检索结果-内蒙古大学图书馆

2nd IEEE Global Conference on Communications and Information Technologies, GCCIT 2024

作者： Mahalle, Parikshit N. Chandra Lohani, Manoj Hemelatha, S. Sharma, Divya Chitra, S. Jayakumar, Sujayaraj Samuel Vishwakarma Institute of Technology Department of Artificial Intelligence & Data Science Pune India Graphic Era Hill University School of Computing Haldwani India Graphic Era Deemed to be University Uttarakhand Dehradun248002 India Karpagam Academy of Higher Education Department of Computer Science Engineering Coimbatore641021 India Chitkara University Centre of Research Impact and Outcome Punjab Rajpura140417 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai127 India School of Sciences Forensic Science Karnataka Bangalore India

ISBN: (纸本)9798350388916

Synthetic computed tomography (sCT) based on magnetic resonance imaging (MRI) streamlines the planning of radiation therapy treatments by doing away with CT simulation and error-prone picture registration, which in turn reduces radiation dosage for patients and setup uncertainty. To create sCT images that matched the MRI anatomy, an optimally trained MultiHead Attention was used in conjunction with the reverse diffusion process. We generated sCT using MRI on two datasets - one for the brain and one for the prostate - to test the suggested strategy. The following metrics were used for qualitative evaluation: ground truth CTs and sCTs normalized cross correlation (NCC) indices, multi-scale Structure Similarity index (MS-SSIM), peak signal-to-noise ratio (PSNR), and mean absolute error (MAE) of Hounsfield unit (HU). A new method for creating CT images from standard MRIs utilizing a transformer-based convolutional neural network (CNN) has been designed and verified by us. Synthetic CT (sCT) pictures of excellent quality and robustness may be produced in a few minutes using this model, which successfully depicts the intricate interaction among CT and MRI images. By cutting down on patient time spent on treatment planning, improving accuracy of treatment delivery, and doing away with the necessity for extra CT scans, this method may considerably streamline radiation treatment planning. © 2024 IEEE.

关键词： Radiotherapy

来源：评论

学校读者我要写书评

暂无评论

EQCNN: Enhanced Remote Sensing Imagery Classification with Circuit-Based Error-Corrected Quantum Convolutional Neural Networks

EQCNN: Enhanced Remote Sensing Imagery Classification with C...

引用

Proceedings of the Digital Image computing: Technqiues and Applications (DICTA)

作者： Muhammad Zaman Tanzila Kehkashan Adnan Akhunzada Hashem Alaidaros Mueen Uddin Muhammad Azeem Faculty of Computer Science University of Lahore Sargodha Punjab Pakistan Faculty of Computing Universiti Teknologi Malaysia Johor Bahru Malaysia Department of Data and Cybersecurity College of Computing & IT University of Doha for Science & Technology Doha Qatar Department of Cybersecurity Dar Al-Hekma University Jeddah Saudi Arabia

ISBN: (数字)9798350379037

ISBN: (纸本)9798350379044

Quantum information processing is more complex than classical counterpart because of the No-Cloning theorem, decoherence, and issues detecting quantum states. Building a quantum computer without error detection and correction module is challenging. To overcome this challenge, qubit error correction codes are implemented. Inadequate error detection and correction codes have been the downfall of earlier attempts to encode quantum information, leading to disrupted qubit transmission. Qubit information is decohered by circuit noise. Unfortunately, the principal qubit error, phase flip error is not corrected by existing qubit error correction methods. In this study, we proposed Quantum Error Detection and Correction scheme (QEDC) to keep qubit in a coherent state. Used S gates, unitary gates, 10 CNOT gates, and Hadamard gates spanning on 4 physical and 1 logical qubits over the IBM Quantum Experience Machine. We found that the error probability is reduced to 7.91% owing to the efficiency of the quantum information encoding and phase flip control. Furthermore, we proposed Error Corrected Quantum Convolution Neural Network (EQCNN) for Image Classification. EQCNN combat and correct qubit errors that occur during the image processing. EQCNN outperformed over Earth Observatory (EO) dataset, EuroSAT and achieved an impressive results of 99.3% accuracy, 98.9% F1-score, 96.73% precision, and 98.4% recall.

关键词： Quantum system Accuracy Observatories Qubit Neural networks Logic gates Quantum state Convolutional neural networks Remote sensing Image classification

来源：评论

学校读者我要写书评

暂无评论

Motivation and Strategies for Effective Inclusion of Cloud Solution Provider Certifications in computing Curricula 22

Motivation and Strategies for Effective Inclusion of Cloud S...

引用

27th Annual Conference on Innovation and Technology in Computer science Education, ITiCSE-WGR 2022

作者： Paterson, James H. Adams, Joshua Foster, Derek Baghban Karimi, Ouldooz Kazmi, Zain Lennon, Ruth G. Nazir, Sajid Stott, Lee White, Laurie Department of Computing Glasgow Caledonian University Glasgow Scotland United Kingdom School of Computing Artificial Intelligence Robotics Data Science Saint Leo University Saint LeoFL United States School of Computer Science University of Lincoln Lincoln England United Kingdom School of Computing Science Simon Fraser University SurreyBC Canada Execusoft Solutions Inc. TorontoON Canada Department of Computing Atlantic Technological University Letterkenny Ireland Microsoft SeattleWA United States Google LLC SeattleWA United States

ISBN: (纸本)9798400700101

A series of Working Groups has met at previous ITiCSE conferences to explore ways of incorporating cloud computing into courses and curricula, including mapping industry job skills to knowledge areas and those areas to student learning objectives. The importance of industry-standard learning content and certification, produced by cloud vendors and others, was apparent throughout this work. This Working Group has focused on the role of certification within cloud computing curricula, from the viewpoints of a range of stakeholders: students, graduates, institutions, vendors and other certification providers;and employers, with the aim to provide insights and recommendations for educators who are considering whether to integrate cloud certifications into their courses. We reviewed the landscape of certifications provided by the most widely recognised cloud vendors, based on publicly available information and the knowledge embedded within the Working Group through the inclusion of vendor representatives in the membership. An overview is provided of the scope of available certifications and their mapping to our knowledge areas and learning outcomes, and of the influence that standards have or should have on learning design. We then explored the perspectives of stakeholders, through surveys of students on courses with a cloud computing element and of employers who have employed graduates of those courses, drawing conclusions on the awareness of certifications and specific vendors within each of those stakeholder groups, and on differences between the groups on the perceived importance of certifications for employability. Finally we explored approaches to integrating certification in academic cloud curricula, and challenges involved in doing so, through thematic analysis of in-depth interviews with a range of educators who have experience of doing so successfully. A set of recommendations for educators is presented, based on the findings of the Working Group's activities. ©

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

NO FREE LUNCH: RETRIEVAL-AUGMENTED GENERATION UNDERMINES FAIRNESS IN LLMS, EVEN FOR VIGILANT USERS

arXiv

引用

arXiv 2024年

作者： Hu, Mengxuan Wu, Hongyi Guan, Zihan Zhu, Ronghang Guo, Dongliang Qi, Daiqing Li, Sheng School of Data Science University of Virginia United States School of Management University of Science and Technology of China China Department of Computer Science University of Virginia United States School of Computing University of Georgia United States

Retrieval-Augmented Generation (RAG) is widely adopted for its effectiveness and cost-efficiency in mitigating hallucinations and enhancing the domain-specific generation capabilities of large language models (LLMs). However, is this effectiveness and cost-efficiency truly a free lunch? In this study, we comprehensively investigate the fairness costs associated with RAG by proposing a practical three-level threat model from the perspective of user awareness of fairness. Specifically, varying levels of user fairness awareness result in different degrees of fairness censorship on the external dataset. We examine the fairness implications of RAG using uncensored, partially censored, and fully censored datasets. Our experiments demonstrate that fairness alignment can be easily undermined through RAG without the need for fine-tuning or retraining. Even with fully censored and supposedly unbiased external datasets, RAG can lead to biased outputs. Our findings underscore the limitations of current alignment methods in the context of RAG-based LLMs and highlight the urgent need for new strategies to ensure fairness. We propose potential mitigations and call for further research to develop robust fairness safeguards in RAG-based LLMs. Copyright © 2024, The Authors. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Securing Smart Homes Using Hybrid Stacking Ensemble Deep Learning-Enabled Framework 2

Securing Smart Homes Using Hybrid Stacking Ensemble Deep Lea...

引用

2nd International Engineering Conference on Electrical, Energy, and Artificial Intelligence, EICEEAI 2023

作者： Moubayed, Abdallah Injadat, MohammadNoor Abdellatif Mohamed, Tamer Mohamed Almatarneh, Sattam Al-Mashagbeh, Malak Aljaidi, Mohammad School of Computing and Augmented Intelligence Arizona State University GilbertAZ United States Lebanese American University Electrical and Computer Engineering Department Byblos Lebanon Western University Electrical and Computer Engineering Department LondonON Canada Zarqa University Data Science and Artificial Intelligence Department Zarqa Jordan School of Engineering Applied Science and Technology Canadian University Dubai Dubai United Arab Emirates Zarqa University Cyber Security Department Zarqa Jordan Zarqa University Computer Science Department Zarqa Jordan

ISBN: (纸本)9798350373363

The added deployment of Internet-of-Things (IoT) devices in various environments has led to people increasingly adding this technology to their homes to make them more comfortable and have a more convenient living environment. Despite the promise and the growth potential of the smart home market, one main concern is the security and privacy of smart home devices. This is because smart home devices equipped with IoT technology are prone to various network-based attacks. With smart home devices having limited computation and memory capabilities, many IoT manufacturers often overlook the security aspect by focusing more on the functionality. To address this issue, the concepts of machine learning (ML) and deep learning (DL) have emerged as viable and promising solutions. To that end, this paper proposes a hybrid stacking ensemble DL-enabled framework that combines both classical ML models with sophisticated DL models. The goal is to make use of the simplicity and interpretability of the classical ML models with the superior time-dependent patterns that DL models can detect. The proposed framework's performance is evaluated using multiple datasets representing different smart home devices. Experimental results show that the proposed framework achieved better detection accuracy, precision, recall, and F-score. © 2023 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

FREEZE THE BACKBONES: A PARAMETER-EFFICIENT CONTRASTIVE APPROACH TO ROBUST MEDICAL VISION-LANGUAGE PRE-TRAINING

arXiv

引用

arXiv 2024年

作者： Qin, Jiuming Liu, Che Cheng, Sibo Guo, Yike Arcucci, Rossella Department of Computing Imperial College London United Kingdom Data Science Institute Imperial College London United Kingdom Department of Earth Science and Engineering Imperial College London United Kingdom Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

Modern healthcare often utilises radiographic images alongside textual reports for diagnostics, encouraging the use of Vision-Language Self-Supervised Learning (VL-SSL) with large pre-trained models to learn versatile medical vision representations. However, most existing VL-SSL frameworks are trained end-to-end, which is computation-heavy and can lose vital prior information embedded in pre-trained encoders. To address both issues, we introduce the backbone-agnostic Adaptor framework, which preserves medical knowledge in pre-trained image and text encoders by keeping them frozen, and employs a lightweight Adaptor module for cross-modal learning. Experiments on medical image classification and segmentation tasks across three datasets reveal that our framework delivers competitive performance while cutting trainable parameters by over 90% compared to current pre-training approaches. Notably, when fine-tuned with just 1% of data, Adaptor outperforms several Transformer-based methods trained on full datasets in medical image segmentation. © 2024, CC BY.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

ACSLs for Large-Scale Bounded Single Depot Multiple Travelling Salesman Problem

ACSLs for Large-Scale Bounded Single Depot Multiple Travelli...

引用

Congress on Evolutionary Computation

作者： Shanu Verma Millie Pant Department of Applied Mathematics & Scientific Computing Indian Institute of Technology Roorkee Roorkee Uttarakhand India Department of Applied Mathematics & Scientific Computing Mehta Family School of Data Science & Artificial Intelligence Indian Institute of Technology Roorkee Roorkee Uttarakhand India

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

Bounded single depot multiple travelling salesman problem (BSD-MTSP) optimizes salesmen tours with constraints on the number of cities visiting per salesman, which ensures balanced routes. BSD-MTSP presents challenges due to its combinatorial nature and additional complexities arising from multiple salesmen and depot-related constraints. Exact solutions for BSD-MTSP via classical methods are computationally expensive, prompting the use of heuristics and metaheuristics for practical solutions. This paper presents ACSLs, a hybrid algorithm combining initialization heuristic, Ant colony system, and Local search operators. ACSLs efficiently tackles large-scale BSD-MTSPs, demonstrating a superiority of up to 9.964% over the most advanced algorithms through comparative analysis.

关键词： Heuristic algorithms Urban areas Metaheuristics Evolutionary computation Benchmark testing Approximation algorithms Space exploration

来源：评论

学校读者我要写书评

暂无评论

HOFD: An Outdated Fact Detector for Knowledge Bases

引用

IEEE Transactions on Knowledge and data Engineering 2023年第10期35卷 10775-10789页

作者： Hao, Shuang Chai, Chengliang Li, Guoliang Tang, Nan Wang, Ning Yu, Xiang Beijing Jiaotong University School of Computer and Information Technology Beijing100044 China Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing100044 China Beijing Institute of Technology School of Computer Science and Technology Beijing100811 China Beijing100190 China Qatar Computing Research Institute Hbku Doha34110 Qatar Huawei Company Gauss Department Beijing100031 China

Knowledge bases (KBs), which store high-quality information, are crucial for many applications, such as enhancing search results and serving as external sources for data cleaning. Not surprisingly, there exist outdated facts in most KBs due to the rapid change of information. Naturally, it is important to keep KBs up-to-date. Traditional wisdom has investigated the problem of using reference data (such as new facts extracted from the news) to detect outdated facts in KBs. However, existing approaches can only cover a small percentage of facts in KBs. In this paper, we propose HOFD, a novel human-in-the-loop approach for outdated fact detection in KBs. HOFD trains a binary classifier using features such as historical update frequency and update time of a fact to compute the likelihood of a fact in a KB to be outdated. Then, HOFD interacts with humans to verify whether a fact with high likelihood is indeed outdated. In addition, HOFD also uses logical rules to detect more outdated facts based on human feedback. The outdated facts detected by the logical rules will also be fed back to train the ML model further for data augmentation. Extensive experiments on real-world KBs, such as Yago and DBpedia, show the effectiveness of our solution. © 1989-2012 IEEE.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Classification Using VGG-19 Based Faster-RCNN 7th

Plant Disease Classification Using VGG-19 Based Faster-RCNN

引用

Proceedings of the 7th International Conference on Advances in computing and data sciences, ICACDS 2023

作者： Nawaz, Marriam Nazir, Tahira Khan, Muhammad Attique Rajinikanth, Venkatesan Kadry, Seifedine Department of Software Engineering University of Engineering and Technology Taxila Taxila47050 Pakistan Faculty of Computing Department of Computer Science Riphah International University Gulberg Green Campus Islamabad Pakistan Department of Computer Science HITEC University Taxila Pakistan Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering SIMATS Chennai602105 India Department of Applied Data Science Noroff University College Kristiansand4612 Norway Ajman University Ajman346 United Arab Emirates Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

ISBN: (纸本)9783031379390

Early plant disease diagnosis can help farmers avoid spending money on costly crop pesticides and aid them to boost food production. Scientists have put a lot of effort to classify plant diseases, but it is difficult to quickly locate and identify different crop abnormalities due to the high degree of resemblance between the normal and damaged parts of plant leaves. Additionally, the procedure of detecting plant diseases has been made more challenging due to the extensive color, size, shape, and intensity variations in the background and foreground of the plant images. To address the existing difficulties, we have introduced an effective deep learning (DL) based system called Faster-RCNN o recognize and classify various types of plant diseases. The suggested method consists of 3 basic steps. In order to identify the area of interest in investigated samples, we first create annotations for them which are later used for Faster-RCNN training. The Faster-RCNN model employs the VGG-19 network to extract the relevant keypoints from the given images which are later passed to the regressor and classification units to identify and categorize the various crop diseases using the estimated features. We evaluated our method on a widely used standard plant sample repository called the PlantVillage database, and the findings show that our approach is reliable for classifying plant diseases under a variety of image-capturing scenarios. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Devil in the Noise: Detecting Advanced Persistent Threats with Backbone Extraction

Devil in the Noise: Detecting Advanced Persistent Threats wi...

引用

IEEE Symposium on Computers and Communications (ISCC)

作者： Caio M. C. Viana Carlos H. G. Ferreira Fabricio Murai Aldri Luiz Dos Santos Lourenço Alves Pereira Júnior Computer Science Division Aeronautics Institute of Technology Brazil Department of Computing and Systems Federal University of Ouro Preto Brazil Data Science & Computer Science Worcester Polytechnic Institute Worcester MA USA Department of Computer Science Federal University of Minas Gerais Brazil

ISBN: (数字)9798350354232

ISBN: (纸本)9798350354249

The use of host intrusion detection systems shows promising results in detecting APT campaigns due to the use of systems logs as source data to get more information about system environment. However, dealing with the increase of logs in time while tracking the execution context is a challenge for security analysts. Therefore, this work presents backbone extraction as a crucial preprocessing step, filtering out irrelevant logs. As the logs are modeled as provenance graphs, we discard spurious edges to detect residuals with distinctive node and edge distributions that indicate security threats. By applying our methodology to state-of-the-art benchmark datasets, we observed an increase in the performance of one-class classifiers by up to 62% on F1-score and 48% on recall in the Streamspot dataset and by up to 40% on F1-score and 33% on recall in the DARPA3 THEIA dataset. Moreover, our results indicate mitigation of the dependency explosion problem and underscore the ability of our methodology to improve the detection landscape by shrinking graph sizes without losing essential aspects to characterize attacks.

关键词： Computers Filtering Image edge detection Prevention and mitigation Noise Intrusion detection Benchmark testing Explosions Security

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：