检索结果-内蒙古大学图书馆

Data-Driven Incentive Mechanisms for Federated Learning in Vehicular Networks

IEEE Transactions on Vehicular Technology 2025年

作者： Fathi, Faeze Montazeri, Mina N.araabi, Babak Du, Hongyang Niyato, Dusit Kebriaei, Hamed University of Tehran School of Ece College of Engineering Tehran Iran Urban Energy Systems Laboratory Dübendorf8600 Switzerland Nanyang Technological University School of Computer Science and Engineering The Energy Research Institute @ Ntu Interdisciplinary Graduate Program Singapore Nanyang Technological University School of Computer Science and Engineering Singapore School of Computer Science Tehran Iran

Centralized machine learning algorithms in vehicular networks face privacy and resource constraints. Federated Learning (FL) addresses these by enabling collaborative model training without sharing raw data. To incentivize vehicle participation despite resource constraints, we propose a contract between Roadside Units (RSUs) and vehicles, specifying required computation resources and rewards based on local data quality. The contract is designed to maximize the utility of the RSU, subject to constraints that ensure the participation of the vehicles in the task and truthful reporting of their data quality parameter. However, designing an optimal contract with classical methods is limited to specific utility functions. To extend the design methodology of optimal contracts to a broader range of utility functions, our study proposes a deep learning-based solution. Specifically, we present a novel application of Deep Neural Networks (DNNs), marking the first instance of applying DNNs in contract theory-based incentive mechanisms to achieve nearoptimal contracts. We design the DNN's structure to inherently satisfy specific constraints of the optimization problem, enhancing its efficiency and accuracy in determining the optimal contract. We utilize an augmented Lagrangian method to approximate the optimal contract in federated learning tasks. A case study on traffic sign recognition demonstrates the applicability and effectiveness of our method. Comparing our approach with the well-known generative diffusion model shows that in the FL scenarios, the DNN results are closer to the optimal contract compared to those of the generative diffusion model. © 1967-2012 IEEE.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning-Based Digital Twin Model for Pressure Prediction in the Fuel Injection System 48

A Machine Learning-Based Digital Twin Model for Pressure Pre...

引用

48th Annual Conference of the IEEE Industrial Electronics Society, IECON 2022

作者： Duarte, Edwin P. Viegas, Eduardo K. Santin, Altair O. Graduate Program in Computer Science PPGIa Pontificia Universidade Catolica Do Parana-Pucpr Brazil Robert Bosch GmbH Engineering Systems Curitiba Brazil Secure Systems Research Center Abu Dhabi United Arab Emirates

ISBN: (数字)9781665480253

ISBN: (纸本)9781665480253

Over the last years, the engine calibration task has mostly been conducted based on the engineers' knowledge. As a result, considering the complexity of modern engines, finding the most suitable configuration for each situation has become an impractical and expensive task. Apart from causing engines to be produced with inadequate calibration configuration, it can also decrease the lifespan of their components, degrading their efficiency. This paper proposes a machine learning-based digital twin model for pressure prediction in a fuel injection system, split into two steps. First, we extract statistical engine features based on a predefined time window to represent the engine behavior over time. Second, a digital twin implemented through a machine learning model is used to predict pressure levels in the fuel injection system. As a result, the predicted values can be used to assist the engine common rail system module in avoiding undesired engine states. Experiments performed on a new dataset, built over a real diesel-based engine, consisting of 208 features and over 1.3 million instances, have shown the feasibility of our proposal. The proposed scheme can predict in an advance time of 0.1 seconds the pressure levels for a fuel injection system with only 0.057 RMSE. Moreover, it increases its error rate by only 10.6% if a 0.5-second time advance is required. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Local Periodicity-Based Beat Tracking for Expressive Classical Piano Music

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2023年 31卷 2824-2835页

作者： Chiu, Ching-Yu Muller, Meinard Davies, Matthew E. P. Su, Alvin Wen-Yu Yang, Yi-Hsuan National Cheng Kung University Academia Sinica Graduate Program of Multimedia Systems and Intelligent Computing Tainan701401 Taiwan International Audio Laboratories Erlangen Erlangen91058 Germany University of Coimbra Department of Informatics Engineering Centre for Informatics and Systems Coimbra3004-531 Portugal National Cheng Kung University Department of Computer Science and Information Engineering Tainan701401 Taiwan Taiwan AI Labs Yating Music Team Taipei103622 Taiwan Academia Sinica Research Center for IT Innovation Taipei11529 Taiwan

To model the periodicity of beats, state-of-the-art beat tracking systems use 'post-processing trackers' (PPTs) that rely on several empirically determined global assumptions for tempo transition, which work well for music with a steady tempo. For expressive classical music, however, these assumptions can be too rigid. With two large datasets of Western classical piano music, namely the Aligned Scores and Performances (ASAP) dataset and a dataset of Chopin's Mazurkas (Maz-5), we report on experiments showing the failure of existing PPTs to cope with local tempo changes, thus calling for new methods. In this paper, we propose a new local periodicity-based PPT, called predominant local pulse-based dynamic programming (PLPDP) tracking, that allows for more flexible tempo transitions. Specifically, the new PPT incorporates a method called 'predominant local pulses' (PLP) in combination with a dynamic programming (DP) component to jointly consider the locally detected periodicity and beat activation strength at each time instant. Accordingly, PLPDP accounts for the local periodicity, rather than relying on a global tempo assumption. Compared to existing PPTs, PLPDP particularly enhances the recall values at the cost of a lower precision, resulting in an overall improvement of F1-score for beat tracking in ASAP (from 0.473 to 0.493) and Maz-5 (from 0.595 to 0.838). © 2014 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Dynamic programming Algorithm using Furniture Industry 0/1 Knapsack Problem 5

Dynamic Programming Algorithm using Furniture Industry 0/1 K...

引用

5th International Conference on Cybernetics and Intelligent systems, ICORIS 2023

作者： Anditta, Mietha Amartya, Natashya Warnars, Laurens Spits Warnars, Harco Leslie Hendric Spits Ramadhan, Arief Siswanto, Teddy Mantoro, Teddy Noordin, Nurulhuda Bina Nusantara University School of Computer Science Computer Science Departement Jakarta11530 Indonesia Bina Nusantara University School of Information Systems Information Systems Departement Jakarta11530 Indonesia Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Departement Jakarta11530 Indonesia Telkom University Pjj Informatika Bandung40257 Indonesia Trisakti University Information Systems Department Jakarta11440 Indonesia Sampoerna University Faculty of Engineering and Technology Jakarta12760 Indonesia Universiti Teknologi Mara School of Computing Sciences College of Computing Informatics and Mathematics Selangor Malaysia

ISBN: (纸本)9798350369489

Dynamic programming is a fundamental algorithm that can be found in our daily lives easily. One of the dynamic programming algorithm implementations consists of solving the 0/1 knapsack problem. A 0/1 knapsack problem can be seen from industrial production cost. It is prevalent that a production cost has to be as efficient as possible, but the expectation is to get the proceeds of the products higher. Thus, the dynamic programming algorithm can be implemented to solve the diverse knapsack problem, one of which is the 0/1 knapsack problem, which would be the main focus of this paper. The implementation was implemented using C language. This paper was created as an early implementation algorithm using a Dynamic program algorithm applied to an Automatic Identification System (AIS) dataset. © 2023 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

IoT-based Efficient Waste Management on University Campus : Enhancing Monitoring and Optimization through Machine Learning

引用

Procedia computer science 2025年 258卷 4157-4168页

作者： Sumathi M. Hanumanthappa J. K.S. Santhosh Kumar S.P. Shiva Prakash Meghana J. Department of Studies in Computer Science Manasagangothri Campus University of Mysore Mysuru Karnataka 570006 India Department of Artificial Intelligence and Machine Learning Mysore University School of Engineering Manasagangothri Campus University of Mysore Mysuru Karnataka 570006 India Department of Information Science and Engineering & Computer Science and Business Systems JSS Science and Technology University Mysuru Karnataka 570006 India Department of Computer Science Mahajana Post Graduate Center Mysuru Karnataka 570016 India

The introduction of an IoT-based smart waste management system is proposed to optimize various aspects of university campus waste recycle management processes, such as garbage collection scheduling, waste type identification, and collection routes. This system utilizes advanced data analytics algorithms, wireless communication protocols, and sensors to measure and document variations in trash levels, enabling real-time monitoring of waste accumulation. Through this IoT-based infrastructure, university administrators and waste management staff gain fine-grained visibility and control over garbage collection processes. The implications for sustainability advocacy and environmental stewardship in academic environments are significant. By fostering a culture of environmental awareness and accountability, universities can instill ideals of conservation and resourcefulness in their student populations and staff. The proposed IoT-enabled waste bin system exemplifies the synergy between technological innovation and environmental responsibility, serving as a model for institutions worldwide. Collaboration among universities can leverage IoT technology to drive positive change, mitigate environmental degradation, and promote sustainable practices beyond campus boundaries. Efficient waste management is crucial for nurturing sustainability on college and university campuses, as evidenced by the urgent need for the collection and recycling of compost, general waste, and recyclables. Our models consistently achieve high performance, with perfect scores (1.000) across all split ratios, indicating flawless classification of waste types. Although the Artificial Neural Network (ANN) demonstrates slightly lower accuracy, ranging from 0.973 to 0.997 depending on data splits, it still performs well. As a result, Naive Bayes produces less accurate results, typically surpassing 0.93 but falling short of Random Forest, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM)’s flawless

关键词： Artificial Intelligence Smart Parking: Smart city Machine Learning Smart Applications

来源：评论

学校读者我要写书评

暂无评论

Historical Study of the Development of the Misuse of Biological Weapons Technology 8

Historical Study of the Development of the Misuse of Biologi...

引用

8th IEEE International Conference on Computing, engineering and Design, ICCED 2022

作者： Agustin, Dian Mantoro, Teddy Yulivan, Ivan State Intelligence College Medical Intelligence Post-graduate Program Bogor Indonesia Sampoerna University and State Intelligence College Media-Tech Lab Department of Computer Science Jakarta Indonesia Indonesia Defence University Department of Information Systems Jakarta Indonesia

ISBN: (纸本)9781665453899

Technology will continue to be an important thing in life, technological developments can be found in everyday life. In medical intelligence technology, to identify bio-Terrorism actions, and aspects that can threaten national security, such as targets that may be the object of attack, identify indicators early, build biosecurity, and analyze pathogen communities. The threat that hit the world is when resources are used by irresponsible people or groups and are used as biological weapons (bioweapons), bioterrorism, and others. These biological weapons are not only used for war but can also be used for terrorism purposes. The involvement of biological weapons in the history of war has been used, various weapons were created before the 20th century biological weapons in the form of biological toxins or bacteria from decaying animals and plants, after the 20th-century weapons switched to bacteria (anthrax), viruses (smallpox), and poison (botulinum). Regarding what is used as a biological weapon, this is regulated by various policies, both national policies, and defense policies. Anticipatory steps and efforts to overcome the threat of bioterrorism need to involve all parties, including the community, security forces, health workers, and scientists. Legal reforms can be carried out to perfect and complement existing legal loopholes as a result of controlling bioterrorism which widens the opportunities or loopholes for bioterrorism attacks in Indonesia that should receive state attention and formulate bioterrorism regulations. © 2022 IEEE.

关键词： Bioterrorism

来源：评论

学校读者我要写书评

暂无评论

IoT for Water Quality Categorization 5

IoT for Water Quality Categorization

引用

5th International Conference on Cybernetics and Intelligent systems, ICORIS 2023

作者： Sastrohartono, Hermantoro Krisdiarto, Andreas Wahyu Uktoro, Arief Ika Rahutomo, Reza Suparyanto, Teddy Pardamean, Bens Institute of Agriculture Stiper Faculty of Agricultural Technology Agricultural Engineering Department Yogyakarta Indonesia Bina Nusantara University School of Information Systems Information System Department Jakarta11480 Indonesia Bina Nusantara University Bioinformatics & Data Science Research Center Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Master of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350369489

In agricultural water research, the adoption of Internet of Things (IoT) technology has emerged as a pivotal approach for large-scale data collection. Water availability in the context of water quality is very important, both for domestic and industrial purposes. For domestic purposes, drinking water and bathing water are separated. Meanwhile, for the palm oil industry, boiler filler is differentiated from additional process water (dilution water). Water quality parameters can be assessed from turbidity and Total Dissolve Solid (TDS). Measurements using measuring instruments separately and repeatedly require significant energy, time, and costs. This research was conducted with the primary objective of presenting a novel method for categorizing water quality with the approach of IoT sensor technology. The research methodology entailed the utilization of an integrated IoT water sensors system in conjunction with manual water categorization. The methods consist of (1) system design, (2) design and installation of sensor and IoT-based microcontrollers, and (3) accuracy and precision testing compared with laboratory measurements. The precision of the integrated IoT water sensors was assessed through a dedicated sensor precision test, resulting in an accuracy rate of 94.4% for the turbidity sensor and 97.5% for the TDS sensor. Notably, this approach successfully discriminated drinking water with valid categorization, while other water types, including groundwater, water with tea, and water with coffee, yielded null categorization results. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Study of runway crosswind and tailwind potential for airport sustainability: A study of Soekarno Hatta airport, Cengkareng, Indonesia 2

Study of runway crosswind and tailwind potential for airport...

引用

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

作者： Sardjono, W. Zulkarnain Kusnoputranto, H. Soesilo, T.E.B. Utama, D.N. Sudirwan, J. Information Systems Management Department BINUS Graduate Program-Master of Information Systems Management BINA NUSANTARA University Jakarta11480 Indonesia Post Graduate Program School of Environmental Science University of Indonesia Jakarta Indonesia Faculty of Public Health University of Infonesia Jakarta Indonesia Post Graduate Program School of Environmental Science University of Indonesia Jakarta Indonesia Computer Science Department BINUS Graduate Program-Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia School of Information Systems Department BINUS Undergraduate Program Bina Nusantara University Jakarta11480 Indonesia

Airport runway designs must consider wind climatology to reduce the potential for crosswind and tailwind events that can cause accidents and aircraft delays. The large potential of crosswind and tailwind on a runway at the airport is very detrimental to aircraft passengers and airlines. Therefore, it is necessary to know the potential of crosswind and tailwind on the runway of Soekarno Hatta Airport and find the right parameters for the approximate direction and speed of the wind on the airport runway. Analysis was carried out using the direction and wind speed data from the Soekarno Hatta meteorological station in 2007-2017 to determine the potential for crosswind and tailwind on the runway of Soekarno Hatta airport and run a Weather Research and Forecasting (WRF) weather model to determine the parameterization of the right weather model for wind forecast at Soekarno Hatta airport. The highest maximum crosswind component in the 2007-2017 period occurred in August 30.53 knots, while the highest maximum tailwind of 25 knots occurred in January for a 250-degree runway and 24 knots occurred in August for a 070-degree runway. The potential for crosswind and tailwind is different every month. The scheme produces forecasts of wind direction and speed with a strong level of correlation with observations of wind direction and speed from the Soekarno Hatta meteorological station, the correlation value is 0.61. The most significant social impact of plane delays is time loss for passengers. While the economic impact on one of the crosswind events at Soekarno Hatta airport was an economic loss for one airline of US $ 43,392. © Published under licence by IOP Publishing Ltd.

关键词： Losses

来源：评论

学校读者我要写书评

暂无评论

Analysis of delay factors on drilling projects on PT China Oilfields Services Limited 2

Analysis of delay factors on drilling projects on PT China O...

引用

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

作者： Sardjono, W. Perdana, W.G. Ansori, R. Utama, D.N. Information Systems Management Department BINUS Graduate Program-Master of Information Systems Management BINA NUSANTARA University Jakarta11480 Indonesia Post Graduate Program School of Environmental Science University of Indonesia Jakarta Indonesia Graduate Program Master of Business Administration Faculty of Economic and Business University of Gadjahmada Yogyakarta Indonesia Computer Science Department BINUS Graduate Program-Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

In carrying out drilling projects at PT China Oilfields Services Limited ( COSL) Indo, especially Project 1 to Project 4, there were a mismatch between the initial plan of the project and the actualisation in the field because there were inhibiting factors in implementing the project. The purpose of the research was to look the factors that caused for the additional time in well drilling project at PT. COSL Indo, to build a relationship model of these factors, and formulate a strategy for the company to be able to overcome the occurrence of additional time in the future project. Data analysis was conducted by using a factor analysis method and the location of the research was carried out in just one company with 102 valid respondents. The results of the research indicate that there are four factors that influence the time gap, namely Project Management Activities, Risk Analysis and Procurement, Manage Stairs, and Project Planning Development. By knowing the causes of the delay, companies can find the best solutions for future learning and the impact on environmental, social and economic problems can also be anticipated so that sustainable development occurs in the context of petroleum management. © Published under licence by IOP Publishing Ltd.

关键词： Risk analysis

来源：评论

学校读者我要写书评

暂无评论

CLINICAL DETERIORATION PREDICTION IN BRAZILIAN HOSPITALS BASED ON ARTIFICIAL NEURAL NETWORKS AND TREE DECISION MODELS 15

CLINICAL DETERIORATION PREDICTION IN BRAZILIAN HOSPITALS BAS...

引用

15th International Conference on ICT, Society and Human Beings, ICT 2022, 19th International Conference on Web Based Communities and Social Media, WBC 2022 and 14th International Conference on e-Health, EH 2022 - Held at the 16th Multi Conference on computer science and Information systems, MCCSIS 2022

作者： Yazdanpanah, Hamed Silva, Augusto C.M. Guedes, Murilo Morales, Hugo M.P. dos Coelho, Leandro S. Moro, Fernando G. Department of Research Robô Laura PR Curitiba Brazil Department of Computer Science University of São Paulo SP São Paulo Brazil Industrial and Systems Engineering Graduate Program Pontifical Catholic University of Parana PR Curitiba Brazil Electrical Engineering Graduate Program Federal University of Parana PR Curitiba Brazil

ISBN: (纸本)9789898704405

Early recognition of clinical deterioration (CD) has vital importance in patients’ survival from exacerbation or death. Electronic health records (EHRs) data have been widely employed in Early Warning Scores (EWS) to measure CD risk in hospitalized patients. Recently, EHRs data have been utilized in Machine Learning (ML) models to predict mortality and CD. The ML models have shown superior performance in CD prediction compared to EWS. Since EHRs data are structured and tabular, conventional ML models are generally applied to them, and less effort is put into evaluating the artificial neural network’s performance on EHRs data. Thus, in this article, an extremely boosted neural network (XBNet) is used to predict CD, and its performance is compared to eXtreme Gradient Boosting (XGBoost) and random forest (RF) models. For this purpose, 103,105 samples from thirteen Brazilian hospitals are used to generate the models. Moreover, the principal component analysis (PCA) is employed to verify whether it can improve the adopted models’ performance. The performance of ML models and Modified Early Warning Score (MEWS), an EWS candidate, are evaluated in CD prediction regarding the accuracy, precision, recall, F1-score, and geometric mean (G-mean) metrics in a 10-fold cross-validation approach. According to the experiments, the XGBoost model obtained the best results in predicting CD among Brazilian hospitals’ data. © 2022 15th International Conference on ICT, Society and Human Beings, ICT 2022, 19th International Conference on Web Based Communities and Social Media, WBC 2022 and 14th International Conference on e-Health, EH 2022 - Held at the 16th Multi Conference on computer science and Information systems, MCCSIS 2022. All rights reserved.

关键词： Neural networks

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：