In the absence of pharmaceutical interventions for the Novel Coronavirus (COVID-19), countries have taken drastic steps like quarantine, prohibit large-scale gatherings, limited transport, social distancing, curfews, and lockdowns to curtail the spread of the virus In light of these events, the current study attempts to understand the short-term changes in road traffic patterns, using data from two Wi-Fi MAC Scanners deployed at strategic locations in Chennai, India The results indicate that the road traffic activities significantly reduced due to the restrictions in non-essential trips, workplace suspensions, and strict surveillance during lockdowns However, as the lockdown rules eased, the road traffic activities began to recover It is found that complete closedown is most effective in reducing road travel activity, but ad-hoc short duration complete closedowns may only yield temporary benefits Also, extended lockdowns without proper enforcement may be ineffective since the public appeared to ignore the advisory after a while [ABSTRACT FROM AUTHOR] Copyright of Transportation Letters is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission However, users may print, download, or email articles for individual use This abstract may be abridged No warranty is given about the accuracy of the copy Users should refer to the original published version of the material for the full abstract (Copyright applies to all Abstracts )

https://www.tandfonline.com/doi/pdf/10.1080/19427867.2021.1899580

Analysis of road traffic pattern changes due to activity restrictions during COVID-19 pandemic in Chennai

We propose a methodology for using the records from Wi-Fi packet sensors to model route choice and time spent at different locations within a tourist area. In contrast to other route choice problems, in tourist areas it is often the case that “the route is the goal,” so we expect route choice behavior to be less destination oriented. Data were collected from Higashiyama Ward, Kyoto, Japan, which is highly frequented by tourists. We utilized Wi-Fi packet sensors, which avoid the need for mobile applications but provide only spot data. Based on the data, we first discuss the extraction of tourist trip chains and the construction of a simplified time-space network with “stay” and “move” links. The network and link attributes are based on the location of the sensors as well as map data. Recursive Logit (RL) models are then employed to formulate tourists’ route choice behavior. The existence of different kinds of “points of interests” (POIs) is shown to explain route choice as well as the time spent on roads with shops, restaurants and sightseeing spots.

Estimation of walking patterns in a touristic area with Wi-Fi packet sensors

Traffic prediction plays a crucial role in alleviating traffic congestion which represents a critical problem globally, resulting in negative consequences such as lost hours of additional travel time and increased fuel consumption. Integrating emerging technologies into transportation systems provides opportunities for improving traffic prediction significantly and brings about new research problems. In order to lay the foundation for understanding the open research challenges in traffic prediction, this survey aims to provide a comprehensive overview of traffic prediction methodologies. Specifically, we focus on the recent advances and emerging research opportunities in Artificial Intelligence (AI)-based traffic prediction methods, due to their recent success and potential in traffic prediction, with an emphasis on multivariate traffic time series modeling. We first provide a list and explanation of the various data types and resources used in the literature. Next, the essential data preprocessing methods within the traffic prediction context are categorized, and the prediction methods and applications are subsequently summarized. Lastly, we present primary research challenges in traffic prediction and discuss some directions for future research. 

/pdf/traffic-prediction-using-artificial-intelligence-review-of-j2lkj4cz.pdf

Traffic prediction using artificial intelligence: Review of recent advances and emerging opportunities

Traffic data collection is one of the major issue faced by the researches as well as government authorities for the study of traffic movement behaviour. Conventional methods of data collection under mixed traffic condition do not yield promising results and cannot be completely relied upon. Thus, this study aims to assess the potential use of Wi-Fi based sensors for the performance evaluation of arterial closed network and formation of O-D matrix in Centre Business District area of Surat city with help of Wi-Fi based data collection technique. This paper expounds the essentiality for the use of Wi-Fi data as an outlining parameter in the performance evaluation of the study network, which is unlike the conventional examinations that signifies the use of Bluetooth observations for evaluating the network operation based on the travel time reliability measures. The data provides exceptional results than the other hackneyed techniques, which results in less sample size and accuracy. Further, the network development was executed with the deployment of four sensors at critical confluences. This was useful for scrutinizing the traffic movements along the arterial network. The sensors used here work on the principle of recurring detections of MAC ids for the devices along with their analogous time stamps for the duration in which they remain within the detection range. Thus, re-identification of the same moving vehicle along various network points will help to determine the travel time where the difference in the time stamps of certain MAC ids moving among several junction points were exercised for the determination of travel time and development of O-D matrix along all possible routes. The Wi-Fi data obtained from the sensors in Surat city network corresponds to the critical routes for various hours of the day. This leads to development of primary and secondary matrix comprising of total and cut through traffic, which are useful for multiple aspects. The trial results show the successful penetration (unique detections to vehicles) ratio ranging from 20-to30percentage after significant results from various statistical analysis test as well as considerations from literature studies. The ultimate outcomes will justify the substantiation of results obtained from sensors along with assessments with other performance-measuring device.

Performance Evaluation of Urban Arterial Network Using Wi-Fi Sensors Under Heterogeneous Traffic Conditions

Reliable, real-time prediction of delay and density is challenging as direct measurement of these variables is difficult. Though studies yielding reasonably accurate predictions of delay and density are reported in the literature, a comprehensive methodology to simultaneously predict both delay and density is lacking. Hence, a recursive technique that uses minimal real-time data for dynamic simultaneous prediction of midblock density and intersection delay is proposed. This study uses conservation equation-based recursive prediction of the number of vehicles inside the midblock section (density), which in turn is used to predict delay using shockwave theory. The Kalman Filter is a one-step-ahead density prediction method that can yield reliable density predictions even under the presence of errors in detector data. The one-step-ahead delay predictions obtained had a Mean Absolute Percentile Error (MAPE) of 10.4%, whereas the one-step-ahead density predictions obtained had a MAPE of 9.96%. Due to its robustness, this method can be used to arrive at one-step-ahead predictions of parameters like delay and queue length for any traffic scenario for which shockwave diagrams can be produced. 

Simultaneous Prediction of Midblock and Intersection Traffic States on Urban Arterials

The investigation and examination of activity conduct are basically reliant on the accessibility of movement information. Movement information accumulation under blended activity conditions is one of the significant issues looked by scientists and in addition activity administrative experts. Travel time can be measured using different types of sensors; however, due to the heterogeneity in vehicle classes, its performance is a major concern, especially for Indian condition. Among the emerging methods, Bluetooth-based sensors are gaining popularity, but the fact that the number of active Bluetooth devices in the traffic stream in India is generally very low and is a hindrance to the effectiveness of data collection. To overcome this limitation, the use of a Wi-Fi/Bluetooth sensor has been thought upon recently. Thus, the main aim of this research is to test the reliability of such Wi-Fi/Bluetooth-based sensors and to determine travel time at mid-block section along with the determination of the distribution model which would best fit for the study condition, and their relations with various statistical parameters to identify the best results.

A Wi-Fi Sensor-Based Approach for Examining Travel Time Reliability Parameters Under Mixed Traffic Conditions

Travel time is one of the elementary traffic stream parameters in both users’ and transport planners’ perspective. Conventional travel time estimation methods have performed out of sorts for Indian urban traffic conditions characterized by heterogeneity in transport modes and lack of lane discipline. Robust to these limitations, Media Access Control (MAC) matching is perceived to be a reliable alternative for travel time estimation. To assist with real-time traffic control strategies, this study aims at developing a reliable structure for forecasting travel time on Indian urban arterials using data from Wi-Fi/ Bluetooth sensors. The data collected on an urban arterial in Chennai has been used as a case study to explain the value of such data and to explore its applicability in implementing various prediction models. To this end, this study examines and compares three different machine learning algorithms k-Nearest Neighbour (kNN), Random Forest (RDF), Naive Bayes, and Kalman filtering technique for prediction. The performance of each model is evaluated to understand its suitability.

/pdf/comparative-analysis-of-travel-time-prediction-algorithms-2dvhspmz7p.pdf

Comparative analysis of travel time prediction algorithms for urban arterials using Wi-Fi Sensor Data

Traffic data collection under mixed traffic conditions is one of the major problems faced by researchers as well as traffic regulatory authorities. For mixed traffic observed in developing countries, no suitable tool is available for this purpose. Keeping in view the necessities of acquiring an extensive database and the difficulties associated with its collection, ITS techniques can be implemented as an accurate and efficient methods of data collection. Among the emerging methods, Bluetooth-based sensors are gaining popularity, but the number of active Bluetooth devices in the traffic stream in India is generally very low and is hindrance to the effectiveness of data collection. Thus, the main aim of this research is to test the reliability of such Wi-Fi/Bluetooth-based sensor which is one of the most reliable and easy-to-use instruments that can aid us in solving above parameters efficiently. Exploration for the performance of such ITS-based technology is carried out in the determination of traffic flow parameters on NE-1 expressway of India and thereby validating the results with the help of videography survey data.

Smit Bharat Thakkar

Papers

A Wi-Fi Sensor-Based Approach for Examining Travel Time Reliability Parameters Under Mixed Traffic Conditions

Performance Evaluation of Urban Arterial Network Using Wi-Fi Sensors Under Heterogeneous Traffic Conditions

Comparative analysis of travel time prediction algorithms for urban arterials using Wi-Fi Sensor Data

Exploring Performance of Intercity Expressway Using ITS-Based Technology