检索结果-内蒙古大学图书馆

computer science, Information Technology and Engineering (ICCoSITE), International Conference on

作者： Mochammad Haldi Widianto Alexander Agung Santoso Gunawan Yaya Heryadi Widodo Budiharto Computer Science Department BINUS Graduate Program - Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

Electrical energy consumption is always increasing, and this causes the supply of electrical energy to be increased to compensate. One solution is to predict electricity energy consumption using Artificial Intelligence (AI) technology in Smart Homes. Several studies' solutions for predicting electrical energy consumption usually focused only on performance but rarely evaluated Machine Learning (ML) by correlation for feature selection and utilized interpretability model. This study uses an ML model for predicting utilization (Linear Regression, Decision Tree, Random Forest, and XGBoost). Then, Feature Selection utilizes correlation to choose the best feature. After that, the interpretability model utilizes Local Interpretable Model-agnostic Explanations (LIME). The results show that XGBoost has the best Root Mean Squared Error (RMSE) value (0.318) with a percentage of the number of train and test data (90/10). After that, by eliminating features that correlate with 0.01, XGBoost improves with an increase of (0.018) to become (0.3). Then from LIME. This work also gets positive feature from XGBoost such as: "Furnance, Well dan Living Room".

关键词： Energy consumption Correlation Linear regression Smart homes Predictive models Feature extraction Data models

来源：评论

学校读者我要写书评

暂无评论

Analyzing Company’s Share Purchase Value Based on Financial Reports Using Artificial Neural Network (ANN)

Analyzing Company’s Share Purchase Value Based on Financial...

引用

International Conference on Computing, Engineering, and Design (ICCED)

作者： Jeremy Shawn Jonathan Gunawan Chen Zi Hao Maria Susan Anggreainy Afdhal Kurniawan Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia

Because financial time series forecasting is sensitive to political, economic, and social factors, it is not a simple task. As a result, those who make investments in currency exchange and financial markets typically search for reliable models that can guarantee they will maximize their profile and minimize their losses. Fortunately, many studies have used a method from Artificial Neural Networks (ANNs) called Backpropagation, could improve the predictive accuracy of the behavior of the financial data over time. This paper aims to forecast stock share prediction from closing value of PT. Bank Central Asia Tbk, and PT. Bank Maybank Indonesia Tbk. The results show that the using Backpropagation gives the closest result. And for the rating of judgement for cast accuracy, it exceeded 10% accuracy, which means high accurate from the prediction. For further checking, comparing the results of research from Victor’s results, it almost hits the same accuracy percentage. Which means, these prediction are accurate enough to do time series forecasting.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ANALYSIS OF NITROGEN FLOW IN FOOD WASTE: A CASE STUDY OF THE university RESTAURANT-UNB 32nd

ANALYSIS OF NITROGEN FLOW IN FOOD WASTE: A CASE STUDY OF THE...

引用

32nd European Biomass Conference and Exhibition, EUBCE 2024

作者： Ramos, Arthur Augusto Frasson De Brites, Eneida Campos Felipe Soares, Raquel Moraes Silveira, Edgar A. Contreras, Francisco University of Brasilia Department of Civil and Environmental Engineering DF Brasilia70910-900 Brazil University of Brasilia Graduate Program on Environmental Technology and Water Resources Department of Civil and Environmental Engineering DF Brasilia70910-900 Brazil Federal Institute of Education Science and Technology of Brasília Estrutural Campus DF Brasília71250-000 Brazil University of Brasília Mechanical Sciences Graduate Program Laboratory of Energy and Environment DF Brasilia70910-900 Brazil

With the projected global population reaching 9.7 billion by 2050, the production and consumption of food continue to escalate. Nitrogen is pivotal in this landscape due to its significance in living organisms and the environmental repercussions associated with nutrient-rich waste. Inappropriate disposal of such residues contributes to nitrogen release into the environment, impacting aquatic ecosystems and precipitating the generation of greenhouse gases. This study tackles the global challenge of effectively managing nitrogen in food waste by utilizing Material Flow Analysis (MFA) as a tool to comprehend this cycle. The analysis uncovered that vegetables, legumes, and fruits constitute the primary sources of waste generation, while meats, despite their lower mass, account for a substantial proportion of total nitrogen depletion. In the surveyed month of October 2023, 174,834 meals were served, resulting in an average food consumption N-footprint of 0.003 kg of nitrogen discarded per individual meal within the restaurant’s organic waste. These findings indicate that 65% of nitrogen is consumed in meal form, while 35% is discarded as organic solid waste. However, 53% of the nitrogen in the residues originates from food preparation processes, with food preparation responsible for over half of this figure. A deeper process analysis reveals that vegetables have low nitrogen concentrations, although they significantly contribute to waste at all stages. In contrast, meats and eggs, with higher nitrogen concentrations, emerge as noteworthy contributors to the overall nitrogen content in waste. Vegetables and meats contribute about 50% and 45% of the total nitrogen, respectively. These outcomes substantially enhance our comprehension of waste generation dynamics and nutrient utilization at the university restaurant, assisting with waste management, design of sustainable menus, reduction of food waste, and optimized resource utilization, contributing to sustainability and re

关键词： Effluent treatment

来源：评论

学校读者我要写书评

暂无评论

Biodiversity or ultra-processed food: an analysis of school meals offered in a riverside school in the Brazilian Amazon

引用

The Lancet. Planetary health 2024年 8卷 S14页

作者： Humbelino de Melo, Paula Regina Alves, Pericles Vale Souza de Camargo, Tatiana Graduate Program in Science Education Federal University of Rio Grande do Sul Porto Alegre Brazil Graduate Program in Environmental Sciences Federal University of São Carlos São Paulo Brazil

BACKGROUND: Rural schools in Amazonas, Brazil, often offer ultra-processed foods in school meals for students, which can lead to health problems and loss of regional food culture. We show an analysis of the menu offered in a riverside school in the Brazilian Amazon and the acceptability of students regarding the consumption of the food they are served with. METHODS: Data were collected in situ, in a riverside school in southern Amazonas, through the analysis of the school menu and the application of an investigative questionnaire to 37 students in the 9th grade of Junior High School. FINDINGS: The research revealed that the foods most consumed by students in school meals are canned beef, canned meatballs, canned sardines, sausage, biscuits, juice, rice porridge, corn porridge, pasta, meat soup, and rice with beans. In the questionnaire that was applied to students, there is a wide variation in the acceptability of the foods offered. However, 57% of students reported not liking the lunch offered at the educational institution. INTERPRETATION: To tackle this problem, it is essential that, local food culture and biodiversity food can be more valued, elements that are often excluded from school menus. This work showed that is also essential to fully adhere to the National School Meal program (PNAE) in Brazil, which recommends that at least 30% of food intended for school meals must come from family farming, highlighting that quality food is crucial for cognitive development of students. Therefore, the meals offered in the chosen riverside school not only do not meet the PNAE guidelines but are also not well accepted by students. This study shows a significant need to consider the direct relationship between planetary health, school meals food security, and food sovereignty, given the various negative effects of foods that are rich in fat, sodium, preservatives, and other substances. Furthermore, it is imperative to integrate food into the students' context, valuing regi

关键词：

来源：评论

学校读者我要写书评

暂无评论

Objective Sleep Quality Measurement based on Fuzzy Logic and Wearable Device

引用

Procedia computer science 2023年 227卷 1153-1162页

作者： Jason A. Wijaya Pauw D. Andersen Nico Surantha Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Department of Electrical Electronic and Communication Engineering Tokyo City University Japan

Sleep is the natural state of relaxation for human being. Sleep quality is an essential yet frequently neglected aspect of sleep in general. Sleep quality is essential because it allows the body to restore itself and prepare for the next day. The standard method for evaluating sleep quality was subjective evaluation. Actigraphy devices, which can measure the sleep cycle, are now widely available. This study developed a method using Fuzzy Logic and an actigraphy device to measure and classify sleep quality. The fuzzy logic method was developed in several stages, which are determining the sleep quality measurement parameters, constructing the fuzzy set for each input variable, and developing the fuzzy rules. To evaluate the proposed fuzzy model, five individuals were invited to participate in the experiment and required to complete the PSQI subjective sleep questionnaire. The evaluation result shows that our proposed Fuzzy model achieves lower error compared to the existing method.

关键词： sleep sleep quality actigraphy artificial intelligences fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Dagang Yuk Yuk As Smartphone Application for MSME Product Sales 2

Dagang Yuk Yuk As Smartphone Application for MSME Product Sa...

引用

2nd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2022

作者： Erinda, Muhammad Fandi Warnars, Harco Leslie Hendric Spits Sumardin, Winters Arianto, Jimmy Vinarycha, Devi Wahyu Bina Nusantara University School of Information Systems Information Systems Department Jakarta11480 Indonesia Bina Nusantara Univesity Binus Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665400527

Many MSMEs manually close their businesses in today's competition, especially those caused by the COVID19 pandemic, and besides that, the lack of technology implementation is even more aggravating. Like it or not, Micro, Small, and Medium Enterprises (MSMEs) must equip their businesses with the application of technology, and unfortunately, there are still many MSMEs that have not been able to take advantage of the benefits of technological developments. Many companies see this condition as an opportunity;for example, Gojek and Grab partner with MSME players to make it easier to trade their products or services. In this paper, a smartphone application for MSMEs called 'Dagang Yuk Yuk, ' which consists of activities such as Login, Create Order, Input Delivery Location, Select Courier, and Select Payment Method has been proposed. Dagang Yuk Yuk tries to give different ideas for implementing MSME actors where this application is only for MSME players as part of an MSME business unit. This paper discusses the application's design using use case diagrams to describe the business process, while class diagrams model the database design. This application was developed using Arduino studio and MySQL database for database storage. © 2022 IEEE.

关键词： Competition

来源：评论

学校读者我要写书评

暂无评论

Data mining for epidemiology: The correlation of typhoid fever occurrence and environmental factors 7

Data mining for epidemiology: The correlation of typhoid fev...

引用

7th International Conference on computer science and Computational Intelligence, CSCI 2022

作者： Asadi, Faisal Trinugroho, Joko Pebrianto Hidayat, Alam Ahmad Rahutomo, Reza Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Information System Department School of Information System Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program-Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia

Typhoid fever is an endemic disease that burdens Indonesia and has a potentially fatal infection multisystem. Salmonella typhi bacterium is responsible for typhoid fever disease. Poor sanitation, crowding, and slums are the main factors of increasing typhoid fever incidences. Environmental factors directly connected to meteorological factors are the main factor in breeding the Salmonella typhi bacterium. This study aims to identify the correlation between meteorological parameters and typhoid fever disease occurrence. The study was carried out in Jakarta, Indonesia, and the Bureau of Meteorological, Climatology, and Geophysics (BMKG) provided the meteorological parameter data. In addition, the Jakarta health surveillance office provided information on typhoid fever hospitalizations from 2019 to 2021. Pearson's concept was utilized d to investigate the correlation between typhoid fever incidences and the meteorological parameters. Humidity, precipitation, and wind speed are the meteorological parameters that significantly affect in contribute to the occurrence of typhoid fever disease. These findings might be used as a reference for Indonesia's government in making public policy to prevent typhoid fever in Indonesia. © 2022 Elsevier B.V.. All rights reserved.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Learning Adaptation and Generalization from Human-Inspired Meta-Reinforcement Learning Using Bayesian Knowledge and Analysis 6

Learning Adaptation and Generalization from Human-Inspired M...

引用

6th IEEE International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2023

作者： Ho, Joshua Wang, Chien-Min King, Chung-Ta You, Yi-Hsin Feng, Chi-Wei Chen, Yen-Min Kuo, Bo-Yi Institute of Information Science Academia Sinica Taipei11529 Taiwan Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Taiwan Institute of Information Systems and Applications National Tsing Hua University Hsinchu30013 Taiwan Department of Computer Science National Tsing Hua University Hsinchu30013 Taiwan Department of Computer Science National Taiwan University Taipei10631 Taiwan Center of Intelligent Healthcare National Taiwan University Hospital Taipei10022 Taiwan

ISBN: (纸本)9798350331288

Over the last decades, there has been growing interest in research in multiple and interdisciplinary fields of human-AI computing. In particular, approaches integrating the intersecting design with reinforcement learning (RL) have received more attention. However, the current research on RL may need to consider its enhancement from a humaninspired approach further. In the present work, we focus on enabling a meta-reinforcement learning (meta-RL) agent to achieve adaptation and generalization according to modeling Markov decision processes using Bayesian knowledge and analysis. By introducing a novel framework called human-inspired meta-RL (HMRL), we incorporate the agent performing resilient actions to leverage the dynamic dense reward based on the knowledge and prediction of a Bayesian analysis. The proposed framework can make the agent learn generalization and prevent the agent from failing catastrophically. The experimental results show that our approach helps the agent reduce computational costs with learning adaptation. Finally, we conclude and anticipate that integrating human-inspired meta-RL can enable learning more formulations relating to robustness and scalability, leading to promising directions and more complex AI goals in the future. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of CNN Models for Multiclass Detection on Colon Disease

Comparative Analysis of CNN Models for Multiclass Detection ...

引用

Information Technology and Digital Applications (ICITDA), IEEE International Conference on

作者： Jason Sebastian Sulistyawan Kuncahyo Setyo Nugroho Mahmud Isnan Bens Pardamean Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331510732

ISBN: (纸本)9798331510749

Gastrointestinal diseases are significant health concerns that mostly affect the digestive and biliary tracts. These can only be observed internally through endoscopy, or a modern approach named Wireless Capsule Endoscopy. Though the approach has proven to work, the process relies heavily on medical experts, which is prone to error when given a considerably large load. The use of deep learning in detecting diseases with images has been proven to work in various cases and can be implemented for gastrointestinal diseases. This study compared four deep learning models based on Convolutional Neural Network architectures consisting of the VGG16, ResNet152V2, InceptionV3, and Xception for classifying colon disease images. The experiment showed that the ResNet152V2 performed the best, compared to the other three with a testing accuracy score of 0.9837. On the other hand, the VGG16 had the lowest performance with around accuracy score of 0.89 while the Xception and InceptionV3models yielded similar accuracy scores of 0.9587 and 0.9549, respectively. The results highlight the effectiveness of ResNet152V2 in handling the complexity of colon disease detection

关键词： Hands Deep learning Accuracy Endoscopes Real-time systems Gastrointestinal tract Data models Colon Medical diagnostic imaging Diseases

来源：评论

学校读者我要写书评

暂无评论

Automatic Multiple Choice Question Generation: A Systematic Literature Review

Automatic Multiple Choice Question Generation: A Systematic ...

引用

Information Technology and Digital Applications (ICITDA), IEEE International Conference on

作者： Matthew Martianus Henry Nur Adhianti Heryanto Mahmud Isnan Kuncahyo Setyo Nugroho Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331510732

ISBN: (纸本)9798331510749

Despite their drawbacks, multiple-choice questions (MCQ) have been widely used to assess the students' understanding of lectures through examinations. The development of automatic MCQ generation is beneficial, especially for educators. As a starting point for further development, a Systematic Literature Review (SLR) is conducted to uncover current trends, future challenges, and opportunities in automatic MCQ generation. Previously, an SLR was conducted, but it lacks coverage of the utilization of transformer-based models. This SLR covers the development of automatic MCQ generation using either traditional or advanced approaches such as Transformers. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses framework was used to gather the data from Scopus, IEEE Xplore, SpringerLink, arXiv, and Semantic Scholar. The included articles must be open-access computer science conference papers or journal articles and written in English less than five years ago. Four independent reviewers analyzed the research workflow, evaluation metric, and dataset used in each study. There are 18 included studies, where 17% (n = 3) studies are from 2024, 33% (n = 6) studies are from 2023, 22% (n = 4) studies are from 2022, 11% (n = 2) studies are from 2021, and 17% (n = 3) studies are from 2020. There are 33% (n = 6) of the studies used the traditional feature-based engineering approach, 39% (n = 7) of the studies used the Transformer-based model fine-tuning approach, and the remaining used novel approaches. The study found that BERT variants are the most utilized Transformer-based model in automatic MCQ. The research notes some challenges, but also open various opportunities for further research, including Large Language Model (LLM) utilization for automatic MCQ generation, the utilization BERT-based models for standardized machine-learned evaluation metrics, and the initiative for the creation of an MCQ dataset benchmark.

关键词： Measurement Semantics Reinforcement learning Benchmark testing Ontologies Transformers Question generation Prompt engineering Standards Systematic literature review

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：