arXiv subjects

Yanyan Xu

Publications and source records attributed to Yanyan Xu.

35 records · Page 2Linked to original sources

arXiv2023

Urban Dynamics Through the Lens of Human Mobility

The urban spatial structure represents the distribution of public and private spaces in cities and how people move within them. While it usually evolves slowly, it can change fast during large-scale emergency events, as well as due to urban renewal in rapidly developing countries. This work presents an approach to delineate such urban dynamics in quasi-real-time through a human mobility metric, the mobility centrality index $ΔKS$. As a case study, we tracked the urban dynamics of eleven Spanish cities during the COVID-19 pandemic. Results revealed that their structures became more monocentric during the lockdown in the first wave, but kept their regular spatial structures during the second wave. To provide a more comprehensive understanding of mobility from home, we also introduce a dimensionless metric, $KS_{HBT}$, which measures the extent of home-based travel and provides statistical insights into the transmission of COVID-19. By utilizing individual mobility data, our metrics enable the detection of changes in the urban spatial structure.

physics.soc-ph↗

arXiv2023

Planning for Electric Vehicles Coupled with Urban Mobility

The rising adoption of plug-in electric vehicles (PEVs) leads to the alignment of their electricity and their mobility demands. Therefore, transportation and power infrastructures are becoming increasingly interdependent. In this work, we uncover patterns of PEV mobility by integrating for the first time two unique data sets: (i) mobile phone activity of 1.39 million Bay Area residents and (ii) charging activity of PEVs in 580,000 sessions obtained in the same region. We present a method to estimate individual mobility of PEV drivers at fine temporal and spatial resolution integrating survey data with mobile phone data and income information obtained from census. Thereupon, we recommend changes in PEVs charging times of commuters at their work stations that take into account individual travel needs and shave the pronounced peak in power demand. Informed by the tariff of electricity, we calculate the12 monetary gains to incentivize the adoption of the recommendations. These results open avenues for planning for the future of coupled transportation and electricity needs using personalized data.

physics.soc-ph↗

arXiv2023

Dynamically Mitigating Data Discrepancy with Balanced Focal Loss for Replay Attack Detection

It becomes urgent to design effective anti-spoofing algorithms for vulnerable automatic speaker verification systems due to the advancement of high-quality playback devices. Current studies mainly treat anti-spoofing as a binary classification problem between bonafide and spoofed utterances, while lack of indistinguishable samples makes it difficult to train a robust spoofing detector. In this paper, we argue that for anti-spoofing, it needs more attention for indistinguishable samples over easily-classified ones in the modeling process, to make correct discrimination a top priority. Therefore, to mitigate the data discrepancy between training and inference, we propose D3M, to leverage a balanced focal loss function as the training objective to dynamically scale the loss based on the traits of the sample itself. Besides, in the experiments, we select three kinds of features that contain both magnitude-based and phase-based information to form complementary and informative features. Experimental results on the ASVspoof2019 dataset demonstrate the superiority of the proposed methods by comparison between our systems and top-performing ones. Systems trained with the balanced focal loss perform significantly better than conventional cross-entropy loss. With complementary features, our fusion system with only three kinds of features outperforms other systems containing five or more complex single models by 22.5% for min-tDCF and 7% for EER, achieving a min-tDCF and an EER of 0.0124 and 0.55% respectively. Furthermore, we present and discuss the evaluation results on real replay data apart from the simulated ASVspoof2019 data, indicating that research for anti-spoofing still has a long way to go. Source code, analysis data, and other details are publicly available at https://github.com/asvspoof/D3M.

cs.CV↗

arXiv2021

SanMove: Next Location Recommendation via Self-Attention Network

Currently, next location recommendation plays a vital role in location-based social network applications and services. Although many methods have been proposed to solve this problem, three important challenges have not been well addressed so far: (1) most existing methods are based on recurrent network, which is time-consuming to train long sequences due to not allowing for full parallelism; (2) personalized preferences generally are not considered reasonably; (3) existing methods rarely systematically studied how to efficiently utilize various auxiliary information (e.g., user ID and timestamp) in trajectory data and the spatio-temporal relations among non-consecutive locations. To address the above challenges, we propose a novel method named SanMove, a self-attention network based model, to predict the next location via capturing the long- and short-term mobility patterns of users. Specifically, SanMove introduces a long-term preference learning module, and it uses a self-attention module to capture the users long-term mobility pattern which can represent personalized location preferences of users. Meanwhile, SanMove uses a spatial-temporal guided non-invasive self-attention (STNOVA) to exploit auxiliary information to learn short-term preferences. We evaluate SanMove with two real-world datasets, and demonstrate SanMove is not only faster than the state-of-the-art RNN-based predict model but also outperforms the baselines for next location prediction.

cs.SI↗

arXiv2021

PG$^2$Net: Personalized and Group Preferences Guided Network for Next Place Prediction

Predicting the next place to visit is a key in human mobility behavior modeling, which plays a significant role in various fields, such as epidemic control, urban planning, traffic management, and travel recommendation. To achieve this, one typical solution is designing modules based on RNN to capture their preferences to various locations. Although these RNN-based methods can effectively learn individual's hidden personalized preferences to her visited places, the interactions among users can only be weakly learned through the representations of locations. Targeting this, we propose an end-to-end framework named personalized and group preference guided network (PG$^2$Net), considering the users' preferences to various places at both individual and collective levels. Specifically, PG$^2$Net concatenates Bi-LSTM and attention mechanism to capture each user's long-term mobility tendency. To learn population's group preferences, we utilize spatial and temporal information of the visitations to construct a spatio-temporal dependency module. We adopt a graph embedding method to map users' trajectory into a hidden space, capturing their sequential relation. In addition, we devise an auxiliary loss to learn the vectorial representation of her next location. Experiment results on two Foursquare check-in datasets and one mobile phone dataset indicate the advantages of our model compared to the state-of-the-art baselines. Source codes are available at https://github.com/urbanmobility/PG2Net.

cs.LG↗

arXiv2021

Explaining the Attention Mechanism of End-to-End Speech Recognition Using Decision Trees

The attention mechanism has largely improved the performance of end-to-end speech recognition systems. However, the underlying behaviours of attention is not yet clearer. In this study, we use decision trees to explain how the attention mechanism impact itself in speech recognition. The results indicate that attention levels are largely impacted by their previous states rather than the encoder and decoder patterns. Additionally, the default attention mechanism seems to put more weights on closer states, but behaves poorly on modelling long-term dependencies of attention states.

cs.CL↗

arXiv2021

An Empirical Study on End-to-End Singing Voice Synthesis with Encoder-Decoder Architectures

With the rapid development of neural network architectures and speech processing models, singing voice synthesis with neural networks is becoming the cutting-edge technique of digital music production. In this work, in order to explore how to improve the quality and efficiency of singing voice synthesis, in this work, we use encoder-decoder neural models and a number of vocoders to achieve singing voice synthesis. We conduct experiments to demonstrate that the models can be trained using voice data with pitch information, lyrics and beat information, and the trained models can produce smooth, clear and natural singing voice that is close to real human voice. As the models work in the end-to-end manner, they allow users who are not domain experts to directly produce singing voice by arranging pitches, lyrics and beats.

cs.SD↗

arXiv2021

Speech Enhancement using Separable Polling Attention and Global Layer Normalization followed with PReLU

Single channel speech enhancement is a challenging task in speech community. Recently, various neural networks based methods have been applied to speech enhancement. Among these models, PHASEN and T-GSA achieve state-of-the-art performances on the publicly opened VoiceBank+DEMAND corpus. Both of the models reach the COVL score of 3.62. PHASEN achieves the highest CSIG score of 4.21 while T-GSA gets the highest PESQ score of 3.06. However, both of these two models are very large. The contradiction between the model performance and the model size is hard to reconcile. In this paper, we introduce three kinds of techniques to shrink the PHASEN model and improve the performance. Firstly, seperable polling attention is proposed to replace the frequency transformation blocks in PHASEN. Secondly, global layer normalization followed with PReLU is used to replace batch normalization followed with ReLU. Finally, BLSTM in PHASEN is replaced with Conv2d operation and the phase stream is simplified. With all these modifications, the size of the PHASEN model is shrunk from 33M parameters to 5M parameters, while the performance on VoiceBank+DEMAND is improved to the CSIG score of 4.30, the PESQ score of 3.07 and the COVL score of 3.73.

cs.SD↗

arXiv2020

Deconstructing laws of accessibility and facility distribution in cities

The era of the automobile has seriously degraded the quality of urban life through costly travel and visible environmental effects. A new urban planning paradigm must be at the heart of our roadmap for the years to come. The one where, within minutes, inhabitants can access their basic living needs by bike or by foot. In this work, we present novel insights of the interplay between the distributions of facilities and population that maximize accessibility over the existing road networks. Results in six cities reveal that travel costs could be reduced in half through redistributing facilities. In the optimal scenario, the average travel distance can be modeled as a functional form of the number of facilities and the population density. As an application of this finding, it is possible to estimate the number of facilities needed for reaching a desired average travel distance given the population distribution in a city.

physics.soc-ph↗

arXiv2020

Socio-economic, built environment, and mobility conditions associated with crime: A study of multiple cities

Nowadays, 23% of the world population lives in multi-million cities. In these metropolises, criminal activity is much higher and violent than in either small cities or rural areas. Thus, understanding what factors influence urban crime in big cities is a pressing need. Mainstream studies analyse crime records through historical panel data or analysis of historical patterns combined with ecological factor and exploratory mapping. More recently, machine learning methods have provided informed crime prediction over time. However, previous studies have focused on a single city at a time, considering only a limited number of factors (such as socio-economical characteristics) and often at large spatial units. Hence, our understanding of the factors influencing crime across cultures and cities is very limited. Here we propose a Bayesian model to explore how crime is related not only to socio-economic factors but also to the built environmental (e.g. land use) and mobility characteristics of neighbourhoods. To that end, we integrate multiple open data sources with mobile phone traces and compare how the different factors correlate with crime in diverse cities, namely Boston, Bogotá, Los Angeles and Chicago. We find that the combined use of socio-economic conditions, mobility information and physical characteristics of the neighbourhood effectively explain the emergence of crime, and improve the performance of the traditional approaches. However, we show that the socio-ecological factors of neighbourhoods relate to crime very differently from one city to another. Thus there is clearly no "one fits all" model.

cs.SI↗

arXiv2019

Complementary Fusion of Multi-Features and Multi-Modalities in Sentiment Analysis

Sentiment analysis, mostly based on text, has been rapidly developing in the last decade and has attracted widespread attention in both academia and industry. However, the information in the real world usually comes from multiple modalities, such as audio and text. Therefore, in this paper, based on audio and text, we consider the task of multimodal sentiment analysis and propose a novel fusion strategy including both multi-feature fusion and multi-modality fusion to improve the accuracy of audio-text sentiment analysis. We call it the DFF-ATMF (Deep Feature Fusion - Audio and Text Modality Fusion) model, which consists of two parallel branches, the audio modality based branch and the text modality based branch. Its core mechanisms are the fusion of multiple feature vectors and multiple modality attention. Experiments on the CMU-MOSI dataset and the recently released CMU-MOSEI dataset, both collected from YouTube for sentiment analysis, show the very competitive results of our DFF-ATMF model. Furthermore, by virtue of attention weight distribution heatmaps, we also demonstrate the deep features learned by using DFF-ATMF are complementary to each other and robust. Surprisingly, DFF-ATMF also achieves new state-of-the-art results on the IEMOCAP dataset, indicating that the proposed fusion strategy also has a good generalization ability for multimodal emotion recognition.

cs.CL↗

arXiv2019

Travel Time Estimation without Road Networks: An Urban Morphological Layout Representation Approach

Travel time estimation is a crucial task for not only personal travel scheduling but also city planning. Previous methods focus on modeling toward road segments or sub-paths, then summing up for a final prediction, which have been recently replaced by deep neural models with end-to-end training. Usually, these methods are based on explicit feature representations, including spatio-temporal features, traffic states, etc. Here, we argue that the local traffic condition is closely tied up with the land-use and built environment, i.e., metro stations, arterial roads, intersections, commercial area, residential area, and etc, yet the relation is time-varying and too complicated to model explicitly and efficiently. Thus, this paper proposes an end-to-end multi-task deep neural model, named Deep Image to Time (DeepI2T), to learn the travel time mainly from the built environment images, a.k.a. the morphological layout images, and showoff the new state-of-the-art performance on real-world datasets in two cities. Moreover, our model is designed to tackle both path-aware and path-blind scenarios in the testing phase. This work opens up new opportunities of using the publicly available morphological layout images as considerable information in multiple geography-related smart city applications.

cs.AI↗

arXiv2017

Trainable back-propagated functional transfer matrices

Connections between nodes of fully connected neural networks are usually represented by weight matrices. In this article, functional transfer matrices are introduced as alternatives to the weight matrices: Instead of using real weights, a functional transfer matrix uses real functions with trainable parameters to represent connections between nodes. Multiple functional transfer matrices are then stacked together with bias vectors and activations to form deep functional transfer neural networks. These neural networks can be trained within the framework of back-propagation, based on a revision of the delta rules and the error transmission rule for functional connections. In experiments, it is demonstrated that the revised rules can be used to train a range of functional connections: 20 different functions are applied to neural networks with up to 10 hidden layers, and most of them gain high test accuracies on the MNIST database. It is also demonstrated that a functional transfer matrix with a memory function can roughly memorise a non-cyclical sequence of 400 digits.

cs.LG↗

arXiv2017

Learning of Human-like Algebraic Reasoning Using Deep Feedforward Neural Networks

There is a wide gap between symbolic reasoning and deep learning. In this research, we explore the possibility of using deep learning to improve symbolic reasoning. Briefly, in a reasoning system, a deep feedforward neural network is used to guide rewriting processes after learning from algebraic reasoning examples produced by humans. To enable the neural network to recognise patterns of algebraic expressions with non-deterministic sizes, reduced partial trees are used to represent the expressions. Also, to represent both top-down and bottom-up information of the expressions, a centralisation technique is used to improve the reduced partial trees. Besides, symbolic association vectors and rule application records are used to improve the rewriting processes. Experimental results reveal that the algebraic reasoning examples can be accurately learnt only if the feedforward neural network has enough hidden layers. Also, the centralisation technique, the symbolic association vectors and the rule application records can reduce error rates of reasoning. In particular, the above approaches have led to 4.6% error rate of reasoning on a dataset of linear equations, differentials and integrals.

cs.AI↗

arXiv2016

The rigidity of hypersurface in Euclidean space

In the present paper, we revisit the rigidity of hypersurfaces in Euclidean space. We highlight Darboux equation and give new proof of rigidity of hypersurfaces by energy method and maximal principle.

math.DG↗

arXiv2016

Collective benefits in traffic during mega events via the use of information technologies

Information technologies today can inform each of us about the best alternatives for shortest paths from origins to destinations, but they do not contain incentives or alternatives that manage the information efficiently to get collective benefits. To obtain such benefits, we need to have not only good estimates of how the traffic is formed but also to have target strategies to reduce enough vehicles from the best possible roads in a feasible way. The opportunity is that during large events the traffic inconveniences in large cities are unusually high, yet temporary, and the entire population may be more willing to adopt collective recommendations for social good. In this paper, we integrate for the first time big data resources to quantify the impact of events and propose target strategies for collective good at urban scale. In the context of the Olympic Games in Rio de Janeiro, we first predict the expected increase in traffic. To that end, we integrate data from: mobile phones, Airbnb, Waze, and transit information, with game schedules and information of venues. Next, we evaluate the impact of the Olympic Games to the travel of commuters, and propose different route choice scenarios during the peak hours. Moreover, we gather information on the trips that contribute the most to the global congestion and that could be redirected from vehicles to transit. Interestingly, we show that (i) following new route alternatives during the event with individual shortest path can save more collective travel time than keeping the routine routes, uncovering the positive value of information technologies during events; (ii) with only a small proportion of people selected from specific areas switching from driving to public transport, the collective travel time can be reduced to a great extent. Results are presented on-line for the evaluation of the public and policy makers.

cs.SI↗

arXiv2014

Hop Doubling Label Indexing for Point-to-Point Distance Querying on Scale-Free Networks

We study the problem of point-to-point distance querying for massive scale-free graphs, which is important for numerous applications. Given a directed or undirected graph, we propose to build an index for answering such queries based on a hop-doubling labeling technique. We derive bounds on the index size, the computation costs and I/O costs based on the properties of unweighted scale-free graphs. We show that our method is much more efficient compared to the state-of-the-art technique, in terms of both querying time and indexing time. Our empirical study shows that our method can handle graphs that are orders of magnitude larger than existing methods.

cs.DB↗