区短期的气温、用气负荷数据,测算了模型参数并对模型进行了验证(最大误差为2.53%)。结果表明,该模型的预测精度较高,可为燃气公司或上游供气企业合理安排销售计划和日调峰等提供决策支撑。