• 学术搜索
  • 科研智能体
    • Research Labs
    • AI 阅读
    • AI 文库
    • 深度研究
    • 学者亮点
  • 学术资源
    • AI2000
    • 期刊/会议
    • 学者库
    • 学术API
      MCP&Skill
    • 溯源树
    • 数据集
  • 知识沉淀
    • 学术空间
订阅小程序
旧版功能
aminer vip
开通会员低至0.73元/天
一次搞定AI科研
立即登录
  • English
  • 联系方式
    蒙大拿大學理工學院

    蒙大拿大學理工學院

    Montana Technological University
    院校
    754论文总数
    9,036引用总数

    Montana Technological University, popularly known as Montana Tech, is a public university in Butte, Montana. Founded in 1900 as the Montana State School of Mines, the university became affiliated with the University of Montana in 1994. After undergoing several names changes, in 2017 the Montana University System Board of Regents voted to designate Montana Tech as part of Special Focus Four-Year Universities, the only such designation in the Montana University System. To recognize this new designation and the greater independence with it, the name was officially changed in 2018 from Montana Tech of the University of Montana to Montana Technological University. Montana Tech's focus is on engineering, applied and health science.In fall 2017, Montana Tech had nearly 2,700 students, 13 campus buildings and offers 45 undergraduate degrees along with 15 minors, 11 certification degrees, and 10 pre-professional career programs. Montana Tech also offers 21 graduate degrees and has Ph.D. programs in Materials Science and Engineering and Earth Science and Engineering.D.D. programs in Materials Science and Engineering and Earth Science and Engineering.

    论文量&引用量时间轴

    机构学者

    论文(754)

    年份
    起
    –
    止
    排序
    1A Closed-Form Persistence-Landmark Pipeline for Certified Point-Cloud and Graph Classification
    Sushovan Majhi,Atish Mitra,Ziga Virk, Pramita Bagchi

    We introduce PLACE (Persistence-Landmark Analytic Classification Engine), a closed-form pipeline for classifying point clouds and graphs through their persistent-homology signatures. Three quantitative guarantees—a margin-based excess-risk rate, a closed-form descriptor-selection rule, and a per-prediction certificate—are derived from training labels alone, with no learned weights or held-out calibration. The embedding sums Mitra–Virk single-point coordinate functions over a sparse landmark grid; the closed-form weight rule $w_k^2 \propto (d_{k+1}^2 - d_k^2)/R_k^2$ maximizes the distortion slope in Mitra–Virk's affine certificate under $\nu$-coherence. The guarantees take the following form. (i) An $O(kR/(\Delta\sqrt{m_{\min}}))$ bound on the excess risk over the empirical $\rho$-margin loss, driven by class-mean separation $\Delta$ and embedding radius $R$, paired in the sample-starved regime $m \lesssim R/\Delta$ with a Le Cam two-point identifiability lower bound ($m = \Omega(R/\Delta)$ needed to tell two $\Delta$-separated populations apart). (ii) The Mahalanobis margin under Ledoit–Wolf-shrunk covariance is the empirically strongest closed-form ranker on a heterogeneous 64-descriptor chemical-graph pool (mean Spearman $\rho = +0.56$ across 11 benchmarks, positive on 10 of 11); the isotropic surrogate $\Delta/\sqrt\ell$ admits a closed-form selection-consistency rate on the homogeneous protein/social pools. (iii) A training-time-decided agreement diagnostic for the nearest-centroid rule, with no per-prediction overhead, in three concrete radii (Pinelis, Gaussian plug-in, and variance-aware Pinelis–Bernstein); it bounds when the empirical and population nearest-centroid rules provably coincide, not whether a prediction is correct. Empirically, PLACE is the strongest diagram-based method on Orbit5k; its closed-form descriptor selector runs a mean 2.2 pp below the in-pool oracle across the graph benchmarks, and that oracle matches the strongest topology-based baseline within statistical noise on MUTAG and COX2. Remaining gaps fall into two diagnosable regimes (descriptor blindness on NCI1/NCI109; pool-coverage limits elsewhere). Carried with its full finite-sample Bernstein term and honest firing condition, the variance-aware radius clears only three benchmarks (NCI1, NCI109, DD); on the others it does not, though on MUTAG the empirical and population nearest-centroid rules nonetheless agree on every one of 940 held-out test predictions.

    TMLR引用:5
    引用
    AI阅读
    加入学术空间
    2A Closed-Form Adaptive-Landmark Kernel for Certified Point-Cloud and Graph Classification
    Sushovan Majhi,Atish Mitra,Žiga Virk, Pramita Bagchi

    We introduce PALACE (Persistence Adaptive-Landmark Analytic Classification Engine), the data-adaptive companion to PLACE, paying a small cross-validation tier on three knobs (budget, radii, bandwidth; ≤ 5 choices each). A cover-theoretic core (Lebesgue-number criterion on the landmark cover) yields four closed-form guarantees. (i) A structural lower distortion bound λ(τ;ν) on 𝒟_n under cross-diagram non-interference, with a (D/L)^2 budget reduction over the uniform grid when diagrams concentrate. (ii) Equal weights w_k = K^-1/2 maximizing λ, and farthest-point-sampling positions 2-approximating the optimal k-center covering radius; both derived from training labels alone, no gradient training. (iii) A kernel-RKHS classification rate O((k-1)√(K)/(γ√(m_min))) with binary necessity threshold m = Ω(√(K)/γ) from a matching Le Cam lower bound, and a closed-form filtration-selection rule. The kernel-Mahalanobis margin _Mah is the strongest closed-form ranker across the chemical-graph pool (mean Spearman ρ≈ +0.60); the isotropic surrogate /√(K) admits a selection-consistency rate, and from (i) provides an independent data-level signal (positive on COX2 and PTC). (iv) A per-prediction certificate, in non-asymptotic Pinelis and asymptotic Gaussian forms, with no calibration split. Empirically, PALACE is the strongest closed-form diagram-based method on Orbit5k (91.3 ± 1.0%, matching Persformer), leads every diagram-based competitor on COX2 and MUTAG, and is competitive on DHFR (within 1 pp of ECP). At 8× domain inflation, adaptive placement maintains 94% while the uniform grid collapses to chance (25% on 4-class data).

    2026引用:5
    引用
    AI阅读
    加入学术空间
    3Interpretable Classification of Time Series Using Euler Characteristic Surfaces
    Buddha Nath Sharma, Vishal Mandal,Salam Rabindrajit Luwang, Md. Nurujjaman,Atish J. Mitra,Sushovan Majhi

    Persistent homology (PH)–the conventional method in topological data analysis–is computationally expensive, requires further vectorization of its signatures before machine learning (ML) can be applied, and captures information along only the spatial axis. For time series data, we propose Euler Characteristic Surfaces (ECS) as an alternative topological signature based on the Euler characteristic ($$\chi$$)–a fundamental topological invariant. The ECS provides a computationally efficient, spatiotemporal, and inherently discretized feature representation that can serve as direct input to ML models. We prove a stability theorem guaranteeing that the ECS remains stable under small perturbations of the input time series. We first demonstrate that ECS effectively captures nontrivial topological differences between the limit cycle and the strange attractor in the Rössler system. We then develop an ECS-based classification framework and apply it to five benchmark biomedical datasets (four ECG, one EEG) from the UCR/UEA archive. On ECG5000, our single-feature ECS classifier achieves $$98\%$$ accuracy with $$O(n+R\cdot T)$$ complexity, compared with the $$62\%$$ reported by a recent interpretability-focused PH-based method under closely matched protocol settings (same single-feature threshold-classifier setup and identical UCR train/test split); this remains a literature-based comparison rather than a fully reimplemented head-to-head benchmark. An AdaBoost extension raises accuracy to $$98.6\%$$, comparable with deep learning results while retaining full interpretability. Strong results are also obtained on TwoLeadECG ($$94.1\%$$) and Epilepsy2 ($$92.6\%$$).

    2026引用:2
    引用
    AI阅读
    加入学术空间
    4Unsupervised Topological Characterization of Slug, Churn and Annular Flow in Small-Diameter Vertical Pipes Using Euler Characteristic Surfaces
    Brady Koenig,Sushovan Majhi,Atish Mitra, Abigail Stein, Burt Todd

    Regime transitions in vertical gas-liquid flow are read from mechanistic models or assigned by eye, and for churn flow neither route has produced a settled criterion. We ask how much an unsupervised topological description of flow video can establish about them. The description is the Euler characteristic surface, a count of the connected gas and liquid regions in each frame across morphological scales. Kernels derived from it are combined by unsupervised multiple kernel learning, and the trials are divided into contiguous groups along gas velocity. For 37 air-water trials in 2-in. tubing at one liquid rate, with three viewing stations averaged, four groups are separated at 4.33, 7.51 and 11.70 m/s. Each division falls at or within one trial of a change in the visual evaluation of the same videos; cuts placed at random would match as closely in 12

    2026引用:2
    引用
    AI阅读
    加入学术空间
    5Vietoris–Rips Shadow for Euclidean Graph Reconstruction
    Rafal Komendarczyk,Sushovan Majhi, Atish Mitra

    The shadow of an abstract simplicial complex 𝒦 with vertices in ℝ^N is a subset of ℝ^N defined as the union of the convex hulls of simplices of 𝒦 . The Vietoris–Rips complex of a metric space (𝒮,d) at scale β is an abstract simplicial complex whose each k-simplex corresponds to (k+1) points of 𝒮 within diameter β . In case 𝒮⊂ℝ^2 and d(a,b)=‖ a-b‖ the standard Euclidean metric, the natural shadow projection of the Vietoris–Rips complex is already proved by Chambers et al. to induce isomorphisms on π _0 and π _1 . We extend the result beyond the standard Euclidean distance on 𝒮⊂ℝ^N to a family of path-based metrics, d^ε _𝒮 . From the pairwise Euclidean distances of points in 𝒮 , we introduce a family (parametrized by ε ) of path-based Vietoris–Rips complexes ℛ^ε _β (𝒮) for a scale β >0 . If 𝒮⊂ℝ^2 is Hausdorff-close to a planar Euclidean graph 𝒢 , we provide quantitative bounds on scales β ,ε for the shadow projection map of the Vietoris–Rips complex of (𝒮,d^ε _𝒮) at scale β to induce π _1 -isomorphism. This paper first studies the homotopy-type recovery of 𝒢⊂ℝ^N using the abstract Vietoris–Rips complex of a Hausdorff-close sample 𝒮 under the d^ε _𝒮 metric. Then, our result on the π _1 -isomorphism induced by the shadow projection lends itself to providing also a geometrically close embedding for the reconstruction. Based on the length of the shortest loop and large-scale distortion of the embedding of 𝒢 , we quantify the choice of a suitable sample density ε and a scale β at which the shadow of ℛ^ε _β (𝒮) is homotopy-equivalent and Hausdorff-close to 𝒢 .

    2026Journal of Applied and Computational Topology(2026)引用:2
    引用
    AI阅读
    加入学术空间
    立即登录,查看全部 754 篇论文

    合作机构(100)

    蒙大拿州立大学合作论文 35
    蒙大拿大学合作论文 26
    桑迪亚国家实验室合作论文 18
    内华达大学雷诺分校合作论文 11
    美国能源部合作论文 10
    乔治华盛顿大学校园合作论文 10
    犹他大学合作论文 9
    怀俄明大学合作论文 9
    成都理工大学合作论文 8
    亚利桑那大学合作论文 8

    机构统计