检索结果-内蒙古大学图书馆

Outcome prediction of cardiac arrest with automatically computed gray-white matter ratio on computed tomography images

引用

Critical Care 2024年第1期28卷 1页

作者： Tsai, Hsinhan Chi, Chien-Yu Wang, Liang-Wei Su, Yu-Jen Chen, Ya-Fang Tsai, Min-Shan Wang, Chih-Hung Hsu, Cheyu Huang, Chien-Hua Wang, Weichung Department of Computer Science and Information Engineering National Taiwan University Taipei 106216 Taiwan Department of Emergency Medicine National Taiwan University Hospital Taipei 100225 Taiwan Department of Medical Imaging National Taiwan University Hospital Taipei 100225 Taiwan Department of Oncology National Taiwan University Hospital Taipei 100225 Taiwan Institute of Applied Mathematical Sciences National Taiwan University Taipei 106216 Taiwan

Background : This study aimed to develop an automated method to measure the gray-white matter ratio (GWR) from brain computed tomography (CT) scans of patients with out-of-hospital cardiac arrest (OHCA) and assess its significance in predicting early-stage neurological outcomes. Methods : Patients with OHCA who underwent brain CT imaging within 12 h of return of spontaneous circulation were enrolled in this retrospective study. The primary outcome endpoint measure was a favorable neurological outcome, defined as cerebral performance category 1 or 2 at hospital discharge. We proposed an automated method comprising image registration, K-means segmentation, segmentation refinement, and GWR calculation to measure the GWR for each CT scan. The K-means segmentation and segmentation refinement was employed to refine the segmentations within regions of interest (ROIs), consequently enhancing GWR calculation accuracy through more precise segmentations. Results : Overall, 443 patients were divided into derivation N=265, 60% and validation N=178, 40% sets, based on age and sex. The ROI Hounsfield unit values derived from the automated method showed a strong correlation with those obtained from the manual method. Regarding outcome prediction, the automated method significantly outperformed the manual method in GWR calculation (AUC 0.79 vs. 0.70) across the entire dataset. The automated method also demonstrated superior performance across sensitivity, specificity, and positive and negative predictive values using the cutoff value determined from the derivation set. Moreover, GWR was an independent predictor of outcomes in logistic regression analysis. Incorporating the GWR with other clinical and resuscitation variables significantly enhanced the performance of prediction models compared to those without the GWR. Conclusions : Automated measurement of the GWR from non-contrast brain CT images offers valuable insights for predicting neurological outcomes during the early post-car

关键词： Clinical decision making CT scan Gray-white matter ratio Hypoxic-ischemic encephalopathy Out-of-hospital cardiac arrest Prognosis Return of spontaneous circulation

来源：评论

学校读者我要写书评

暂无评论

Teranga Go!: Carpooling Collaborative Consumption Community with multi-criteria hesitant fuzzy linguistic term set opinions to build confidence and trust

arXiv

引用

arXiv 2024年

作者： Montes, Rosana Morales, Jeovani Zermeño, Noe Duran, Jeronimo Herrera, Francisco Department of Software Engineering University of Granada Spain Department of Computer Science and Artificial Intelligence University of Granada Spain Andalusian Research Institute in Data Science and Computational Intelligence DaSCI Spain

Classic Delphi and Fuzzy Delphi methods are used to test content validity of a data collection tools such as questionnaires. Fuzzy Delphi takes the opinion issued by judges from a linguistic perspective reducing ambiguity in opinions by using fuzzy numbers. We propose an extension named 2-Tuple Fuzzy Linguistic Delphi method to deal with scenarios in which judges show different expertise degrees by using fuzzy multigranular semantics of the linguistic terms and to obtain intermediate and final results expressed by 2-tuple linguistic values. The key idea of our proposal is to validate the full questionnaire by means of the evaluation of its parts, defining the validity of each item as a Decision Making problem. Taking the opinion of experts, we measure the degree of consensus, the degree of consistency, and the linguistic score of each item, in order to detect those items that affect, positively or negatively, the quality of the instrument. Considering the real need to evaluate a b-learning educational experience with a consensual questionnaire, we present a Decision Making model for questionnaire validation that solve it. Additionally, we contribute to this consensus reaching problem by developing an online tool under GPL v3 license. The software visualizes the collective valuations for each iteration and assists to determine which parts of the questionnaire should be modified to reach a consensual solution. © 2024, CC BY-NC-ND.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Application of Artificial Intelligence Technique to Detect Alzheimer's Disease

Application of Artificial Intelligence Technique to Detect A...

引用

Intelligent Computing and Control for engineering and Business Systems (ICCEBS)

作者： Arulprakash A S. Ponmaniraj Gokul Rajan V Divya A Department of Computer Science and Engineering Sathyamaba Institute of Science and Technology Chennai Department of Computational Intelligence Saveetha School of Engineering SIMATS University Thandalam School of Computing Science and Engineering Galgotias University Greater Noida Department of Computer Science and Engineering Vandayar Engineering College Thanjavur

Aeras of investigational and clinical study have demonstrated several pathways in the progression of Alzheimer's disease (AD), but no treatments have been developed. Patient lifestyle, clinical, and biological data are increasingly being collected through open data-sharing programmes, and the resulting data set may be infinite in size, far exceeding the capacity of humans to make sense of it. Recent advances in artificial intelligence have opened the door to the possibility of using analysis of medical imagery to aid in the analysis of Alzheimer's disease. A variety of methods, including those based on artificial intelligence, have been devised and used in several research to aid in the CAD of AD identification. The use of AI methods to solve Alzheimer's disease diagnosis challenges in brain imaging will be a major focus of future research in this field. This article delivers an impression of the many images processing, feature extraction, and machine learning approaches that are used to solve the AD detection problem. The final section of the study will include a synopsis of the existing body of knowledge as well as a critical appraisal of potential future research avenues and open questions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality and Artificial Intelligence in Sign Language Expression

Augmented Reality and Artificial Intelligence in Sign Langua...

引用

IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing (INCOS)

作者： Kaviyaraj R P. Sathya P. Nandhini Vinoth Kumar P Sureshkumar Chelliah Ezhilmathi S Department of computational intelligence SRM institute of science and technology Kattankulathur India Department of Computer Science and Engineering Sri Shanmuga Collage of Engineering and Technology Sankari India Department of Artificial Intelligence and Data Science St. Joseph's Institute of Technology OMR Chennai

ISBN: (数字)9798350361186

ISBN: (纸本)9798350361193

Sign language, the vibrant tapestry of hand gestures and facial expressions, is the lifeblood of Deaf and hardof-hearing communities. For millions of signers, American Sign Language (ASL) runs deeper than communication, fundamental to identity, expression, and belonging. And yet an unshakeable communication gap leaves users of ASL frequently marooned away from the hearing world, kept from education, healthcare, or employment, or from basic, everyday transactions. By posing this new unsolved challenge to the power and promise of Artificial Intelligence (AI), this work leads the way towards closing that chasm by real-time recognition and translation of full ASL. Our approach employs a novel variant of Random Forest and utilizes cutting-edge video processing techniques to identify and understand the nuanced, often exquisitely delicate detail of ASL signing, at unprecedented levels of accuracy, and at speed. Another layer of innovation that characterizes our work is our integration of augmented reality (AR). By embedding AR along with our translator of artificial intelligence tech, we intend to completely change the way American Sign Language (ASL) is conveyed by directly engraining our already robust Random Forest model and advanced video processing techniques to project the ASL translation directly into your visual field in real time. The goal to demystify this complex and vivid language and, in doing so, to remove the communication barriers that persist between the Deaf community and the rest of the world, thus, fostering inclusion.

关键词： Sign language computational modeling Signal processing algorithms Assistive technologies Predictive models Streaming media Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Differentially Private Non-Convex Optimization under the KL Condition with Optimal Rates

arXiv

引用

arXiv 2023年

作者： Menart, Michael Ullah, Enayat Arora, Raman Bassily, Raef Guzmán, Cristóbal Department of Computer Science & Engineering The Ohio State University United States Department of Computer Science The Johns Hopkins University United States The Ohio State University United States Institute for Mathematical and Computational Engineering Faculty of Mathematics School of Engineering Pontificia Universidad Católica de Chile Chile

We study private empirical risk minimization (ERM) problem for losses satisfying the (γ, κ)-KurdykaLojasiewicz (KL) condition, that is, the empirical loss F satisfies F (w) − minw F (w) ≤ γκk∇F (w)kκ. The Polyak-Lojasiewicz (PL) condition is a special case of this condition when κ = 2. Specifically, we study this problem under the constraint of ρ zero-concentrated differential privacy (zCDP). When κ ∈ [1, 2] and the loss function is Lipschitz and smooth over a sufficiently large region, we provide a new algorithm based on variance reduced gradient descent that achieves the rate O((n√ √dρ)κ) on the excess empirical risk, where n is the dataset size and d is the dimension. We further show that this rate is nearly optimal. When κ ≥ 2 and the loss is instead Lipschitz and weakly convex, we show it is possible to achieve the rate O((n√ √dρ)κ) with a private implementation of the proximal point method. When the KL parameters are unknown, we provide a novel modification and analysis of the noisy gradient descent algorithm and show that this algorithm achieves a rate of O((n√ √dρ) 42−κκ) adaptively, which is nearly optimal when κ = 2. We further show that, without assuming the KL condition, the same gradient descent algorithm can achieve fast convergence to a stationary point when the gradient stays sufficiently large during the run of the algorithm. Specifically, we show that this algorithm can approximate stationary points of Lipschitz, smooth (and possibly nonconvex) objectives with rate as fast as O(n√ √dρ) and never worse than O((n√ √dρ)1/2). The latter rate matches the best known rate for methods that do not rely on variance reduction. © 2023, CC BY.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced Healthcare: Densenet Based Alzheimer's Disease Prediction and Online Consultation for Accessible Medical Support

AI-Enhanced Healthcare: Densenet Based Alzheimer's Disease P...

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： Wilfred Blessing N. R Hemalatha Gunasekaran Hariharan B. Jaber Saleh Salim Al Jabri Kavitha S. J Sutherlin Subitha G. College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Sultanate of Oman Department of Computational Intelligence SRM Institute of Science and Technology Kattankulathur Tamil Nadu India Department of Computer Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India Department of Computer Science and Engineering Stella Mary's College of Engineering Aruthenganvilai Tamil Nadu India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Improvements in patient care and early disease detection possibilities are two of the ways artificial intelligence is transforming the healthcare industry. Alzheimer's disease, a neurodegenerative disease that worsens with time, is among the most difficult diseases to exactly identify in early stages. Patients thus delay in treatment and experience a decline in their quality of life. Research is still under progress, thus knowledge about how AI-driven prediction models could be combined with readily available healthcare services remains lacking. This work presents a special artificial intelligence-powered system consisting of DenseNet-based deep learning for Alzheimer's disease prediction with an online consultation platform. The proposed approach analyzes brain MRI data and classifies Alzheimer's stages with higher accuracy using a DenseNet architecture, well-known for its exceptional performance in the field of feature extraction. Comprising three thousand magnetic resonance imaging (MRI) images, the dataset has been preprocessed for noise reduction and tuned for models performance. At 98.5%, the DenseNet model exceeded other methods including VGGNet and ResNet in accuracy.

关键词： Accuracy Magnetic resonance imaging Redundancy Medical services Predictive models Brain modeling Real-time systems Alzheimer's disease Medical diagnostic imaging Overfitting

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence in Health Care Computing and Assessments in Oman: an Effectual Study

Artificial Intelligence in Health Care Computing and Assessm...

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Health care plays a vital responsibility in a human life span. World countries targets to provide better care for their citizens. Digital transformations and innovations in Artificial Intelligence (AI) technologies helps in deep for the novel solutions to speed-up the decision making process in health management and patient consulting. AI branches including Machine Learning (ML), Deep Learning (DL), Neural Networks (NN), Natural Language Processing (NLP) and so forth can support innovations in heal care domain. This paper presents the comprehensive and noble review on recent existing tools and techniques and also recommends advanced techniques for health care industry that are to be used in Sultanate of Oman. Furthermore, overcoming AI challenges are resulted and presented through the study. This work mainly aimed to produce the multiple dimensions and challenges that helps to develop AI powered real-life applications in health care support system.

关键词： Deep learning Technological innovation Ethics Reviews Decision making Surgery Medical services Natural language processing Medical diagnostic imaging Diseases

来源：评论

学校读者我要写书评

暂无评论

TOWARDS DIVERSE EVALUATION OF CLASS INCREMENTAL LEARNING: A REPRESENTATION LEARNING PERSPECTIVE 3

TOWARDS DIVERSE EVALUATION OF CLASS INCREMENTAL LEARNING: A ...

引用

3rd Conference on Lifelong Learning Agents, CoLLAs 2024

作者： Cha, Sungmin Kwak, Jihwan Shim, Dongsub Kim, Hyunwoo Lee, Moontae Lee, Honglak Moon, Taesup Computer Science Department Courant Institute of Mathematical Sciences New York University United States Department of Electrical and Computer Engineering Seoul National University Korea Republic of Advanced Machine Learning Lab LG AI Research Korea Republic of Zhejiang Lab China Department of Information and Decision Sciences University of Illinois Chicago United States ASRI INMC IPAI AIIS Seoul National University Korea Republic of

Class incremental learning (CIL) algorithms aim to continually learn new object classes from incrementally arriving data while not forgetting past learned classes. The common evaluation protocol for CIL algorithms is to measure the average test accuracy across all classes learned so far - however, we argue that solely focusing on maximizing the test accuracy may not necessarily lead to developing a CIL algorithm that also continually learns and updates the representations, which may be transferred to the downstream tasks. To that end, we experimentally analyze neural network models trained by CIL algorithms using various evaluation protocols in representation learning and propose new analysis methods. Our experiments show that most state-of-the-art algorithms prioritize high stability and do not significantly change the learned representation, and sometimes even learn a representation of lower quality than a naive baseline. However, we observe that these algorithms can still achieve high test accuracy because they enable a model to learn a classifier that closely resembles an estimated linear classifier trained for linear probing. Furthermore, the base model learned in the first task, which involves single-task learning, exhibits varying levels of representation quality across different algorithms, and this variance impacts the final performance of CIL algorithms. Therefore, we suggest that the representation-level evaluation should be considered as an additional recipe for more diverse evaluation for CIL algorithms. © 2024 CoLLAs. All Rights Reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Physics Informed Deep Learning for Strain Gradient Continuum Plasticity

arXiv

引用

arXiv 2024年

作者： Tyagi, Ankit Suman, Uttam Mamajiwala, Mariya Roy, Debasish Computational Mechanics Lab Department of Civil Engineering Indian Institute of Science Bangalore India Department of Computer Science University of Sheffield United Kingdom Centre of Excellence in Advanced Mechanics of Materials Indian Institute of Science Bangalore India

We use a space-time discretization based on physics informed deep learning (PIDL) to approximate solutions of a class of rate-dependent strain gradient plasticity models. The differential equation governing the plastic flow, the so-called microforce balance for this class of yield-free plasticity models, is very stiff, often leading to numerical corruption and a consequent lack of accuracy or convergence by finite element (FE) methods. Indeed, setting up the discretized framework, especially with an elaborate meshing around the propagating plastic bands whose locations are often unknown apriori, also scales up the computational effort significantly. Taking inspiration from physics informed neural networks, we modify the loss function of a PIDL model in several novel ways to account for the balance laws, either through energetics or via the resulting PDEs once a variational scheme is applied, and the constitutive equations. The initial and the boundary conditions may either be imposed strictly by encoding them within the PIDL architecture, or enforced weakly as a part of the loss function. The flexibility in the implementation of a PIDL technique often makes for its ready interface with powerful optimization schemes, and this in turn provides for many possibilities in posing the problem. We have used freely available open-source libraries that perform fast, parallel computations on GPUs. Using numerical illustrations, we demonstrate how PIDL methods could address the computational challenges posed by strain gradient plasticity models. Also, PIDL methods offer abundant potentialities, vis-á-vis a somewhat straitjacketed and poorer approximant of FE methods, in customizing the formulation as per the problem objective. © 2024, CC BY.

关键词： Constitutive equations

来源：评论

学校读者我要写书评

暂无评论

Hybrid2 Neural ODE Causal Modeling and an Application to Glycemic Response

arXiv

引用

arXiv 2024年

作者： Zou, Bob Junyi Levine, Matthew E. Zaharieva, Dessi P. Johari, Ramesh Fox, Emily B. Institute for Computational and Mathematical Engineering Stanford University United States Broad Institute of MIT and Harvard United States Department of Pediatrics Stanford University United States Department of Management Science and Engineering Stanford University United States Department of Statistics Department of Computer Science Stanford University United States Chan Zuckerberg Biohub – San Francisco United States

Hybrid models composing mechanistic ODE-based dynamics with flexible and expressive neural network components have grown rapidly in popularity, especially in scientific domains where such ODE-based modeling offers important interpretability and validated causal grounding (e.g., for counterfactual reasoning). The incorporation of mechanistic models also provides inductive bias in standard blackbox modeling approaches, critical when learning from small datasets or partially observed, complex systems. Unfortunately, as the hybrid models become more flexible, the causal grounding provided by the mechanistic model can quickly be lost. We address this problem by leveraging another common source of domain knowledge: ranking of treatment effects for a set of interventions, even if the precise treatment effect is unknown. We encode this information in a causal loss that we combine with the standard predictive loss to arrive at a hybrid loss that biases our learning towards causally valid hybrid models. We demonstrate our ability to achieve a win-win, state-of-the-art predictive performance and causal validity, in the challenging task of modeling glucose dynamics post-exercise in individuals with type 1 diabetes. © 2024, CC BY.

关键词： Ordinary differential equations

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：