检索结果-内蒙古大学图书馆

Multilingual Facial Emotion Decoding and Posture Recognition using Random Forest Classifier

学校读者我要写书评

暂无评论

Multilingual Facial Emotion Decoding and Posture Recognition...

2024 Asian Conference on Intelligent Technologies, ACOIT 2024

作者： Sangeetha, K. Balaji, V.S. Manju, M. Renuka Devi, S. Velayutham, P. Department of Artificial Intelligence and Machine Learning Rajalakshmi Engineering College Chennai India Department of Artificial Intelligence and Data Science Rajalakshmi Engineering College Chennai India Department of Computer Science and Engineering Aarupadai Veedu Institute of Technology Chennai India

ISBN: (纸本)9798350374933

Effective communication is crucial for success in various interactions, including personal and online interviews. The work proposed is to refine the communication effectiveness and extend the understanding of interactions by incorporating new system functions of real-time emotion and body language capture. Facial and body landmarks are analyzed using Google’s Mediapipe to ensure accurate identification of the frequently performed emotions and frequently posed postures. The proposed system uses three classifiers, namely Random Forest, Gradient Boosting, and Ridge Classifier, all integrated in one pipeline;this makes our work distinct. In the testing phase the classifiers are checked to avoid misidentification of emotions or incorrect posture in different situations. One of the major novelties of this work is its ability to address users of different languages, thus it is relevant anywhere in the world. This dynamic and robust system provides accurate emotion analysis achieving the accuracy of 92%, enhancing understanding in various communication contexts and setting a new standard for interview and interaction analysis. © 2024 IEEE.

关键词： Emotion Recognition

Dynamic k-Anonymity for Electronic Health Records: A Topological Framework 19th

学校读者我要写书评

暂无评论

Dynamic k-Anonymity for Electronic Health Records: A Topolo...

19th International Workshop on data Privacy Management, DPM 2024, 8th International Workshop on Cryptocurrencies and Blockchain Technology, CBT 2024 and 10th Workshop on the Security of Industrial Control Systems and of Cyber-Physical Systems, CyberICPS 2024 which were held in conjunction with the 29th European Symposium on Research in Computer Security, ESORICS 2024

作者： Swaminathan, Arjhun Akgün, Mete Medical Data Privacy and Privacy Preserving Machine Learning Department of Computer Science University of Tübingen Tübingen Germany Institute for Bioinformatics and Medical Informatics Tübingen Germany

ISBN: (纸本)9783031823480

With the rapid digitization of Electronic Health Records (EHRs), fast and adaptive data anonymization methods have become increasingly important. While tools from topological data analysis (TDA) have been proposed to anonymize static datasets—allowing the creation of multiple generalizations for different anonymization needs from a single computation—the application to dynamic datasets remains unexplored. To address this, our work adapts existing methodologies to the dynamic setting. We develop an improved version of weighted persistence barcodes that track higher-dimensional holes in data, allowing us to edit persistence information on the fly. Additionally, we introduce filtration trimming, a novel technique designed to update persistence data quickly with minimal computing effort when data is added. Our work represents a significant advancement in healthcare data privacy, offering a refined approach to protecting highly sensitive and evolving patient data through dynamic k-anonymity. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Electronic health record

Bringing closure to FDR control: beating the e-Benjamini-Hochberg procedure

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Xu, Ziyu Fischer, Lasse Ramdas, Aaditya Department of Statistics and Data Science Carnegie Mellon University United States Competence Center for Clinical Trials Bremen University of Bremen Germany Department of Statistics and Data Science Machine Learning Department Carnegie Mellon University United States

False discovery rate (FDR) has been a key metric for error control in multiple hypothesis testing, and many methods have developed for FDR control across a diverse cross-section of settings and applications. We develop a closure principle for all FDR controlling procedures, i.e., we provide a characterization based on e-values for all admissible FDR controlling procedures. A general version of this closure principle can recover any multiple testing error metric and allows one to choose the error metric post-hoc. We leverage this idea to formulate the closed eBH procedure, a (usually strict) improvement over the eBH procedure for FDR control when provided with e-values. This also yields a closed BY (BY) procedure that dominates the Benjamini-Yekutieli (BY) procedure for FDR control with arbitrarily dependent p-values, thus proving that the latter is inadmissibile. We demonstrate the practical performance of our new procedures in simulations. Copyright © 2025, The Authors. All rights reserved.

关键词：

Application of data Mining Techniques in Automobile Insurance Fraud Detection 23

学校读者我要写书评

暂无评论

Application of Data Mining Techniques in Automobile Insuranc...

6th International Conference on Mathematics and statistics, ICoMS 2023

作者： Na Bangchang, Kannat Wongsai, Sangdao Simmachan, Teerawat Department of Mathematics and Statistics Faculty of Science and Technology Thammasat University Pathum Thani Thailand Department of Mathematics and Statistics Thammasat University Research Unit in Data Learning Faculty of Science and Technology Thammasat University Pathum Thani Thailand

ISBN: (纸本)9798400700187

The insurance industry is a fast-growing industry and handles substantial amounts of data. Fraudulent claims are the main problem in the industry. Auto insurance fraud is one of the most prominent types of insurance fraud. Numerous fraudulent claims affect not only the insurance company but also the sincere policy holders because of the increasing in premium amounts. Therefore, detection of insurance fraud is a challenging problem. Traditional approaches are hard to handle and inefficient. data mining has recently offered significant contributions to insurance analysis. To overcome this, data mining techniques are used to predict fraudulent claims. This work would help in a screening process to investigate claims, thus minimizing human resources and monetary losses. Three sets of features are obtained by logistic regression models: one with forward selection, one with backward elimination, and one without variable selection. Three algorithms including Naïve Bayes, random forest and adaptive boosting are employed as classifiers. K-fold cross validation is used to evaluate the algorithm performance. The results suggest that the smaller number of features, the better performance. The random forest performs the best with highest accuracy (85.28%), sensitivity (93.85%), and precision (97.91%) whereas the adaptive boosting provides the highest specificity (70.41%) and F-score (89.86%). © 2023 ACM.

关键词： Adaptive Boosting Naïve Bayes Random Forest Variable Selection

Graph fission and cross-validation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Leiner, James Ramdas, Aaditya Department of Statistics and Data Science Carnegie Mellon University United States Machine Learning Department Carnegie Mellon University United States

We introduce a technique called graph fission which takes in a graph which potentially contains only one observation per node (whose distribution lies in a known class) and produces two (or more) independent graphs with the same node/edge set in a way that splits the original graph’s information amongst them in any desired proportion. Our proposal builds on data fission/thinning, a method that uses external randomization to create independent copies of an unstructured dataset. We extend this idea to the graph setting where there may be latent structure between observations. We demonstrate the utility of this framework via two applications: inference after structural trend estimation on graphs and a model selection procedure we term "graph cross-validation". Copyright © 2024, The Authors. All rights reserved.

关键词： machine learning

Sharp Matrix Empirical Bernstein Inequalities

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Hongjian Ramdas, Aaditya Department of Statistics and Data Science Carnegie Mellon University United States Machine Learning Department Carnegie Mellon University United States

We present two sharp empirical Bernstein inequalities for symmetric random matrices with bounded eigenvalues. By sharp, we mean that both inequalities adapt to the unknown variance in a tight manner: the deviation captured by the first-order 1/√n term asymptotically matches the matrix Bernstein inequality exactly, including constants, the latter requiring knowledge of the variance. Our first inequality holds for the sample mean of independent matrices, and our second inequality holds for a mean estimator under martingale dependence at stopping times. Copyright © 2024, The Authors. All rights reserved.

关键词： Matrix algebra

Positive Semidefinite Matrix Supermartingales

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Hongjian Ramdas, Aaditya Department of Statistics and Data Science Carnegie Mellon University United States Machine Learning Department Carnegie Mellon University United States

We explore the asymptotic convergence and nonasymptotic maximal inequalities of supermartingales and backward submartingales in the space of positive semidefinite matrices. These are natural matrix analogs of scalar nonnegative supermartingales and backward nonnegative submartingales, whose convergence and maximal inequalities are the theoretical foundations for a wide and ever-growing body of results in statistics, econometrics, and theoretical computer science. Our results lead to new concentration inequalities for either martingale dependent or exchangeable random symmetric matrices under a variety of tail conditions, encompassing now-standard Chernoff bounds to self-normalized heavy-tailed settings. Further, these inequalities are usually expressed in the Loewner order, are sometimes valid simultaneously for all sample sizes or at an arbitrary data-dependent stopping time, and can often be tightened via an external randomization *** Codes 60B20, 60G48, 62L10 Copyright © 2024, The Authors. All rights reserved.

关键词： Matrix algebra

Testing by Betting while Borrowing and Bargaining

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Hongjian Ramdas, Aaditya Department of Statistics and Data Science Carnegie Mellon University United States Machine Learning Department Carnegie Mellon University United States

Testing by betting has been a cornerstone of the game-theoretic statistics literature. In this framework, a betting score (or more generally an e-process), as opposed to a traditional p-value, is used to quantify the evidence against a null hypothesis: the higher the betting score, the more money one has made betting against the null, and thus the larger the evidence that the null is false. A key ingredient assumed throughout past works is that one cannot bet more money than they currently have. In this paper, we ask what happens if the bettor is allowed to borrow money after going bankrupt, allowing further financial flexibility in this game of hypothesis testing. We propose various definitions of (adjusted) evidence relative to the wealth borrowed, indebted, and accumulated. We also ask what happens if the bettor can "bargain", in order to obtain odds bettor than specified by the null hypothesis. The adjustment of wealth in order to serve as evidence appeals to the characterization of arbitrage, interest rates, and numéraire-adjusted pricing in this setting. Copyright © 2024, The Authors. All rights reserved.

关键词： Game theory

An efficient doubly-robust test for the kernel treatment effect 23

学校读者我要写书评

暂无评论

An efficient doubly-robust test for the kernel treatment eff...

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Diego Martinez-Taboada Aaditya Ramdas Edward H. Kennedy Department of Statistics and Data Science Carnegie Mellon University Pittsburgh PA Department of Statistics and Data Science Machine Learning Department Carnegie Mellon University Pittsburgh PA

The average treatment effect, which is the difference in expectation of the counter-factuals, is probably the most popular target effect in causal inference with binary treatments. However, treatments may have effects beyond the mean, for instance decreasing or increasing the variance. We propose a new kernel-based test for distributional effects of the treatment. It is, to the best of our knowledge, the first kernel-based, doubly-robust test with provably valid type-I error. Furthermore, our proposed algorithm is computationally efficient, avoiding the use of permutations.

关键词：