Consider the dispatch of ridesharing trips to drivers lining up at airports, or the allocation of deceased donor organs to patients in transplant wait lists. In such dynamic queueing games, heterogeneity in short-lived items combined with agents' discretion to decline induce substantial cherrypicking, resulting in high rates of unfulfilled trips and discarded organs. Existing research typically focuses on easy-to-analyze dispatch policies, sometimes making fluid assumptions for tractability. In this work, we introduce a best-response-based solver for general dispatch policies with closed-form updates, which computes agents' equilibrium acceptance, entry, and reneging strategies as functions of queue length and queue position. For a family of dispatch policies where dispatch probabilities are queue-length independent and items are offered monotonically down the queue, we prove that our solver converges to a Markov perfect equilibrium in a finite number of iterations and that such an equilibrium always exists. For more general dispatch policies, we characterize their equilibria, and the solver converges in simulation despite the lack of theoretical guarantees. Via extensive numerical results, we show that the solver recovers known equilibria for policies that can be analyzed theoretically, and provides insights (beyond what can be gleaned from previous analysis) into more complex policies better suited for practice.

Medical image segmentation challenges stem from complex lesion morphologies and real-time clinical needs. Here we present MAR-Net, a novel framework that integrates adaptive attention mechanisms, hierarchical contextual modeling, and efficient training strategies to address these challenges. The architecture employs a CBAM-based dual-attention module to dynamically enhance discriminative features while suppressing redundant information, improving lesion boundary localization. Cascaded dilated convolutions expand the receptive field for global context capture, complemented by a multi-scale decoder that integrates deep semantic and shallow spatial features. A multi-scale training strategy with hierarchical loss supervision optimizes model adaptability without compromising inference efficiency. Experimental validation on ISIC and CholecSeg8K datasets demonstrates MAR-Net’s superiority: it outperforms mainstream methods across segmentation accuracy, recall rate, and other metrics, achieving notable improvements for complex lesions of varying sizes. Notably, MAR-Net maintains high performance on both dermoscopic and laparoscopic images, showcasing its broad applicability. These results confirm MAR-Net as a robust medical segmentation solution, balancing precision and efficiency for clinical use.

Neurological dysfunction encompasses a variety of diseases resulting from neural damage. Accurate assessment of neurological function is critical for diagnosis and the development of effective treatment plans. A significant number of patients with neurological disorders exhibit ocular abnormalities. Analyzing ocular status through eye movement capture plays a pivotal role in understanding various neurological dysfunctions. However, current methods of analyzing ocular status for neurological function assessments lack precision and objectivity, often relying heavily on physicians’ subjective judgment. This work proposes the Ocular-enhanced Face Keypoints Network (OFKNet), a facial keypoint detection model based on deep convolutional neural networks. OFKNet employs ConvNeXt as its backbone network and introduces a multi-scale input enhancement strategy. Additionally, a region enhancement module based on MobileNetV3 is designed to optimize features in the canthus area. Multiscale feature fusion and channel weighting are achieved through an improved Path Aggregation Network and Squeeze-and-Excitation modules. To validate OFKNet’s accuracy, we compared it with state-of-the-art models, including MediaPipe FaceLandmarker, InsightFace, Dlib68, and Dlib81, using a patient dataset we collected. Experimental results demonstrate that OFKNet outperforms existing models, particularly in calibration accuracy around the eyes. By monitoring eye movements in real-time, OFKNet ensures high-precision extraction of key points in each frame, accurately reflecting changes in patients’ ocular movements.

Accurate estimated time of arrival (ETA) prediction for long vehicular trips remains challenging in intelligent transportation systems (ITS) due to heterogeneous traffic patterns and limited local data availability. While federated learning (FL) addresses privacy concerns by decentralizing data training, traditional FL frameworks often struggle with high computational costs and poor adaptability to multi-task scenarios. To overcome these limitations, this paper proposes a Lightweight Multi-task Federated Learning (LMFL) framework for efficient and privacy-preserving ETA prediction. LMFL integrates a novel SE-CIFG, combining a Squeeze-Excitation (SE) attention module to prioritize critical spatio-temporal features and a Coupled Input and Forget Gate (CIFG) to simplify long-term traffic dependency modeling. Additionally, LMFL employs a Federated Gradient Compression Algorithm (FedGCA) to reduce communication overhead between edge and cloud using adaptive thresholding and sparse tensor encoding. Real-world traffic simulation dataset demonstrates that LMFL achieves significantly higher predictive accuracy compared to existing methods, achieving an average 17.1% improvement in prediction precision while reducing training time by 4.1%.

How significant was the role of racial preferences in U.S. college admissions before the Supreme Court's 2023 decision to ban race-based affirmative action? How much might test-optional admission policies impact racial diversity and academic merit? In this work, we estimate a simple model of college admissions decisions from 2012--2021, leveraging a novel dataset of applicant profiles and admissions outcomes across the full spectrum of college selectivity. We find that, broadly, the impact of race and testing policies on diversity and merit of admits decreases by college selectivity. For America's less selective colleges that collectively enroll over three-quarters of students, fully eliminating racial preferences---expressed either directly or via unobserved correlates---has little impact on the proportion of underrepresented minorities (URM) and on the average SAT score of admitted students. In contrast, for the 34 most selective colleges accounting for 3 percent of total enrollment, our estimates suggest that admissions going "race blind"---absent any compensating changes in admissions criteria---could reduce URM admission by one-third while increasing the average SAT score of admits by no more than 10 points. We also estimate that universal test-optional admission does not materially affect the proportion of URMs at elite colleges, and may decrease the average SAT score by up to 10 points. At less selective institutions, the effects are estimated to be negligible.

With the exacerbation of bridge aging issues, the demand for efficient and cost-effective bridge inspection solutions becomes increasingly urgent. Currently, most methods for surface damage detection on bridges employ single-modal, image-based object detection models. Despite their overall effectiveness on specific datasets, such methods frequently encounter error detection issues during actual inspection processes. This study proposes a multimodal (image and text) model for surface damage detection in bridge structures by combining the CLIP model with the YOLOv8 model. By conducting tests on the composite concrete bridge of the Jiaozhou Bay Bridge, Qingdao, the effectiveness of bridge detection using drones is validated, and the common issue of false positive detections in traditional object detection models is successfully addressed.

We study the matching of jobs to workers waiting in a queue, for example a ridesharing platform dispatching drivers to pick up riders at an airport. Under FIFO dispatching, the heterogeneity in earnings from different trips incentivizes drivers to cherrypick, increasing riders' waiting times for a match, and resulting in poor reliability for riders, low average earnings for drivers, and a loss of throughput and revenue for the platform. Simple fixes by limiting dispatching transparency or drivers' flexibility are neither desirable nor fully effective. Optimal origin-destination based prices are incentive aligned in theory, but are hard to implement in practice due to operational constraints.

We study revenue-optimal pricing and driver compensation in ridesharing platforms when drivers have heterogeneous preferences over locations. If a platform ignores drivers' location preferences, it may make inefficient trip dispatches; moreover, drivers may strategize so as to route towards their preferred locations. In a model with stationary and continuous demand and supply, we present a mechanism that incentivizes drivers to both (i) report their location preferences truthfully and (ii) always provide service. In settings with unconstrained driver supply or symmetric demand patterns, our mechanism achieves (full-information) first-best revenue. Under supply constraints and unbalanced demand, we show via simulation that our mechanism improves over existing mechanisms and has performance close to the first-best.

Without monetary payments, the Gibbard-Satterthwaite theorem proves that under mild requirements all truthful social choice mechanisms must be dictatorships. When payments are allowed, the Vickrey-Clarke-Groves (VCG) mechanism implements the value-maximizing choice, and has many other good properties: it is strategy-proof, onto, deterministic, individually rational, and does not not make positive transfers to the agents. By Roberts' theorem, with three or more alternatives, the weighted VCG mechanisms are essentially unique for domains with quasi-linear utilities. The goal of this paper is to characterize domains of non-quasi-linear utilities where "reasonable'' mechanisms (with VCG-like properties) exist. Our main result is a tight characterization of the maximal non quasi-linear utility domain, which we call the largest parallel domain. We extend Roberts' theorem to parallel domains, and use the generalized theorem to prove two impossibility results. First, any reasonable mechanism must be dictatorial when the type domain is quasi-linear together with any single non-parallel type. Second, for richer utility domains that still differ very slightly from quasi-linearity, every strategy-proof, onto and deterministic mechanism must be a dictatorship.

Power companies such as Southern California Edison (SCE) uses Demand Response (DR) contracts to incentivize consumers to reduce their power consumption during periods when demand forecast exceeds supply. Current mechanisms in use offer contracts to consumers independent of one another, do not take into consideration consumers' heterogeneity in consumption profile or reliability, and fail to achieve high participation. We introduce DR-VCG, a new DR mechanism that offers a flexible set of contracts (which may include the standard SCE contracts) and uses VCG pricing. We prove that DR-VCG elicits truthful bids, incentivizes honest preparation efforts, and enables efficient computation of allocation and prices. With simple fixed-penalty contracts, the optimization goal of the mechanism is an upper bound on probability that the reduction target is missed. Extensive simulations show that compared to the current mechanism deployed by SCE, the DR-VCG mechanism achieves higher participation, increased reliability, and significantly reduced total expenses.

Cellular network providers collect and use a wide variety of data for assessing the service quality experienced by their smartphone users. The data is essential for tasks ranging from event detection, problem diagnosis, impact analysis, coverage and capacity planning, load balancing, and performance optimization. For example, service quality measurements and data from drive-by tests provide useful and detailed information about different aspects of quality of service such as dropped calls due to handovers or radio interference. However, a major challenge for effective service quality management in operational setup is the presence of missing or unavailable data. Furthermore, the cellular data is inherently multidimensional, i.e. is a function of several variables such as location, device type, and time. Motivated by recent advances in handling multidimensional data, we propose to use tensor algebraic models and methods for cellular data prediction. The main idea is to model the data as a low rank tensor and use a rank constrained interpolation for data prediction. We focus on two recently proposed algebraic models employing two different notions of tensor rank. We test and compare the performance of the two approaches on real-world data sets collected from an operational cellular network and indicate the regimes in which one method is superior to the other. Based on these observations the proposed algorithm chooses the best of the two approaches using cross-validation.