DataLearner: A Data Mining and Knowledge Discovery Tool for Android Smartphones and Tablets

Abstract

Smartphones have become the ultimate 'personal' computer, yet despite this, general-purpose data mining and knowledge discovery tools for mobile devices are surprisingly rare. DataLearner is a new data mining application designed specifically for Android devices that imports the Weka data mining engine and augments it with algorithms developed by Charles Sturt University. Moreover, DataLearner can be expanded with additional algorithms. Combined, DataLearner delivers 40 classification, clustering and association rule mining algorithms for model training and evaluation without need for cloud computing resources or network connectivity. It provides the same classification accuracy as PCs and laptops, while doing so with acceptable processing speed and consuming negligible battery life. With its ability to provide easy-to-use data mining on a phone-size screen, DataLearner is a new portable, self-contained data mining tool for remote, personalised and educational applications alike. DataLearner features four elements -this paper, the app available on Google Play, the GPL3-licensed source code on GitHub and a short video on YouTube.

GPU backed Data Mining on Android Devices

“…The DBSCAN and the Kmeans algorithms were not part of their survey. Short after the same authors have published an article [19] on a data mining app ("DataLearner") developed by them and designed for the use on Android mobile devices. They followed the same approach they described in the former paper.…”

FastForest: Increasing Random Forest Processing Speed While Maintaining Accuracy

“…The first was for Weka version 3.8.3 on PC (the test PC featured Intel Core i5 CPU, 16GB of RAM, Windows 8.1 operating system and Intel 535-series solid state drive). The second was for an un-released update of DataLearner [13] for smartphone use (as shown in Fig. 10, tested on a 2019 Samsung Galaxy A30 phone with 8-core CPU, 3GB of RAM and Android 9.0 operating system).…”

“…The smartphone tests were conducted on the 30 datasets of Groups 1 and 2, while the PC tests were carried out on all three test groups introduced in Section 4. DataLearner [13] is currently limited to single-core processing and thus, testing with the large record-count datasets of Group 3 would have been excessive. However, DataLearner [13] is the only application of its type on Google Play at time of writing and in its first iteration.…”

“…DataLearner [13] is currently limited to single-core processing and thus, testing with the large record-count datasets of Group 3 would have been excessive. However, DataLearner [13] is the only application of its type on Google Play at time of writing and in its first iteration.…”

“…With the rise of smartphones and Internet of Things (IoT) over recent years, there is growing potential to bring data mining to hardware-constrained devices, despite the reduced levels of processing speed they may offer. As an example, our previous research [13] has brought locally-executed data mining to the Android platform through our open-source DataLearner app, available free on Google Play 1 . Moreover, moves by cloud service providers such as Amazon Web Services to change the cost structure of these services from a per-hour to a per-second basis [14] suggests there can also be direct cost savings by implementing more efficient algorithms in cloud-based applications.…”