检索结果-内蒙古大学图书馆

A novel deep learning model for early diabetes risk prediction using attention-enhanced deep belief networks with highly imbalanced data

引用

International Journal of Information Technology (Singapore) 2025年第4期17卷 1933-1955页

作者： Olabanjo, Olusola Wusu, Ashiribo Olabanjo, Olufemi Asokere, Mauton Afisi, Oseni Akinnuwesi, Boluwaji Center for Equitable AI and Machine Learning Systems (CEAMLS) Morgan State University Baltimore 21251 MD United States Department of Mathematics Morgan State University Baltimore MD United States Department of Computer Science Lagos State University Lagos Nigeria Department of Mathematics Lagos State University Lagos Nigeria Department of Cybersecurity University of Derby Derby United Kingdom Department of Philosophy Lagos State University Lagos Nigeria Department of Computer Science Faculty of Science and Engineering University of Eswatini Kwaluseni Swaziland

Diabetes mellitus is a prevalent chronic illness with severe complications that demand timely diagnosis. This study introduces an attention-enhanced Deep Belief Network (DBN) for early diabetes risk prediction, designed to address challenges associated with highly imbalanced datasets. Using a dataset from Sylhet Diabetes Hospital, which includes symptom and demographic information from patients, we applied an ensemble feature selection approach to identify critical predictors. To address the class imbalance, Generative Adversarial Networks (GANs) were used to generate synthetic data, ensuring the model’s robustness in identifying underrepresented cases. Additionally, a hybrid loss function combining cross-entropy and focal loss was implemented to improve classification, especially for hard-to-detect instances. Our results show that the attention-based DBN model, augmented with synthetic data from GANs and optimized with a hybrid loss function, achieves an AUC of 1.00, F1-score of 0.97, precision of 0.98, and recall of 0.95, outperforming several baseline models. This research offers a novel and effective approach for early diabetes detection, demonstrating potential for use as a clinical tool in preventive healthcare settings. © The Author(s) 2025.

关键词： Attention mechanism Deep belief networks (DBN) Diabetes risk Generative adversarial networks (GANs) Hybrid loss function Imbalanced data

来源：评论

学校读者我要写书评

暂无评论

Weisfeiler and leman go loopy: a new hierarchy for graph representational learning 24

Weisfeiler and leman go loopy: a new hierarchy for graph rep...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Raffaele Paolino Sohir Maskey Pascal Welke Gitta Kutyniok Department of Mathematics LMU Munich and Munich Center for Machine Learning (MCML) Department of Mathematics LMU Munich Faculty of Computer Science TU Wien Department of Mathematics LMU Munich and Munich Center for Machine Learning (MCML) and Institute for Robotics and Mechatronics DLR-German Aerospace Center and Department of Physics and Technology University of Tromsø

ISBN: (纸本)9798331314385

We introduce r-loopy Weisfeiler-Leman (r-ℓWL), a novel hierarchy of graph isomorphism tests and a corresponding GNN framework, r-ℓMPNN, that can count cycles up to length r + 2. Most notably, we show that r-ℓWL can count homomorphisms of cactus graphs. This extends 1-WL, which can only count homomorphisms of trees and, in fact, we prove that r-ℓWL is incomparable to k-WL for any fixed k. We empirically validate the expressive and counting power of r-ℓMPNN on several synthetic datasets and demonstrate the scalability and strong performance on various real-world datasets, particularly on sparse graphs. Our code is available on https://***/RPaolino/loopy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A scalable generative model for dynamical system reconstruction from neuroimaging data 38

A scalable generative model for dynamical system reconstruct...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Volkmann, Eric Brändle, Alena Durstewitz, Daniel Koppe, Georgia Medical Faculty Mannheim Heidelberg University Mannheim Germany Institute for Machine Learning Johannes Kepler University Linz Austria Interdisciplinary Center for Scientific Computing Heidelberg University Heidelberg Germany Faculty of Physics and Astronomy Heidelberg University Heidelberg Germany Hector Institute for AI in Psychiatry Dept. for Psychiatry and Psychotherapy CIMH Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany

Data-driven inference of the generative dynamics underlying a set of observed time series is of growing interest in machine learning and the natural sciences. In neuroscience, such methods promise to alleviate the need to handcraft models based on biophysical principles and allow to automatize the inference of inter-individual differences in brain dynamics. Recent breakthroughs in training techniques for state space models (SSMs) specifically geared toward dynamical systems (DS) reconstruction (DSR) enable to recover the underlying system including its geometrical (attractor) and long-term statistical invariants from even short time series. These techniques are based on control-theoretic ideas, like modern variants of teacher forcing (TF), to ensure stable loss gradient propagation while training. However, as it currently stands, these techniques are not directly applicable to data modalities where current observations depend on an entire history of previous states due to a signal's filtering properties, as common in neuroscience (and physiology more generally). Prominent examples are the blood oxygenation level dependent (BOLD) signal in functional magnetic resonance imaging (fMRI) or Ca2+ imaging data. Such types of signals render the SSM's decoder model non-invertible, a requirement for previous TF-based methods. Here, exploiting the recent success of control techniques for training SSMs, we propose a novel algorithm that solves this problem and scales exceptionally well with model dimensionality and filter length. We demonstrate its efficiency in reconstructing dynamical systems, including their state space geometry and long-term temporal properties, from just short BOLD time series. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Authentication Protocol Suitable for Constrained RFID Systems

引用

IEEE Access 2024年 12卷 61610-61628页

作者： Hosseinzadeh, Mehdi Servati, Mohammad Reza Rahmani, Amir Masoud Safkhani, Masoumeh Lansky, Jan Janoscova, Renata Ahmed, Omed Hassan Tanveer, Jawad Lee, Sang-Woong Duy Tan University Institute of Research and Development Da Nang550000 Viet Nam Duy Tan University School of Medicine and Pharmacy Da Nang550000 Viet Nam Shahid Rajaee Teacher Training University Department of Computer Engineering Tehran16788-15811 Iran National Yunlin University of Science and Technology Future Technology Research Center Douliou Yunlin64002 Taiwan School of Computer Science Tehran19395-5746 Iran University of Finance and Administration Faculty of Economic Studies Department of Computer Science and Mathematics Prague101 00 Czech Republic University of Human Development Department of Information Technology Sulaymaniyah0778-6 Iraq Sejong University Department of Computer Science and Engineering Seoul05006 Korea Republic of Gachon University Pattern Recognition and Machine Learning Laboratory Department of Ai Software Seongnam-si13557 Korea Republic of

RFID technology offers an affordable and user-friendly solution for contactless identification of objects and individuals. However, the widespread adoption of RFID systems raises concerns regarding security and privacy. Vulnerabilities such as message tampering, interception, and eavesdropping pose significant risks to the integrity of the system. This study examines the effectiveness of two recently proposed ultra-lightweight RFID authentication protocols, URASP and KUAJB, in addressing these security challenges. Surprisingly, our findings reveal that both URASP and KUAJB protocols are susceptible to secret disclosure attacks, despite their claims of providing robust security. Consequently, the development of a truly ultra-lightweight protocol that ensures adequate security becomes a formidable task. As a potential solution, the enhancement of the URASP protocol through the integration of a simple cryptographic primitive is suggested to bolster its security measures. © 2013 IEEE.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Decomposing global feature effects based on feature interactions

The Journal of Machine Learning Research

引用

The Journal of machine learning Research 2024年第1期25卷 18629-18693页

作者： Julia Herbinger Marvin N. Wright Thomas Nagler Bernd Bischl Giuseppe Casalicchio Department of Statistics LMU Munich Munich Germany and Munich Center for Machine Learning (MCML) Munich Germany Leibniz Institute for Prevention Research and Epidemiology and Faculty of Mathematics and Computer Science University of Bremen Bremen Germany and Department of Public Health University of Copenhagen Copenhagen Denmark

Global feature effect methods, such as partial dependence plots, provide an intelligible visualization of the expected marginal feature effect. However, such global feature effect methods can be misleading, as they do not represent local feature effects of single observations well when feature interactions are present. We formally introduce generalized additive decomposition of global effects (GADGET), which is a new framework based on recursive partitioning to find interpretable regions in the feature space such that the interaction-related heterogeneity of local feature effects is minimized. We provide a mathematical foundation of the framework and show that it is applicable to the most popular methods to visualize marginal feature effects, namely partial dependence, accumulated local effects, and Shapley additive explanations (SHAP) dependence. Furthermore, we introduce and validate a new permutation-based interaction detection procedure that is applicable to any feature effect method that fits into our proposed framework. We empirically evaluate the theoretical characteristics of the proposed methods based on various feature effect methods in different experimental settings. Moreover, we apply our introduced methodology to three real-world examples to showcase their usefulness.

关键词： interpretable machine learning feature interactions partial dependence accumulated local effect SHAP dependence

来源：评论

学校读者我要写书评

暂无评论

Overcoming common flaws in the evaluation of selective classification systems 24

Overcoming common flaws in the evaluation of selective class...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Jeremias Traub Till J. Bungert Carsten T. Lüth Michael Baumgartner Klaus H. Maier-Hein Lena Maier-Hein Paul F. Jäger German Cancer Research Center (DKFZ) Heidelberg Interactive Machine Learning Group Germany and Helmholtz Imaging DKFZ Heidelberg Germany German Cancer Research Center (DKFZ) Heidelberg Interactive Machine Learning Group Germany and Helmholtz Imaging DKFZ Heidelberg Germany and Faculty of Mathematics and Computer Science University of Heidelberg Germany Helmholtz Imaging DKFZ Heidelberg Germany and DKFZ Heidelberg Division of Medical Image Computing (MIC) Germany and Faculty of Mathematics and Computer Science University of Heidelberg Germany Helmholtz Imaging DKFZ Heidelberg Germany and DKFZ Heidelberg Division of Medical Image Computing (MIC) Germany and Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Heidelberg Germany and Faculty of Mathematics and Computer Science University of Heidelberg Germany and National Center for Tumor Diseases (NCT) Heidelberg Helmholtz Imaging DKFZ Heidelberg Germany and DKFZ Heidelberg Division of Intelligent Medical Systems (IMSY) Germany and Faculty of Mathematics and Computer Science University of Heidelberg Germany and National Center for Tumor Diseases (NCT) Heidelberg

ISBN: (纸本)9798331314385

Selective Classification, wherein models can reject low-confidence predictions, promises reliable translation of machine-learning based classification systems to real-world scenarios such as clinical diagnostics. While current evaluation of these systems typically assumes fixed working points based on pre-defined rejection thresholds, methodological progress requires benchmarking the general performance of systems akin to the AUROC in standard classification. In this work, we define 5 requirements for multi-threshold metrics in selective classification regarding task alignment, interpretability, and flexibility, and show how current approaches fail to meet them. We propose the Area under the Generalized Risk Coverage curve (AUGRC), which meets all requirements and can be directly interpreted as the average risk of undetected failures. We empirically demonstrate the relevance of AUGRC on a comprehensive benchmark spanning 6 data sets and 13 confidence scoring functions. We find that the proposed metric substantially changes metric rankings on 5 out of the 6 data sets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

COUNTARFACTUALS - GENERATING PLAUSIBLE MODEL-AGNOSTIC COUNTERFACTUAL EXPLANATIONS WITH ADVERSARIAL RANDOM FORESTS

arXiv

引用

arXiv 2024年

作者： Dandl, Susanne Blesch, Kristin Freiesleben, Timo König, Gunnar Kapar, Jan Bischl, Bernd Wright, Marvin N. Department of Statistics LMU Munich Germany Leibniz Institute for Prevention Research & Epidemiology BIPS Germany Faculty of Mathematics and Computer Science University of Bremen Germany Department of Public Health University of Copenhagen Denmark Cluster: Machine Learning for Science University of Tübingen Germany Tübingen AI Center University of Tübingen Germany

Counterfactual explanations elucidate algorithmic decisions by pointing to scenarios that would have led to an alternative, desired outcome. Giving insight into the model's behavior, they hint users towards possible actions and give grounds for contesting decisions. As a crucial factor in achieving these goals, counterfactuals must be plausible, i.e., describing realistic alternative scenarios within the data manifold. This paper leverages a recently developed generative modeling technique - adversarial random forests (ARFs) - to efficiently generate plausible counterfactuals in a model-agnostic way. ARFs can serve as a plausibility measure or directly generate counterfactual explanations. Our ARF-based approach surpasses the limitations of existing methods that aim to generate plausible counterfactual explanations: It is easy to train and computationally highly efficient, handles continuous and categorical data naturally, and allows integrating additional desiderata such as sparsity in a straightforward manner. © 2024, CC BY-SA.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Predictive Imaging Biomarker Discovery Through Treatment Effect Analysis

Enhancing Predictive Imaging Biomarker Discovery Through Tre...

引用

IEEE Workshop on Applications of computer Vision (WACV)

作者： Shuhan Xiao Lukas Klein Jens Petersen Philipp Vollmuth Paul F. Jaeger Klaus H. Maier-Hein German Cancer Research Center (DKFZ) Heidelberg Division of Medical Image Computing Germany Faculty of Mathematics and Computer Science Heidelberg University Germany DKFZ Heidelberg Interactive Machine Learning Group Germany Institute for Machine Learning ETH Zürich Switzerland DKFZ Heidelberg Helmholtz Imaging Germany Division for Computational Radiology Clinical AI (CCIBonn.ai) Clinic for Neuroradiology University Hospital Bonn Germany Medical Faculty Bonn University of Bonn Germany Department of Radiation Oncology Pattern Analysis and Learning Group Heidelberg University Hospital Germany

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Identifying predictive covariates, which forecast individual treatment effectiveness, is crucial for decision-making across different disciplines such as personalized medicine. These covariates, referred to as biomarkers, are extracted from pretreatment data, often within randomized controlled trials, and should be distinguished from prognostic biomarkers, which are independent of treatment assignment. Our study focuses on discovering predictive imaging biomarkers, specific image features, by leveraging pretreatment images to uncover new causal relationships. Unlike laborintensive approaches relying on handcrafted features prone to bias, we present a novel task of directly learning predictive features from images. We propose an evaluation protocol to assess a model's ability to identify predictive imaging biomarkers and differentiate them from purely prognostic ones by employing statistical testing and a comprehensive analysis of image feature attribution. We explore the suitability of deep learning models originally developed for estimating the conditional average treatment effect (CATE) for this task, which have been assessed primarily for their precision of CATE estimation while overlooking the evaluation of imaging biomarker discovery. Our proof-of-concept analysis demonstrates the feasibility and potential of our approach in discovering and validating predictive imaging biomarkers from synthetic outcomes and real-world image datasets. Our code is available at https://***/MIC-DKFZ/predictive_image_biomarker_analysis.

关键词： Analytical models Statistical analysis Biological system modeling Precision medicine Decision making Imaging Estimation Biomarkers Predictive models Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A scalable generative model for dynamical system reconstruction from neuroimaging data

arXiv

引用

arXiv 2024年

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

A hybrid flow shop scheduling optimization using puma optimizer: Addressing energy efficiency and workforce restrictions

引用

Alexandria Engineering Journal 2025年 128卷 340-365页

作者： Lee, Sang-Woong Tanveer, Jawad Rahmani, Amir Masoud Gharehchopogh, Farhad Soleimanian Abdollahzadeh, Benyamin Rokny, Hamid Porntaveetus, Thantrira Lansky, Jan Hosseinzadeh, Mehdi Pattern Recognition and Machine Learning Lab School of Computing Gachon University Seongnam13120 Korea Republic of Department of Computer Science and Engineering Sejong University Seoul05006 Korea Republic of Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan Department of Computer Engineering Ur. C. Islamic Azad University Urmia Iran Center of Excellence in Precision Medicine and Digital Health Department of Physiology Faculty of Dentistry Chulalongkorn University Bangkok10330 Thailand Department of Computer Science and Mathematics Faculty of Economic Studies University of Finance and Administration Prague Czech Republic School of Computer Science Duy Tan University Da Nang Viet Nam Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura140401 India

The Hybrid Flow Shop Scheduling Problem (HFSP) is a complex challenge in production and manufacturing, requiring efficient scheduling solutions that optimize productivity while considering real-world constraints. This study proposes an advanced optimization framework utilizing the Puma Optimizer, a metaheuristic algorithm enhanced with an adaptive control mechanism for intelligently selecting phases and operators. This feature makes it well-suited for discrete optimization problems such as HFSP. Our approach integrates heuristic decoding and adaptive local search, balancing exploration and exploitation to generate high-quality schedules. The proposed mathematical model optimizes makespan and total tardiness while energy consumption is incorporated as a constraint to enhance sustainability. Extensive computational experiments demonstrate the superior performance of the proposed algorithm compared to traditional methods, achieving shorter makespan and lower tardiness while ensuring workforce feasibility. These results highlight the Puma Optimizer's adaptability and potential to set new benchmarks for HFSP, offering a scalable and effective solution for modern production systems. © 2025 The Authors

关键词： Local search (optimization)

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：