检索结果-内蒙古大学图书馆

Nonlinearity in Large-Cycle Cellular Automata

Complex Systems 2025年第1期34卷 129-160页

作者： Mukherjee, Sukanya Adak, Sumit Department of Computer Science and Engineering Institute of Engineering and Management Kolkata University of Engineering and Management West Bengal Kolkata700091 India Department of Applied Mathematics and Computer Science DTU Compute Technical University of Denmark Kgs. Lyngby2800 Denmark

The class of maximal-length cellular automata (CAs) has gained significant attention over the last few years due to the fact that it can generate cycles with the longest possible lengths. For every l of the form l = 2n-1 where n ∈ , a cycle of length l can be generated by a cellular automaton (CA) of size ⌊log2 l⌋ + 1;this maximal-length CA is in fact the optimal (minimum-sized) CA to generate a cycle of length l. However, maximal-length CAs are, in general, linear and have some drawbacks. Moreover, it is nontrivial to address this problem for any l ∈ , that is, removing the constraint that l is of the form 2n-1. In this paper we therefore employ nonlinearity in the rules and aim to generate the near-optimal CA for any given cycle length l, meaning that the generated CAs will be of size n = (⌊log2 l⌋ + 1) + d, where the displacement d is as small as possible. We use a generic operator to concatenate a collection of component CAs of sizes n1, n2, …, nk by employing an evolutionary strategy. Here, n = n1 + n2 + ⋯ + nk and l ≥ lcm(1, 2, …, k ), where i (1 ≤ i ≤ k) is the maximum cycle length of a CA of size ni . An influencing factor in the design of component CAs is to achieve the near-optimal CA for a given cycle length. Here we consider nonlinear reversible large-cycle CAs as component CAs. We also measure the effectiveness of nonlinearity in large-cycle generation. © 2025, Complex Systems Publications, Inc. All rights reserved.

关键词： CAs cellular automata evolution large-cycle CA neighborhood dependent nonlinearity reversible CAs

来源：评论

学校读者我要写书评

暂无评论

A Convolutional Neural Network Model for Wheat Crop Disease Prediction

引用

computers, Materials & Continua 2023年第5期75卷 3867-3882页

作者： Mahmood Ashraf Mohammad Abrar Nauman Qadeer Abdulrahman A.Alshdadi Thabit Sabbah Muhammad Attique Khan Department of Computer Science and Artificial Intelligence College of Computer Science and EngineeringUniversity of JeddahJeddah21577Saudi Arabia Department of Computer Science Bacha Khan University CharsaddaKhyber Pakhtunkhwa24461Pakistan Department of Computer Science Federal Urdu University of ArtsScience&TechnologyIslamabad45570Pakistan Department of Information Systems and Technology College of Computer Science and EngineeringUniversity of JeddahJeddah21577Saudi Arabia Faculty of Technology and Applied Sciences Al-Quds Open UniversityAl-Bireh1804Palestine Department of Computer Science HITEC UniversityTaxila47080Pakistan

Wheat is the most important cereal crop,and its low production incurs import pressure on the *** fulfills a significant portion of the daily energy requirements of the human *** wheat disease is one of the major factors that result in low production and negatively affects the national ***,timely detection of wheat diseases is necessary for improving *** CNN-based architectures showed tremendous achievement in the image-based classification and prediction of crop ***,these models are computationally expensive and need a large amount of training *** this research,a light weighted modified CNN architecture is proposed that uses eight layers particularly,three convolutional layers,three SoftMax layers,and two flattened layers,to detect wheat diseases *** high-resolution images were collected from the fields in Azad Kashmir(Pakistan)and manually annotated by three human *** convolutional layers use 16,32,and 64 *** filter uses a 3×3 kernel *** strides for all convolutional layers are set to *** this research,three different variants of datasets are *** variants S1-70%:15%:15%,S2-75%:15%:10%,and S3-80%:10%:10%(train:validation:test)are used to evaluate the performance of the proposed *** extensive experiments revealed that the S3 performed better than S1 and S2 datasets with 93%*** experiment also concludes that a more extensive training set with high-resolution images can detect wheat diseases more accurately.

关键词： Machine learning wheat crop disease prediction convolutional neural network artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Robust WCET Estimation via Ensemble Learning with Fractional-Order Legendre Function Kernels 5

Robust WCET Estimation via Ensemble Learning with Fractional...

引用

5th National and the 1st International Conference on applied Research in Electrical Engineering, AREE 2025

作者： Monfared, Amir Hussein Ataei Moghaddam, Mahdi Movahedian Sharif-Bakhtiar, Sheedeh Parand, Kourosh Borna, Keivan Kharazmi University Faculty of Mathematics and Computer Science Department of Computer Science Tehran Iran Shahid Beheshti University Faculty of Mathematical Sciences Department of Computer and Data Sciences Tehran Iran Institute for Cognitive and Brain Sciences Shahid Beheshti University Department of Cognitive Modeling Tehran Iran

ISBN: (纸本)9798350377170

Estimating Worst-Case Execution Time (WCET) as a regression problem has become increasingly challenging due to the complexity of modern hardware and software systems. Traditional statistical methods often fall short of providing accurate and reliable estimates. To address these limitations, ensemble learning methods have emerged as a promising approach for capturing edge cases in execution scenarios. This paper proposes a novel ensemble model that integrates fractional-order Legendre functions (FLF) to enrich feature representation. This integration reduces correlations between individual models within the ensemble, enhancing generalization capabilities. Our method achieves significant reductions in Mean Squared Error (MSE) for WCET estimates while maintaining high levels of safeness. Specifically, the proposed model maintained an error below one across most benchmarks, with safeness levels of %100 in 13 out of 16 benchmarks. These findings underscore the efficacy of our approach and its potential to provide robust and accurate WCET estimates for complex systems. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Continual Reinforcement Learning Without Replay Buffers 12

Continual Reinforcement Learning Without Replay Buffers

引用

12th IEEE International Conference on Intelligent Systems, IS 2024

作者： Krawczyk, Alexander Bagus, Benedikt Denker, Yannick Gepperth, Alexander University of Applied Sciences Fulda Applied Computer Science Department Fulda36037 Germany

ISBN: (纸本)9798350350982

We introduce a novel technique to address continual reinforcement learning (CRL), i.e., reinforcement learning (RL) in non-stationary environments. This requires agents to rapidly update their policies to new statistics while avoiding the catastrophic forgetting (CF) of previous policies. In RL, CF is commonly circumvented by experience replay (ER) from a large buffer. As we show, this leads to slow updating of policies, since new statistics must be sufficiently represented in the buffer. In addition, non-stationarities can introduce contradictions that an agent needs to adapt to. Our approach, unlike traditional methods such as deep Q-networks (DQNs) with ER, enables fast reaction times under minimal memory requirements, making it suitable for real-world applications. It generalizes adiabatic replay (AR), a recently introduced generative replay (GR) method for continual learning (CL). For evaluation, we introduce two robotic simulation-based CRL benchmarks which are partitioned into tasks by environment shifts, showcasing our approach's ability to retain previously acquired policies while being able to learn novel skills. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Video Object Segmentation Using JIT K-Means Clustering 16

Efficient Video Object Segmentation Using JIT K-Means Cluste...

引用

16th International Conference on Knowledge and Smart Technology, KST 2024

作者： Khamprapai, Wanida Pensiri, Fuangfar Visutsak, Porawat Kasetsart University Faculty of Science at Sriracha Department of Computer Science and Information Sriracha Campus Chonburi Thailand KMUTNB Faculty of Applied Science Department of Computer and Information Science Bangkok Thailand

ISBN: (纸本)9798350370737

Video segmentation dissects video sequences into distinct regions based on visual cues like object borders, movement patterns, color variations, and textures. This partitioning aims to isolate individual objects and temporal events from the background, ultimately revealing a more structured and interpretable representation of the video content. In this work, we propose K-means clustering and MATLAB Just-In-Time (JIT) accelerator within a video segmentation framework to boost both accuracy and efficiency, especially in resource-limited environments. This work aims to evaluate K-means for video object segmentation, assess JIT's impact on its speed and resource usage, and optimize their integration considering feature representation and clustering parameters. Our experimental results show that the MATLAB JIT is able to achieve a significant speedup compared to the video segmentation in a normal mode with the average acceleration = 89.88%. © 2024 IEEE.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Analysis of Student Behaviour on Large Learning Management Systems 31

Analysis of Student Behaviour on Large Learning Management S...

引用

31st International Conference on Software, Telecommunications and computer Networks, SoftCOM 2023

作者： Mehnen, Lars Mandl, Thomas Pohn, Birgit Blaickner, Matthias Dregely, Isabel University of Applied Sciences Technikum Wien Faculty Computer Science and Applied Mathematics Department of Computer Science Austria

ISBN: (纸本)9798350301076

This paper presents a comprehensive analysis of student behaviour on Moodle, a widely used Learning Management System (LMS), in a large university setting with over 2000 students. The study investigates the distribution of student access to the LMS relative to the deadlines of quizzes (self-checked). Further, it explores the correlation between student engagement with course materials and their academic performance, finding that students with higher grades tend to access course materials earlier and more frequently before quiz deadlines. The paper also examines the distribution of two different student engagement with quizzes across different weekdays, highlighting distinct patterns between weekdays and weekends, and a unique trend on Saturdays due to lecture schedules for two study types-full-Time and part-Time. These findings provide valuable insights into student learning behaviours on large LMS, with potential implications for enhancing teaching strategies and improving student outcomes. The paper contributes to the growing body of research on learning analytics and offers a foundation for future studies in this area. © 2023 University of Split, FESB.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Transformer-Based Automatic Speech Recognition for Qur’an Reciters

引用

computers, Materials & Continua 2023年第2期74卷 3471-3487页

作者： Mohammed Hadwan Hamzah A.Alsayadi Salah AL-Hagree Department of Information Technology College of ComputerQassim UniversityBuraydah51452Saudi Arabia Department of Computer Science College of Applied SciencesTaiz UniversityTaiz6803Yemen Computer Science Department Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Computer Science Department Faculty of SciencesIbb UniversityYemen Department of Computer Sciences&Information Ibb UniversityYemen

The attention-based encoder-decoder technique,known as the trans-former,is used to enhance the performance of end-to-end automatic speech recognition(ASR).This research focuses on applying ASR end-toend transformer-based models for the Arabic language,as the researchers’community pays little attention to *** Muslims Holy Qur’an book is written using Arabic diacritized *** this paper,an end-to-end transformer model to building a robust Qur’an *** is *** acoustic model was built using the transformer-based model as deep learning by the PyTorch framework.A multi-head attention mechanism is utilized to represent the encoder and decoder in the acoustic *** filter bank is used for feature *** build a language model(LM),the Recurrent Neural Network(RNN)and Long short-term memory(LSTM)were used to train an n-gram word-based *** a part of this research,a new dataset of Qur’an verses and their associated transcripts were collected and processed for training and evaluating the proposed model,consisting of 10 h *** recitations performed by 60 *** experimental results showed that the proposed end-to-end transformer-based model achieved a significant low character error rate(CER)of 1.98%and a word error rate(WER)of 6.16%.We have achieved state-of-the-art end-to-end transformer-based recognition for Qur’an reciters.

关键词： Attention-based encoder-decoder recurrent neural network long short-term memory qur’an reciters recognition diacritized arabic text

来源：评论

学校读者我要写书评

暂无评论

CSCW – past, present and future

引用

i-com 2024年第1期23卷 1-5页

作者： Richter, Alexander Koch, Michael Prilla, Michael Computer Science Department Universität der Bundeswehr München München Germany Wellington School of Business and Government Victoria University of Wellington Wellington New Zealand Interactive Systems Department for Human Centered Computing and Cognitive Science Faculty for Computer Science University of Duisburg-Essen Duisburg Germany

来源：评论

学校读者我要写书评

暂无评论

Enhancing Internet of Smart City Security: Utilizing Logistic Boosted Algorithms for Anomaly Detection and Cyberattack Prevention

引用

SN computer science 2024年第5期5卷 548页

作者： Al-Atawi, Abdullah A. Department of Computer Science Applied College University of Tabuk Tabuk 47512 Saudi Arabia

With the increasing deployment of Internet of Things (IoT) devices in Smart Cities, ensuring the security and integrity of these systems is of paramount importance. This study focuses on the detection of anomalies and prevention of security attacks in Smart City environments, specifically in the context of traffic management. We compare the performance of three machine learning algorithms, namely logistic boosted algorithms, random forest, and support vector machines, using a dataset collected from various Smart City devices. Through comprehensive evaluation metrics such as accuracy, precision, recall, and F1 score, we analyze the efficacy of each algorithm. Our results indicate that the logistic boosted algorithm outperforms the other approaches in accurately identifying data outliers and achieving high performance across all evaluation metrics. Notably, it excels in handling imbalanced datasets and leveraging ensemble methods to enhance overall performance. While the random forest algorithm demonstrates exceptional performance in all metrics, the support vector machines approach exhibits superior recall but comparatively lower accuracy, precision, and F1 score. Moreover, the logistic boosted method showcases fewer misclassifications in the confusion matrices, making it highly effective for anomaly detection. The area under the ROC curve is highest for the logistic boosted algorithm (0.98), further emphasizing its effectiveness in filtering out anomalies. The random forest algorithm achieves the highest area under the curve (0.982), while the support vector machines method shows the lowest (0.968). Based on our findings, we conclude that the logistic boosted algorithm is the most effective for monitoring Smart City systems, followed by the random forest approach. However, the support vector machines method can be a viable alternative if recall is the primary performance metric of concern. Future research can focus on comparing the efficacy of different machine lear

关键词： Cyber security Internet of Things (IoT) Logistic boosted algorithms Smart Cities Traffic anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Explain the Explainer: Interpreting Model-Agnostic Counterfactual Explanations of a Deep Reinforcement Learning Agent

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第4期5卷 1443-1457页

作者： Chen, Ziheng Silvestri, Fabrizio Tolomei, Gabriele Wang, Jia Zhu, He Ahn, Hongshik Stony Brook University Department of Applied Mathematics and Statistics Stony BrookNY11794 United States Sapienza University of Rome Department of Computer Engineering The Department of Computer Science Rome00185 Italy Xi'An Jiaotong-Liverpool University Department of Intelligent Science Suzhou215000 China Rutgers University-New Brunswick Department of Computer Science PiscatawayNJ08854 United States

Counterfactual examples (CFs) are one of the most popular methods for attaching post hoc explanations to machine learning models. However, existing CF generation methods either exploit the internals of specific models or depend on each sample's neighborhood;thus, they are hard to generalize for complex models and inefficient for large datasets. This article aims to overcome these limitations and introduces ReLAX, a model-agnostic algorithm to generate optimal counterfactual explanations. Specifically, we formulate the problem of crafting CFs as a sequential decision-making task. We then find the optimal CFs via deep reinforcement learning (DRL) with discrete-continuous hybrid action space. In addition, we develop a distillation algorithm to extract decision rules from the DRL agent's policy in the form of a decision tree to make the process of generating CFs itself interpretable. Extensive experiments conducted on six tabular datasets have shown that ReLAX outperforms existing CF generation baselines, as it produces sparser counterfactuals, is more scalable to complex target models to explain, and generalizes to both the classification and regression tasks. Finally, we show the ability of our method to provide actionable recommendations and distill interpretable policy explanations in two practical real-world use cases. © 2020 IEEE.

关键词： Reinforcement learning

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：