检索结果-内蒙古大学图书馆

A novel image-based approach for interactive characterization of rock fracture spacing in a tunnel face

Journal of Rock Mechanics and Geotechnical engineering 2022年第4期14卷 1077-1088页

作者： Jiayao Chen Yifeng Chen Anthony G.Cohn Hongwei Huang Jianhong Man Lijun Wei Key Laboratory of Geotechnical and Underground Engineering of Ministry of Education Department of Geotechnical EngineeringTongji UniversityShanghai200092China School of Computing University of LeedsLeedsLS29JTUK Department of Computer Science and Technology Tongji UniversityShanghai211985China School of Civil Engineering Shandong UniversityJinan250061China Luzhong Institute of Safety Environmental Protection Engineering and Materialsand School of Mechanical and Electrical EngineeringQingdao University of Science and TechnologyQingdao255000China

This paper presents a novel integrated method for interactive characterization of fracture spacing in rock tunnel *** main procedure includes four steps:(1)Automatic extraction of fracture traces,(2)digitization of trace maps,(3)disconnection and grouping of traces,and(4)interactive measurement of fracture set spacing,total spacing,and surface rock quality designation(S-RQD)*** evaluate the performance of the proposed method,sample images were obtained by employing a photogrammetrybased scheme in tunnel *** were then conducted to determine the optimal parameter values(*** threshold,angle threshold,and number of fracture trace grouping)for characterizing rock fracture *** applying the identified optimal parameters involved in the model,the proposed method could lead to excellent qualitative results to a new tunnel *** perform a quantitative analysis,three methods(***,straightening,and the proposed method)were employed in the same study and comparisons were *** proposed method agrees well with the field measurement in terms of the maximum and average values of measured spacing ***,the proposed method has reasonably good accuracy and interactive advantage for estimating the ultimate fracture spacing and *** can be a possible extension of existing methods for fracture spacing characterization for two-dimensional(2D)rock tunnel faces.

关键词： Fracture spacing Rock tunnel Image processing Fracture set grouping

来源：评论

学校读者我要写书评

暂无评论

Automatic Skull Shape Completion of Defective Skulls Using Transformers for Cranial Implant Design

引用

Procedia Computer science 2024年 235卷 3305-3314页

作者： Resmi S RimjhimPadam Singh Kannappan Palaniappan Department. of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita VishwaVidyapeetham India Dept. of Electrical Engineering and Computer Science University of Missouri Missouri USA

Cranioplasty is a surgical method that restores the aesthetic and protecting function of a damaged skull by implanting material into the damaged *** and accurate design of patient specific cranial implants is very much required in the process of *** time consumption for designing and manufacturing of patient specific cranial implant has become an obstruction for cranioplasty procedures. Hence, a fully automatic and fast design of cranial implant becomes very important. The cranial implant design processmainly comprises of two steps. The former step concentrates on the automatic skull shape completion of defective skulls to fill the gaps and the cracks created in the skull. While the second step computes the difference between defective input and the completed skull for generating the implant. Currently computer aided design is used for the skull shape completion task which is a time consuming process. The application of deep learning techniques may result to faster and accurate skull shape completionwhich can be used for the design of patient specific cranial implants. This work proposes a novel approach combining 3D U-Net with Transformers for the automatic skull shape completion *** are using a vision transformer in the encoder section of the 3D U-Net architecture to consider the volumetric skull reconstruction as sequence- to-sequence prediction problem and to efficaciously grasp the global contextual information. The work also compares its performance with the famous variants of 3D U-Net deep network model namely, 3D U-Net and 3D U-Net with attention. From the values resulted for the dice coefficient metric it is clear that the proposed 3D U-Net with transformer approach performs better than the other two models on test images.

关键词： Cranioplasty 3DU-Net 3DU-Net with Attention 3DU-Net with Transformer Dice coefficient

来源：评论

学校读者我要写书评

暂无评论

Personalized Smart Grocery Delivery with IoT Technology Using Collaborative Filtering Algorithms 11

Personalized Smart Grocery Delivery with IoT Technology Usin...

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Kulkarni, Shirish Dattatreya Raman, Ramakrishnan Sutaria, Kruti Kamal Mishra, Nilamadhab Sujatha, S. Nandagopal, V. Maharashtra Pune India Maharashtra Pune India Parul Institute of Engineering and Technology Parul University Faculty of Engineering and Technology Gujarat Vadodara India School of Computing Science and Engineering Vit Bhopal University Madhya Pradesh India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Biomedical Engineering Tamil Nadu Chennai India School of Engineering Mohan Babu University Department of Electrical and Electornics Engineering Andrapradesh Tirupathi India

ISBN: (纸本)9798350350357

Personalized suggestions may enhance the use of online food shopping, an already popular and handy service. But data sparsity and scalability problems restrict the current recommendation systems rely on user-based collaborative filtering algorithms. Smart grocery delivery with personalized suggestions is proposed in this system using item-based collaborative filtering algorithms and Internet of Things (IoT) technologies. In the system, smart appliances like fridges and scales track food supplies and consumption, and then, according to the user's preferences, they automatically place purchases on internet platforms. It makes use of item-based collaborative filtering algorithms to examine other users' evaluations and purchase histories in order to provide the user with relevant and varied product recommendations. The method is tested on a real-world dataset and contrasted with collaborative filtering methods rely on user input. Techniques outperform the competition in terms of suggestion accuracy, variety, and coverage while simultaneously decreasing delivery time and costs. By implementing our strategy, not only can online grocery shopping be made more enjoyable for users, but it can also spur the growth of e-commerce and the IoT. © 2024 IEEE.

关键词： Food supply

来源：评论

学校读者我要写书评

暂无评论

SSL-WAEIE:Self-Supervised Learning With Weighted Auto-Encoding and Information Exchange for Infrared and Visible Image Fusion

引用

IEEE/CAA Journal of Automatica Sinica 2022年第9期9卷 1694-1697页

作者： Gucheng Zhang Rencan Nie Jinde Cao the School of Information Science and Engineering Yunnan UniversityKunming 650500China the School of Information Science and Engineering Yunnan UniversityKunming 650500 Yunnan Key Laboratory of Intelligent Systems and Computing Kunming 650500and also with the School of AutomationSoutheast UniversityNanjing 210096China the School of Mathematics Southeast UniversityNanjing 210096China Yonsei Frontier Laboratory Yonsei UniversitySeoul 03722South Korea

Dear editor,Infrared and visible image fusion(IVIF)technologies are to extract complementary information from source images and generate a single fused result[1],which is widely applied in various high-level visual ta... 详细信息

关键词： editor SSL Image Exchange

来源：评论

学校读者我要写书评

暂无评论

CrisisHateMM: Multimodal Analysis of Directed and Undirected Hate Speech in Text-Embedded Images from Russia-Ukraine Conflict

CrisisHateMM: Multimodal Analysis of Directed and Undirected...

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Bhandari, Aashish Shah, Siddhant B. Thapa, Surendrabikram Naseem, Usman Nasim, Mehwish Delhi Technological University Department of CSE India Virginia Tech Department of Computer Science United States School of Computer Science The University of Sydney Australia School of Physics Mathematics and Computing The University of Western Australia Australia College of Science and Engineering Flinders University Australia

ISBN: (纸本)9798350302493

Text-embedded images are frequently used on social media to convey opinions and emotions, but they can also be a medium for disseminating hate speech, propaganda, and extremist ideologies. During the Russia-Ukraine war, both sides used text-embedded images extensively to spread propaganda and hate speech. To aid in moderating such content, this paper introduces CrisisHateMM, a novel multimodal dataset of over 4,700 text-embedded images from the Russia-Ukraine conflict, annotated for hate and non-hate speech. The hate speech is annotated for directed and undirected hate speech, with directed hate speech further annotated for individual, community, and organizational targets. We benchmark the dataset using unimodal and multimodal algorithms, providing insights into the effectiveness of different approaches for detecting hate speech in text-embedded images. Our results show that multimodal approaches outperform unimodal approaches in detecting hate speech, highlighting the importance of combining visual and textual features. This work provides a valuable resource for researchers and practitioners in automated content moderation and social media analysis. The CrisisHateMM dataset and codes are made publicly available at https://***/aabhandari/CrisisHateMM. © 2023 IEEE.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Wearable Circularly Polarized SIW Antenna for Off-body Communications

引用

IEEE Antennas and Wireless Propagation Letters 2025年

作者： Gao, Guo-Ping Bai, Jin-Ming Jin, Li-Jun Ma, Ge Wang, Dan Wang, Shi-Chen Hu, Bin Lanzhou University Gansu Provincial Key Laboratory of Wearable Computing School of Information Science and Engineering Lanzhou730000 China

A compact low-profile circularly polarized Substrate Integrated Waveguide (SIW) Antenna for off-body communications is proposed. The antenna is made of felt and conductive fabric to have good wearability. An annulus slot and four rectangular slots are etched on a circular SIW to adjust and combine the TM11 mode of the circular patch with the TM010 mode of the SIW resonant cavity, thereby achieving broadband. To achieve circular polarization, an inclined 45 ° rectangular slot is etched on the circular patch. The measured -3 dB Axial Ratio (AR) bandwidth is 240 MHz (5.31 GHz -5.56 GHz). The average gain in the working band is 7.76 dBi. The low Specific Absorption Ratio (SAR) results also demonstrate that the radiation of the antenna to the human body is within the safe range. © 2002-2011 IEEE.

关键词： Wearable antennas

来源：评论

学校读者我要写书评

暂无评论

The Impact of Backbone Selection in Yolov8 Models on Brain Tumor Localization

SSRN

引用

SSRN 2024年

作者： Ranjbarzadeh, Ramin Crane, Martin Bendechache, Malika School of Computing Faculty of Engineering and Computing Dublin City University Ireland ADAPT Research Centre School of Computer Science University of Galway Ireland

This study investigates the utilization of the You Only Look Once (YOLOv8) deep learning framework for accurately identifying the location of brain tumors in medical imaging. We investigate the effects of model size and pretraining on the accuracy and computational efficiency of tumor detection by utilizing different setups of the YOLOv8 model. These setups include various configurations, ranging from very small to large, and can be pretrained on the COCO dataset or not. The experimental results, carried out on Google Colaboratory using NVIDIA Tesla T4 GPUs, show that pre-trained models often achieve better performance by utilizing the extensive feature representations learned from the COCO dataset, resulting in increased precision in tumor location. The research uncovers a subtle connection between the complexity of the model, pretraining, and the time required for training. It emphasizes the possible advantages and constraints of pretraining for various sizes of models. The results of our study indicate that pretraining improves the performance of models, particularly in smaller ones. However, this benefit becomes less significant as the complexity of the model increases. This study enhances the optimization of deep learning models for medical imaging by suggesting potential improvements in model design and learning techniques. © 2024, The Authors. All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

PAC-MC: An Efficient Password-Based Access Control Framework for Time Sequence Aware Media Cloud

引用

IEEE Transactions on Mobile computing 2025年第7期24卷 5632-5648页

作者： Wang, Haiyan Liu, Penghui Zhong, Xiaoxiong Luo, Fucai Xiao, Bin Yang, Yuanyuan Peng Cheng Laboratory Department of New Networks Shenzhen518000 China Zhejiang Gongshang University School of Computer Science and Technology Hangzhou China Hong Kong Polytechnic University Department of Computing Hong Kong Stony Brook University Department of Electrical and Computer Engineering Stony BrookNY11794 United States

Cloud storage makes it easier for users to access and share data remotely, but it often requires integration with cryptographic technologies to address consumer-oriented applications, such as fine-grained data access, secure data sharing and retrieval. This paper focuses on the fine-grained access problem of media applications based on time sequence, that is, certain critical media applications based on time sequences should ideally be accessible only to authorized clients. The traditional keyword-based searchable encryption (SE) allows effective search and access over encrypted data while preserving data privacy, but most existing solutions do not support temporal access control (i.e., a mechanism that grants access permissions to users within a specified time range). In this paper, we propose PAC-MC, an efficient password-based access control framework for media cloud relying on content control with the time sequence attribute. PAC-MC not only supports multi-keyword search using any monotonic boolean formulas but also allows media owners to control content-encryption keys for different time periods with an updatable password. Furthermore, it supports the self-retrieval of content-encryption keys. In addition, PAC-MC is provably secure under the standard model. Finally, the detailed performance evaluation results and experimental comparisons indicate that PAC-MC is very efficient and outperforms the previous solutions in terms of computation, communication, and storage costs. © 2025 IEEE.

关键词： Media Encryption Access control Cloud computing Servers Passwords Keyword search Copyright protection Streaming media Performance evaluation

来源：评论

学校读者我要写书评

暂无评论

Real-Time Drowsiness Detection System Using Machine Learning 2nd

Real-Time Drowsiness Detection System Using Machine Learning

引用

2nd International Conference on Advanced Communication and Intelligent Systems, ICACIS 2023

作者： Kotiyal, Arnav Kumar, D. K. Santhosh Prasad, M. S. Guru Manjunath, S.R. Chandrappa, S. Prabhu, B. P. Aniruddha Dehradun India Department of Computer Science and Engineering St Joseph Engineering College Karnataka Mangaluru India School of Computing and Information Technology Reva University Bengaluru India Bengaluru India Department of Computer Science and Engineering Graphic Era Hill University Dehradun India

ISBN: (纸本)9783031451201

Road transport is an essential component of human endeavors and activities. On the highway, there are an uncountable number of drivers at all hours of the day and night. Lack of sleep is a problem for people who drive long distances, such as taxi drivers, bus drivers, truck drivers, and anyone who travels long distances by car. The driver’s lack of alertness is to blame for a significant portion of the automobile collisions that take place every day. The experience of sleepiness lowers a driver’s level of alertness, which heightens the risk of being involved in an accident and makes driving more difficult. In this context, the utilization of new technologies in the design and construction of systems that are able to monitor drivers and to assess the amount of concentration that they are giving to the task of driving during the entirety of the driving process is essential. Therefore, in order to stop these incidents from happening, we are going to design a system with Python, OpenCV, and Keras that will notify the driver if he begins to feel tired. The proposed work goal is to develop a sleepiness detection system that can identify when a person’s eyelids are closed for a few seconds at a time. When it determines that the driver is becoming sleepy, this system will sound an alarm. During the course of this work, we will be making use of OpenCV to collect the pictures that are captured by the camera. These images will then be fed into a Deep Learning model, which will determine if the person’s eyes are "open" or "closed." © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

YOLOv4-Powered Traffic Intelligence: From Detection to Optimization

YOLOv4-Powered Traffic Intelligence: From Detection to Optim...

引用

Information Technology, Electronics and Intelligent Communication Systems (ICITEICS), IEEE International Conference on

作者： Sinha Sanjiv Tharunn E M. Baskar Department of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (数字)9798350382693

ISBN: (纸本)9798350382709

The Traffic Analysis System utilizes machine learning for real-time traffic insights at a junction. It provides instant stats like vehicle count, density, and FPS, while summarizing average vehicle crossings, densities, stop times, and identifying peak minutes. Machine learning techniques include object detection, tracking, and lane segmentation. The system offers a user-friendly interface with graphical representations, aiding traffic management decisions. It not only ensures efficient traffic control but also allows for predictive analytics and potential integration with traffic light systems for adaptive signal adjustments. Continuous model training and future enhancements promise improved accuracy and adaptability to evolving traffic scenarios.

关键词： Training Accuracy Refining Machine learning Object detection Traffic control Real-time 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：