检索结果-内蒙古大学图书馆

Reinforcement Learning with Deep Features: A Dynamic Approach for Intrusion Detection in IOT Networks

IEEE Access 2025年 13卷 92319-92337页

作者： Khayat, Mohamad Barka, Ezedin Serhani, Mohamed Adel Sallabi, Farag Shuaib, Khaled Khater, Heba M. United Arab Emirates University College of Information Technology Al Ain United Arab Emirates Zagazig University Faculty of Computers and Informatics Zagazig 44519 Egypt University of Sharjah College of Computing and Informatics Sharjah United Arab Emirates

Intrusion detection in Internet of Things (IoT) networks is essential to identify and mitigate security breaches and unauthorized access to connected devices. As IoT devices continue to advance, securing interconnected systems against malicious attacks is essential to ensure data privacy, system integrity, and user safety. However, traditional intrusion detection systems (IDSs) often struggle to adapt to novel and evolving threats. Developing a system that can autonomously learn and enhance intrusion detection capabilities to effectively identify and mitigate emerging threats is challenging. To address this issue, we propose a reinforcement learning (RL)-based approach for enhancing cybersecurity in IoT networks. First, various preprocessing techniques such as handling missing values, outliers, and min-max scaling normalization were applied. Then, domain-specific features related to network traffic patterns, including packet size distribution, packet count, and packet rate, were extracted. Statistical measures, including mean, variance, and entropy, were calculated from these features to determine temporal and spatial variations in the network data. Moreover, deep learning models, including long short-term memory networks and convolutional neural networks (CNNs), were used to automatically extract high-level features from raw data such as network logs or sensor readings. The extracted feature sets were concatenated within a feature fusion layer that enabled efficient dimensionality reduction via principal component analysis. A hybrid optimization approach was also introduced for feature selection using green anaconda optimization and the chaotic learning osprey optimization algorithm. Furthermore, an RL-based IDS (RL-IDS) that incorporates RNNs and autoencoders with a deep Q-network was proposed to enhance threat detection. Experimental outcomes emphasize the superiority of the method, obtaining 99.45% accuracy with 70% training data and 99.80% with 80%. Precision a

关键词： Deep learning feature selection intrusion detection IoT optimization

来源：评论

学校读者我要写书评

暂无评论

Knowledge Augmented Significant Language Model-Based Chatbot for Explainable Diabetes Mellitus Prediction

Knowledge Augmented Significant Language Model-Based Chatbot...

引用

International Conference on Ubiquitous Information Management and Communication (IMCOM)

作者： Mazen Elfayoumi Mohamed AbouElazm Omar Mohamed Tamer Abuhmed Shaker El-Sappagh Faculty of Computer Science and Engineering Galala University Egypt Faculty of Computer Science Goldsmith UOL United Kingdom College of Computing and Informatics Sungkyunkwan University South Korea

ISBN: (数字)9798331507817

ISBN: (纸本)9798331507824

This study proposes an innovative diabetes prediction chatbot that utilizes large language models (LLMs) to determine the likelihood of diabetes based on specific patient inputs. Unlike conventional machine learning models and in addition to providing precise, individualized, robust prediction of diabetes augmented by the percentage of its confidence, this chatbot provides detailed text-based explanations for its individual predictions and enhances user's understanding by retrieving and presenting similar cases using case-based reasoning techniques. Utilizing key health indicators such as hypertension status, heart disease presence, smoking history, BMI, HbA1c level, and blood glucose levels, the chatbot not only predicts the presence of diabetes but also educates users about the underlying reasons for each prediction. The system's explanation module promotes transparency and trust in the predictive process. The proposed architecture integrates the retrieval augmented generation (RAG) technique with prompt engineering across multiple LLMs, including Llama 3.1, GPT- 3.5, and Gemma2. This approach augments the chatbot's responses with contextually relevant data from similar past cases, thereby enhancing both relevance and accuracy. Furthermore, RAG minimizes LLM hallucinations while enhancing them with up-to-date, precise, personalized medical information. The objective of this chatbot is to offer healthcare professionals and patients a dependable, educational instrument for early detection of diabetes supported by transparent AI principles. This will have a positive effect on preventative healthcare measures.

关键词： Technological innovation Accuracy Large language models Computational modeling Retrieval augmented generation Medical services Predictive models Chatbots Diabetes Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Towards Robust Federated Learning: Investigating Poisoning Attacks Under Clients Data Heterogeneity

Towards Robust Federated Learning: Investigating Poisoning A...

引用

International Conference on Ubiquitous Information Management and Communication (IMCOM)

作者： Abdenour Soubih Seyyid Ahmed Lahmer Mohammed Abuhamad Tamer Abuhmed College of Computing and Informatics Sungkyunkwan University Suwon Korea Department of Information Engineering University of Padova Padua Italy Department of Computer Science Loyola University Chicago Chicago USA

ISBN: (数字)9798331507817

ISBN: (纸本)9798331507824

Federated Learning (FL) offers a privacy-preserving solution by enabling multiple clients to train a shared model collaboratively without centralizing data. However, the decentralized nature of FL presents challenges, particularly regarding security and performance under adversarial conditions. This paper investigates the effects of poisoning attacks under data heterogeneity. Our experiments evaluate the impact of varying malicious client fractions and poison concentration levels on the accuracy of the model. We explore the effects of poisoning attacks on FedAvg and FedNova models using medical imaging tasks. Our findings reveal that increasing data heterogeneity exacerbates the effects of poisoning, with FedNova demonstrating greater resilience compared to FedAvg. We found that the number of malicious clients plays a more significant role in degrading performance than the ratio of poisoning samples shared by each malicious client, suggesting that even modest levels of poisoning can be tolerated by most algorithms. The study highlights the importance of developing robust defense mechanisms to maintain model performance under adversarial conditions.

关键词： Training Toxicology Federated learning Computational modeling Data models Information management Security Reliability Faces Resilience

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient and Intelligent Lighting Solutions: A Prototype for Smart Cities

Energy-Efficient and Intelligent Lighting Solutions: A Proto...

引用

Mobile computing and Sustainable informatics (ICMCSI), International Conference on

作者： Mohamed Imran Mohamed Ariff Batrisyia Qistina Razally Azilawati Azizan Samsiah Ahmad Zalikha Zulkifli Noreen Izza Arshad Computing Sciences Studies College of Computing Informatics and Mathematics Universiti Teknologi MARA Perak Branch Malaysia EMI Solutions Sdn Bhd Jalan Universiti Petaling Jaya Selangor Malaysia Department of Computer and Information Sciences PETRONAS Universiti Teknologi Malaysia

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

This paper presents a Smart Street Lighting System (SSLS) aimed at improving energy efficiency and providing enhanced convenience for urban areas, with a particular focus on parking facilities. By employing light, rain, and motion sensors, the SSLS ensures precise control over lighting levels, optimizing energy use while enhancing safety and visibility. The system's light sensors adjust illumination according to ambient conditions, minimizing energy waste during daylight hours. During rain, brightness levels are automatically elevated for better visibility, while motion sensors activate full brightness when movement is detected to guarantee safety. A dedicated mobile application offers users real-time control and monitoring of energy usage and lighting settings. Among its notable contributions are the implementation of an IoT-based adaptive lighting framework and a scalable design that has demonstrated up to 35% energy savings in varied urban environments. This innovative solution addresses key challenges in urban lighting, ensuring sustainability and reducing operational expenses.

关键词： Rain Costs Smart cities Brightness Lighting Motion detection Energy efficiency Real-time systems Safety Monitoring

来源：评论

学校读者我要写书评

暂无评论

The Conductivity and the Depolarization Factor of a Spheroid based on its Polarization Tensor and Volume

The Conductivity and the Depolarization Factor of a Spheroid...

引用

International Colloquium on Signal Processing & Its Applications, CSPA

作者： Nurhazirah Mohamad Yunos Taufiq Khairi Ahmad Khairuddin Siti Nur Auni Rusli Department of Mathematical Sciences Faculty of Science Universiti Teknologi Malaysia Johor Malaysia Mathematical Sciences Studies College of Computing Informatics and Mathematics Universiti Teknologi MARA Johor Malaysia

ISBN: (数字)9798331522193

ISBN: (纸本)9798331522209

The polarization tensor can be used to describe an object presented in an electric field. This is useful in getting accurate image about the object with electrical imaging device or increasing the likelihood of detecting the object with metal detector. Given the first order polarization tensor and the volume of a spheroid, some properties of the spheroid, such as its conductivity and depolarization factor, have not yet been investigated. Thus, this study aims to propose a method to determine the conductivity and depolarization factor of the spheroid, based on its first order polarization tensor and volume. In order to achieve this, the system of nonlinear equations is first derived based on the given first order polarization tensor, before being solved by the Newton's method. Numerical examples are then provided to demonstrate and justify the proposed algorithm. The findings show that the error for the computed conductivity and depolarization factor is small, suggesting that the proposed algorithm is reliable. In addition, the relationship between the spheroid's volume and conductivity is also discussed. The results illustrate an inverse relationship between the conductivity and depolarization factor when considering a positive definite first order polarization tensor. In contrast, for a negative definite first order polarization tensor, the findings reveal a positive correlation between spheroid's conductivity and its volume. The results obtained can then be used to characterize the spheroid based on its first order polarization tensor and also its volume. This provides additional information about the spheroid, which may contribute to the improvement of future techniques in electrical imaging and metal detection.

关键词： Tensors Nonlinear equations Correlation Integral equations Metals Imaging Conductivity Reliability Electric fields Newton method

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Predictive Analytics for CRM to Enhance Retention Personalization and Decision-Making

引用

International Journal of Advanced Computer Science and Applications 2025年第4期16卷 552-563页

作者： Gaidhani, Yashika Ramesh, Janjhyam Venkata Naga Singh, Sanjit Dagar, Reetika Rao, T. Subha Mastan Godla, Sanjiv Rao Baker El-Ebiary, Yousef A. Department of Electronics Engineering Yeshwantrao Chavan College of Engineering Maharashtra Nagpur India Department of CSE Graphic Era Hill University Dehradun248002 India Department of CSE Graphic Era Deemed to Be University Uttarakhand Dehradun248002 India Department of MBA-Sanjivani College of Engineering Savitribai Phule Pune University Pune India GD Goenka University Haryana Gurugram India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh Guntur India Department of Computer Science and Engineering Aditya University Andhra Pradesh Surampalem India Faculty of Informatics and Computing UniSZA University Malaysia

The advent of Artificial Intelligence (AI) has dramatically altered Customer Relationship Management (CRM) by allowing organizations to anticipate customer behavior, customize interactions and automate service delivery. This research introduces an extensive AI-based predictive analytics framework aimed at improving customer engagement, retention and satisfaction using advanced Machine Learning (ML) and Natural Language Processing (NLP) methodologies. By using XGBoost for churn prediction and BERT-based models for sentiment analysis, the system efficiently handles both structured and unstructured customer data. The methodology involves sophisticated feature engineering, customer segmentation via K-Means clustering, and Customer Lifetime Value (CLV) prediction to aid data-driven business strategies. An NLP-driven chatbot offers real-time, personalized support, response time and improving user experience. Evaluation metrics such as accuracy, precision, recall and F1-score demonstrate the better performance of the proposed system compared to conventional CRM approaches. This work also addresses important issues such as data privacy compliance, algorithmic bias and explainability of AI decision-making. Ethical deployment and transparency of AI are emphasized for building confidence in automated CRM systems. Future evolution will tackle the use of reinforcement learning to facilitate learning-based interaction schemes and federated learning for trusted, decentralized management of data. This architecture does not only provide better CRM functionality but also builds a platform towards intelligent, responsible and scalable solutions for customer relations across industries. © (2025), (Science and Information Organization). All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

New Opportunities, Risks, and Harm of Generative AI for Fostering Safe Online Communities 25

New Opportunities, Risks, and Harm of Generative AI for Fost...

引用

2025 ACM International Conference on Supporting Group Work, GROUP Companion 2025

作者： Freeman, Guo Zytko, Douglas Razi, Afsaneh Lampe, Cliff Candello, Heloisa Jakobi, Timo Aal, Konstantin Kosta School of Computing Clemson University ClemsonSC United States University of Michigan-Flint FlintMI United States Department of Information Science College of Computing &amp Informatics Drexel University PhiladelphiaPA United States School of Information University of Michigan Ann ArborMI United States IBM Research Sao Paulo Brazil Nuremberg University of Applied Sciences Georg Simon Ohm Bavaria Nuremberg Germany Information Systems and New Media University of Siegen NRW Siegen Germany

ISBN: (纸本)9798400711879

Recently, there is a growing trend of using generative AI systems and tools for fostering and protecting online collaborative communities. Yet, existing AI tools may introduce new risks and even harm to diverse communities’ online safety. How to better maximize the novel opportunities of AI and mitigate its emerging risks and harm for our future online safety is a critically needed discussion for the HCI community. Featuring experts from both industry and academia, the goal for this panel is to promote interdisciplinary, community-wide discussions and collective reflections on important questions and considerations at the unique intersection of AI and online communities, including but not limited to: how the design of AI systems may discourage existing online harm but also invite new online harm in various online spaces;how different populations, cultures, and communities may perceive and experience AI’s new roles for their online safety;and what new strategies, principles, and directions can be envisioned and identified to better design future AI technologies to protect rather than harm various online communities. © 2025 Copyright held by the owner/author(s).

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Calculating SIRD model parameters and Re-susceptibility in Malaysia, Pakistan, India and United Arab Emirates

引用

Communications in Nonlinear Science and Numerical Simulation 2025年 148卷

作者： Basit, Abdul Zain, Jasni Mohamad Mojahid, Hafiza Zoya Jumaat, Abdul Kadir Hamdan, Nur'Izzati Bagal, Dilip Kumar College of Computing Informatics and Mathematics Universiti Teknologi Mara Selangor Shah Alam40450 Malaysia Kompleks Al-Khawarizmi Universiti Teknologi Mara Selangor Shah Alam40450 Malaysia Department of Mechanical Engineering Government College of Engineering Kalahandi Odisha Bhawanipatna India

During the dynamic spread of COVID-19 and the looming threat of future pandemics the essential need of precise epidemiological models are indispensable. Key to these algorithms are the estimation of core parameters a pivotal metric indicating pandemic expansion. Yet, existing algorithms often overlook crucial facets such as viral mutations risks. Addressing this gap, we propose an innovative algorithm merging the Susceptible-Infected-Recovered-Dead (SIRD) model with Re-susceptible compartment incorporated by least square method with linear regression approach that ensures the accurate parameter estimation facilitating real-time forecasting. This idea analyzed different countries full lockdown scenario. These incorporation of statistical and mathematical algorithms enhances parameters estimation, forecasting and provides insights into re-susceptibility percentage. The experiments revealed convincing results with the incorporation of statistical and mathematical algorithms enhancing parameter estimation with best R-square values of 0.9902 for country Pakistan exemplifying its vital contribution to pandemic response strategies. Our work offers a vital tool for governments, institutions and individuals grappling with pandemic responded full lockdown policy. © 2025 Elsevier B.V.

关键词： Integration

来源：评论

学校读者我要写书评

暂无评论

MUFF: Stable and Sensitive Post-training Mutation Testing for Deep Learning

arXiv

引用

arXiv 2025年

作者： Kim, Jinhan Humbatova, Nargiz Jahangirova, Gunel Yoo, Shin Tonella, Paolo Software Institute Università della Svizzera italiana Lugano Switzerland Department of Informatics King's College London London United Kingdom School of Computing KAIST Daejeon Korea Republic of

Rapid adoptions of Deep Learning (DL) in a broad range of fields led to the development of specialised testing techniques for DL systems, including DL mutation testing. However, existing post-training DL mutation techniques often generate unstable mutants across multiple training repetitions and multiple applications of the same mutation operator. Additionally, while extremely efficient, they generate mutants without taking into account the mutants' sensitivity and killability, resulting in a large number of ineffective mutants compared to pre-training mutants. In this paper, we present a new efficient post-training DL mutation technique, named MUFF, designed to ensure the stability of the mutants and capable of generating killable and sensitive mutants. MUFF implements an automated stability check and introduces two mutation operators, named weight and neuron inhibitors. Our extensive empirical experiments show that MUFF generates mutants with 60%pt and 25%pt higher sensitivity compared to DEEPMUTATION++ and DEEPCRIME, respectively, while also producing mutants that are more stable than those of DEEPMUTATION++ and different from the mutants of DEEPCRIME. Moreover, MUFF preserves the benefits of the post-training mutation technique, being 61 times faster than DEEPCRIME in generating mutants. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing User Interaction in Digital Financial Systems Using AI-Driven Front-End Technologies: A Personalised Response Approach

Enhancing User Interaction in Digital Financial Systems Usin...

引用

Data Science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： R. Thalapathi Rajasekaran Muthu Selvam Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai Tamil Nadu India College of Computing and Informatics University of North Carolina at Charlotte Charlotte North Carolina USA

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

This study highlights the rapid advancements in artificial intelligence (AI) and machine learning (ML), which have transformed the financial sector by enhancing personalised user interactions and customer engagement. An innovative AI-driven framework was proposed to deliver real-time, context-aware, and highly personalised responses for Digital Banking users. The system architecture employs advanced ML models, natural language processing (NLP) techniques, and modern front-end technologies such as React and GraphQL to address the challenges related to data silos, computational demand, and data privacy. ML models such as user segmentation, recommendation, and NLP models work together to analyse user behaviour, predict needs, and generate human-like responses. Utilising React, GraphQL subscriptions, and Edge AI, the front-end layer ensures a seamless and responsive user experience. The experimental results showed a 120% increase in click-through rates, a 180% increase in follow-up actions, and a 70% reduction in average response time, demonstrating significant improvements in user engagement. User satisfaction, measured by the Net Promoter Score, was significantly higher for the personalised system (8.5) than for the traditional system (5.2). The proposed methodology lays the foundation for an agile trust-based financial environment. Future enhancements will focus on explainable AI, multimodal interactions, and blockchain integration to boost transparency, engagement, and data privacy.

关键词： Data privacy Analytical models Computational modeling Systems architecture Banking Predictive models Natural language processing Real-time systems User experience Time factors

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：