Dataset

This dataset was created by Shashank

Contents

The data are provided to illustrate methods in evaluating systematic transactional data reuse in machine learning. A library account-based recommender system was developed using machine learning processing over transactional data of 383,828 transactions (or check-outs) sourced from a large multi-unit research library. The machine learning process utilized the FP-growth algorithm over the subject metadata associated with physical items that were checked-out together in the library. The purpose of this research is to evaluate the results of systematic transactional data reuse in machine learning. The analysis herein contains a large-scale network visualization of 180,441 subject association rules and corresponding node metrics.

Additional file 1. Spark application of the e-learning recommender system.

This dataset presents a collection of co-existence features extracted from the original CICMalDroid 2020 using the FP-Growth algorithm. The co-existence features are combinations of two features that frequently occur together within the dataset.

Mined rules by FP-Growth algorithm.

Additional file 1. Table 1. Disease generalization in ICD-10 codes. Table 2. Comparison among OMOP ID, Concept Code and the generlization ICD-10 codes. Table 3. The rules verified by literatures. Table 4. The rules discoveried by FP-growth algorithm.

As the penetration rate of new energy in the power system gradually increases and the complexity of cascading faults increases, it is of great significance for the power system to comprehensively explore the chain of cascading faults in the new energy power system and quickly determine the closely related lines in the cascading faults. In response to the lack of consideration in existing research of the changes in the importance of transmission lines after the introduction of new energy, this paper proposes a cascading failure prediction index that integrates the importance and operational status of transmission lines in new energy power systems and applies it to the search for cascading failures in new energy power systems. First, the development characteristics of cascading faults were analyzed, and the main factors influencing cascading faults were identified: the importance of the transmission line and operating status of the new energy power system. Based on these factors, a prediction index for cascading faults was established, and the accident chain was searched using this index. Then, the FP-growth algorithm was used to analyze the lines in the fault chain concentration, and based on the analysis results, the correlation relationship suitable for the cascading failure lines in the new energy power system was determined. Finally, a simulation was conducted on an IEEE 10 machine 39 node system containing new energy wind turbines, and the results verified the effectiveness of the proposed indicators and strategies.