通用网络流量监测报警系统的设计与实现

网络流量监测是网络管理的一项重要内容。通过流量测量与预测,可以了解自治域、网络之间的流量情况及其趋势,从而更好地进行网络改进和负载均衡的设计。本文使用指数平滑法建立流量预测模型,可对网络流量进行实时监测与预警。     

基于 A-LSTM 算法的烧结矿质量预测

针对烧结厂烧结杯实验周期长等问题,构建一种 A-LSTM 的烧结矿质量预测模型。在 LSTM 网络基础上借鉴注意力机制思想,通过权重再分配使网络更加关注训练过程中的非冗余数据。为减少损失函数在训练过程中的震荡,提出加权均方误差损失计算方式,考虑每轮输入数据缺失值占总体的比重,使模型预测更为准确。实验结果表明,A-LSTM 预测方法准确率可达 92.7%,相比于原始 LSTM,预测准确率提升了 1.9%。     

巢湖水质污染的社会经济因子分析及趋势研究

文章运用灰色关联分析法探讨了2000-2006年间影响巢湖水质的社会经济因子,并采用灰色预测模型对未来五年巢湖水质的污染状况进行了预测.以期为巢湖水污染治理提供新思路.结果表明巢湖COD的排放,主要受流域工业废水排放的影响,其次受农村人口的生活中产生的污水排放的影响;TN主要受农业生产中农药化肥的大量使用的影响;TP主要受城镇、农村人口的生活废水垃圾排泄物的影响.模型预测结果显示未来五年巢湖水质有望好转,但是湖区水质TN、TP指标仍介于Ⅳ～Ⅴ类之间.因此,今后巢湖水质的主要污染物是TN、TP,而农业和城镇、农村人口的生活废水排放将成为污染物的主要来源.有必要采取发展生态农业、控制含磷商品的使用、加强对农村生活污水尽可能的集中处理等措施有效控制巢湖的水质污染.     

我国高中教育发展规模的计量预测与分析

近年来,我国教育事业发展很快,但高中阶段教育发展较为滞后,这也阻碍了高等教育的进一步发展。因此,科学预测和规划未来高中阶段的教育发展规模显得特别重要。本主要采用计量方法对未来高中阶段的教育发展规模进行预测,并简要分析预测与规划结果的合理性。     

Examining rater accuracy and consistency with a special education observation protocol

Research indicates that instructional aspects of teacher performance are the most difficult to reach consensus on, significantly limiting teacher observation as a way to systematically improve instructional practice. Understanding the rationales that raters provide as they evaluate teacher performance with an observation protocol offers one way to better understand the training efforts required to improve rater accuracy. The purpose of this study was to examine the accuracy of raters evaluating special education teachers’ implementation of evidence-based math instruction. A mixed-methods approach was used to investigate: 1) the consistency of the raters’ application of the scoring criteria to evaluate teachers’ lessons, 2) raters’ accuracy on two lessons with those given by expert-raters, and 3) the raters’ understanding and application of the scoring criteria through a think-aloud process. The results show that raters had difficulty understanding some of the high inference items in the rubric and applying them accurately and consistently across the lessons. Implications for rater training are discussed.     

Explicit time embedding based cascade attention network for information popularity prediction

Predicting information cascade popularity is a fundamental problem in social networks. Capturing temporal attributes and cascade role information (e.g., cascade graphs and cascade sequences) is necessary for understanding the information cascade. Current methods rarely focus on unifying this information for popularity predictions, which prevents them from effectively modeling the full properties of cascades to achieve satisfactory prediction performances. In this paper, we propose an explicit Time embedding based Cascade Attention Network (TCAN) as a novel popularity prediction architecture for large-scale information networks. TCAN integrates temporal attributes (i.e., periodicity, linearity, and non-linear scaling) into node features via a general time embedding approach (TE), and then employs a cascade graph attention encoder (CGAT) and a cascade sequence attention encoder (CSAT) to fully learn the representation of cascade graphs and cascade sequences. We use two real-world datasets (i.e., Weibo and APS) with tens of thousands of cascade samples to validate our methods. Experimental results show that TCAN obtains mean logarithm squared errors of 2.007 and 1.201 and running times of 1.76 h and 0.15 h on both datasets, respectively. Furthermore, TCAN outperforms other representative baselines by 10.4%, 3.8%, and 10.4% in terms of MSLE, MAE, and R-squared on average while maintaining good interpretability.     

Meta-learning adaptation network for few-shot link prediction in heterogeneous social networks

Link prediction, which aims to predict future or missing links among nodes, is a crucial research problem in social network analysis. A unique few-shot challenge is link prediction on newly emerged link types without sufficient verification information in heterogeneous social networks, such as commodity recommendation on new categories. Most of current approaches for link prediction rely heavily on sufficient verified link samples, and almost ignore the shared knowledge between different link types. Hence, they tend to suffer from data scarcity in heterogeneous social networks and fail to handle newly emerged link types where has no sufficient verified link samples. To overcome this challenge, we propose a model based on meta-learning, called the meta-learning adaptation network (MLAN), which acquires transferable knowledge from historical link types to improve the prediction performance on newly emerged link types. MLAN consists of three main components: a subtask slicer, a meta migrator, and an adaptive predictor. The subtask slicer is responsible for generating community subtasks for the link prediction on historical link types. Subsequently, the meta migrator simultaneously completes multiple community subtasks from different link types to acquire transferable subtask-shared knowledge. Finally, the adaptive predictor employs the parameters of the meta migrator to fuse the subtask-shared knowledge from different community subtasks and learn the task-specific knowledge of newly emerged link types. Experimental results conducted on real-world social media datasets prove that our proposed MLAN outperforms state-of-the-art models in few-shot link prediction in heterogeneous social networks.     

Is there a sweet spot on the foot in Australian football drop punt kicking?

In the collision between a striking implement and ball, the term “sweet spot” represents the impact location producing best results. In football kicking, it is not known if a sweet spot exists on the foot because no method to measure impact location in three-dimensional space exists. Therefore, the aims were: (1) develop a method to measure impact location on the foot in three-dimensional space; (2) determine if players impacted the ball with a particular location; (3) determine the relationship between impact location with kick performance; (4) discuss if a sweet spot exists on the foot. An intra-individual analysis was performed on foot-ball impact characteristics of ten players performing 30 Australian football drop punt kicks toward a target. (1) A method to measure impact location was developed and validated. (2) The impact locations were normally distributed, evidenced by non-significant results of the Shapiro-Wilk test (p > 0.05) and inspection of histograms, meaning players targeted a location on their foot. (3) Impact location influenced foot-ball energy transfer, ball flight trajectory and ankle plantar/dorsal flexion. (4) These results indicate a sweet spot exists on the foot for the Australian football drop punt kick. In conclusion, the impact location is an important impact characteristic.     

Physiological determinants of elite mountain bike cross-country Olympic performance

Detailed physiological phenotyping was hypothesized to have predictive value for Olympic distance cross-country mountain bike (XCO-MTB) performance. Additionally, mean (MPO) and peak power output (PPO) in 4 × 30 s all-out sprinting separated by 1 min was hypothesized as a simple measure with predictive value for XCO-MTB performance. Parameters indicative of body composition, cardiovascular function, power and strength were determined and related to XCO-MTB national championship performance (n = 11). Multiple linear regression demonstrated 98% of the variance (P < 0.001) in XCO-MTB performance (t_XCO-MTB; [min]) is explained by maximal oxygen uptake relative to body mass (VO_2peak,rel; [ml/kg/min]), 30 s all-out fatigue resistance (FI; [%]) and with a minor contribution from quadriceps femoris maximal torque (T_max; [Nm]): t_XCO-MTB = ?0.217× VO_2peak,rel.–0.201× FI+ 0.012× T_max+ 85.4. Parameters with no additional predictive value included hemoglobin mass, leg peak blood flow, femoral artery diameter, knee-extensor peak workload, jump height, quadriceps femoris maximal voluntary contraction force and rate of force development. Additionally, multiple linear regression demonstrated parameters obtained from 4x30s repeated sprinting explained 88% of XCO-MTB variance (P < 0.001) with t_XCO-MTB = ?5.7× MPO+ 5.0× PPO+ 55.9. In conclusion, XCO-MTB performance is predictable from VO_2peak,rel and 30 s all-out fatigue resistance. Additionally, power variables from a repeated sprint test provides a cost-effective way of monitoring athletes XCO-MTB performance.     

采用改进模拟植物生长算法的世界石油船队总运力预测

为准确预测世界石油船队总运力情况,收集近15年来世界石油船队总运力的统计数据,分别从总运力趋势波动和运力净增量波动两个方面进行分析。建立时间序列模型来揭示世界石油船队总运力的变化规律,用改进的模拟植物生长算法(plant growth simulation algorithm,PGSA)进行求解。与遗传算法进行对比,改进算法的程序运行时间、均方根误差和平均绝对百分比误差均较低,算法预测的结果与历史数据的拟合度达92. 32%,预测结果具有较高的准确性。分析思路和方法可为航运企业科学决策提供技术支撑。