arXiv subjects

Carlo Ratti

Publications and source records attributed to Carlo Ratti.

At least 73 records · Page 4Linked to original sources

arXiv2018

Deep Learning Architect: Classification for Architectural Design through the Eye of Artificial Intelligence

This paper applies state-of-the-art techniques in deep learning and computer vision to measure visual similarities between architectural designs by different architects. Using a dataset consisting of web scraped images and an original collection of images of architectural works, we first train a deep convolutional neural network (DCNN) model capable of achieving 73% accuracy in classifying works belonging to 34 different architects. Through examining the weights in the trained DCNN model, we are able to quantitatively measure the visual similarities between architects that are implicitly learned by our model. Using this measure, we cluster architects that are identified to be similar and compare our findings to conventional classification made by architectural historians and theorists. Our clustering of architectural designs remarkably corroborates conventional views in architectural history, and the learned architectural features also coheres with the traditional understanding of architectural designs.

cs.CV↗

arXiv2018

Quantifying the sensing power of crowd-sourced vehicle fleets

Sensors can measure air quality, traffic congestion, and other aspects of urban environments. The fine-grained diagnostic information they provide could help urban managers to monitor a city's health. Recently, a `drive-by' paradigm has been proposed in which sensors are deployed on third-party vehicles, enabling wide coverage at low cost} Research on drive-by sensing has mostly focused on sensor engineering, but a key question remains unexplored: How many vehicles would be required to adequately scan a city? Here, we address this question by analyzing the sensing power of a taxi fleet. Taxis, being numerous in cities and typically equipped with some sensing technology (e.g. GPS), are natural hosts for the sensors. Our strategy is to view drive-by sensing as a spreading process, in which the area of sensed terrain expands as sensor-equipped taxis diffuse through a city's streets. In tandem with a simple model for the movements of the taxis, this analogy lets us analytically determine the fraction of a city's street network sensed by a fleet of taxis during a day. Our results agree with taxi data obtained from nine major cities, and reveal that a remarkably small number of taxis can scan a large number of streets. This finding appears to be universal, indicating its applicability to cities beyond those analyzed here. Moreover, because taxi motions combine randomness and regularity (passengers' destinations being random, but the routes to them being deterministic), the spreading properties of taxi fleets are unusual; in stark contrast to random walks, the stationary densities of our taxi model obey Zipf's law, consistent with the empirical taxi data. Our results have direct utility for town councilors, smart-city designers, and other urban decision makers.

physics.soc-ph↗

arXiv2018

Analysis of visitors' mobility patterns through random walk in the Louvre museum

This paper proposes a random walk model to analyze visitors' mobility patterns in a large museum. Visitors' available time makes their visiting styles different, resulting in dissimilarity in the order and number of visited places and in path sequence length. We analyze all this by comparing a simulation model and observed data, which provide us the strength of the visitors' mobility patterns. The obtained results indicate that shorter stay-type visitors exhibit stronger patterns than those with the longer stay-type, confirming that the former are more selective than the latter in terms of their visitation type.

physics.soc-ph↗

arXiv2018

Estimating savings in parking demand using shared vehicles for home-work commuting

The increasing availability and adoption of shared vehicles as an alternative to personally-owned cars presents ample opportunities for achieving more efficient transportation in cities. With private cars spending on the average over 95\% of the time parked, one of the possible benefits of shared mobility is the reduced need for parking space. While widely discussed, a systematic quantification of these benefits as a function of mobility demand and sharing models is still mostly lacking in the literature. As a first step in this direction, this paper focuses on a type of private mobility which, although specific, is a major contributor to traffic congestion and parking needs, namely, home-work commuting. We develop a data-driven methodology for estimating commuter parking needs in different shared mobility models, including a model where self-driving vehicles are used to partially compensate flow imbalance typical of commuting, and further reduce parking infrastructure at the expense of increased traveled kilometers. We consider the city of Singapore as a case study, and produce very encouraging results showing that the gradual transition to shared mobility models will bring tangible reductions in parking infrastructure. In the future-looking, self-driving vehicle scenario, our analysis suggests that up to 50\% reduction in parking needs can be achieved at the expense of increasing total traveled kilometers of less than 2\%.

cs.CY↗

arXiv2018

Treepedia 2.0: Applying Deep Learning for Large-scale Quantification of Urban Tree Cover

Recent advances in deep learning have made it possible to quantify urban metrics at fine resolution, and over large extents using street-level images. Here, we focus on measuring urban tree cover using Google Street View (GSV) images. First, we provide a small-scale labelled validation dataset and propose standard metrics to compare the performance of automated estimations of street tree cover using GSV. We apply state-of-the-art deep learning models, and compare their performance to a previously established benchmark of an unsupervised method. Our training procedure for deep learning models is novel; we utilize the abundance of openly available and similarly labelled street-level image datasets to pre-train our model. We then perform additional training on a small training dataset consisting of GSV images. We find that deep learning models significantly outperform the unsupervised benchmark method. Our semantic segmentation model increased mean intersection-over-union (IoU) from 44.10% to 60.42% relative to the unsupervised method and our end-to-end model decreased Mean Absolute Error from 10.04% to 4.67%. We also employ a recently developed method called gradient-weighted class activation map (Grad-CAM) to interpret the features learned by the end-to-end model. This technique confirms that the end-to-end model has accurately learned to identify tree cover area as key features for predicting percentage tree cover. Our paper provides an example of applying advanced deep learning techniques on a large-scale, geo-tagged and image-based dataset to efficiently estimate important urban metrics. The results demonstrate that deep learning models are highly accurate, can be interpretable, and can also be efficient in terms of data-labelling effort and computational resources.

cs.CV↗

arXiv2018

Towards matching user mobility traces in large-scale datasets

The problem of unicity and reidentifiability of records in large-scale databases has been studied in different contexts and approaches, with focus on preserving privacy or matching records from different data sources. With an increasing number of service providers nowadays routinely collecting location traces of their users on unprecedented scales, there is a pronounced interest in the possibility of matching records and datasets based on spatial trajectories. Extending previous work on reidentifiability of spatial data and trajectory matching, we present the first large-scale analysis of user matchability in real mobility datasets on realistic scales, i.e. among two datasets that consist of several million people's mobility traces, coming from a mobile network operator and transportation smart card usage. We extract the relevant statistical properties which influence the matching process and analyze their impact on the matchability of users. We show that for individuals with typical activity in the transportation system (those making 3-4 trips per day on average), a matching algorithm based on the co-occurrence of their activities is expected to achieve a 16.8% success only after a one-week long observation of their mobility traces, and over 55% after four weeks. We show that the main determinant of matchability is the expected number of co-occurring records in the two datasets. Finally, we discuss different scenarios in terms of data collection frequency and give estimates of matchability over time. We show that with higher frequency data collection becoming more common, we can expect much higher success rates in even shorter intervals.

cs.SI↗

arXiv2018

A novel method for predicting and mapping the presence of sun glare using Google Street View

The sun glare is one of the major environmental hazards that cause traffic accidents. Every year, many people died and injured in traffic accidents related to sun glare. Providing accurate information about when and where sun glare happens would be helpful to prevent sun glare caused traffic accidents and save lives. In this study, we proposed to use publicly accessible Google Street View (GSV) panorama images to estimate and predict the occurrence of sun glare. GSV images have view sight similar to drivers, which would make GSV images suitable for estimating the visibility of sun glare to drivers. A recently developed convolutional neural network algorithm was used to segment GSV images and predict obstructions on sun glare. Based on the predicted obstructions for given locations, we further estimated the time windows of sun glare by estimating the sun positions and the relative angles between drivers and the sun for those locations. We conducted a case study in Cambridge, Massachusetts, USA. Results show that the method can predict the presence of sun glare precisely. The proposed method would provide an important tool for drivers and traffic planners to mitigate the sun glare and decrease the potential traffic accidents caused by the sun glare.

cs.CV↗

arXiv2018

Quantifying memories: mapping urban perception

What people choose to see, like, or remember is of profound interest to city planners and architects. Previous research suggests what people are more likely to store in their memory - buildings with dominant shapes and bright colors, historical sites, and intruding signs - yet little has been done by the systematic survey. This paper attempts to understand the relationships between the spatial structure of the built environment and inhabitants' memory of the city derived from their perceptual knowledge. For this purpose, we employed the web-based visual survey in the form of a geo-guessing game. This enables us to externalize people's spatial knowledge as a large-scale dataset. The result sheds light on unknown aspects of the cognitive role in exploring the built environment, and hidden patterns embedded in the relationship between the spatial elements and the mental map.

physics.soc-ph↗

arXiv2017

Optimality Of Community Structure In Complex Networks

Community detection is one of the pivotal tools for discovering the structure of complex networks. Majority of community detection methods rely on optimization of certain quality functions characterizing the proposed community structure. Perhaps, the most commonly used of those quality functions is modularity. Many heuristics are claimed to be efficient in modularity maximization, which is usually justified in relative terms through comparison of their outcomes with those provided by other known algorithms. However as all the approaches are heuristics, while the complete brute-force is not feasible, there is no known way to understand if the obtained partitioning is really the optimal one. In this article we address the modularity maximization problem from the other side --- finding an upper-bound estimate for the possible modularity values within a given network, allowing to better evaluate suggested community structures. Moreover, in some cases when then upper bound estimate meets the actually obtained modularity score, it provides a proof that the suggested community structure is indeed the optimal one. We propose an efficient algorithm for building such an upper-bound estimate and illustrate its usage on the examples of well-known classical and synthetic networks, being able to prove the optimality of the existing partitioning for some of the networks including well-known Zachary's Karate Club.

cs.SI↗

arXiv2017

Driving Behavior Analysis through CAN Bus Data in an Uncontrolled Environment

Cars can nowadays record several thousands of signals through the CAN bus technology and potentially provide real-time information on the car, the driver and the surrounding environment. This paper proposes a new method for the analysis and classification of driver behavior using a selected subset of CAN bus signals, specifically gas pedal position, brake pedal pressure, steering wheel angle, steering wheel momentum, velocity, RPM, frontal and lateral acceleration. Data has been collected in a completely uncontrolled experiment, where 64 people drove 10 cars for or a total of over 2000 driving trips without any type of pre-determined driving instruction on a wide variety of road scenarios. We propose an unsupervised learning technique that clusters drivers in different groups, and offers a validation method to test the robustness of clustering in a wide range of experimental settings. The minimal amount of data needed to preserve robust driver clustering is also computed. The presented study provides a new methodology for near-real-time classification of driver behavior in uncontrolled environments.

cs.LG↗

arXiv2017

Graph Theoretic Properties of the Darkweb

We collect and analyze the darkweb (a.k.a. the "onionweb") hyperlink graph. We find properties highly dissimilar to the well-studied world wide web hyperlink graph; for example, our analysis finds that >87% of darkweb sites never link to another site. We compare our results to prior work on world-wide-web and speculate about reasons for their differences. We conclude that in the term "darkweb", the word "web" is a connectivity misnomer. Instead, it is more accurate to view the darkweb as a set of largely isolated dark silos.

cs.CR↗

arXiv2017

Analysis of pedestrian behaviors through non-invasive Bluetooth monitoring

This paper analyzes pedestrians' behavioral patterns in the pedestrianized shopping environment in the historical center of Barcelona, Spain. We employ a Bluetooth detection technique to capture a large-scale dataset of pedestrians' behavior over a one-month period, including during a key sales period. We focused on comparing particular behaviors before, during, and after the discount sales by analyzing this large-scale dataset, which is different but complementary to the conventionally used small-scale samples. Our results uncover pedestrians actively exploring a wider area of the district during a discount period compared to weekdays, giving rise to strong underlying mobility patterns.

physics.soc-ph↗

arXiv2016

Scaling Law of Urban Ride Sharing

Sharing rides could drastically improve the efficiency of car and taxi transportation. Unleashing such potential, however, requires understanding how urban parameters affect the fraction of individual trips that can be shared, a quantity that we call shareability. Using data on millions of taxi trips in New York City, San Francisco, Singapore, and Vienna, we compute the shareability curves for each city, and find that a natural rescaling collapses them onto a single, universal curve. We explain this scaling law theoretically with a simple model that predicts the potential for ride sharing in any city, using a few basic urban quantities and no adjustable parameters. Accurate extrapolations of this type will help planners, transportation companies, and society at large to shape a sustainable path for urban growth.

physics.soc-ph↗

arXiv2016

Indoor Space Recognition using Deep Convolutional Neural Network: A Case Study at MIT Campus

In this paper, we propose a robust and parsimonious approach using Deep Convolutional Neural Network (DCNN) to recognize and interpret interior space. DCNN has achieved incredible success in object and scene recognition. In this study we design and train a DCNN to classify a pre-zoning indoor space, and from a single phone photo to recognize the learned space features, with no need of additional assistive technology. We collect more than 600,000 images inside MIT campus buildings to train our DCNN model, and achieved 97.9% accuracy in validation dataset and 81.7% accuracy in test dataset based on spatial-scale fixed model. Furthermore, the recognition accuracy and spatial resolution can be potentially improved through multiscale classification model. We identify the discriminative image regions through Class Activating Mapping (CAM) technique, to observe the model's behavior in how to recognize space and interpret it in an abstract way. By evaluating the results with misclassification matrix, we investigate the visual spatial feature of interior space by looking into its visual similarity and visual distinctiveness, giving insights into interior design and human indoor perception and wayfinding research. The contribution of this paper is threefold. First, we propose a robust and parsimonious approach for indoor navigation using DCNN. Second, we demonstrate that DCNN also has a potential capability in space feature learning and recognition, even under severe appearance changes. Third, we introduce a DCNN based approach to look into the visual similarity and visual distinctiveness of interior space.

cs.CV↗

arXiv2016

Urban association rules: uncovering linked trips for shopping behavior

In this article, we introduce the method of urban association rules and its uses for extracting frequently appearing combinations of stores that are visited together to characterize shoppers' behaviors. The Apriori algorithm is used to extract the association rules (i.e., if -> result) from customer transaction datasets in a market-basket analysis. An application to our large-scale and anonymized bank card transaction dataset enables us to output linked trips for shopping all over the city: the method enables us to predict the other shops most likely to be visited by a customer given a particular shop that was already visited as an input. In addition, our methodology can consider all transaction activities conducted by customers for a whole city in addition to the location of stores dispersed in the city. This approach enables us to uncover not only simple linked trips such as transition movements between stores but also the edge weight for each linked trip in the specific district. Thus, the proposed methodology can complement conventional research methods. Enhancing understanding of people's shopping behaviors could be useful for city authorities and urban practitioners for effective urban management. The results also help individual retailers to rearrange their services by accommodating the needs of their customers' habits to enhance their shopping experience.

physics.soc-ph↗

arXiv2016

Scaling of foreign attractiveness for countries and states

People's behavior on online social networks, which store geo-tagged information showing where people were or are at the moment, can provide information about their offline life as well. In this paper we present one possible research direction that can be taken using Flickr dataset of publicly available geo-tagged media objects (e.g., photographs, videos). Namely, our focus is on investigating attractiveness of countries or smaller large-scale composite regions (e.g., US states) for foreign visitors where attractiveness is defined as the absolute number of media objects taken in a certain state or country by its foreign visitors compared to its population size. We also consider it together with attractiveness of the destination for the international migration, measured through publicly available dataset provided by United Nations. By having those two datasets, we are able to look at attractiveness from two different perspectives: short-term and long-term one. As our previous study showed that city attractiveness for Spanish cities follows a superlinear trend, here we want to see if the same law is also applicable to country/state (i.e., composite regions) attractiveness. Finally, we provide one possible explanation for the obtained results.

cs.SI↗

arXiv2016

An analysis of visitors' behavior in the Louvre Museum: A study using Bluetooth data

Museums often suffer from so-called "hyper-congestion", wherein the number of visitors exceeds the capacity of the physical space of the museum. This can potentially deteriorate the quality of visitor's experience disturbed by other visitors' behaviors and presences. Although this situation can be mitigated by managing visitors' flow between spaces, a detailed analysis of the visitor's movement is required to fully realize and apply a proper solution to the problem. This paper analyzes the visitor's sequential movements, the spatial layout, and the relationship between them in large-scale art museums - Louvre Museum - using anonymized data collected through noninvasive Bluetooth sensors. This enables us to unveil some features of visitor's behavior and spatial impact that shed some light on the mechanism of the museum overcrowding. The analysis reveals that the visiting style of short and long stay visitors are not as significantly different as one could expect. Both types of visitors tend to visit a similar number of key locations in the museum while the longer stay type visitors just tend to do so more extensively. In addition, we reveal that some ways of exploring the museum appear frequently for both types of visitors, although long stay type visitors might be expected to diversify much more given the greater time spent in the museum. We suggest that these similarities/dissimilarities make for an uneven distribution of the quantity of visitors in the museum space. The findings increase the understanding of the unknown behaviors of visitors, which is key to improve the museum's environment and visiting experience.

cs.CY↗

arXiv2016

An analysis of visitors' length of stay through noninvasive Bluetooth monitoring in the Louvre Museum

Art Museums traditionally employ observations and surveys to enhance their knowledge of visitors' behavior and experience. However, these approaches often produce spatially and temporally limited empirical evidence and measurements. Only recently has the ubiquity of digital technologies revolutionized the ability to collect data on human behavior. Consequently, the greater availability of large-scale datasets based on quantifying visitors' behavior provides new opportunities to apply computational and comparative analytical techniques. In this paper, we attempt to analyze visitors' behavior in the Louvre Museum from anonymized longitudinal datasets collected from noninvasive Bluetooth sensors. We examine visitors' length of stay in the museum and consider this relationship with occupation density around artwork. This data analysis increases the knowledge and understanding of museum professionals related to the experience of visitors.

cs.CY↗