arXiv subjects

Michael Xie

Publications and source records attributed to Michael Xie.

6 recordsLinked to original sources

arXiv2026

Evaluation Principles for MRI-MRA Registration in Trigeminal Neuralgia: An ROI-Centered Neurovascular Benchmark

Preoperative evaluation of trigeminal neuralgia (TN) often requires joint interpretation of structural MRI, which depicts the trigeminal nerve and surrounding cisternal anatomy, and time-of-flight MRA, which highlights vascular structures. Although MRI-MRA fusion is clinically attractive for visualizing neurovascular compression, this task is poorly captured by conventional whole-brain registration evaluation because the clinically relevant target is a small trigeminal ROI, vessel annotations are partial and clinically focused, local TOF-MRA contrast is variable, and field-of-view mismatch can limit deformable alignment. We formulate TN MRI-MRA fusion as an ROI-centered neurovascular registration-evaluation problem and construct a benchmark from 149 patients with clinician-annotated bilateral trigeminal ROIs. Six representative registration pipelines were evaluated using local image-based metrics, segmentation-derived vessel-localization metrics, prediction-volume analysis, and contrast- and FOV-stratified comparisons. Conventional evaluation summaries were often misleading: local image similarity, vessel-background separability, and downstream vessel localization did not co-rank methods; one-sided vessel distances were strongly affected by predicted vessel extent under partial annotations; and local MRA contrast determined when vessel-separability metrics were informative. Deformable refinement provided only a small, FOV-dependent benefit over affine alignment, while reader review showed that locally favorable vessel distances could coexist with globally implausible registrations. These findings indicate that TN MRI-MRA registration should be evaluated as a local, vessel-aware, contrast-sensitive, and FOV-aware visualization task rather than as generic multimodal brain registration. Our code is publicly available at https://github.com/jhuldr/TN-Reg-Benchmark.

cs.CV↗

arXiv2026

Differentially Private Graph Coloring

Differential Privacy is the gold standard in privacy-preserving data analysis. This paper addresses the challenge of computing an edge-differentially private vertex coloring. In this paper, we present two novel algorithms for this problem. Both algorithms begin by coloring each vertex uniformly at random from a fixed-size palette, and then apply the exponential mechanism to locally resample colors for either all vertices or a selected subset of vertices. Any non-trivial edge differentially private coloring of a graph needs to be defective, as a proper coloring exposes the non-existence of an edge between two vertices of the same color. A coloring is $k$-defective if each vertex shares its color with at most $k$ of its neighbors. Our goal is to design coloring algorithms that use the minimum number of colors, while achieving the smallest possible defect under the edge-differential privacy. Our first algorithm applies to $d$-inductive graphs with maximum degree $\Delta$. We show that it yields a $3\epsilon$-differentially private coloring with $O(\frac{\log n}{\epsilon}+d)$ maximum defect, using a palette of size $\Theta(\frac{\Delta}{\log n}+\frac{1}{\epsilon})$. Our second algorithm utilizes noisy thresholding to guarantee $O(\frac{\log n}{\epsilon})$ maximum defect, using a palette of size $\Theta(\frac{\Delta}{\log n}+\frac{1}{\epsilon})$, generalizing the results to all graphs rather than just $d$-inductive ones.

cs.DS↗

arXiv2026

BenchMarker: An Education-Inspired Toolkit for Highlighting Flaws in Multiple-Choice Benchmarks

Multiple-choice question answering (MCQA) is standard in NLP, but benchmarks lack rigorous quality control. We present BenchMarker, an education-inspired toolkit using LLM judges to flag three common MCQ flaws: 1) contamination: items appearing exactly online; 2) shortcuts: cues in the choices that enable guessing; and 3) writing errors: structural/grammatical issues based on a 19-rule education rubric. We validate BenchMarker with human annotations, then run the tool to audit 12 benchmarks, revealing: 1) flaws persist in MCQA benchmarks, especially automatically-made and crowdsourced data - we detect 47% of TruthfulQA appears online and 100% of HellaSwag violates multiple writing rules; 2) contaminated MCQs tend to inflate accuracy, while writing errors tend to lower it and change rankings beyond random; and 3) prior benchmark repairs address their targeted issues (i.e., lowering accuracy with LLM-written distractors), but inadvertently add new flaws (i.e. implausible distractors, many correct answers). Overall, flaws in MCQs degrade NLP evaluation, but education research offers a path forward. We release BenchMarker to bridge the fields and improve MCQA benchmark design.

cs.CL↗

arXiv2019

A Soft Range Limited K-Nearest Neighbours Algorithm for Indoor Localization Enhancement

This paper proposes a soft range limited K nearest neighbours (SRL-KNN) localization fingerprinting algorithm. The conventional KNN determines the neighbours of a user by calculating and ranking the fingerprint distance measured at the unknown user location and the reference locations in the database. Different from that method, SRL-KNN scales the fingerprint distance by a range factor related to the physical distance between the user's previous position and the reference location in the database to reduce the spatial ambiguity in localization. Although utilizing the prior locations, SRL-KNN does not require knowledge of the exact moving speed and direction of the user. Moreover, to take into account of the temporal fluctuations of the received signal strength indicator (RSSI), RSSI histogram is incorporated into the distance calculation. Actual on-site experiments demonstrate that the new algorithm achieves an average localization error of $0.66$ m with $80\%$ of the errors under $0.89$ m, which outperforms conventional KNN algorithms by $45\%$ under the same test environment.

eess.SP↗

arXiv2016

Hierarchical Online Intrusion Detection for SCADA Networks

We propose a novel hierarchical online intrusion detection system (HOIDS) for supervisory control and data acquisition (SCADA) networks based on machine learning algorithms. By utilizing the server-client topology while keeping clients distributed for global protection, high detection rate is achieved with minimum network impact. We implement accurate models of normal-abnormal binary detection and multi-attack identification based on logistic regression and quasi-Newton optimization algorithm using the Broyden-Fletcher-Goldfarb-Shanno approach. The detection system is capable of accelerating detection by information gain based feature selection or principle component analysis based dimension reduction. By evaluating our system using the KDD99 dataset and the industrial control system dataset, we demonstrate that HOIDS is highly scalable, efficient and cost effective for securing SCADA infrastructures.

cs.CR↗

arXiv2016

Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping

The lack of reliable data in developing countries is a major obstacle to sustainable development, food security, and disaster relief. Poverty data, for example, is typically scarce, sparse in coverage, and labor-intensive to obtain. Remote sensing data such as high-resolution satellite imagery, on the other hand, is becoming increasingly available and inexpensive. Unfortunately, such data is highly unstructured and currently no techniques exist to automatically extract useful insights to inform policy decisions and help direct humanitarian efforts. We propose a novel machine learning approach to extract large-scale socioeconomic indicators from high-resolution satellite imagery. The main challenge is that training data is very scarce, making it difficult to apply modern techniques such as Convolutional Neural Networks (CNN). We therefore propose a transfer learning approach where nighttime light intensities are used as a data-rich proxy. We train a fully convolutional CNN model to predict nighttime lights from daytime imagery, simultaneously learning features that are useful for poverty prediction. The model learns filters identifying different terrains and man-made structures, including roads, buildings, and farmlands, without any supervision beyond nighttime lights. We demonstrate that these learned features are highly informative for poverty mapping, even approaching the predictive performance of survey data collected in the field.

cs.CV↗