检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhou, Junpeng Zhang, Na Li, Qia School of Computer Sciences and Engineering Sun Yat-Sen University Guangzhou510006 China Department of Applied Mathematics College of Mathematics and Informatics South China Agricultural University Guangzhou510642 China School of Computer Sciences and Engineering Guangdong Province Key Laboratory of Computational Science Sun Yat-Sen University Guangzhou510006 China

In this paper, we consider a class of structured fractional programs, where the numerator part is the sum of a block-separable (possibly nonsmooth nonconvex) function and a locally Lipschitz differentiable (possibly nonconvex) function, while the denominator is a convex (possibly nonsmooth) function. We first present a novel reformulation for the original problem and show the relationship between optimal solutions, critical points and KL exponents of these two problems. Inspired by the reformulation, we propose a flexible framework of multi-proximity gradient algorithms (MPGA), which computes the proximity operator with respect to the Fenchel conjugate associated with the convex denominator of the original problem rather than evaluating its subgradient as in the existing methods. Also, MPGA employs a nonmonotone linear-search scheme in its gradient descent step, since the smooth part in the numerator of the original problem is not globally Lipschitz differentiable. Based on the framework of MPGA, we develop two specific algorithms, namely, cyclic MPGA and randomized MPGA, and establish their subsequential convergence under mild conditions. Moreover, the sequential convergence of cyclic MPGA with the monotone line-search (CMPGA ML) is guaranteed if the extended objective associated with the reformulated problem satisfies the Kurdyka-Lojasiewicz (KL) property and some other mild assumptions. In particular, we prove that the corresponding KL exponents are 12 for several special cases of the fractional programs, and so, CMPGA ML exhibits a linear convergence rate. Finally, some preliminary numerical experiments are performed to demonstrate the efficiency of our proposed algorithms. Copyright © 2023, The Authors. All rights reserved.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

An efficient algorithm for fuzzy frequent itemset mining

An efficient algorithm for fuzzy frequent itemset mining

引用

作者： Wu, Tsu-Yang Lin, Jerry Chun-Wei Yun, Unil Chen, Chun-Hao Srivastava, Gautam Lv, Xianbiao College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China Department of Computer Science Electrical Engineering and Mathematical Sciences Western Norway University of Applied Sciences Bergen Norway Department of Computer Engineering Sejong University Seoul Korea Republic of Department of Computer Science and Information Engineering Tamkang University New Taipei City Taiwan Department of Information and Finance Management National Taipei University of Technology Taipei Taiwan Department of Mathematics Computer Science Brandon University Brandon Canada Shenzhen China

Association-rule mining (ARM) has concerned as an important and critical research issue in the field of data analytics and mining that aims at finding the correlations among the items in binary databases. However, the conventional algorithms considered the frequency of the item(set) in binary databases for ARM, which is not sufficient in real-life situations. Mining of useful information is not an easy task especially if the item(set) consists of the added values. Moreover, the discovered knowledge is not easy to understand if you are not the domain experts. For the past decades, several intelligent systems involved the fuzzy-set theory for many domains and applications due to it is interpretable for human reasoning. Before, the Apriori-based method for discovering fuzzy frequent itemsets (FFIs) based on the type-2 fuzzy-set theory was proposed, which requires the amount of computations with enormous candidates. In this study, we then first present a fast list-based multiple fuzzy frequent itemset mining (named as LFFT2)algorithm under type-2 fuzzy-set theory. It is developed by the type-2 membership functions to retrieve the multiple fuzzy frequent itemsets for presenting more useful and meaningful knowledge for making the efficient strategies or decisions. From the results shown in the experiments, it is clear to see that the developed LFFT2 outperforms the conventional Apriori-based approach regarding the execution time and the number of examined nodes in the search space. © 2020 - IOS Press and the authors. All rights reserved.

关键词： Fuzzy set theory

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Evaluation of Driver Drowsiness Identification System using Camera based Improved Deep Learning Methodology

A Comprehensive Evaluation of Driver Drowsiness Identificati...

引用

International Conference on Smart Structures and Systems (ICSSS)

作者： P. Malathi Sivakami Sundari M S. Karkuzhali Umamaheswari. B A Thenmozhi Velu Aiyyasamy Department of Data Analytics Saveetha College of Liberal Arts and Sciences SIMATS Chennai Tamil Nadu India Department of Mathematics Agni College of Technology OMR Chennai Chennai Tamil Nadu India Department of General Engineering R.M.K. Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Tamil Nadu India Department of Electronics and Communication Engineering Kings Engineering College Chennai Tamil Nadu India Department of M.E.- Applied Electronics Meenakshi Sundararajan Engineering College Chennai Tamil Nadu India

Particularly on highways, drowsy driving causes a large number of collisions while driving. With the goal to identify driver sleepiness while enhancing roadway security, it is now vital to grasp the situation and take early remedial steps. Using a proposed Image based Learning Strategy for Drowsiness Identification (ILSDI) and cross-validation with the conventional model called Convolutional Neural Network (CNN), the suggested framework offers an approach to assess the degree of fatigue among drivers according to modifications in a driver eyeballs motion. This will assist in deal with the problem concerning roadway protection. In addition, four types of expressions on the face were identified and categorized—open, closed, blinking, and no gazing using ILSDI and CNN models, indicating levels of tiredness. Finding, following, and analyzing the driver’s face and eyes in real-time to calculate a sleepiness index is the goal of this technology, which operates in different lighting circumstances. Avoiding these kinds of accidents is possible with the help of a driver sleepiness monitoring structure, which uses a digital camera and accompanying software to measure the rate of blinking as well as the dimension of the driver’s eyes. The driver sleepiness recognition system can identify when the driver is getting sleepy and sound an alarm if necessary. It is based on an offline implementation of a deep learning algorithm that uses ILSDI and CNN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bounds on the ground state energy of quantum p-spin Hamiltonians

arXiv

引用

arXiv 2024年

作者： Anschuetz, Eric R. Gamarnik, David Kiani, Bobak T. Institute for Quantum Information and Matter Caltech Walter Burke Institute for Theoretical Physics Caltech MIT Center for Theoretical Physics MIT United States Operations Research Center Statistics and Data Science Center Sloan School of Management MIT United States John A. Paulson School of Engineering and Applied Sciences Department of Electrical Engineering and Computer Science MIT Harvard United States

We consider the problem of estimating the ground state energy of quantum p-local spin glass random Hamiltonians, the quantum analogues of widely studied classical spin glass models. Our main result shows that the maximum energy achievable by product states has a well-defined limit (for even p) as n → ∞ and is Eproduct∗ = √2 log p in the limit of large p. This value is interpreted as the maximal energy of a much simpler so-called Random Energy Model, widely studied in the setting of classical spin glasses. The proof of the limit existing follows from an extension of Fekete’s Lemma after we demonstrate near super-additivity of the (normalized) quenched free energy. The proof of the value follows from a second moment method on the number of states achieving a given energy when restricting to an ǫ-net of product states. Furthermore, we relate the maximal energy achieved over all states to a p-dependent constant γ (p), which is defined by the degree of violation of a certain asymptotic independence ansatz over graph matchings. We show that the maximal energy achieved by all states E∗ (p) in the limit of large n is at most pγ (p)Eproduct∗ . We also prove using Lindeberg’s interpolation method that the limiting E∗ (p) is robust with respect to the choice of the randomness and, for instance, also applies to the case of sparse random Hamiltonians. This robustness in the randomness extends to a wide range of random Hamiltonian models including SYK and random quantum max-cut. Copyright © 2024, The Authors. All rights reserved.

关键词： Hamiltonians

来源：评论

学校读者我要写书评

暂无评论

Fundamentals of Clustered Molecular Nanonetworks

arXiv

引用

arXiv 2022年

作者： Azimi-Abarghouyi, Seyed Mohammad Dhillon, Harpreet S. Tassiulas, Leandros The School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Wireless@VT Bradley Department of Electrical and Computer Engineering Virginia Tech BlacksburgVA United States The School of Engineering & Applied Science The Yale Institute for Network Science Yale University New HavenCT United States

We present a comprehensive approach to the modeling, performance analysis, and design of clustered molecular nanonetworks in which nano-machines of different clusters release an appropriate number of molecules to transmit their sensed information to their respective fusion centers. The fusion centers decode this information by counting the number of molecules received in the given time slot. Owing to the propagation properties of the biological media, this setup suffers from both inter- and intra-cluster interference that needs to be carefully modeled. To facilitate rigorous analysis, we first develop a novel spatial model for this setup by modeling nanomachines as a Poisson cluster process with the fusion centers forming its parent point process. For this setup, we first derive a new set of distance distributions in the three-dimensional space, resulting in a remarkably simple result for the special case of the Thomas cluster process. Using this, total interference from previous symbols and different clusters is characterized and its expected value and Laplace transform are obtained. The error probability of a simple detector suitable for biological applications is analyzed, and approximate and upper-bound results are provided. The impact of different parameters on the performance is also investigated. © 2022, CC0.

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

Explainable Artificial Intelligence to Detect Image Spam Using Convolutional Neural Network

arXiv

引用

arXiv 2022年

作者： Zhang, Zhibo Damiani, Ernesto Hamadi, Hussam Al Yeun, Chan Yeob Taher, Fatma C2PS Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi United Arab Emirates Department of Computing and Applied Technology Zayed University Dubai United Arab Emirates

Image spam threat detection has continually been a popular area of research with the internet's phenomenal expansion. This research presents an explainable framework for detecting spam images using Convolutional Neural Network (CNN) algorithms and Explainable Artificial Intelligence (XAI) algorithms. In this work, we use CNN model to classify image spam respectively whereas the post-hoc XAI methods including Local Interpretable Model Agnostic Explanation (LIME) and Shapley Additive Explanations (SHAP) were deployed to provide explanations for the decisions that the black-box CNN models made about spam image detection. We train and then evaluate the performance of the proposed approach on a 6636 image dataset including spam images and normal images collected from three different publicly available email corpora. The experimental results show that the proposed framework achieved satisfactory detection results in terms of different performance metrics whereas the model-independent XAI algorithms could provide explanations for the decisions of different models which could be utilized for comparison for the future study. © 2022, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Brief Review of Explainable Artificial Intelligence in Healthcare

SSRN

引用

SSRN 2023年

作者： Sadeghi, Zahra Alizadehsani, Roohallah Cifci, Mehmet Akif Kausar, Samina Rehman, Rizwan Mahanta, Priyakshi Bora, Pranjal Kumar Almasri, Ammar Alkhawaldeh, Rami S. Hussain, Sadiq Alatas, Bilal Shoeibi, Afshin Moosaei, Hossein Hladík, Milan Nahavandi, Saeid Pardalo, Panos M. Institute for Big Data Analytics Faculty of Computer Science Dalhousie University Canada Deakin University Geelong Australia The Institute of Computer Technology Tu Wien University Vienna1040 Austria University of Kotli Azad Jammu and Kashmir Azad Kashmir Kotli Pakistan Centre for Computer Science and Applications Dibrugarh University Assam India Department of Management Information Sys Al-Balqa Applied University Salt19117 Jordan Department of Computer Information Systems The University of Jordan Aqaba77110 Jordan Examination Branch Dibrugarh University Assam Dibrugarh India Department of Software Eng. Firat University Elazig23100 Turkey Data Science and Computational Intelligence Institute University of Granada Spain Department of Informatics Faculty of Science Jan Evangelista Purkyně University in Ústí nad Labem Czech Republic Department of Applied Mathematics School of Computer Science Faculty of Mathematics and Physics Charles University Prague Czech Republic Harvard Paulson School of Engineering and Applied Sciences Harvard University AllstonMA02134 United States Swinburne University of Technology HawthornVIC3122 Australia Center for Applied Optimization Department of Industrial and Systems Engineering University of Florida Gainesville32611 United States

XAI refers to the techniques and methods for building AI applications which assist end users to interpret output and predictions of AI models. Black box AI applications in high-stakes decision-making situations, such as medical domain have increased the demand for transparency and explainability since wrong predictions may have severe consequences. Model explainability and interpretability are vital successful deployment of AI models in healthcare practices. AI applications' underlying reasoning needs to be transparent to clinicians in order to gain their trust. This paper presents a systematic review of XAI aspects and challenges in the healthcare domain. The primary goals of this study are to review various XAI methods, their challenges, and related machine learning models in healthcare. The methods are discussed under six categories: Features-oriented methods, global methods, concept models, surrogate models, local pixel-based methods, and human-centric methods. Most importantly, the paper explores XAI role in healthcare problems to clarify its necessity in safety-critical applications. The paper intends to establish a comprehensive understanding of XAI-related applications in the healthcare field by reviewing the related experimental results. To facilitate future research for filling research gaps, the importance of XAI models from different viewpoints and their limitations are investigated. © 2023, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

The classification of stages of epiretinal membrane using convolutional neural network on optical coherence tomography image

引用

Methods (San Diego, Calif.) 2023年 214卷 28-34页

作者： Che-Lun Hung Keng-Hung Lin Yu-Kai Lee Dariusz Mrozek Yin-Te Tsai Chun-Hsien Lin Institute of Biomedical Informatics National Yang Ming Chiao Tung University Taiwan ROC Computer Science and Communication Engineering Providence University Taiwan ROC. Electronic address: clhung@nycu.edu.tw. Department of Ophthalmology Taichung Veterans General Hospital Taiwan ROC. Electronic address: linkh@vghtc.gov.tw. Department of Computer Science and Information Engineering Providence University Taiwan ROC. Electronic address: s1091906@gm.pu.edu.tw. Department of Applied Informatics Silesian University of Technology Poland. Electronic address: dariusz.mrozek@polsl.pl. Computer Science and Communication Engineering Providence University Taiwan ROC. Electronic address: yttsai@pu.edu.tw. Department of Ophthalmology Taichung Veterans General Hospital Taiwan ROC. Electronic address: linchunhsien@vghtc.gov.tw.

BACKGROUND AND OBJECTIVE:The gold standard for diagnosing epiretinal membranes is to observe the surface of the internal limiting membrane on optical coherence tomography images. The stages of the epiretinal membrane are used to decide the condition of the health of the membrane. The stages are not detected because some of them are similar. To accurately classify the stages, a deep-learning technology can be used to improve the classification accuracy. METHODS:A combinatorial fusion with multiple convolutional neural networks (CNN) algorithms are proposed to enhance the accuracy of a single image classification model. The proposed method was trained using a dataset of 1947 optical coherence tomography images diagnosed with the epiretinal membrane at the Taichung Veterans General Hospital in Taiwan. The images consisted of 4 stages; stages 1, 2, 3, and 4. RESULTS:The overall accuracy of the classification was 84%. The combination of five and six CNN models achieves the highest testing accuracy (85%) among other combinations, respectively. Any combination with a different number of CNN models outperforms any single CNN algorithm working alone. Meanwhile, the accuracy of the proposed method is better than ophthalmologists with years of clinical experience. CONCLUSIONS:We have developed an efficient epiretinal membrane classification method by using combinatorial fusion with CNN models on optical coherence tomography images. The proposed method can be used for screening purposes to facilitate ophthalmologists making the correct diagnoses in general medical practice.

关键词： Classification Combintorial Fusion Convolutional Neural Network Epiretinal Membrane Optical Coherence Tomography

来源：评论

学校读者我要写书评

暂无评论

Morpho-Mechanical Analysis of Porcine Growth Plate Tissue Mechanics Under Torsional Shear

SSRN

引用

SSRN 2024年

作者： Hucke, Lucie Quelhas Teixeira, Graciosa Seitz, Andreas Martin Gámez, Antonio Huß, Armin Hammer, Niels Wittek, Andreas Niestrawska, Justyna A. Personalized Biomedical Engineering Laboratory Department 2: Computer Science and Engineering Frankfurt University of Applied Sciences Frankfurt Germany Department of Mechanical Engineering and Industrial Design School of Engineering Universidad de Cádiz Cádiz Spain Division of Macroscopic and Clinical Anatomy Gottfried Schatz Research Center Medical University of Graz Graz Austria Institute of Orthopedic Research and Biomechanics Ulm University Medical Centre Ulm Germany Department of Orthopaedic and Trauma Surgery University of Leipzig Leipzig Germany Fraunhofer IWU Dresden Germany

This study aimed to investigate the microstructural and mechanical properties of growth plate tissue under torsional loading, focusing on variations across individuals, growth plate types, and anatomical locations.A total of 398 samples from three distinct growth plates in five porcine subjects were subjected to cyclic torsion tests followed by ultimate failure testing. Additionally, histological analyses were performed using Movat's pentachrome staining to assess tissue *** testing revealed significant differences in shear moduli across growth plate types;notably, the proximal femur exhibited a higher primary shear modulus compared to both the distal femur and proximal tibia. Correlation analyses showed a negative relationship between hypertrophic zone thickness and primary shear modulus (rho = -0.49 at 0.5 °/s, p © 2024, The Authors. All rights reserved.

关键词： Shear strain

来源：评论

学校读者我要写书评

暂无评论

engineering the directionality of hot carrier tunneling in plasmonic tunneling structures

arXiv

引用

arXiv 2023年

作者： Abbasi, Mahdiyeh Liao, Shusen Zhu, Yunxuan Natelson, Douglas Department of Electrical and Computer Engineering Rice University HoustonTX77005 United States Applied Physics Graduate Program Smalley-Curl Institute Rice University HoustonTX77005 United States Department of Physics and Astronomy Engineering Rice University HoustonTX77005 United States Department of Materials Science and Nanoengineering Rice University HoustonTX77005 United States

Tunneling metal-insulator-metal (MIM) junctions can exhibit an open-circuit photovoltage (OCPV) response under illumination that may be useful for photodetection. One mechanism for photovoltage generation is hot carrier tunneling, in which photoexcited carriers generate a net photocurrent that must be balanced by a drift current in the open-circuit configuration. We present experiments in electromigrated planar MIM structures, designed with asymmetric plasmonic properties using Au and Pt electrodes. Decay of optically excited local plasmonic modes preferentially creates hot carriers on the Au side of the junction, leading to a clear preferred directionality of the hot electron photocurrent and hence a preferred polarity of the resulting OCPV. In contrast, in an ensemble of symmetric devices constructed from only one Au, polarity of the OCPV has no preferred direction. Copyright © 2023, The Authors. All rights reserved.

关键词： Plasmonics

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：