检索结果-内蒙古大学图书馆

Joint probabilistic modeling analysis of head and eye behaviors in autism spectrum disorder children based on a social interaction paradigm

引用

BIOMEDICAL SIGNAL processING AND control 2025年 106卷

作者： Su, Tongxu Yang, Minqiang Zhou, Wei Tao, Yongfeng Ni, Minghui Zheng, Weihao Hu, Bin Lanzhou Univ Sch Informat Sci & Engn Lanzhou Peoples R China Beijing Inst Technol Sch Med Technol Beijing Peoples R China

Autism Spectrum Disorder (ASD), as a complex neurodevelopmental disorder, is closely associated with attention deficits that manifest through eye and head movements. Previous studies on the eye gaze and head posture of children with ASD have been somewhat limited by the contexts in which the children were observed, Exploring head and eye coordination in natural environments is crucial for developing effective intervention strategies applicable to everyday life. This paper aims to examine the perceptual and behavioral responses of children with ASD in simulated real-life social environments. Using asocial interaction paradigm based on real-life scenarios, we propose a joint probabilistic modeling method for head and eye behaviors. This method includes the influence of head posture on gaze direction in eye-tracking studies within social interaction contexts. For each participant, we establish a data-driven Markov chain model based on individual data, preserving the temporal nature of eye movement behavior and the highly individualized nature of visual behavior. We conducted experiments on a video dataset of children with ASD that we collected, achieving a classification accuracy of 79.66%, demonstrating the feasibility and effectiveness of our proposed method. Additionally, we found that one manifestation of attention deficits in children with ASD is an increased occurrence of head-eye counter movement. This finding provides new reference indicators for the early diagnosis and screening of ASD.

关键词： Autism spectrum disorder Eye movements Head gestures Joint probabilistic

来源：评论

学校读者我要写书评

暂无评论

modeling of biogas production from hydrothermal carbonization products in a continuous anaerobic digester

引用

ACM TRANSACTIONS ON modeling AND COMPUTER SIMULATION 2024年第4期34卷 1-19页

作者： Dekhici, Benaissa Benyahia, Boumediene Cherki, Brahim Fiori, Luca Andreottola, Gianni Univ Trento Civil Environm & Mech Engn Trento Italy Abou Bekr Belkaid Univ Automat Lab Tlemcen Tilimsen Tlemcen Algeria

The coupling between anaerobic digestion and hydrothermal carbonization (HTC) is a promising alternative for sustainable energy production. This study presents a dynamic model tailored for a lab-scale anaerobic digester operating on HTC products, specifically hydrochar and HTC liquor derived from sewage and agroindustrial digestate. Leveraging a modified version of the Anaerobic Model 2 (AM2), our simplified model of four states integrates pH and biomass decay rates into biomass kinetics. Simulation results of the mode were compared with experimental data collected over 164 days from the digester. The obtained results have proven the ability of the proposed model to predict the trend of the biogas production as well as important measured outputs of the bioreactor. The developed model could be used to control and optimize the performance of the digester, which provides potential for bioenergy production from waste streams such as digestate and digestate treated through the HTC process.

关键词： Anaerobic digestion hydrothermal carbonization HTC mathematical modeling and simulation sensitivity analysis AM2 model bioprocess model identification and optimization

来源：评论

学校读者我要写书评

暂无评论

A stochastic model based on Gaussian random fields to characterize the morphology of granular objects

引用

PATTERN RECOGNITION 2024年 149卷

作者： Theodon, L. Coufort-Saudejaud, C. Debayle, J. CNRS UMR 5307 LGF Ctr SPIN Mines St Etienne St Etienne France Univ Toulouse Lab Genie Chim UPS CNRSINPT Toulouse France

The geometrical modeling of granular objects is a complex challenge that exists in many scientific fields, such as the modeling of granular materials or rocks and coarse aggregates with applications in civil, mechanical, and chemical engineering. In this paper, a model called SPHERE (Stochastic process for Highly Effective Radial Expansion) is proposed, which is based on the deformation of an ellipsoid mesh using multiple 3D Gaussian random fields. The model is designed to be flexible (full control over 2D and 3D morphological properties of granular objects), ultra-fast (over 1000 aggregates in less than 5 s), and independent of the mesh and base shape used (as long as it is a star-shaped object). The flexibility of the model and its ability to reflect real data is illustrated using images of latex nanoparticle aggregates. Using 2D measurements on images from a morphogranulometer, a method based on the SPHERE model is proposed to estimate the 3D morphological properties of aggregates. A multiscale optimization process is applied, in particular using a partial reconstruction of 2D shapes from elliptic Fourier descriptors, in order to best reproduce the shape, angularity and texture of the aggregates using the SPHERE model. Validation of the method on 3D printed data shows relative errors of less than 3% for all measured 2D and 3D morphological characteristics, and validation on a population of synthetic objects shows relative errors of less than 6%. The results are compared and discussed with those obtained using other models based on overlapping spheres and show consistency with previous work. Finally, suggestions for improvement are given

关键词： 3D modeling Aggregate Agglomerate Fourier descriptor Gaussian random fields Image analysis Morphological characterization

来源：评论

学校读者我要写书评

暂无评论

A Multi-dimensional Model for the Design and Development of Analytical Information Systems 25th

A Multi-dimensional Model for the Design and Development of ...

引用

25th International Working conference on Business process modeling, Development, and Support (BPMDS) / 29th International Working conference on Exploring modeling Methods for Systems analysis and Development (EMMSAD)

作者： Santos, Maribel Yasmina Leon, Ana Univ Minho ALGORITMI Res Ctr Campus Azurem P-4800058 Guimaraes Portugal Univ Politen Valencia Valencian Res Insitute Artificial Intelligence VR Valencia Spain

ISBN: (纸本)9783031610066;9783031610073

The design and development of Analytical Information Systems demand efficient techniques and technologies for processing vast amounts of data that arrive at high velocity or that are available in legacy/operational systems. While many advances have been verified in the technological field to deal with the potential volume, velocity, and variety of the data, fewer contributions can be found in the methodological domain. These conceptual and methodological perspectives are key to providing the foundations for designing and developing Analytical Information Systems that also guarantee the veracity and value of the data. Considering three levels of detail, this paper proposes a multidimensional model that abstracts the dimensions to be considered, the driving components of the dimensions, and the core concepts of the components with the supporting approaches, techniques, or technologies for designing and developing Analytical Information Systems. We exemplify the proposed model with an instantiation that highlights the decisions or actions to be taken toward the design and development of more effective and efficient systems supporting decision-making in organizations.

关键词： Big data Analytics data Analytics Analytical Information Systems Conceptual modeling

来源：评论

学校读者我要写书评

暂无评论

data-driven fault diagnosis based on the integrated deep nonlinear dynamic system model 43

Data-driven fault diagnosis based on the integrated deep non...

引用

43rd Chinese control conference, CCC 2024

作者： Tang, Xiaochu Tao, Na Zhang, Yi Li, Yuan Shenyang Aerospace University School of Automation Shenyang China Shenyang University of Chemical Technology College of Information Engineering Shenyang China

ISBN: (纸本)9789887581581

To ensure the safety and reliability of complex industrial processes are very important. Therefore, extracting multiple features of data effectively is a great significance to improve the accuracy of modeling for fault diagnosis. Dynamic, uncertainty and nonlinearity are main characteristics of industrial process data. However, it is challenging for modeling to extract multiple features of process data at the same time. In this paper, an integrated nonlinear dynamic system model is proposed for fault diagnosis based on variational autoencoder-linear dynamic system (VAE-LDS). First, the deep learning algorithm variational autoencoder (VAE) is used to extract the nonlinear data feature and learn the potential representation of data. Furthermore, the VAE model is embedded into the linear dynamic system (LDS) so that the dynamics and uncertainty underlying data can be extracted simultaneously. In this way, A comprehensive model integrating multiple features can be established. Finally, the proposed method is applied to the TE process for fault diagnosis comparing with other methods. The results show the proposed method has superior performance. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： data-driven Fault Detection Fault Diagnosis Linear Dynamic System Variational Autoencoder

来源：评论

学校读者我要写书评

暂无评论

A Robust Semi-Supervised Fisher Discriminant analysis for Industrial Fault Classification

引用

IEEE SENSORS JOURNAL 2024年第4期24卷 4735-4745页

作者： Liu, Jun Yao, Jiayang Jiang, Peng Song, Chunyue Hangzhou Normal Univ Sch Informat Sci & Technol Hangzhou 311121 Peoples R China Chaochuang Digital Energy Technol Co Ltd Hangzhou 310064 Peoples R China Zhejiang Univ Inst Ind Proc Control State Key Lab Ind Control Technol Hangzhou 310027 Peoples R China

Owing to the advanced sensing technologies, data-based modeling has become a popular choice in the area of industrial process monitoring. For the data-based semi-supervised industrial fault classification problem, the samples from unobserved faults may severely degrade the performance of the classification model. Specifically speaking, on the one hand, the offline training samples from unobserved faults will act as outliers and seriously hinder the offline model training;on the other hand, the online testing samples from unobserved faults will be inevitably misclassified into observed fault categories in the online model usage. Despite the importance of these two issues, there are still no related works that can address them simultaneously. To this end, a robust semi-supervised Fisher discriminant analysis (FDA) model is proposed in this article. First, before the model training, based on the deviation information of training samples for each observed fault, a sample recognizing technique is designed to preprocess the training samples, with the purpose of recognizing the training samples from the unobserved fault. Second, to fully employ the supervised and unsupervised information hidden in preprocessed training samples, a regularized between-class scatter matrix and a within-class scatter matrix are constructed, and a semi-supervised FDA (SFDA) classification method is developed. Third, during the online model usage, the sample recognizing technique is also exploited to recognize the testing samples from the unobserved faults. Experiments on the benchmark Tennessee Eastman (TE) process and a real industrial air separation unit (ASU) demonstrate the effectiveness and the superiority of the proposed model.

关键词： Fisher discriminant analysis (FDA) industrial fault classification sample recognizing semi-supervised unobserved fault

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of Feature Representations for Topic modeling with Latent Dirichlet Allocation 15

Comparative Analysis of Feature Representations for Topic Mo...

引用

15th International conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Nallamothu, Sai Karthik Yenduri, Rohith Kamal Kumar Pippalla, Sai Sandeep Karthik, Kpvm Alapati, Bhargav Sai Veldhi, Sri Naga Venkata Kowshik Boyapati, Prashanthi SRM University-AP Department of Computer Science and Engineering Andhra Pradesh 522240 India

ISBN: (纸本)9798350370249

Topic analysis is also known as topic detection or topic extraction, refers to ML method that categorizes larger text datasets into categories based on the individual text. It employs natural language processing to analyze human communication by breaking it down into components such as speech, words, sentences, and context, aiming to identify patterns and unveil underlying meanings within texts. This process aids in deriving insights and facilitating data-driven decisions. Within topic analysis, the primary machine learning techniques employed areas of focus include topic modeling and topic classification within this field. However, topic modeling encounters various challenges, specific to document properties. NLP is an integrative subject that merges CS, AI, and linguistics to construct systems capable of comprehending and processing human language. The prevalent machine using labeled data to categorize unlabeled data. This process relies on the knowledge gained during training to classify new data. In general, text classification methods handle predefined and finite categories such as predicting labels like credible or not credible for credibility assessment, or determining movie ratings (bad, okay, good) based on reviews. The difficulty in text classification arises from the predetermined set of topics or labels. When the topics are not known in advance, the concept of topic modeling becomes crucial. This statistical modeling approach is designed to identify abstract topics within a set of documents that lack predefined labels. By analyzing labelled data, this method extracts underlying topics. © 2024 IEEE.

关键词： modeling languages

来源：评论

学校读者我要写书评

暂无评论

Inherently Interpretable Physics-Informed Neural Network for Battery modeling and Prognosis

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2025年第1期36卷 1145-1159页

作者： Wang, Fujin Zhi, Quanquan Zhao, Zhibin Zhai, Zhi Liu, Yingkai Xi, Huan Wang, Shibin Chen, Xuefeng Xi An Jiao Tong Univ Natl Key Lab Aerosp Power Syst & Plasma Technol Xian Peoples R China Xi An Jiao Tong Univ Sch Mech Engn Xian 710049 Peoples R China Beijing Aerosp Control Ctr Beijing 100094 Peoples R China Xi An Jiao Tong Univ Key Lab ThermoFluid Sci & Engn Minist Educ Sch Energy & Power Engn Xian 710049 Peoples R China

\Lithium-ion batteries are widely used in modern society. Accurate modeling and prognosis are fundamental to achieving reliable operation of lithium-ion batteries. Accurately predicting the end-of-discharge (EOD) is critical for operations and decision-making when they are deployed to critical missions. Existing data-driven methods have large model parameters, which require a large amount of labeled data and the models are not interpretable. Model-based methods need to know many parameters related to battery design, and the models are difficult to solve. To bridge these gaps, this study proposes a physics-informed neural network (PINN), called battery neural network (BattNN), for battery modeling and prognosis. Specifically, we propose to design the structure of BattNN based on the equivalent circuit model (ECM). Therefore, the entire BattNN is completely constrained by physics. Its forward propagation process follows the physical laws, and the model is inherently interpretable. To validate the proposed method, we conduct the discharge experiments under random loading profiles and develop our dataset. analysis and experiments show that the proposed BattNN only needs approximately 30 samples for training, and the average required training time is 21.5 s. Experimental results on three datasets show that our method can achieve high prediction accuracy with only a few learnable parameters. Compared with other neural networks, the prediction MAEs of our BattNN are reduced by 77.1%, 67.4%, and 75.0% on three datasets, respectively. Our data and code will be available at: https://***/wang-fujin/BattNN.

关键词： End-of-discharge (EOD) inherently interpretable lithium-ion battery physics-informed neural network (PINN) prognosis

来源：评论

学校读者我要写书评

暂无评论

Transition Network analysis: A Novel Framework for modeling, Visualizing, and Identifying the Temporal Patterns of Learners and Learning processes 25

Transition Network Analysis: A Novel Framework for Modeling,...

引用

15th International conference on Learning Analytics and Knowledge

作者： Saqr, Mohammed Lopez-Pernas, Sonsoles Tormanen, Tiina Kaliisa, Rogers Misiejuk, Kamila Tikka, Santtu Univ Eastern Finland Joensuu Finland Univ Oulu Oulu Finland Univ Oslo Oslo Norway Univ Bergen Ctr Sci Learning & Technol SLATE Bergen Norway Fernuniv Ctr Adv Technol Assisted Learning & Predict Analy Hagen Germany Univ Jyvaskyla Jyvaskyla Finland

ISBN: (纸本)9798400707018

This paper presents a novel learning analytics method: Transition Network analysis (TNA), a method that integrates Stochastic process Mining and probabilistic graph representation to model, visualize, and identify transition patterns in the learning process data. Combining the relational and temporal aspects into a single lens offers capabilities beyond either framework, including centralities to capture important learning events, community detection to identify behavior patterns, and clustering to reveal temporal patterns. Furthermore, TNA introduces several significance tests that go beyond either method and add rigor to the analysis. Here, we introduce the theoretical and mathematical foundations of TNA and we demonstrate the functionalities of TNA with a case study where students (n=191) engaged in small-group collaboration to map patterns of group dynamics using the theories of co-regulation and socially-shared regulated learning. The analysis revealed that TNA can map the regulatory processes as well as identify important events, patterns, and clusters. Bootstrap validation established the significant transitions and eliminated spurious transitions. As such, TNA can capture learning dynamics and provide a robust framework for investigating the temporal evolution of learning processes. Future directions include -inter alia- expanding estimation methods, reliability assessment, and building longitudinal TNA.

关键词： Transition Network analysis process Mining Social Network analysis Learning process Learning analytics

来源：评论

学校读者我要写书评

暂无评论

control-Oriented Gray-Box modeling for Thermoset Injection Molding 11

Control-Oriented Gray-Box Modeling for Thermoset Injection M...

引用

11th Vienna International conference on Mathematical Modelling (MATHMOD)

作者： Ahlers, Jens Schulte, Christopher Mascher, Moritz Zimmermann, Christoph Vallery, Heike Hopmann, Christian Stemmler, Sebastian Rhein Westfal TH Aachen Inst Automat Control IRT Aachen Germany Rhein Westfal TH Aachen Inst Plast Proc IKV Aachen Germany

Cavity pressure control can enhance the repeatability of injection molding processes. While extensive research has focused on thermoplastic cavity pressure control, there is a notable gap in models and control strategies for thermoset injection molding. This study aims to develop a model structure for thermoset injection molding suitable for integration into a model-based control scheme. The modeling approach is intended to be as generalizable as possible and sufficiently flexible to adapt to various process conditions. At the same time, it should be easy to parameterize or to train. To address this challenge, we first derive a first-principles process model. In the second step, we integrate a feed-forward artificial neural network into this model, which learns parameters and source terms from past injection molding cycles, resulting in a gray-box model. The neural network outputs replace the initial model parameters with functions of system inputs, states, and time. We validate both models against experimental data from a thermoset injection molding machine using a flat-plate mold geometry and a phenolic resin compound. We identify limitations of the proposed approach and suggest potential solutions. Copyright (c) 2025 The Authors. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0/)

关键词： Thermoset Injection Molding Gray-Box modeling Hybrid modeling Physics-informed Machine Learning Artificial Neural Networks System Identification

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：