检索结果-内蒙古大学图书馆

Journal of Network Intelligence 2024年第1期9卷 474-491页

作者： Zhao, Yu-Hang Tang, Zhen He, Zhong-Jun School of Art and Design Shanghai University of Engineering Science Shanghai201620 China School of Computer Science Taylor’s University Selangor 47500 Malaysia

In the three-dimensional modeling technology, it is very difficult to draw all plants accurately and carefully. The current level of computer software and hardware is far from meeting the requirements. In addition, many application fields require realtime rendering, so we must make the necessary balance between accuracy and complexity. Therefore, in order to solve the above problems, a fast and realistic intelligent generation method of plant landscaping based on deep learning is proposed. Firstly, Bezier parametric curves are used as vertex control curves to generate trunks, branches and leaves, and various plant entities are generated by combining the diversity of geometric models with the diversity of image textures. Then, based on the half-edge folding algorithm, the low-precision three-dimensional geometric model is optimized by using the bidirectional cyclic network auto-encoder, so as to improve the fidelity and reduce the computational overhead. Finally, in the process of detail level drawing, a preprocessing selection stage is added, and the appropriate parallax measurement coefficient is selected for the scene area of each frame through the calculation of projection value. The experimental results show that compared with other modeling methods, the proposed modeling method realizes the rapid rendering of plants, and shows better performance in frame rate change and execution time. © 2024, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Cervical Cancer Risk Identification with Random Forest Using Web Platform 4

Cervical Cancer Risk Identification with Random Forest Using...

引用

4th International Conference on Electrical, computer, Communications and Mechatronics Engineering, ICECCME 2024

作者： Halim, Giselle Samosir, Ridha Sefina School of Computer Science and Design Kalbis University Jakarta Indonesia

ISBN: (纸本)9798350391183

Cervical cancer continues to be a major public health concern, requiring effective risk assessment tools for early detection and prevention. This study presents a newly developed web application designed to predict cervical cancer risk using machine learning algorithms. The model was developed using secondary data from the UCI Machine Learning repository, including patient behavior, disease history, and diagnostic results from Hospital Universitario de Caracas, Venezuela. Several machine learning models-Random Forest, XGBoost, AdaBoost, Gradient Boost, and SVM-were compared, with Random Forest emerging as the best-performing model. The Random Forest model demonstrated strong performance, achieving 98% accuracy, with 0.73 for recall, 0.89 for precision, and Fl-score of 0.80, an AUC-ROC of 0.85, and a specificity of 0.99, despite the imbalance in the positive class data. Cost-sensitive learning and oversampling methods were employed to address data imbalance. This model was then integrated into a Flask-based web framework, allowing users to assess cervical cancer risk without interacting with the underlying processes. Comprehensive black box testing confirmed the application's reliability and compliance with specified requirements. Unlike previous studies focused solely on data analysis, this research successfully deploys the predictive model as an accessible web application, enhancing usability and providing a practical tool for the general public to efficiently assess cervical cancer risk, thereby supporting early detection and prevention strategies. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Sufficient learning: mining denser high-quality pixel-level labels for edge detection

引用

Neural Computing and Applications 2025年第14期37卷 8245-8260页

作者： Chen, Xiaodiao Yang, Wenya Wu, Wen Tao, Xiuting Mao, Xiaoyang School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China School of Media and Design Hangzhou Dianzi University Hangzhou310018 China Department of Computer Science and Engineering University of Yamanashi Kofu400-8511 Japan

The success of deep neural networks can largely be attributed to large-scale datasets with accurate annotations. In many practical applications, labels are annotated by multiple annotators, resulting in ambiguous labels. To mitigate the impact of such labels, existing deep edge detectors tend only to exploit sparsely reliable samples with high-confident labels by simple voting mechanism. However, lacking sufficient pixel-level learnable samples would severely degrade detection performance. To combat this issue, this work designs a sufficient learning framework for edge detection (SLED) to sufficiently explore reliable samples for model learning, which consists of three stages: sample selection, label refinement, and retraining. Firstly, we propose a sample selection scheme founded on history prediction, which aims to identify more reliable samples and locate unreliable regions containing potentially reliable samples. Secondly, we design an efficient label refinement strategy based on a graph convolutional network (GCN) to propagate reliable label information to unreliable nodes. This strategy can generate "new training targets" with denser, reliable labels for all images. Finally, we retrain the network with these new targets, obtaining a more robust model. Experimental results on three widely used benchmarks show that the proposed detector outperforms all compared SOTA methods. Our code will be released at https://***/wenya1994/SLED. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Pairwise-Semantic Enhancement Hashing for Large-Scale Cross-Modal Retrieval

引用

IEEE Transactions on Multimedia 2025年 27卷 3238-3250页

作者： Wong, Wai Keung Fei, Lunke Qin, Jianyang Zhao, Shuping Wen, Jie He, Zhihao The Hong Kong Polytechnic University School of Fashion and Textiles Laboratory for Artificial Intelligence in Design Hong Kong Hong Kong Guangdong University of Technology School of Computer Science and Technology Guangzhou510006 China School of Computer Science and Technology Shenzhen518055 China

Cross-modal hash learning has drawn widespread attention for large-scale multimodal retrieval because of its stability and efficiency in approximate similarity searches. However, most existing cross-modal hashing approaches employ discrete label-guided information to coarsely reflect intra- and intermodality correlations, making them less effective to measuring the semantic similarity of data with multiple modalities. In this paper, we propose a new heterogeneous pairwise-semantic enhancement hashing (HPsEH) for large-scale cross-modal retrieval by distilling higher-level pairwise-semantic similarity from supervision information. First, we adopt a supervised self-expression to learn a data-specific quantified semantic matrix, which uses real values to measure both the similarity and dissimilarity ranks of paired instances, such that the intrinsic semantics of the data can be well captured. Then, we fuse the label-based information and quantified semantic similarity to collaboratively learn the hash codes of multimodal data, such that both the intermodality consistency and modality-specific features can be simultaneously obtained during hash code learning. Moreover, we employ effective iterative optimization to address the discrete binary solution and massive pairwise matrix calculation, making the HPsEH scalable to large-scale datasets. Extensive experimental results on three widely used datasets demonstrate the superiority of our proposed HPsEH method over most state-of-the art approaches. © 1999-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Adaptive IoT-Based Monitoring System in Edge Network for Aquaponics Ecosystem 3

Adaptive IoT-Based Monitoring System in Edge Network for Aqu...

引用

3rd International Conference on Digital Transformation and Applications, ICDXA 2024

作者： Prasetya, Nyoman Wira Anto, Yuli Azis, Baskoro Budi, Marcelino Hans Setia School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia School of Design Bina Nusantara University Interior Design Department Jakarta Indonesia

ISBN: (纸本)9798350373424

Aquaponics is a modern method of farming and cultivating fish. With the various advantages offered, this method has become popular with the public. Water quality is the key to success in using the aquaponics method. Farmers must monitor water quality regularly and continuously to ensure that water conditions still meet standards as a place for fish to live and contain sufficient nutrients for plant growth. To overcome this problem, an adaptive aquaponics system was created to retrieve and display the data automatically. This system will provide data every minute. The system will be IoT-based and adaptive. Adaptive here means the system can adapt to the state of the existing internet connection. So that the system can be more resilient in overcoming connection problems, and the collected data will not be lost when the system is disconnected from the internet. © 2024 IEEE.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

User Interface (UI) of Singosari Temple Interactive Virtual Reality Touring System 3

User Interface (UI) of Singosari Temple Interactive Virtual ...

引用

3rd International Conference on Digital Transformation and Applications, ICDXA 2024

作者： Sari, Wina Permana Primadani, Tiara Ika Widia Huda, Miranti Nurul Acarya, Hanustavira Guru School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia Interior Design School of Design Bina Nusantara University Jakarta Indonesia Visual and Communication Design School of Design Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798350373424

After the current COVID-19 pandemic, many sectors have been affected, one of which is the tourism sector. The tourism sector is at the bottom of the ranking which has experienced the most drastic decline in income. There is a positive side that can be learned from the post-pandemic conditions, several tourism sectors are starting to innovate with IT technology which has made tourism able to survive to this day. However, unfortunately, this IT technology innovation can only be implemented for tourism and medium to large scale purposes, but for tourism in local and remote areas this cannot be done due to limited human resources, facilities in the temple area and around the temple, lack of technology. support and limited marketing regarding Singosari temple. Especially for heritage tourism such as temple buildings which according to today's millennial children are less interesting to visit, because they think they are outdated and old school. This is the background for researchers to develop the application 'Singosari Temple Interactive Virtual Reality Tour System for Rebranding Heritage Tourism in Malang'. This application aims to preserve Indonesian culture and help rebranding and marketing tourism, especially heritage tourism in Malang, with the help of technology, namely Virtual Reality, in accordance with suggestions from Singosari Temple experts. So it can attract the interest of not only millennial children but also all ages, from domestic to foreign visitors because bilingual languages are available. The results of this paper are that Scrum is very suitable to be implemented in this Virtual Reality research because it supports rapid change and by using the UAT testing method the average user satisfaction is 92.1% (usability aspect 91.52%, information quality aspect 90.97%, and interaction quality aspects 94.06%). © 2024 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Data delivery delay and cross-layer packet size analysis for reliable transmission of Licklider transmission protocol in space networks

引用

science China(Information sciences) 2024年第9期67卷 229-244页

作者： Guannan YANG Ruhai WANG Kanglian ZHAO Wenfeng LI Dong YAN School of Information Engineering Nanjing University of Finance and Economics Drayer Department of Electrical and Computer Engineering Lamar University School of Electronic Science and Engineering Nanjing University Beijing Aircraft Overall Design Department

Delay/disruption tolerant networking(DTN) is proposed as a networking architecture to overcome challenging space communication characteristics for reliable data transmission service in presence of long propagation delays and/or lengthy link disruptions. Bundle protocol(BP) and Licklider Transmission Protocol(LTP) are the main key technologies for DTN. LTP red transmission offers a reliable transmission mechanism for space networks. One of the key metrics used to measure the performance of LTP in space applications is the end-to-end data delivery delay, which is influenced by factors such as the quality of spatial channels and the size of cross-layer packets. In this paper, an end-to-end reliable data delivery delay model of LTP red transmission is proposed using a roulette wheel algorithm, and the roulette wheel algorithm is more in line with the typical random characteristics in space networks. The proposed models are validated through real data transmission experiments on a semi-physical testing platform. Furthermore, the impact of cross-layer packet size on the performance of LTP reliable transmission is analyzed, with a focus on bundle size, block size, and segment size. The analysis and study results presented in this paper offer valuable contributions towards enhancing the reliability of LTP transmission in space communication scenarios.

关键词： Licklider transmission protocol DTN bundle protocol cross-layer packets size space communication

来源：评论

学校读者我要写书评

暂无评论

MeshWGAN: Mesh-to-Mesh Wasserstein GAN with Multi-Task Gradient Penalty for 3D Facial Geometric Age Transformation

引用

IEEE Transactions on Visualization and computer Graphics 2024年第8期30卷 4927-4940页

作者： Zhang, Jie Zhou, Kangneng Luximon, Yan Lee, Tong-Yee Li, Ping The Hong Kong Polytechnic University Department of Computing The School of Design Hong Kong University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China The Hong Kong Polytechnic University School of Design Hong Kong Laboratory for Artificial Intelligence in Design Hong Kong National Cheng-Kung University Department of Computer Science and Information Engineering Tainan70101 Taiwan

As the metaverse develops rapidly, 3D facial age transformation is attracting increasing attention, which may bring many potential benefits to a wide variety of users, e.g., 3D aging figures creation, 3D facial data augmentation and editing. Compared with 2D methods, 3D face aging is an underexplored problem. To fill this gap, we propose a new mesh-to-mesh Wasserstein generative adversarial network (MeshWGAN) with a multi-task gradient penalty to model a continuous bi-directional 3D facial geometric aging process. To the best of our knowledge, this is the first architecture to achieve 3D facial geometric age transformation via real 3D scans. As previous image-to-image translation methods cannot be directly applied to the 3D facial mesh, which is totally different from 2D images, we built a mesh encoder, decoder, and multi-task discriminator to facilitate mesh-to-mesh transformations. To mitigate the lack of 3D datasets containing children's faces, we collected scans from 765 subjects aged 5-17 in combination with existing 3D face databases, which provided a large training dataset. Experiments have shown that our architecture can predict 3D facial aging geometries with better identity preservation and age closeness compared to 3D trivial baselines. We also demonstrated the advantages of our approach via various 3D face-related graphics applications. © 1995-2012 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

In-service performance of emergency shutdown valves and dependent operational relationships in the offshore oil and gas industry

引用

Petroleum 2023年第4期9卷 613-620页

作者： Keith Cameron Andrew Lewis Diogo Montalvao Mohammad Reza Herfatmanesh School of Physics Engineering and Computer ScienceUniversity of HertfordshireUnited Kingdom Department of Design and Engineering Faculty of Science and TechnologyBournemouth UniversityUnited Kingdom

Industrial process plants use emergency shutdown valves(ESDVs)as safety barriers to protect against hazardous events,bringing the plant to a safe state when potential danger is *** ESDVs are used extensively in offshore oil and gas processing plants and have been mandated in the design of such systems from national and international standards and *** paper has used actual ESDV operating data from four mid/late life oil and gas production platforms in the North Sea to research operational relationships that are of interest to those responsible for the technical management and operation of *** first of the two relationships is between the closure time(CT)of the ESDV and the time it remains in the open position,prior to the close *** has been hypothesised that the CT of the ESDV is affected by the length of time that it has been open prior to being closed(Time since the last stroke).In addition to the general analysis of the data series,two sub-categories were created to further investigate this possible relationship for CT and these are“above mean”and“below mean”.The correlations(Pearson's based)resulting from this analysis are in the“weak”and“very weak”*** second relationship investigated was the effect of very frequent closures to assess if this improves the *** operational records for six subjects were analysed to find closures that occurred within a 24 h period of each ***,no discriminating trend was apparent where CT was impacted positively or negatively by the frequent closure *** was concluded that the variance of ESDV closure time cannot be influenced by the technical management of the ESDV in terms of scheduling the operation of the ESDV.

关键词： Emergency Shutdown Valve Safety instrumented systems Closure time IEC-61511

来源：评论

学校读者我要写书评

暂无评论

Central Attention Mechanism for Convolutional Neural Networks

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2024年第10期51卷 1642-1648页

作者： Geng, Y.X. Wang, L. Wang, Z.Y. Wang, Y.G. School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China Automation Design Institute Metallurgical Engineering Technology Co. Ltd. Dalian116000 China

Model performance has been significantly enhanced by channel attention. The average pooling procedure creates skewness, lowering the performance of the network architecture. In the channel attention approach, average pooling is used to collect feature information to provide representative values. By leveraging the central limit theorem, we hypothesize that the strip-shaped average pooling operation will generate a one-dimensional tensor by considering the spatial position information of the feature map. The resulting tensor, obtained through average pooling, serves as the representative value for the features, mitigating skewness during the process. By incorporating the concept of the central limit theorem into the channel attention operation process, this study introduces a novel attention mechanism known as the"Central Attention Mechanism (CAM)." Instead of directly using average pooling to generate channel representative values, the central attention approach employs star-stripe average pooling to normalize multiple feature representative values into a single representative value. In this way, strip-shaped average pooling can be utilized to collect data and generate a one-dimensional tensor, while star-stripe average pooling can provide feature representative values based on different spatial directions. To generate channel attention for the complementary input features, the activation of the feature representation value is performed for each channel. Our attention approach is flexible and can be seamlessly incorporated into various traditional network structures. Through rigorous testing, we demonstrate the effectiveness of our attention strategy, which can be applied to a wide range of computer vision applications and outperforms previous attention techniques. © (2024), (International Association of Engineers). All rights reserved.

关键词： Tensors

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：