检索结果-内蒙古大学图书馆

Exploring Nonuniform Structure of NSRTDs for Characterizing MACA Rules in the Null-Boundary Condition

Complex Systems 2025年第1期34卷 91-127页

作者： Hazra, Suvadip Banerjee, Som Dalui, Mamata Chakraborty, Bidesh Department of Computer Science and Engineering Indian Institute of Information Technology Karnataka Dharwad58009 India Department of Computer Science and Engineering National Institute of Technology West Bengal Durgapur713209 India Department of Computer Science and Engineering Haldia Institute of Technology West Bengal Haldia721657 India

The cellular automaton (CA), a discrete model, is gaining popularity in simulations and scientific exploration across various domains, including cryptography, error-correcting codes, VLSI design and test pattern generation. This paper examines a two-state three-neighborhood nonuniform finite CA with a specified number of fixed points. We utilize a graph-based tool known as the next state rule minterm transition diagram (NSRTD) to analyze the spatiotemporal behavior of these cellular automata (CAs) across all lengths. We devise methods for synthesizing nonuniform single length cycle multi-attractor CAs (MACAs), a specialized class of irreversible CA with a predefined number of fixed points for any arbitrary length. Despite the method’s exponential worstcase time complexity, it offers the advantage of selecting rules for each CA cell from a set of candidate rules, ensuring the desired number of fixed points. © 2025, Complex Systems Publications, Inc. All rights reserved.

关键词： cellular automata fixed-point attractor length cycle multi-attractor cellular automata MACA next state rule minterm transition diagram NSRTD

来源：评论

学校读者我要写书评

暂无评论

Effects of feature selection and normalization on network intrusion detection

Data Science and Management

引用

Data science and Management 2025年第1期8卷 23-39页

作者： Umar, Mubarak Albarka Chen, Zhanfang Shuaib, Khaled Liu, Yan College of Information Technology United Arab Emirates University Al Ain15551 United Arab Emirates School of Computer Science and Technology Changchun University of Science and Technology Changchun130022 China Department of Computer Science Shantou University Guangdong Shantou515063 China

The rapid rise of cyberattacks and the gradual failure of traditional defense systems and approaches led to using artificial intelligence (AI) techniques (such as machine learning (ML) and deep learning (DL)) to build more efficient and reliable intrusion detection systems (IDSs). However, the advent of larger IDS datasets has negatively impacted the performance and computational complexity of AI-based IDSs. Many researchers used data preprocessing techniques such as feature selection and normalization to overcome such issues. While most of these researchers reported the success of these preprocessing techniques on a shallow level, very few studies have been performed on their effects on a wider scale. Furthermore, the performance of an IDS model is subject to not only the utilized preprocessing techniques but also the dataset and the ML/DL algorithm used, which most of the existing studies give little emphasis on. Thus, this study provides an in-depth analysis of feature selection and normalization effects on IDS models built using three IDS datasets: NSL-KDD, UNSW-NB15, and CSE–CIC–IDS2018, and various AI algorithms. A wrapper-based approach, which tends to give superior performance, and min-max normalization methods were used for feature selection and normalization, respectively. Numerous IDS models were implemented using the full and feature-selected copies of the datasets with and without normalization. The models were evaluated using popular evaluation metrics in IDS modeling, intra- and inter-model comparisons were performed between models and with state-of-the-art works. Random forest (RF) models performed better on NSL-KDD and UNSW-NB15 datasets with accuracies of 99.86% and 96.01%, respectively, whereas artificial neural network (ANN) achieved the best accuracy of 95.43% on the CSE–CIC–IDS2018 dataset. The RF models also achieved an excellent performance compared to recent works. The results show that normalization and feature selection positively affect I

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Life Expectancy Prediction in Developed and Developing Regions

引用

IEEE Access 2025年 13卷 69520-69531页

作者： Ahamad, Shaik Shakeel Kumar, K. Praveen Ganesh, Sankuratri Sri Alharbi, Fayez Alharby, Sultan Awad Dendukuri, Venkata S. P. Koneru, Suvarna Vani Majmaah University College of Computer and Information Sciences Department of Information Technology Al-Majmaah11952 Saudi Arabia Deemed to Be University Velagapudi Ramakrishna Siddhartha School of Engineering Siddhartha Academy of Higher Education Department of Computer Science and Engineering Andhra Pradesh Vijayawada520007 India Majmaah University College of Computer and Information Sciences Department of Computer Science Al-Majmaah11952 Saudi Arabia

The life expectancy of a population is a vital measure of its overall health and healthcare quality. This study use machine learning methods, notably XGBoost, to predict life expectancy in industrialized and emerging countries. XGBoost, or Extreme Gradient Boosting, is a robust machine-learning technique renowned for its precision and efficiency in handling structured data. The objective is to develop a precise prediction model and identify the primary factors influencing life expectancy. The experimental findings indicate that our XGBoost-based model effectively forecasts life expectancy in both industrialized and developing nations. Mean Absolute Error, Mean Squared Error, and R2 score are used for model selection. XGBoost is selected because to its mean squared error of 2.45, mean absolute error of 1.03, and R2 scores of 0.99 for the training set and 0.97 for the testing set. In this a feature significance analysis was conducted to identify the most relevant factors affecting life expectancy. Our results underscore the significance of variables such as HIV/AIDS, income composition, and adult mortality in influencing life expectancy. The model's findings may assist lawmakers and healthcare professionals in making decisions to enhance public health outcomes, allocate resources efficiently, and formulate focused solutions. © 2013 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

DualRec: A Collaborative Training Framework for Device and Cloud Recommendation Models

引用

IEEE Transactions on Mobile Computing 2025年第6期24卷 5202-5213页

作者： Zhang, Ye Deng, Yongheng Yue, Sheng Li, Qiushi Ren, Ju Beijing Information Science and Technology University School of Computer Science Beijing100101 China Tsinghua University Department of Computer Science and Technology BNRist Beijing100084 China Zhongguancun Laboratory Beijing100084 China

Recommendation systems (RS) play a vital role in various domains. However, under recent data regulations like General Data Protection Regulation (GDPR), traditional RS that rely on collecting user's interaction data centrally face significant challenges. Federated learning (FL) enables collaborative model training among users while keeping their private data locally. Yet, the constrained resources of devices often limit the size of the learned model, resulting in suboptimal recommendation performance. To overcome the dilemma of data accessibility and model size, we propose DualRec, a novel collaborative training framework for device and cloud recommendation models. In DualRec, users train lightweight models on devices to harness their local private data, while a larger model is simultaneously trained on the cloud server to exploit its substantial resources. Devices and the cloud server collaboratively train their models, compensating for individual limitations of model size and data availability, enabling mutual empowerment and benefits. Specifically, we introduce an efficient aggregation mechanism for recommendation models to boost the collaborative training performance of device models. With the learned device models, we propose to generate pseudo user interaction data to train the server model. To enhance the training performance of the server model, we design an automated denoising mechanism to mitigate the negative impact of noisy samples in the generated pseudo dataset. Finally, the learned knowledge of the server model is distilled to device models for enhanced on-device recommendation performance. Extensive experiments demonstrate the superior performance of DualRec compared to state-of-the-art baselines. © 2002-2012 IEEE.

关键词： Collaborative learning

来源：评论

学校读者我要写书评

暂无评论

uFOIL: An Unsupervised Fusion of Image Processing and Language Understanding

引用

IEEE Access 2025年 13卷 31683-31700页

作者： Rahman, Md. Abdur Hasan, Md. Tanzimul Farooq Howlader, Umar Kader, Md. Abdul Islam, Md. Motaharul Hung Pham, Phuoc Mehedi Hassan, Mohammad United International University Department of Computer Science and Engineering Dhaka1212 Bangladesh Providence College Department of Mathematics and Computer Science ProvidenceRI02918 United States King Saud University College of Computer and Information Sciences Department of Information Systems Riyadh11543 Saudi Arabia

In academic institutions, processing and evaluating documents such as exam scripts remains a labor-intensive process susceptible to human error. Traditional digitization systems face significant challenges in handling the complexities of mixed handwritten and printed text and varying document structures. These challenges are exacerbated by the absence of annotated datasets due to privacy concerns, particularly in contexts involving sensitive exam evaluations. To address these issues, this study introduces uFOIL, an unsupervised ensemble-based framework that integrates advanced image and language processing techniques to automate the extraction and validation of key information. The framework employs a majority voting mechanism that combines four state-of-the-art optical character recognition systems. Furthermore, a transformer architecture is incorporated to enhance contextual understanding and the structured formatting of extracted text that follows a post-processing confidence scoring mechanism. The proposed framework achieves high performance, with accuracies of 95.77% and 96.48% for student names and IDs, respectively;and 95.07% for total mark validation based on a dataset of exam script samples. Additionally, experiments on the benchmark ICDAR2013 dataset suggest the framework’s strong applicability achieving precision, recall, and F1-scores of 95.89%, 97.86%, and 96.87%, respectively. © 2025 The Authors.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Neuraltalk+: neural image captioning with visual assistance capabilities

引用

Multimedia Tools and Applications 2025年第10期84卷 6843-6871页

作者： Sharma, Himanshu Padha, Devanand Department of Computer Science and Information Technology Central University of Jammu Kashmir Jammu181124 India

Image captioning is a technique that generates concise and meaningful descriptions of the visual contents present in an image. Image captioning frameworks generally employ an encoder-decoder-based pipeline to generate image descriptions. Multimodal meaning space, visual and semantic fusion, and influential recurrent decoding are some of the highlights of these frameworks. However, the lack of cutting-edge implementation schemes, such as ensemble feature extraction, context-aware fusion, and real-time captioning, limit their integration in the vision assistance domain. In this research work, we introduce Neuraltalk+, which comprises various structural and functional enhancements, and feature-based extensions, making it lightweight, robust, effective, and automated. Neuraltalk+ uses ensemble feature extraction to extract visual and spatial image features for efficient image comprehension. We then map these feature vectors with multimodal semantic knowledge using dual context-aware feature fusion followed by self-attention-assisted decoding. Lastly, we introduce two new features: real-time captioning and visual similarity comparison, which allow vision assistance and sight comprehension capabilities. Experimental analysis on the Flickr 8K and Flickr 30K datasets demonstrates that our model trains faster and generates improved quantitative (BLEU(72.08), METEOR(33.65), and CIDEr(143.5)) and qualitative results. Neuraltalk+ also demonstrates high performance in real-time captioning for both familiar and unfamiliar contexts. We also offer potential suggestions for extending our work in the future. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

RoPe-Door: Toward Robust and Persistent Backdoor Data Poisoning Attacks in Federated Learning

引用

IEEE Network 2025年第3期39卷 302-310页

作者： Liu, Ye Chang, Shan Li, Denghui Shi, Shaohuai Li, Bo Jiangxi Normal University School of Computer and Information Engineering Nanchang330022 China Donghua University School of Computer Science and Technology Shanghai201620 China Harbin Institute of Technology School of Computer Science and Technology Shenzhen518057 China The Hong Kong University of Science and Technology Department of Computer Science and Engineering Sai Kung Hong Kong

Federated Learning (FL) enables privacy-preserving collaborative training and builds a federation through exchanges of immutable data such as model parameters or gradient updates. FL remains vulnerable to a variety of attacks during critical processes like local model training and parameter transmission, in which the backdoor attack is particularly evident. In this paper, we propose a novel backdoor data poisoning attack method, RoPe-Door, using a trigger generation algorithm to improve the robustness and persistence of attacks even under Byzantine aggregation methods. We conduct extensive experiments on four image classification tasks to evaluate the effectiveness of RoPe-Door. The experimental results demonstrate that, compared to backdoor attacks using random triggers, RoPe-Door exhibits significant advantages in robustness, persistence, and attack effectiveness under both IID and Non-IID data settings. © 1986-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent integration of AI and IoT for advancing ecological health, medical services, and community prosperity

引用

Alexandria Engineering Journal 2025年 127卷 522-540页

作者： Alzahrani, Abdulrahman Kostkova, Patty Alshammari, Hamoud Habibullah, Safa Alzahrani, Ahmed Department of Information System and Technology College of Computer Science and Engineering University of Jeddah Saudi Arabia University College London United Kingdom Department of Information systems College of Computer and Information Sciences Jouf University Saudi Arabia

Artificial Intelligence (AI) and the Internet of Things (IoT) are developing so fast that they can bring revolutionary changes in ecological sustainability, public health, and community welfare. In contrast, the present waste management system has a set of inefficiencies due to some challenges, such as poor waste stream segregation, limited real-time data analysis, and negligible integration of recent technology. These challenges lead to environmental degradation, public health hazards, and inefficient usage of resources. This research targets these challenges by designing an IWM framework like AI-IoT for smart waste management. The system employs AI models powered by IoT sensors for efficient waste collection, classification, and optimization of recycling schedules. CNN (convolutional neural networks) with transfer learning enabled by Res-Net provides high-accuracy image recognition, which can be used for waste classification. Bidirectional Encoder Representations from Transformers (BERT) allow multilingual users to interact and communicate properly in any linguistic environment. Data collected from IoT-enabled smart bins is transmitted in real-time to a central control system for dynamic decision-making and follow-up analysis. A pilot exercise to verify the system's effectiveness was implemented in metropolitan settings to show the transformation: landfill dependency was decreased by 30 %, recycling efficiency was greatly increased to 90 %, and thus the cost of waste management was optimized. At the same time, environmental health inequity, causing pathogen-related threats, was reduced by 35 %. The model has an accuracy of 96.8 %. The features of the proposed framework not only provide solutions to the existing inefficiencies but also enhance scalability, cost-effectiveness, and global environmental standardization. This dawns the futuristic growth of AI- and IoT-enabled waste management systems, which hinge on sustainability, public health, and resource efficienc

关键词： Artificial Intelligence Internet of Things BERT Medical Services Res-Net Waste Management

来源：评论

学校读者我要写书评

暂无评论

Multimodal emotion recognition model via hybrid model with improved feature level fusion on facial and EEG feature set

引用

Multimedia Tools and Applications 2025年第1期84卷 1-36页

作者： Singh, Pratima Tripathi, Mukesh Kumar Patil, Mithun B. Shivendra Neelakantappa, Madugundu Department of Computer Science and Engineering Galgotias University Gautam Buddh Nagar Uttar Pradesh India Department of Computer Science and Engineering Vardhaman College of Engineering Telangana Hyderabad India Department of Computer Science and Engineering N K Orchid College of Engineering & Technology Maharastra Solapur India Department of Computer Application D. K. College Dumraon Bihar Buxar India Department of Information Technology Vasavi College of Engineering Telangana Hyderabad India

In recent years, academics have placed a high value on multi-modal emotion identification, as well as extensive research has been conducted in the areas of video, text, voice, and physical signal emotion detection. This paper proposes a novel multimodal emotion recognition model that employs a hybrid model with AMIG-based feature fusion on facial and EEG feature sets. The EEG signal and facial image are subjected to preprocessing to remove unwanted background noises with the Butterworth filter and Viola Jones Algorithm, respectively. While considering the pre-processed EEG signal, features such as EWFS-transform, wavelet features, and CSP-based features are extracted. In the proposed EWFS-transform, the window function is modified by using the frequency function and updated STFT. Conversely, the features including SE-AMM-EST-based features;LGXP and GLCM are extracted while considering the preprocessed face image. In the proposed SE-AMM-EST-based features, the mean of shape is updated and covariance in PCA for extracting texture-based features. In order to extract redundant free essential features, AMIG-based feature fusion is proposed. Further, the fused features are fed into a proposed hybrid model that includes LSTM and AML-CNN models. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Detection of Driver Drowsiness Using Adaptive Eye Characteristic Ratio for Enhanced Road Safety

引用

IEEE Access 2025年 13卷 84313-84328页

作者： Lamba, Puneet Singh Jain, Rimjhim Khan, Shakir Alanazi, Sultan M. Jain, Achin Zamani, Abu Taha Panwar, Arvind Abdallah, Alsadig Mohammed Adam University of Delhi S.G.T.B Khalsa College Department of Computer Science Delhi110007 India University of North Carolina Charlotte United States Imam Mohammad Ibn Saud Islamic University College of Computer and Information Sciences Information Technology Department Riyadh Saudi Arabia Northern Border University Department of Department of Computer Science Faculty of Science Arar Saudi Arabia Bharati Vidyapeeth’s College of Engineering Department of Information Technology New Delhi India Galgotias University School of Computer Science and Engineering Uttar Pradesh Greater Noida India

Every year, countless people lose their lives in serious car accidents, and drowsy driving is a major cause. However, because the earliest indications of exhaustion can be identified before a dangerous scenario develops, the detection and signaling of driver drowsiness are ongoing research topics. This study presents a real-time detection system designed to detect driver’s sleep and deliver timely warnings. The mechanism employs an eye monitoring system that uses eye feature points to detect whether a driver’s eye is tired and delivers an alert if the driver is drowsy. The proposed work recognizes the driver’s face by collecting facial landmarks and gives warning to the driver to avoid crashes by performing adaptive thresholding and drowsiness diagnoses based on Eye Characteristic Ratio. The empirical results show that using random forest classifier, decision tree classifier, KNN classifier, and multinomial classifier, the proposed model achieved 90.48%, 89.44%, 88.63%, and 84.32% accuracy, respectively. © 2013 IEEE.

关键词： Highway accidents

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：