STF-RNN: Space Time Features-based Recurrent Neural Network for predicting people next location

Empowering A* Search Algorithms with Neural Networks for Personalized Route Recommendation

“…With the revival of deep learning, it sheds light on the development of more effective PRR models using neural networks. Especially, sequential neural models, i.e., Recurrent Neural Networks (RNN), have been widely used for modeling sequential trajectory data [1,31,34]. However, to our knowledge, these models mainly focus on one-step or short-term location prediction, which may not be suitable for the PRR task.…”

Thirty Years of Machine Learning: The Road to Pareto-Optimal Wireless Networks

“…Moreover, Xu et al [346] proposed a deep reinforcement learning framework for power-efficient resource allocation in CRANs, which optimized the expected and cumulative long term power consumption, including the transmit power consumption, the sleep/active transition power consumption as well as the RRU's power consumption. A twostep deep reinforcement learning aided decision making scheme was conceived, where the learning agent first decides on activating/deactivating the sleeping mode of [312] channel estimation DNN learn nonlinear distortion, interference and frequency selectivity of wireless channels [321] modulation classification RNN capture amplitude and phase information without expert knowledge [322] signal detection DNN transmit signal detection from noisy and corrupted signals without underlying CSI [313] interference identification CNN learn features through self-optimization during the GPU based training process [324] PHY representation DNN represent simple system having one transmitter and receiver without accurate CSI [325] PHY representation DNN represent single user MIMO system relying on DNN aided auto-encoder [326] software-defined radio DNN be capable of easing the current restriction on short block lengths [327] traffic prediction DNN deep auto-encoder and LSTM for modeling spatial and temporal features [328] packet routing DNN traffic routing scheme with little signal overhead, large throughput and small delay [329] traffic control CNN consider previous network abnormalities, lower average delay and packet loss rate [330] traffic offloading DNN integrate both DNN structure and edge computing technique into multimedia IoT [331] power control DNN an almost-real-time power control algorithm in interference-limited wireless networks [332] network security DBN a real-time detection of malicious false data injection attack in smart grid [314]- [318] indoor localization DNN device-free wireless localization and recognition by learning from ambient wireless signals [320] mobility prediction CNN learn human mobility pattern relying on analyzing continuous mobile data stream [334] mobility prediction RNN integrate spatial feature from GPS and temporal feature from associated time stamps [335] transportation mode RNN predict both human mobility and transportation mode for large-scale transport networks [337] activity prediction RNN characterize primary users' activity in CR with different traffic distribution [338] traffic prediction CNN traffic modeling and prediction based on a convo...…”

“…With regard to learning from users or devices, Ouyang et al [320] conceived a CNN-aided online learning architecture for understanding human mobility patterns relying on analyzing continuous mobile data streams. Al-Molegi et al [334] integrated both the spatial features gleaned from GPS data and the temporal features extracted from the associated time stamps for predicting human mobility based on a RNN. Moreover, Song et al [335] proposed an intelligent deep LSTM RNN based system for predicting both human mobility and the specific transportation mode in a large-scale transportation network, which was beneficial in terms of providing accurate traffic control for intelligent transportation systems (ITS).…”

Vehicle Location Prediction Based on Spatiotemporal Feature Transformation and Hybrid LSTM Neural Network

“…This method applies the spatiotemporal features, but ignores the dependence problem of long trajectory sequence, which will lead to the decrease of prediction accuracy. Molegi et al [29] proposed a location prediction method, called spatiotemporal features-based recurrent neural network (STF-RNN). This method is to input the spatiotemporal features directly into the network, and extract the internal representation of the spatiotemporal features through the network self-learning.…”

“…Information 2020, 11, 84 2 of 23 mining [17][18][19][20][21][22][23][24][25][26], and the location prediction methods based on recurrent neural network (RNN) [27][28][29]. The location prediction methods based on the MC model are to calculate the probability of the next location of a moving object by establishing the transfer-probability matrix of the moving object.…”