Simultaneous Past and Current Social Interaction-aware Trajectory Prediction for Multiple Intelligent Agents in Dynamic Scenes

Trajectory prediction of multiple agents in a crowded scene is an essential component in many applications, including intelligent monitoring, autonomous robotics, and self-driving cars. Accurate agent trajectory prediction remains a significant challenge because of the complex dynamic interactions among the agents and between them and the surrounding scene. To address the challenge, we propose a decoupled attention-based spatial-temporal modeling strategy in the proposed trajectory prediction method. The past and current interactions among agents are dynamically and adaptively summarized by two separate attention-based networks and have proven powerful in improving the prediction accuracy. Moreover, it is optional in the proposed method to make use of the road map and the plan of the ego-agent for scene-compliant and accurate predictions. The road map feature is efficiently extracted by a convolutional neural network, and the features of the ego-agent’s plan is extracted by a gated recurrent network with an attention module based on the temporal characteristic. Experiments on benchmark trajectory prediction datasets demonstrate that the proposed method is effective when the ego-agent plan and the the surrounding scene information are provided and achieves state-of-the-art performance with only the observed trajectories.

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.

Prediction of Football Match Results Based on Edge Computing and Machine Learning Technology

With the rapid development of artificial intelligence, various machine learning algorithms have been widely used in the task of football match result prediction and have achieved certain results. However, traditional machine learning methods usually upload the results of previous competitions to the cloud server in a centralized manner, which brings problems such as network congestion, server computing pressure and computing delay. This paper proposes a football match result prediction method based on edge computing and machine learning technology. Specifically, we first extract some game data from the results of the previous games to construct the common features and characteristic features, respectively. Then, the feature extraction and classification task are deployed to multiple edge nodes.Finally, the results in all the edge nodes are uploaded to the cloud server and fused to make a decision. Experimental results have demonstrated the effectiveness of the proposed method.

Crystal Structure Prediction and Lattice Dynamical Calculations for the Rare Platinum-Group Mineral Zaccariniite (RhNiAs)

The crystal structures of newly found minerals are routinely determined using single-crystal techniques. However, many rare minerals usually form micrometer-sized aggregates that are difficult to study with conventional structural methods. This is the case for numerous platinum-group minerals (PGMs) such as, for instance, zaccariniite (RhNiAs), the crystal structure of which was first obtained by studying synthetic samples. The aim of the present work is to explore the usefulness of USPEX, a powerful crystal structure prediction method, as an alternative means of determining the crystal structure of minerals such as zaccariniite, with a relatively simple crystal structure and chemical formula. We show that fixed composition USPEX searches with a variable number of formula units, using the ideal formula of the mineral as the only starting point, successfully predict the tetragonal structure of a mineral. Density functional theory (DFT) calculations can then be performed in order to more tightly relax the structure of the mineral and calculate different fundamental properties, such as the frequency of zone-center Raman-active phonons, or even their pressure behavior. These theoretical data can be subsequently compared to experimental results, which, in the case of newly found minerals, would allow one to confirm the correctness of the crystal structure predicted by the USPEX code.

DeepGOZero: Improving protein function prediction from sequence and zero-shot learning based on ontology axioms

Motivation: Protein functions are often described using the Gene Ontology (GO) which is an ontology consisting of over 50,000 classes and a large set of formal axioms. Predicting the functions of proteins is one of the key challenges in computational biology and a variety of machine learning methods have been developed for this purpose. However, these methods usually require significant amount of training data and cannot make predictions for GO classes which have only few or no experimental annotations. Results: We developed DeepGOZero, a machine learning model which improves predictions for functions with no or only a small number of annotations. To achieve this goal, we rely on a model-theoretic approach for learning ontology embeddings and combine it with neural networks for protein function prediction. DeepGOZero can exploit formal axioms in the GO to make zero-shot predictions, i.e., predict protein functions even if not a single protein in the training phase was associated with that function. Furthermore, the zero-shot prediction method employed by DeepGOZero is generic and can be applied whenever associations with ontology classes need to be predicted. Availability: http://github.com/bio-ontology-research-group/deepgozero