A Location Prediction Method Based on GA-LSTM Networks and Associated Movement Behavior Information

Due to the lack of consideration of movement behavior information other than time and location perception in current location prediction methods,the movement characteristics of trajectory data cannot be well expressed,which in turn affects the accuracy of the prediction results.First,a new trajectory data expression method by associating the movement behavior information is given.The pre-association method is used to model the movement behavior information according to the individual movement behavior features and the group movement behavior features extracted from the trajectory sequence and the region.The movement behavior features based on pre-association may not always be the best for the prediction model.Therefore,through association analysis and importance analysis,the final association feature is selected from the pre-association features.The trajectory data is input into the LSTM networks after associated features and genetic algorithm(GA)is used to optimize the combination of the length of time window and the number of hidden layer nodes.The experimental results show that compared with the original trajectory data,the trajectory data associated with the movement behavior information helps to improve the accuracy of location prediction.

SPATIAL TRAJECTORY PREDICTION OF VISUAL SERVOING

Target tracking is one typical application of visual servoing technology. It is still a difficult task to track high speed target with current visual servo system. The improvement of visual servoing scheme is strongly required. A position-based visual servo parallel system is presented for tracking target with high speed. A local Frenet frame is assigned to the sampling point of spatial trajectory. Position estimation is formed by the differential features of intrinsic geometry, and orientation estimation is formed by homogenous transformation. The time spent for searching and processing can be greatly reduced by shifting the window according to features location prediction. The simulation results have demonstrated the ability of the system to track spatial moving object.

A novel proactive soft load balancing framework for ultra dense network

A major challenge for the future wireless network is to design the self-organizing architecture.The reactive self-organizing model of traditional networks needs to be transformed into an active self-organizing network.Due to the user mobility and the coverage of small cells,the network load often becomes unbalanced,resulting in poor network performance.Mobility management has become an important issue to ensure seamless communication when users move between cells,and proactive mobility management is one of the important functions of the active Self-Organizing Network(SON).This paper proposes a proactive mobility management framework for active SON,which transforms the original reactive load balancing into a forward-aware and proactive load balancing.The proposed framework firstly uses the BART model to predict the users’temporal and spatial mobility based on a weekly cycle and then formulate the MLB optimization problem based on the soft load.Two solutions are proposed to solve the above MLB problem.The simulation results show that the proposed method can better optimize the network performance and realize intelligent mobile management for the future network.

Quantitative analysis on tectonic deformation of active rupture zones

Based on the regional GPS data of high spatial resolution, we present a method of quantitative analysis on the tectonic deformation of active rupture zones in order to predict the location of forthcoming major earthquakes. Firstly we divide the main fault area into certain deformation units, then derive the geometric deformation and relative dislocation parameters of each unit and finally estimate quantitatively the slip and strain rates in each segment of the rupture zone. Furthermore, by comparing the consistency of deformation in all segments of the whole rupture zone, we can determine the possible anomalous segments as well as their properties and amplitudes. In analyzing the eastern boundaries of Sichuan-Yunnan block with the GPS velocity data for the period of 1991-2001, we have discovered that the Mianning-Ningnan-Dongchuan segment on the Zemuhe-Xiaojiang fault zone is relatively locked and the left-lateral shear strain rate here is higher.

Predicting mobile users’behaviors and locations using dynamic Bayesian networks

This paper studies the traveling location prediction problem for detecting whether mobile users will leave their living area and where they will go.We investigate the hidden connections between users’behaviors in different locations and online social interactions.We combine dynamic Bayesian networks with a majority voting model which is based on social interaction information to estimate the users’behaviors and predict the locations.By analyzing Instagram media records,spanning a period of 3 months,we explore rarely visited locations,which are often ignored as noise in previous research.In comparison,our model,using Instagram data with two existing location prediction models,shows that(1)our location prediction is more accurate and robust in both the general location and the location outside the living area;(2)social relations are instrumental in the location prediction as social interaction information can increase the accuracy of the prediction.

Location-and Relation-Based Clustering on Privacy-Preserving Social Networks

Graph clustering has a long-standing problem in that it is difficult to identify all the groups of vertices that are cohesively connected along their internal edges but only sparsely connected along their external edges. Apart from structural information in social networks, the quality of the location-information clustering has been improved by identifying clusters in the graph that are closely connected and spatially compact. However, in real-world scenarios, the location information of some users may be unavailable for privacy reasons, which renders existing solutions ineffective. In this paper, we investigate the clustering problem of privacy-preserving social networks, and propose an algorithm that uses a prediction-and-clustering approach. First, the location of each invisible user is predicted with a probability distribution. Then, each user is iteratively assigned to different clusters. The experimental results verify the effectiveness and efficiency of our method, and our proposed algorithm exhibits high scalability on large social networks.

Where to go?Predicting next location in IoT environment

Next location prediction has aroused great inter-ests in the era of internet of things(IoT).With the ubiquitous deployment of sensor devices,e.g..GPS and Wi-Fi,loT en-vironment offers new opportunities for proactively analyzing human mobility patterns and predicting user's future visit in low cost,no matter outdoor and indoor.In this paper,we con-sider the problem of next location prediction in loT environ-ment via a session-based manner.We suggest that user's future intention in each session can be better inferred for more ac-curate prediction if patterns hidden inside both trajectory and signal strength sequences ollected from IoT devices can be jointly modeled,which however existing state-of the-art meth-ods have rarely addressed.To this end,we propose a trajectory and sIgnal sequence(TSIS)model,where the trajectory transi-tion regularities and signal temporal dynamics are jointly embedded in a neural network based model.Specifically,we employ gated recurrent unit(GRU)for capturing the temporal dy-namics in the mutivariate signal strength sequence.Moreover,we adapt gated graph neural networks(gated GNNs)on loca-tion transition graphs to explicitly model the transition patterns of trajectories.Finally,both the low-dimensional representa-tions learned from trajectory and signal sequence are jointly optimized to construct a session embedding,which is further employed to predict the next location.Extensive experiments on two real-world Wi-Fi based mobility datasets demonstrate that TSIS is effective and robust for next location prediction pompared with other competitive baselines.

Mining Object Similarity for Predicting Next Locations

Next location prediction is of great importance for many location-based applications. With the virtue of solid theoretical foundations, Markov-based approaches have gained success along this direction. In this paper, we seek to enhance the prediction performance by understanding the similarity between objects. In particular, we propose a novel method, called weighted Markov model （weighted-MM）, which exploits both the sequence of just-passed locations and the object similarity in mining the mobility patterns. To this end, we first train a Markov model for each object with its own trajectory records, and then quantify the similarities between different objects from two aspects： spatial locality similarity and trajectory similarity. Finally, we incorporate the object similarity into the Markov model by considering the similarity as the weight of the probability of reaching each possible next location, and return the top-rankings as results. We have conducted extensive experiments on a real dataset, and the results demonstrate significant improvements in prediction accuracy over existing solutions.