Profiles of Chilean students according to academic performance in mathematics: An exploratory study using classification trees and random forests

Attempting to deepen the understanding of factors that explain student performance, this study seeks to identify and characterize profiles of Chilean students based on academic performance in mathematics. As analytical method, statistical techniques known as random forest (RF) and classification and regression tree (CART) were used to identify groups of eighth-grade elementary students according to their performance in 2011 test, using features related to individual and family behavior. The analysis was performed with a database provided by the Education Quality Measurement System of Chile. Results show that “parents’ educational expectations” (42.7%) is key factor to obtain the best children's performances. Additionally, the analysis showed that the “type of school” (26.6%) and the “index of mathematical abilities” (26.1%) influence good performance.     

Temporal burstiness and collaborative camouflage aware fraud detection

With the prosperity and development of the digital economy, many fraudsters have emerged on e-commerce platforms to fabricate fraudulent reviews to mislead consumers’ shopping decisions for profit. Moreover, in order to evade fraud detection, fraudsters continue to evolve and present the phenomenon of adversarial camouflage and collaborative attack. In this paper, we propose a novel temporal burstiness and collaborative camouflage aware method (TBCCA) for fraudster detection. Specifically, we capture the hidden temporal burstiness features behind camouflage strategy based on the time series prediction model, and identify highly suspicious target products by assigning suspicious scores as node priors. Meanwhile, a propagation graph integrating review collusion is constructed, and an iterative fraud confidence propagation algorithm is designed for inferring the label of nodes in the graph based on Loop Belief Propagation (LBP). Comprehensive experiments are conducted to compare TBCCA with state-of-the-art fraudster detection approaches, and experimental results show that TBCCA can effectively identify fraudsters in real review networks with achieving 6%–10% performance improvement than other baselines.     

Measuring robustness in rank aggregation based on the error-effectiveness curve

Rank aggregation is an obligatory operation for many tasks of democratic elections, product recommendation, and gene identification. While the awareness of imperfect information in input rankings would lead to unreliable aggregation results has promoted the robust rank aggregation to become an increasingly active research topic recently. In this study, we focus on the problem of robustness measuring of rank aggregation methods. We first provide an analytical framework of rank aggregation robustness, in which we generate rankings with adjustable imperfect information and observe the response of rank aggregation methods. In particular, to quantify the robustness of rank aggregation methods, we introduce the concept of error-effectiveness curve, which presents the aggregation effectiveness under different imperfect information scenarios, and describes the ability of each method in giving stable aggregation results. By doing so, a robustness measure of rank aggregation with random error is developed. Comprehensive experimental evaluations were conducted considering synthetic datasets with various levels of random error to demonstrate the validity of the proposed measure. Exact robustness was quantified for each evaluated rank aggregation methods, and significant robustness distinctions were achieved among them.     

随机误差的Matlab处理方法研究

测量过程中不可避免存在着随机误差,当测量次数n增大时,用手工处理随机误差不仅过程复杂,计算量大,可靠性也不高。本文讨论了借助Matlab强大的数据处理功能处理随机误差,使处理过程简单快速。     

Interpolative coding of integer sequences supporting log-time random access

Sequences of integers are common data types, occurring either as primary data or ancillary structures. The sizes of sequences can be large, making compression an interesting option. Effective compression presupposes variable-length coding, which destroys the regular alignment of values. Yet it would often be desirable to access only a small subset of the entries, either by position (ordinal number) or by content (element value), without having to decode most of the sequence from the start. Here such a random access technique for compressed integers is described, with the special feature that no auxiliary index is needed. The solution applies a method called interpolative coding, which is one of the most efficient non-statistical codes for integers. Indexing is avoided by address calculation guaranteeing sufficient space for codes even in the worst case. The additional redundancy, compared to regular interpolative coding, is only about 1 bit per source integer for uniform distribution. The time complexity of random access is logarithmic with respect to the source size for both position-based and content-based retrieval. According to experiments, random access is faster than full decoding when the number of accessed integers is not more than approximately 0.75 · n/log₂n for sequence length n. The tests also confirm that the method is quite competitive with other approaches to random access coding, suggested in the literature.     

基于改进的LBP特征和随机森林相结合的人脸关键点检测方法研究

提出了一种人脸关键点检测方法,该方法用了少量的正面图像,不用归一化人脸图像,而传统的人脸关键点检测方法需要对图像进行严格预处理。随机森林是一种分类器融合算法,可以很好地解决多类分类问题,虽然LBP特征简单,但其可以包含大量的纹理信息。利用改进的LBP特征与随机森林相结合,构成一种对人脸关键点检测的方法。通过高斯平滑图像的LBP特征的提取,对每个点生成特征,计算出有用的特征作为正例,并且与反例集合变为训练集。通过随机森林分类器进行分类,误差率较低,仅在10％左右。     

一种强素数生成算法

RSA公钥加密体制由美国麻省理工学院于1978年提出,它是第一个成熟的、最为成功的公开密码体制,它的原理和安全性是基于数论中的Euler定理和计算复杂性理论中的论断:求两个大素数的乘积是容易计算的,但要把两个大素数的乘积分解成素因子则是非常困难的。随着密码体系分析的发展,RSA需要具有更强性质的素数(强素数)。本文提出了一种简单的强素数生成算法,同时介绍了一种伪随机数生成器和Rabin-Miller概率素性检测算法。     

A comparative study of automated legal text classification using random forests and deep learning

Automated legal text classification is a prominent research topic in the legal field. It lays the foundation for building an intelligent legal system. Current literature focuses on international legal texts, such as Chinese cases, European cases, and Australian cases. Little attention is paid to text classification for U.S. legal texts. Deep learning has been applied to improving text classification performance. Its effectiveness needs further exploration in domains such as the legal field. This paper investigates legal text classification with a large collection of labeled U.S. case documents through comparing the effectiveness of different text classification techniques. We propose a machine learning algorithm using domain concepts as features and random forests as the classifier. Our experiment results on 30,000 full U.S. case documents in 50 categories demonstrated that our approach significantly outperforms a deep learning system built on multiple pre-trained word embeddings and deep neural networks. In addition, applying only the top 400 domain concepts as features for building the random forests could achieve the best performance. This study provides a reference to select machine learning techniques for building high-performance text classification systems in the legal domain or other fields.     

基于随机森林算法的潜在高价值专利预测方法研究

【目的/意义】为了支持高价值专利培育工作开展,面向潜在高价值专利预测的需求,提出基于随机森林算法的潜在高价值专利预测方法。【方法/过程】梳理现有研究,选择用于潜在高价值专利预测的指标,构建基于随机森林算法的潜在高价值专利预测模型。使用“语音信号识别”领域的19647条专利进行实证分析,模型预测准确率达96.01%。【结果/结论】目前适于从海量早期申请中发掘潜在高价值专利的方法研究较少,本方法能够在专利申请早期发挥作用,同时具有预测准确率高、处理数据量大、模型可解释性好的优点。     

在线考试系统设计与实现——以市政设计院考试系统为例

针对目前中国市政工程中南设计研究总院（以下简称中南市政院）考试模式存在的问题,提出并开发了一套适合在设计院内联网使用的在线考试系统。着重介绍了该系统的设计、开发过程及系统实现关键技术。