检索结果-内蒙古大学图书馆

2nd International Conference on Biospheric Harmony Advanced Research, ICOBAR 2020

作者： Rahutomo, R. Purwandari, K. Sigalingging, J.W.C. Pardamean, B. Information System Department School of Information Systems Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia Database Center Division of BMKG Meteorological Climatological and Geophysical Agency Jakarta10720 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia

After Large-Scale Social Restriction (PSBB) established in Jakarta, a change of air quality was indicated by the citizens. Representatives of Indonesia's Agency for Meteorology, Climatology, and Geophysics (BMKG) supported as the fact that mobility of Jakarta's citizen and commuters were reduced. With utilizing Weather Data Acquisition System managed by BMKG, this research compared fluctuations of Jakarta's air quality during two periods of time: Pre-PSBB and During-PSBB. This study proved that Jakarta's air quality has positively improved compared to the previous year, although in the lower range of unhealthy level. © Published under licence by IOP Publishing Ltd.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Mapping of Smart Economy Research Themes: A Nine-Year Review 8

Mapping of Smart Economy Research Themes: A Nine-Year Review

引用

8th International Conference on ICT for Smart Society, ICISS 2021

作者： Purnomo, Agung Dian Sano, Albert Verasius Nindito, Hendro Madyatmadja, Evaristus Didik Sianipar, Corinthias P. M. Entrepreneurship Department BINUS Business School Undergraduate Program Bina Nusantara University Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia Graduate School of Global Environmental Studies Kyoto University Department of Global Ecology Kyoto606-8502 Japan

ISBN: (纸本)9781665416979

Research on the smart economy as a part of a smart city continues to develop but is limited to one country and/or one field. From a bibliometric review, this study aims to visually study mapping and research trends in the field of the smart economy on an international scale. This study used bibliometric techniques with secondary data from Scopus. Analyze and visualize data using the VOSViewer program and the analyze search results function on Scopus. This study analyzed 125 scientific documents published from 2011 to 2020. According to the research, the Peter the Great St. Petersburg Polytechnic University, Russia, and Mboup, G. had the most active individual scientists and in smart economy research. computer science and Advances in 21st Century Human Settlements were the most studied and disseminated outlet of smart economy research. There was one category map of collaborative researchers from around the world. Based on the identification of a collection of knowledge generated from nine years of publication, this research proposes a grouping of smart economy research themes: Economy, Application of smart cities, Smart technology, Smart cities character, Economy of urban, Education and Smart environment, abbreviated as EASSEES research themes. © 2021 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Unmasking Illusions: Understanding Human Perception of Audiovisual Deepfakes

arXiv

引用

arXiv 2024年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Institute of Information Science Academia Sinica Taipei11529 Taiwan Institute of Information Systems and Applications National Tsing Hua University Hsinchu300044 Taiwan Department of Computer Science National Chengchi University Taipei11529 Taiwan Department of Electrical Engineering Institute of Communications Engineering National Tsing Hua University Hsinchu300044 Taiwan Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan Institute of Information Science Academia Sinica Taipei11529 Taiwan

The emergence of contemporary deepfakes has attracted significant attention in machine learning research, as artificial intelligence (AI) generated synthetic media increases the incidence of misinterpretation and is difficult to distinguish from genuine content. Currently, machine learning techniques have been extensively studied for automatically detecting deepfakes. However, human perception has been less explored. Malicious deepfakes could ultimately cause public and social problems. Can we humans correctly perceive the authenticity of the content of the videos we watch? The answer is obviously uncertain;therefore, this paper aims to evaluate the human ability to discern deepfake videos through a subjective study. We present our findings by comparing human observers to five state-of-the-art deepfake detection models. To this end, we used gamification concepts to provide 110 participants (55 native English speakers and 55 non-native English speakers) with a web-based platform where they could access a series of 40 videos (20 real and 20 fake) to determine their authenticity. Each participant performed the experiment twice with the same 40 videos in different random orders. The videos are manually selected from the FakeAVCeleb dataset. We found that all AI models performed significantly better than humans when evaluated on the same 40 videos. The study also reveals that while deception is not impossible, humans tend to overestimate their detection capabilities. Our experimental results may help benchmark human versus machine performance, advance forensics analysis, and enable adaptive countermeasures. © 2024, CC BY.

关键词： Audiovisual

来源：评论

学校读者我要写书评

暂无评论

Understanding Audiovisual Deepfake Detection: Techniques, Challenges, Human Factors and Perceptual Insights

arXiv

引用

arXiv 2024年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min The Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Institute of Information Science Academia Sinica Taipei11529 Taiwan The Institute of Information Systems and Applications National Tsing Hua University Hsinchu300044 Taiwan The Department of Computer Science National Chengchi University Taipei11529 Taiwan The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu300044 Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan The Institute of Information Science Academia Sinica Taipei11529 Taiwan

Deep Learning has been successfully applied in diverse fields, and its impact on deepfake detection is no exception. Deepfakes are fake yet realistic synthetic content that can be used deceitfully for political impersonation, phishing, slandering, or spreading misinformation. Despite extensive research on unimodal deepfake detection, identifying complex deepfakes through joint analysis of audio and visual streams remains relatively unexplored. To fill this gap, this survey first provides an overview of audiovisual deepfake generation techniques, applications, and their consequences, and then provides a comprehensive review of state-of-the-art methods that combine audio and visual modalities to enhance detection accuracy, summarizing and critically analyzing their strengths and limitations. Furthermore, we discuss existing open source datasets for a deeper understanding, which can contribute to the research community and provide necessary information to beginners who want to analyze deep learning-based audiovisual methods for video forensics. By bridging the gap between unimodal and multimodal approaches, this paper aims to improve the effectiveness of deepfake detection strategies and guide future research in cybersecurity and media integrity. © 2024, CC BY.

关键词： Audiovisual

来源：评论

学校读者我要写书评

暂无评论

Extraction of c- F os Protein Regions from Mouse Brain Slice Images using Multi-channelization, 1 x 1 Convolution and U -Net

Extraction of c- F os Protein Regions from Mouse Brain Slice...

引用

International Symposium on Soft Computing and Intelligent systems (SCIS)

作者： Ziyue Wang Hibiki Okamura Shijie Luo Yu Hayashi Hotaka Takizawa Master's Program in Computer Science University of Tsukuba Tsukuba Japan Ph.D. Program in Humanics International Institute for Integrative Sleep Medicine University of Tsukuba Tsukuba Japan International Institute for Integrative Sleep Medicine University of Tsukuba Tsukuba Japan Institute of Systems and Information Engineering Academic Computing & Communications Center University of Tsukuba Tsukuba Japan

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

This study proposed a novel extraction method of c-Fos protein regions in DAB(3,3‘-diaminobenzidine)-stained mouse brain slice images using the U-Net model combined with the multi-channelization and $1\times 1$ convolution techniques. Our U-Net m odel, called $1\times 1$ conv U-Net, was applied to three DAB- strainedmouse slice images whose resolutions were $1000\mathrm{x}1000$ pixels. The experimental results demonstrated that the $1\times 1$ conv U-Net outperformed the conventional U-Net.

关键词： Proteins Visualization Image resolution Image analysis Convolution Feature extraction Brain modeling Biology Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Preprocessing Techniques for Enhancing Vision-Based Detection System for Tire Sidewall Extraction

Preprocessing Techniques for Enhancing Vision-Based Detectio...

引用

International Seminar on Research of information Technology and Intelligent systems (ISRITI)

作者： Jia Hao Loo Veronica Lestari Jauw Chin Seong Lim Khairul-Rijal Sarmin Nunung Nurul Qomariyah Ahmad Nurul Fajar Department of Mechanical Materials and Manufacturing Engineering University of Nottingham Malaysia Malaysia Continental Tyre Technology Centre Malaysia Petaling Jaya Malaysia Computer Science Department School of Computing and Creative Arts Bina Nusantara University Jakarta Indonesia Information System Management Department BINUS Graduate Program-Master Information Systems Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

This study aims to develop a system for extracting crucial information from tire sidewalls using Optical Character Recognition (OCR). Initially, images of tire were captured manually by smartphone cameras, including Redmi 9T, iPhone 11, and Galaxy S23 Ultra. The captured images are then transferred to a computer for storage. Subsequently, these images were cropped according to the boundaries identified by Hough Circle Transform (HCT). The cropped images were then further pre-processed. During the pre-processing phase, geometrical transformation and image sharpening techniques are applied to enhance the clarity and readability of the text images. The text is then extracted using Google Vision, with the extracted text categorized by size, DOT, brand and pattern. The results indicated that the effectiveness of image pre-processing was constrained by the accuracy of circle detection, which reached a maximum rate of 87.1%. This causes parts of the text to be cut out inaccurately, leading to a suboptimal extraction accuracy of 55.65%. It is also observed that the Redmi 9T camera produced inconsistent results compared to other devices. Specifically, the iPhone 11 and Samsung Galaxy S23 Ultra demonstrated superior extraction accuracies of 69.71% and 66.37%, respectively, whereas the Redmi 9T achieved a lower extraction accuracy of 37.76%.

关键词： Accuracy Optical character recognition Text categorization Lighting Transforms US Department of Transportation Cameras Tires Internet Data mining

来源：评论

学校读者我要写书评

暂无评论

Smart Contract Development Model and the Future of Blockchain Technology 2020

Smart Contract Development Model and the Future of Blockchai...

引用

2020 the 3rd International Conference on Blockchain Technology and Applications

作者： Richard Richard Harjanto Prabowo Agung Trisetyarso Benfano Soewito Information Systems Department School of Information Systems Bina Nusantara University Computer Science Department BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Indonesia Computer Science Department BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Indonesia

ISBN: (纸本)9781450388962

Blockchain has become a mainstream technology in our society in recent years. With its nature of secure decentralization, people can create decentralized applications by developing smart contracts on top of a blockchain platform. With blockchain, technology is still in the developing phase, the smart contract development process in blockchain has its unique complexity and uncertainty. The condition will drive the challenge for any developers to work on this issue. In this research, we determine the smart contract development model in creating decentralized applications. Our proposed model aligned with our findings in the systematic mapping process of this study.

关键词： Decentralized Applications Smart Contract Systematic Mapping Smart Contract Development Blockchain

来源：评论

学校读者我要写书评

暂无评论

Restaurant Customer Feedback Sentiment Analysis using Aspect Embedding Long Short-term Memory Model

Restaurant Customer Feedback Sentiment Analysis using Aspect...

引用

computer Science, information Technology and Engineering (ICCoSITE), International Conference on

作者： Yaya Heryadi Bambang Dwi Wijanarko Dina Fitria Murad Cuk Tho Kiyota Hashimoto Computer Science Department BINUS Graduate Program-Doctor of Computer Science Jakarta Indonesia Computer Science Department BINUS Online Learning Jakarta Indonesia Information Systems Department BINUS Online Learning Jakarta Indonesia Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Prince of Songkla University Phuket Thailand

In the past ten years, there has been a proliferation of unstructured textual data from a variety of fields, allowing for the analysis of the sentiment polarity of the text authors in each of those datasets. To analyze sentiment polarity from unstructured data, machine learning tasks such as aspect-based sentiment analysis are used. The public dataset of restaurant patron feedback was used as the input for this study's empirical results of aspect-based sentiment analysis utilizing the Aspect Embedding Long Short-Term Memory model. The primary experiment's results show that the aspect embedding long short-term memory model can predict aspect sentiment polarization from customer feedback to restaurant service and aspect text representation (aspect text embedding) as input with excellent performance. For example, the Aspect Embedding Long Short-term Memory model, which uses ReLU as its activation function in the Dense layer tends to achieve higher performance (0.97 average accuracies) than the same model equipped with Sigmoid, and Tanh functions which achieve 0.954 and 0.956 average training accuracy respectively.

关键词： Training computer science Sentiment analysis Analytical models Computational modeling Machine learning Predictive models

来源：评论

学校读者我要写书评

暂无评论

Aspect-based Sentiment Analysis using Long Short-term Memory Model for Leveraging Restaurant Service Management

Aspect-based Sentiment Analysis using Long Short-term Memory...

引用

computer Science, information Technology and Engineering (ICCoSITE), International Conference on

In general, the hospitality industry has been acknowledged as a major sector that gives a high contribution to economic development in many countries including Indonesia. For that reason, many initiatives have been implemented to help the growth of the hospitality industry in many countries including Indonesia to rebound from the harsh impact of the Covid-19 Pandemic. One such initiative is improving restaurant services as the main sector of the hospitality industry. This paper presents empirical results of sentiment analysis as a means to assess the quality of restaurant services as the first step to improving service quality. In particular, this study explores the aspect-based sentiment analysis method to identify some aspects of restaurant service which need improvement by learning the polarity of customers toward the restaurant services without having to meet the customers directly. By using the aspect-based sentiment analysis method, the customer sentiments comprising opinions, sentiments, evaluations, attitudes, and emotions from restaurant service can be analyzed using customers’ online reviews as input. The main experiment findings showed that the Long Short-term Memory model can achieve high performance in predicting aspect polarization in restaurant service reviews. Other findings suggest that Sigmoid as an activation function achieved 0.97 average training accuracy and 0.69 average testing accuracy giving a better performance to the model in comparison to ReLU, Tanh, and ELU activation functions.

关键词： Industries Training Economics Sentiment analysis Pandemics Computational modeling Predictive models

来源：评论

学校读者我要写书评

暂无评论

Comparing the Effect of Attention Mechanism and Aspect Embedding on the Performance of Long Short-term Memory Model for Aspect-Based Sentiment Analysis

Comparing the Effect of Attention Mechanism and Aspect Embed...

引用

computer Science, information Technology and Engineering (ICCoSITE), International Conference on

The attention mechanism is one of the key enablers which have positioned transformer models as the state-of-the-art models in Natural Language Processing. By having the attention mechanism, the first version (vanilla) transformer model can retrieve the hidden state but at the same time can maintain a low requirement on the context vector dimension by selectively choosing to which encoder hidden states to give priority attention. The objective of this study is to evaluate the effect of modified Long Short-term Memory models architecture on the model performance as a predictive model. The first model is modified by adding an attention mechanism to its architecture; whilst, the second model is modified by adding additional input to its architecture. The performance of both models is compared by assigning each model the same task: to address the aspect-based sentiment analysis task. The experiment results show that adding an attention mechanism is not significantly increase the performance of the Long Short-term Memory model in comparison to adding input to the same model. In particular, the average training accuracy of the former model is 0.885; whilst, the average training accuracy of the latter model is 0.942.

关键词： Training Analytical models Sentiment analysis Computational modeling Memory architecture Predictive models Transformers

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：