检索结果-内蒙古大学图书馆

25th International Arab Conference on Information technology, ACIT 2024

作者： Attar, Hani Ababneh, Jafar Rachini, Ali Bahy, Ramy M. Hafez, Mohamed Solyman, Ahmed Zarqa University Faculty of Engineering Zarqa Jordan Zarqa University Faculty of Information Technology Cyber Security Department Zarqa Jordan Department of Computer Science and Information Technology Jounieh Lebanon Technical Research Center Cairo Egypt Feqs INTI-IU-University Faculty of Engineering Nilai Malaysia Glasgow Caledonian University School of Computing Engineering and Built Environment Glasgow United Kingdom

ISBN: (纸本)9798331540012

Underwater communication systems have garnered significant interest due to the limitations of the wireless spectrum and the growing need for sustained, covert communication capabilities. However, existing systems face significant challenges from doubly dispersive channels that cause time and frequency fading, disrupting the orthogonality of conventional OFDM subcarriers and leading to severe inter-symbol interference (ISI), even with complex equalizers like MMSE. This paper proposes a Fractional Fourier Transform (FrFT)-based OFDM system, offering better adaptability in the time-frequency domain. The FrFT-OFDM system effectively concentrates power around the diagonal of the channel matrix, mitigating Doppler shifts and multipath fading, thus enhancing spectral efficiency and robustness. A low-complexity equalizer is introduced, reducing computational demands while maintaining high performance, ensuring practical real-time application in underwater environments. Simulation results show that the proposed DFrFT-OFDM system with the optimized equalizer surpasses traditional OFDM under severe channel dispersion, demonstrating improved bit error rates and signal-to-noise ratios by about 3 db. This confirms its capability for reliable underwater communication with reduced computational overhead by about 90% comparing the OFDM with MMSA and DFrFT-OFDM with bande MMSA, marking a significant step forward for high-performance data transmission in challenging aquatic environments. © 2024 IEEE.

关键词： Bit error rate

来源：评论

学校读者我要写书评

暂无评论

Petroleum Drilling Monitoring and Optimization: Ranking the Rate of Penetration Using Machine Learning Algorithms

Petroleum Drilling Monitoring and Optimization: Ranking the ...

引用

作者： Acheme, Ijegwa David Nwankwo, Wilson Olayinka, Akinola S. Makinde, Ayodeji S. Nwankwo, Chukwuemeka P. Department of Computer Science Edo State University Uzairue Nigeria Department of Physics Edo State University Uzairue Nigeria Department of Cyber Security Delta State University of Science and Technology Ozoro Nigeria

Oil prospection and exploration is a major economic venture requiring enormous expertise and technologies in developing countries. In this study, we set out to examine an important issue that affects the efficiency of oil drilling operations that is, the rate of penetration (ROP) during oil exploration. We attempt to apply different machine learning algorithms in order to discover the most efficient algorithm that could be used for the prediction of the ROP. We use the North Sea oil field data set while eighteen intelligent models were developed. On comparative analysis of the models, it is shown that the random forest algorithm exhibits the best efficiency in the prediction workflow having an RMSE value of 0 0010, and an R2 score of 0 891. Findings also showed that significant parameters of concern during drilling operations were the measured depth, bit rotation per minute, for-mation porosity, shale volume, water saturation, and log permeability respectively. We conclude that the result of this study provides a good template to guide the selection of machine learning algorithms to drive solutions for the optimization of oil drilling operations. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Educational FinTech: Promoting Stakeholder Confidence Through Automatic Incidence Resolution

Educational FinTech: Promoting Stakeholder Confidence Throug...

引用

作者： Nwankwo, Wilson Chinedu, Paschal U. Daniel, Aliu Shaba, Saliu Mohammed Muyideen, Momoh Omuya Nwankwo, Chukwuemeka P. Adigwe, Wilfred Oghoriodo, Duke Uwadia, Francis Department of Computer Science Edo State University Uzairue Uzairue Nigeria Department of Computer Engineering Edo State University Uzairue Uzairue Nigeria Federal College of Freshwater Fisheries Technology New Bussa Nigeria Faculty of Air Engineering Air Force Institute of Technology Kaduna Kaduna Nigeria Department of Computer Science Delta University of Science and Technology Ozoro Nigeria Department of Cyber Security Delta University of Science and Technology Ozoro Nigeria

Though FinTech solutions have the potentials to increase efficiency and convenience with education-related payments and remittances in developing countries, it is noted that tens of thousands of stakeholders are still hesitant on using electronic channels due to high transaction failure rates, lack of transparency, and the extensive effort and time stakeholders expend in getting failed transactions reconciled especially when such transactions are false positives that is, the transaction appears to have failed yet the bank account of the payer is debited. This paper is intended to provide a fine-grained model for remedying these problems. In this paper, we address the challenges of false positives in FinTech transactions. We adopt a case study approach complemented by the famous object-based systems development methodology. We demonstrate an improvement on a traditional multi-channel FinTech solution earlier implemented in a public University. The improvement is made by a smart integration of an algorithm that keep the histories of every action of the payer during the payment process as well as the intermediate processes across the application programming interfaces (APIs) used during electronic data interchange (EDI). Whenever there is a false positive, the user/payer can remedy this by using a verification button which queries all the records in the transaction workflow and updates the true status of the payer on the institutional FinTech platform. By this action, the payer’s usual need to seek human support on reconciliation of false positive transactions from the FinTech operator, client support, or the payer’s bank, is eliminated. We present part of a Tertiary Education Enterprise Resource Planning System (TEERPS), an end-to-end solution for all academic and administrative workflows including financial transaction processing. We observed the system in a production environment over several months and the results have shown that the integration of a reverse verifi

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Gate-Attention and Dual-End Enhancement Mechanism for Multi-Label Text Classification

引用

computers, Materials & Continua 2023年第11期77卷 1779-1793页

作者： Jieren Cheng Xiaolong Chen Wenghang Xu Shuai Hua Zhu Tang Victor S.Sheng School of Computer Science and Technology Hainan UniversityHaikou570228China Hainan Blockchain Technology Engineering Research Center Hainan UniversityHaikou570228China School of Cyberspace Security Hainan UniversityHaikou570228China Department of Computer Science Texas Tech UniversityLubbock79409USA

In the realm of Multi-Label Text Classification(MLTC),the dual challenges of extracting rich semantic features from text and discerning inter-label relationships have spurred innovative *** studies in semantic feature extraction have turned to external knowledge to augment the model’s grasp of textual content,often overlooking intrinsic textual cues such as label statistical *** contrast,these endogenous insights naturally align with the classification *** our paper,to complement this focus on intrinsic knowledge,we introduce a novel Gate-Attention *** mechanism adeptly integrates statistical features from the text itself into the semantic fabric,enhancing the model’s capacity to understand and represent the ***,to address the intricate task of mining label correlations,we propose a Dual-end enhancement *** mechanism effectively mitigates the challenges of information loss and erroneous transmission inherent in traditional long short term memory *** conducted an extensive battery of experiments on the AAPD and RCV1-2 *** experiments serve the dual purpose of confirming the efficacy of both the Gate-Attention mechanism and the Dual-end enhancement *** final model unequivocally outperforms the baseline model,attesting to its *** findings emphatically underscore the imperativeness of taking into account not just external knowledge but also the inherent intricacies of textual data when crafting potent MLTC models.

关键词： Multi-label text classification feature extraction label distribution information sequence generation

来源：评论

学校读者我要写书评

暂无评论

PRESS: Defending Privacy in Retrieval-Augmented Generation via Embedding Space Shifting

PRESS: Defending Privacy in Retrieval-Augmented Generation v...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： He, Jiaming Liu, Cheng Hou, Guanyu Jiang, Wenbo Li, Jiachen School of Computer Science and Engineering University of Electronic Science and Technology of China China College of Computer Science and Cyber Security Oxford Brookes College Chengdu University of Technology China School of Data Science The Chinese University of Hong Kong Shenzhen China School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798350368741

Retrieval-augmented generation (RAG) expands the capabilities of large language models (LLMs) in various applications by integrating relevant information retrieved from external data sources. However, the RAG systems are exposed to substantial privacy risks during the information retrieval process, leading to potential data leakage of private information. In this work, we present a Privacy-preserving Retrieval-augmented generation via Embedding Space Shifting (PRESS), systematically exploring how to protect privacy in RAG systems. Specifically, we first conduct proximal policy optimization (PPO) based training on pre-trained language models to generate target training samples. Then we employ a purposive shift fine-tuning on the text embedding model with the generated samples for guiding the RAG system to map potential privacy leaking queries to safe target in embedding space. Extensive experimental results on representative models and datasets demonstrate that our protection method achieves high defense performance with high efficiency while keeping the normal functionality of the RAG system. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EVADE: Targeted Adversarial False Data Injection Attacks for State Estimation in Smart Grid

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable Computing 2024年第3期10卷 534-546页

作者： Tian, Jiwei Shen, Chao Wang, Buhong Ren, Chao Xia, Xiaofang Dong, Runze Cheng, Tianhao Ministry of Education Key Laboratory for Intelligent Networks and Network Security School of Cyber Science and Engineering Xi'an Jiaotong University Xi'an China Air Traffic Control and Navigation College Air Force Engineering University Xi'an China Information and Navigation College Air Force Engineering University Xi'an China School of Electrical and Electronic Engineering Nanyang Technological University Singapore School of Computer Science and Technology Xidian University Xi'an China

Although conventional false data injection attacks can circumvent the detection of bad data detection (BDD) in sustainable power grid cyber physical systems, they are easily detected by well-trained deep learning-based detectors. Still, state estimation models with deep leaning-based detectors are not secure due to the vulnerabilities and fragility of deep learning models. Using the related laws of conventional false data injection attacks and adversarial sample attacks, this paper proposes the targEted adVersarial fAlse Data injEction (EVADE) strategy to explore targeted adversarial false data injection attacks for state estimation in Smart Grid. The proposed EVADE attack strategy selects key state variables based on adversarial saliency maps to improve the attack efficiency and perturbs as few state variables as possible to reduce the attack cost. In this way, the EVADE attack strategy can bypass the detection of BDD and neural attack detection (NAD) methods (that is, maintaining deep stealthy) with a high success rate and achieve the attack target simultaneously. Experimental results demonstrate the effectiveness of the proposed strategy, posing serious and pressing concerns for sustainable cyber physical power system security. © 2016 IEEE.

关键词： cyber attacks

来源：评论

学校读者我要写书评

暂无评论

JANE: Joint Angle Networks Assisting 3D Human Pose Estimation

JANE: Joint Angle Networks Assisting 3D Human Pose Estimatio...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wang, Jinhuan Zhao, Yuzhen Song, Xujie Chen, Wenzhou Xuan, Qi Institute of Cyberspace Security College of Information Engineering Zhejiang University of Technology HangZhou China Department of Computer Science and Technology Hangzhou Dianzi University HangZhou China

ISBN: (纸本)9798350368741

3D human pose estimation (HPE) is crucial due to its extensive applications. While current 3D HPE methods focus on human skeleton topology for accuracy, they often overlook joint angle information, which is vital in 2D-to-3D pose lifting. This paper introduces the Joint Angle Network (JANE) model to leverage joint angle features from 2D poses. We propose an angle graph convolution module to extract joint angle features and a multi-stage parallel fusion module to integrate these features with input image data. Experiments on Human3.6M show that our method improves accuracy by 8.7% and 2.6% over non-spatiotemporal baselines using 2D ground truth and 2D pose detectors, respectively. © 2025 IEEE.

关键词： 3D Human Pose Estimation Graph Convolution Network Joint Angle Network

来源：评论

学校读者我要写书评

暂无评论

Fake Currency Note Recognition using Extreme Learning Machine 2

Fake Currency Note Recognition using Extreme Learning Machin...

引用

2nd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2023

作者： Kumar, Rajeev Lamba, Anil Kumar Mohammed, Sayed Asokan, Anju Aswal, Upendra Singh Kolavennu, Subbarao Gopal Narayan Singh University Faculty of Information Technology Bihar Jamuhar India Psna College of Engineering and Technology Ece Tamilnadu Dindigul India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India School of Computer Science and Engineering Geeta University Delhi India Sri Eshwar College of Engineering Kinathukadavu Department of Computer and Communication Engineering Tamilnadu Coimbatore India Sphoorthy Engineering College Cse Cyber Security Department Telangana Hyderabad India

ISBN: (纸本)9781665456302

Color printing technology has made it simpler for forgers to make and copy large numbers of fake currency. The production of legible banknotes was once the sole purview of print shops, but today even a novice printer with a simple laser printer can do the job. Because of this, the prevalence of counterfeit money has increased dramatically. A number of problems, including corruption and the existence of 'black money,' have hounded India for a long time. There is also a serious problem with the circulation of counterfeit currency. The outcome is a system that can detect fake currency with greater speed and precision. It is a serious crime to create counterfeit currency, which is money that has not been authorized by the government. The vast majority of them do this professionally. The circulation of counterfeit currency retards economic development and devalues legitimate currency. In this study, it uses image processing to the problem of identifying fake Indian notes. This technique finishes the initial acquisition before the image is processed further. Pre-processing includes actions such as cropping, smoothing, and modifying the image;converting the image to greyscale;applying image segmentation;extracting features;and resizing the image. The model is then trained using an ELM. Proposed model exceeds both the CNN and SVM models in terms of accuracy, at around 97.8 percent. © 2023 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Intelligent wearable vision systems for the visually impaired in Saudi Arabia

引用

Neural Computing and Applications 2025年第14期37卷 8571-8591页

作者： Talaat, Fatma M. El-Shafai, Walid Soliman, Naglaa F. Algarni, Abeer D. El-Samie, Fathi E. Abd Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt Faculty of Computer Science and Engineering New Mansoura University Gamasa35712 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Navigating the world with visual impairments presents unique challenges, often limiting independence and safety. This research introduces SafeStride, a novel algorithm designed to empower visually impaired individuals through real-time obstacle detection and navigation assistance. SafeStride functions through five interconnected phases: sensor data acquisition, data preprocessing, obstacle detection, path planning, and feedback and guidance. A combination of ultrasonic sensors, cameras, and inertial measurement units (IMUs) feed comprehensive environmental data into the system, enabling accurate obstacle detection and safe path planning. Evaluating SafeStride's performance involved the MNIST dataset for image recognition and a dedicated indoor object detection dataset. Additionally, comparisons were made against three deep learning models—convolutional neural network (CNN), long short-term memory (LSTM), and gated recurrent unit (GRU). The results showcased SafeStride's high accuracy and effectiveness in both obstacle detection and classification. Beyond its impressive performance, SafeStride represents a significant leap forward in navigation aids for the visually impaired. By offering a comprehensive solution that enhances safety and independence in diverse environments, it holds immense potential to improve the lives of countless individuals. Future efforts will focus on further optimizing the algorithm and testing its real-world capabilities, paving the way for a future where safe and independent navigation becomes a reality for all. All three deep learning models (CNN, LSTM, GRU) excelled in the experiment, achieving high accuracy above 0.98, strong recall and F1-scores near 0.99, and exceptional AUC-ROC scores exceeding 0.9998. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

An Effective Lung Cancer Diagnosis Model Using Pre-Trained CNNs

引用

computer Modeling in engineering & Sciences 2025年第4期143卷 1129-1155页

作者： Majdi Rawashdeh Muath A.Obaidat Meryem Abouali Dhia Eddine Salhi Kutub Thakur Department of Business Information Technology Princess Sumaya University for TechnologyAmman11941Jordan Department of Computer Engineering Al Yamamah UniversityRiyadh11512Saudi Arabia Department of Computer Science John Jay College and the Graduate CenterThe City University of New YorkNew YorkNY 10019USA Department of Computer Science John Jay College at the City University of NewYorkNewYorkNY 10019USA LIMOSE Laboratory Department of Computer ScienceM’hamed Bougara UniversityBoumerdes35000Algeria Department of Professional Security Studies New Jersey City UniversityJersey CityNJ 07305USA

Cancer is a formidable andmultifaceted disease driven by genetic aberrations and metabolic *** 19% of cancer-related deaths worldwide are attributable to lung and colon cancer,which is also the top cause of death *** malignancy has a terrible 5-year survival rate of 19%.Early diagnosis is critical for improving treatment outcomes and survival *** study aims to create a computer-aided diagnosis(CAD)that accurately diagnoses lung disease by classifying histopathological *** uses a publicly accessible dataset that includes 15,000 images of benign,malignant,and squamous cell carcinomas in the *** addition,this research employs multiscale processing to extract relevant image features and conducts a comprehensive comparative analysis using four Convolutional Neural Network(CNN)based on pre-trained models such as AlexNet,VGG(Visual Geometry Group)16,ResNet-50,and VGG19,after hyper-tuning these models by optimizing factors such as batch size,learning rate,and *** proposed(CNN+VGG19)model achieves the highest accuracy of 99.04%.This outstanding performance demonstrates the potential of the CAD system in accurately classifying lung cancer histopathological *** study contributes significantly to the creation of a more precise CNN-based model for lung cancer identification,giving researchers and medical professionals in this vital sector a useful tool using advanced deep learning techniques and publicly available datasets.

关键词： Lung cancer machine learning computer aided diagnosis CNN medical imaging transfer 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：