Crime Based Evaluation of GPS Network Using Machine Learning Techniques

With the increased usage of data transmission, data leakage and privacy protection are becoming increasingly critical. Data comes in a variety of forms, and the amount of protection required for each one differs. With the rapid development and demand of Global Positioning System (GPS) networks in every of big data technology, the vulnerability of the transportation system to unintentional and intentional GPS disruption is also increasing. The GPS signal is degraded and lost as a result of opposing interests' attacks. Potential assaults vary from GPS signal jamming and spoofing to GPS ground stations and satellite disruption. Security issues with respect to data increases during data transmission. Data travelling across an organization's network is frequently sensitive and internet being the storehouse of every kind of data with methods for accessing the precise information serves as an auspicious medium for the hackers [19]. Network security solutions must deal with complicated data in this setting in order to detect and minimize any threats in real time. There are several techniques to the problem of data security such as cryptographic algorithms, classification-based models, and block-chain methods [1]–[6]. Through this research, crime rates are evaluated in a GPS network data with different other parameters using machine learning (ML) algorithms. Moreover, the inferred features effecting the crimes during data transmission are extracted. Some of the techniques used includes techniques such as ‘Decision Tree (DT)’, ‘K Nearest Neighbors (KNN)’, ‘Random Forest (RF)’, ‘Multivariable Regression (MR)’ and ‘Naïve Bayes (NB)’. It was seen that the best accuracy was given by RF - of approximately 84.25%.