arXiv subjects

Jinhua Zhao

Publications and source records attributed to Jinhua Zhao.

104 records · Page 6Linked to original sources

arXiv2021

Deep Neural Networks for Choice Analysis: Architectural Design with Alternative-Specific Utility Functions

Whereas deep neural network (DNN) is increasingly applied to choice analysis, it is challenging to reconcile domain-specific behavioral knowledge with generic-purpose DNN, to improve DNN's interpretability and predictive power, and to identify effective regularization methods for specific tasks. This study designs a particular DNN architecture with alternative-specific utility functions (ASU-DNN) by using prior behavioral knowledge. Unlike a fully connected DNN (F-DNN), which computes the utility value of an alternative k by using the attributes of all the alternatives, ASU-DNN computes it by using only k's own attributes. Theoretically, ASU-DNN can dramatically reduce the estimation error of F-DNN because of its lighter architecture and sparser connectivity. Empirically, ASU-DNN has 2-3% higher prediction accuracy than F-DNN over the whole hyperparameter space in a private dataset that we collected in Singapore and a public dataset in R mlogit package. The alternative-specific connectivity constraint, as a domain-knowledge-based regularization method, is more effective than the most popular generic-purpose explicit and implicit regularization methods and architectural hyperparameters. ASU-DNN is also more interpretable because it provides a more regular substitution pattern of travel mode choices than F-DNN does. The comparison between ASU-DNN and F-DNN can also aid in testing the behavioral knowledge. Our results reveal that individuals are more likely to compute utility by using an alternative's own attributes, supporting the long-standing practice in choice modeling. Overall, this study demonstrates that prior behavioral knowledge could be used to guide the architecture design of DNN, to function as an effective domain-knowledge-based regularization method, and to improve both the interpretability and predictive power of DNN in choice analysis.

cs.LG↗

arXiv2021

Competition between shared autonomous vehicles and public transit: A case study in Singapore

Emerging autonomous vehicles (AV) can either supplement the public transportation (PT) system or compete with it. This study examines the competitive perspective where both AV and PT operators are profit-oriented with dynamic adjustable supply strategies under five regulatory structures regarding whether the AV operator is allowed to change the fleet size and whether the PT operator is allowed to adjust headway. Four out of the five scenarios are constrained competition while the other one focuses on unconstrained competition to find the Nash Equilibrium. We evaluate the competition process as well as the system performance from the standpoints of four stakeholders -- the AV operator, the PT operator, passengers, and the transport authority. We also examine the impact of PT subsidies on the competition results including both demand-based and supply-based subsidies. A heuristic algorithm is proposed to update supply strategies for AV and PT based on the operators' historical actions and profits. An agent-based simulation model is implemented in the first-mile scenario in Tampines, Singapore. We find that the competition can result in higher profits and higher system efficiency for both operators compared to the status quo. After the supply updates, the PT services are spatially concentrated to shorter routes feeding directly to the subway station and temporally concentrated to peak hours. On average, the competition reduces the travel time of passengers but increases their travel costs. Nonetheless, the generalized travel cost is reduced when incorporating the value of time. With respect to the system efficiency, the bus supply adjustment increases the average vehicle load and reduces the total vehicle kilometer traveled measured by the passenger car equivalent (PCE), while the AV supply adjustment does the opposite.

physics.soc-ph↗

arXiv2021

Estimating the potential for shared autonomous scooters

Recent technological developments have shown significant potential for transforming urban mobility. Considering first- and last-mile travel and short trips, the rapid adoption of dockless bike-share systems showed the possibility of disruptive change, while simultaneously presenting new challenges, such as fleet management or the use of public spaces. In this paper, we evaluate the operational characteristics of a new class of shared vehicles that are being actively developed in the industry: scooters with self-repositioning capabilities. We do this by adapting the methodology of shareability networks to a large-scale dataset of dockless bike-share usage, giving us estimates of ideal fleet size under varying assumptions of fleet operations. We show that the availability of self-repositioning capabilities can help achieve up to 10 times higher utilization of vehicles than possible in current bike-share systems. We show that actual benefits will highly depend on the availability of dedicated infrastructure, a key issue for scooter and bicycle use. Based on our results, we envision that technological advances can present an opportunity to rethink urban infrastructures and how transportation can be effectively organized in cities.

cs.CY↗

arXiv2021

Individual Mobility Prediction: An Interpretable Activity-based Hidden Markov Approach

Individual mobility is driven by demand for activities with diverse spatiotemporal patterns, but existing methods for mobility prediction often overlook the underlying activity patterns. To address this issue, this study develops an activity-based modeling framework for individual mobility prediction. Specifically, an input-output hidden Markov model (IOHMM) framework is proposed to simultaneously predict the (continuous) time and (discrete) location of an individual's next trip using transit smart card data. The prediction task can be transformed into predicting the hidden activity duration and end location. Based on a case study of Hong Kong's metro system, we show that the proposed model can achieve similar prediction performance as the state-of-the-art long short-term memory (LSTM) model. Unlike LSTM, the proposed IOHMM model can also be used to analyze hidden activity patterns, which provides meaningful behavioral interpretation for why an individual makes a certain trip. Therefore, the activity-based prediction framework offers a way to preserve the predictive power of advanced machine learning methods while enhancing our ability to generate insightful behavioral explanations, which is useful for enhancing situational awareness in user-centric transportation applications such as personalized traveler information.

cs.LG↗

arXiv2020

Modeling Epidemic Spreading through Public Transit using Time-Varying Encounter Network

Passenger contact in public transit (PT) networks can be a key mediate in the spreading of infectious diseases. This paper proposes a time-varying weighted PT encounter network to model the spreading of infectious diseases through the PT systems. Social activity contacts at both local and global levels are also considered. We select the epidemiological characteristics of coronavirus disease 2019 (COVID-19) as a case study along with smart card data from Singapore to illustrate the model at the metropolitan level. A scalable and lightweight theoretical framework is derived to capture the time-varying and heterogeneous network structures, which enables to solve the problem at the whole population level with low computational costs. Different control policies from both the public health side and the transportation side are evaluated. We find that people's preventative behavior is one of the most effective measures to control the spreading of epidemics. From the transportation side, partial closure of bus routes helps to slow down but cannot fully contain the spreading of epidemics. Identifying "influential passengers" using the smart card data and isolating them at an early stage can also effectively reduce the epidemic spreading.

physics.soc-ph↗

arXiv2020

Theory-based residual neural networks: A synergy of discrete choice models and deep neural networks

Researchers often treat data-driven and theory-driven models as two disparate or even conflicting methods in travel behavior analysis. However, the two methods are highly complementary because data-driven methods are more predictive but less interpretable and robust, while theory-driven methods are more interpretable and robust but less predictive. Using their complementary nature, this study designs a theory-based residual neural network (TB-ResNet) framework, which synergizes discrete choice models (DCMs) and deep neural networks (DNNs) based on their shared utility interpretation. The TB-ResNet framework is simple, as it uses a ($δ$, 1-$δ$) weighting to take advantage of DCMs' simplicity and DNNs' richness, and to prevent underfitting from the DCMs and overfitting from the DNNs. This framework is also flexible: three instances of TB-ResNets are designed based on multinomial logit model (MNL-ResNets), prospect theory (PT-ResNets), and hyperbolic discounting (HD-ResNets), which are tested on three data sets. Compared to pure DCMs, the TB-ResNets provide greater prediction accuracy and reveal a richer set of behavioral mechanisms owing to the utility function augmented by the DNN component in the TB-ResNets. Compared to pure DNNs, the TB-ResNets can modestly improve prediction and significantly improve interpretation and robustness, because the DCM component in the TB-ResNets stabilizes the utility functions and input gradients. Overall, this study demonstrates that it is both feasible and desirable to synergize DCMs and DNNs by combining their utility specifications under a TB-ResNet framework. Although some limitations remain, this TB-ResNet framework is an important first step to create mutual benefits between DCMs and DNNs for travel behavior modeling, with joint improvement in prediction, interpretation, and robustness.

cs.LG↗

arXiv2020

Profiling presence patterns and segmenting user locations from cell phone data

The dynamic monitoring of commuting flows is crucial for improving transit systems in fast-developing cities around the world. However, existing methodology to infer commuting originations and destinations have to either rely on large-scale survey data, which is inherently expensive to implement, or on Call Detail Records but based on ad-hoc heuristic assignment rules based on the frequency of appearance at given locations. In this paper, we proposed a novel method to accurately infer the point of origin and destinations of commuting flows based on individual's spatial-temporal patterns inferred from Call Detail Records. Our project significantly improves the accuracy upon the heuristic assignment rules popularly adopted in the literature. Starting with the historical data of geo-temporal travel patterns for a panel of individuals, we create, for each person-location, a vector of probability distribution capturing the likelihood that the person will appear in that location for a given the time of day. Stacked in this way, the matrix of historical geo-temporal data enables us to apply Eigen-decomposition and use unsupervised machine learning techniques to extract commonalities across locations for the different groups of travelers, which ultimately allows us to make inferences and create labels, such as home and work, on specific locations. Testing the methodology on real-world data with known location labels shows that our method identifies home and workplaces with significant accuracy, improving upon the most commonly used methods in the literature by 79% and 34%, respectively. Most importantly, our methodology does not bear any significant computation burden and is easily scalable and easily expanded to other real-world data with historical tracking.

cs.SI↗

arXiv2020

Assignment-based Path Choice Estimation for Metro Systems Using Smart Card Data

Urban rail services are the principal means of public transportation in many cities. To understand the crowding patterns and develop efficient operation strategies in the system, obtaining path choices is important. This paper proposed an assignment-based path choice estimation framework using automated fare collection (AFC) data. The framework captures the inherent correlation of crowding among stations, as well as the interaction between path choice and left behind. The path choice estimation is formulated as an optimization problem. The original problem is intractable because of a non-analytical constraint and a non-linear equation constraint. A solution procedure is proposed to decompose the original problem into three tractable sub-problems, which can be solved efficiently. The model is validated using both synthetic data and real-world AFC data in Hong Kong Mass Transit Railway (MTR) system. The synthetic data test validates the model's effectiveness in estimating path choice parameters, which can outperform the purely simulation-based optimization methods in both accuracy and efficiency. The test results using actual data show that the estimated path shares are more reasonable than survey-derived path shares and uniform path shares. Model robustness in terms of different initial values and different case study dates are also verified.

cs.DS↗

arXiv2019

Deep Neural Networks for Choice Analysis: A Statistical Learning Theory Perspective

While researchers increasingly use deep neural networks (DNN) to analyze individual choices, overfitting and interpretability issues remain as obstacles in theory and practice. By using statistical learning theory, this study presents a framework to examine the tradeoff between estimation and approximation errors, and between prediction and interpretation losses. It operationalizes the DNN interpretability in the choice analysis by formulating the metrics of interpretation loss as the difference between true and estimated choice probability functions. This study also uses the statistical learning theory to upper bound the estimation error of both prediction and interpretation losses in DNN, shedding light on why DNN does not have the overfitting issue. Three scenarios are then simulated to compare DNN to binary logit model (BNL). We found that DNN outperforms BNL in terms of both prediction and interpretation for most of the scenarios, and larger sample size unleashes the predictive power of DNN but not BNL. DNN is also used to analyze the choice of trip purposes and travel modes based on the National Household Travel Survey 2017 (NHTS2017) dataset. These experiments indicate that DNN can be used for choice analysis beyond the current practice of demand forecasting because it has the inherent utility interpretation, the flexibility of accommodating various information formats, and the power of automatically learning utility specification. DNN is both more predictive and interpretable than BNL unless the modelers have complete knowledge about the choice task, and the sample size is small. Overall, statistical learning theory can be a foundation for future studies in the non-asymptotic data regime or using high-dimensional statistical models in choice analysis, and the experiments show the feasibility and effectiveness of DNN for its wide applications to policy and behavioral analysis.

econ.GN↗

arXiv2019

Multitask Learning Deep Neural Networks to Combine Revealed and Stated Preference Data

It is an enduring question how to combine revealed preference (RP) and stated preference (SP) data to analyze travel behavior. This study presents a framework of multitask learning deep neural networks (MTLDNNs) for this question, and demonstrates that MTLDNNs are more generic than the traditional nested logit (NL) method, due to its capacity of automatic feature learning and soft constraints. About 1,500 MTLDNN models are designed and applied to the survey data that was collected in Singapore and focused on the RP of four current travel modes and the SP with autonomous vehicles (AV) as the one new travel mode in addition to those in RP. We found that MTLDNNs consistently outperform six benchmark models and particularly the classical NL models by about 5% prediction accuracy in both RP and SP datasets. This performance improvement can be mainly attributed to the soft constraints specific to MTLDNNs, including its innovative architectural design and regularization methods, but not much to the generic capacity of automatic feature learning endowed by a standard feedforward DNN architecture. Besides prediction, MTLDNNs are also interpretable. The empirical results show that AV is mainly the substitute of driving and AV alternative-specific variables are more important than the socio-economic variables in determining AV adoption. Overall, this study introduces a new MTLDNN framework to combine RP and SP, and demonstrates its theoretical flexibility and empirical power for prediction and interpretation. Future studies can design new MTLDNN architectures to reflect the speciality of RP and SP and extend this work to other behavioral analysis.

econ.GN↗

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

Dynamic Pricing in Shared Mobility on Demand Service

We consider a profit maximization problem in an urban mobility on-demand service, of which the operator owns a fleet, provides both exclusive and shared trip services, and dynamically determines prices of offers. With knowledge of the traveler preference and the distribution of future trip requests, the operator wants to find the pricing strategy that optimizes the total operating profit of multiple trips during a specific period, namely, a day in this paper. This problem is first formulated and analyzed within the dynamic programming framework, where a general approach combining parametric rollout policy and stochastic optimization is proposed. A discrete-choice-based price optimization model is then used for the request level optimal decision problem and leads to a practical and computationally tractable algorithm for the problem. Our algorithm is evaluated with a simulated experiment in the urban traffic network in Langfang, China, and it is shown to generate considerably higher profit than naive strategies. Further analysis shows that this method also leads to higher congestion level and lower service capacity in the urban traffic system, which highlights a need for policy interventions that balance the private profit making and the system level optimality.

math.OC↗

arXiv2016

Managing travel demand: Location recommendation for system efficiency based on mobile phone data

Growth in leisure travel has become increasingly significant economically, socially, and environmentally. However, flexible but uncoordinated travel behaviors exacerbate traffic congestion. Mobile phone records not only reveal human mobility patterns, but also enable us to manage travel demand for system efficiency. In this paper, we propose a location recommendation system that infers personal preferences while accounting for constraints imposed by road capacity in order to manage travel demand. We first infer unobserved preferences using a machine learning technique from phone records. We then formulate an optimization method to improve system efficiency. Coupling mobile phone data with traffic counts and road network infrastructures collected in Andorra, this study shows that uncoordinated travel behaviors lead to longer average travel delay, implying the opportunities in managing travel demand by collective decisions. The interplay between congestion relief and overall satisfied location preferences observed in extensive simulations indicate that moderate sacrifices of individual utility lead to significant travel time savings. Specifically, the results show that under full compliance rate, travel delay fell by 52% at a cost of 31% less satisfaction. Under 60% compliance rate, 41% travel delay is saved with a 17% reduction in satisfaction. This paper highlights the effectiveness of the synergy among collective behaviors in increasing system efficiency.

cs.CY↗

arXiv2009

Response delay as a strategy for survival in fluctuating environment

Response time-delay is an ubiquitous phenomenon in biological systems. Here we use a simple stochastic population model with time-delayed switching-rate conversion to quantitatively study the biological influence of the response time-delay on the survival fitness of cells living in periodically fluctuating and stochastic environment, respectively. Our calculation and simulation show that for the cells having a slow rate transition into fit phenotype and a fast rate transition into unfit phenotype, the response time-delay can always enhance their fitness during the environment change. Particularly, in the periodic or stochastic environment with small variance, the optimal fitness achieved by these cells is superior to that of cells with reverse switching rates even if the latter exhibits rapid response. These results suggest that the response time delay may be utilized by cells to enhance their adaptation to the fluctuating environment.

q-bio.PE↗