检索结果-内蒙古大学图书馆

IEEE International Conference on Industrial Technology (ICIT)

作者： Argemiro Oliveira Marcelo Pellenz Marco Teixeira PPGia-PUCPR Curitiba Pontifícia Universidade Católica do Paraná (PUCPR) Curitiba Parana Brazil PPGIa-PUCPR Curitiba Graduate Program in Informatics (PPGIa/PUCPR) Parana Brazil PPGIa-PUCPR Curitiba Research Group on CyberPhysical Systems Parana Brazil

ISBN: (数字)9798331521950

ISBN: (纸本)9798331521967

This study presents a comprehensive analysis of methods, techniques, and technologies employed in facial emotion recognition in human-robot interaction (HRI). A total of 124 articles were reviewed, selected based on specific criteria, resulting in 80 relevant studies for analysis. Techniques such as CNNs, Transfer Learning, and ViT stand out for their effectiveness, while approaches like HOG and LBP remain relevant in lowcost scenarios. Widely used datasets, such as FER-2013 and CK+, demonstrate robustness, and hardware solutions range from highperformance setups to accessible options like Google Colab. The study concludes by highlighting the importance of multimodal techniques and the potential of approaches such as ViT and MTL, proposing strategies to overcome variability challenges and adapt to real classroom conditions.

关键词： Computer vision Emotion recognition Adaptation models Digital images Transfer learning Human-robot interaction Transformers Robustness Hardware Internet

来源：评论

学校读者我要写书评

暂无评论

An Analysis of UX Based on Users’ Emotional Intention and Values, Both Expressed Through Twitter Posts 1

引用

8th Workshop of Human-Computer Interaction Aspects to the Social Web, WAIHCWS 2017 and the 9th Workshop of Human-Computer Interaction Aspects to the Social Web, WAIHCWS 2018

作者： Furtado, Elizabeth S. Mendes, Marilia S. Oliveira, Denilson C. Lima, Lanna Graduate Program in Applied Informatics University of Fortaleza FortalezaCE Brazil RussasCE Brazil

ISBN: (数字)9783030461300

ISBN: (纸本)9783030461294

Texts written by users are often used in investigations of their experiences using a system. When users write about texts based on their own decisions, the texts are a rich context for User eXperience (UX) evaluation of such systems due to the users’ spontaneity. Usually, UX goals are evaluated in users’ texts, including their perception about the usability of the system. An UX analysis from the perspective of the user’s emotional intent and the expression of their personal or social values in the posts has not yet been performed. In this chapter, we analyzed the UX reported on users’ Twitter posts relating to these two perspectives. We identified significant correlations calculated from posts that express a particular level of emotional intention of the user and a certain social or personal value. All levels of emotion had a significant relationship with at least 2 of the 12 values analyzed. Results showed that these relationships from texts written by users are useful to analyze the UX of the posts. © 2020, Springer Nature Switzerland AG.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Towards a Reliable and Lightweight Onboard Fault Detection in Autonomous Unmanned Aerial Vehicles

Towards a Reliable and Lightweight Onboard Fault Detection i...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Sai Srinadhu Katta Eduardo Kugler Viegas Secure Systems Research Center (SSRC) Technology Innovation Institute (TII) Abu Dhabi United Arab Emirates Graduate Program in Informatics (PPGIa) Pontifícia Universidade Catolica do Paraná (PUCPR) Brazil

This paper proposes a new model for onboard physical fault detection on autonomous unmanned aerial vehicles (UAV) through machine learning (ML) techniques. The proposal performs the detection task with high accuracies and minimal processing requirements while signaling an unreliable ML model to the operator, implemented in two main phases. First, a wrapper-based feature selection is performed to de-crease the feature extraction computational costs, coped with a classification assessment technique to identify ML model unreliability. Second, physical UAV faults are signaled through a multi-view rationale that evaluates a variety of UAV sensors while triggering alerts based on a sliding window scheme. Experiments performed on a real quadcopter UAV with a broken propeller use case shows the proposal's feasibility. Our model can decrease the false-positive rates up to only 0.4%, while also decreasing the computational costs by at least 43 % when compared to traditional techniques. Notwithstanding, it can identify ML model unreliability, signaling the UAV operator when model fine-tuning is needed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

How Does the Composition and Configuration of Green Space Influence Urban Noise?: A Systematic Literature Review

引用

Current Landscape Ecology Reports 2024年第4期9卷 73-87页

作者： Stuhlmacher, Michelle Woods, Joshua Yang, Liping Sarigai, Sarigai Department of Geography and GIS DePaul University Chicago USA Sustainable Urban Development Graduate Program DePaul University Chicago USA GeoAIR Lab Department of Geography and Environmental Studies University of New Mexico Albuquerque USA Center for the Advancement of Spatial Informatics Research and Education (ASPIRE) University of New Mexico Albuquerque USA

The attenuation of anthropogenic noise is an often overlooked benefit of incorporating green space into the urban built environment. High levels of noise exposure pose a significant health risk to urban dwellers, but vegetation can both physically block and absorb noise, as well as lower perceived noise levels. To advance understanding on how green space can be leveraged for reducing urban noise, we conduct a systematic literature review on the composition and configuration of urban green space and its relationship to anthropogenic noise levels in cities. We find that the literature is in agreement that green space composition and configuration contributes to decreased noise levels in a variety of ways: greater total area, larger patches, taller trees, and deeper vertical vegetation were associated with greater noise reductions. Furthermore, clustered sets of green space patches and less compact individual patches were linked with lower noise levels. The review was conducted following PRISMA guidelines and the reviewed articles are summarized in an interactive web-app to make the information accessible to urban policymakers and residents seeking to design green spaces that mitigate the negative impacts of urban environmental noise.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of Intention and Use of Audit Tools Linked Archive System (ATLAS) at Public Accounting Firms 7

Analysis of Intention and Use of Audit Tools Linked Archive ...

引用

7th International Conference on Information Management and Technology, ICIMTech 2022

作者： Widuri, Rindang Hidayatullah Novianti, Intan BINUS Graduate Program - Master of Accounting Bina Nusantara University Accounting Department Jakarta11480 Indonesia Informatics and Business Institute Darmajaya Faculty of Economics and Business Accounting Department Lampung Bandar Lampung35141 Indonesia PT. Global Tiket Network Finance Department Jakarta10230 Indonesia

ISBN: (数字)9781665450904

ISBN: (纸本)9781665450904

The goal of this study is to explore the influence of performance expectation, effort expectation, social influence, and facilitating conditions on the intention to continue using Audit Tools and Linked Archive System (ATLAS) by the external auditor at a public accounting firm in Indonesia. This study adopted the Unified Theory of Acceptance and Use of Technology. This study collected data from 126 external auditors using the purposive sampling method. The empirical data indicate that performance expectations, effort expectations, and social influence have a substantial impact on continuation intent. Moreover, facilitating conditions have no appreciable positive impact. This study suggests that an accounting firm needs to provide better IT support and improve the quality of information about the parties that can be contacted if there are difficulties and obstacles in using ATLAS. © 2022 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Energy Planning and Utilization in the North Sulawesi Electricity System

Energy Planning and Utilization in the North Sulawesi Electr...

引用

International Conference on Electrical Engineering and informatics, ICEEI

作者： Arif Majiid Nusa Pratama Bagas Maulana Sutardi Irfan Zidny Irvan Lewi Hasanuddin Syarif Hidayat Pradita Octaviandiningrum Hadi Graduate Program PLN-ITB PLN Corporate University Jakarta Indonesia PLN UIP3B Sulawesi Makassar Indonesia Bandung Institute of Technology School of Electrical and Informatics Engineering Bandung Indonesia

Energy sector is one of the contributors to climate change besides forestry, environment, and transportation sectors. Then, the results of the COP 26 in Glasgow meeting states that Indonesia have a target to achieve Net Zero Emission (NZE) by 2060 if there is international support for funding and technology with some note that this project does not interfere with availability and affordability. In achieving the zero-emission target, the government is implementing five main principles, which include increasing the use of new renewable energy (NRE), reducing fossil energy, explore the use of electric vehicles in the transportation sector, increasing the use of electricity in households and industries, and utilizing Carbon Capture and Storage (CCS). In this paper several proposals can be made to further reduce production costs and reduce greenhouse gas emissions in the North Sulawesi system compared to Electricity Supply Business Plan by PLN which is called RUPTL. Two additional scenarios can be used for the proposal, which are addition of geothermal, solar and pump hydro to replace coal power plant and construction of North Sulawesi interconnection with Central Sulawesi. From the simulation results of the cost and carbon emission analysis between three scenarios, the scenario from RUPTL is the cheapest in terms of cost at 3.295 billion USD and the interconnection scenario is the smallest in terms of emissions, with CO 2 emissions reaching 0 Mt.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Battery Energy Storage Systems in Isolated Grids: Novel Approach to Shave Peaks & Optimize Energy Costs

A Comparative Study of Battery Energy Storage Systems in Iso...

引用

International Conference on Power Engineering and Renewable Energy (ICPERE)

作者： Bagas Maulana Sutardi Ariesa Budi Zakaria Ilham Akbar Kevin Marojahan Banjar-Nahor Nanang Hariyanto Graduate Program PLN-ITB PLN Corporate University Jakarta Indonesia School of Electrical Engineering and Informatics Institut Teknologi Bandung (ITB) Bandung Indonesia

ISBN: (纸本)9781665455497

Isolated power systems are typically found in rural areas that are far separated from the power grid. Rapid decrease in BESS (Battery Energy Storage Systems) cost provides new opportunities and preferences for utilities to store cheap energy at low loads and power out that energy at peak loads. BESS is installed to shave or level demand during peak hours in an isolated system can avoid the use of peaking generations mostly coming from oil fuels. Considering the BESS function for peak shaving, the approach is to simulate the unit commitment of different battery sizes at 10 MW, because the use of oil fuels about 10 MW at peak load, so the simulation will be representing the total energy of the battery needed by the system. Based on the simulation, the life cycle cost is significantly greater than the benefit at all power and energy ratings. The purpose of this paper is to demonstrate the comprehensive technical and financial analysis needs to find the optimum battery type and capacity to provide optimum impact and financially benefit the system with an approach to shaving peaks and energy costs. A study-case method is demonstrated by taking an isolated system as the base and BESS performance can accelerate voltage in the subsystem for every substation when discharging at peak load. The simulation results that 10 MW/10 MWh lithium-ion batteries provide the highest benefit compared to the life cycle cost.

关键词： Renewable energy sources Costs Substations Oils Simulation Voltage Power grids

来源：评论

学校读者我要写书评

暂无评论

A deep learning approach to Lung Nodule Growth Prediction using CT image combined with Demographic and image features 23

A deep learning approach to Lung Nodule Growth Prediction us...

引用

7th International Conference on Medical and Health informatics, ICMHI 2023

作者： Li, Ai-Hsien Adams Nguyen, Duc-Khanh Lai, Yen-Jun Chien, Ting-Ying Chiu, Yen-Ling Chan, Chien-Lung Yang, Pan-Chyr Division of Cardiology Far Eastern Memorial Hospital Taipei220 Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan City Taiwan Department of Information Management Yuan Ze University Taoyuan320 Taiwan Department of Radiology Far Eastern Memorial Hospital Taipei220 Taiwan Department of Computer Science and Engineering Yuan Ze University Taoyuan City Taiwan Innovation Center for Big Data and Digital Convergence Yuan Ze University Taoyuan City Taiwan Graduate Institute of Medicine and Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan Taiwan Department of Medical Research Far Eastern Memorial Hospital Taipei Taiwan Innovation Center for Big Data and Digital Convergence Yuan Ze University Taoyuan320 Taiwan Institute of Biomedical Sciences Academia Sinica Taipei106 Taiwan Department of Internal Medicine College of Medicine National Taiwan University Taipei100 Taiwan Center of Genomic Medicine National Taiwan University Taipei100 Taiwan

ISBN: (纸本)9798400700712

Lung cancer remains a significant global public health concern, being the leading cause of cancer-related deaths worldwide. Despite recent medical advancements, the disease still has a high mortality rate, making early detection and treatment critical for improving patient outcomes. Accurate prediction of nodule growth is key to early lung cancer treatment, but current assessments offer unclear indications of future growth, leading physicians to recommend costly and anxiety-provoking follow-up appointments every 3 to 12 months. To address this need, this study develops an ensemble deep learning approach that combines demographic data with existing CT images to predict whether lung nodules will grow, potentially reducing unnecessary examinations and easing the burden on patients. Our study, conducted on 862 patients with 1004 nodules, produced promising preliminary results with Accuracy, Sensitivity, Precision, F1 Score, and AUC of 0.66, 0.66, 0.67, 0.66, and 0.71, respectively. The proposed method provides a promising support system to empower patients to make informed decisions about seeking medical attention and helps physicians facilitate early treatment regimens, leading to improved patient outcomes and potentially saving lives. © 2023 ACM.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Hamiltonian Cycles for Finite Weyl Groupoids

arXiv

引用

arXiv 2023年

作者： Inoue, Takato Yamane, Hiroyuki Mathematics and Informatics Program Graduate School of Science and Engineering University of Toyama 3190 Gofuku Toyama930-8555 Japan Faculty of Science Academic Assembly University of Toyama 3190 Gofuku Toyama930-8555 Japan

Let Γ(W) be the Cayley graph of a finite Weyl groupoid W. In this paper, we show an existence of a Hamitonian cycle of Γ(W) for any W. We exatctly draw a Hamiltonian cycle of Γ(W) for any (resp. some) irreducible W of rank three (resp. four). Moreover for the irreducible W of rank three, we give a second largest eigenvalue of the adjacency matrix of Γ(W), and know if Γ(W) is a bipartite Ramanujan graph or not. Copyright © 2023, The Authors. All rights reserved.

关键词： Hamiltonians

来源：评论

学校读者我要写书评

暂无评论

ConvNeXt Model for Breast Cancer Image Classification

ConvNeXt Model for Breast Cancer Image Classification

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Devin Setiawan Andrea Stevens Karnyoto Indo Intan Bens Pardamean Department of Electrical Engineering and Computer Science University of Kansas Lawrence United States Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Department of Informatics Engineering Universitas Dipa Makassar Makassar Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331539603

ISBN: (纸本)9798331539610

Breast cancer is an occurrence of cancer that attacks breast tissue and is the most common cancer among women worldwide, affecting one in eight women. In this modern world, breast cancer image classification simplifies the process of analyzing, providing objective and accurate results. By leveraging machine learning algorithms and computer vision techniques, we developed breast cancer detection. The dataset is histopathology dataset from BreakHis and UNHAS Hospital. We chose the ConvNeXt-Tiny model then modified the classifier head as the proposed method. Before the dataset is processed by the model, we augment the images by applying random horizontal and vertical flips, adjustments to brightness, contrast, saturation, and hue using color jitter. The augmentation process simulates real-world variance and enhances the model's ability to generalize to unseen data. Our proposed model gained better performance (accuracy, F1-Score) results compared two other techniques to VGG16 and SVM. According to our experiments, the F1-Score for the ConvNeXt-Tiny model with classifier head modification is higher at 0.9516, than the gain for VGG16 at 0.9292, and the gain for the SVM at 0.83.

关键词： Support vector machines Accuracy Head Computational modeling Transfer learning Breast cancer Magnetic heads Data models Reliability Image classification

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：