检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Hung Chun Hsu Ting-Le Lin Bo-Jun Wu Ming-Yi Hong Che Lin Chih-Yu Wang Graduate Program of Data Science National Taiwan University and Academia Sinica Taiwan Department of Accounting and Statistics National ChengChi University Taiwan Department of Risk Management and Insurance National ChengChi University Taiwan Department of Electrical Engineering National Taiwan University Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan Research Center for Information Technology Innovation Academia Sinica Taiwan

Graph Neural Networks (GNNs) frequently face class imbalance issues, especially in heterogeneous graphs. Existing GNNs often assume balanced class sizes, which isn’t true in many cases. Applying them directly to imbalanced data can lead to sub-optimal performance. Traditional oversampling methods, while effective, risk overfitting and face difficulties in reintegrating synthetic samples into the original graph. In this study, we introduce Framework of Imbalanced Node Classification on heterogeneous graph neural network with GAN (FincGAN), a new framework that utilizes oversampling techniques to address class imbalance in heterogeneous graphs. Instead of duplicating existing samples, FincGAN employs a Generative Adversarial Network (GAN) to create synthetic samples and uses deep learning-based edge generators to connect them back to the original graph. Our evaluations on spam user detection in the Amazon and Yelp Review datasets show that FincGAN outperforms baseline models in all essential metrics, including F-score and AUC-PRC score, showing its effectiveness in addressing class imbalance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Air Quality Prediction Based on Air Pollution Emissions in the City Environment Using XGBoost with SMOTE

Air Quality Prediction Based on Air Pollution Emissions in t...

引用

International Conference of Computer Science and information technology

作者： Adli A Nababan Sutarman Muhammad Zarlis Erna B Nababan Department of Computer Science Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Department of Mathematics Faculty of Mathematics and Natural Sciences Universitas Sumatera Utara Medan Indonesia Department of Information Systems Management BINUS Graduate Program-Master of Information Systems Management Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798350399080

Air pollution makes it worse in populated regions. Indonesia's major cities are also impacted by air pollution. Due to rising traffic, material consumption by vehicles, industrial growth, land burning, and garbage collection, air quality has altered significantly. Accurate measurement and classification of air quality are required. Results of accurate classification aid in forming governmental regulations. To reach the criteria for livable air quality, we intend to manage controls. Some of the characteristics of air pollution include particulate (PM10) or PM25, sulfides (in the form of SO2), carbon monoxide (CO), ozone (O3), and nitrites (NO2). Using the XGBoost algorithm and synthetic minority oversampling (SMOTE) methods based on the Air Pollution Standard Index (ISPU) category, this study seeks to uncover factors that affect air quality. XGBoost, an ensemble machine learning approach built on a decision tree and applying a gradient reinforcement framework, is the classification algorithm in use. Air quality categorization has been tested and shown to work with the XGBoost algorithm. The dataset used in this study is air quality in 2021 which was collected by the Jakarta Environmental Ministry The proposed classification model will be evaluated using the Repeated k-fold cross-validation method for objective results. The results of the study prove that SMOTE and XGBoost have better performance than using only the XGBoost method in predicting air quality, where the overall accuracy value of SMOTE with XGBoost is 99.60%, The overall precision value is 99.60%, the overall recall value is 99.60% and the overall f1-score is 99.60% and the overall ROC AUC value is 99.96%. The overall SMOTE method with the proposed XGBoost has given better performance in air pollution prediction.

关键词： Machine learning algorithms Urban areas Air pollution Prediction algorithms Particle measurements Regulation Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Model of Sustainable Development Based on FinTech in Financial and Banking Industry: A Mixed-Method Research 3

Model of Sustainable Development Based on FinTech in Financi...

引用

3rd International Conference on Computer and Informatics Engineering, IC2IE 2020

作者： Legowo, Mercurius Broto Subanidja, Steph Sorongan, Fanky Antoneus Information Technology Faculty Institute of Perbanas Information System Study Program Jakarta Indonesia Post Graduate School Institute of Perbanas Master of Management Program Jakarta Indonesia Economic and Business Faculty Institute of Perbanas Accounting Study Program Jakarta Indonesia

ISBN: (纸本)9781728182476

In the past decade, it stated that the discourse on Sustainable Development and the Financial technology(FinTech) role in the financial and banking industries, has attention on researchers, practitioners, regulators, and policymakers. The real problem arises from the discourse on whether FinTech has an effect on sustainable development in the financial and banking industry in Indonesia. This discourse needed to be understood better and more deeply. For credible research results, it is necessary to use a mixedmethod research approach. This research aims to develop a model that will help uncover the phenomenon of FinTech to sustainable development in the Financial and Banking Industry in Indonesia, using mixed methods research. In this study, Exploratory Sequential Mixed Method used as a type of mixedmethod approach. The main results of this study reveal that FinTech, which is influenced by business drivers, has a significant role in sustainable development in the Financial and Banking Industry in Indonesia. The contribution of this research can provide insight and understanding for researchers and practitioners in the financial and banking industry who want to implement a sustainable development model based on FinTech in more depth. © 2020 IEEE.

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Classification machine learning with chromagram and word embedding feature

引用

AIP Conference Proceedings 2025年第1期3223卷

作者： Thoyyibah Ines Heidiani Ikasari Perani Rosyani Wasis Haryono Sofa Sofiana Neny Rosmawarni Information Systems Management Department BINUS Graduate Program-Master of Information System Management Bina Nusantara University Jakarta Indonesia 11480 Information Technology University of Pamulang Banten South Tangerang Indonesia Faculty of Information Technology Veterans National Development University Jakarta Jakarta Indonesia

Indonesia is a country that is rich in artistic diversity. This art can be a song. In addition to traditional songs, Indonesia is rich in songs from various genres. Some of the genres used by the author are pop, ballad, dangdut. Song or music has become an interesting area of research in computer science. Music recognition is a computational problem in the field of computer vision. Music introduction aims to classify music into several categories such as genre, mood, or music generation. Although in the last ten years a number of studies have been published, the problem of music recognition is still a difficult problem to solve by computers. In addition, it is necessary to explore several features that represent music, including audio spectrograms, chromagrams, and song lyrics. The author processes the lyrics and audio features in the form of a chromagram using many songs. Music can be a collection of data that can be processed by machine learning. The data used for classification is song data in the form of datasets. The author uses his own dataset or manual methods in collecting and processing datasets. The song is downloaded from YouTube after that it is converted into mp3 and cut. The author processed 1181 songs from the 70’s and 80’s era which only took the chorus part. Lyrics in chorus form are saved in excel. The audio chorus is saved in .wav. The results of the Mood classification used by the author in music consist of 3, namely happy, sad and neutral which are processed using machine learning. Using 2 experiments on Chromagram and word embedding feature has a higher value of 81%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An approach to parameter optimizer for music mood classification in machine learning

引用

AIP Conference Proceedings 2025年第1期3223卷

作者： Nunik Destria Arianti T. Thoyyibah Achmad Udin Zailani Neny Rosmawarni Rinna Rachmatika Achmad Lutfi Fuadi Information System University of Nusaputra Sukabumi Indonesia Information Systems Management Department BINUS Graduate Program-Master of Information System Management Bina Nusantara University Jakarta Indonesia 11480 Information Technology University of Pamulang Banten Indonesia Faculty of Information Technology Veterans National Development University Indonesia

Music is a blend of the human voice and instruments that bring beauty to the listener. Many people like music to create an atmosphere or atmosphere. In the field of computer science, with a lot of data, music is an object that can be studied both through lyrics, audio, biographies and others. This research focuses on the mood of Indonesian music in the 70s and 80s. The data set used consists of text data and audio data. The mood tested consisted of sad, happy and neutral. This area of interest was investigated using the Crisp-DM method derived from business understanding, data understanding, data preparation, modelling, evaluation, deployment. In building the Confusion Matrix, this study uses several parameters, namely epoch, dimensions, set size, learning rate and others. The value generated by the confusion matrix contains a good 85 % value.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Construction and Evaluation of Situational System for Introducing Interactive technology into Ecotourism of Active Aging Group 22nd

Construction and Evaluation of Situational System for Introd...

引用

22nd International Conference on Human Computer Interaction, HCII 2020

作者： Lu, Li-Shu Wu, PeiFen Huan, Guan-Yuan Department and Graduate School of Digital Media Design National Yunlin University of Science and Technology Douliu Taiwan Department of Information Management and Master Program in Digital Content Technology and Management National Changhua University of Education Changhua Taiwan

ISBN: (纸本)9783030601485

Due to the issue of population aging faced by Taiwan, the government is implementing policies on encouraging the elderly to engage in social activities in their life after retirement, so as to enable them to enjoy a contented and happy retirement life and further forget their ages. In the population aging society, the elderly have an increasingly greater demand for ecotourism. Therefore, in this study, by taking ecotourism as an example, a research on the engagement of the elderly in technology enhanced interactive scenarios of ecotourism was conducted. Purpose of this study was mainly to propose the design system of technology enhanced interactive scenarios suitable for experience of the elderly. In this study, experience demands of the elderly were understood through relevant literature review, preliminary survey and field survey. Subsequently, design concepts of interactive scenarios were proposed through Scenario Approach and a prototype of interactive scenario was designed through Rapid Prototyping Method. Research results: a total of 8 concepts of interactive scenarios were proposed in this study through demand investigation, including provision of experience information, voice guide experience, enhancement of experience fun, trigger of experience scenario, enhancement of intellectual fun, basic knowledge query, enhancement of sensory experience, and sharing and memory. At last, the prototype of "i-Travel" interactive experience scenario was proposed through Prototyping Method. The interactive system consists of 8 interactive scenario concepts, experience contents and navigation design, design of scenario navigation APP, etc. Results of this study will be applied for subsequent assessment and validation of scenario experience awareness of this system. © 2020, Springer Nature Switzerland AG.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Explainable machine learning models for estimating daily dissolved oxygen concentration of the Tualatin River

引用

Engineering Applications of Computational Fluid Mechanics 2024年第1期18卷

作者： Li, Shuguang Qasem, Sultan Noman Band, Shahab S. Ameri, Rasoul Pai, Hao-Ting Mehdizadeh, Saeid School of Computer Science and Technology Shandong Technology and Business University Yantai China Computer Science Department College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic University (IMSIU) Riyadh Saudi Arabia Computer Science Department Faculty of Applied Science Taiz University Taiz Yemen Future Technology Research Center National Yunlin University of Science and Technology Douliu Taiwan Department of Information Management International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Douliu Taiwan Department of Information Management National Yunlin University of Science and Technology Douliu Taiwan Bachelor Program of Big Data Applications in Business National Pingtung University Pingtung Taiwan Water Engineering Department Urmia University Urmia Iran

Monitoring the quality of river water is of fundamental importance and needs to be taken into consideration when it comes to the research into the hydrological field. In this context, the concentration of the dissolved oxygen (DO) is one of the most significant indicators of the quality of river water. The current study aimed to estimate the minimum, maximum, and mean DO concentrations (DO min, DO max, DO mean) at a gauging station located on Tualatin River, United States. To that end, four machine learning models, such as support vector regression (SVR), multi-layer perceptron (MLP), random forest (RF), and gradient boosting (GB) were established. Root mean square error (RMSE), mean absolute error (MAE), coefficient of correlation (R), and Nash-Sutcliffe efficiency (NSE) metrics were employed to better assess the accuracies of these models. The modeling results demonstrated that the SVR and MLP surpassed the RF and GB models. Despite this, the SVR was concluded to be the best-performing method when used to estimate the DO min, DO max, and DO mean. The best error statistics in the testing phase were related to the SVR model with full (four) inputs to estimate DO mean concentration (RMSE = 0.663 mg/l, MAE = 0.508 mg/l, R = 0.945, NSE = 0.875). Finally, the explainability of the superior models (i.e. SVR models) was conducted using SHapley Additive exPlanations (SHAP) for the first time to estimate DO concentration. In fact, evaluating the explainability of machine learning models can provide useful information about the impact of each of the input estimators used in the procedure of models development. It was concluded that the specific conductance (SC) and followed by water temperature (WT) could provide the most contributions for estimating the DO min, DO max, and DO mean concentrations. © 2024 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： dissolved oxygen concentration estimation Explainable machine learning SHapley additive explanations

来源：评论

学校读者我要写书评

暂无评论

Exploring the Contextual Relationship of Narrating Life Stories by Elderly People 22nd

Exploring the Contextual Relationship of Narrating Life Stor...

引用

22nd International Conference on Human Computer Interaction, HCII 2020

作者： Fan, KuangYi Wu, PeiFen The Graduate Institute of Animation and Multimedia Design National University of Tainan Tainan Taiwan Department of Information Management and Master Program in Digital Content Technology and Management National Changhua University of Education Changhua City Taiwan

ISBN: (纸本)9783030601485

Global aging is an important issue for global development. Elderly people should not be the burden of individual families, but the assets of the entire society. With the help of life stories or past events that elderly people often repeat, we can better understand the importance of certain things. Therefore, life review is a normal and necessary process that can help the elderly to review past experience with a rational attitude, help them to find the meaning of life, and see the essence of their life. The interviews in this study used Nvivo qualitative software to record and analyze the life stories of 4 elderly people in southern Taiwan, in order to understand the important memories and emotions in their lives, discover the background factors of elderly people recalling their life, and maintain precious human stories for families and society via recording and saving. Guiding the elderly to review their lives through nostalgic narrative has the function of storied therapy, and its values include: personal self-identification, rebuilding the integrity of life through memories, and helping the elderly to reposition themselves in a lonely life through their past experience. © 2020, Springer Nature Switzerland AG.

关键词： Autobiographical memory Elderly Life narrative Narrative gerontology Storied therapy

来源：评论

学校读者我要写书评

暂无评论

Transformative Sport Science Using Social Media as a Collaboration Tool 7

Transformative Sport Science Using Social Media as a Collabo...

引用

7th International Conference on ICT for Smart Society, ICISS 2020

作者： Oktavia, Tanty Gaol, Ford Lumban Hosoda, Takaaki Syahir, Arsyan Bina Nusantara University School of Information Systems Information Systems Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program - Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia Advanced Institute of Industrial Technology Decision Science Department Tokyo Japan Bina Nusantara University BINUS Graduate Program - Master of Information Systems Management Information Systems Management Department Jakarta11480 Indonesia

ISBN: (纸本)9781665404228

Sports science can have a significant and positive impact on coaches and athletes, as well as for the professional sports organization. According to this situation, more and more organizations are competing to implement sports science as the monitoring systems. Along with the development of technology, it becomes easier for humans to carry out their activities, including communication with each other. Advances in the field of communication technologies have led to the use of social networks to support all activity. With social media, all kinds of information that people want to search for can be found easily. Social networks have their uniqueness in their characteristics. Like LINE has free calling and video calling features, while Instagram has features like Instagram Story, where users can document their activities in the form of photos or recordings. By all the characteristics of social networks, it will support the activity of sports science. The methodology of this research focused on quantitative research based on the T-test approach. The result shows that social media involvement can significantly support collaboration in sports science, so it can increase people's motivation to interact with other participants in sport organizations. © 2020 IEEE.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

Patient Confidential Data Hiding and Transmission System Using Amplitude Quantization in the Frequency Domain of ECG Signals

引用

Sensors 2023年第22期23卷 9199-9199页

作者： Chen, Shuo-Tsung Ye, Ren-Jie Wu, Tsung-Hsien Cheng, Chun-Wen Zhan, Po-You Chen, Kuan-Ming Zhong, Wan-Yu Department of Medical Informatics Chung Shan Medical University Taichung40201 Taiwan Department of Information Center Chung Shan Medical University Hospital Taichung40201 Taiwan Graduate School of Applied Chinese Studies National Yunlin University of Science and Technology Yunlin 64002 Taiwan Bachelor’s Program in Business Management Fu Jen Catholic University New Taipei City242062 Taiwan

The transform domain provides a useful tool in the field of confidential data hiding and protection. In order to protect and transmit patients’ information and competence, this study develops an amplitude quantization system in a transform domain by hiding patients’ information in an electrocardiogram (ECG). In this system, we first consider a non-linear model with a hiding state switch to enhance the quality of the hidden ECG signals. Next, we utilize particle swarm optimization (PSO) to solve the non-linear model so as to have a good signal-to-noise ratio (SNR), root mean square error (RMSE), and relative root mean square error (rRMSE). Accordingly, the distortion of the shape in each ECG signal is tiny, while the hidden information can fulfill the needs of physiological diagnostics. The extraction of hidden information is reversely similar to a hiding procedure without primary ECG signals. Preliminary outcomes confirm the effectiveness of our proposed method, especially an Amplitude Similarity of almost 1, an Interval RMSE of almost 0, and SNRs all above 30. © 2023 by the authors.

关键词： Electrocardiograms

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：