检索结果-内蒙古大学图书馆

4th International Conference on Cybernetics and Intelligent System, ICORIS 2022

作者： Setiawan, Karli Eka Elwirehardja, Gregorius Natanael Pardamean, Bens Bina Nusantara University BINUS Graduate Program Master of Computer Science Program Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta11480 Indonesia

ISBN: (纸本)9781665453950

Precise predictions of indoor climate conditions are required in the implementation of Smart Solar Dryer Dome (SDD). Trend development of prediction models is discussed in this review from 15 selected research papers (2018-2022) on indoor climate prediction which was obtained from research paper databases The output shows that the most used model for predicting indoor climate is Artificial Neural Network (ANN), especially Recurrent Neural Network (RNN) such as LSTM and GRU. However, there are some potential methods such as Transformer, Combined Support Vector Machines (SVM)-Deep Learning, and sequence-to-sequence which could outperform other commonly used models. Based on findings various opportunities exist to improve the precision of indoor climate prediction, which can bring power consumption efficiency and others benefit to Smart SDD users. Such studies may further be explored to produce more accurate machine learning models. © 2022 IEEE.

关键词： Domes

来源：评论

学校读者我要写书评

暂无评论

Optimizing Government Funding Allocation with Ensemble Machine Learning Models

Optimizing Government Funding Allocation with Ensemble Machi...

引用

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

Seamless High Availability in MySQL Database Systems: An Advanced Implementation of ProxySQL, Orchestrator, and Keepalived

Seamless High Availability in MySQL Database Systems: An Adv...

引用

Advancement in Data science, E-learning and Information Systems (ICADEIS), International Conference on

作者： Jeremy Loa Benfano Soewito Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331513320

ISBN: (纸本)9798331513337

High availability (HA) in MySQL databases remains a critical challenge, particularly due to risks such as single point of failure (SPOF) and limited scalability in existing setups. Previous studies have explored various approaches to address these issues. One study implemented ProxySQL and Orchestrator for query routing and failover but relied on a single server instance, creating a SPOF that could disrupt client access during failures. Another study implemented HAProxy to balance traffic and couple database servers with specific web applications. While effective for certain use cases, this approach reduced resource efficiency and scalability, because it relies on HTTP protocol and database server are coupled to each application, making it less suitable for dynamic, shared environments requiring high flexibility. These limitations highlight the need for a more robust and scalable HA solution. This paper proposes an improved HA architecture that eliminates SPOFs and enhances scalability by combining redundant ProxySQL instances synchronized with Keepalived managed Virtual IP (VIP) and automated failover using Orchestrator. The architecture allows shared database resources across multiple applications while decoupling them from specific application servers. Test results confirm the system's ability to maintain seamless failover, consistent query routing, and uninterrupted client access through dynamic Virtual IP reassignment to backup server. By addressing the issues of previous studies, this solution provides a practical and scalable framework to achieve high availability in the MySQL cluster by combing ProxySQL, Orchestrator, and Keepalived, making it suitable for modern enterprise environments.

关键词： Costs Databases Scalability Query processing Robustness Servers IP networks Synchronization Stress Testing

来源：评论

学校读者我要写书评

暂无评论

Investigating the Impact on Data Recovery in computer Forensics

Investigating the Impact on Data Recovery in Computer Forens...

引用

Cryptography, Informatics, and Cybersecurity (ICoCICs), IEEE International Conference on

作者： Semi Yulianto Benfano Soewito Computer Science Department Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department Graduate Program. Master of Computer Science Bina Nusantara University Jakarta Indonesia

Defragmentation can potentially be employed as a tactic by perpetrators to conceal, misrepresent, or eliminate digital evidence. This study explores the effects of minor defragmentation, a potential method to conceal digital evidence, on recovering file system data in digital forensics. Our investigation sought to determine the influence of minor defragmentation on the effectiveness of data recovery and to identify methods that can augment the success rate post-defragmentation. We limited the scope of this study to defragmentation in Hard Disk Drives (HDDs), solid-state drives (SSDs), and USB drives. A mixed-method approach employs a literature review, case studies, and controlled experiments. Comparative analysis was used as the main data analysis technique to investigate its impact. Preliminary findings suggest that minor defragmentation hampers data recovery; however, certain strategies can augment success rates. These results can significantly influence the development of data recovery policies, particularly those of digital forensic analysts and law enforcement. The primary objective of this study is to bolster the efficiency and dependability of file system data recovery post-defragmentation while upholding ethical and legal standards.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Tuning of U-Net for Active Fire Segmentation in Peatlands of Indonesia Using Landsat 8 Data

Hyperparameter Tuning of U-Net for Active Fire Segmentation ...

引用

Informatics International Conference (BTS-I2C), Beyond Technology Summit on

作者： Irsyad Kharisma Sani Muhamad Isa Computer Science Binus Graduate Program Universitas Bina Nusantara Jakarta Indonesia

ISBN: (数字)9798331508579

ISBN: (纸本)9798331508586

This study focuses on fire segmentation in peatland areas using the U-Net model, involving hyperparameter tuning combined with data masking developed using a modified ToPeCAl algorithm. The data masking process utilizes TIRS-1 band, band 7, and band 6, while the training data consists of composite images from bands 7, 6, and 4 (764) and 7, 6, and 2 (762) for comparison. Input data includes image patches sized 128×128, 256×256, and 512×512, derived from the 764 and 762 composites, respectively. The study reveals that the use of the leakyReL U activation function, a dilation rate strategy, a learning rate schedule, 50% image patch overlap, and a patch size of 128×128, improves the model's performance for fire segmentation compared to the baseline model. The final evaluation metrics demonstrate Precision, Recall, F1 Score, and IoU values of 88.85%, 89.70%, 89.08%, and 77.36%, respectively.

关键词： Measurement Image segmentation Schedules Training data Landsat Data models Informatics Tuning

来源：评论

学校读者我要写书评

暂无评论

Network-based Intrusion Detection Through Image-based CNN and Transfer Learning

Network-based Intrusion Detection Through Image-based CNN an...

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Pedro Horchulhack Eduardo K. Viegas Altair O. Santin João A. Simioni Graduate Program in Computer Science Pontifical Catholic University of Parana (PUCPR) Brazil

ISBN: (数字)9798350361261

ISBN: (纸本)9798350361278

Machine learning (ML) techniques for network intrusion detection is still limited in production environments despite promising results reported in the literature. Network traffic behavior exhibits considerable variability and evolves over time, requiring periodic model updates. This paper proposes a new approach to intrusion detection modeling based on CNN and transfer learning to reduce updating overhead. Its implementation is twofold. First, CNN is implemented using flow-based feature expansion derived from neural flattened hyperdimensional space. This expanded space representation contributes to a longer model lifetime and maintains system accuracy over time. Second, the required training data and computational cost are significantly reduced by performing periodic model updates based on a transfer learning approach. Experiments on a novel dataset with over 2.6 TB of data and one year of real-world network traffic demonstrate the feasibility of the proposal. Our proposal improves the average F1 score by up to 0.19 when no model updates are performed. While improving the system’s accuracy, model updates impose only 42.8% of the computational cost.

关键词： Wireless communication Accuracy Computational modeling Transfer learning Training data Network intrusion detection Telecommunication traffic

来源：评论

学校读者我要写书评

暂无评论

Dagger Linear Logic and Categorical Quantum Mechanics

arXiv

引用

arXiv 2023年

作者： Srinivasan, Priyaa Varshinee Graduate Program in Computer Science CalgaryAB Canada

This thesis develops the categorical proof theory for the non-compact multiplicative dagger (†) linear logic, and investigates its applications to Categorical Quantum Mechanics (CQM). The existing frameworks of CQM are categorical proof theories of compact †-linear logic, and are motivated by the interpretation of quantum systems in the category of finite dimensional Hilbert spaces. This thesis describes a new non-compact framework called Mixed Unitary Categories which can accommodate infinite dimensional systems, and develops models for the framework. To this end, it builds on linearly distributive categories, and ∗-autonomous categories which are categorical proof theories of (non-compact) multiplicative linear logic. The proof theory of non-compact †-linear logic is obtained from the basic setting of an LDC by adding a dagger functor satisfying appropriate coherences to give a †-LDC. From every (isomix) †-LDC one can extract a canonical "unitary core" which up to equivalence is the traditional CQM framework of †-monoidal categories. This leads to the framework of Mixed Unitary Categories (MUCs): every MUC contains a (compact) unitary core which is extended by a (non-compact) isomix †-LDC. Various models of MUCs based on Finiteness Spaces, Chu spaces, Hopf modules, etc., are developed in this thesis. This thesis also generalizes the key algebraic structures of CQM, such as observables, measurement, and complementarity, to MUC framework. Furthermore, using the MUC framework, this thesis establishes a connection between the complementary observables of quantum mechanics and the exponential modalities of linear logic. © 2023, CC BY.

关键词： Linear algebra

来源：评论

学校读者我要写书评

暂无评论

Aspect-based Sentiment Analysis in Tourism Industry for Tourism Recommender System 5

Aspect-based Sentiment Analysis in Tourism Industry for Tour...

引用

5th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2022

作者： Huda, Choirul Heryadi, Yaya Lukas Budiharto, Widodo Bina Nusantara University Doctor of Computer Science Graduate Program Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Jakarta Indonesia

ISBN: (纸本)9781665455121

The improvement of some aspects in tourism industry needs further study through aspect-based sentiment analysis based on tourist experience. The aim of this study is presenting the empiric results of aspect-based sentiment analysis to extract some useful aspects of services for leveraging tourism industry development based on user's feedback. The study uses customer review data from TripAdvisor website for developing classification model using machine learning algorithms including Decision Tree (DT), Random Forest Classifier (RFC), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost) models. Each machine learning model under study is trained using K-Fold Cross Validation. The empiric results found that accuracy of RFC achieved the highest result (99.5%) followed by XGBoost (87.3%), DT (82.9%), and SVM (80.5%). The extracted meaningful aspects from customer feedback give many valuable insights for service quality improvement in tourism industry in the effort to strengthening the rising-up of sustainability economic growth through tourism industry. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Accelerating free5GC Data Plane Using programmable Hardware 24

Accelerating free5GC Data Plane Using Programmable Hardware

引用

24th Asia-Pacific Network Operations and Management Symposium, APNOMS 2023

作者： Elangovan, Muthuraman Iqbal, Muhammad Shahid Chen, Chien Chen, Jyh-Cheng EECS International Graduate Program Taiwan Department of Computer Science National Yang Ming Chiao Tung University Taiwan Saviah Technologies Inc. Taiwan

ISBN: (纸本)9788995004395

– The demands of today’s 5G mobile network, especially low latency and high bandwidth, are a big challenge for the 5G Core (5GC) provider. The most critical user data packet handler in the 5GC Network Function (NF) is the User Plane Function (UPF), which is responsible for moving data from the user equipment to the destination data network, and vice versa. Existing work mainly focuses on implementing UPF using the key technologies of high-speed data processing. In this paper, with a mobile core provider called free5GC for a standalone (SA) 5G network, we share our experience with the implementation of UPF by using a programmable hardware appliance, which can offer more Tbps compared to the implementation of software UPF that can offer only a few hundred Gbps. For that, we demonstrate how to build up a more flexible architecture of UPF by using the Software-Defined Networking (SDN) concept due to the opacity of protocol specification. We split the UPF control signal implementation into a software application, and user data packet processing into a programmable hardware appliance. We also show how to integrate a number of current UPF data plane free5GC implementations such as Data Plane Development Kit (DPDK), Linux kernel module, and SmartNIC. Furthermore, we analyze and make use of microservices to support the specific features of the UPF data plane that cannot be implemented in a programmable hardware appliance. We tested our free5GC mobile network and the new UPF design architecture that can run on a real programmable hardware appliance from Accton CSP-7551. The evaluation results show that our programmable user plane can reach the line rate. Copyright 2023 KICS.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Replacing the FitzHugh-Nagumo Electrophysiology Model by Physics-Informed Neural Networks 23rd

Replacing the FitzHugh-Nagumo Electrophysiology Model by P...

引用

23rd International Conference on Computational science, ICCS 2023

作者： Werneck, Yan Barbosa dos Santos, Rodrigo Weber Rocha, Bernardo Martins Oliveira, Rafael Sachetto Graduate Program in Computational Modeling Federal University of Juiz de Fora Juiz de Fora Brazil Graduate Program in Computer Science Federal University of São Jõao del Rei São Jão del Rei Brazil

ISBN: (纸本)9783031360206

This paper presents a novel approach to replace the FitzHugh-Nagumo (FHN) model with physics-informed neural networks (PINNs). The FHN model, a system of two ordinary differential equations, is widely used in electrophysiology and neurophysiology to simulate cell action potentials. However, in tasks such as whole-organ electrophysiology modeling and drug testing, the numerical solution of millions of cell models is computationally expensive. To address this, we propose using PINNs to accurately approximate the two variables of the FHN model at any time instant, any initial condition, and a wide range of parameters. In particular, this eliminates the need for causality after training. We employed time window marching and increased point cloud density on transition regions to improve the training of the neural network due to nonlinearity, sharp transitions, unstable equilibrium, and bifurcations of parameters. The PINNs were generated using NVIDIA’s Modulus framework, allowing efficient deployment on modern GPUs. Our results show that the generated PINNs could reproduce FHN solutions with average numerical errors below 0.5%, making them a promising lightweight computational model for electrophysiology and neurophysiology research. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Electrophysiology

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：