Blind classification of e-scooter trips according to their relationship with public transport.

E-scooter services have multiplied worldwide as a form of urban transport. Their use has grown so quickly that policymakers and researchers still need to understand their interrelation with other transport modes. At present, e-scooter services are primarily seen as a first-and-last-mile solution for public transport. However, we demonstrate that 50% of e-scooter trips are either substituting it or covering areas with little public transportation infrastructure. To this end, we have developed a novel data-driven methodology that autonomously classifies e-scooter trips according to their relation to public transit. Instead of predefined design criteria, the blind nature of our approach extracts the city's intrinsic parameters from real data. We applied this methodology to Rome (Italy), and our findings reveal that e-scooters provide specific mobility solutions in areas with particular needs. Thus, we believe that the proposed methodology will contribute to the understanding of e-scooter services as part of shared urban mobility.

Analysis of Extended Information Provided by Bluetooth Traffic Monitoring Systems to Enhance Short-Term Level of Service Prediction.

Bluetooth monitoring systems (BTMS) have opened a new era in traffic sensing, providing a reliable, economical, and easy-to-deploy solution to uniquely identify vehicles. Raw data from BTMS have traditionally been used to calculate travel time and origin-destination matrices. However, we could extend this to include other information like the number of vehicles or their residence times. This information, together with their temporal components, can be applied to the complex task of forecasting traffic. Level of service (LOS) prediction has opened a novel research line that fulfills the need to anticipate future traffic states, based on a standard link-based variable, accepted for both researchers and practitioners. In this paper, we incorporate BTMS's extended variables and temporal information to an LOS classifier based on a Random Undersampling Boost algorithm, which is proven to efficiently respond to the data unbalance intrinsic to this problem. By using this approach, we achieve an overall recall of 87.2% for up to 15-min prediction horizons, reaching 96.6% predicting congestion, and improving the results for the intermediate traffic states, especially complex given their intrinsic instability. Additionally, we provide detailed analyses on the impact of temporal information on the LOS predictor's performance, observing improvements up to a separation of 50 min between last features and prediction horizons. Furthermore, we study the predictor importance resulting from the classifiers to highlight those features contributing the most to the final achievements.

Data-driven analysis of the impact of COVID-19 on Madrid's public transport during each phase of the pandemic.

COVID-19 has become a major global issue with large social-economic and health impacts, which led to important changes in people's behavior. One of these changes affected the way people use public transport. In this work we present a data-driven analysis of the impact of COVID-19 on public transport demand in the Community of Madrid, Spain, using data from ticket validations between February and September 2020. This period of time covers all stages of pandemic in Spain, including de-escalation phases. We find that ridership has dramatically decreased by 95% at the pandemic peak, recovering very slowly and reaching only half its pre-pandemic levels at the end of September. We analyze results for different transport modes, ticket types, and groups of users. Our work corroborates that low-income groups are the most reliant on public transportation, thus observing significantly lower decreases in their ridership during pandemic. This paper also shows different average daily patterns of public transit demand during each phase of the pandemic in Madrid. All these findings provide relevant information for transit agencies to design responses to an emergence situation like this pandemic, contributing to extend the global knowledge about COVID-19 impact on transport comparing results with other cities worldwide.

Characterization of COVID-19's Impact on Mobility and Short-Term Prediction of Public Transport Demand in a Mid-Size City in Spain.

COVID-19 has dramatically struck each section of our society: health, economy, employment, and mobility. This work presents a data-driven characterization of the impact of COVID-19 pandemic on public and private mobility in a mid-size city in Spain (Fuenlabrada). Our analysis used real data collected from the public transport smart card system and a Bluetooth traffic monitoring network, from February to September 2020, thus covering relevant phases of the pandemic. Our results show that, at the peak of the pandemic, public and private mobility dramatically decreased to 95% and 86% of their pre-COVID-19 values, after which the latter experienced a faster recovery. In addition, our analysis of daily patterns evidenced a clear change in the behavior of users towards mobility during the different phases of the pandemic. Based on these findings, we developed short-term predictors of future public transport demand to provide operators and mobility managers with accurate information to optimize their service and avoid crowded areas. Our prediction model achieved a high performance for pre- and post-state-of-alarm phases. Consequently, this work contributes to enlarging the knowledge about the impact of pandemic on mobility, providing a deep analysis about how it affected each transport mode in a mid-size city.

Data-Driven Performance Evaluation Framework for Multi-Modal Public Transport Systems.

Transport agencies require accurate and updated information about public transport systems for the optimal decision-making processes regarding design and operation. In addition to assessing topology and service components, users' behaviors must be considered. To this end, a data-driven performance evaluation based on passengers' actual routes is key. Automatic fare collection platforms provide meaningful smart card data (SCD), but these are incomplete when gathered by entry-only systems. To obtain origin-destination (OD) matrices, we must manage complete journeys. In this paper, we use an adapted trip chaining method to reconstruct incomplete multi-modal journeys by finding spatial similarities between the outbound and inbound routes of the same user. From this dataset, we develop a performance evaluation framework that provides novel metrics and visualization utilities. First, we generate a space-time characterization of the overall operation of transport networks. Second, we supply enhanced OD matrices showing mobility patterns between zones and average traversed distances, travel times, and operation speeds, which model the real efficacy of the public transport system. We applied this framework to the Comunidad de Madrid (Spain), using 4 months' worth of real SCD, showing its potential to generate meaningful information about the performance of multi-modal public transport systems.

Data-Driven Analysis of Bicycle Sharing Systems as Public Transport Systems Based on a Trip Index Classification.

Bicycle Sharing Systems (BSSs) are exponentially increasing in the urban mobility sector. They are traditionally conceived as a last-mile complement to the public transport system. In this paper, we demonstrate that BSSs can be seen as a public transport system in their own right. To do so, we build a mathematical framework for the classification of BSS trips. Using trajectory information, we create the trip index, which characterizes the intrinsic purpose of the use of BSS as transport or leisure. The construction of the trip index required a specific analysis of the BSS shortest path, which cannot be directly calculated from the topology of the network given that cyclists can find shortcuts through traffic lights, pedestrian crossings, etc. to reduce the overall traveled distance. Adding a layer of complication to the problem, these shortcuts have a non-trivial existence in terms of being intermittent, or short lived. We applied the proposed methodology to empirical data from BiciMAD, the public BSS in Madrid (Spain). The obtained results show that the trip index correctly determines transport and leisure categories, which exhibit distinct statistical and operational features. Finally, we inferred the underlying BSS public transport network and show the fundamental trajectories traveled by users. Based on this analysis, we conclude that 90.60% of BiciMAD's use fall in the category of transport, which demonstrates our first statement.

Estimating Vehicle Movement Direction from Smartphone Accelerometers Using Deep Neural Networks.

Characterization of driving maneuvers or driving styles through motion sensors has become a field of great interest. Before now, this characterization used to be carried out with signals coming from extra equipment installed inside the vehicle, such as On-Board Diagnostic (OBD) devices or sensors in pedals. Nowadays, with the evolution and scope of smartphones, these have become the devices for recording mobile signals in many driving characterization applications. Normally multiple available sensors are used, such as accelerometers, gyroscopes, magnetometers or the Global Positioning System (GPS). However, using sensors such as GPS increase significantly battery consumption and, additionally, many current phones do not include gyroscopes. Therefore, we propose the characterization of driving style through only the use of smartphone accelerometers. We propose a deep neural network (DNN) architecture that combines convolutional and recurrent networks to estimate the vehicle movement direction (VMD), which is the forward movement directional vector captured in a phone's coordinates. Once VMD is obtained, multiple applications such as characterizing driving styles or detecting dangerous events can be developed. In the development of the proposed DNN architecture, two different methods are compared. The first one is based on the detection and classification of significant acceleration driving forces, while the second one relies on longitudinal and transversal signals derived from the raw accelerometers. The final success rate of VMD estimation for the best method is of 90.07%.

Obstructive Sleep Apnea in Women: Study of Speech and Craniofacial Characteristics.

BACKGROUND: Obstructive sleep apnea (OSA) is a common sleep disorder characterized by frequent cessation of breathing lasting 10 seconds or longer. The diagnosis of OSA is performed through an expensive procedure, which requires an overnight stay at the hospital. This has led to several proposals based on the analysis of patients' facial images and speech recordings as an attempt to develop simpler and cheaper methods to diagnose OSA. OBJECTIVE: The objective of this study was to analyze possible relationships between OSA and speech and facial features on a female population and whether these possible connections may be affected by the specific clinical characteristics in OSA population and, more specifically, to explore how the connection between OSA and speech and facial features can be affected by gender. METHODS: All the subjects are Spanish subjects suspected to suffer from OSA and referred to a sleep disorders unit. Voice recordings and photographs were collected in a supervised but not highly controlled way, trying to test a scenario close to a realistic clinical practice scenario where OSA is assessed using an app running on a mobile device. Furthermore, clinical variables such as weight, height, age, and cervical perimeter, which are usually reported as predictors of OSA, were also gathered. Acoustic analysis is centered in sustained vowels. Facial analysis consists of a set of local craniofacial features related to OSA, which were extracted from images after detecting facial landmarks by using the active appearance models. To study the probable OSA connection with speech and craniofacial features, correlations among apnea-hypopnea index (AHI), clinical variables, and acoustic and facial measurements were analyzed. RESULTS: The results obtained for female population indicate mainly weak correlations (r values between .20 and .39). Correlations between AHI, clinical variables, and speech features show the prevalence of formant frequencies over bandwidths, with F2/i/ being the most appropriate formant frequency for OSA prediction in women. Results obtained for male population indicate mainly very weak correlations (r values between .01 and .19). In this case, bandwidths prevail over formant frequencies. Correlations between AHI, clinical variables, and craniofacial measurements are very weak. CONCLUSIONS: In accordance with previous studies, some clinical variables are found to be good predictors of OSA. Besides, strong correlations are found between AHI and some clinical variables with speech and facial features. Regarding speech feature, the results show the prevalence of formant frequency F2/i/ over the rest of features for the female population as OSA predictive feature. Although the correlation reported is weak, this study aims to find some traces that could explain the possible connection between OSA and speech in women. In the case of craniofacial measurements, results evidence that some features that can be used for predicting OSA in male patients are not suitable for testing female population.

Reviewing the connection between speech and obstructive sleep apnea.

BACKGROUND: Sleep apnea (OSA) is a common sleep disorder characterized by recurring breathing pauses during sleep caused by a blockage of the upper airway (UA). The altered UA structure or function in OSA speakers has led to hypothesize the automatic analysis of speech for OSA assessment. In this paper we critically review several approaches using speech analysis and machine learning techniques for OSA detection, and discuss the limitations that can arise when using machine learning techniques for diagnostic applications. METHODS: A large speech database including 426 male Spanish speakers suspected to suffer OSA and derived to a sleep disorders unit was used to study the clinical validity of several proposals using machine learning techniques to predict the apnea-hypopnea index (AHI) or classify individuals according to their OSA severity. AHI describes the severity of patients' condition. We first evaluate AHI prediction using state-of-the-art speaker recognition technologies: speech spectral information is modelled using supervectors or i-vectors techniques, and AHI is predicted through support vector regression (SVR). Using the same database we then critically review several OSA classification approaches previously proposed. The influence and possible interference of other clinical variables or characteristics available for our OSA population: age, height, weight, body mass index, and cervical perimeter, are also studied. RESULTS: The poor results obtained when estimating AHI using supervectors or i-vectors followed by SVR contrast with the positive results reported by previous research. This fact prompted us to a careful review of these approaches, also testing some reported results over our database. Several methodological limitations and deficiencies were detected that may have led to overoptimistic results. CONCLUSION: The methodological deficiencies observed after critically reviewing previous research can be relevant examples of potential pitfalls when using machine learning techniques for diagnostic applications. We have found two common limitations that can explain the likelihood of false discovery in previous research: (1) the use of prediction models derived from sources, such as speech, which are also correlated with other patient characteristics (age, height, sex,…) that act as confounding factors; and (2) overfitting of feature selection and validation methods when working with a high number of variables compared to the number of cases. We hope this study could not only be a useful example of relevant issues when using machine learning for medical diagnosis, but it will also help in guiding further research on the connection between speech and OSA.

Formant Frequencies and Bandwidths in Relation to Clinical Variables in an Obstructive Sleep Apnea Population.

OBJECTIVES: We investigated whether differences in formants and their bandwidths, previously reported comparing small sample population of healthy individuals and patients with obstructive sleep apnea (OSA), are detected on a larger population representative of a clinical practice scenario. We examine possible indirect or mediated effects of clinical variables, which may shed some light on the connection between speech and OSA. STUDY DESIGN: In a retrospective study, 241 male subjects suspected to suffer from OSA were examined. The apnea-hypopnea index (AHI) was obtained for every subject using overnight polysomnography. Furthermore, the clinical variables usually reported as predictors of OSA, body mass index (BMI), cervical perimeter, height, weight, and age, were collected. Voice samples of sustained phonations of the vowels /a/, /e/, /i/, /o/, and /u/ were recorded. METHODS: Formant frequencies F1, F2, and F3 and bandwidths BW1, BW2, and BW3 of the sustained vowels were determined using spectrographic analysis. Correlations among AHI, clinical parameters, and formants and bandwidths were determined. RESULTS: Correlations between AHI and clinical variables were stronger than those between AHI and voice features. AHI only correlates poorly with BW2 of /a/ and BW3 of /e/. A number of further weak but significant correlations have been detected between voice and clinical variables. Most of them were for height and age, with two higher values for age and F2 of /o/ and F2 of /u/. Only few very weak correlations were detected between voice and BMI, weight and cervical perimeter, wich are the clinical variables more correlated with AHI. CONCLUSIONS: No significant correlations were detected between AHI and formant frequencies and bandwidths. Correlations between voice and other clinical factors characterizing OSA are weak but highlight the importance of considering indirect or mediated effects of such clinical variables in any research on speech and OSA.

Speech Signal and Facial Image Processing for Obstructive Sleep Apnea Assessment.

Obstructive sleep apnea (OSA) is a common sleep disorder characterized by recurring breathing pauses during sleep caused by a blockage of the upper airway (UA). OSA is generally diagnosed through a costly procedure requiring an overnight stay of the patient at the hospital. This has led to proposing less costly procedures based on the analysis of patients' facial images and voice recordings to help in OSA detection and severity assessment. In this paper we investigate the use of both image and speech processing to estimate the apnea-hypopnea index, AHI (which describes the severity of the condition), over a population of 285 male Spanish subjects suspected to suffer from OSA and referred to a Sleep Disorders Unit. Photographs and voice recordings were collected in a supervised but not highly controlled way trying to test a scenario close to an OSA assessment application running on a mobile device (i.e., smartphones or tablets). Spectral information in speech utterances is modeled by a state-of-the-art low-dimensional acoustic representation, called i-vector. A set of local craniofacial features related to OSA are extracted from images after detecting facial landmarks using Active Appearance Models (AAMs). Support vector regression (SVR) is applied on facial features and i-vectors to estimate the AHI.