History Of Journey Research Articles

A trajectory prediction method based on bayonet importance encoding and bidirectional LSTM

Predicting vehicle trajectories can not only provide users with efficient travel suggestions, but also help traffic managers make better decisions. This paper aims to address the next position prediction problem to enable the prediction of the movement trajectory of an individual vehicle by considering where it will go. With this aim, it investigates using deep learning methods for predicting a vehicle’s next position based on its journey history. A deep learning model based on bidirectional long short-term memory (Bi-LSTM) with self-attention mechanism that fuses bayonet importance encoding (Bi-LSTMAI) is proposed, which can well capture both local and global semantic dependency. In specific, word embedding in natural language processing (NLP) is introduced to measure the relevance of bayonets and the PageRank algorithm is improved to obtain the bayonet importance encoding. By using real bayonet data, this research compares the prediction performance of the proposed model with several baselines, including LSTM, GRU, Bi-LSTM and Bi-GRU. The result shows that the proposed model yields better performance in all experimental metrics for the task of trajectory prediction.

Vehicle Destination Prediction Using Bidirectional LSTM with Attention Mechanism.

Satellite navigation has become ubiquitous to plan and track travelling. Having access to a vehicle’s position enables the prediction of its destination. This opens the possibility to various benefits, such as early warnings of potential hazards, route diversions to pass traffic congestion, and optimizing fuel consumption for hybrid vehicles. Thus, reliably predicting destinations can bring benefits to the transportation industry. This paper investigates using deep learning methods for predicting a vehicle’s destination based on its journey history. With this aim, Dense Neural Networks (DNNs), Long Short-Term Memory (LSTM) networks, Bidirectional LSTM (BiLSTM), and networks with and without attention mechanisms are tested. Especially, LSTM and BiLSTM models with attention mechanism are commonly used for natural language processing and text-classification-related applications. On the other hand, this paper demonstrates the viability of these techniques in the automotive and associated industrial domain, aimed at generating industrial impact. The results of using satellite navigation data show that the BiLSTM with an attention mechanism exhibits better prediction performance destination, achieving an average accuracy of 96% against the test set (4% higher than the average accuracy of the standard BiLSTM) and consistently outperforming the other models by maintaining robustness and stability during forecasting.

SafeDri: A mobile-based application for safety driving

Globally, around 1.3 million people die every year and more than 50 million people suffer permanent disability due to traffic accidents. This condition has worsened in many countries in the world in line with the high rate of ownership of motorized vehicles. The most common reasons for traffic accidents are distracted driving, over speeding, drunk driving and reckless driving. All those reasons are related with unsafe behaviour while driving. To cope with the problem, we developed a mobile based application that assists driver to drive more safely. The apps will collect information during a stipulated journey and recognize speeding facts, harsh acceleration, heavy breaking, and fuel consumption. While using this application, the drivers will learn how to drive safely, set goals and preferences, get alerts upon over limit violation, and receive feedback on their completed journeys. The results of a usability test on the application indicate that the app managed to identify misbehaviour while driving and rate driver behaviour based on journey history.

Journey history reconstruction from the soils and sediments on footwear: An empirical approach

The value of environmental evidence for reconstructing journey histories has significant potential given the high transferability of sediments and the interaction of footwear with the ground. The importance of empirical evidence bases to underpin the collection, analysis, interpretation and presentation of forensic trace materials is increasingly acknowledged. This paper presents two experimental studies designed to address the transfer and persistence of sediments on the soles of footwear in forensically relevant scenarios, by means of quartz grain surface texture analysis, a technique which has been demonstrated to be able to distinguish between samples of mixed provenance.It was identified that there is a consistent trend of transfer and persistence of sediments from hypothetical pre-, syn- and post-crime event locations across the sole of the shoe, with sediments from ‘older’ locations likely to be retained in small proportions. Furthermore, the arch of the shoe (the area of lowest foot pressure distribution) typically (but not exclusively) retained the highest proportion of grain types from previous locations including the crime scene. A lack of chronological layering of the retained sediments was observed indicating that techniques that can identify the components of mixed provenance samples are important for analysing footwear sediment samples. It was also identified that the type of footwear appeared to have an influence on what particles were retained, with high relief soles that incorporate recessed areas being more likely to retain sediments transferred from ‘older’ locations from the journey history. In addition, the inners of footwear were found to retain sediments from multiple locations from the journey history that are less susceptible to differential loss in comparison to the outer sole. These findings provide important data that can form the basis for the effective collection, analysis and interpretation of sediments recovered from both the outer soles and inners of footwear, building on the findings of previously published studies. These data offer insights that enable inferences to be made about mixed source sediments that are identified on footwear in casework, and provide the beginnings of an empirical basis for assessing the significance of such sediment particles for a specific forensic reconstruction.