Abstract-Tracking congestion throughout the network road is a critical component of Intelligent transportation network management systems. Understanding how the traffic flows and short-term prediction of congestion occurrence due to rush-hour or incidents can be beneficial to such systems to effectively manage and direct the traffic to the most appropriate detours. Many of the current traffic flow prediction systems are designed by utilizing a central processing component where the prediction is carried out through aggregation of the information gathered from all measuring stations. However, centralized systems are not scalable and fail provide real-time feedback to the system whereas in a decentralized scheme, each node is responsible to predict its own short-term congestion based on the local current measurements in neighboring nodes.We propose a decentralized deep learning-based method where each node accurately predicts its own congestion state in realtime based on the congestion state of the neighboring stations. Moreover, historical data from the deployment site is not required, which makes the proposed method more suitable for newly installed stations. In order to achieve higher performance, we introduce a regularized euclidean loss function that favors high congestion samples over low congestion samples to avoid the impact of the unbalanced training dataset. A novel dataset for this purpose is designed based on the traffic data obtained from traffic control stations in northern California. Extensive experiments conducted on the designed benchmark reflect a successful congestion prediction.
Spatio-temporal data serves as a foundation for most location-based applications nowadays. To handle spatio-temporal data, an appropriate methodology needs to be properly followed, in which space and time dimensions of data must be taken into account 'altogether'unlike spatial (or temporal) data management tools which consider space (or time) separately and assumes no dependency on one another. In this paper, we conducted a survey on spatial, temporal, and spatio-temporal database research. Additionally, to use an original example to illustrate how today's technologies can be used to handle spatio-temporal data and applications, we categorize the current technologies into two groups: (1) traditional, mainstay tools (e.g. SQL ecosystem) and (2) emerging, data-intensive tools (e.g. deep learning). Specifically, in the first group, we use our spatio-temporal application based on SQL system, 'hydrological rainstorm analysis', as an original example showing how analysis and mining tasks can be performed on the conceptual storm stored in a spatio-temporal RDB. In the second group, we use our spatio-temporal application based on deep learning, 'users' future locations prediction based on historical trajectory GPS data using hyper optimized ANNs and LSTMs', as an original example showing how deep learning models can be applied to spatio-temporal data.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.