Please enable JavaScript.

Coggle requires JavaScript to display documents.

Urban Computing: Concepts, Methodologies, and Applications SEPTEMBER 2014

- - - - Composed of 4 layers
        
        Data management
        
        data are well organized by some indexing structure that simultaneously incorporates spatiotemporal information and texts for supporting efﬁcient data analytics
        
        Data analytics
        
        Verify anomalies and identify differences from origin patterns
        
        Urban sensing
        
        Collect data by using sensors or devices and from the Internet (social media)
        
        Service Providing
        
        Send data to the people and deliver information for diagnosing the anomaly
      - Different tasks can be fulﬁlled by combining different data sources with different data acquisition, management, and analytics techniques from different layers of the framework.
    - - Urban sensing and data acquisition
        
        Continually probing the citywide trafﬁc is challenging.
        
        SOLUTIONS
        
        :check: Humans as a sensor
        
        CHALLENGES
        
        Energy consumption and privacy
        
        Loose-controlled and nonunifom distributed sensors
        
        We cannot control people
        
        Data-missing and sparsity problems
        
        Redundancy
        
        Unstructured, implicit, and noise data
        
        Data by users in a free format (images and text) cannot explicitly lead to the ﬁnal goal as when using traditional sensors.
        
        :red_cross: Building new sensing infrastructures
      - Computing with heterogeneous data
        
        Both effective and efﬁcient learning ability
        
        Many urban computing scenarios require instant answers.
        
        Need to aggregate data management and mining and machine-learning algorithms into a computing framework to provide both an effective and efﬁcient knowledge discovery ability
        
        traditional data management techniques are usually designed for a single modal data source
        
        advanced management methodology is still missing
        
        computing with multiple heterogeneous data is a fusion of data and algorithms
        
        Visualization
        
        The multimodal data in urban computing scenarios leads to high dimensions of views,such as spatial, temporal, and social, for a visualization
        
        When facing multiple types and huge volumes of data, seeing how exploratory visualization can provide an interactive way for people to generate new hypotheses becomes even more difﬁcult
        
        integration of instant data-mining techniques into a visualization framework is still missing in urban computing
        
        Learn mutually reinforced knowledge from heterogeneous data
        
        Advanced data analytics models can learn mutually reinforced knowledge among multiple heterogeneous data generated from different sources
        
        data-mining and machine-learning techniques
        
        equally treating features extracted from different data sources does not achieve the best performance
        
        Multiple data sources in an application leads to a high-dimension space, which aggravates the data sparsity problem
      - Hybrid systems blending the physical and virtual worlds
        
        urban computing usually integrates the data from both worlds
        
        The data is generated in the physical world and then sent back to the digital world (e.g. cloud system); the knowledge learned from the data will be used to serve users from the physical world
        
        design of such a system is much more challenging than for conventional systems that only reside in one world, as the system needs to communicate with many devices and users simultaneously and send and receive data of different formats and at different frequencies
  - - - Existing data acquisition technologies folds
        
        Passive crowd sensing
        
        leverages existing infrastructures to passively collect the data generated by crowds
        
        Participatory sensing
        
        people actively obtain the information around them and contribute their own data to formulate collective knowledge that can solve a problem, in short, humans as sensors
        
        Traditional sensing and measurement
        
        collects data through installing sensors dedicated to some applications