scholarly journals Classifying Vehicle Activity to Improve Point of Interest Extraction

2021 ◽  
Vol 2021 ◽  
pp. 1-20
Author(s):  
James Van Hinsbergh ◽  
Nathan Griffiths ◽  
Phillip Taylor ◽  
Zhou Xu ◽  
Alex Mouzakitis

Knowledge of drivers’ mobility patterns is useful for enabling context-aware intelligent vehicle functionality, such as route suggestions, cabin preconditioning, and power management for electric vehicles. Such patterns are often described in terms of the Points of Interest (PoIs) visited by an individual. However, existing PoI extraction methods are general purpose and typically rely on detecting periods of low mobility, meaning that when they are applied to vehicle data, they often extract a large number of false PoIs (for example, incorrectly extracting PoIs due to stopping in traffic), reducing their usefulness. To reduce the number of false PoIs that are extracted, we propose using features derived from vehicle signals, such as the selected gear and status of doors, to classify candidate PoIs and filter out those that are irrelevant. In this paper, we (i) present Activity-based Vehicle PoI Extraction (AVPE), a wrapper method around existing PoI extraction methods, that utilizes a postclustering classification stage to filter out false PoIs, (ii) evaluate the benefits of AVPE compared to three state-of-the-art general purpose PoI extraction algorithms, and (iii) demonstrate the effectiveness of AVPE when applied to real-world driving data.

2020 ◽  
Vol 2020 ◽  
pp. 1-13 ◽  
Author(s):  
Zheng Zhang ◽  
Yanyan Chen ◽  
Jie Xiong ◽  
Tianwen Liang

Car hailing is undergoing rapid global development, thereby providing new opportunities and challenges to operators and transport engineers due to uneven or irregular demand in certain areas. To date, only a limited number of studies have analyzed regional mobility patterns or anomaly detection. This study therefore proposes a methodology for recognizing regional mobility patterns using car-hailing order datasets and point of interest datasets. More specifically, we detect regional mobility patterns by incorporating regional intrinsic properties to a hierarchical mixture model termed latent Dirichlet allocation (LDA). This model can simulate the process of generating car-hailing order data and yield regional mobility patterns from spatial, temporal, and spatiotemporal perspectives. Moreover, by combining the trained results with future mobility records, we can measure similarities between areas and detect anomalous areas by calculating the perplexity. We also implement our workflow on a real-word car-hailing order dataset and reveal that it is possible to identify areas with similar or anomaly mobility patterns. This research will contribute to the design of regional transportation policies and customized bus services.


2010 ◽  
Vol 15 (9) ◽  
pp. 119-128
Author(s):  
Guang-Xun Kim ◽  
Woon-Soo Choi ◽  
Tae-Woo Lee ◽  
Joon-Suk Lee ◽  
Kyoung-Ok Koo ◽  
...  

2019 ◽  
pp. 121-138
Author(s):  
Juan Carlos Escaravajal Rodríguez ◽  
Juana Ester Blázquez Perán

El objetivo del presente trabajo es identificar y valorar los puntos de interés didáctico turístico existentes en Águilas. En cuanto a la metodología, mediante un diseño observacional, se ha utilizado el método cualitativo a través de una hoja de observación, para valorar diversos factores asociados a los puntos de interés. La muestra está compuesta por 59 bienes patrimoniales, y para el análisis de los datos se ha realizado una estadística descriptiva de frecuencias y porcentajes.  En base a los resultados obtenidos, se puede concluir que Águilas posee al menos 59 puntos de interés, éstos se encuentran en un estado de conservación principalmente desfavorable, la mayoría puede visitarse sin inconvenientes, un importante porcentaje no es accesible para personas con movilidad reducida y, además, la mayoría no posee información “in situ”. A partir de estos datos se pueden iniciar y valorar diversas propuestas para facilitar el acercamiento del patrimonio a los ciudadanos. The aim of this project is to identify and assess every existent didactic point of interest in Águilas. Regarding the methodology, using an observational design, a qualitative method through an observation sheet has been employed; in order to assess different factors associated to these points of interest. The sample is made of 59 heritage assets and, for the data analysis, a descriptive statistics of frequency and percentages were created. According to the results, it can be concluded that Águilas has at least 59 points of interest, these are now in an unfavorable condition, and although the majority of them can be visited without any inconvenient, a significant percentage is not accessible to people with reduced mobility and moreover, the majority of them does not have on-site information. From this data we can start and assess several proposals in order to bring this heritage closer to the citizens


2020 ◽  
Vol 1 ◽  
pp. 2551-2560
Author(s):  
J. Orlovska ◽  
C. Wickman ◽  
R. Soderberg

AbstractAdvanced Driver Assistance Systems (ADAS) require a high level of interaction between the driver and the system, depending on driving context at a particular moment. Context-aware ADAS evaluation based on vehicle data is the most prominent way to assess the complexity of ADAS interactions. In this study, we conducted interviews with the ADAS development team at Volvo Cars to understand the role of vehicle data in the ADAS development and evaluation. The interviews’ analysis reveals strategies for improvement of current practices for vehicle data-driven ADAS evaluation.


2018 ◽  
Vol 9 (1) ◽  
pp. 14 ◽  
Author(s):  
Julia Krause ◽  
Stefan Ladwig ◽  
Lotte Saupp ◽  
Denis Horn ◽  
Alexander Schmidt ◽  
...  

Fast-charging infrastructure with charging time of 20–30 min can help minimizing current perceived limitations of electric vehicles, especially considering the unbalanced and incomprehensive distribution of charging options combined with a long perceived charging time. Positioned on optimal location from user and business perspective, the technology is assumed to help increasing the usage of an electric vehicle (EV). Considering the user perspectives, current and potential EV users were interviewed in two different surveys about optimal fast-charging locations depending on travel purposes and relevant location criteria. The obtained results show that customers prefer to rather charge at origins and destinations than during the trip. For longer distances, charging locations on axes with attractive points of interest are also considered as optimal. From the business model point of view, fast-charging stations at destinations are controversial. The expensive infrastructure and the therefore needed large number of charging sessions are in conflict with the comparatively time consuming stay.


Author(s):  
A R Chaudhari ◽  
R H Thring

This paper presents the data recorded from two G-Wiz Reva electric vehicles (EVs) over a period of two years and approximately 8000 km on each vehicle. The analysis of the vehicle data demonstrates that the range of the vehicle obtained for a certain state-of-charge (SOC) drop was not consistent. The results show that the main factor affecting the available range was irregular vehicle usage. The recharge energy consumption patterns of the vehicle were identified and it was demonstrated that infrequent vehicle usage increased energy consumed by the vehicle. A maximum range of 66.8 km was achieved when the vehicle was regularly used, but this fell to 42.8 km when it was infrequently used. The energy economy when the vehicle was regularly used was 8.3 km/kWh. Additionally, the analysis results identify the need to determine discharge rate of the vehicle batteries to determine the precise effects on the available range and energy consumption of the vehicle.


Author(s):  
A. J. Jara ◽  
Y. Bocchi ◽  
D. Fernandez ◽  
G. Molina ◽  
A. Gomez

Smart Cities requires the support of context-aware and enriched semantic descriptions to support a scalable and cross-domain development of smart applications. For example, nowadays general purpose sensors such as crowd monitoring (counting people in an area), environmental information (pollution, air quality, temperature, humidity, noise) etc. can be used in multiple solutions with different objectives. For that reason, a data model that offers advanced capabilities for the description of context is required. This paper presents an overview of the available technologies for this purpose and how it is being addressed by the Open and Agile Smart Cities principles and FIWARE platform through the data models defined by the ETSI ISG Context Information Management (ETSI CIM).


Author(s):  
Vasudev S. Salunke ◽  
Santosh J. Lagad ◽  
Ravindra S. Bhagat ◽  
Nanabhau S. Kudnar

This study aims to identify geographical points of interest and tourism potential in Parner tehsil of Ahmednagar District of Maharashtra and to highlight the attractive tourist destinations and religious places in the region. To the introduced exact situation and importance of many wonderful, useful distinctive places and geographical point of interest in Parner tehsil. This paper is descriptive in nature and qualitative study based on empirical observations. This study based on primary and secondary data. All natural geographical, historical and cultural tourist centers were visited during study period. Parner tehsil is enriched of geographical, historical, and cultural tourism aspects. Suitable maps were prepared with the help of QGIS and ARC MAP software’s for the ease of tourists. Tourist attractions in the tehsil as is, natural beauty, potholes, caves, temples, ideal village, industries, festivals etc. Even though Nighoj potholes and Vadgaon Darya caves are famous geographical destinations but other places are neglected by tourism industry experts. This paper will also become much helpful for planner, tourists, historians, geographers and archeologists to access remote but well known destinations.


PLoS ONE ◽  
2021 ◽  
Vol 16 (5) ◽  
pp. e0250170
Author(s):  
Nak Won Rim ◽  
Kyoung Whan Choe ◽  
Coltan Scrivner ◽  
Marc G. Berman

Many eye-tracking data analyses rely on the Area-of-Interest (AOI) methodology, which utilizes AOIs to analyze metrics such as fixations. However, AOI-based methods have some inherent limitations including variability and subjectivity in shape, size, and location of AOIs. In this article, we propose an alternative approach to the traditional AOI dwell time analysis: Weighted Sum Durations (WSD). This approach decreases the subjectivity of AOI definitions by using Points-of-Interest (POI) while maintaining interpretability. In WSD, the durations of fixations toward each POI is weighted by the distance from the POI and summed together to generate a metric comparable to AOI dwell time. To validate WSD, we reanalyzed data from a previously published eye-tracking study (n = 90). The re-analysis replicated the original findings that people gaze less towards faces and more toward points of contact when viewing violent social interactions.


2019 ◽  
Vol 24 (1) ◽  
pp. 93-98
Author(s):  
Ryan L. Sharp ◽  
Ted T. Cable ◽  
Aubrey Burns

This paper presents the results of the application of GPS Visitor Tracking (GVT) to evaluate visitor movements through a heritage site. This method provides temporal and spatial distribution and “heat maps” that depict visitor movements through the site. Documenting these visitor movements indicates to interpreters where to concentrate interpretive efforts and identifies opportunities to strategically encourage visitation to less visited areas of the site. The research team approached 117 travel parties and 106 elected to participate in the study, yielding a 90.6% response rate. Analysis revealed that visitors typically travel in a clockwise direction once they entered the park, stopping at a point of interest then proceeding to the visitor center. However, the density maps revealed that other points of interest were less visited. This information about temporal and spatial distribution of visitors can provide information for creating interpretive programs that people may engage with at the park.


Sign in / Sign up

Export Citation Format

Share Document