This work proposes an implicit interaction approach to ease implementing basic car-related tasks on a smartphone application. Many car drivers use apps on their smartphones to get support in typical tasks related to car usage, yet some of the available apps have a poor user experience because they require the user's attention, causing a distraction while driving. In addition, they often rely on users inputting relevant data repetitively. Implicit interaction is a possible solution to improve the user experience of car-related interfaces. Basic user tasks for many car applications are (i) reporting parking the car in a specific position, (ii) declaring that the user will soon free a parking spot, and (iii) that a new trip with the car has begun (thus, that a parking spot became free). The proposed context-aware interaction approach to executing these tasks is described together with its implementation in an application that leverages the smartphone's sensing capability of users' locations and motion activities and merges them to infer parking and unparking events. CCS CONCEPTS• Human-centered computing → User interface design; Interaction techniques.

No abstract

Implicit interaction is a possible approach to improve the user experience of smartphone apps in car-related environments. Indeed, it can enhance safety and avoids unnecessary and repetitive interactions on the user's part.This demo paper presents a smartphone app based on an implicit interaction approach to detect when the user enters and exits their vehicle automatically. We describe the app interface and usage, and how we plan to demonstrate its performances during the conference demo session. CCS CONCEPTS• Human-centered computing → User interface design; Interaction techniques.

No abstract

Cruising-for-parking in an urban area is a time-consuming and frustrating activity. We present four machine learning-based models to predict the parking availability of street segments in an urban area on a three-level scale, which navigator and smart-parking apps can exploit to ease and reduce the cruising phase. The models were trained with data generated by a cruising-for-parking simulator that we developed, replicating four parking behavior types (workers, residents, buyers, and visitors). The generated data is comparable to that collectible with smartphones’ sensors. We simulated 40 users moving for 200 weeks in the city area of San Giovanni in Rome. We collected information about users’ parking, unparking, and cruising actions over considered road segments at different time slots. Once a significant amount of trips were collected, we extracted ten features for each road segment at a given time slot. With the obtained dataset, which contained 761 samples, we trained and compared four supervised machine learning models that receive the history of a segment and, in return, classify the Parking Availability Level of the segment as Green, Yellow or Red. The four models were further evaluated in a different city area, San Lorenzo, and obtained very accurate results. We can predict parking availability with an accuracy above 97% for all the street segments where we collected 30 or more user actions, confirming the robustness of the simulator in generating synthetic cruising-for-parking data and the suitability of designing a Parking Availability Classifier (PAC) based on data collectible by smartphones.