检索结果-内蒙古大学图书馆

Detecting Bipolar Disorder based on Crowdsourced Symptoms using Machine Learning with Shapley Additive Explanations

Procedia computer science 2024年 245卷 290-298页

作者： Marvel Martawidjaja Matthew Lefrandt Ni Luh Putu Satyaning Pradnya Paramita Rongfang Zhan Renata Komalasari Felix Indra Kurniadi Erna Fransisca Angela Sihotang Maria Susan Anggreainy Dwy Bagus Cahyono Putu Hadi Purnama Jati Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11530 Indonesia Department of Rehabilitation and Health Services University of North Texas Denton 76203 United States of America College of Nursing Pennsylvania State University State College 16802 United States of America Statistics Department School of Computer Science Bina Nusantara University Jakarta 11530 Indonesia Computer Science Department BINUS Graduate Program Doctor of Computer Science Bina Nusantara University Jakarta 11530 Indonesia Meta Lab Jakarta 10310 Indonesia

Bipolar disorder is a mental health condition characterized by extreme mental states ranging from manic highs to depressive lows. Early intervention is crucial to prevent progression and complications of bipolar disorder, which can lead to significant loss. This study proposes a framework to detect bipolar disorder based on crowdsourced symptoms in the form of free texts. We extract the features by transforming these free-text symptoms into binary features using a set of natural language processing techniques. We build support vector machine models with different kernel functions and penalized logistic regression models with different penalty functions, where the best models have a precision of 0.7, recall of 0.78, F1 score of 0.74, and accuracy of 0.88. Moreover, the models are explainable since we incorporate a model-agnostic explanation method called Shapley additive explanations to understand the symptoms that mostly contributed to the prediction of bipolar disorder. The models presented in this study can be implemented in the initial screening process of bipolar disorder for further examination.

关键词： bipolar disorder crowdsourcing explainable machine learning support vector machine penalized logistic regression natural language processing

来源：评论

学校读者我要写书评

暂无评论

Combined Effect of Concept Drift and Class Imbalance on Model Performance During Stream Classification

引用

computers, Materials & Continua 2023年第4期75卷 1827-1845页

作者： Abdul Sattar Palli Jafreezal Jaafar Manzoor Ahmed Hashmani Heitor Murilo Gomes Aeshah Alsughayyir Abdul Rehman Gilal Department of Computer and Information Sciences Universiti Teknologi PETRONAS(UTP)Seri Iskandar32610Malaysia Centre for Research in Data Science UTPPerak32610Malaysia High Performance Cloud Computing Centre(HPC3) UTPPerak32610Malaysia School of Engineering and Computer Science Victoria University of WellingtonWellington6012New Zealand AI Institute University of Waikato WellingtonHamilton3240New Zealand Anti-Narcotics Force Ministry of Narcotics ControlIslamabad46000Pakistan College of Computer Science and Engineering Taibah UniversityMadinah42353Saudi Arabia

Every application in a smart city environment like the smart grid,health monitoring, security, and surveillance generates non-stationary datastreams. Due to such nature, the statistical properties of data changes overtime, leading to class imbalance and concept drift issues. Both these issuescause model performance degradation. Most of the current work has beenfocused on developing an ensemble strategy by training a new classifier on thelatest data to resolve the issue. These techniques suffer while training the newclassifier if the data is imbalanced. Also, the class imbalance ratio may changegreatly from one input stream to another, making the problem more *** existing solutions proposed for addressing the combined issue of classimbalance and concept drift are lacking in understating of correlation of oneproblem with the other. This work studies the association between conceptdrift and class imbalance ratio and then demonstrates how changes in classimbalance ratio along with concept drift affect the classifier’s *** analyzed the effect of both the issues on minority and majority classesindividually. To do this, we conducted experiments on benchmark datasetsusing state-of-the-art classifiers especially designed for data stream ***, recall, F1 score, and geometric mean were used to measure theperformance. Our findings show that when both class imbalance and conceptdrift problems occur together the performance can decrease up to 15%. Ourresults also show that the increase in the imbalance ratio can cause a 10% to15% decrease in the precision scores of both minority and majority *** study findings may help in designing intelligent and adaptive solutionsthat can cope with the challenges of non-stationary data streams like conceptdrift and class imbalance.

关键词： Classification data streams class imbalance concept drift class imbalance ratio

来源：评论

学校读者我要写书评

暂无评论

Locally Adaptive Shrinkage Priors for Trends and Breaks in Count Time Series

arXiv

引用

arXiv 2023年

作者： Schafer, Toryn L.J. Matteson, David S. Department of Statistics Texas A&M University United States Department of Statistics and Data Science Cornell University United States

Non-stationary count time series characterized by features such as abrupt changes and fluctuations about the trend arise in many scientific domains including biophysics, ecology, energy, epidemiology, and social science domains. Current approaches for integer-valued time series lack the flexibility to capture local transient features while more flexible models for continuous data types are inadequate for universal applications to integer-valued responses such as settings with small counts. We present a modeling framework, the negative binomial Bayesian trend filter (NB-BTF), that offers an adaptive model-based solution to capturing multiscale features with valid integer-valued inference for trend filtering. The framework is a hierarchical Bayesian model with a dynamic global-local shrinkage process. The flexibility of the global-local process allows for the necessary local regularization while the temporal dependence induces a locally smooth trend. In simulation, the NB-BTF outperforms a number of alternative trend filtering methods. Then, we demonstrate the method on weekly power outage frequency in Massachusetts townships. Power outage frequency is characterized by a nominal low level with occasional spikes. These illustrations show the estimation of a smooth, non-stationary trend with adequate uncertainty quantification. Copyright © 2023, The Authors. All rights reserved.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Synergizing SVM Classifier with Hybrid CNN Architecture for Handwritten Recognition 6

Synergizing SVM Classifier with Hybrid CNN Architecture for ...

引用

6th IEEE International Conference on Emerging Smart Computing and Informatics, ESCI 2024

作者： Sujay, V. Lakshmi, B. Seetha Venkatesan, T. Ram, S Sakthiya Sangeetha, E. Satheeshkumar, S. Krishna University College of Engineering and Technology Department of Computer Science and Engineering Andhra Pradesh Machilipatnam India Sri Shanmugha College of Engineering and Technology Department of Artificial Intelligence and Data Science Tamil Nadu Namakkal India R.M.D. Engineering College Department of Mathematics Tamil Nadu Thiruvallur India Bannari Amman Institute of Technology Department of ECE Tamil Nadu Erode India Department of ECE Tamil Nadu Namakkal India

ISBN: (纸本)9798350306613

The integration of Hybrid Convolutional Neural Network (CNN) architecture with a Support Vector Machine (SVM) classifier is proposed in the study as an innovative technique for Handwritten Recognition. The necessity for the research originates from existing systems' limitations in effectively understanding handwritten material due to their dependence on basic models. Existing system limitations included low accuracy, particularly in the presence of variances in writing styles and situations. The proposed system takes advantage of CNN's feature extraction and representation capabilities and SVM's discriminative power in classification. The hybrid design improves the model's capacity to grasp complicated patterns in handwritten input, overcoming existing system limitations. The results show a considerable improvement in recognition accuracy after extensive testing and analysis, confirming the effectiveness of the proposed system. The results demonstrate the system's durability in dealing with a wide range of handwritten inputs, making it a potential alternative for real-world applications requiring accuracy and flexibility. © 2024 IEEE.

关键词： Convolutional Neural Network (CNN) Feature Extraction Handwritten Recognition Hybrid Architecture Recognition Accuracy Support Vector Machine (SVM) Classifier Writing Style

来源：评论

学校读者我要写书评

暂无评论

Degree-heterogeneous Latent Class Analysis for High-dimensional Discrete data

arXiv

引用

arXiv 2024年

作者： Lyu, Zhongyuan Chen, Ling Gu, Yuqi Department of Statistics United States Data Science Institute Columbia University United States Department of Statistics Columbia University New YorkNY10027 United States

The latent class model is a widely used mixture model for multivariate discrete data. Besides the existence of qualitatively heterogeneous latent classes, real data often exhibit additional quantitative heterogeneity nested within each latent class. The modern latent class analysis also faces extra challenges, including the high-dimensionality, sparsity, and heteroskedastic noise inherent in discrete data. Motivated by these phenomena, we introduce the Degree-heterogeneous Latent Class Model and propose an easy-to-implement HeteroClustering algorithm for it. HeteroClustering uses heteroskedastic PCA with 2 normalization to remove degree effects and perform clustering in the top singular subspace of the data matrix. We establish the result of exact clustering under minimal signal-to-noise conditions. We further investigate the estimation and inference of the high-dimensional continuous item parameters in the model, which are crucial to interpreting and finding useful markers for latent classes. We provide comprehensive procedures for global testing and multiple testing of these parameters with valid error controls. The superior performance of our methods is demonstrated through extensive simulations and applications to three diverse real-world datasets from political voting records, genetic variations, and single-cell sequencing. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Outlier Robust Multivariate Polynomial Regression 32

Outlier Robust Multivariate Polynomial Regression

引用

32nd Annual European Symposium on Algorithms, ESA 2024

作者： Arora, Vipul Bhattacharyya, Arnab Boban, Mathews Guruswami, Venkatesan Kelman, Esty School of Computing National University of Singapore Singapore Department of EECS Department of Mathematics University of California BerkeleyCA United States CSAIL Massachusetts Institute of Technology CambridgeMA United States Department of Computer Science Faculty of Computing & Data Sciences Boston University MA United States

ISBN: (纸本)9783959773386

We study the problem of robust multivariate polynomial regression: let p: Rn → R be an unknown n-variate polynomial of degree at most d in each variable. We are given as input a set of random samples (xi, yi) ∈ [−1, 1]n × R that are noisy versions of (xi, p(xi)). More precisely, each xi is sampled independently from some distribution χ on [−1, 1]n, and for each i independently, yi is arbitrary (i.e., an outlier) with probability at most ρ n log d), where the hidden constant depends on n, if χ is the n-dimensional Chebyshev distribution. The sample complexity is On(d2n log d), if the samples are drawn from the uniform distribution instead. The approximation error is guaranteed to be at most O(σ), and the run-time depends on log(1/σ). In the setting where each xi and yi are known up to N bits of precision, the run-time's dependence on N is linear. We also show that our sample complexities are optimal in terms of dn. Furthermore, we show that it is possible to have the run-time be independent of 1/σ, at the cost of a higher sample complexity. © Vipul Arora, Arnab Bhattacharyya, Mathews Boban, Venkatesan Guruswami, and Esty Kelman;licensed under Creative Commons License CC-BY 4.0.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Supply Chain Management Using Internet of Things and Blockchain for Smart Meat Packaging

Supply Chain Management Using Internet of Things and Blockch...

引用

data Intelligence and Cognitive Informatics (ICDICI), International Conference on

作者： KanwalPreet Kour S Kanwal Deep Singh Malvinder Singh Bali G S Pradeep Ghantasala Rajesh Sharma R U Ananthanagu School of Computer Science and Engineering Manipal University Jaipur India Department of Computer Science Federation University Australia Department of Data Science and Engineering Manipal University Jaipur Rajasthan India Department of Computer Science and Engineering Alliance College of Engineering and Design Alliance University Bengaluru India

ISBN: (数字)9798350389609

ISBN: (纸本)9798350389616

In recent times, blockchain has evolved the security of traditional supply chain systems. Different issues of supply chain management like flexibility and reliability can be easily addressed using blockchain. Meat Packing Industry involves the complete process of processing, packaging and supplying the meat and its products throughout the world for human consumption. The animals used for the meat supply chain include pigs, sheep, cattle etc. Due to the enormous increase in the number of meat-eaters worldwide, its packing and timely supply are of utmost importance. The meat packing industry has revolutionized a lot by using the latest supply chain methods based on new technologies like blockchain. These include adulteration, long-term delays leading to spoilage of the product, mixing of other similar products which are lower in price etc. All these issues can be easily handled by using blockchain and IoT for meat supply chain management. Using these technologies, the challenges ranging from timely transportation of good quality meat to the best quality meat delivered to the customer can be easily addressed. In this paper, an effective blockchain and IoT-based model has been proposed which will counter the above challenges and improve the reliability and security factor.

关键词： Industries Supply chain management Supply chains Transportation Packaging Blockchains Safety Security Reliability Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Value Gradients with Action Adaptive Search Trees in Continuous (PO)MDPs

arXiv

引用

arXiv 2025年

作者： Lev-Yehudi, Idan Novitsky, Michael Barenboim, Moran Benchetrit, Ron Indelman, Vadim Department of Computer Science Department of Aerospace Engineering Department of Data and Decision Sciences Technion - Israel Institute of Technology Haifa32000 Israel

Solving Partially Observable Markov Decision Processes (POMDPs) in continuous state, action and observation spaces is key for autonomous planning in many real-world mobility and robotics applications. Current approaches are mostly sample based, and cannot hope to reach near-optimal solutions in reasonable time. We propose two complementary theoretical contributions. First, we formulate a novel Multiple Importance Sampling (MIS) tree for value estimation, that allows to share value information between sibling action branches. The novel MIS tree supports action updates during search time, such as gradient-based updates. Second, we propose a novel methodology to compute value gradients with online sampling based on transition likelihoods. It is applicable to MDPs, and we extend it to POMDPs via particle beliefs with the application of the propagated belief trick. The gradient estimator is computed in practice using the MIS tree with efficient Monte Carlo sampling. These two parts are combined into a new planning algorithm Action Gradient Monte Carlo Tree Search (AGMCTS). We demonstrate in a simulated environment its applicability, advantages over continuous online POMDP solvers that rely solely on sampling, and we discuss further implications. © 2025, CC BY-NC-ND.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Improving the stability and efficiency of high-order operator-splitting methods

arXiv

引用

arXiv 2025年

作者： Wei, Siqi Guenter, Victoria Spiteri, Raymond J. Department of Mathematics and Statistics University of Saskatchewan SaskatoonSK Canada Department of Computer Science University of Saskatchewan SaskatoonSK Canada

Operator-splitting methods are widely used to solve differential equations, especially those that arise from multi-scale or multi-physics models, because a monolithic (single-method) approach may be inefficient or even infeasible. The most common operator-splitting methods are the first-order Lie–Trotter (or Godunov) and the second-order Strang (Strang–Marchuk) splitting methods. High-order splitting methods with real coefficients require backward-in-time integration in each operator and hence may be adversely impacted by instability for certain operators such as diffusion. However, besides the method coefficients, there are many other ancillary aspects to an overall operator-splitting method that are important but often overlooked. For example, the operator ordering and the choice of sub-integration methods can significantly affect the stability and efficiency of an operator-splitting method. In this paper, we investigate some design principles for the construction of operator-splitting methods, including minimization of local error measure, choice of sub-integration method, maximization of linear stability, and minimization of overall computational cost. We propose a new four-stage, third-order, 2-split operator-splitting method with seven sub-integrations per step and optimized linear stability for a benchmark problem from cardiac electrophysiology. We then propose a general principle to further improve stability and efficiency of such operator-splitting methods by using low-order, explicit sub-integrators for unstable sub-integrations. We demonstrate an almost 30% improvement in the performance of methods derived from these design principles compared to the best-known third-order methods. © 2025, CC BY.

关键词： Linear stability analysis

来源：评论

学校读者我要写书评

暂无评论

WELL-POSEDNESS AND BLOWUP OF 1D ELECTRON MAGNETOHYDRODYNAMICS

arXiv

引用

arXiv 2025年

作者： Dai, Mimi Department of Mathematics Statistics and Computer Science University of Illinois at Chicago ChicagoIL60607 United States

MSC Codes 35Q35, 76B03, 76D03, 76W05The one-dimensional toy models proposed for the three-dimensional electron magnetohydrodynamics in our previous work [16] share some similarities with the original dynamics under certain symmetry. We continue to study the well-posedness issue and explore the potential singularity formation scenario for these models. Copyright © 2025, The Authors. All rights reserved.

关键词： Magnetohydrodynamics

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：