检索结果-内蒙古大学图书馆

International Conference on Electronics, computers and Artificial Intelligence (ECAI)

作者： Anand Singh Rajawat S.B. Goyal Aarti Goyal Kavita Rajawat Maria Simona Raboaca Chaman Verma Traian Candin Mihaltan School of Computer Science & Engineering Sandip University Nashik India Faculty of Information Technology City University Petaling Jaya Malaysia Mind Intellect Technology Indore India ICSI Energy Department National Research and Development Institute for Cryogenics and Isotopic Technologies Ramnicu Valcea Romania Department of Media and Educational Informatics Faculty of Informatics Eötvös Loránd University Budapest Hungary Faculty of Building Services Technical University of Cluj-Napoca Cluj-Napoca Romania

This study examines how blockchain technology and consensus mechanisms can safeguard and grow the metaverse ecosystem. Blockchain is transparent and decentralized. It is unchangeable, cryptographically verified, and runs without a central authority. Blockchain technology can secure the metaverse and users' data. This study compares blockchain-based consensus algorithms such as POW(PoW), PoS, and PBFT to ensure metaverse safety. These consensus mechanisms provide safe, decentralized transaction verification, waste reduction, and network consensus. Studying blockchain technology's metaverse scaling restrictions and scaling solutions, including sharding, sidechains, and off-chain protocols. These methods increase throughput, parallel computing, and transaction speed. They improve the metaverse's eco-system. Quantitative analysis, simulations, and experiments determine the security and scalability of blockchain-based metaverse consensus processes. Changes will be quantified by measuring transaction speed, network throughput, and resource consumption. This study enables safe, scalable metaverse environments. Blockchain-based consensus mechanisms allow the metaverse to retain user data safely, halt undesirable conduct, and allow users to join without trusting each other. Scalability solutions declutter networks, enabling the metaverse to handle more individuals and transactions. Blockchain-based consensus mechanisms could make the metaverse more secure, private, and scalable. Users will trust each other, create new apps, and be more open to this groundbreaking digital world.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PollenNet: A novel architecture for high precision pollen grain classification through deep learning and explainable AI

引用

Heliyon 2024年第19期10卷 e38596页

作者： Shamrat, F M Javed Mehedi Idna Idris, Mohd Yamani Zhou, Xujuan Khalid, Majdi Sharmin, Sharmin Sharmin, Zeseya Ahmed, Kawsar Moni, Mohammad Ali Department of Computer System and Technology Universiti Malaya Kuala Lumpur 50603 Malaysia School of Business University of Southern Queensland Toowoomba Australia Department of Computer Science and Artificial Intelligence College of Computing Umm Al-Qura University Makkah 21955 Saudi Arabia School of Information Technology Faculty of Science Engineering and Built Environment Deakin University Australia Department of Electrical and Computer Engineering University of Saskatchewan 57 Campus Drive Saskatoon S7N 5A9 SK Canada Group of Bio-photomatiχ Information and Communication Technology Mawlana Bhashani Science and Technology University Santosh Tangail 1902 Bangladesh Health Informatics Research Lab Department of Computer Science and Engineering Daffodil International University Daffodil Smart City (DSC) Birulia Savar Dhaka 1216 Bangladesh AI & Digital Health Technology Artificial Intelligence & Cyber Future Institute Charles Stuart University Bathurst 2795 NSW Australia AI & Digital Health Technology Rural Health Research Institute Charles Stuart University Orange 2800 NSW Australia

Pollen grains play a critical role in environmental, agricultural, and allergy research despite their tiny dimensions. The accurate classification of pollen grains remains a significant challenge, mainly attributable to their intricate structures and the extensive diversity of species. Traditional methods often lack accuracy and effectiveness, prompting the need for advanced solutions. This study introduces a novel deep learning framework, PollenNet, designed to tackle the intricate challenge of pollen grain image classification. The efficiency of PollenNet is thoroughly evaluated through stratified 5-fold cross-validation, comparing it with cutting-edge methods to demonstrate its superior performance. A comprehensive data preparation phase is conducted, including removing duplicates and low-quality images, applying Non-local Means Denoising for noise reduction, and Gamma correction to adjust image brightness. Furthermore, Explainable AI (XAI) is utilized to enhance the interpretability of the model, while Receiver Operating Characteristic (ROC) curve analysis serves as a quantitative method for evaluating the model's capabilities. PollenNet demonstrates superior performance when compared to existing models, with an accuracy of 98.45 %, precision of 98.20 %, specificity of 98.40 %, recall of 98.30 %, and f1-score of 98.25 %. The model also maintains low Mean Squared Error (0.03) and Mean Absolute Error (0.02) rates. The ROC curve analysis, the low False Positive Rate (0.016), and the False Negative Rate (0.017) highlight the reliability and dependability of the model. This study significantly improves the efficacy of classifying pollen grains, indicating an important advancement in the application of deep learning for ecological research. © 2024 The Authors

关键词： Deep learning Explainable AI Image processing Pollen grain classification PollenNet model

来源：评论

学校读者我要写书评

暂无评论

Investigation of the Impact of Height and Bandwidth on Path Loss Exponent of 5G FR1 Wireless Networks at 800, 3500, and 5900 MHz

Investigation of the Impact of Height and Bandwidth on Path ...

引用

Multidisciplinary engineering and Applied Science (ICMEAS), International Conference on

作者： Yusuf Olayinka Imam-Fulani Nasir Faruk Aliyu D. Usman Abubakar Abdulkarim Abdoulie M.S Tekanyi Abdulmalik S. Yaro Emmanuel Alozie Salisu Garba Kayode S. Adewole Abdulkarim A. Oloyede Olugbenga A. Sowande Bashir Abdullahi Baba Abdulwaheed Musa Agbotiname Lucky Imoize Yinusa A. Adediran Hawau I. Olagunju Lawan S. Taura Department of Telecommunication Science University of Ilorin Ilorin Nigeria Department of Electronics and Telecommunication Engineering Ahmadu Bello University Zaria Nigeria Department of Information Technology Sule Lamido University Kafin Hausa Nigeria Directorate of Information and Communication Technology Sule Lamido University Kafin Hausa Nigeria Department of Electrical Engineering Ahmadu Bello University Zaria Nigeria Department of Electrical and Telecommunication Engineering Kampala International University Kampala Uganda Department of Informatics and Qualitative Methods Faculty of Informatics and Management University of Hradec Králové Hradec Králové Czech Republic Department of Software Engineering Sule Lamido University Kafin Hausa Nigeria Department of Computer Science University of Ilorin Ilorin Nigeria Department of Electrical and Computer Engineering Kwara State University Malete Nigeria Institute for Intelligent Systems University of Johannesburg Johannesburg South Africa Department of Electrical and Electronics Engineering University of Lagos Lagos Nigeria Department of Electrical Engineering and Information Technology Institute of Digital Communication Ruhr University Bochum Germany Department of Electrical and Electronics Engineering University of Ilorin Ilorin Nigeria Department of Physics Sule Lamido University Kafin Hausa Nigeria

5G communication systems provide an end-to-end wireless connection to billions of users and devices across the globe. The quality of signals received during radio communication is notably influenced by the behavior of the radio propagation channel. A major parameter used in characterizing this channel is the Path Loss Exponent (PLE). Several works that have estimated and analyzed the PLE mostly considered the effect of distance and carrier frequency. However, the effect of base station antenna height and channel bandwidth on the PLE for 5G networks have not been adequately considered. To address this, the impact of antenna height of base station and channel bandwidth on the PLE within the 5G Frequency Range 1 (FR1) frequencies was investigated in this study, specifically at 800, 3500, and 5900 MHz. The licensed EDX Signal Pro software® with Cirrus high resolution global terrain and clutter data base was utilized to model, simulate and analyze the PLE for Kano City, Nigeria. Results showed that for the tested frequencies, an increase in either base station height or channel bandwidth leads to a significant reduction in the PLE. This study can be utilized by network planning engineers and the wireless research community to further improve network implementation and optimization toward understanding the behavior of signal propagation in 5G networks and beyond.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards living manufacturing systems 53

Towards living manufacturing systems

引用

53rd CIRP Conference on Manufacturing Systems, CMS 2020

作者： Monostori, László Váncza, József Centre of Excellence in Production Informatics and Control Institute for Computer Science and Control Budapest Hungary Department of Manufacturing Science and Engineering Budapest University of Technology and Economics Budapest Hungary

The impact of the forth industrial revolution on the social and natural environment is considered significant and far-reaching, even though the interactions of the human, natural and manufactured assets are less understood, extremely complex and unpredictable. The paper discusses how present days' - so-called cyber-physical - manufacturing systems operate in the fabrics of society and the natural environment. It is underlined that they show and - to an increasing extent - will show features and capabilities reminiscent of living beings and organizations. This view helps to understand how manufacturing interacts with the ecosystem and suggests resolutions for the dilemma of competitive and sustainable manufacturing. © 2020 The Authors.

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

The Potential of Deep Learning to Counter the Matrix Effect for Assessment of Honey Quality and Monoflorality

SSRN

引用

SSRN 2024年

作者： Truong, Hien Thi Dieu Al-Sarayreh, Mahmoud Pullanagari, Reddy Reis, Marlon M. Archer, Richard School of Food and Advanced Technology Massey University Riddet Road Fitzherbert Palmerston North4410 New Zealand Food Informatics AgResearch Massey University Riddet Road Manawatu Tennent Drive Turitea4474 New Zealand Riddet Institute University Avenue Fitzherbert Palmerston North4474 New Zealand Department of Computer Engineering German Jordanian University Amman11180 Jordan

The complexity of biological matrices affects Near-infrared (NIR) signals. Honey, a complex food matrix, changes in chemical and physical properties over time indicating strong matrix effects when capturing NIR spectra. The varied floral sources in most honeys also contribute to this effect. A real dataset of 1656 honey samples spanning eight geographic districts of the North Island of New Zealand captured by NIR hyperspectral camera was analyzed with machine learning and deep learning models to assess mānuka honey quality and identity. One-dimensional neural network (1D-CNN) showed high capacity to accommodate the complexity of the honey matrix, better than did linear machine learning models, particularly for prediction of a trademarked continuous quality score of mānuka honey, known as Unique Mānuka Factor (UMFTM). Monofloral mānuka honey was distinguished well from multi-floral and non-mānuka when classified with 1D-CNN, achieving > 90 % class accuracy, better than conventional classifiers. Interestingly, 1D-CNN models could precisely identify important spectral regions such as Visible (666 - 725 nm) & NIR (991 and 1435 nm) supporting the evaluation of mānuka honey quality and determining botanical origin as Leptospermum scoparium. Both are useful for future model development and application to automated assessment of honey quality and monoflorality before lumped extraction. © 2024, The Authors. All rights reserved.

关键词： Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Passive Object-based Video Authentication Using Stereo Statistical Descriptor on Wavelet Decomposition

Passive Object-based Video Authentication Using Stereo Stati...

引用

2021 International Conference on Information technology, ICIT 2021

作者： Mizher, Manar Abduljabbar Ang, Mei Choo Abdullah, Siti Norul Huda Sheikh Ng, Kok Weng Mazhar, Ahmad A. Mizher, Manal Abd-Aljabbar Faculty of Computer Sciences and Informatics Amman Arab University Amman Jordan Universiti Kebangsaan Malaysia Bangi Malaysia Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Bangi Malaysia Faculty of Engineering University of Nottingham Malaysia Semenyih Malaysia SAE Institute Media Production Department Amman Jordan

ISBN: (纸本)9781665428705

Determining video authenticity has become a challenging task in video forgery detection and localization systems. One of the core difficulties is to extract a suitable feature descriptor. The recent studies on passive object-based video authentication are limited to localize the forged frames in copy-paste/delete object forgery. That is done without considering the object motion interpolation. It performs video authentication on simple videos with a static camera without using dynamic texture. This research work proposes an Action Passive Object-based Video Authentication Algorithm (APOVA). The APOVA consists a new statistical texture descriptor and a forged keyframes localization algorithm to validate video data. The APOVA algorithm has been tested on the Shih-Tang dataset. The experimental results shows that APOVA can obtain the best results in accuracy using the proposed descriptor. In addition, it is able to achieve the best performance in forged keyframes localization with F0.5_score = 0.93 and video authentication with F0.5_score = 0.99. As a result, APOVA based on APOKL is considered suitable algorithm for complex color video authentication, especially for passive object-based video forgery systems. © 2021 IEEE.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Prompting Disentangled Embeddings for Knowledge Graph Completion with Pre-trained Language Model

arXiv

引用

arXiv 2023年

作者： Geng, Yuxia Chen, Jiaoyan Zeng, Yuhang Chen, Zhuo Zhang, Wen Pan, Jeff Z. Wang, Yuxiang Xu, Xiaoliang Powerchina Huadong Engineering Corporation Limited Hangzhou311112 China School of Computer Science Hangzhou Dianzi University Hangzhou310018 China Department of Computer Science The University of Manchester ManchesterM13 9PL United Kingdom HDU-ITMO Joint Institute Hangzhou Dianzi University Hangzhou310018 China College of Computer Science and Technology Zhejiang University Hangzhou310028 China School of Software Technology Zhejiang University Ningbo315048 China School of Informatics The University of Edinburgh EdinburghEH8 9AB United Kingdom

Both graph structures and textual information play a critical role in Knowledge Graph Completion (KGC). With the success of Pre-trained Language Models (PLMs) such as BERT, they have been applied for text encoding for KGC. However, the current methods mostly prefer to fine-tune PLMs, leading to huge training costs and limited scalability to larger PLMs. In contrast, we propose to utilize prompts and perform KGC on a frozen PLM with only the prompts trained. Accordingly, we propose a new KGC method named PDKGC with two prompts — a hard task prompt which is to adapt the KGC task to the PLM pre-training task of token prediction, and a disentangled structure prompt which learns disentangled graph representation so as to enable the PLM to combine more relevant structure knowledge with the text information. With the two prompts, PDKGC builds a textual predictor and a structural predictor, respectively, and their combination leads to more comprehensive entity prediction. Solid evaluation on three widely used KGC datasets has shown that PDKGC often outperforms the baselines including the state-of-the-art, and its components are all effective. Our codes and data are available at https://***/genggengcss/PDKGC. © 2023, CC BY.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Non-Linear Spectral Dimensionality Reduction Under Uncertainty

arXiv

引用

arXiv 2022年

作者： Laakom, Firas Raitoharju, Jenni Passalis, Nikolaos Iosifidis, Alexandros Gabbouj, Moncef Faculty of Information Technology and Communication Sciences Tampere University Tampere Finland The Programme for Environmental Information Finnish Environment Institute Jyväskylä Finland The Department of Informatics Aristotle University of Thessaloniki Greece The Department of Electrical and Computer Engineering Aarhus University Aarhus Denmark

In this paper, we consider the problem of non-linear dimensionality reduction under uncertainty, both from a theoretical and algorithmic perspectives. Since real-world data usually contain measurements with uncertainties and artifacts, the input space in the proposed framework consists of probability distributions to model the uncertainties associated with each sample. We propose a new dimensionality reduction framework, called NGEU, which leverages uncertainty information and directly extends several traditional approaches, e.g., KPCA, MDA/KMFA, to receive as inputs the probability distributions instead of the original data. We show that the proposed NGEU formulation exhibits a global closed-form solution, and we analyze, based on the Rademacher complexity, how the underlying uncertainties theoretically affect the generalization ability of the framework. Empirical results on different datasets show the effectiveness of the proposed framework. © 2022, CC BY.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Generalizable Cervical Cancer Screening via Large-scale Pretraining and Test-Time Adaptation

arXiv

引用

arXiv 2025年

作者： Jiang, Hao Jin, Cheng Lin, Huangjing Zhou, Yanning Wang, Xi Ma, Jiabo Ding, Li Hou, Jun Liu, Runsheng Chai, Zhizhong Luo, Luyang Shi, Huijuan Qian, Yinling Wang, Qiong Li, Changzhong Han, Anjia Chan, Ronald Cheong Kin Chen, Hao Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Tencent AI Lab Shenzhen China Department of Pathology The First Affiliated Hospital Sun Yat-sen University Guangzhou China Center of Obstetrics and Gynecology Peking University Shenzhen Hospital Shenzhen China Institute of Obstetrics and Gynecology Shenzhen PKU-HKUST Medical Center Shenzhen China Shenzhen Key Laboratory on Technology for Early Diagnosis of Major Gynecologic Diseases Shenzhen China Department of Biomedical Informatics Harvard University United States Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Department of Anatomical and Cellular Pathology The Chinese University of Hong Kong Hong Kong Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology Hong Kong HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen China Division of Life Science The Hong Kong University of Science and Technology Hong Kong State Key Laboratory of Molecular Neuroscience The Hong Kong University of Science and Technology Hong Kong

Cervical cancer is a leading malignancy in female reproductive system. While AI-assisted cytology offers a cost-effective and non-invasive screening solution, current systems struggle with generalizability in complex clinical scenarios. To address this issue, we introduced Smart-CCS, a generalizable Cervical Cancer Screening paradigm based on pretraining and adaptation to create robust and generalizable screening systems. To develop and validate Smart-CCS, we first curated a large-scale, multi-center dataset named CCS-127K, which comprises a total of 127,471 cervical cytology whole-slide images collected from 48 medical centers. By leveraging large-scale self-supervised pretraining, our CCS models are equipped with strong generalization capability, potentially generalizing across diverse scenarios. Then, we incorporated test-time adaptation to specifically optimize the trained CCS model for complex clinical settings, which adapts and refines predictions, improving real-world applicability. We conducted large-scale system evaluation among various cohorts. In retrospective cohorts, Smart-CCS achieved an overall area under the curve (AUC) value of 0.965 and sensitivity of 0.913 for cancer screening on 11 internal test datasets. In external testing, system performance maintained high at 0.950 AUC across 6 independent test datasets. In prospective cohorts, our Smart-CCS achieved AUCs of 0.947, 0.924, and 0.986 in three prospective centers, respectively. Moreover, the system demonstrated superior sensitivity in diagnosing cervical cancer, confirming the accuracy of our cancer screening results by using histology findings for validation. Interpretability analysis with cell and slide predictions further indicated that the system’s decision-making aligns with clinical practice. Smart-CCS represents a significant advancement in cervical cancer screening and highlights the potential for generalizable screening in real-word practice across diverse clinical contexts. Copyright ©

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

RECOMED: A Comprehensive Pharmaceutical Recommendation System

arXiv

引用

arXiv 2022年

作者： Zomorodi, Mariam Ghodsollahee, Ismail Martin, Jennifer H. Talley, Nicholas J. Salari, Vahid Plawiak, Pawel Rahimi, Kazem Acharya, U. Rajendra Department of Computer Science Faculty of Computer Science and Telecommunications Cracow University of Technology Krakow Poland Department of Computer Engineering Ferdowsi University of Mashhad Iran The University of Newcastle CallaghanNSW Australia Institute for Quantum Science and Technology Department of Physics and Astronomy University of Calgary Alberta Canada Institute of Theoretical and Applied Informatics Polish Academy of Sciences Gliwice Poland Deep Medicine Nuffield Department of Women’s and Reproductive Health University of Oxford Oxford United Kingdom School of Mathematics Physics and Computing University of Southern Queensland ToowoombaQLD Australia

OBJEctiVES: To build datasets containing useful information from drug databases and recommend a list of drugs to physicians and patients with high accuracy by considering features of a spectrum of people, diseases, and chemicals. METHODS: A comprehensive pharmaceutical recommendation system was designed based on the features of a spectrum of people, diseases, and medicines extracted from two major drug databases, a dataset of patients and drug information. Then the recommendation was given, and the response was analysed using patient and caregiver ratings and the knowledge obtained from drug specifications and interactions. Sentiment analysis was employed by natural language processing approaches in pre-processing, along with neural network-based methods and recommender system algorithms for modelling the system. Patient conditions and medicine features were used for making two models based on matrix factorisation. Then we used drug interaction criteria to filter drugs with severe or mild interactions with other drugs. We developed a deep learning model for recommending drugs by using data from 2304 patients as a training set, and then we used data from 660 patients as our validation set. We used knowledge from critical drug information and combined the model’s outcome into a knowledge-based system with the rules obtained from constraints on taking medicine. RESULTS: The results show that our recommendation system can recommend an acceptable combination of medicines according to the existing real-life prescriptions available. Compared with conventional matrix factorisation, our proposed model improves the accuracy, sensitivity, and hit rate by 26%, 34%, and 40%, respectively. In addition, it improves the accuracy, sensitivity, and hit rate by an average of 31%, 29%, and 28% compared to other machine learning methods. We have open-sourced our implementation in Python. CONCLUSION: Compared to conventional machine learning approaches, we obtained average accuracy, sens

关键词： Recommender systems

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：