Association rule mining (ARM) is a commonly encountred data mining method. There are many approaches to mining frequent rules and patterns from a database and one among them is heuristics. Many heuristic approaches have been proposed but, to the best of our knowledge, there is no comprehensive literature review on such approaches, yet with only a limited attempt. This gap needs to be filled. This paper reviews heuristic approaches to ARM and points out their most significant strengths and weaknesses. We propose eight performance metrics, such as execution time, memory consumption, completeness, and interestingness, we compare approaches against these performance metrics and discuss our findings. For instance, comparison results indicate that SRmining, PMES, Ant‐ARM, and MDS‐H are the fastest heuristic ARM algorithms. HSBO‐TS is the most complete one, while SRmining and ACS require only one database scan. In addition, we propose a parameter, named GT‐Rank for ranking heuristic ARM approaches, and based on that, ARMGA, ASC, and Kua emerge as the best approaches. We also consider ARM algorithms and their characteristics as transactions and items in a transactional database, respectively, and generate association rules that indicate research trends in this area.

A survey on association rules mining using heuristics

Computer programming has attracted a lot of attention in the development of information and communication technologies in the real world. Meeting the growing demand for highly skilled programmers in the ICT industry is one of the major challenges. In this point, online judge (OJ) systems enhance programming learning and practice opportunities in addition to classroom-based learning. Consequently, OJ systems have created a large number of problem-solving data (solution codes, logs, and scores) archives that can be valuable raw materials for programming education research. In this paper, we propose an educational data mining framework to support programming learning using unsupervised algorithms. The framework includes the following sequence of steps: (i) problem-solving data collection (logs and scores are collected from the OJ) and preprocessing; (ii) MK-means clustering algorithm is used for data clustering in Euclidean space; (iii) statistical features are extracted from each cluster; (iv) frequent pattern (FP)-growth algorithm is applied to each cluster to mine data patterns and association rules; (v) a set of suggestions are provided on the basis of the extracted features, data patterns, and rules. Different parameters are adjusted to achieve the best results for clustering and association rule mining algorithms. For the experiment, approximately 70,000 real-world problem-solving data from 537 students of a programming course (Algorithm and Data Structures) were used. In addition, synthetic data have leveraged for experiments to demonstrate the performance of MK-means algorithm. The experimental results show that the proposed framework effectively extracts useful features, patterns, and rules from problem-solving data. Moreover, these extracted features, patterns, and rules highlight the weaknesses and the scope of possible improvements in programming learning.

https://ieeexplore.ieee.org/ielx7/6287639/9668973/09729752.pdf

Educational Data Mining to Support Programming Learning Using Problem-Solving Data

务;感知;社交媒体 ABSTRACT Natural wetlands play a vital role in maintaining regional water balance, regulating regional climate, and maintaining biodiversity. Due to urban sprawl in China, the loss of natural wetlands has been dramatic. In recent years, nature-based solutions, including wetland parks, have been advocated to compensate for this loss and to reduce vulnerability and disaster risks. As a result, inspired by natural wetlands or building on existing wetland ecosystems, hundreds of wetland parks have been created in China over the last decade. Most research on ecosystem services of wetland parks has to date focused on technical perspectives, with only a few addressing public perception; the public’s perception of wetland parks is not well understood. This research used social media (i.e. Sina Weibo) to access large volumes of data and provide temporal and geographic granularity. A semantic analysis of microblogs was performed to understand how the public perceives the ecosystem services of wetland parks in Guangzhou. This study explored the public’s perceptions and compared these with the ecosystem services as communicated by professional institutions, and probed into the factors that affect these perceptions. The results showed that the top three ecosystem services perceived by both the general public and communicated by institutions are recreation, aesthetics, and refugia / habitat. There is a strong interconnection between the perceptions of recreation and aesthetics services. Flowering plant species and colored-leaf trees are the most important stimuli affecting perceptions of aesthetics services, and birds are key to the perception of refugia / habitat services. These results provide a basis for better aligning management of projects utilizing naturebased solutions, such as wetland parks, with expectations from the public.

/pdf/using-social-media-to-explore-perceptions-of-ecosystem-3v4xath8bo.pdf

Using social media to explore perceptions of ecosystem services by nature-based solution projects

Reducing students’ high dropout rates in the computer programming courses is a challenging problem of great concern in computer science education. Online Judge (OJ) systems were recently being investigated to address this problem and promote computer programming education. Most of the existing OJ systems have been confined only for evaluation purposes, and do not provide any personalized recommendations to enhance the productivity of a student. With this motivation, this paper proposes a novel rule-based OJ recommender system to promote computer programming education. The proposed system involves the following five steps: (i) scoring the programs submitted by a student automatically, (ii) generation of a transactional database, (iii) clustering the database with respect to their scores and other evaluation parameters, (iv) discovering interesting association rules that exist in each of the cluster’s data, and (v) providing appropriate recommendations to the users. Experimental results on the data generated by a real-world OJ system demonstrate that the proposed system is efficient.

A Novel Rule-Based Online Judge Recommender System to Promote Computer Programming Education

Computer programming has attracted a lot of attention in the development of information and communication technologies in the real world. Meeting the growing demand for highly skilled programmers in the ICT industry is one of the major challenges. In this point, online judge (OJ) systems enhance programming learning and practice opportunities in addition to classroom-based learning. Consequently, OJ systems have created a large number of problem-solving data (solution codes, logs, and scores) archives that can be valuable raw materials for programming education research. In this paper, we propose an educational data mining framework to support programming learning using unsupervised algorithms. The framework includes the following sequence of steps: (<inline-formula> <tex-math notation="LaTeX">$i$ </tex-math></inline-formula>) problem-solving data collection (logs and scores are collected from the OJ) and preprocessing; (<inline-formula> <tex-math notation="LaTeX">$ii$ </tex-math></inline-formula>) MK-means clustering algorithm is used for data clustering in Euclidean space; (<inline-formula> <tex-math notation="LaTeX">$iii$ </tex-math></inline-formula>) statistical features are extracted from each cluster; (<inline-formula> <tex-math notation="LaTeX">$iv$ </tex-math></inline-formula>) frequent pattern (FP)-growth algorithm is applied to each cluster to mine data patterns and association rules; (<inline-formula> <tex-math notation="LaTeX">$v$ </tex-math></inline-formula>) a set of suggestions are provided on the basis of the extracted features, data patterns, and rules. Different parameters are adjusted to achieve the best results for clustering and association rule mining algorithms. For the experiment, approximately 70,000 real-world problem-solving data from 537 students of a programming course (Algorithm and Data Structures) were used. In addition, synthetic data have leveraged for experiments to demonstrate the performance of MK-means algorithm. The experimental results show that the proposed framework effectively extracts useful features, patterns, and rules from problem-solving data. Moreover, these extracted features, patterns, and rules highlight the weaknesses and the scope of possible improvements in programming learning. 

Association rules mining (ARM) is one of the most useful techniques in the field of knowledge discovery and data mining and so on. Frequent item sets mining plays an important role in association rules mining. Apriori algorithm and FP-growth algorithm are famous algorithms to find frequent item sets. Based on analyzing on an association rule mining algorithm, a new association rule mining algorithm, called HSP-growth algorithm, is presented to generate the simplest frequent item sets and mine association rules from the sets. HSP-growth algorithm uses Huffman tree to describe frequent item sets. The basic idea and process of the algorithm are described and how to affects association rule mining is discussed. The performance study and the experimental results show that the HSP-growth algorithm has higher mining efficiency in execution time and is more efficient than Apriori algorithm and FP-growth algorithm.

Research and improvement on association rule algorithm based on FP-Growth

Intrusion detection is an important security tool. Intrusion detection systems are becoming ubiquitous defenses in today's networks. But some researches showed that the volume of alerts generated from intrusion detection systems can be overwhelming. The alert aggregation and alert correlation capability has the potential to reduce alert volume and improve detection performance. In this paper, an approach of correlating intrusion alerts based on the association rules mining is proposed, which can effectively reduce the repeated alert thereby to reduce the rate of false alarm.

Jingbo Yuan

Papers

Research and improvement on association rule algorithm based on FP-Growth

An alerts correlation technology for large-scale network intrusion detection