检索结果-内蒙古大学图书馆

International Conference on Computational and Characterization Techniques in engineering & Sciences (CCTES)

作者： Umesh Santoshkumar Rathod Sanjose A Thomas Fulsundar Shrikant Maruti Pratima Balasaheb Kadam Harshad Laxman Jadhav Mohammad Jamal Bdair Lean Campus Start-ups (A Part of Mission Catalyst) Mumbai Department of Sociology Sacred Heart College(Autonomous) Thevara Department of Economics Gramonnati Mandalas Arts Commerce & Science College Narayangaon (Pune) Department of Economics Rayat Shikshan Sansthas Mahatma Phule Mahavidyalaya Pimpri Pune Department of Economics Rayat Shikshan Sanstha’s Karmaveer Bhaurao Patil College ( Empowered Autonomous College) Navi Mumbai School of Architecture Computing and Engineering University of East London

ISBN: (数字)9798350364699

ISBN: (纸本)9798350364705

The purpose of this investigation is to investigate the incorporation of underlying literacy (RL) in the process of developing sustainable business models within the context of social entrepreneurship. Traditional methods of developing business models frequently face difficulties in striking a balance between the social impact and the commercial viability of their ideas. The purpose of this study is to present a new framework that makes use of support vector machine techniques to robustly adapt and optimise business strategies, hence ensuring alignment with sustainability pretensions. By utilising RL methods, social enterprises can simulate functional scripts, gain knowledge from feedback received from the real world, and iterate to improve their models to improve both their social value and their financial performance. The paper demonstrates the potential for RL to address difficult decision-making challenges that are vital in social entrepreneurship. It also guides perpetration and offers practical perspectives on the subject. The investigation reveals, via the use of empirical analysis and case studies, how RL may be used to push further successful and sustainable business practices, which will ultimately contribute to the larger goal of producing a positive social impact.

关键词： Support vector machines Adaptation models Technological innovation Scalability Decision making Entrepreneurship Companies Reinforcement learning Internet of Things Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Enhanced Lung Cancer Detection Using CNNs for Accurate and Efficient CT Image Classification

Enhanced Lung Cancer Detection Using CNNs for Accurate and E...

引用

computing, Sciences and Communications (ICCSC), International Conference on

作者： Mohammad Bdair E D Kanmani Ruby Prachi Juyal Rakheeba Taseen A. Abirami A Soujanya School of Architecture Computing & Engineering University of East London London UK Department of ECE Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Allied Science (Mathematics) Graphic Era (Deemed to be University) Dehradun Uttarakhand India School of computer science and Engineering Presidency university Bangalore India Department of Mathematics Sona College of Technology Salem Tamil Nadu India Department of Computer Science and Engineering CVR College of Engineering Ibrahimpatnam (M) Telangana India

ISBN: (数字)9798350353648

ISBN: (纸本)9798350353655

Lung cancer must be detected as early as possible, but it may be difficult with existing methods since they often depend on human judgment and outdated image processing. These techniques take a lot of time and are prone to errors, which produces uneven outcomes. The research provides a unique deep learning-based method for classifying lung nodules from CT images using convolutional neural networks (CNNs). By automating feature extraction and categorization, the suggested technique greatly increases diagnostic precision. The result shows superior performance over existing systems is demonstrated by evaluation measures such as AUC-ROC, accuracy, sensitivity, and specificity. With a training duration of 12 hours, an AUC-ROC of 0.95, accuracy of 92%, sensitivity of 94%, specificity of 90%, and inference speed of 0.5 seconds per scan, the results demonstrate notable improvements in diagnostic efficiency and accuracy. Deep learning has the potential to revolutionize the diagnosis of lung cancer and enhance patient care, as demonstrated by the study.

关键词： Training Accuracy Lungs Computed tomography Lung cancer Sensitivity and specificity Feature extraction Data models Stability analysis Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Boosting the Restoring Performance of Deduplication Data by Classifying Backup Metadata

引用

ACM/IMS Transactions on Data Science 2021年第2期2卷 1–16页

作者： Yang, Ru Deng, Yuhui Zhou, Yi Huang, Ping Department of Computer Science Jinan University Guangzhou510632 China Department of Computer Science Jinan University China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China TSYS School of Computer Science Columbus State University Doimukh Georgia College of Engineering Temple University United States

Restoring data is the main purpose of data backup in storage systems. The fragmentation issue, caused by physically scattering logically continuous data across a variety of disk locations, poses a negative impact on the restoring performance of a deduplication system. Rewriting algorithms are used to alleviate the fragmentation problem by improving the restoring speed of a deduplication system. However, rewriting methods give birth to a big sacrifice in terms of deduplication ratio, leading to a huge storage space waste. Furthermore, traditional backup approaches treat file metadata and chunk metadata as the same, which causes frequent on-disk metadata accesses. In this article, we start by analyzing storage characteristics of backup metadata. An intriguing finding shows that with 10 million files, the file metadata merely takes up approximately 340 MB. Motivated by this finding, we propose a Classified-Metadata based Restoring method (CMR) that classifies backup metadata into file metadata and chunk metadata. Because the file metadata merely takes up a meager amount of space, CMR maintains all file metadata in memory, whereas chunk metadata are aggressively prefetched to memory in a greedy manner. A deduplication system with CMR in place exhibits three salient features: (i) It avoids rewriting algorithms' additional overhead by reducing the number of disk reads in a restoring process, (ii) it increases the restoring throughput without sacrificing the deduplication ratio, and (iii) it thoroughly leverages the hardware resources to boost the restoring performance. To quantitatively evaluate the performance of CMR, we compare our CMR against two state-of-the-art approaches, namely, a history-aware rewriting method (HAR) and a context-based rewriting scheme (CAP). The experimental results show that compared to HAR and CAP, CMR reduces the restoring time by 27.2% and 29.3%, respectively. Moreover, the deduplication ratio is improved by 1.91% and 4.36%, respectively. © 2

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

A Deep-Learning-Based Method for Automated Detection and Characterization of Cracks in Drainage Pipes

SSRN

引用

SSRN 2024年

作者： Yang, Chenhao Zheng, Feifei Kapelan, Zoran Savic, Dragan Pan, Gang Feng, Yu Ma, Yiyi College of Civil Engineering and Architecture Zhejiang University China Department of Water Management Delft University of Technology Netherlands Centre for Water Systems University of Exeter North Park Road ExeterEX4 4QF United Kingdom KWR Water Research Institute Netherlands Faculty of Civil Engineering University of Belgrade Serbia College of Intelligence and Computing Tianjin University China Cartography and Visual Analytics Technical University of Munich Germany

Currently, the interpretation of closed-circuit television images for structural defect analysis of drainage pipes is mostly conducted manually, which is labor-intensive. In this study, an integrated deep-learning-based algorithm is proposed, namely the Crack Detection and Characterization (CDC) method, which can detect and quantify (e.g., length) pipe cracks. The CDC algorithm is verified by images of pipe cracks both artificially created in the laboratory and from real filed inspection. From the results, the CDC algorithm with the DeepLab V3+ crack detection model performs best for both the laboratory and field cases. The results also show the significant effect of the deblurring process in improving the accuracy of the CDC algorithm. The process increases the mean intersection over union (mIoU) of the calculated results by 1.2%. This study offers an innovative way of detection and characterization of drainage pipe cracks, capable of more accurate pipe defect assessment compared with traditional work. © 2024, The Authors. All rights reserved.

关键词： Crack detection

来源：评论

学校读者我要写书评

暂无评论

Automated Detection and Quantification of Sewage Pipe Cracks Using Deep Learning for Urban Water Environment Management

SSRN

引用

SSRN 2024年

Sewage pipe defects can significantly affect urban water environment, like leakage of pollutants through pipe cracks to groundwater. Currently, the detection of sewage pipe defects is mainly through closed-circuit television inspection, which is conducted manually and time-consuming. In this study, an integrated deep-learning-based algorithm is proposed to detect and quantify pipe cracks from images, namely the Crack Detection and Characterization (CDC) method. The method is based on models created in two steps (i) crack detection by semantic segmentation, and (ii) crack length quantification using an innovative algorithm. The CDC algorithm is verified by images both artificially created in the laboratory and from real filed inspection. For both laboratory and field cases, the CDC method performs well in crack identification and length quantification, and exhibits a higher accuracy than other existing models. The results also show the deblurring process can improve the accuracy greatly. This study can contribute to decision-making in sewage pipe maintenance and water environment management by providing an innovative way capable of more efficient and accurate pipe defect assessment compared with traditional labor-intensive work. © 2024, The Authors. All rights reserved.

关键词： Crack detection

来源：评论

学校读者我要写书评

暂无评论

Semantic Data engineering for Intelligent Educational Learning Systems through Process Mining

Semantic Data Engineering for Intelligent Educational Learni...

引用

Digital Ecosystem and Emerging Tools for Education, Future of Educational Innovation-Workshop Series Data in Action:

作者： Kingsley Okoye Syed Islam Usman Naeem Samira Hosseini Writing Lab Institute for Future of Education & College of Arts Technologies and Innovation Tecnologico de Monterrey & University of East London Mexico & London Monterrey UK School of Architecture Computing and Engineering College of Arts Technologies and Innovation University of East London London United Kingdom Writing Lab Institute for Future of Education & School of Engineering and Sciences Tecnologico de Monterrey Monterrey Mexico

Today, the growing technological turnaround from ‘‘big data’’ to ‘‘big analytics’’ has made it essential for process scientists and analysts to leverage more powerful techniques in analyzing and understanding the different types of data and formats, otherwise allied to the notion of‘‘semantic data engineering Technological advancement has provided data mining solutions capable of processing the data/information in formats that are conceptually comprehended by humans and computers in real-time or realworld settings, and facilitating building of systems and applications that inclusively manage the information or data they contain (machine-understandable systems). For this purpose, this study introduced a ‘‘semantic-based process mining’’ technique capable of discovering abstract or useful information or models from event logs of a learning process (educational domain), and then subsequently used to predict users’ patterns through the semantically-inclined modeling and exploration of the discovered process models. Technically, the study focused on improving the results/outcomes of the learning process and mining using the set of proposed algorithms and model that incorporates semantic annotation (labeling), semantic representations (ontology), and semantic reasoning (inference modules or reasoner) of the discovered models. In turn, the outcome of the method shows that data processing and models analyses provided by traditional process mining techniques in education can be enhanced by adding ‘‘semantic information’’ (properties description) to the discovered models or events $\log$ about the processes and domain.

关键词： Analytical models Computational modeling Semantics Knowledge based systems Predictive models Ontologies Data engineering

来源：评论

学校读者我要写书评

暂无评论

Empirical Investigation of Discipline-Specific Skills Required for the Employability of Built Environment Graduates

引用

International Journal of Construction Education and Research 2023年第4期19卷 460-479页

作者： Aliu, John Aghimien, Douglas Aigbavboa, Clinton Oke, Ayodeji Ebekozien, Andrew Temidayo, Osunsanmi Institute for Resilient Infrastructure Systems College of Engineering University of Georgia Athens GA United States School of Art Design and Architecture Faculty of Arts Design and Humanities De Montfort University Leicester United Kingdom CIDB Centre of Excellence Faculty of Engineering and the Built Environment University of Johannesburg Johannesburg South Africa Department of Quantity Surveying Federal University of Technology Akure Akure Nigeria CIDB centre of Excellence University of Johannesburg South Africa Department of Construction Management and Quantity Surveying University of Johannesburg Johannesburg South Africa School of Social Sciences Universiti Sains Malaysia Gelugor Malaysia Department of Quantity Surveying Auchi Polytechnic Auchi Nigeria School of Computing Engineering and Built Environment Edinburgh Napier University United Kingdom

As the world continues to experience significant and dynamic changes, the concept of graduate employability remains a well-discussed subject in the body of knowledge. Consequently, the concept has attracted the interest of educators, policymakers, researchers and graduates themselves. As a vital cog in the employability conversation, the quality of present-day graduates is highly dependent on the effectiveness of training received from higher education institutions. This formal training provides learners with discipline-specific skills (academic skills) and knowledge which helps them obtain a firm foundation in their chosen discipline or profession. This study seeks to unearth the various discipline-specific skills (DSS) that built-environment graduates need to possess to thrive in the labor market after graduation. A quantitative research approach was adopted to achieve this study’s objective with close-ended questionnaires developed and administered to built environment professionals based in the Gauteng province of South Africa. Retrieved data were analyzed using several statistical tools such as percentage, frequency, Mean Item Score, One-Sample T-test and Exploratory Factor Analysis. Findings revealed four clusters highlighting the key DSS required by built environment graduates. These include lifelong learning, hands-on experience, digital literacy and knowledge of the subject area. The outcomes of this study will be beneficial to several stakeholders involved in construction education and employability skills discussion. © 2022 Associated Schools of Construction.

关键词： Built environment construction education discipline-specific skills employability employability skills engineering education graduateness pedagogy

来源：评论

学校读者我要写书评

暂无评论

Predictive Classification of Covid-19: Assessing the Impact of Digital Technologies

Predictive Classification of Covid-19: Assessing the Impact ...

引用

International conference of Electronics, Communication and Aerospace Technology (ICECA)

作者： Bonda Kiran Kumar Anurima Majumdar Saidatul Akmar Ismail Rohit R Dixit Hairani Wahab Md Hafizi Ahsan KL School of Architecture KL Deemed to be University Koneru Lakshmaiah Educational Foundation vaddeswaram Andhra Pradesh Department of Electronics and Communication Engineering Guru Nanak Institute of Technology School of Information Science College of Computing Informatics & Mathematics Universiti Teknologi MARA Shah Alam Malaysia Siemens Healthineers School of Information Science College of Computing Informatics and Mathematics Universiti Teknologi MARA Labuan Faculty of International Finance Universiti Malaysia Sabah

The recent severe outbreak of the disease has been linked to the COVID-19 virus. It is essential for healthcare professionals and individuals with the capacity to provide intensive care to offer clear explanations of this situation. To address this issue, the World Health Organization (WHO) has implemented several measures. The National Emergency Telecritical Care Network (NETCCN) has the capability to assess these actions using digital technologies. This section provides a comprehensive explanation of these developments, and NETCCN has put forth a recommendation. Version 2.0 of this digital health data will be made available; it will significantly enhance potential crises in the future. Artificial Intelligence (AI) is used in the suggested digital prediction approach to gather past data on the infection. Telemetry, sophisticated maintenance robotics, and monitoring intelligence may all be found with this technology. These may be created to incorporate data relevant to various infections. Health experts will coordinate all of these. To maintain sustained preparedness for emergency catastrophe protection, frequent testing should be conducted.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic-based process mining: A conceptual model analysis and framework 10th

Semantic-based process mining: A conceptual model analysis a...

引用

10th International Conference on Innovations in Bio-Inspired computing and Applications, IBICA 2019 and 9th World Congress on Information and Communication Technologies, WICT 2019

作者： Okoye, Kingsley Tecnologico de Monterrey Writing Lab TecLabs Vicerrectoría de Investigación y Transferencia de Tecnología MonterreyNL64849 Mexico School of Architecture Computing and Engineering College of Arts Technologies and Innovation University of East London London United Kingdom

ISBN: (纸本)9783030493387

Semantics has been a major challenge when applying the Process Mining (PM) technique to real-time business processes. In theory, efforts to bridge the semantic gap has spanned the advanced notion of Semantic-based Process Mining (SPM). The SPM devotes its methods to the idea of making use of existing semantic technologies to support the analysis of PM techniques. Technically, the semantic-based process mining is applied through acquisition and representation of abstract knowledge about the domain processes in question. To this effect, this paper demonstrates how semantically focused process modelling and reasoning methods are used to improve the outcomes of PM techniques from the syntactic to a more conceptual level. Also, the work systematically reviews the current tools and methods that are used to support the outcomes of the process mining, and to this end, propose an SPM-based framework that proves to be more intelligent with a higher level of semantic reasoning aptitudes. In other words, this work provides a process mining approach that uses information (semantics) about different activities that can be found in any given process to generate rules and patterns through the method for annotation, conceptual assertions, and reasoning. Moreover, this is done to determine how the various activities that make up the said processes depend on each other or are performed in reality. In turn, the method is applied to enrich the informative values of the resultant models. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

A Machine Vision-Based Person Detection Under Low-Illuminance Conditions Using High Dynamic Range Imagery for Visual Surveillance System

A Machine Vision-Based Person Detection Under Low-Illuminanc...

引用

Smart Technologies in computing, Electrical and Electronics (ICSTCEE), International Conference on

作者： Julie Ann B. Susa Sammy V. Militante Aimee G. Acoba Ryan Soriente Evangelista Luisito Lolong Lacatan Charlemagne G. Laviňa Bartolome T. Tanguilig Dept. of Computer Engineering Southern Luzon State University Lucban Quezon Philippines College of Engineering and Architecture University of Antique Antique Philippines Electronics Eng'g Technology Department Technological University of the Philippines Manila Philippines School of Graduate Studies Sulu State College Sulu Philippines College of Computing and Engineering Pamantasan ng Cabuyao Laguna Philippines

The most difficult component of any computer vision application objects recognition and tracking. Video surveillance is a major study subject in computer vision in a dynamic environment, especially for security purposes. Video surveillance technology is critical in preventing crime, terrorism, and other threats. Several existing technologies can accurately monitor a person's mobility in interior environments. As well as regulated outdoor settings, object recognition and tracking at night, on the other hand, remain significant challenges for visual surveillance. The objects are usually farther away, inconspicuous, and have low brightness against the background. In this paper, detecting objects specifically people under low lighting conditions with the help of deep learning algorithms was used. For applications like in-car cameras and surveillance systems that operate in low light, these algorithms might improve picture identification performance.

关键词： Deep learning Training Visualization Computer vision Heuristic algorithms Computational modeling Lighting

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：