检索结果-内蒙古大学图书馆

Enhancing network security: an intrusion detection system using residual network-based convolutional neural network

CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS 2025年第4期28卷 1-24页

作者： Farhan, Saima Mubashir, Jovaria Haq, Yasin Ul Mahmood, Tariq Rehman, Amjad Lahore Coll Women Univ Dept Comp Sci Lahore 54000 Pakistan Univ Engn & Technol Lahore Dept Comp Sci & Engn Narowal Campus Narowal 51600 Pakistan CCIS Prince Sultan Univ Artificial Intelligence & Data Analyt AIDA Lab Riyadh 11586 Saudi Arabia Univ Educ Fac Informat Sci Vehari Campus Vehari 61161 Pakistan

With the rapid growth of cyber threats, traditional Intrusion Detection Systems (IDS) face limitations in accurately detecting evolving and diverse attack types. These systems often struggle with scalability, manual feature extraction, and generalization to new attack patterns. To address these issues, this study proposes a Residual Network-based Convolutional Neural Network (ResNet-CNN) model to enhance the detection and classification of network intrusions. The proposed model combines advanced deep learning techniques for automatic feature extraction and robust classification performance. Using the NSL-KDD dataset, five experimental setups were conducted, including binary classification, binary classification with feature division, multiclass classification, multiclass classification with feature division, and binary classification of attack types. The proposed model achieved remarkable accuracies of 98.94% and 98.92% for binary and multiclass classification tasks, respectively. Additionally, the model demonstrated exceptional accuracy in detecting individual attack types, exceeding 99%. This research highlights the significance of leveraging basic features for optimal classification and introduces a promising methodology for safeguarding against sophisticated cyber threats.

关键词： Classification Deep learning Intrusion detection system Network security Residual network based convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Microscopy: Cutting-Edge Approach for Breast Tissue Prognosis Using Microscopic Images

引用

MICROSCOPY RESEARCH AND TECHNIQUE 2025年第5期88卷 1335-1359页

作者： Mahmood, Tariq Saba, Tanzila Al-Otaibi, Shaha Ayesha, Noor Almasoud, Ahmed S. CCIS Prince Sultan Univ Artificial Intelligence & Data Analyt AIDA Lab Riyadh Saudi Arabia Univ Educ Fac Informat Sci Vehari Campus Vehari Pakistan Princess Nourah bint Abdulrahman Univ Coll Comp & Informat Sci Dept Informat Syst Riyadh Saudi Arabia Prince Sultan Univ Ctr Excellence CyberSecur Riyadh Saudi Arabia

Microscopic imaging aids disease diagnosis by describing quantitative cell morphology and tissue size. However, the high spatial resolution of these images poses significant challenges for manual quantitative evaluation. This project proposes using computer-aided analysis methods to address these challenges, enabling rapid and precise clinical diagnosis, course analysis, and prognostic prediction. This research introduces advanced deep learning frameworks such as squeeze-and-excitation and dilated dense convolution blocks to tackle the complexities of quantifying small and intricate breast cancer tissues and meeting the real-time requirements of pathological image analysis. Our proposed framework integrates a dense convolutional network (DenseNet) with an attention mechanism, enhancing the capability for rapid and accurate clinical assessments. These multi-classification models facilitate the precise prediction and segmentation of breast lesions in microscopic images by leveraging lightweight multi-scale feature extraction, dynamic region attention, sub-region classification, and regional regularization loss functions. This research will employ transfer learning paradigms and data enhancement methods to enhance the models' learning further and prevent overfitting. We propose the fine-tuning employing pre-trained architectures such as VGGNet-19, ResNet152V2, EfficientNetV2-B1, and DenseNet-121, modifying the final pooling layer in each model's last block with an SPP layer and associated BN layer. The study uses labeled and unlabeled data for tissue microscopic image analysis, enhancing models' robust features and classification abilities. This method reduces the costs and time associated with traditional methods, alleviating the burden of data labeling in computational pathology. The goal is to provide a sophisticated, efficient quantitative pathological image analysis solution, improving clinical outcomes and advancing the computational field. The model, trained, va

关键词： dense convolution diluted convolution health risk microscopic image tumor grading

来源：评论

学校读者我要写书评

暂无评论

C.A.L.I.X: Leveraging Hybrid RAG for Responsible AI in the Medical Field

C.A.L.I.X: Leveraging Hybrid RAG for Responsible AI in the M...

引用

Women in data Science at Prince Sultan University (WiDS PSU), International Conference of

作者： Muddassir Khalidi Arwa Bawazir Tanzila Saba Zainab Mariya Mohiuddin Saeed lababidi Anees Ara Asma Vaheed Khan Abdul Rahman Mamdouh Artificial Intelligence and Data Analytics Lab Prince Sultan University Riyadh Saudi Arabia

ISBN: (数字)9798331520922

ISBN: (纸本)9798331520939

Conversational AI memory systems work much like human memory. They record, maintain, and retrieve contextual information from earlier interactions, just as human memory draws on past experiences and learned knowledge to shape understanding and responses. However, individuals often face challenges with long-term recall of specific details from past events and short-term working memory, such as retaining lists, which can limit their ability to provide well-informed and nuanced responses. This research aims at implementing a simple Retrieve-Augment-Generate (RAG) system to implement a memory augmentation system with a particular focus on a use case in the medical field. This paper introduces C.A.L.I.X (Cognitive Archive for Learning and Information Exchange), an AI powered conversational memory assistant designed in alignment with Responsible AI principles. CA.L.I.X has been engineered to monitor conversations and extract data using voice interactions, ensuring that the information gathered is reliable. Future efforts will be focused on enhancing the accuracy of memory retrieval, streamlining the control of memory decay, and elevating the overall user experience.

关键词： Conversational artificial intelligence Accuracy Memory management Medical services Documentation Vectors User experience Time factors Information exchange Strain

来源：评论

学校读者我要写书评

暂无评论

Novel Feature Extractor Framework in Conjunction with Supervised Three Class-XGBoost Algorithm for Osteosarcoma Detection from Whole Slide Medical Histopathology Images

引用

Computers, Materials & Continua 2025年第2期82卷 3337-3353页

作者： Tanzila Saba Muhammad Mujahid Shaha Al-Otaibi Noor Ayesha Amjad Rehman Khan Artificial Intelligence&Data Analytics Lab College of Computer&Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Information Systems College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11671Saudi Arabia Center of Excellence in Cyber Security(CYBEX) Prince Sultan UniversityRiyadh11586Saudi Arabia

Osteosarcomas are malignant neoplasms derived from undifferentiated osteogenic mesenchymal cells. It causes severe and permanent damage to human tissue and has a high mortality rate. The condition has the capacity to occur in any bone;however, it often impacts long bones like the arms and legs. Prompt identification and prompt intervention are essential for augmenting patient longevity. However, the intricate composition and erratic placement of osteosarcoma provide difficulties for clinicians in accurately determining the scope of the afflicted area. There is a pressing requirement for developing an algorithm that can automatically detect bone tumors with tremendous accuracy. Therefore, in this study, we proposed a novel feature extractor framework associated with a supervised three-class XGBoost algorithm for the detection of osteosarcoma in whole slide histopathology images. This method allows for quicker and more effective data analysis. The first step involves preprocessing the imbalanced histopathology dataset, followed by augmentation and balancing utilizing two techniques: SMOTE and ADASYN. Next, a unique feature extraction framework is used to extract features, which are then inputted into the supervised three-class XGBoost algorithm for classification into three categories: non-tumor, viable tumor, and non-viable tumor. The experimental findings indicate that the proposed model exhibits superior efficiency, accuracy, and a more lightweight design in comparison to other current models for osteosarcoma detection.

关键词： Medical image processing deep learning healthcare image classification histopathology

来源：评论

学校读者我要写书评

暂无评论

MathVision: An Accessible Intelligent Agent for Visually Impaired People to Understand Mathematical Equations

引用

IEEE ACCESS 2025年 13卷 6155-6165页

作者： Ahmad, Muhammad Awais Ahmed, Tauqir Aslam, Muhammad Rehman, Amjad Alamri, Faten S. Bahaj, Saeed Ali Saba, Tanzila Univ Engn & Technol Dept CS Lahore 39161 Punjab Pakistan Prince Sultan Univ Riyadh Artificial Intelligence & Data Analyt Lab CCIS Riyadh 11586 Saudi Arabia Princess Nourah Bint Abdulrahman Univ Coll Sci Dept Math Sci POB 84428 Riyadh 11671 Saudi Arabia Prince Sattam Bin Abdulaziz Univ MIS Dept Coll Business Adm Alkharj 11942 Saudi Arabia

2.2 billion people worldwide suffer from some form of vision impairment, according to the World Health Organization. Children with vision impairment and visual impairment may experience impaired physical, linguistic, and cognitive development, resulting in reduced levels of academic accomplishment. Many visually impaired people are working in the education sector whether they are students or teachers. Without external assistance reading of mathematical equations in images for visually impaired people is very challenging due to the complexity of notations, symbols, and variables. This paper presents a model named MathVision which converts the mathematical equation into voice. This voice is quite helpful for visually impaired people to understand mathematical equations. The proposed model is comprised of YOLOv7 object detection architecture to detect and categorize mathematical equations inside images into four distinct types: limits, trigonometry, integration, and an additional category. The input image is divided into a grid by the YOLOv7 model, and each grid cell is responsible for finding equations that fall into its respective category. bounding box coordinates, object labels, and probability scores are predicted for each equation. In the next stage, a fine-tuned DenseNet is utilized for detailed feature extraction from mathematical equation images. This involves optimizing a pre-trained DenseNet model to capture intricate patterns specific to equations. The fine-tuned DenseNet enhances overall accuracy in equation detection and categorization within the system. In the subsequent phase, an attention mechanism-based LSTM network is employed to generate natural language descriptions for mathematical equations. During the decoding process, the model is better able to focus on pertinent portions of the equation due to the integration of attention. The LSTM architecture, chosen for its effectiveness with sequential data, is trained on a dataset containing paired examp

关键词： Mathematical models Accuracy Symbols Natural languages Feature extraction Long short term memory Handwriting recognition Neural networks Image recognition Decoding Mathematical equations fine-tuned YOLO v7 convolution neural network attention mechanism long short term memory neural text to speech technological development

来源：评论

学校读者我要写书评

暂无评论

MSegNet: A Multi-View Coupled Cross-Modal Attention Model for Enhanced MRI Brain Tumor Segmentation

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL intelligence SYSTEMS 2025年第1期18卷 1-32页

作者： Wang, Yu Xu, Juan Guan, Yucheng Ahmad, Faizan Mahmood, Tariq Rehman, Amjad Shandong Res Inst Ind Technol Jinan Shandong Peoples R China Taian City Cent Hosp Dept Endocrinol Tai An Peoples R China Northeastern Univ Coll Engn San Jose CA USA Qiqihar Med Univ Qiqihar Heilongjiang Peoples R China Prince Sultan Univ Artificial Intelligence & Data Analyt AIDA Lab CCIS Riyadh 11586 Saudi Arabia Univ Educ Fac Informat Sci Vehari Campus Vehari 61100 Pakistan

Brain tumor incidence and mortality rates are increasing due to unique location and treatment challenges. Early detection, robust diagnosis, and prompt treatment are crucial for better clinical evaluations. However, traditional neural network-based diagnostic methods often overlook issues such as variation in multimodality information, loss of spatial information, and under-utilization of boundary information. This study presents the Multi-View Coupled Cross-Modal Attention Network (MSegNet), a novel Transformer-based segmentation framework that integrates cross-modal attention mechanisms and a multi-view architecture. MSegNet is designed to exploit multimodal MRI data's spatial and depth dimensions, effectively capturing nuanced intermodal relationships and modeling long-range dependencies. The proposed framework also employs three data augmentation methods, which help prevent overfitting and improve the performance of segmentation network training, enhancing the model's robustness and generalizability. The proposed model is validated using BraTS2019, BraTS2020 and Figshate brain datasets and is compared against three state-of-the-art 3D segmentation networks. Extensive experiments, including ablation studies and hyperparameter sensitivity analyses, highlight MSegNet's robust performance. The dice scores for the whole tumor (WT), tumor core (TC) and enhancing tumor (ET) regions improved by 13. 96%, 12. 39%, and 11. 83%, respectively, while the Hausdorff distances were reduced by 3.64 mm, 2.98 mm, and 14.72 mm. These results demonstrate the model's efficacy in enhancing segmentation precision, making it a valuable tool for clinical diagnosis and treatment planning.

关键词： Transformer model Brain tumor segmentation Multi-modal fusion Cross-modal attention Health Issue

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Shape-Driven Combined Approach for Breast Cancer Tumor Segmentation

Deep Learning and Shape-Driven Combined Approach for Breast ...

引用

International Conference on Advancements in Computational Sciences (ICACS)

作者： Mudassar Ali Haoji Hu Tufail Muhammad Muhammad Ahsan Qureshi Tariq Mahmood College of Information Science and Electronic Engineering Zhejiang University Hangzhou China Department of Computer Science Air University Islamabad Pakistan Artificial Intelligence and Data Analytics Lab CCIS Prince Sultan University Riyadh Kingdom of Saudi Arabia.

ISBN: (数字)9798331533038

ISBN: (纸本)9798331533045

Our aim is to enhance the performance of segmenting breast cancer from medical images by overcoming major challenges, including data insufficiency and complexity when training a model. Using the INbreast dataset, it proposes a hybrid method for improving the segmentation accuracy and computational efficiency by combining M3D-Neural Cellular Automata with Shape-Guided Segmentation. This work aims at optimal performance on complex tasks of tumor segmentation by leveraging shape priors and reducing the need for extensive training data. Results confirm that significant improvements in both accuracy and robustness are achieved, which reduces computation time and improves tumor boundary delineation. The hybrid approach provides a time- and cost-effective method for precise detection in breast cancer diagnosis and treatment.

关键词： Deep learning Training Image segmentation Accuracy Shape Training data Breast cancer data models Robustness Real-time systems

来源：评论

学校读者我要写书评

暂无评论

data Frequency Coverage Impact on AI Performance 18

Data Frequency Coverage Impact on AI Performance

引用

18th IEEE International Conference on Software Testing, Verification and Validation Workshops, ICSTW 2025

作者： Lanus, Erin Lee, Brian Chandrasekaran, Jaganmohan Freeman, Laura J. Raunak, M.S. Kacker, Raghu N. Richard Kuhn, D. Virginia Tech National Security Institute ArlingtonVA United States Virginia Tech Sanghani Center for Artificial Intelligence & Data Analytics ArlingtonVA United States National Institute of Standards and Technology Information Technology Lab MD United States

ISBN: (纸本)9798331534677

artificial intelligence (AI) models use statistical learning over data to solve complex problems for which straightforward rules or algorithms may be difficult or impossible to design;however, a side effect is that models that are complex enough to sufficiently represent the function may be uninterpretable. Combinatorial testing, a black-box approach arising from software testing, has been applied to test AI models. A key differentiator between traditional software and AI is that many traditional software faults are deterministic, requiring a failureinducing combination of inputs to appear only once in the test set for it to be discovered. On the other hand, AI models learn statistically by reinforcing weights through repeated appearances in the training dataset, and the frequency of input combinations plays a significant role in influencing the model's behavior. Thus, a single occurrence of a combination of feature values may not be sufficient to influence the model's behavior. Consequently, measures like simple combinatorial coverage that are applicable to software testing do not capture the frequency with which interactions are covered in the AI model's input space. This work develops methods to characterize the data frequency coverage of feature interactions in training datasets and analyze the impact of imbalance, or skew, in the combinatorial frequency coverage of the training data on model performance. We demonstrate our methods with experiments on an open-source dataset using several classical machine learning algorithms. This pilot study makes three observations: performance may increase or decrease with data skew, feature importance methods do not predict skew impact, and adding more data may not mitigate skew effects. © 2025 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Suhail the Guiding Star: A Sustainable Chatbot for Saudi Arabia Culture

Suhail the Guiding Star: A Sustainable Chatbot for Saudi Ara...

引用

Women in data Science at Prince Sultan University (WiDS PSU), International Conference of

作者： Wahaj Saidam Lina Alnasi Sarah Ayman Rasha Alnaji Alqahtani Heyfa Ammar Anis Koubaa CCIS Prince Sultan University Riyadh Saudi Arabia College of Comp. and Info. Sciences Prince Sultan University Riyadh Saudi Arabia Artificial Intelligence and Data Analytics Lab. CCIS Prince Sultan University Riyadh Saudi Arabia University of Tunis ELManar Tunisia Alfaisal University Riyadh Saudi Arabia

ISBN: (数字)9798331520922

ISBN: (纸本)9798331520939

Protecting the cultural heritage is essential to ensure its survival for future generations while fostering cultural diversity and global understanding. It is then crucial to develop engaging, interactive and innovative approaches to inform and educate people about the significance of cultural heritage, making it accessible and appealing to diverse audiences. Particularly in the Kingdom of Saudi Arabia, various solutions have been proposed to assist visitors during their journey in the kingdom. However, the existing solutions lack localized content or fail to provide immersive dynamic user experiences, making them less effective in achieving cultural education goals. In this regard, the present work proposes Suhail: a novel AI-powered chatbot that allows for interactive communication, and improves understanding of Saudi cultural heritage through relevant responses. Suhail's reliability is underpinned by two novel datasets that we propose in this work, derived from trusted and verified sources. Our evaluation indicates an impressive accuracy score of 93.3%. Suhail's potential to advance Saudi cultural preservation and dissemination is underscored through expert interviews and survey responses in the direction of Saudi Vision 2030 and UN Sustainable Development Goals, specifically Quality Education (SDG 4) and Sustainable Cities (SDG 11).

关键词： Surveys Accuracy Education Urban areas Stars Chatbots Cultural differences Global communication Reliability Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Proactive and data-centric Internet of Things-based fog computing architecture for effective policing in smart cities

引用

COMPUTERS & ELECTRICAL ENGINEERING 2025年 123卷

作者： Butt, Ateeq Ur Rehman Saba, Tanzila Khan, Inayat Mahmood, Tariq Khan, Amjad Rehman Singh, Sushil Kumar Daradkeh, Yousef Ibrahim Ullah, Inam Natl Text Univ Dept Comp Sci Faisalabad 37610 Pakistan CCIS Prince Sultan Univ Artificial Intelligence & Data Analyt AIDA Lab Riyadh 11586 Saudi Arabia Univ Engn & Technol Mardan Dept Comp Sci Mardan 23200 Pakistan Marwadi Univ Dept Comp Engn Rajkot Gujarat India Prince Sattam bin Abdulaziz Univ Coll Engn Wadi Alddawasir Dept Comp Engn & Informat Al Kharj 16273 Saudi Arabia Gachon Univ Dept Comp Engn Seongnam 13120 South Korea

Smart surveillance is crucial for improving citizen security and ensuring a sustainable environment for routine tasks, particularly within intelligent transportation systems (ITS). However, it can be costly and burden taxpayers. The lack of public interaction makes it difficult for police to arrest and conduct investigations. Additionally, incidents increase due to similar patterns, making smart surveillance essential for reporting and addressing these issues. Smart devices such as sensors or actuators installed on the roads and within vehicles are critical components of any smart surveillance and ITS framework. This integration enhances system agility and facilitates proactive rather than reactive responses. It empowers security agencies to plan more effectively and respond swiftly during emergencies. The incorporation of cloud computing capabilities transforms traditional surveillance and ITS operations. Employing the Internet of Things (IoT) with edge or cloud computing extensions, such as fog computing, modernizes the management of security gadgets for Field Forces. This study investigates a smart surveillance fog-enabled approach to reduce response times for aiding agencies within ITS. By optimizing individual journeys through an RFID-based passing system, incidents are reported promptly to the nearest field force, enhancing overall ITS efficiency. The proactive approach improves resource consumption (energy, CPU, and network usage) compared to traditional reactive methods. The fog-enabled experiments demonstrated a CPU efficiency of approximately 95.76%, significantly outperforming the Cloud-only deployment, achieving a maximum average efficiency of 92.12%. Experimental evaluations in a simulation environment demonstrate that the proposed method significantly outperforms conventional approaches, marking a substantial advancement in IoT-aided ITS.

关键词： Internet of Things Intelligent transportation system Fog computing Effective policing Smart surveillance Smart cities

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：