A Deep Learning Spatiotemporal Prediction Framework for Mobile Crowdsourced Services

Mobile Networks and Applications - This papers presents a deep learning-based framework to predict crowdsourced service availability spatially and temporally. A novel two-stage prediction model is...     

Visual interaction using an iconic system

IBS (Icon Based System) is an experimental graphical query language based on icons. It demonstrates the capabilities of a workstation environment by integrating the aspects of database programming in one graphical setting. Namely, it allows direct manipulation of objects dealing with pictorial data as well as alphanumeric data. We point out the interaction techniques between users and database systems. Then we describe the design of IBS, illustrate its features, and show how queries are formulated in a medical context.     

Spatiotemporal data mining: a survey on challenges and open problems

Spatiotemporal data mining (STDM) discovers useful patterns from the dynamic interplay between space and time. Several available surveys capture STDM advances and report a wealth of important progress in this field. However, STDM challenges and problems are not thoroughly discussed and presented in articles of their own. We attempt to fill this gap by providing a comprehensive literature survey on state-of-the-art advances in STDM. We describe the challenging issues and their causes and open gaps of multiple STDM directions and aspects. Specifically, we investigate the challenging issues in regards to spatiotemporal relationships, interdisciplinarity, discretisation, and data characteristics. Moreover, we discuss the limitations in the literature and open research problems related to spatiotemporal data representations, modelling and visualisation, and comprehensiveness of approaches. We explain issues related to STDM tasks of classification, clustering, hotspot detection, association and pattern mining, outlier detection, visualisation, visual analytics, and computer vision tasks. We also highlight STDM issues related to multiple applications including crime and public safety, traffic and transportation, earth and environment monitoring, epidemiology, social media, and Internet of Things.

     

Detecting deception attacks in cyber-physical linear parameter varying systems with packet loss

The increased connectivity of cyber-physical systems (CPS) to enterprise networks raises challenging security concerns. Detecting attacks on CPS is a vital step to improving their security. Most of the existing attack detectors are for CPS with linear dynamics. In this study, an investigation is made for designing a detector of deception attacks in a cyber-physical linear parameter varying (LPV) system in the presence of packet loss. A model-based attack detector is designed to detect deception attacks on output measurements, actuators, or schedule variables. With an unreliable network, the LPV attack detector enhances detection capacity and attenuates disturbances on the detector module to improve detection accuracy. During communication, packet loss results in network unreliability, which is modeled by the Bernoulli process. Stochastic stability is used to determine LPV attack detector parameters. A residual signal is built by comparing the detector's output and the actual sensor measurement and provides the deception attack's essential data. However, the packet loss causes some impulse signals in the residual signal, resulting in false alarms. Therefore, the detector module is equipped with a median filter to suppress packet loss's effect on evaluating the residual signal. Tests and validations of the proposed approach are performed on a two-tank system and a continuous stirred tank reactor. According to evaluation results conducted on two testbeds, the proposed method accurately detects deception attacks even when there is packet loss.