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

Diabetic Retinopathy Classification Using A Hybrid and Efficient MobileNetV2-SVM Model

Diabetic Retinopathy Classification Using A Hybrid and Effic...

引用

2020 IEEE Region 10 Conference, TENCON 2020

作者： Taufiqurrahman, Shidqie Handayani, Astri Hermanto, Beni Rio Mengko, Tati Latifah Erawati Rajab Institut Teknologi Bandung Biomedical Engineering Program School of Electrical Engineering and Informatics Bandung Indonesia

ISBN: (纸本)9781728184555

Deep learning has been proposed as one of the automated solutions for diabetic retinopathy (DR) severity classification problem. However, most of the successful deep learning models are based on large convolutional neural network (CNN) architectures, requiring a vast volume of training data as well as dedicated computational resources. In this study, we used MobileNetV2 architecture, which was considered a small-scale architecture (4.2 million trainable parameters), to perform DR classification task in APTOS 2019 dataset (3662 color retinal images). We used the generic MobileNetV2 pre-trained weights from ImageNet as initialization and implemented data augmentation and resampling during training. We further optimized our model by combining it with an SVM classifier, resulting a hybrid and computationally efficient deep learning model, MobileNetV2-SVM. This model obtained quadratic weighted kappa score of 0.925, 85% accuracy, and area under receiving operating characteristic (AUROC) of 1.00, 0.82, 0.94, 0.94, 0.93 for normal, mild, moderate, severe, and proliferative DR classes, respectively;which is better or at least comparable with the larger architecture performance on the same dataset. Our result shows that with proper optimization strategy, a relatively small and generic CNN architecture, can achieve promising DR classification performance, and even outperform the performance of CNN model with larger architecture. © 2020 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Goal-oriented inference of environment from redundant observations

arXiv

引用

arXiv 2023年

作者： Takahashi, Kazuki Fukai, Tomoki Sakai, Yutaka Takekawa, Takashi Informatics Program Graduate School of Engineering Kogakuin University of Technology and Engineering Japan Neural Coding and Brain Computing Unit Okinawa Institute of Science and Technology Japan Brain Science Institute Tamagawa University Japan

The agent learns to organize decision behavior to achieve a behavioral goal, such as reward maximization, and reinforcement learning is often used for this optimization. Learning an optimal behavioral strategy is difficult under the uncertainty that events necessary for learning are only partially observable, called as Partially Observable Markov Decision Process (POMDP). However, the real-world environment also gives many events irrelevant to reward delivery and an optimal behavioral strategy. The conventional methods in POMDP, which attempt to infer transition rules among the entire observations, including irrelevant states, are ineffective in such an environment. Supposing Redundantly Observable Markov Decision Process (ROMDP), here we propose a method for goal-oriented reinforcement learning to efficiently learn state transition rules among reward-related"core states" from redundant observations. Starting with a small number of initial core states, our model gradually adds new core states to the transition diagram until it achieves an optimal behavioral strategy consistent with the Bellman equation. We demonstrate that the resultant inference model outperforms the conventional method for POMDP. We emphasize that our model only containing the core states has high explainability. Furthermore, the proposed method suits online learning as it suppresses memory consumption and improves learning speed. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

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

Need Analysis of Interactive Multimedia Development for Virtual Learning in Pandemic 4

Need Analysis of Interactive Multimedia Development for Virt...

引用

4th International Conference on Electrical, Electronics, informatics, and Vocational Education, ICE-ELINVO 2021

作者： Lempas, J.F. Soenarto, S. Barahama, A.D. Instructional Technology Post-Graduate Program Universitas Negeri Yogyakarta Jalan Colombo 01 Daerah Istimewa Yogyakarta 55281 Indonesia Department of Electronics and Informatics Engineering Education Post-Graduate Program Universitas Negeri Yogyakarta Jalan Colombo 01 Daerah Istimewa Yogyakarta 55281 Indonesia

The pandemic that has not ended has an impact on changing the educational paradigm. Existing conditions demand to continue to use virtual learning. During the epidemic, this study will examine students' demand for interactive multimedia in virtual learning. The interviews reveal that the media that teachers provide in virtual learning during this pandemic has limits. Data was gathered through interviews and questionnaires given to teachers and students. The student requirements questionnaire reveals that interactive multimedia is the most effective instructional medium for pupils. This study is part of a larger investigation of the evolution of multimedia learning during a pandemic. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Students

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

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

A Comparison of Multi Class Support Vector Machine vs Deep Convolutional Neural Network for Brain Tumor Classification

A Comparison of Multi Class Support Vector Machine vs Deep C...

引用

International Seminar on Application for Technology of Information and Communication (ISemantic)

作者： Nur Ryan Dwi Cahyo Christy Atika Sari Eko Hari Rachmawanto Cahaya Jatmoko Rabei Raad Ali Al-Jawry Mohamed Ayad Alkhafaji Department of Informatics Engineering University of Dian Nuswantoro Semarang Indonesia Study Program in Informatics Engineering University of Dian Nuswantoro Semarang Indonesia Department Computer Science Northern Technical University Semarang Indonesia Department of Computer Engineering Technology Northern Technical University Mosul Iraq Department of Computer Sciece National University of Science and Technology DhiQar Iraq

Multi SVM has long been one of the popular methods in classification, while DCNN has recently gained significant attention in image processing and pattern recognition. This research evaluates the effectiveness of Multi Class Support Vector Machine (M-SVM) and Deep Convolutional Neural Network (DCNN) techniques in classifying brain tumors. A dataset of 2660 3D medical images with dimensions 227 x 227 x 3; including Glioma, Meningioma, and Pituitary tumors, has been partitioned into distinct sets for both training and testing purposes. DCNN approach achieves excellent accuracy in identifying tumor names, with a training accuracy of 97.8% and 100% success rate in 9 experiments. The Multi SVM method demonstrates relatively good accuracy, with training accuracies ranging from 70% to 90% based on different kernel functions. These findings provide valuable insights for selecting appropriate methods in brain tumor classification and encourage further exploration of hybrid Multi SVM-DCNN approaches to enhance accuracy and reliability.

关键词：

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

Kombucha tea derived from papaya (Carica papaya L.) as a potential functional food: physicochemical parameters, biological activities, and sensory evaluation

引用

International Journal of Food Science and Technology 2024年第10期59卷 7786-7794页

作者： Do, Anh Duy Nguyen, Le Bao Xuyen Pham, Dang Quoc Le, Thang Truong Leya, Mwense Phan Van, Thach Department of Biotechnology NTT Hi-tech Institute Nguyen Tat Thanh University Ho Chi Minh City700000 Viet Nam Department of Life Science College of Natural Sciences Hanyang University Seoul04763 Korea Republic of Faculty of Environmental and Food Engineering Institute of Applied Technology and Sustainable Development Nguyen Tat Thanh University Ho Chi Minh City700000 Viet Nam Smart Medicine and Health Informatics Program National Taiwan University Taipei City10617 Taiwan Biosafety Research Institute and Laboratory of Pathology College of Veterinary Medicine Jeonbuk National University Iksan54896 Korea Republic of

Fermented foods, such as kombucha, have gained popularity due to their rich content of beneficial bioactive compounds. Papaya leaves, known for their abundance of bioactive substances such as alkaloids, flavonoids, and phenolic compounds, have garnered attention for their potential to improve immune function by neutralising free radicals. This study investigates the suitability of papaya leaves and petioles as substrates for kombucha fermentation. Our findings indicate that papaya leaves and petioles were suitable substrates for kombucha fermentation, indicated by the SCOBY mass accumulation during fermentation. The gradual decrease in brix and pH values over a 14 days fermentation period corresponds to sugar metabolism and the accumulation of acetic acid. Additionally, fermentation increases total polyphenol (PPK: 250.07 ± 3.00 mg/L, PLK: 330.87 ± 15.56 mg/L) and total flavonoid content (PPK: 26.67 ± 6.31 mg/L, PLK: 34.44 ± 5.55 mg/L). Moreover, papaya-derived kombucha demonstrates enhanced antibacterial properties and inhibits ⍺-amylase linked to diabetes. Sensory evaluations confirm that papaya kombucha achieves a well-balanced and appealing sensory profile, catering to diverse palates. In summary, papaya leaves and petiole exhibit promise as substrates for kombucha production, offering elevated nutritional value and potential health advantages. © 2024 Institute of Food, Science and Technology (IFSTTF).

关键词： Substrates

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：