Recent Trends of Machine Learning Predictions Using Open Data: A Systematic Review

Abstract

Machine learning (ML) prediction determinants based on open data (OD) are investigated in this work, which is accomplished by examining current research trends over ten years. Currently, OD is commonly regarded as the most crucial trend for users to improve their ability to make decisions, particularly to the exponential expansion of social networking sites (SNSs) and open government data (OGD).The purpose of this study was to examine if there was an increase in the usage of OD in ML prediction techniques by conducting a systematic literature review (SLR) of the results of the trends. The papers published in major online scientific databases between 2011 and 2020, including ScienceDirect, Scopus, IEEE Xplore, ACM, and Springer, were identified and analysed. After various selection and Springer, were identified and analysed. After various selection processes, according to SLR based on precise inclusion and exclusion criteria, a total of 302 articles were located. However, only 81 of them were included. The findings were presented and plotted based on the research questions (RQs). In conclusion, this research could be beneficial to organisations, practitioners, and researchers by providing information on current trends in the implementation of ML prediction using OD setting by mapping studies based on the RQs designed, the most recent growth, and the necessity for future research based on the findings.

A Modified Gated Recurrent Unit Approach for Epileptic Electroencephalography Classification

“…DL models such as the Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long-short term memory (LSTM), Gated Recurrent Unit (GRU), and Autoencoders (AEs) are widely used for the automatic detection of an epileptic seizure (Natu et al, 2022). Chen et al (2016) reviewed the LSTM model as a distinguished technique with the best performance measures (Ismail & Yusof, 2022). RNNs with a gated mechanism have emerged as useful for modelling sequential inputs such as speech or EEG.…”

GIS-Based Spatial Analysis Model for Assessing Impact and Cumulative Risk in Road Traffic Accidents via Analytic Hierarchy Process (AHP)—Case Study: Romania

“…This has also been influenced by the methods of developing, calibrating, and adapting models to the socio-economic, cultural and development conditions of the areas in where they have been proposed and tested [5,32,[37][38][39]. The increasing availability of car crash data has enabled the development of a new research direction related to road accident prediction, in which machine learning analysis methods are used due to their ability to flexibly process and manage multi-dimensional data to determine crash severity [12,[40][41][42][43][44][45].…”