检索结果-内蒙古大学图书馆

International Image Processing, Applications and Systems Conference (IPAS)

作者： Mary Linda Panakal Augustine Sotirios Spanogianopoulos Mhd Saeed Sharif Department of Computer Science and Digital Technologies School of Architecture Computing and Engineering University of East London London UK School of Electrical and Mechanical Engineering University of Portsmouth Portsmouth UK

ISBN: (数字)9798331506520

ISBN: (纸本)9798331506537

This paper uses deep learning algorithms including InceptionV2, InceptionV3, DenseNet, MobileNet, and VGG19 to improve skin cancer detection. This research aims to improve skin cancer diagnosis. This work aims to determine the most effective evolutionary metrics-based technique to recognizing skin cancer, which is comparable to other diseases. Ultimately, our paper aims to create a realistic skin cancer detection system that uses the best deep learning algorithm. This discovery might improve medical diagnostics, leading to earlier diagnosis and improved healthcare outcomes.

关键词： Deep learning Machine learning algorithms Image processing Transfer learning Medical diagnosis Reliability Skin cancer Image classification

来源：评论

学校读者我要写书评

暂无评论

A Novel Effectiveness Assessment Framework for Neoadjuvant Chemoradiotherapy of Locally Advanced Rectal Cancer Based on Multi-modal Intelligence

A Novel Effectiveness Assessment Framework for Neoadjuvant C...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Tian, Xiao Sui, Dong Liu, Weifeng Guo, Maozu Luo, Gongning Wang, Kuanquan Beijing Key Laboratory for Intelligent Processing Methods of Architectural Big Data Beijing China School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing China Perceptual Computing Research Center Harbin Institute of Technology Harbin China

ISBN: (纸本)9798350337488

Neoadjuvant chemoradiotherapy (nCRT) is the standard treatment for locally advanced rectal cancer (LARC). With the development of artificial intelligence, an increasing number of studies have begun to explore its application in cancer treatment prediction. However, the prior methods exhibit considerable variability even with slight modifications to the input data, which could potentially undermine the reliability of the results. In this paper, we proposed RP-Net, a novel multi-modal fusion-based framework that combines feature information from magnetic resonance imaging (MRI) and whole slide images (WSI), establishing a relationship to map the therapeutic effectiveness of nCRT for LARC. We investigated the relationship of the tumour region and its periphery tissues, and demonstrated the validity of the proposed framework that involving 11 different combinations of modalities. The experimental results revealed that it has achieved higher prediction accuracy compared to the four intra-categories single-modal combinations and outperformed the two intra-categories multi-modal combinations. When compared to the other four inter-categories multi-modal combinations, the fusion features get accuracy of 2% ∼ 6% improvement respectively. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Development of Bim Object Libraries for Construction Site Modeling: A Parametric Design Methodology

SSRN

引用

SSRN 2024年

作者： Getuli, Vito Bruttini, Alessandro Rahimian, Farzad Pour University of Florence Department of Architecture Florence Italy School of Computing Engineering and Digital Technologies Teesside University United Kingdom

This paper tackles the challenge of standardizing digital reproduction approaches for construction site entities, which is crucial for effective Building Information Modeling (BIM) in site layouts and construction activities planning. We propose a novel workflow and object library creation methodology, informed by a comprehensive review of BIM standards and guidelines, demonstrated through a case study in Italy. Findings include a hierarchical library structure and a six-step workflow for developing informative content, parametric geometries, and support documentation. The resulting library, with 253 object typologies, demonstrates practical applicability. This research addresses the lack of BIM object development standards for construction site entities, offering a vendor-neutral methodology valuable for practitioners and industry stakeholders in BIM-based site layout modeling and activity planning. © 2024, The Authors. All rights reserved.

关键词： Construction industry

来源：评论

学校读者我要写书评

暂无评论

Leveraging Digital Identity and Open Banking Data for Fraud Prevention in the Financial Industry

Leveraging Digital Identity and Open Banking Data for Fraud ...

引用

International Conference on Future Internet of Things and Cloud (FiCloud)

作者： Nada Khalifa Wael Elmedany Saeed Sharif College of Information Technology University of Bahrain Bahrain School of Architecture Computing and Engineering University of East London United Kingdom

ISBN: (数字)9798331527198

ISBN: (纸本)9798331527204

Financial institutions, organizations, and customers face great harm as a result of fraud in the industry. The potential risks associated with fraud schemes are increasing, and preventive actions are essential to reduce their level of impact. In order to combat fraud in the financial industry, this research paper investigates the possibilities of using open banking data and digital identification solutions. Digital identification solutions provide trusted ways to confirm people’s identities by combining technology like biometrics and secure authentication processes. Accurate and secure identification verification is made possible by different technologies such as facial and fingerprint recognition. Users and service providers can establish secure and trusted connections through the use of secure authentication protocols like OpenID Connect and OAuth. By strengthening identity verification procedures, these solutions help prevent fraudulent activity. Financial organizations can identify possible fraud possibilities with the help of open banking data that is made available by third party data analytics providers through APIs. Account specifics, transactional data, and consumer behavior patterns are all included in this data. Financial institutions can detect unusual behavior and possible fraud threats by analyzing this data. Proactive detection and improved fraud prevention tactics are made possible by the integration of open banking data. he objective of this research paper is to examine the effectiveness of these technologies in identifying and preventing fraudulent activities and their overall impact on fraud prevention strategies in the financial industry.

关键词： Open banking Data analysis Consumer behavior Prevention and mitigation Authentication Organizations Market research Stability analysis Fraud Security

来源：评论

学校读者我要写书评

暂无评论

Advancements in Sentiment Analysis: Insights, Innovations and Future Directions

Advancements in Sentiment Analysis: Insights, Innovations an...

引用

International Conference on Future Internet of Things and Cloud (FiCloud)

作者： MhD Saeed Sharif Madhav Theeng Mohammed Swalih Koya Wael Elmedany School of Architecture Computing and Engineering UEL London United Kingdom College of Information Technology University of Bahrain Kingdom of Bahrain

ISBN: (数字)9798331527198

ISBN: (纸本)9798331527204

This paper presents a comprehensive study on sentiment analysis utilizing X data to uncover insights, innovations, and future directions. The study aimed to develop and evaluate machine learning techniques for sentiment classification, addressing challenges such as class imbalance and feature engineering. Methodologically, the research involved rigorous data pre-processing, exploratory data analysis, model training, and evaluation. Preliminary analysis indicated tweet length's limited role in sentiment classification while emphasizing platform-specific linguistics. Data pre-processing encompassed tokenization, cleaning, stemming, and stop word elimination, leading to Count Vectorization. The Bag-of-Words approach transformed text into numerical vectors, facilitating model training. Multiple classifiers were tested, with the random forest classifier emerging superior, boasting 99.92% training and 98.44% validation accuracies. The results demonstrate the promising accuracy and resilience of the machine learning models, with the random forest model emerging as a frontrunner. The study highlights practical implications for commercial entities and policymakers and suggests future research directions, including multi-lingual analysis and further exploration of deep learning methodologies. This paper contributes to understanding and applying sentiment analysis in real-world contexts.

关键词： Training Deep learning Sentiment analysis Analytical models Technological innovation Accuracy Data analysis Data models Numerical models Random forests

来源：评论

学校读者我要写书评

暂无评论

DeST 3.0:A new-generation building performance simulation platform

引用

Building Simulation 2022年第11期15卷 1849-1868页

作者： Da Yan Xin Zhou Jingjing An Xuyuan Kang Fan Bu Youming Chen Yiqun Pan Yan Gao Qunli Zhang Hui Zhou Kuining Qiu Jing Liu Yan Liu Honglian Li Lei Zhang Hong Dong Lixin Sun Song Pan Xiang Zhou Zhe Tian Wenjie Zhang Ruhong Wu Hongsan Sun Yu Huang Xiaohong Su Yongwei Zhang Rui Shen Diankun Chen Guangyuan Wei Yixing Chen Jinqing Peng Building Energy Research Center School of ArchitectureTsinghua UniversityBeijing 100084China School of Architecture Southeast UniversityNanjingJiangsu 210096China School of Environment and Energy Engineering Beijing University of Civil Engineering and ArchitectureBeijing 100044China College of Civil Engineering Hunan UniversityChangshaHunan 410082China School of Mechanical Engineering Tongji UniversityShanghai200092China Beijing Key Lab of Heating Gas SupplyVentilating and Air Conditioning EngineeringBeijing University of Civil Engineering and ArchitectureBeijing 100044China China State Construction Technology Center Beijing 101320China School of Architecture Harbin Institute of TechnologyHarbinHeilongjiang 150090China School of Architecture Xi'an University of Architecture and TechnologyXi'anShaanxi 710055China School of Architecture South China University of TechnologyGuangzhouGuangdong 510641China Institute of Building Environment and Energy China Academy of Building ResearchBeijing 100013China Beijing Key Laboratory of Green Built Environment and Energy Efficient Technology Beijing University of TechnologyBeijing 100124China Key Lab of Built Environment and Energy of Tianjin School of Environmental Science and EngineeringTianjin UniversityTianjin 300350China School of Energy and Power Engineering Nanjing University of Science and TechnologyNanjing 210094China School of Civil Engineering Guangzhou UniversityGuangzhou 510006China Faculty of Computing Harbin Institute of TechnologyHarbinHeilongjiang 150001China Beijing Glory PKPM Technology Co. Ltd.Beijing 100013China Beijing Tangent Software Co. LtdBeijing 100081China Shanghai Huadianyuan Information Technology Co. LtdShanghai200092China Luoyang Hongye Information Technology Co. Ltd.LuoyangHenan 471822China

Buildings contribute to almost 30%of total energy consumption *** building energy modeling programs is of great significance for lifecycle building performance assessment and *** in novel building technologies,the requirements of high-performance computation,and the demands for multi-objective models have brought new challenges for building energy modeling software and *** meet the increasing simulation demands,DeST 3.0,a new-generation building performance simulation platform,was developed and *** structure of DeST 3.0 incorporates four simulation engines,including building analysis and simulation(BAS)engine,HVAC system engine,combined plant simulation(CPS)engine,and energy system(ES)engine,connected by air loop and water loop balancing *** 3.0 offers numerous new simulation features,such as advanced simulation modules for building envelopes,occupant behavior and energy systems,cross-platform and compatible simulation kernel,FMI/FMU-based co-simulation functionalities,and high-performance parallel simulation *** 3.0 has been thoroughly evaluated and validated using code verification,inter-program comparison,and case-study *** 3.0 has been applied in various aspects throughout the building lifecycle,supporting building design,operation,retrofit analysis,code appliance,technology adaptability evaluation as well as research and *** new generation building simulation platform DeST 3.0 provides an efficient tool and comprehensive simulation platform for lifecycle building performance analysis and optimization.

关键词： DeST building performance simulation building energy modeling

来源：评论

学校读者我要写书评

暂无评论

Predicting Shear Capacity of RC Beams Strengthened with NSM FRP Using Neural Networks

Predicting Shear Capacity of RC Beams Strengthened with NSM ...

引用

Innovation and Intelligence for Informatics, computing, and Technologies (3ICT), International Conference o

作者： Ozan Guler Husham Ahmed Ali Abbas Mhd Saeed Sharif Dept. of Engineering and Construction School of Architecture Computing and Engineering UEL London UK Principal- Civil/Structural Engineering Jacobs UK Ltd London UK Department Computer Science and Digital Technologies School of Architecture Computing and Engineering UEL London UK

This research aims to predict the shear capacity of NSM FRP beams using artificial neural network approach. The study investigates the key considerations and the necessary analysis for this prediction. NSM FRP beams are reinforced concrete beams that are strengthened with near-surface mounted (NSM) fiber-reinforced polymer (FRP) composites. Accurately predicting their shear capacity is important for ensuring their safety and reliability in real-world applications. The neural network method is a machine learning approach that is increasingly used in engineering analysis and design. The study explores how this method can be used to predict the shear capacity of NSM FRP beams and what factors should be taken into account in this analysis. The research also discusses the analytical approach required for this prediction, highlighting the necessary steps for obtaining accurate results. Overall, this study provides valuable insights into the use of the neural network for predicting the shear capacity of NSM FRP beams. The findings can help inform future research and practical applications in the field of structural engineering, contributing to the development of safer and more reliable structures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tracking Anti-Vax Social Movement Using AI-Based Social Media Monitoring

IEEE Transactions on Technology and Society

引用

IEEE Transactions on Technology and Society 2022年第4期3卷 290-299页

作者： Sufi, Fahim K. Razzak, Imran Khalil, Ibrahim Federal Government Solution Design and Architecture MelbourneVIC3000 Australia University of New South Wales School of Computer Science and Engineering SydneyNSW2052 Australia Rmit University School of Computing Technologies MelbourneVIC3000 Australia

Anti-Vax social movement possesses a dire threat to governments' aim of mass vaccination. Moreover, by propagating serious misconceptions and misinformation about COVID-19, Anti-Vaxxers directly and indirectly cause harm to the overall health and wellbeing of the society. In addition, the ongoing clashes between Anti-Vaxxers and Pro-Vaxxers have created great social conflicts in recent times. This article proposes an artificial intelligence (AI)-based solution to identify and monitor social groups, such as Anti-Vax and Pro-Vax, in ethical manner. The proposed solution uses AI-based sentiment analysis and named entity recognition (NER) to advice political scientist, social scientists, and policy makers to assess the influence and impact of social groups. The proposed solution was deployed via iOS, Android, and Windows App on a range of platforms integrating publicly available 40 857 Twitter data related to COVID-19 in 55 different languages from 15 June 2021 till 31 December 2021. Our system demonstrated that Anti-Vax and Pro-Vax social movements posted 72% and 65% more negative contents compared to average negative sentiments of global COVID-19 related posts during the monitored period. Moreover, Anti-Vax-related posts with 'Hoax' keyword were found to have the highest level of social impact with 38 849 retweets and highest level of negativity (i.e., sentiment score of 0.87). We found out that Pro-Vax community engages in social conflict with Anti-Vaxxers referring them as ignorant (i.e., average sentiment score 0.91), stupid (i.e., average sentiment score 0.89), and confused (i.e., average sentiment score 0.88). Most importantly, the social conflict detection system reveals possible locations of conflict. © 2020 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A computer-aided speech analytics approach for pronunciation feedback using deep feature clustering

A computer-aided speech analytics approach for pronunciation...

引用

作者： Nazir, Faria Majeed, Muhammad Nadeem Ghazanfar, Mustansar Ali Maqsood, Muazzam Department of Software Engineering University of Engineering and Technology Taxila Taxila Pakistan Department of Data Science University of the Punjab Lahore Pakistan School of Architecture Computing and Engineering University of East London London United Kingdom Department of Computer Science COMSATS University Islamabad Attock Campus Pakistan

Nowadays, the demand for language learning is increasing because people need to communicate with other people belonging to different regions for their business deals, study, etc. During language learning, a lot of pronunciation mistakes occur due to unfamiliarity with a new language and differences in accent. In this paper, we perform speech mistakes analysis using deep feature-based clustering. We proposed two novel methods for speech analysis, one to deal with phonemic errors (confusing phonemes) and the other to deal with the prosodic errors (partially changed pronunciation variation of phones). For accurate and efficient language learning, it is important to learn both phonemic as well as prosodic error corrections. In our first method, we perform speech analysis by combining deep CNN features and clustering algorithm to detect the phonemic errors. We classify the phonemes using K-nearest neighbor, Naïve Bayes, and support vector machine (SVM). We perform experiments on the six most frequently mispronounced confusing pairs of Arabic to handle phonemic errors and achieve an accuracy of 94%. In our second method, we proposed the unsupervised phone variation model (PVM) to detect prosodic errors. In PVM, each phone is extended to represent the different types of pronunciation variation of that phone with different proficiency levels. We use an Arabic dataset of 28 individual phones for speech analysis and provide feedback based on the variation of each phone and achieves an accuracy of 97%. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Integrating Machine Learning with Concrete Science: Bridging Traditional Testing and Advanced Predictive Modelling

Integrating Machine Learning with Concrete Science: Bridging...

引用

International Conference on Innovation and Intelligence for Informatics, computing, and Technologies (3ICT)

作者： Salim Barbhuiya Mhd Saeed Sharif Department of Engineering and Construction University of East London London UK Intelligent Technologies Research Group School of Architecture Computing and Engineering London UK

ISBN: (数字)9798331533137

ISBN: (纸本)9798331533144

This paper thoroughly explores the application of machine learning (ML) in concrete science, bridging traditional testing methods with advanced ML techniques. It begins with an overview of ML fundamentals and their relevance to concrete materials, highlighting ML's transformative potential in enhancing predictive modelling and analysis. The discussion covers various ML techniques, including supervised, unsupervised, and deep learning, along with common algorithms and models used in concrete research. Practical aspects such as data collection methods, preprocessing techniques, and feature engineering specific to concrete science are detailed, illustrating how ML improves the accuracy and efficiency of predicting properties like compressive strength, durability, and workability. The paper also examines challenges such as data quality, model interpretability, and scalability, and discusses future trends, ethical considerations, and the societal impacts of ML applications in advancing sustainable infrastructure.

关键词： Workability Technological innovation Computational modeling Scalability Predictive models Prediction algorithms Market research Informatics Monitoring Testing

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：