DeepRoute+: Modeling Couriers’ Spatial-temporal Behaviors and Decision Preferences for Package Pick-up Route Prediction

Over 10 billion packages are picked up every day in China. A fundamental task raised in the emerging intelligent logistics systems is the couriers’ package pick-up route prediction, which is beneficial for package dispatching, arrival-time estimation and overdue-risk evaluation, by leveraging the predicted routes to improve those downstream tasks. In the package pick-up scene, the decision-making of a courier is affected by strict spatial-temporal constraints (e.g., package location, promised pick-up time, current time, and courier’s current location). Furthermore, couriers have different decision preferences on various factors (e.g., time factor, distance factor, and balance of both), based on their own perception of the environments and work experience. In this article, we propose a novel model, named DeepRoute+, to predict couriers’ future package pick-up routes according to the couriers’ decision experience and preference learned from the historical behaviors. Specifically, DeepRoute+ consists of three layers: (1) The representation layer produces experience- and preference-aware representations for the unpicked-up packages, in which a decision preference module can dynamically adjust the importance of factors that affects the courier’s decision under the current situation. (2) The transformer encoder layer encodes the representations of packages while considering the spatial-temporal correlations among them. (3) The attention-based decoder layer uses the attention mechanism to generate the whole pick-up route recurrently. Experiments on a real-world logistics dataset demonstrate the state-of-the-art performance of our model.

Fast prediction of distances between synthetic routes with deep learning

We expand the recent work on clustering of synthetic routes and train a deep learning model to predict the distances between arbitrary routes. The model is based on an long short-term memory (LSTM) representation of a synthetic route and is trained as a twin network to reproduce the tree edit distance (TED) between two routes. The ML approach is approximately two orders of magnitude faster than the TED approach and enables clustering many more routes from a retrosynthesis route prediction. The clusters have a high degree of similarity to the clusters given by the TED-based approach and are accordingly intuitive and explainable. We provide the developed model as open-source.

Automatic Vehicle Route Prediction based on Multi-Sensor Fusion

To solve the problem of inaccurate results of vehicle routing prediction caused by a large number of uncertain information collected by different sensors in previous automatic vehicle route prediction algorithms, an automatic vehicle route prediction algorithm based on multi-sensor fusion is studied. The process of fusion of multi-sensor information based on the D-S evidence reasoning fusion algorithm is applied to automatic vehicle route prediction. According to the contribution of a longitudinal acceleration sensor and yaw angular velocity sensor detection information to the corresponding motion model, the basic probability assignment function of each vehicle motion model is obtained; the basic probability assignment function of each motion model is synthesized by using D-S evidence reasoning synthesis formula. The new probability allocation of each motion model is obtained under all evidence and then deduced according to the decision rules. Guided by the current optimal motion model, the optimal motion model at each time is used to accurately predict the vehicle movement route. The simulation results show that the prediction error of the algorithm is less than 4% in the process of 30 minutes of automatic vehicle route prediction.

MEQA-RPL: A Mobility Energy and Queue Aware Routing Protocol for Mobile Nodes in Internet of Things

Increase in mobile nodes has brought new challenges to IoT’s routing protocol-RPL. Mobile nodes (MN) bring new possibilities as well as challenges to the network. MN creates frequent route disruption, energy loss and increases end-to-end delay in the network. This could be solved by improving RPL to react faster to route failures through route prediction, while keeping energy expenditure for this process in reasonable limits. In this context a new Mobility Energy and Queue Aware-RPL (MEQA-RPL) is proposed that have the capability to sense route failure and to identify proactively the next possible route before the current route fails. While identifying the next route, MEQA-RPL employs constraint check on energy and queue availability to guarantee QoS for MN and better lifetime for the network. When compared to RPL with mobility support our model reduce average signaling cost by 31%, handover delay by 32% and improve packet delivery ratio by 17%. We run simulations with multiple mobile nodes which have also shown promising results on aforementioned parameters.

Fast Prediction of Distances Between Synthetic Routes with Deep Learning

We expand our recent work on clustering of synthesis routes and train a deep learning model to predict the distances between arbitrary routes. The model is based on an long short-term memory (LSTM) representation of a synthesis route and is trained as a twin network to reproduce the tree edit distance (TED) between two routes. The ML approach is approximately two orders of magnitude faster than the TED approach and enables clustering many more routes from a retrosynthesis route prediction. The clusters have a high degree of similarity to the clusters given by the TED-based approach and are accordingly intuitive and explainable. We provide the developed model as open-source (https://github.com/MolecularAI/route-distances).

Fast Prediction of Distances Between Synthetic Routes with Deep Learning

We expand our recent work on clustering of synthesis routes and train a deep learning model to predict the distances between arbitrary routes. The model is based on an long short-term memory (LSTM) representation of a synthesis route and is trained as a twin network to reproduce the tree edit distance (TED) between two routes. The ML approach is approximately two orders of magnitude faster than the TED approach and enables clustering many more routes from a retrosynthesis route prediction. The clusters have a high degree of similarity to the clusters given by the TED-based approach and are accordingly intuitive and explainable. We provide the developed model as open-source (https://github.com/MolecularAI/route-distances).

A deep learning based approach for trajectory estimation using geographically clustered data

This study presents a novel approach to predict a complete source to destination trajectory of a vehicle using a partial trajectory query. The proposed architecture is scalable to extremely large-scale data with respect to the dense road network. A deep learning model Long Short Term Memory (LSTM) has been used for analyzing the temporal data and predicting the complete trajectory. To handle a large amount of data, clustering of similar trajectory data is used that helps in reducing the search space. The clusters based on geographical locations and temporal values are used for training different LSTM models. The proposed approach is compared with the other published work on the parameters as Average distance error and one step prediction accuracy The one-step prediction accuracy is as good as 81% and Distance error are .33 Km. Our proposed approach termed Clustered LSTM is outperforming in both the parameters when compared with other reported results. The proposed solution is a clustering-based predictive model that effectively contributes to accurately handle the large scale data. The outcome of this study leads to improvise the navigation systems, route prediction, traffic management, and location-based recommendation systems.