Search

In recent years, agents have become capable of communicating seamlessly via natural language and navigating in environments that involve cooperation and competition, a fact that can introduce social dilemmas. Due to the interleaving of cooperation and competition, understanding agents' decision-making in such environments is challenging, and humans can benefit from obtaining explanations. However, such environments and scenarios have rarely been explored in the context of explainable AI. While some explanation methods for cooperative environments can be applied in mixed-motive setups, they do not address inter-agent competition, cheap-talk, or implicit communication by actions. In this work, we design explanation methods to address these issues. Then, we proceed to establish generality and demonstrate the applicability of the methods to three games with vastly different properties. Lastly, we demonstrate the effectiveness and usefulness of the methods for humans in two mixed-motive games. The first is a challenging 7-player game called no-press Diplomacy. The second is a 3-player game inspired by the prisoner's dilemma, featuring communication in natural language., Comment: To be published in AAAI 2025

This paper proposes a multi-day needs-based model for activity and travel demand analysis. The model captures the multi-day dynamics in activity generation, which enables the modeling of activities with increased flexibility in time and space (e.g., e-commerce and remote working). As an enhancement to activity-based models, the proposed model captures the underlying decision-making process of activity generation by accounting for psychological needs as the drivers of activities. The level of need satisfaction is modeled as a psychological inventory, whose utility is optimized via decisions on activity participation, location, and duration. The utility includes both the benefit in the inventory gained and the cost in time, monetary expense as well as maintenance of safety stock. The model includes two sub-models, a Deterministic Model that optimizes the utility of the inventory, and an Empirical Model that accounts for heterogeneity and stochasticity. Numerical experiments are conducted to demonstrate model scalability. A maximum likelihood estimator is proposed, the properties of the log-likelihood function are examined and the recovery of true parameters is tested. This research contributes to the literature on transportation demand models in the following three aspects. First, it is arguably better grounded in psychological theory than traditional models and allows the generation of activity patterns to be policy-sensitive (while avoiding the need for ad hoc utility definitions). Second, it contributes to the development of needs-based models with a non-myopic approach to model multi-day activity patterns. Third, it proposes a tractable model formulation via problem reformulation and computational enhancements, which allows for maximum likelihood parameter estimation., Comment: 38 pages, 11 figures

The quasistellar neutron spectrum produced via $^{7}$Li($p$, $n$)$^{7}$Be reaction at a proton energy of 1.912 MeV has been extensively studied and employed reaction for neutron-induced reaction studies. We are working towards using this reaction at various proton energies from 1.9 MeV to 3.6 MeV to produce a neutron field at a temperature range of $\sim$1.5-3.5 GK to conduct measurements of neutron-induced charge particle reaction cross sections on various unstable nuclei at explosive stellar temperatures. In this paper, we are reporting our design and simulation study with regards to experimental set-up and a gaseous detector with a segmented Micromegas detector for conducting neutron-induced charge particle reactions studies for nuclei of astrophysics importance, for example, $^{26}$Al($n$, $p$)$^{26}$Mg, $^{26}$Al($n$, $\alpha$)$^{23}$Na and $^{40}$K($n$, $p$)$^{40}$Ar, $^{40}$K($n$, $\alpha$)$^{37}$Cl reactions. We plan to perform our experiments with a 10-$\mu$A proton beam at the Physikalisch Technische Bundesanstalt facility (PTB, Germany), with a Micromegas-based gaseous detector under construction as discussed in the paper.

The distributional impacts of congestion pricing have been widely studied in the literature and the evidence on this is mixed. Some studies find that pricing is regressive whereas others suggest that it can be progressive or neutral depending on the specific spatial characteristics of the urban region, existing activity and travel patterns, and the design of the pricing scheme. Moreover, the welfare and distributional impacts of pricing have largely been studied in the context of passenger travel whereas freight has received relatively less attention. In this paper, we examine the impacts of several third-best congestion pricing schemes on both passenger transport and freight in an integrated manner using a large-scale microsimulator (SimMobility) that explicitly simulates the behavioral decisions of the entire population of individuals and business establishments, dynamic multimodal network performance, and their interactions. Through simulations of a prototypical North American city, we find that a distance-based pricing scheme yields the largest welfare gains, although the gains are a modest fraction of toll revenues (around 30\%). In the absence of revenue recycling or redistribution, distance-based and cordon-based schemes are found to be particularly regressive. On average, lower income individuals lose as a result of the scheme, whereas higher income individuals gain. A similar trend is observed in the context of shippers -- small establishments having lower shipment values lose on average whereas larger establishments with higher shipment values gain. We perform a detailed spatial analysis of distributional outcomes, and examine the impacts on network performance, activity generation, mode and departure time choices, and logistics operations.

Major depressive disorder (MDD) is a heterogeneous condition; multiple underlying neurobiological substrates could be associated with treatment response variability. Understanding the sources of this variability and predicting outcomes has been elusive. Machine learning has shown promise in predicting treatment response in MDD, but one limitation has been the lack of clinical interpretability of machine learning models. We analyzed data from six clinical trials of pharmacological treatment for depression (total n = 5438) using the Differential Prototypes Neural Network (DPNN), a neural network model that derives patient prototypes which can be used to derive treatment-relevant patient clusters while learning to generate probabilities for differential treatment response. A model classifying remission and outputting individual remission probabilities for five first-line monotherapies and three combination treatments was trained using clinical and demographic data. Model validity and clinical utility were measured based on area under the curve (AUC) and expected improvement in sample remission rate with model-guided treatment, respectively. Post-hoc analyses yielded clusters (subgroups) based on patient prototypes learned during training. Prototypes were evaluated for interpretability by assessing differences in feature distributions and treatment-specific outcomes. A 3-prototype model achieved an AUC of 0.66 and an expected absolute improvement in population remission rate compared to the sample remission rate. We identified three treatment-relevant patient clusters which were clinically interpretable. It is possible to produce novel treatment-relevant patient profiles using machine learning models; doing so may improve precision medicine for depression. Note: This model is not currently the subject of any active clinical trials and is not intended for clinical use.

In most cities, transit consists solely of fixed-route transportation, whence the inherent limited Quality of Service for travellers in suburban areas and during off-peak periods. On the other hand, completely replacing fixed-route (FR) with demand-responsive (DR) transit would imply a huge operational cost. It is still unclear how to integrate DR transportation into current transit systems to take full advantage of it. We propose a Continuous Approximation model of a transit system that gets the best from fixed-route and DR transportation. Our model allows deciding whether to deploy a FR or a DR feeder, in each sub-region of an urban conurbation and each time of day, and to redesign the line frequencies and the stop spacing of the main trunk service. Since such a transit design can adapt to the spatial and temporal variation of the demand, we call it Adaptive Transit. Numerical results show that, with respect to conventional transit, Adaptive Transit significantly improves user-related cost, by drastically reducing access time to the main trunk service. Such benefits are particularly remarkable in the suburbs. Moreover, the generalized cost, including agency and user cost, is also reduced. These findings are also confirmed in scenarios with automated vehicles. Our model can assist in planning future-generation transit systems, able to improve urban mobility by appropriately combining fixed and DR transportation., Comment: 57 pages, 13 figures

Self-supervised learning aims to learn image feature representations without the usage of manually annotated labels. It is often used as a precursor step to obtain useful initial network weights which contribute to faster convergence and superior performance of downstream tasks. While self-supervision allows one to reduce the domain gap between supervised and unsupervised learning without the usage of labels, the self-supervised objective still requires a strong inductive bias to downstream tasks for effective transfer learning. In this work, we present our material and texture based self-supervision method named MATTER (MATerial and TExture Representation Learning), which is inspired by classical material and texture methods. Material and texture can effectively describe any surface, including its tactile properties, color, and specularity. By extension, effective representation of material and texture can describe other semantic classes strongly associated with said material and texture. MATTER leverages multi-temporal, spatially aligned remote sensing imagery over unchanged regions to learn invariance to illumination and viewing angle as a mechanism to achieve consistency of material and texture representation. We show that our self-supervision pre-training method allows for up to 24.22% and 6.33% performance increase in unsupervised and fine-tuned setups, and up to 76% faster convergence on change detection, land cover classification, and semantic segmentation tasks.

Calibration is an essential process to make an agent-based simulator operational. Especially, the calibration for freight demand is challenging due to the model complexity and the shortage of available freight demand data compared with passenger data. This paper proposes a novel calibration method that relies solely on screenline counts, named Screenline-based Two-step Calibration (SLTC). SLTC consists of two parts: (1) tour-based demand adjustment and (2) model parameter updates. The former generates screenline-based tours by cloning/removing instances of the simulated goods vehicle tours, aiming to minimize the gaps between the observed and the simulated screenline counts. The latter updates the parameters of the commodity flow model which generates inputs to simulate goods vehicle tours. To demonstrate the practicality of the proposed method, we apply it to an agent-based urban freight simulator, SimMobility Freight. The result shows that SLTC allows the simulator to replicate the observed screenline counts with reasonable computational cost for calibration.

A precise estimate of allele and haplotype polymorphism is of great interest in theoretical population genetics, but also has practical applications, such as bone marrow registries management. Allele polymorphism is driven mainly by point mutations, while haplotype polymorphism is also affected by recombination. Current estimates treat recombination as mutations in an infinite site model. We here show that even in the simple case of two loci in a haploid individual, for a finite population, most recombination events produce existing haplotypes, and as such are silent. Silent recombination considerably reduces the total number of haplotypes expected from the infinite site model for populations that are not much larger than one over the mutation rate. Moreover, in contrast with mutations, the number of haplotypes does not grow linearly with the population size. We hence propose a more accurate estimate of the total number of haplotypes that takes into account silent recombination. We study large-scale Human Leukocyte Antigen (HLA) haplotype frequencies from human populations to show that the current estimated recombination rate in the HLA region is underestimated., Comment: 12 pages, 7 figures

The costly process of obtaining semantic segmentation labels has driven research towards weakly supervised semantic segmentation (WSSS) methods, using only image-level, point, or box labels. The lack of dense scene representation requires methods to increase complexity to obtain additional semantic information about the scene, often done through multiple stages of training and refinement. Current state-of-the-art (SOTA) models leverage image-level labels to produce class activation maps (CAMs) which go through multiple stages of refinement before they are thresholded to make pseudo-masks for supervision. The multi-stage approach is computationally expensive, and dependency on image-level labels for CAMs generation lacks generalizability to more complex scenes. In contrary, our method offers a single-stage approach generalizable to arbitrary dataset, that is trainable from scratch, without any dependency on pre-trained backbones, classification, or separate refinement tasks. We utilize point annotations to generate reliable, on-the-fly pseudo-masks through refined and filtered features. While our method requires point annotations that are only slightly more expensive than image-level annotations, we are to demonstrate SOTA performance on benchmark datasets (PascalVOC 2012), as well as significantly outperform other SOTA WSSS methods on recent real-world datasets (CRAID, CityPersons, IAD).

This is a methodological guide to the use of deep neural networks in the processing of pulsed dipolar spectroscopy (PDS) data encountered in structural biology, organic photovoltaics, photosynthesis research, and other domains featuring long-lived radical pairs and paramagnetic metal ions. PDS uses distance dependence of magnetic dipolar interactions; measuring a single well-defined distance is straightforward, but extracting distance distributions is a hard and mathematically ill-posed problem requiring careful regularisation and background fitting. Neural networks do this exceptionally well, but their "robust black box" reputation hides the complexity of their design and training - particularly when the training dataset is effectively infinite. The objective of this paper is to give insight into training against simulated databases, to discuss network architecture choices, to describe options for handling DEER (double electron-electron resonance) and RIDME (relaxation-induced dipolar modulation enhancement) experiments, and to provide a practical data processing flowchart.

Simulation-based Dynamic Traffic Assignment models have important applications in real-time traffic management and control. The efficacy of these systems rests on the ability to generate accurate estimates and predictions of traffic states, which necessitates online calibration. A widely used solution approach for online calibration is the Extended Kalman Filter (EKF), which -- although appealing in its flexibility to incorporate any class of parameters and measurements -- poses several challenges with regard to calibration accuracy and scalability, especially in congested situations for large-scale networks. This paper addresses these issues in turn so as to improve the accuracy and efficiency of EKF-based online calibration approaches for large and congested networks. First, the concept of state augmentation is revisited to handle violations of the Markovian assumption typically implicit in online applications of the EKF. Second, a method based on graph-coloring is proposed to operationalize the partitioned finite-difference approach that enhances scalability of the gradient computations. Several synthetic experiments and a real world case study demonstrate that application of the proposed approaches yields improvements in terms of both prediction accuracy and computational performance. The work has applications in real-world deployments of simulation-based dynamic traffic assignment systems., Comment: 26 pages, 15 figures

To improve outcomes in math, many Texas colleges are adopting mathematics pathways, which accelerate developmental math and tailor math courses to different majors instead of requiring all students to take algebra. This study examines whether students participating in Dana Center Mathematics Pathways (DCMP) developmental courses enroll in and pass college-level math courses at higher rates than students who take traditional developmental math courses. It employs regression analysis controlling for student characteristics using student-level data compiled by the state from the more than 20 Texas community colleges that implemented the DCMP model in 2015 and 2016. Results from this study are encouraging. They suggest that DCMP compressed prerequisite developmental courses are effective at accelerating community college students through their math requirements. Yet this study also found systematic sorting of students into DCMP by race/ethnicity, which could exacerbate educational inequalities. Key findings include: (1) DCMP students were about 13 percentage points more likely to enroll in college-level math in the next semester and 8 percentage points more likely to pass college-level math in that term than peers in non-DCMP developmental courses; (2) The advantaged gained by DCMP students was maintained over time--there was still a 5-percentage-point improvement in passing college-level math two years later among students in the fall 2015 cohort; and (3) Compared with non-DCMP courses, DCMP courses included more White students and fewer Hispanic students than would be expected based on the distribution of students at the colleges. This indicates inequality in subgroup access to reformed developmental math pathways.

This paper discusses capabilities that are essential to models applied in policy analysis settings and the limitations of direct applications of off-the-shelf machine learning methodologies to such settings. Traditional econometric methodologies for building discrete choice models for policy analysis involve combining data with modeling assumptions guided by subject-matter considerations. Such considerations are typically most useful in specifying the systematic component of random utility discrete choice models but are typically of limited aid in determining the form of the random component. We identify an area where machine learning paradigms can be leveraged, namely in specifying and systematically selecting the best specification of the random component of the utility equations. We review two recent novel applications where mixed-integer optimization and cross-validation are used to algorithmically select optimal specifications for the random utility components of nested logit and logit mixture models subject to interpretability constraints.

Tradable mobility credit (TMC) schemes are an approach to travel demand management that have received significant attention in recent years. This paper proposes and analyzes alternative market models for a TMC system -- focusing on market design aspects such as allocation/expiration of tokens, rules governing trading, transaction fees, and regulator intervention -- and develops a methodology to explicitly model the dis-aggregate behavior of individuals within the market. Extensive simulation experiments are conducted within a combined mode and departure time context for the morning commute problem to compare the performance of the alternative designs relative to congestion pricing and a no-control scenario. The simulation experiments employ a day-to-day assignment framework wherein transportation demand is modeled using a logit-mixture model with income effects and supply is modeled using a standard bottleneck model. The results indicate that small fixed transaction fees can effectively mitigate undesirable behavior in the market without a significant loss in efficiency (total welfare) whereas proportional transaction fees are less effective both in terms of efficiency and in avoiding undesirable market behavior. Further, an allocation of tokens in continuous time can be beneficial in dealing with non-recurrent events and avoiding concentrated trading activity. In the presence of income effects, despite small fixed transaction fees, the TMC system yields a marginally higher social welfare than congestion pricing while attaining revenue neutrality. Further, it is more robust in the presence of forecasting errors and non-recurrent events due to the adaptiveness of the market. Finally, as expected, the TMC scheme is more equitable (when revenues from congestion pricing are not redistributed) although it is not guaranteed to be Pareto-improving when tokens are distributed equally.

The emergence of ride-sourcing platforms has brought an innovative alternative in transportation, radically changed travel behaviors, and suggested new directions for transportation planners and operators. This paper provides an exploratory analysis on the operations of a ride-sourcing service using large-scale data on service performance. Observations over multiple days in Singapore suggest reproducible demand patterns and provide empirical estimates of fleet operations over time and space. During peak periods, we observe significant increases in the service rate along with surge price multipliers. We perform an in-depth analysis of fleet utilization rates and are able to explain daily patterns based on drivers' behavior by involving the number of shifts, shift duration, and shift start and end time choices. We also evaluate metrics of user experience, namely waiting and travel time distribution, and explain our empirical findings with distance metrics from driver trajectory analysis and congestion patterns. Our results of empirical observations on actual service in Singapore can help to understand the spatiotemporal characteristics of ride-sourcing services and provide important insights for transportation planning and operations., Comment: 18 pages, 11 figures, 5 tables

Technological advancements have brought increasing attention to Automated Mobility on Demand (AMOD) as a promising solution that may improve future urban mobility. During the last decade, extensive research has been conducted on the design and evaluation of AMOD systems using simulation models. This paper adds to this growing body of literature by investigating the network impacts of AMOD through high-fidelity activity- and agent-based traffic simulation, including detailed models of AMOD fleet operations. Through scenario simulations of the entire island of Singapore, we explore network traffic dynamics by employing the concept of the Macroscopic Fundamental Diagram (MFD). Taking into account the spatial variability of density, we are able to capture the hysteresis loops, which inevitably form in a network of this size. Model estimation results at both the vehicle and passenger flow level are documented. Environmental impacts including energy and emissions are also discussed. Findings from the case study of Singapore suggest that the introduction of AMOD may bring about significant impacts on network performance in terms of increased VKT, additional travel delay and energy consumption, while reducing vehicle emissions, with respect to the baseline. Despite the increase in network congestion, production of passenger flows remains relatively unchanged., Comment: 29 pages, 9 figures, 6 tables, submitted to the journal Simulation Modelling Practice and Theory

Machine vision for precision agriculture has attracted considerable research interest in recent years. The goal of this paper is to develop an end-to-end cranberry health monitoring system to enable and support real time cranberry over-heating assessment to facilitate informed decisions that may sustain the economic viability of the farm. Toward this goal, we propose two main deep learning-based modules for: 1) cranberry fruit segmentation to delineate the exact fruit regions in the cranberry field image that are exposed to sun, 2) prediction of cloud coverage conditions and sun irradiance to estimate the inner temperature of exposed cranberries. We develop drone-based field data and ground-based sky data collection systems to collect video imagery at multiple time points for use in crop health analysis. Extensive evaluation on the data set shows that it is possible to predict exposed fruit's inner temperature with high accuracy (0.02% MAPE). The sun irradiance prediction error was found to be 8.41-20.36% MAPE in the 5-20 minutes time horizon. With 62.54% mIoU for segmentation and 13.46 MAE for counting accuracies in exposed fruit identification, this system is capable of giving informed feedback to growers to take precautionary action (e.g. irrigation) in identified crop field regions with higher risk of sunburn in the near future. Though this novel system is applied for cranberry health monitoring, it represents a pioneering step forward for efficient farming and is useful in precision agriculture beyond the problem of cranberry overheating., Comment: IEEE Winter Conference on Applications of Computer Vision (WACV) 2021

The e-commerce delivery demand has grown rapidly in the past two decades and such trend has accelerated tremendously due to the ongoing coronavirus pandemic. Given the situation, the need for predicting e-commerce delivery demand and evaluating relevant logistics solutions is increasing. However, the existing simulation models for e-commerce delivery demand are still limited and do not consider the delivery options and their attributes that shoppers face on e-commerce order placements. We propose a novel modeling framework which jointly predicts the average total value of e-commerce purchase, the purchase amount per transaction, and delivery option choices. The proposed framework can simulate the changes in e-commerce delivery demand attributable to the changes in delivery options. We assume the model parameters based on various sources of relevant information and conduct a demonstrative sensitivity analysis. Furthermore, we have applied the model to the simulation for the Auto-Innovative Prototype city. While the calibration of the model using real-world survey data is required, the result of the analysis highlights the applicability of the proposed framework.

Time-sensitive parcel deliveries, shipments requested for delivery in a day or less, are an increasingly important research subject. It is challenging to deal with these deliveries from a carrier perspective since it entails additional planning constraints, preventing an efficient consolidation of deliveries which is possible when demand is well known in advance. Furthermore, such time-sensitive deliveries are requested to a wider spatial scope than retail centers, including homes and offices. Therefore, an increase in such deliveries is considered to exacerbate negative externalities such as congestion and emissions. One of the solutions is to leverage spare capacity in passenger transport modes. This concept is often denominated as cargo-hitching. While there are various possible system designs, it is crucial that such solution does not deteriorate the quality of service of passenger trips. This research aims to evaluate the use of Mobility-On-Demand services to perform same-day parcel deliveries. For this purpose, we use SimMobility, a high-resolution agent-based simulation platform of passenger and freight flows, applied in Singapore. E-commerce demand carrier data are used to characterize simulated parcel delivery demand. Operational scenarios that aim to minimize the adverse effect of fulfilling deliveries with Mobility-On-Demand vehicles on Mobility-On-Demand passenger flows (fulfillment, wait and travel times) are explored. Results indicate that the Mobility-On-Demand services have potential to fulfill a considerable amount of parcel deliveries and decrease freight vehicle traffic and total vehicle-kilometers-travelled without compromising the quality of Mobility On-Demand for passenger travel., Comment: 19 pages, 4 tables, 7 figures. Submitted to Transportation (Springer)

Accurate flood detection in near real time via high resolution, high latency satellite imagery is essential to prevent loss of lives by providing quick and actionable information. Instruments and sensors useful for flood detection are only available in low resolution, low latency satellites with region re-visit periods of up to 16 days, making flood alerting systems that use such satellites unreliable. This work presents H2O-Network, a self supervised deep learning method to segment floods from satellites and aerial imagery by bridging domain gap between low and high latency satellite and coarse-to-fine label refinement. H2O-Net learns to synthesize signals highly correlative with water presence as a domain adaptation step for semantic segmentation in high resolution satellite imagery. Our work also proposes a self-supervision mechanism, which does not require any hand annotation, used during training to generate high quality ground truth data. We demonstrate that H2O-Net outperforms the state-of-the-art semantic segmentation methods on satellite imagery by 10% and 12% pixel accuracy and mIoU respectively for the task of flood segmentation. We emphasize the generalizability of our model by transferring model weights trained on satellite imagery to drone imagery, a highly different sensor and domain., Comment: Submitted to WACV2021

Understanding customer behavior is fundamental for many use-cases in industry, especially in accelerated growth areas such as fin-tech and e-commerce. Structured data are often expensive, time-consuming and inadequate to analyze and study complex customer behaviors. In this paper, we propose a multi-graph embedding approach for creating a non-linear representation of customers in order to have a better knowledge of their characteristics without having any prior information about their financial status or their interests. By applying the current method we are able to predict users' future behavior with a reasonably high accuracy only by having the information of their friendship network. Potential applications include recommendation systems and credit risk forecasting., Comment: 6 pages, 4 figures

This study investigates the efficiency and effectiveness of an area-based tradable credit scheme (TCS) using the trip-based Macroscopic Fundamental Diagram model for the morning commute problem. In the proposed TCS, the regulator distributes initial credits to all travelers and designs a time-varying and trip length specific credit tariff. Credits are traded between travelers and the regulator via a credit market, and the credit price is determined by the demand and supply of credits. The heterogeneity of travelers is considered in terms of desired arrival time, trip length and departure-time choice preferences. The TCS is incorporated into a day-to-day modelling framework to examine the travelers' learning process, the evolution of network, and the properties of the credit market. The existence of an equilibrium solution and the uniqueness of the credit price at the equilibrium state are established analytically. Furthermore, an open-source simulation framework is developed to validate the analytical properties of the proposed TCS and compare it with alternative control strategies in terms of mobility, network performance, and social welfare. Bayesian optimization is then adopted to optimize the credit toll scheme. The numerical results demonstrate that the proposed TCS outperforms the no-control case and matches the performance of the time-of-day pricing strategy, while maintaining revenue-neutral nature., Comment: 44 pages, 11 figures