This paper presents the comparative evaluation of multiple compact and lightweight 2D laser scanners for their possible backpack based scanning and mapping applications. These scanners include Hokuyo URG-04LX, Slamtec RPLidar A1-M8 and Hokuyo UTM-30LX-EW scanners. Since the technical datasheets provide general information and limited working details, this research presents a thorough study on the performance of each scanner related explicitly to indoor mapping operations. A series of scanning experiments have been performed for the characterization of each scanner using statistical analysis. During the testing, all the scanning data has been recorded using Robot Operating System (ROS) and then computed in offline processing. In initial tests, each scanner’s drift effect on range measurements has been tested and presented in the relevant section of the paper. In continuation, the effect of various scanning distances on measurement accuracy has been evaluated and discussed. Later the impact of various materials typically found in indoor vicinities and their respective properties of color and smoothness have been tested and provided in the paper. Finally, a Kalman Filtering based mathematical formulation has been utilized to calibrate each scanner and to reduce the measuring uncertainties as observed in various tests for each scanner.

Summary Accurate application layer classification of Internet traffic has been a necessary requirement for various regulatory, control, and operational purposes of Internet service provider (ISP). Due to the dynamic and ever evolving nature of Internet applications generating a diverse mixture of Internet traffic, it has been necessary to apply deep packet inspection (DPI) techniques for traffic classification. DPI methods offer accuracy but degrade overall network throughput and thus cause problems in ensuring quality of service (QoS) and maintaining service‐level agreements. Moreover, Internet traffic is mostly end to end encrypted. This in turn limits the applicability of DPI techniques and renders them useless, unless the encryption tunnel is broken by the service provider which would risk violating user privacy. To address these trade‐offs between classification accuracy, performance, and user privacy, we resort to machine learning (ML)‐based algorithms. In this article, we apply three ensemble ML algorithms and report their performance metrics in the application layer classification of Internet traffic.

No abstract