Machine and Deep Learning Technologies, Location Tracking and Obstacle Avoidance Algorithms, and Cognitive Wireless Sensor Networks in Intelligent Transportation Planning and Engineering.

• Author: Beckett, Susan

1. Introduction

   Intelligent transportation infrastructures develop on real-time Internet of Things data, augmented analytics tools, and cognitive data fusion techniques. The purpose of my systematic review is to examine the recently published literature on intelligent transportation planning and engineering and integrate the insights it configures on machine and deep learning technologies, location tracking and obstacle avoidance algorithms, and cognitive wireless sensor networks. By analyzing the most recent (2021-2022) and significant (Web of Science, Scopus, and ProQuest) sources, my paper has attempted to prove that virtual mapping and data mining tools, 3D virtual simulation technology, and mobile wireless sensor networks (Balcerzak et al, 2022; Kral et al, 2020; Nica et al, 2022a, b) configure sustainable urban monitoring systems. The actuality and novelty of this study are articulated by addressing automated sensing tools, visual object detection-based systems, and smart traffic planning and analytics (Blake and Frajtova Michalikova, 2021; Mihaila et al, 2016; Popescu et al, 2018; Valaskova et al, 2022), that is an emerging topic involving much interest. My research problem is whether visualization and analytics tools, augmented and virtual technologies, and automated simulation modeling shape data-driven smart sustainable urbanism. In this review, prior findings have been cumulated indicating that visual recognition tools, cloud computing algorithms, and spatial data analytics articulate urban driving environments. The identified gaps advance big geospatial data analytics, vehicle routing and navigation tools, and smart sustainable urban mobility behaviors. My main objective is to indicate that urban data fusion, perception and prediction dynamics, and multi-object detection and tracking tools (Barbu et al, 2021; Lazaroiu et al, 2017; Peters, 2022) further smart transportation systems. This systematic review contributes to the literature on object detection and tracking, vehicular communication technologies, and sensor fusion algorithms (Andronie et al, 2021a, b; Glogovetan et al., 2022; Pelau et al., 2021; Popescu et al., 2022) by clarifying that smart mobility technologies develop on computational object instantiation and recognition, sensor data processing algorithms, predictive simulation tools, and urban traffic modeling.

2. Theoretical Overview of the Main Concepts

   Autonomous driving perception algorithms, transportation analytics, and intelligent routing systems decrease traffic jams. Urban sensing technologies deploy cognitive computing systems, data monitoring algorithms, and virtual simulation tools. Big data-driven urban analytics, tracking control algorithms, and cloud and edge computing technologies typify smart transportation systems. Intelligent transportation systems integrate machine learning algorithms, geospatial mapping tools, and sensing and computing technologies. The manuscript is organized as following: theoretical overview (section 2), methodology (section 3), automated sensing tools, visual object detection-based systems, and smart traffic planning and analytics (section 4), object detection and tracking, vehicular communication technologies, and sensor fusion algorithms (section 5), urban computing algorithms, geospatial data mining tools, and dynamic mapping processes (section 6), discussion (section 7), synopsis of the main research outcomes (section 8), conclusions (section 9), limitations, implications, and further directions of research (section 10).

3. Methodology

   Throughout March 2022, I performed a quantitative literature review of the Web of Science, Scopus, and ProQuest databases, with search terms including "intelligent transportation planning and engineering" + "machine and deep learning technologies," "location tracking and obstacle avoidance algorithms," and "cognitive wireless sensor networks." The search terms were determined as being the most employed words or phrases across the analyzed literature. As I inspected research published between 2021 and 2022, only 82 articles satisfied the eligibility criteria. By eliminating controversial findings, outcomes unsubstantiated by replication, too imprecise material, or having similar titles, I decided upon 13, generally empirical, sources (Tables 1 and 2). Extracting and inspecting publicly accessible files (scholarly sources) as evidence, before the research began no institutional ethics approval was required. Data visualization tools: Dimensions (bibliometric mapping) and VOSviewer (layout algorithms). Reporting quality assessment tool: PRISMA. Methodological quality assessment tools include: AXIS, Dedoose, Distiller SR, and MMAT (Figures 1-6).

4. Automated Sensing Tools, Visual Object Detection-based Systems, and Smart Traffic Planning and Analytics

   Big geospatial data analytics, vehicle routing and navigation tools, and smart sustainable urban mobility behaviors (Penmetsa et al., 2021; Yang et al., 2021) are pivotal in mixed traffic environments. Embedded sensors in autonomous driving systems have limited perception capacities, resulting in impractical sensing of surroundings. High-profile collisions may influence public opinion and trust in relation to autonomous driving systems. Urban data fusion, perception and prediction dynamics, and multi-object detection and tracking tools further smart transportation systems.

   Internet of Things sensing infrastructures, self-driving car perception systems, and autonomous driving algorithms and behaviors (Duleba et al., 2021; Stilgoe, 2021) shape sustainable urban governance networks. Big data-driven urban analytics, tracking control algorithms, and cloud and edge computing technologies typify smart transportation systems. Designing safe systems and upgrading infrastructure are crucial in reducing public risk perceptions as regards connected and autonomous vehicles in uncontrolled environments. Sensor data, automated collision avoidance systems, and predictive control algorithms reduce traffic congestion.

   Automated sensing tools, visual object detection-based...