ALBERT

Description: Neural machine translation is a prominent field in the computational linguistics domain. By leveraging the recent developments of deep learning, it gave birth to powerful algorithms for translating text from one language to another. This study aims to assess the feasibility of transferring the neural machine translation approach into a completely different context, namely human mobility and trajectory analysis. Building a conceptual parallelism between sentences (sequences of words) and motion traces (sequences of locations), we aspire to translate individual trajectories generated by a certain category of users into the corresponding mobility traces potentially generated by a different category of users. The experiment is inserted in the background of tourist mobility analysis, with the goal of translating the motion behavior of tourists belonging to a specific nationality into the motion behavior of tourists belonging to a different nationality. The model adopted is based on the seq2seq approach and consists of an encoder–decoder architecture based on long short-term memory (LSTM) neural networks and neural embeddings. The encoder turns an input location sequence into a corresponding hidden vector; the decoder reverses the process, turning the vector into an output location sequence. The proposed framework, tested on a real-world large-scale dataset, explores an effective attempt of motion transformation between different entities, arising as a potentially powerful source of mobility information disclosure, especially in the context of crowd management and smart city services.

Description: The interest in human mobility analysis has increased with the rapid growth of positioning technology and motion tracking, leading to a variety of studies based on trajectory recordings. Mapping the routes that people commonly perform was revealed to be very useful for location-based service applications, where individual mobility behaviors can potentially disclose meaningful information about each customer and be fruitfully used for personalized recommendation systems. This paper tackles a novel trajectory labeling problem related to the context of user profiling in “smart” tourism, inferring the nationality of individual users on the basis of their motion trajectories. In particular, we use large-scale motion traces of short-term foreign visitors as a way of detecting the nationality of individuals. This task is not trivial, relying on the hypothesis that foreign tourists of different nationalities may not only visit different locations, but also move in a different way between the same locations. The problem is defined as a multinomial classification with a few tens of classes (nationalities) and sparse location-based trajectory data. We hereby propose a machine learning-based methodology, consisting of a long short-term memory (LSTM) neural network trained on vector representations of locations, in order to capture the underlying semantics of user mobility patterns. Experiments conducted on a real-world big dataset demonstrate that our method achieves considerably higher performances than baseline and traditional approaches.

Description: The rapid growth of positioning technology allows tracking motion between places, making trajectory recordings an important source of information about place connectivity, as they map the routes that people commonly perform. In this paper, we utilize users’ motion traces to construct a behavioral representation of places based on how people move between them, ignoring geographical coordinates and spatial proximity. Inspired by natural language processing techniques, we generate and explore vector representations of locations, traces and visitors, obtained through an unsupervised machine learning approach, which we generically named motion-to-vector (Mot2vec), trained on large-scale mobility data. The algorithm consists of two steps, the trajectory pre-processing and the Word2vec-based model building. First, mobility traces are converted into sequences of locations that unfold in fixed time steps; then, a Skip-gram Word2vec model is used to construct the location embeddings. Trace and visitor embeddings are finally created combining the location vectors belonging to each trace or visitor. Mot2vec provides a meaningful representation of locations, based on the motion behavior of users, defining a direct way of comparing locations’ connectivity and providing analogous similarity distributions for places of the same type. In addition, it defines a metric of similarity for traces and visitors beyond their spatial proximity and identifies common motion behaviors between different categories of people.

Description: Parks are essential public places and play a central role in urban livability. However, traditional methods of investigating their attractiveness, such as questionnaires and in situ observations, are usually time- and resource-consuming, while providing less transferable and only site-specific results. This paper presents an improved methodology of using social media (Twitter) data to extract spatial and temporal patterns of park visits for urban planning purposes, along with the sentiment of the tweets, focusing on frequent Twitter users. We analyzed the spatiotemporal park visiting behavior of more than 4000 users for almost 1700 parks, examining 78,000 tweets in London, UK. The novelty of the research is in the combination of spatial and temporal aspects of Twitter data analysis, applying sentiment and emotion extraction for park visits throughout the whole city. This transferable methodology thereby overcomes many of the limitations of traditional research methods. This study concluded that people tweeted mostly in parks 3–4 km away from their center of activity and they were more positive than elsewhere while doing so. In our analysis, we identified four types of parks based on their visitors’ spatial behavioral characteristics, the sentiment of the tweets, and the temporal distribution of the users, serving as input for further urban planning-related investigations.

Description: The increasing availability of trajectory recordings has led to the mining of a massive amount of historical track data, allowing for a better understanding of travel behaviors by revealing meaningful motion patterns. In the context of human mobility analysis, the problem of motion prediction assumes a central role and is beneficial for a wide range of applications, including for touristic purposes, such as personalized services or targeted recommendations, and sustainability studies related to crowd management and resource redistribution. This paper tackles a particular case of the trajectory prediction problem, focusing on large-scale mobility traces of short-term foreign tourists. These sparse trajectories, short and non-repetitive, lack spatial and temporal regularity, making prediction analysis based on individual historical motion data unreliable. To face this issue, we hereby propose a deep learning-based approach, taking into account the collective mobility of tourists over the territory. The underlying semantics of motion patterns are captured by means of a long short-term memory (LSTM) neural network model trained on pre-processed location sequences, aiming to predict the next visited place in the trajectory. We tested the methodology on a real-world big dataset, demonstrating its higher feasibility with respect to traditional approaches.

Description: Monitoring the distribution of vehicles across the city is of great importance for urban traffic control. In particular, information on the number of vehicles entering and leaving a city, or moving between urban areas, gives a valuable estimate on potential bottlenecks and congestions. The possibility of predicting such flows in advance is even more beneficial, allowing for timely traffic management strategies and targeted congestion warnings. Our work is inserted in the context of short-term forecasting, aiming to predict rapid changes and sudden variations in the traffic volume, beyond the general trend. Moreover, it concurrently targets multiple locations in the city, providing an instant prediction outcome comprising the future distribution of vehicles across several urban locations. Specifically, we propose a multi-target deep learning regressor for simultaneous predictions of traffic volumes, in multiple entry and exit points among city neighborhoods. The experiment focuses on an hourly forecasting of the amount of vehicles accessing and moving between New York City neighborhoods through the Metropolitan Transportation Authority (MTA) bridges and tunnels. By leveraging a single training process for all location points, and an instant one-step volume inference for every location at each time update, our sequential modeling approach is able to grasp rapid variations in the time series and process the collective information of all entry and exit points, whose distinct predicted values are outputted at once. The multi-target model, based on long short-term memory (LSTM) recurrent neural network layers, was tested on a real-world dataset, achieving an average prediction error of 7% and demonstrating its feasibility for short-term spatially-distributed urban traffic forecasting.

Description: The traditional categorization of crime types relies on a hierarchical structure, from high-level categories to lower-level subtypes. This tree-based classification treats crime types as mutually independent when they do not branch from the same higher-level category, therefore lacking inter-category semantic relations. The issue then extends over crime distribution analysis of urban regions, often reporting statistics based on crime type counts, but neglecting implicit relations between different crime categories. Our study aims to fill this information gap, providing a more complete understanding of urban crime in both qualitative and quantitative terms. Specifically, we propose a vector-based crime type representation, constructed via unsupervised machine learning on temporal and geographic factors. The general idea is to define crime types as “related” if they often occur in the same area at the same time span, regardless of any initial hierarchical categorization. This opens to a new metric of comparison that goes beyond pre-defined structures, revealing hidden relationships between crime types by generating a vector space in a completely data-driven manner. Crime types are represented as points in this space, and their relative distances disclose stronger or weaker semantic relations. A direct application on urban crime distribution analysis stands out in the form of visualization tools for intuitive data investigations and convenient comparison measures on composite vectors of urban regions. Meaningful insights on crime type distributions and a better understanding of urban crime characteristics determine a valuable asset to urban management and development.