检索结果-内蒙古大学图书馆

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

作者： Budi Prasetyo Suharjito Computer Science Department Binus Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Barat Indonesia

ISBN: (数字)9798331529376

ISBN: (纸本)9798331529383

Given the limited availability of state funds, managing state finances in an effective, efficient, and prudent manner is essential. High demand for additional state funds without sound justification can lead to inefficiencies and poor budget execution. Therefore, decisions regarding the allocation of additional funds should be made selectively and based on historical data reflecting the quality of the work unit in budget management. This research aims to develop a machine learning application to assist decision-makers in recommending additional funding percentages. Utilizing the Budget Implementation Quality Indicator (IKPA) data, we performed feature selection using Principal Component Analysis (PCA), resulting in three selected features. These features were then used to build models with base models (Decision Tree Regression, K-Nearest Neighbor Regression) and ensemble learning methods (Stacking, Bagging, Random Forest, Boosting: AdaBoost, XGBoost, LightGBM). After to-Fold Cross-Validation and hyperparameter tuning, LightGBM demonstrated the lowest error rate with a Root Mean Square Error (RMSE) of 0.0646 and a Mean Absolute Error (MAE) of 0.0520, outperforming XGBoost in predicting additional fund allocation proportions. The application supports informed and accountable financial decision-making, promoting efficient and prudent national financial management. By comparing base models and ensemble techniques, this research provides critical insights into machine learning applications in financial management, driving methodological innovation and advancing the field.

关键词： Biological system modeling Government Machine learning Financial management Data models Resource management Ensemble learning Root mean square Regression tree analysis Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Detection of Narcotics Money Laundering in Suspicious Financial Transactions Using Convolutional Extreme Gradient Boosting (ConvXGB)

Detection of Narcotics Money Laundering in Suspicious Financ...

引用

Intelligent Cybernetics Technology & Applications (ICICyTA), International Conference on

作者： Leonardus Verrell Sayoga Kinantra Winarno Antoni Wibowo Computer Science Department Binus Graduate Program – Master of Computer Science School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331506490

ISBN: (纸本)9798331506506

With the development of narcotics problems that continue to increase, the Indonesian Government responds through the Badan Narkotika Nasional (BNN) with data showing the condition of narcotics tends to grow every year and is followed by the number of assets of money laundering (ML) crimes against narcotics cases. One of the banks in Indonesia as a reporting party for suspicious financial transactions (SFT) has obstacles in detecting narcotics ML due to complex and rarely found patterns. Some previous studies conducted experiments using Convolutional Neural Network (CNN), Extreme Gradient Boosting (XGBoost), and even a combination of both into Convolutional Extreme Gradient Boosting (ConvXGB), and improved model performance in several datasets. This paper designs a model using the ConvXGB algorithm by adopting the CNN architecture, LeNet-5, by applying several convolution layers and pooling layers as a baseline model for feature learning, and the XGBoost as feature classification. Three phases of research are the preprocessing phase by collecting data, transforming data, balancing data with a hybrid sampling technique, splitting data, and scaling data, followed by the implementation phase by creating a ConvXGB model, training and testing the model, then finally the evaluation phase by analyzing results and hyperparameter tuning. The dataset used is SFT from the bank during 2023. This ConvXGB has three convolution layers, a pooling layer, and a flattened layer. The performance test results are the accuracy value and F1-Score value of 99.11% each after hyperparameter tuning. By performing a hybrid model, the model performance results are better.

关键词： Training Representation learning Analytical models Convolution Government Boosting Data models Convolutional neural networks Tuning Testing

来源：评论

学校读者我要写书评

暂无评论

Software Testing Model by Measuring the Level of Accuracy Fault Output Using Neural Network Algorithm 7

Software Testing Model by Measuring the Level of Accuracy Fa...

引用

7th IEEE International Conference on Information Technology and Digital Applications, ICITDA 2022

作者： Zulkifli Gaol, Ford Lumban Trisetyarso, Agung Budiharto, Widodo Binus University Binus Graduate Program - Computer Science Computer Science Department Jakarta Indonesia Binus University School of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (数字)9781665461368

ISBN: (纸本)9781665461368

The testing stage is essential in software development because it determines the quality level, which is indicated by minimal errors. Meanwhile, the error that is discovered by the tester is called a fault. Therefore, this research aims to create a Model-Based Testing (MBT) using the equivalence partitioning technique in the black-box method. The model is expected to log software errors such as Access, performance, initialization, a data structure or external database, incorrect or missing functions, to identify, categorize, and fix them methodically and appropriately. Based on the discoveries, the errors form a dataset that measures the accuracy of the fault output using a neural network algorithm. The result showed the formation of MBT can be developed using the equivalence partitioning technique by measuring the fault output accuracy level using a neural network algorithm, where the average accuracy rate is 80%. © 2022 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Social Network Analysis of Cryptocurrency using Business Intelligence Dashboard

HighTech and Innovation Journal

引用

HighTech and Innovation Journal 2022年第2期3卷 220-229页

作者： Setyono, Jonathan C. Suryawidjaja, William S. Girsang, Abba S. Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

There are currently more than 10.000 cryptocurrencies available to buy from the online market, with a vast range of prices for each coin it sells. The fluctuation of each coin is affected by any social events or by several important companies or people behind it. The aim of this research is to compare three cryptocurrencies, which are Bitcoin, Ethereum, and Binance Coin, using Social Network Analysis (SNA) by visualizing them using Business Intelligence (BI Dashboard). This study uses the SNA parameters of degree, diameter, modularity, centrality, and path length for each network and its actors and their actual market price by crawling (data collecting process) from Twitter as one of the social media platforms. From the research conducted, the popularity of cryptocurrencies is affected by their market price and the activeness of their actors on social media. These results are important because they could help in the decision-making to buy cryptocurrencies with high popularity on social media because they tend to retain their value over time and could benefit from price spikes from influential people. © Authors retain.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Coffee Bean Binary Classification Through Deep Learning Techniques 1

引用

International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications, CITISIA 2022

作者： Islamy, Fajrul Muchtar, Kahlil Arnia, Fitri Dawood, Rahmad Febriana, Alifya Elwirehardja, Gregorius Natanael Pardamean, Bens Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh23111 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department Master of Computer Science Program BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

ISBN: (数字)9783031290787

ISBN: (纸本)9783031290770

Coffee beans are one of the high-value commodities in Indonesia, but the sorting method for the quality of coffee beans still uses visual methods and sieves with mechanical machines. This study aims to provide an alternative to classifying coffee beans using Deep Learning algorithms, such as the ResNet-18 and MobileNetV2. The dataset used is USK-COFFEE which consists of two classes, the normal coffee bean class, and the defect coffee bean class. The models were trained using the balanced and imbalanced datasets, meaning that two scenarios were performed. From the results of this study, the accuracy value for the ResNet-18 model was 91.50% when trained on the balanced dataset and 90.87% on the imbalanced dataset. It outperformed the MobileNetV2 architecture, which only achieved 0.8125 and 0.8112 accuracy scores when trained on the balanced and imbalanced datasets, respectively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Enhancing Efficiency in Yolov8n for Real-Time Detection of Oil Palm Fruits in Plantations Using Mobileone and Cross-Fusion

SSRN

引用

SSRN 2024年

作者： Hugo, Gregory Mushlik, Muhammad Suharjito Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia Industrial Engineering Department BINUS Graduate Program – Master of Industrial Engineering Bina Nusantara University Jakarta11480 Indonesia

Accurate detection of fresh fruit bunches (FFB) ripeness in complex plantation environments is challenging due to occlusion, varying lighting, intricate visual features, and limited computational resources of mobile devices. To address this, a resource-efficient, real-time detection system was developed using an optimized YOLOv8n model. The model integrates MobileOne modules and Cross-Fusion blocks to enhance efficiency without compromising accuracy. Specifically, Conv and C2f modules were replaced with MobileOne modules, reducing parameters by 85% and 81%, respectively. Cross-Fusion improved feature fusion, and its combination with MobileOne (CF-MobileOne) achieved a 51% reduction in parameters while maintaining performance. The dataset comprised images from videos captured in plantations, annotated into five maturity stages: flower, unripe, underripe, ripe, and abnormal, and underwent augmentation with class balancing through manual undersampling. The model outperformed baseline YOLOv8 variants and heavier models like YOLOv9c and Faster R-CNN, achieving an mAP50 of 0.795 and an inference speed of 140.57 FPS. Hyperparameter tuning with a batch size of 64, SGD optimizer, and a learning rate of 0.01 yielded optimal results. Despite challenges in detecting certain classes due to visual similarities and environmental variations, the system effectively enhances productivity and efficiency in precision agriculture for the palm oil industry. © 2024, The Authors. All rights reserved.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Toward Learning Factory for Industry 4.0: Virtual Reality (VR) for Learning Human–Robot Collaboration 1

引用

International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications, CITISIA 2022

作者： Ariansyah, Dedy Colombo, Giorgio Pardamean, Bens Bioinformatics and Data Science Research Centre Bina Nusantara University Jakarta11480 Indonesia Department of Mechanical Engineering Politecnico di Milano Milan20156 Italy Computer Science Department BINUS Graduate Program Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia

ISBN: (数字)9783031290787

ISBN: (纸本)9783031290770

Industry 4.0 will bring not only transformation to the manufacturing technologies but also to the profile of the workforce. Education system should be revised to prepare the future graduates embracing the knowledge of the ongoing revolution. Initiatives on the modification of curriculum and tools to deliver the concepts of Industry 4.0 must be taken. This paper examines limitations of current engineering tools and proposes a virtual reality (VR)-based learning platform to support the teaching and learning activity for Industry 4.0, focusing on the design of Human–robot Collaboration (HRC). The development process began with the identification of the general Intended Learning Outcomes (ILOs) which were extracted from the review of the HRC design issues, followed by the evaluation of the current teaching tool. From these results, the new requirements of the tools to achieve ILOs are redefined. The implementation of the system is demonstrated to show the feasibility of the proposed learning platform. This workflow can serve as initial development of another learning platform for the other innovative concepts that form the building blocks of Industry 4.0. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Industry 4.0

来源：评论

学校读者我要写书评

暂无评论

Variational quantum neural network with optimized ansatz for predicting malignant ventricular arrhythmias

引用

Procedia computer science 2024年 245卷 109-116页

作者： Nicholas Dominic Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia

Preventive strategies should be the utmost priority when dealing with diverse patients suffering from malignant ventricular arrhythmia (MVA) that can lead to sudden cardiac death (SCD). Electrocardiogram (ECG) data is commonly used as a predictor for MVA predictive models. In this study, all ECG signals from MIT-BIH databases were fragmented into five-minute durations with a frequency sampling of 128 Hz. To solve the absence of hybrid optimizations in Machine Learning (ML) models, a novel Variational Quantum Neural Network (VQNN) was invented. Empowered by deep learning capabilities and optimized quantum circuits design, VQNN achieved remarkable performances designated by an accuracy of up to 95.1%, a perfect 100% recall, and a 95.2% score of the area under the Receiver Operating Characteristic curve (AUC ROC) with Conjugate Gradient as an optimizer and EfficientSU2 as a quantum ansatz. Despite the susceptibility to quantum noise, this research settles a new trajectory of utilizing quantum variational algorithms to predict and expand its applicability for MVA cases.

关键词： Malignant Ventricular Arrhythmia Sudden Cardiac Death Variational Quantum Algorithm Quantum Computing Neural Network

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality in Chemistry Learning: A Systematic Literature Review 7

Augmented Reality in Chemistry Learning: A Systematic Litera...

引用

7th IEEE International Conference on Information Technology and Digital Applications, ICITDA 2022

作者： Ariessanti, Hani Dewi Prabowo, Harjanto Gaol, Ford Lumban Meyliana Bina Nusantara University Binus Graduate Program - Information System Jakarta11480 Indonesia Management Bina Nusantara University Binus Graduate Program - Computer Science Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program - Computer Science Jakarta11480 Indonesia

ISBN: (数字)9781665461368

ISBN: (纸本)9781665461368

This study reviews factors affecting AR-based chemistry learning with the BIM model. Although there have been many kinds of research explaining the application of augmented reality (AR) and building information modeling (BIM) in learning, no research has been found that discusses the factors affecting the integration of BIM in AR-based learning. This study adopted the SLR method with the PRISMA protocol by scanning articles written in English or articles written in Indonesian from accredited online databases, and fully accessible by the authors. The articles reviewed were related to AR, BIM, Virtual Reality (VR), and chemistry learning. The predefined strings were used to extract the 156 articles. Only 41 articles met the inclusion criteria that were used as the reference for this study. Six factors were found that affect the AR-based chemistry learning with the BIM model. They are AR work performance, accessibility, user interaction with the system, presentation of material, understanding, and models. This study implies that the factors extracted can be considered as a model in developing learning media to improve chemistry learning. The limitation of this study is the absence of further analysis of which critical factors should be addressed. Researchers recommend further research by reviewing more literature. © 2022 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Density Based Spatial Clustering of Applications with Noise and Sentence Bert Embedding for Indonesian Utterance Clustering

Density Based Spatial Clustering of Applications with Noise ...

引用

2023 International Conference on computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Hasani, Muhammad Fikri Heryadi, Yaya Arifin, Yulyani Lukas Suparta, Wayan Bina Nusantara University BINUS Graduate Program Computer Science School of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program Computer Science Computer Science Department Jakarta11480 Indonesia Jakarta12930 Indonesia Institut Teknologi Nasional Yogyakarta Faculty of Industrial Technology Department of Electrical Engineering Yogyakarta55281 Indonesia

ISBN: (纸本)9798350320954

Task oriented chatbots are a sub-topic related to chatbots, where chatbots will perform certain tasks with specific goals. One part of creating a task-oriented chatbot is doing intent classification. Intent classification is a task of text classification. As in general text classification, the required dataset requires a label to carry out the classification process. To speed up and help the utterance analysis process, there is already a method, namely clustering, and Density-based clustering is a part of clustering that can determine cluster patterns based on arbitrary data, with DBScan as one of its algorithms. This research used 10000 client utterance data of awhatsapp based e-commerce conversation. SentenceBert also used as a state of art sentence embedding. This research yield silhouette score of 0.327 as the best result from eps of 0.1 and MinPts of 95. However, based on the cluster result, sentences labelled as noise can be further clustered. Text Preprocessing, text augmentation and sentence embedding techniques can be explored to increase the cluster performance. © 2023 IEEE.

关键词： Embeddings

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：