Location Prediction Problem Research Articles

An autonomous location prediction model for maritime transport applications: a case study of Persian Gulf

ABSTRACT In this paper, a machine-learning-based location prediction model for maritime transport applications is proposed. In the proposed model, only environmental parameters are used as the input of the model, which makes the model autonomous. Meaning that the proposed model does not require information from any source other than onboard sensors. The Persian Gulf is used as the test case in this study. The sea depth, magnetic field intensity, and gravitational field intensity are three input features of the proposed model, and the corresponding coordination are the output. In the proposed methodology, the problem of location prediction is formulated as a regression problem and the above three parameters are used to train the main regression models. In this paper, two methods are used as the baseline, artificial neural networks (ANN) and support vector regression. The simulation results illustrate the high accuracy and good performance of the ANN in location prediction tasks.

When and Where to Go Next: Deep Learning Framework for Modeling Drivers’ Behaviors Using Automatic Vehicle Identification Data

In recent years, automatic vehicle identification (AVI) systems have rapidly developed in many countries, which provides an excellent opportunity to understand drivers’ mobility patterns in urban road networks. Few efforts have been devoted to fully utilizing the AVI data to address the prediction issue in behaviors modeling. This paper proposes a deep learning (DL) framework driven by AVI data to model drivers’ behaviors and further incorporate travel time prediction in the next location prediction problem. Specifically, DeepWalk encoder and DeepWalk + Time long short-term memory (DT-LSTM) were proposed to capture the spatial and temporal correlations simultaneously. By learning the spatial relationship between the sensors from the historical trajectories, the DeepWalk encoder converted the sensors into low-dimensional numerical vectors essential for DL. As a vector form, the spatial relationship of the sensor can be adequately measured. Besides, a new long short-term memory (LSTM) variant, DT-LSTM, was designed to memorize drivers’ short-term and long-term interests, respectively. By adding additional time gates, DT-LSTM facilities the location and travel time consistency in the trajectories sequences with different time intervals. Experimental results demonstrated the effectiveness of the model, which achieved the state-of-the-art performance (SOTA) compared with other benchmark methods, with the Acc-1 of 82%, Acc-5 of 95%, and MAPE of 17%.

Origin-Aware Location Prediction Based on Historical Vehicle Trajectories

Next location prediction is of great importance for many location-based applications and provides essential intelligence to various businesses. In previous studies, a common approach to next location prediction is to learn the sequential transitions with massive historical trajectories based on conditional probability. Nevertheless, due to the time and space complexity, these methods (e.g., Markov models) only utilize the just passed locations to predict next locations, neglecting earlier passed locations in the trajectory. In this work, we seek to enhance the prediction performance by incorporating the travel time from all the passed locations in the query trajectory to each candidate next location. To this end, we propose a novel prediction method, namely the Travel Time Difference Model, which exploits the difference between the shortest travel time and the actual travel time to predict next locations. Moreover, we integrate the Travel Time Difference Model with a Sequential and Temporal Predictor to yield a joint model. The joint prediction model integrates local sequential transitions, temporal regularity, and global travel time information in the trajectory for the next location prediction problem. We have conducted extensive experiments on two real-world datasets: the vehicle passage record data and the taxi trajectory data. The experimental results demonstrate significant improvements in prediction accuracy over baseline methods.

Predictive online 3D target tracking with population-based generative networks for image-guided radiotherapy.

Respiratory motion of thoracic organs poses a severe challenge for the administration of image-guided radiotherapy treatments. Providing online and up-to-date volumetric information during free breathing can improve target tracking, ultimately increasing treatment efficiency and reducing toxicity to surrounding healthy tissue. In this work, a novel population-based generative network is proposed to address the problem of 3D target location prediction from 2D image-based surrogates during radiotherapy, thus enabling out-of-plane tracking of treatment targets using images acquired in real time. The proposed model is trained to simultaneously create a low-dimensional manifold representation of 3D non-rigid deformations and to predict, ahead of time, the motion of the treatment target. The predictive capabilities of the model allow correcting target location errors that can arise due to system latency, using only a baseline volume of the patient anatomy. Importantly, the method does not require supervised information such as ground-truth registration fields, organ segmentation, or anatomical landmarks. The proposed architecture was evaluated on both free-breathing 4D MRI and ultrasound datasets. Potential challenges present in a realistic therapy, like different acquisition protocols, were taken into account by using an independent hold-out test set. Our approach enables 3D target tracking from single-view slices with a mean landmark error of 1.8mm, 2.4mm and 5.2mm in volunteer MRI, patient MRI and US datasets, respectively, without requiring any prior subject-specific 4D acquisition. This model presents several advantages over state-of-the-art approaches. Namely, it benefits from an explainable latent space with explicit respiratory phase discrimination. Thanks to the strong generalization capabilities of neural networks, it does not require establishing inter-subject correspondences. Once trained, it can be quickly deployed with an inference time of only 8ms. The results show the capability of the network to predict future anatomical changes and track tumors in real time, yielding statistically significant improvements over related methods.

Joint prediction of next location and travel time from urban vehicle trajectories using long short-term memory neural networks

This paper aims to incorporate travel time prediction in the next location prediction problem to enable the prediction of the city-wide movement trajectory of an individual vehicle by considering both where the vehicle will go next and when it will arrive. We propose two deep learning models based on long short-term memory (LSTM) neural networks with self-attention mechanism—namely, hybrid LSTM and sequential LSTM. These models capture patterns in location and time sequences in trajectory data and their dependencies to predict next locations and travel times simultaneously. Using Bluetooth vehicle trajectory data from Brisbane, Australia, we compare the prediction performance of the proposed models with several existing approaches including hidden Markov model and other LSTM-based models. The results show that the proposed models produce higher prediction accuracy for both location and time prediction tasks, with the sequential LSTM yielding the best performance. Compared to the conventional next location prediction problem, which considers location sequences only without travel time consideration, the study finds that jointly modelling location and travel time sequences actually improves the next location prediction performance itself, potentially because travel time observations capture the information on traffic conditions in the network, which may affect drivers’ location choices. We demonstrate an application of the proposed models in network traffic management, where important locations can be identified to mitigate congestion in a hot-spot by predicting where vehicles come from and go next in an urban road network.

Where to go? Predicting next location in IoT environment

Next location prediction has aroused great interests in the era of internet of things (IoT). With the ubiquitous deployment of sensor devices, e.g., GPS and Wi-Fi, IoT environment 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 consider the problem of next location prediction in IoT environment via a session-based manner. We suggest that user’s future intention in each session can be better inferred for more accurate prediction if patterns hidden inside both trajectory and signal strength sequences collected from IoT devices can be jointly modeled, which however existing state-of-the-art methods have rarely addressed. To this end, we propose a trajectory and sIgnal sequence (TSIS) model, where the trajectory transition 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 dynamics in the multivariate signal strength sequence. Moreover, we adapt gated graph neural networks (gated GNNs) on location transition graphs to explicitly model the transition patterns of trajectories. Finally, both the low-dimensional representations 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 compared with other competitive baselines.

End-to-End Neural Matching for Semantic Location Prediction of Tweets

The impressive increasing availability of social media posts has given rise to considerable research challenges. This article is concerned with the problem of semantic location prediction of geotagged tweets. The underlying task is to associate to a social media post, the focal spatial object, if any (e.g., Place Of Interest POI), it topically focuses on. Although relevant for a number of applications such as POI recommendation, this problem has not so far received the attention it deserves. In previous work, the problem has mainly been tackled by means of language models that rely on costly probability estimation of word relevance across spatial regions. We propose the Spatially-aware Geotext Matching (SGM) model, which relies on a neural network learning framework. The model combines exact word-word-local interaction matching signals with semantic global tweet-POI interaction matching signals. The local interactions are built over kernel spatial word distributions that allow revealing spatially driven word pair similarity patterns. The global interactions consider the strength of the interaction between the tweet and the POI from both the spatial and semantic perspectives. Experimental results on two real-world datasets demonstrate the effectiveness of our proposed SGM model compared to state-of-the-art baselines including language models and traditional neural interaction-based models.

OMuLeT: Online Multi-Lead Time Location Prediction for Hurricane Trajectory Forecasting

Hurricanes are powerful tropical cyclones with sustained wind speeds ranging from at least 74 mph (for category 1 storms) to more than 157 mph (for category 5 storms). Accurate prediction of the storm tracks is essential for hurricane preparedness and mitigation of storm impacts. In this paper, we cast the hurricane trajectory forecasting task as an online multi-lead time location prediction problem and present a framework called OMuLeT to improve path prediction by combining the 6-hourly and 12-hourly forecasts generated from an ensemble of dynamical (physical) hurricane models. OMuLeT employs an online learning with restart strategy to incrementally update the weights of the ensemble model combination as new observation data become available. It can also handle the varying dynamical models available for predicting the trajectories of different hurricanes. Experimental results using the Atlantic and Eastern Pacific hurricane data showed that OMuLeT significantly outperforms various baseline methods, including the official forecasts produced by the U.S. National Hurricane Center (NHC), by more than 10% in terms of its 48-hour lead time forecasts.

Location prediction in large-scale social networks: an in-depth benchmarking study

Location details of social users are important in diverse applications ranging from news recommendation systems to disaster management. However, user location is not easy to obtain from social networks because many users do not bother to provide this information or decline to do so due to privacy concerns. Thus, it is useful to estimate user locations from implicit information in the network. For this purpose, many location prediction models have been proposed that exploit different network features. Unfortunately, these models have not been benchmarked on common datasets using standard metrics. We fill this gap and provide an in-depth empirical comparison of eight representative prediction models using five metrics on four real-world large-scale datasets, namely Twitter, Gowalla, Brightkite, and Foursquare. We formulate a generalized procedure-oriented location prediction framework which allows us to evaluate and compare the prediction models systematically and thoroughly under extensive experimental settings. Based on our results, we perform a detailed analysis of the merits and limitations of the models providing significant insights into the location prediction problem.

Venue2Vec: An Efficient Embedding Model for Fine-Grained User Location Prediction in Geo-Social Networks

Geo-Social Networks (GSN) significantly improve location-aware capability of services by offering geo-located content based on the huge volumes of data generated in the GSN. The problem of user location prediction based on user-generated data in GSN has been extensively studied. However, existing studies are either concerning predicting users’ next check-in location or predicting their future check-in location at a given time with coarse granularity. A unified model that can predict both scenarios with fine granularity is quite rare. Also, due to the heterogeneity of multiple factors associated with both locations and users, how to efficiently incorporate these information still remains challenging. Inspired by the recent success of word embedding in natural language processing, in this paper, we propose a novel embedding model called Venue2Vec which automatically incorporates temporal-spatial context, semantic information, and sequential relations for fine-grained user location prediction. Locations of the same type, and those that are geographically close or often visited successively by users will be situated closer within the embedding space. Based on our proposed Venue2Vec model, we design techniques that allow for predicting a user’s next check-in location, and also their future check-in location at a given time. We conduct experiments on three real-world GSN datasets to verify the performance of the proposed model. Experimental results on both tasks show that Venue2Vec model outperforms several state-of-the-art models on various evaluation metrics. Furthermore, we show how the Venue2Vec model can be more time-efficient due to being parallelizable.

Efficient Parcel Delivery by Predicting Customers’ Locations*

ABSTRACTAn important aspect of the growing e‐commerce sector involves the delivery of tangible goods to the end customer, the so‐called last mile. This final stage of the logistics chain remains highly inefficient due to the problem of failed deliveries. To address this problem, delivery service providers can apply data science to determine the optimal, customer‐centered location and time window for handover. In this article, we present a three‐step approach for location prediction, based on mobile location data, in order to support delivery planning. The first step is identifying a user's locations of interest through density‐based clustering. Next, the semantics (home or work) of the user's locations of interest are discovered, based on temporal assumptions. Finally, we predict future locations with a decision tree model that is trained on each user's historical location data. Though the problem of location prediction is not new, this work is the first to apply it to the field of parcel delivery with its corresponding implications. Moreover, we provide a novel and detailed evaluation on real‐world data from a parcel delivery service. The promising results indicate that our approach has the potential to help delivery service providers to gain insights into their customers’ optimal delivery time and location in order to support delivery planning. Eventually this will decrease last‐mile delivery costs and boost customer satisfaction.

PMLPR: A novel method for predicting subcellular localization based on recommender systems

The importance of protein subcellular localization problem is due to the importance of protein’s functions in different cell parts. Moreover, prediction of subcellular locations helps to identify the potential molecular targets for drugs and has an important role in genome annotation. Most of the existing prediction methods assign only one location for each protein. But, since some proteins move between different subcellular locations, they can have multiple locations. In recent years, some multiple location predictors have been introduced. However, their performances are not accurate enough and there is much room for improvement. In this paper, we introduced a method, PMLPR, to predict locations for a protein. PMLPR predicts a list of locations for each protein based on recommender systems and it can properly overcome the multiple location prediction problem. For evaluating the performance of PMLPR, we considered six datasets RAT, FLY, HUMAN, Du et al., DBMLoc and Höglund. The performance of this algorithm is compared with six state-of-the-art algorithms, YLoc, WOLF-PSORT, prediction channel, MDLoc, Du et al. and MultiLoc2-HighRes. The results indicate that our proposed method is significantly superior on RAT and Fly proteins, and decent on HUMAN proteins. Moreover, on the datasets introduced by Du et al., DBMLoc and Höglund, PMLPR has comparable results. For the case study, we applied the algorithms on 8 proteins which are important in cancer research. The results of comparison with other methods indicate the efficiency of PMLPR.

A Fast Vehicle Detection Method for Road Monitoring

To address the issue that current traffic monitoring system needs to automatically detect the objects on the road, a fast vehicle detection method was proposed. Applied the YOLO framework, this paper considered the vehicle detection as a regression problem of vehicle location prediction and classification prediction. Under the precondition of guaranteeing accuracy, the structure of convolution neural network (CNN) is optimized to speed up the detection. The vehicle model CarNet was trained on a dataset containing a large number of road vehicle sample images. The experimental results show that with this method vehicle in video can be detected quickly even on a computer without GPU. The method also shows good robustness and high precision.

Personalized location prediction for group travellers from spatial–temporal trajectories

In recent years, research on location predictions by mining trajectories of users has attracted a lot of attentions. Existing studies on this topic mostly focus on individual movements, considering the trajectories as solo movements. However, a user usually does not visit locations just for the personal interest. The preference of a travel group has significant impacts on the places they visit. In this paper, we propose a novel personalized location prediction approach which further takes into account users’ travel group type. To achieve this goal, we propose a new group pattern discovery approach to extract the travel groups from spatial–temporal trajectories of users. Type of the discovered groups, then, are identified through utilizing the profile information of the group members. The core idea underlying our proposal is the discovery of significant movement patterns of users to capture frequent movements by considering the group types. Finally, the problem of location prediction is formulated as an estimation of the probability of a given user visiting a given location based on his/her current movement and his/her group type. To the best of our knowledge, this is the first work on location prediction based on trajectory pattern mining that investigates the influence of travel group type. By means of a comprehensive evaluation using various datasets, we show that our proposed location prediction framework achieves significantly higher performance than previous location prediction methods.

Large-Scale Location Prediction for Web Pages

Location information of Web pages plays an important role in location-sensitive tasks such as Web search ranking for location-sensitive queries. However, such information is usually ambiguous, incomplete, or even missing, which raises the problem of location prediction for Web pages. Meanwhile, Web pages are massive and often noisy, which pose challenges to the majority of existing algorithms for location prediction. In this paper, we propose a novel and scalable location prediction framework for Web pages based on the query-URL click graph. In particular, we introduce a concept of term location vectors to capture location distributions for all terms and develop an automatic approach to learn the importance of each term location vector for location prediction. Empirical results on a large URL set demonstrate that the proposed framework significantly improves the location prediction accuracy comparing with various representative baselines. We further provide a principled way to incorporate the proposed framework into the search ranking task and experimental results on a commercial search engine show that the proposed method remarkably boosts the ranking performance for location-sensitive queries.

Temporal Markov Chain Location Prediction

With the rapid development of social mobile networks, it is highly desirable to be able to accurately predict the next check-in location. Most methods of social mobile networks are mainly based on vast user check-in historic records to analyze the feature of users’ behaviors. The Markov Model is a frequently used method in location prediction problem. However, due to the diversity and sparsity of the social mobile network check-in data, tradition Markov Model location prediction, cannot take full advantages of potential information existed in plentiful check-in data. Then, we propose a prediction algorithm, temporal Markov Model (TMM) based on time characteristic. This algorithm relies on Markov Model to make a primary prediction of user checkin position. Then, utilizing the temporal character modifies the forecast result. We have conducted extensive experiments in two real datasets, and the results demonstrate the superiority of TMM over traditional Markov Models.

Predicting the Next Location: A Recurrent Model with Spatial and Temporal Contexts

Spatial and temporal contextual information plays a key role for analyzing user behaviors, and is helpful for predicting where he or she will go next. With the growing ability of collecting information, more and more temporal and spatial contextual information is collected in systems, and the location prediction problem becomes crucial and feasible. Some works have been proposed to address this problem, but they all have their limitations. Factorizing Personalized Markov Chain (FPMC) is constructed based on a strong independence assumption among different factors, which limits its performance. Tensor Factorization (TF) faces the cold start problem in predicting future actions. Recurrent Neural Networks (RNN) model shows promising performance comparing with PFMC and TF, but all these methods have problem in modeling continuous time interval and geographical distance. In this paper, we extend RNN and propose a novel method called Spatial Temporal Recurrent Neural Networks (ST-RNN). ST-RNN can model local temporal and spatial contexts in each layer with time-specific transition matrices for different time intervals and distance-specific transition matrices for different geographical distances. Experimental results show that the proposed ST-RNN model yields significant improvements over the competitive compared methods on two typical datasets, i.e., Global Terrorism Database (GTD) and Gowalla dataset.

Random Walk Based Location Prediction in Wireless Sensor Networks

With the development of wireless sensor network (WSN) technologies, WSNs have been applied in many areas. In all WSN technologies, localization is a crucial problem. Traditional localization approaches in WSNs mainly focus on calculating the current location of sensor nodes or mobile objects. In this paper, we study the problem of future location prediction in WSNs. We assume the location histories of mobile objects as a rating matrix and then use a random walk based social recommender algorithm to predict the future locations of mobile objects. Experiments show that the proposed algorithm has better prediction accuracy and can solve the rating matrix sparsity problem more effectively than related works.

Efficient Location Prediction in Mobile Cellular Networks

Mobile context-aware applications are capable of predicting the context of the user in order to operate pro-actively and provide advanced services. We propose an efficient spatial context classifier and a short-term predictor for the future location of a mobile user in cellular networks. We introduce different variants of the considered location predictor dealing with location (cell) identifiers and directions. Symbolic location classification is treated as a supervised learning problem. We evaluate the prediction efficiency and accuracy of the proposed predictors through synthetic and real-world traces and compare our solution with existing algorithms for location prediction. Our findings are very promising for the location prediction problem and the adoption of proactive context-aware applications and services.