Kaixu Liu

Personal Mobility Service System in Urban Areas: The IRMA Project

We present an ongoing research project, namely Integrated Real-time Mobility Assistant (IRMA). IRMA is a software system that targets the personal mobility in a near future scenario, oriented to green, shared and public transports. IRMA aims to be an extensible, easy-to-implement and sustainable modular platform based on the combined use of multiple information sources (crowd, open, social, and sensor data) and on array of value propositions, each serving a class of stakeholders, which include municipality, users, transport providers. Hence, IRMA supports users in the entire lifecycle of mobility, and municipalities and transport providers in the whole cycle of mobility management. IRMA is deployed on both smartphone and web, and is built on a hierarchy of re-usable web services, that are based on SOA/EDA (Service Oriented Architecture / Event Driven Architecture).

CITY FEED: A Pilot System of Citizen-Sourcing for City Issue Management

Crowdsourcing implies user collaboration and engagement, which fosters a renewal of city governance processes. In this article, we address a subset of crowdsourcing, named citizen-sourcing, where citizens interact with authorities collaboratively and actively. Many systems have experimented citizen-sourcing in city governance processes; however, their maturity levels are mixed. In order to focus on the service maturity, we introduce a city service maturity framework that contains five levels of service support and two levels of information integration. As an example, we introduce CITY FEED, which implements citizen-sourcing in city issue management process. In order to support such process, CITY FEED supports all levels of the maturity framework (publishing, transacting, interacting, collaborating, and evaluating) and integrates related information relationally and heterogeneously. In order to integrate heterogeneous information, it implements a threefold feed deduplication mechanism based on the geographic, text semantic, and image similarities of feeds. Currently, CITY FEED is in a pilot stage.

Delivering Real-Time Information Services on Public Transit: A Framework

Public transit is described by a wide range of data, which include sensor data, open data, and social network data. Data come in large real-time streams, and are heterogeneous. How to integrate such data in real time? We propose MOBility ANAlyzer (MOBANA), a distributed stream-based framework. MOBANA deals with the integration of heterogeneous information, processing efficiency, and redundancy reduction. As far as integration is concerned, MOBANA integrates data at different layers, and converts them into exchangeable data formats. Specifically, to integrate feed information, MOBANA uses an improved incremental text classifier, based on Kullback Leibler distance. As far as efficiency is concerned, MOBANA is implemented by distributed stream processing engine and distributed messaging system, which enable scalable, efficient, and reliable real-time processing. Specifically, within the transport domain, MOBANA identifies the real-time position of vehicles by an as-needed adjustment of planned position against the real-time position, thus dropping network load. As far as redundancy is concerned, MOBANA filters tweets through a three-fold similarity analysis, which encompasses geo-location, text, and image. In addition, MOBANA is a complete framework, which has been tested as a pilot with real data in the city of Pavia, Italy.

XYZ Indoor Navigation through Augmented Reality: A Research in Progress.

We present an overall framework of services for indoor navigation, which includes Indoor Mapping, Indoor Positioning, Path Planning, and En-route Assistance. Within such framework we focus on an augmented reality (AR) solution for en-route assistance. AR assists the user walking in a multi-floor building by displaying a directional arrow under a camera view, thus freeing the user from knowing his/her position. Our AR solution relies on geomagnetic positioning and north-oriented space coordinates transformation. Therefore, it can work without infrastructure and without relying on GPS. The AR visual interface and the integration with magnetic positioning is the main novelty of our solution, which has been validated by experiments and shows a good performance.

Multi-floor Indoor Navigation with Geomagnetic Field Positioning and Ant Colony Optimization Algorithm

We here illustrate a new indoor navigation system. It is an outcome of creativity, which merges an imaginative scenario and new technologies. The system intends to guide a person in unknown building by relying on technologies which do not depend on infrastructures. The system includes two key components, namely positioning and path planning. Positioning is based on geomagnetic fields, and it overcomes the several limits of WIFI and Bluetooth, etc. Path planning is based on a new and optimized Ant Colony algorithm, called Ant Colony Optimization (ACO), which offers better performances than the classic A* algorithms. The paper illustrates the logic and the architecture of the system, and also presents experimental results.

A Threefold Similarity Analysis of Crowdsourcing Feeds

Crowdsourcing is a valuable social sensing for the smarter city. We present an approach for classifying crowd sourced feeds from a threefold point of view, namely image, text, and geography. The main idea is to extract feeds within a specific geographic range, and then analyze similarity of image color and text semantic. The approach enables to identify feeds that report the same issue, hence filtering redundant information. Based on proved methods and algorithms, such approach has been implemented in a software application, called CITY FEED, that is used by the Municipality of Pavia.

Overview of Smart White Canes: Connected Smart Cane from Front End to Back End

There are 285 million visually impaired people (VIP) worldwide, among whom 39 million are blind (WHO 2014).

Wi-Fi-Aided Magnetic Field Positioning with Floor Estimation in Indoor Multi-Floor Navigation Services

Our paper addresses Indoor Navigation, i.e., the navigation in the three-dimensional space of buildings. Indoor navigation lifecycle is alike outdoor navigation, and it embraces Mapping, Positioning, Path Planning, and En-route Assistance. In such life cycle, positioning is, of course, a critical element. In indoor navigation, an ideal positioning should operate in the indoor three-dimensional space, and integrate sensors, magnetometer, accelerator, etc. In order to achieve this goal, we combine External Navigation System (ENS) and Inertial Navigation System (INS). In ENS, Wi-Fi signal strengths estimate the floor information, and magnetometer matches magnetic data in real time. In INS, pedestrian motion is measured by accelerator with heading, user steps and walking distance. An eXtended Particle Filtering (XPF) effectively combines both positioning measurements and user movements. The integration of Wi-Fi-aided magnetic field positioning and XPF with Dead Reckoning is the main novelty of our solution, which has been validated by experiments and shows a good performance.

An Analysis of Social Data Credibility for Services Systems in Smart Cities – Credibility Assessment and Classification of Tweets

In the “Information Age”, Smart Cities rely on a wide range of different data sources. Among them, social networks can play a big role, if information veracity is assessed. Veracity assessment has been, and is, a rather popular research field. Specifically, our work investigates the credibility of data from Twitter, an online social network and a news media, by considering not only credibility, and type, but also origin. Our analysis proceeds in four phases: Features Extraction, Features Analysis, Features Selection, and Classification. Finally, we classify whether a Tweet is credible or incredible, is rumor or spam, is generated by a human or a Bot. We use Social Media Mining and Machine Learning techniques. Our analysis reaches an overall accuracy higher than the benchmark, and it adds the origin dimension to the credibility analysis method.

MOBANA: A Distributed Stream-Based Information System for Public Transit

Public transit generates a wide range of diverse data, which include static data and high-velocity data streams from sensors. Integrating and processing this big real-time data is a challenge in developing analytical systems for public transit. We here propose MOBANA (MOBility ANAlyzer), a distributed stream-based system, which provides real-time information to a wide range of users for monitoring and analyzing the performance of public transit. To do so, MOBANA integrates the diverse data sources of public transit, and converts them into standard and exchangeable data formats. In order to manage such diverse data, we propose a layered architecture, where each layer handles a specific kind of data. MOBANA is designed to be efficient. e.g., it identifies the real time position of vehicles by adjusting planned position with real-time data as needed, thus dropping network load. MOBANA is implemented by Distributed Stream Processing Engine (DSPE) and Distributed Messaging System (DMS), which pursue scalable, efficient and reliable real-time processing and analytics. MOBANA was deployed as pilot in Pavia, and tested with real data.