检索结果-内蒙古大学图书馆

4th IEEE Eurasia conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022

作者： Solomons, Cassandra D. Mathew, Ammu Anna Karthikeyan, v. Shanmugasundaram, vivekanandan Thomas, Hannah Mary Sathya, A. Rose, Jeyanth School of Electrical Engineering Vellore Institute of Technology Vellore India Christian Medical College Dept. of Radiation Oncology Vellore India

ISBN: (数字)9781728195797

ISBN: (纸本)9781728195797

Anterior Segment OCT is a valuable tool in providing B scan images of the cornea and anterior segment of the eye. Corneal scarring is a residue of various ocular diseases which include corneal ulcers, trauma and dystrophies. Corneal scarring results in corneal blindness and severe visual disability for the affected patient. Current grades of assessing corneal scarring are purely qualitative in nature. Though these clinical grades (nebula, macula, leucoma) are useful in guiding clinicians in making clinical decisions regarding treatment, they lack precision because of the absence of numeric data. Experimental research involving corneal scarring would greatly benefit from quantitative methods which are amenable to statistical analysis. Purpose: To determine the quantum of corneal scarring by image analysis of Anterior Segment Optical Coherence Tomographic (AS-OCT) vertical and horizontal scans of both the scarred and normal corneas of 32 subjects. Methods: Image processing and pixel analysis of the vertical and horizontal AS-OCT scans were done in the normal and scarred eyes to determine the mean pixel intensity, corneal thickness and quantum of corneal scarring. Results: The mean pixel intensity for scarred corneas was determined to be 126.2 for horizontal and 136.17 for vertical and 100.09 for horizontal, 96.75 for vertical on the normal corneas. The mean corneal thickness on scarred eyes was 204.46 and 217.38 for horizontal and vertical. Whereas on the normal corneas was 202.78 and 201.09 for horizontal and vertical. Quantum of variability for the scarred eyes was 26.11 and 39.42 for horizontal and vertical, respectively. The differences in medians of quantums of three scarred groups were statistically significant. © 2022 IEEE.

关键词： Image analysis

来源：评论

学校读者我要写书评

暂无评论

Development of an Augmented Reality Interface to Aid Astronauts in Extravehicular Activities

Development of an Augmented Reality Interface to Aid Astrona...

引用

IEEE Aerospace conference (AeroConf)

作者： Miller, Lea S. Fornito, Michael J. Flanagan, Riley Kobrick, Ryan L. Embry Riddle Aeronaut Univ 1 Aerosp Blvd Daytona Beach FL 32114 USA Paragon Space Dev Corp 445 Union BlvdSuite 125 Lakewood CO 80228 USA

ISBN: (纸本)9781728174365

NASA's projected return to the lunar surface with the Artemis program opens the possibility for technological developments that maximize human exploration in ways that were unimaginable during the Apollo program. Specifically, the implementation of heads-up displays (HUD) has the potential to greatly increase astronaut performance during extravehicular activities (EvA) by increasing their situational awareness, providing relevant scientific resources, and presenting live personal biometric data that can safeguard mission success and astronaut health. Though they are an excellent mechanism for conveying information without incurring unnecessary physical strain, the implementation of heads-up displays in the vacuum of space presents challenges including: illumination variance;brightness;contrast;interface control mechanisms;and the general volume of data that can be conveyed without inducing cognitive burnout through clutter. To satisfy the desire to improve astronaut performance with HUDs while also accounting for the above design challenges, ALEXEI, short for Augmented Lunar exploration and Extravehicular Interface, was developed in the Embry-Riddle Aeronautical University (ERAU) Spacesuit Utilization of Innovative Technology Laboratory (S.U.I.T. Lab) to be an augmented reality interface that can enhance an astronauts ability to conduct successful, scientifically relevant EvAs on the lunar surface. The resulting deliverable was created for the 2020 NASA SUITS (Spacesuit User Interface Technologies for Students) Challenge and balances features that past and current astronauts have expressed a functional desire for while also being cautious of human limitations in terms of visualizing and synthesizing information. Those features include a simplistic visual appearance, which displays a breadth of information that monitors mission progress, provides detailed instructions of mission tasks, and displays biometric vital signs, while only requiring a minimalistic level of i

关键词： visualization Biometrics (access control) Moon NASA User interfaces Task analysis Usability

来源：评论

学校读者我要写书评

暂无评论

AoI-Aware Resource Allocation for C-v2X Networks via Multi-Agent Reinforcement Learning with Attention

AoI-Aware Resource Allocation for C-V2X Networks via Multi-A...

引用

IEEE conference on vehicular Technology (vTC)

作者： Jiaao Chen Qiang Wang Yiming Liu National Engineering Center for Mobile Network Technologies School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798331517786

ISBN: (纸本)9798331517793

This paper delves into the dynamic resource allocation challenges for spectrum sharing in vehicle-to-Everything (v2X) communication, influenced by the time-varying channel conditions. We concentrate on the dual goals of sub-channel and power allocation in complex v2X environment, underscoring the pivotal role that the Age of Information (AoI) plays in preserving the reliability of safety-critical data across vehicle-to-vehicle (v2v) links. To address the complex interplay between minimizing AoI for v2v links and maximizing the overall capacity for vehicle-to-infrastructure (v2I) links, we introduce a novel approach grounded in multi-agent reinforcement learning. This strategy enables adaptive learning in response to v2X rapidly changing channel conditions, with v2v links conceptualized as agents. These agents employ an actor network to select actions and a critic network to evaluate those actions through Q-values, incorporating observations, actions, and individual contributions via attention mechanisms. Our method is further refined by incorporating maximum entropy to enhance action exploration. Through extensive simulations, we demonstrate that our algorithm allows agents to effectively sample and assess the states of their counterparts, leading to optimized decision-making processes.

关键词： vehicular and wireless technologies vehicle-to-infrastructure vehicular ad hoc networks Reinforcement learning Time-varying channels Information age Stability analysis Resource management Reliability vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

analysis of acid and multi-stage hydraulic fracturing efficiency taking into account geological and field data

Analysis of acid and multi-stage hydraulic fracturing effici...

引用

2021 International conference on IT in Business and Industry, ITBI 2021

作者： Petrova, Larisa v. voronova, Evgeniya v. Gutorov, Alexander Yu Department of Oil and Gaz Field Exploration and Development Ufa State Petroleum Technological University Branch of the University in the City of Oktyabrsky Republic of Bashkortostan Oktyabrsky Russia

Currently, one of the promising methods of increasing oil recovery, as well as the method of well development, is acid and multi-stage hydraulic fracturing of formations in the carbonate deposits of Ural-volga region and terrigenous reservoirs of Western Siberia. The paper is devoted to the evaluation of the effectiveness of hydraulic fracturing at the fields of the Russian Federation in order to further improve their efficiency. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Hydraulic fracturing

来源：评论

学校读者我要写书评

暂无评论

Using Artificial Neural Network in Conjunction with Well Log data to Assess the Permeability Distribution in Fractured Basement Reservoir, BP Oil Field, vietnam Continental Shelf 7th

Using Artificial Neural Network in Conjunction with Well Log...

引用

7th International conference on Geotechnics, Civil Engineering and Structures, CIGOS 2024

作者： viet, An Nguyen Nguyen, Tuan van, Xuan Tran van, Tri Tran Duc, Lan Tran Xuan, Kha Nguyen 268 Ly Thuong Kiet Street District 10 Ho Chi Minh City Viet Nam Vietnam National University Ho Chi Minh City Linh Trung Ward Thu Duc City Ho Chi Minh City Viet Nam Vũng Tàu Viet Nam General Department of Geology and Minerals of Viet Nam Hanoi Viet Nam

Unlike sedimentary rocks, the permeability of fractured basement rock in BP oil field primary derives from dual pore structure and the geometric arrangement of the fracture and vuggy networks. Due to the complication of basement rock’s structure, the "conventional methods" used to assess and identify the permeability distribution of basement rocks are encountered difficulties and remain uncertainties. The permeability measurement from the core analysis is direct and trustful;however, it is not throughout representative for the fractured basement reservoir (FBR). Another reference is the average permeability encountered from production test, and it is strongly based on the effective thickness of the interval-a parameter is still difficult to be determined. In order to determine the permeability distribution, an Artificial Neural Network (ANN) system which 02 phases developed in conjunction with well log curves building the relationships between permeability and well log data. Therefore, the ANN is applied to reduce the uncertainty in identifying the permeability of BP FBR. In addition, each well log curve just expresses an aspect of the permeability;hence the permeability essence is fully described by the combination of multi well log curves. In the BP FBR there are four permeability profile types and the permeability values vary by both area and depth in the whole field with six specific areas. The variation trend decays from West to East and from top to bottom, significantly occurring at Central block and trivially occurring at North East block. According to the statistics, in BP FBR the permeability has a log-normal distribution pattern, the decreasing orders of average permeability in basement blocks are appropriately as: Central Block, North West Block, North Block, South Block, minima at North East Block. The study results by Permeability Profile Types allow to acquire more knowledge on FBR Structure, particularly in BP oil field. © The Author(s), under exclusi

关键词： Oil well logging

来源：评论

学校读者我要写书评

暂无评论

Prediction of Oil Production Using Optimized Gated Recurrent Unit (GRU)

Prediction of Oil Production Using Optimized Gated Recurrent...

引用

Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence (RAEEUCCI), International conference on

作者： venkata Ramana Avula Bala Brahmini Kapavarapu Muhammed Mubashir K Arjun Chandran M v Abhinav Balagopalan Mudavath Somla Naik Department of Petroleum Engineering Godavari Institute of Engineering And Technology (A) Rajamundry Andhra Pradesh India

ISBN: (数字)9798350354539

ISBN: (纸本)9798350354546

Around the world, hundreds of oil wells are undergoing repair, and this number is predicted to stay constant for the foreseeable future. These oil wells must operate safely for the sake of the environment and our way of life. Although it would be easier to forecast anomalies and unwanted events in advance and avert potentially disastrous situations, the intricacy of the issue makes manual prediction challenging. This project proposes a prediction of oil using an optimized gated recurrent unit. Initially, in the data collection process, getting input data for the prediction of oil production. The input data is moved for preprocessing. The dataset is pre-processed in order to handle missing values, data cleaning, and data filtering. Pre-processed data are further moved to the data analysis and exploration process. This procedure, which frequently makes use of data processing techniques, analyzes, investigates, and summarizes data sets' primary features. These data are further split into training and testing using feature selection. Selected features are subsequently classified using the Optimized Gated Recurrent Unit (GRU). Finally, from the classification of RMSE (Root Mean Square Error) and MAE (Mean Absolute Error), R2 score values are accurately predicted. This project is implemented using Python software. The MAE, MSE and RMSE Comparison of the Classification values are listed as 0.0157181852040254, 0.00302712813431332 and 0.0550193432741006 for SvM, ANN and GRU Classier Respectively.

关键词： Support vector machines Training Oils Production Logic gates Predictive models Software

来源：评论

学校读者我要写书评

暂无评论

Transactional Panorama: A Conceptual Framework for User Perception in Analytical visual Interfaces

引用

PROCEEDINGS OF THE vLDB ENDOWMENT 2023年第6期16卷 1494-1506页

作者： Tang, Dixin Fekete, Alan Gupta, Indranil Parameswaran, Aditya G. Univ Calif Berkeley Berkeley CA 94720 USA Univ Sydney Sydney NSW Australia Univ Illinois Champaign IL USA

Many tools empower analysts and data scientists to consume analysis results in a visual interface. When the underlying data changes, these results need to be updated, but this update can take a long time-all while the user continues to explore the results. Tools can either (i) hide away results that haven't been updated, hindering exploration;(ii) make the updated results immediately available to the user (on the same screen as old results), leading to confusion and incorrect insights;or (iii) present old-and therefore stale-results to the user during the update. To help users reason about these options and others, and make appropriate trade-offs, we introduce Transactional Panorama, a formal framework that adopts transactions to jointly model the system refreshing the analysis results and the user interacting with them. We introduce three key properties that are important for user perception in this context: visibility (allowing users to continuously explore results), consistency (ensuring that results presented are from the same version of the data), and monotonicity (making sure that results don't "go back in time"). Within transactional panorama, we characterize all feasible property combinations, design new mechanisms (that we call lenses) for presenting analysis results to the user while preserving a given property combination, formally prove their relative orderings for various performance criteria, and discuss their use cases. We propose novel algorithms to preserve each property combination and efficiently present fresh analysis results. We implement our framework into a popular, open-source BI tool, illustrate the relative performance implications of different lenses, and demonstrate the benefits of the novel lenses and our optimizations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ResNet vs Inception-v3 vs SvM: A Comparative Study of Deep Learning Models for Image Classification of Plant Disease Detection

ResNet vs Inception-v3 vs SVM: A Comparative Study of Deep L...

引用

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE conference on

作者： Md Abu Hanif Md Khadimul Islam Zim Harpreet Kaur Department of Computer Science and Engineering Master’s of Technology Lovely Professional University Phagwara Punjab India Department of Computer Science and Engineering Lovely Professional University Phagwara Punjab India

One of the primary reasons for decreased crop yields is the presence of plant diseases, which also leads to substantial financial losses for farmers and the entire agricultural industry. It is possible to lessen agricultural losses and stop the spread of diseases by detecting and diagnosing plant diseases early. Deep learning models have shown great potential in recent years to detect and diagnose plant diseases using images. This research summarizes and analyses current state-of-the-art plant disease detection systems that use deep learning. Plant diseases considerably influence crop productivity and quality, leading to economic losses for farmers and food shortages for the people. Because of this, there is a demand for deep-learning models to be used in plant disease identification. visual inspection and laboratory testing are time-consuming, expensive, and potentially inaccurate. This is especially true early in disease development. Deep learning approaches may solve these issues by automating photo analysis for fast, accurate diagnosis. ResNet, Inception v3, and other deep learning models can learn data representations through several non-linear transformations. They can recognize complicated picture patterns and diagnose diseases accurately. Using variants, deep learning algorithms can learn data representations. This study compares ResNet with Inception-v3, SvM for image classification using the CIFAR-10 dataset. The results of our trials demonstrate that ResNet surpasses Inception-v3 by a significant margin. ResNet achieved a classification accuracy of 99.81%, Inception-v3 only reached 87%, and SvM with 99.88%. We also compare the two models' performance when subjected to varying hyperparameters and find that ResNet is less affected by tweaking these parameters than Inception-v3.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CrossvQA: Scalably Generating Benchmarks For Systematically Testing vQA Generalization

CrossVQA: Scalably Generating Benchmarks For Systematically ...

引用

conference on Empirical Methods in Natural Language Processing (EMNLP)

作者： Akula, Arjun R. Changpinyo, Soravit Gong, Boqing Sharma, Piyush Zhu, Song-Chun Soricut, Radu Univ Calif Los Angeles Ctr Vis Cognit Learning & Auton Los Angeles CA 90024 USA Beijing Inst Gen Artificial Intelligence BIGAI Beijing Peoples R China Google Res Mountain View CA USA Tsinghua Univ Beijing Peoples R China Peking Univ Beijing Peoples R China

ISBN: (纸本)9781955917094

One challenge in evaluating visual question answering (vQA) models in the cross-dataset adaptation setting is that the distribution shifts are multi-modal, making it difficult to identify if it is the shifts in visual or language features that play a key role. In this paper, we propose a semi-automatic framework for generating disentangled shifts by introducing a controllable visual question-answer generation (vQAG) module that is capable of generating highly-relevant and diverse question-answer pairs with the desired dataset style. We use it to create CrossvQA, a collection of test splits for assessing vQA generalization based on the vQA2, vizWiz, and Open Images datasets. We provide an analysis of our generated datasets and demonstrate its utility by using them to evaluate several state-of-the-art vQA systems. One important finding is that the visual shifts in cross-dataset vQA matter more than the language shifts. More broadly, we present a scalable framework for systematically evaluating the machine with little human intervention.

关键词： visual languages

来源：评论

学校读者我要写书评

暂无评论

Development of E-learning Software for Aluminum Alloy Bending Experiment Based on Simulation Technology

Development of E-learning Software for Aluminum Alloy Bendin...

引用

Computer Science, Engineering, and Education (CSEE), International conference on

作者： Shang Wang Xing Mao Yajuan Zhang School of Automotive Engineering Beijing Polytechnic Beijing China Institute of Engineering Technology University of Science and Technology Beijing Beijing China College of Automation Engineering Beijing Polytechnic Beijing China

ISBN: (数字)9798350376852

ISBN: (纸本)9798350376869

This study developed a simulation-based E-learning software to enhance the learning outcomes of aluminum alloy bending experiments for engineering mechanics students. The bending process was modeled using simulation software on a server infrastructure. Mises stress contour plots generated from the simulations were incorporated into an E-learning application developed using C# for educational purposes. The findings demonstrate the software’s effective impact on improving comprehension. visual materials such as stress distribution diagrams significantly enhanced learners’ understanding of abstract concepts. The software also led to notable increases in learner enthusiasm and interest in the subject. Post-experiment surveys showed 89.47% and 94.87% acceptance rates respectively, indicating the value of supplementing traditional teaching with digital resources. Overall, incorporating simulation technologies addresses scarcity of such materials and warrants further exploration. This research emphasizes the benefits of integrating simulation-based E-learning in mechanics education and lays the foundation for optimizing future educational experiences through innovative digital-focused approaches.

关键词： Surveys visualization Electronic learning data analysis Education Bending Aluminum alloys

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：