检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Jose, Sharu Theresa Moothedath, Shana Department of Computer Science University of Birmingham BirminghamB15 2TT United Kingdom The Department of Electrical Engineering Iowa State University AmesIA50011 United States

We study stochastic linear contextual bandits (CB) where the agent observes a noisy version of the true context through a noise channel with unknown channel parameter. Our objective is to design an action policy that can "approximate" that of a Bayesian oracle that has access to the reward model and the noise channel parameter. We introduce a modified Thompson sampling algorithm and analyze its Bayesian cumulative regret with respect to the oracle action policy via information-theoretic tools. For d-dimensional Gaussian bandits with Gaussian context noise, our information-theoretic analysis shows that the Bayesian cumulative regret scales as O(d√T), where T is the horizon. We also consider the problem setting where the agent observes the true context with some delay after receiving the reward, and show that delayed true contexts lead to lower regret. Finally, we empirically demonstrate the performance of the proposed algorithms against baselines. © 2024, CC BY.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Task Consistent Prototype Learning for Incremental Few-shot Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： Xu, Wenbo Wu, Yanan Jiang, Haoran Wang, Yang Wu, Qiang Zhang, Jian Faculty of Engineering and Information Technology University of Technology Sydney Sydney2007 Australia School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China Department of Computer Science and Software Engineering Concordia University MontrealH3G2J1 Canada

Incremental Few-Shot Semantic Segmentation (iFSS) tackles a task that requires a model to continually expand its segmentation capability on novel classes using only a few annotated examples. Typical incremental approaches encounter a challenge that the objective of the base training phase (fitting base classes with sufficient instances) does not align with the incremental learning phase (rapidly adapting to new classes with less forgetting). This disconnect can result in suboptimal performance in the incremental setting. This study introduces a meta-learning-based prototype approach that encourages the model to learn how to adapt quickly while preserving previous knowledge. Concretely, we mimic the incremental evaluation protocol during the base training session by sampling a sequence of pseudo-incremental tasks. Each task in the simulated sequence is trained using a meta-objective to enable rapid adaptation without forgetting. To enhance discrimination among class prototypes, we introduce prototype space redistribution learning, which dynamically updates class prototypes to establish optimal inter-prototype boundaries within the prototype space. Extensive experiments on iFSS datasets built upon PASCAL and COCO benchmarks show the advanced performance of the proposed approach, offering valuable insights for addressing iFSS challenges. © 2024, CC BY-NC-SA.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Handling Imbalanced Data for Credit Card Fraud Detection 24

Handling Imbalanced Data for Credit Card Fraud Detection

引用

24th International Conference on computer and Information Technology, ICCIT 2021

作者： Mondal, Istiak Ahmed Haque, Md. Enamul Hassan, Al-Maruf Shatabda, Swakkhar United International University Department of Computer Science and Engineering Plot-2 United City Madani Avenue Bada Dhaka1212 Bangladesh

ISBN: (纸本)9781665494359

With the rising trend in online transactions, the threat of financial fraud is also rising. This makes the necessity for an effective Fraud Detection System (FDS) more than ever before. To develop such a system the financial institutes are moving towards machine learning-based approaches due to their effectiveness. Machine learning-based systems need historical data to learn. As fraud cases take place rarely, the number of positive labeled classes in financial fraud datasets are very small and the datasets remain imbalanced. For this, the possibility for machine learning-based FDS to produce misleading results is high. To counter this problem Machine Learning (ML) researchers use multiple solutions from the perspective of data-level approach, algorithm-level approach, feature engineering, ensemble models, or any combination of them. In this paper, we propose to use Generative Adversarial Network (GAN) based synthetic data generation to handle the data imbalance problem followed by an ensemble classifier for classification. We have used a standard benchmark dataset of credit card fraud data. In our experiments, we have used both traditional oversampling/undersampling and GAN-based techniques from the data-level approach and investigated their effectiveness using ML algorithms and ensemble models. We have found Generative Adversarial Network (GAN) to be more effective and stable in performance compared to traditional oversampling techniques for both ML and ensemble models. Experiments also suggest that the combination of GAN-based sampling and ensemble models provides the best results. We also have found Synthetic Minority Oversampling Technique (SMOTE) to provide more stable results compared to Adaptive Synthetic Sample (ADASYN) from the traditional oversampling technique. © 2021 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Deduction, Constrained Zero Forcing, and Constrained Searching

arXiv

引用

arXiv 2024年

作者： Burgess, Andrea Dyer, Danny Ojakian, Kerry Wang, Lusheng Xiao, Mingyu Yang, Boting Department of Mathematics and Statistics University of New Brunswick Saint JohnNBE2L 4L5 Canada Department of Mathematics and Statistics Memorial University of Newfoundland St. John’sNLA1C 5S7 Canada Department of Mathematics and Computer Science Bronx Community College The City University of New York BronxNY United States Department of Computer Science City University of Hong Kong Hong Kong School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Department of Computer Science University of Regina ReginaSKS4S 0A2 Canada

Deduction is a recently introduced graph searching process in which searchers clear the vertex set of a graph with one move each, with each searcher’s movement determined by which of its neighbors are protected by other searchers. In this paper, we show that the minimum number of searchers required to clear the graph is the same in deduction as in constrained versions of other previously studied graph processes, namely zero forcing and fast-mixed search. We give a structural characterization, new bounds and a spectrum result on the number of searchers required. We consider the complexity of computing this parameter, giving an NP-completeness result for arbitrary graphs, and exhibiting families of graphs for which the parameter can be computed in polynomial time. We also describe properties of the deduction process related to the timing of searcher movement and the success of terminal *** Codes 05C57, 05C85 Copyright © 2024, The Authors. All rights reserved.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Shewhart Median Scheme with Estimated Process Parameters Using Median Run Length for Smart Manufacturing 10

Shewhart Median Scheme with Estimated Process Parameters Usi...

引用

10th IEEE Asia-Pacific Conference on Applied Electromagnetics, APACE 2024

作者： Chong, Zhi Lin Teoh, Wei Lin Ng, Peh Sang Yeong, Wai Chung Teh, Sin Yin Universiti Tunku Abdul Rahman Faculty of Engineering and Green Technology Department of Electronic Engineering Kampar31900 Malaysia Heriot-Watt University Malaysia School of Mathematical and Computer Sciences Jalan Venna P5/2 Precinct 5 Putrajaya62200 Malaysia Universiti Tunku Abdul Rahman Faculty of Science Department of Physical and Mathematical Science Perak Kampar31900 Malaysia Monash University School of Science Jalan Lagoon Selatan Bandar Sunway Selangor Subang Jaya47500 Malaysia Universiti Sains Malaysia School of Management Penang 11800 Malaysia

ISBN: (纸本)9798350364163

The exclusive reliance on the average run length (ARL) as a control scheme's performance metric has drawn a lot of criticisms in the literature. This is because the form and skewness of the run length distribution changes depending on the amount of the mean shift in any process, making interpretation based only on the ARL potentially inaccurate. Therefore, when the process parameters are estimated (U-Case), we take into account the median run length (MRL) performance metric for the Shewhart median scheme. To demonstrate how to apply the U-Case Shewhart median scheme, we provide an example for smart manufacturing using a dataset related to the forged piston ring manufacturing process. © 2024 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

OriFeat: Origin of Replication Identification Using DNA Sequence Based Features 7

OriFeat: Origin of Replication Identification Using DNA Sequ...

引用

7th International Conference on Software engineering and computer Systems and 4th International Conference on Computational science and Information Management, ICSECS-ICOCSIM 2021

作者： Promi, Mashiyat Alam Shatabda, Swakkhar United International University Department of Computer Science and Engineering Plot-2 United City Madani Avenue Badda Dhaka1212 Bangladesh

ISBN: (纸本)9781665414074

In the genome of every species, there exists an origin, known as the origin of replication (ORI), from where the genome starts to replicate itself during the process of cell division. Finding out this origin is very important as this is the main responsible key-factor for DNA replication. In this paper, we propose a novel approach, OriFeat to predict the origin of replication. OriFeat uses a set of inexpensive features that are generated from sequences only and an effective feature selection method. The selected features are then trained by using a logistic regression classifier. We perform our experiments with a benchmark dataset of a yeast named Saccharomyces cerevisiae, and achieve 98.15%of accuracy with 10-fold cross validation. We also show a comparative study using a large number of classifiers. OriFeat significantly outperforms state-of-the-art methods. © 2021 IEEE.

关键词： DNA sequences

来源：评论

学校读者我要写书评

暂无评论

Structured Tensor Decomposition Based Channel Estimation and Double Refinements for Active RIS Empowered Broadband Systems

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Wang, Yirun Wang, Yongqing Shen, Yuyao Wang, Gongpu Tellambura, Chintha Beijing Institute of Technology School of Information and Electronics Beijing100081 China Beijing Jiaotong University Engineering Research Center of Network Management Technology for High Speed Railway Ministry of Education School of Computer Science and Technology Beijing100044 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada

Channel parameter recovery is critical for the next-generation reconfigurable intelligent surface (RIS)-empowered communications and sensing. Tensor-based mechanisms are particularly effective, inherently capturing the multi-dimensional nature of wireless channels. However, existing studies assume either a line-of-sight (LOS) scenario or a blocked TX-RX channel. This paper solves a novel problem: tensor-based channel parameter estimation for active RIS-aided multiple-antenna broadband connections in fully multipath environments with the TX-RX link. System settings are customized to construct a fifth-order canonical polyadic (CP) signal tensor that matches the five-dimensional channel. Four tensor factors contain redundant columns, rendering the classical Kruskal's condition for decomposition uniqueness unsatisfied. The fifth-order Vandermonde structured CP decomposition (VSCPD) is developed to address this challenge, making the tensor factorization problem solvable using only linear algebra and offering a relaxed general uniqueness condition. With VSCPD as a perfect decoupling scheme, a sequential triple-stage channel estimation algorithm is proposed based on one-dimensional parameter estimation. The first stage enables multipath identification and algebraic coarse estimation. The following two stages offer optional successive refinements at the cost of increased complexity. The closed-form Cramér-Rao lower bound (CRLB) is derived to assess the estimation performance. Herein, the noise covariance matrix depends on multipath parameters in our active-RIS scenario. Numerical results are provided to verify the effectiveness of proposed algorithms under various evaluation metrics. Our results also show that active RIS can significantly improve channel estimation performance compared to passive RIS. © 2025 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Representation Refinement Based on Convex Combination for 3-D Human Poses Estimation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6500-6508页

作者： Chen, Luefeng Cao, Wei Zheng, Biao Wu, Min Pedrycz, Witold Hirota, Kaoru China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada Macau University of Science and Technology Institute of Systems Engineering Taipa999078 China Istinye University Research Center of Performance and Productivity Analysis Istanbul34010 Turkey Tokyo Institute of Technology Yokohama226-8502 Japan

In the human pose estimation task, on the one hand, 3-D pose always has difficulty in dividing different 2-D poses if the view is limited;on the other hand, it is hard to reduce the lifting ambiguity because of the lack of depth information, it is an important and challenging problem. Therefore, two-stage representation refinement based on the convex combination for 3-D human pose estimation is proposed, in which the two-stage method includes a dense-spatial-temporal convolutional network and a local-to-refine network. The former is applied to determine the features between each video frame;the latter is used to get the different scales of pose details. It aims to address the difficulty of estimating 3-D human pose from 2-D image sequences. In such a way, it can better use the relations between every frame in the sequence of the pose video to produce more accurate results. Finally, we combine the above network with a block called convex combination to help refine the 3-D pose location. We test the proposed approach on both Human3.6m and MPII datasets. The result confirms that our method can achieve better performance than improved CNN supervision, a simple yet effective baseline, and coarse-to-fine volumetric prediction. Besides, a robustness test experiment is carried out for the proposed method while the input is interrupted. The result verifies that our method shows better robustness. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Effect of impurity and radiation defects on the scattering of normal and fluctuation carriers in YBa2Cu3O7–δ and Y1–zPrzBa2Cu3O7–δ single crystals

引用

Fizika Nizkikh Temperatur 2024年第11期50卷 1128-1138页

作者： Azarenkov, N.A. Khadzhai, G.Ya. Gevorkyan, E.S. Goulatis, I. Chroneos, A. Feher, A. Komisarov, A.O. Vragov, O.Yu. Kovrigin, V.A. Vovk, R.V. V. N. Karazin Kharkiv National University Kharkiv61022 Ukraine Institute of Solid State Physics Materials Science and Technologies NSC-KIPT Kharkiv61108 Ukraine Ukrainian State University of Railway Transport Kharkiv61050 Ukraine Casimir Pulaski Radom University Radom Poland Department of Electrical and Computer Engineering University of Thessaly Volos38333 Greece Department of Materials Imperial College London LondonSW7 2BP United Kingdom Centre of Low Temperature Physics Faculty of Science P. J. Safarik University Kosice041 54 Slovakia

The effect of medium fluences (from 1019 е/cm2 to 1020 е/cm2) of fast electron irradiation or the change in the praseodymium concentration in the range 0.0 ≤ z ≤ 0.5 on the excess conductivity of optimally oxygen-doped YBa2Cu3O7–δ single crystals has been investigated. Irradiation leads to the appearance of a significant number of defects that cause a decrease in anisotropy, an appreciable increase in phonon scattering, reduction of Tc, and broadening of the superconducting transition. Under the conditions specified, the temperature dependence of electrical resistivity is approximated with high accuracy by the charge carriers’ scattering on defects and phonons, and fluctuating conductivity in the Lawrence–Doniach model. It was determined that at fluences 0 ≤ Ф ≤ 6.5·1019 е/cm2, the value of the transverse coherence length ξс(0) increases with an increase of Ф by about three times or more than four times as the content of praseodymium in the sample increases to z ≈ 0.42. In both cases, the 2D–3D crossover point shifts upward in temperature. In contrast to the case of irradiation with low fluences (Ф ≤ 1019 е/cm2) or doping with praseodymium up to concentrations z ≤ 0.39, irradiation with medium fluences and doping with praseodymium at higher concentrations leads to a nonmonotonic dependence of the transverse coherence length ξс(0) on the irradiation fluence, with characteristic maxima at Ф ~ (7–8)·1019 е/cm2 or z ≈ 0.42, which may be due to the general suppression of the superconducting characteristics. © N. A. Azarenkov, G. Ya. Khadzhai,·E. S. Gevorkyan, I. Goulatis, A. Chroneos, A. Feher, A. O. Komisarov, O. Yu. Vragov, V. A. Kovrigin, and R. V. Vovk, 2024.

关键词： Phonon scattering

来源：评论

学校读者我要写书评

暂无评论

Predictive modeling and optimization of WS2 thin-film solar cells: A comprehensive study integrating machine learning, deep learning and SCAPS-1D approaches

引用

Renewable Energy 2025年 252卷

作者： Khan, Tanvir Mahtab Shams, Md Atik Khatun, Most Marzia Chowdhury, Jamim Hossain Uddin, Md Saif Emon, Tofail Ahmmed Shakil, Mirza Md Ahmed, Sheikh Rashel Al Department of Electrical and Electronic Engineering Bangladesh University of Business and Technology Mirpur-2 Dhaka1216 Bangladesh Department of Computer Science and Engineering University of Asia Pacific 74/A Green Rd Dhaka1205 Bangladesh Department of Electrical Electronic and Communication Engineering Pabna University of Science and Technology Pabna6600 Bangladesh Department of Electrical & Electronic Engineering Rajshahi University of Engineering & Technology Rajshahi6204 Bangladesh Department of Electrical and Electronic Engineering University of Asia Pacific 74/A Green Rd Dhaka1205 Bangladesh

In this study, the SCAPS-1D simulator is employed to design and examine the photovoltaic characteristics of the WS2 absorber-based thin-film solar cell with various electron and hole transport layers. Among the various structures, the Al/FTO/TiO2/WS2/Zn3P2/Ni photovoltaic device provides excellent performances due to the proper energy band alignment at interfaces with favorable material properties. Here, the outputs of the proposed structure are assessed by varying the thickness, carrier concentration, and defect density of the absorber layer. The thermal stability of the device is also determined by analyzing the impact of temperature on the cell performance. The proposed device reveals outstanding performances, including Voc of 1.03 V, Jsc of 35.04 mA/cm2, fill-factor of 87.73 %, and admirable efficiency of 31.78 %. Furthermore, three machine learning and eight deep learning methods are introduced to compare and determine the most efficient algorithm for photovoltaic devices. Among the eleven algorithms, the multi-layer perceptron model demonstrates outstanding performance including a lower MSE of 0.0213 and an outstanding R2 of 0.9992, making it the most accurate model for outcome prediction. Here, the impact of material properties on model output is also investigated. In general, these results may help experimental researchers to design highly efficient and low-cost solar devices. © 2025 Elsevier Ltd

关键词： Polymer solar cells

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：