检索结果-内蒙古大学图书馆

6th International Youth Conference on Radio Electronics, Electrical and Power Engineering, REEPE 2024

作者： Shahhoud, Farah Deeb, Ahmad Ali Terekhov, Valery I. Bauman Moscow State Technical University Computer Science and Control Systems Department Moscow Russia

ISBN: (纸本)9798350382891

In telecommunication, speech signals need to be coded to ensure good transmission quality of the signals to far receivers. The objective of the codec system is to compress the signals to as few bits as possible while keeping good quality of the output signals. Unfortunately, encoding speech signals decreases their quality, especially when there are limits on the sent bitrates, which cause uncomfortable experience of communication for both sides. In this paper, a speech enhancement filter is proposed, which reduces distortions of the decoded speech at low bitrates to make it more pleasant, reduce listening effort and improve the intelligibility of the signal. The filter is a complex convolutional neural network model with Long-Short Term Memory (LSTM) units, that enhances the speech signals decoded by Enhanced Voice Services (EVS) codec. Our model was trained using perceptual metric for speech quality evaluation (PMSQE) which is a more intelligent loss function. In result, the Perceptual Evaluation of Speech Quality (PESQ) score evaluation of speech signals, enhanced by the model, has a raise by 0.2 on average for different bitrates signals. © 2024 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

A Review of Evaluation Metrics Algorithmic Used in Scholarly Research Recommender System 4

A Review of Evaluation Metrics Algorithmic Used in Scholarly...

引用

4th International Multidisciplinary Information Technology and Engineering Conference, IMITEC 2024

作者： Ovono, Gerald Zuva, Travos Otunniyi, Temidayo Faculty of Applied and Computer Sciences Department of Computer South Africa VaalUniversity of Technology Faculty of Engineering and Technology Department of Process Control and Computer Systems South Africa

ISBN: (纸本)9798350387988

The exponential growth of academic publications has made scholarly research recommender systems indispensable tools for researchers. These systems rely on diverse evaluation metrics to assess their effectiveness and relevance. This paper provides a comprehensive review and analysis of these metrics, categorizing them into accuracy, ranking, diversity, user-centric, coverage, temporal, and computational metrics. By employing a mixed-methods approach, combining systematic literature review and empirical analysis, we identify the prevalence and application of these metrics across various scholarly domains such as literature, conferences, and reviewers. Our findings highlight the widespread use of traditional metrics like precision, recall, and Fl-score, while emphasizing the growing importance of novel metrics such as unexpectedness and serendipity, especially in literature and conference recommendations. We also underscore the domain-specific nature of metric selection, with user-centric evaluations more prominent in literature recommendations, and ranking-focused metrics dominant in conference and reviewer recommendations. Furthermore, the study reveals a significant gap in the use of temporal and computational metrics, suggesting key areas for future research. This review offers valuable insights for researchers and practitioners, guiding them in metric selection and highlighting potential directions for enhancing the effectiveness, adaptability, and user satisfaction of scholarly recommender systems. © 2024 IEEE.

关键词： Algorithms Evaluation Metrics Novelty Recommender systems Scholarly Research Serendipity

来源：评论

学校读者我要写书评

暂无评论

On the Efficiency of Economic Activity of Small Enterprises Operating in the Field of Ground Passenger Transportation (Code 34 in All-Russian Classifier of Economic Activities OKVED2) 17

On the Efficiency of Economic Activity of Small Enterprises ...

引用

17th International Conference on Management of Large-Scale System Development, MLSD 2024

作者： Promakhina, Irina Federal Research Center 'Computer Science and Control' of the Ras Department of Information Systems Moscow Russia

ISBN: (纸本)9798350375718

The aim of the work was to identify factors affecting the total revenue of regional small enterprises operating in the field of ground passenger transportation, and to evaluate the efficiency of these enterprises. This was done using production function and stochastic frontier models. The statistics were taken from the Complete statistical survey of small and medium-sized businesses in 2020. © 2024 IEEE.

关键词： Economic efficiency

来源：评论

学校读者我要写书评

暂无评论

computer Decision Support System for Resource-Saving Polymer Extrusion Design Based on Virtual Models

Computer Decision Support System for Resource-Saving Polymer...

引用

2023 Applied Mathematics, Computational Science and Mechanics: Current Problems, AMCSM 2023

作者： Polosin, Andrey Chistyakova, Tamara Department of Computer-Aided Design and Control Systems Saint Petersburg Russia

ISBN: (纸本)9798350348576

A computer decision support system for the design and change-over of production of multi-assortment polymeric materials has been developed. The system helps to solve the problems of choosing hardware design and technological modes of extrusion, ensuring resource saving in production. The system includes a subsystem for selecting the brand of the extruder and assembling a 3D model of the modular screw of the extruder, a subsystem for synthesizing a mathematical model for calculating the extrusion efficiency indices depending on the operating parameters of the extruder, a database of types of polymeric materials, a database of brands of extruders, a database of technological regulations of extrusion. 3D models of elements of screw extruders of various types, rules of placement and layout of 3D models of elements when assembling a 3D screw model, mathematical models of physical processes in the channels of screws and heads of extruders are the core of the system. The system allows you to select the brand of the extruder, form the configuration of the extruder screw and determine the operating parameters of extrusion, at which the specified requirements for the quality of the extrudate, throughput and specific energy consumption of the extrusion are satisfied. Testing of the system has been carried out according to the data of industrial extrusion and calendering productions of multi-assortment polymeric films for packaging food and medicines. The test results have confirmed the operability of the software. They have showed an increase in production efficiency due to a reduction in defective products (non-returnable waste), energy saving, and a reduction in the time of change-over of production on new tasks. © 2023 IEEE.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Methodology and Features of the Development of control Programs for Machine Tools with Dynamically Changing Kinematics

Methodology and Features of the Development of Control Progr...

引用

2023 International Russian Automation Conference, RusAutoCon 2023

作者： Evstafieva, Svetlana Msut Stankin Department of Computer-Architecture Control Systems Moscow Russia

ISBN: (纸本)9798350345551

The issues of developing control programs for machine tools with dynamically changing kinematics are considered. The features and additional control commands related to changing the kinematic scheme, controlling the channels of the control system, switching the operating modes of the axes, saving the state of the M and G-vectors are generalized. The features of the execution of the control program in one or several channels are considered. In the case of a program running in several channels and using processors with low performance, it is possible to use a memory-oriented architecture of the control system. A technique for developing control programs has been developed, individual steps of the technique have been identified, features and ways of their implementation have been given. An example of the development of a control program according to the obtained methodology is given. © 2023 IEEE.

关键词： Kinematics

来源：评论

学校读者我要写书评

暂无评论

Debugging control Programs Using Interactive Models of Machine Tools

Debugging Control Programs Using Interactive Models of Machi...

引用

2023 International Russian Automation Conference, RusAutoCon 2023

作者： Evstafieva, Svetlana Grublyak, Vladislav Streshina, Maksim Control Systems Msut Stankin Department of Computer-Architecture Moscow Russia

ISBN: (纸本)9798350345551

The article discusses the features of debugging control programs. The possibilities of debugging control programs in various CNCs, both domestic and foreign, are analyzed. It was found that in many systems there is no collision tracking mode, and when simulating the execution of the control program, fixtures and tooling of the machine are not displayed. The structure of the control system is given and the connection between the control system and the interactive model is implemented. An interactive model of a CNC machine has been developed. The model receives signals from the CNC system. The movement of the model nodes is carried out according to the tasks from the CNC system. The work of the proposed solution is considered on the example of the automatic tool change mechanism. Implemented subroutines for the operation of the elements of the electric machine tool to control the change of tools. The proposed approach makes it possible to evaluate possible equipment collisions. © 2023 IEEE.

关键词： Machine tools

来源：评论

学校读者我要写书评

暂无评论

Social NSTransformers: Low-Quality Pedestrian Trajectory Prediction

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5575-5588页

作者： Jiang, Zihan Ma, Yiqun Shi, Bingyu Lu, Xin Xing, Jian Goncalves, Nuno Jin, Bo Suzhou215000 China Northeast Forestry University College of Computer and Control Engineering Harbin150000 China University of Coimbra Institute of Systems and Robotics Department of Electrical and Computer Engineering Coimbra3030-290 Portugal

This article introduces a novel model for low-quality pedestrian trajectory prediction, the social nonstationary transformers (NSTransformers), that merges the strengths of NSTransformers and spatiotemporal graph transformer (STAR). The model can capture social interaction cues among pedestrians and integrate features across spatial and temporal dimensions to enhance the precision and resilience of trajectory predictions. We also propose an enhanced loss function that combines diversity loss with logarithmic root mean squared error (log-RMSE) to guarantee the reasonableness and diversity of the generated trajectories. This design adapts well to complex pedestrian interaction scenarios, thereby improving the reliability and accuracy of trajectory prediction. Furthermore, we integrate a generative adversarial network (GAN) to model the randomness inherent in pedestrian trajectories. Compared to the conventional standard Gaussian distribution, our GAN approach better simulates the intricate distribution found in pedestrian trajectories, enhancing the trajectory prediction's diversity and robustness. Experimental results reveal that our model outperforms several state-of-the-art methods. This research opens the avenue for future exploration in low-quality pedestrian trajectory prediction. © 2024 IEEE.

关键词： Stars

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Calibration Approaches for Single-Beam and Multiple-Beam Distance Sensors

引用

IEEE Sensors Journal 2024年第1期24卷 975-983页

作者： Syu, Jia-Hao Lin, Jerry Chun-Wei Biernacki, Piotr Ziebinski, Adam National Taiwan University Department of Computer Science and Information Engineering Taipei10617 Taiwan Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science Department of Distributed Systems and Informatics Devices Gliwice44-100 Poland Silesian University of Technology Department of Distributed Systems and Informatic Devices Gliwice44-100 Poland

Sensors are the foundation to facilitate smart cities, smart grids, and smart transportation, and distance sensors are especially important for sensing the environment and gathering information. Researchers have developed various methods to calibrate distance sensors;however, they mainly focus on using external information for calibration, which is inefficient and computationally expensive. To alleviate the above problems, we propose machine learning (ML)-based calibration approaches for distance sensors. We develop two calibration mechanisms, where the naive mechanism directly predicts the true distance, while the residual mechanism predicts the residual for calibration. The conventional ML regression algorithms are then adopted to predict the true distance or calibration residual. Experimental results show that the designed residual calibration mechanism outperforms the naive mechanism by reducing the root mean square error (RMSE) by 92.2% and mean absolute error (MAE) by 93.3% in the fitting task. In prediction, the proposed 2-D-residual mechanism achieves an improvement of 78.6% and 65.7% compared to the state-of-the-art method. The experimental results show the effectiveness and generalization of the proposed ML-based calibration method, especially for the 2-D mechanism, which achieves the highest robustness in all fitting and prediction tasks. © 2001-2012 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Innovative, Semi-Permanent Sensors in the Era of Industry 4.0: Technological Solutions for Efficient Monitoring and Automation

Innovative, Semi-Permanent Sensors in the Era of Industry 4....

引用

2025 International Russian Smart Industry Conference, SmartIndustryCon 2025

作者： Kovalev, Ilya Korshunova, Elena Tagaev, Arsen MSUT 'STANKIN' Department of Computer Control Systems Moscow Russia MSUT 'STANKIN' Department of Economics and Enterprise Management Moscow Russia

ISBN: (纸本)9798331511241

In the era of Industry 4.0, manufacturing and research environments demand increasingly sophisticated monitoring and diagnostic systems. Alongside traditional stationary and portable sensors, semi-permanent (hybrid) sensors have emerged to offer a balanced solution that leverages the high accuracy of fixed installations and the mobility of handheld devices. These hybrid sensors integrate seamlessly with wireless communication protocols, such as Bluetooth Low Energy (BLE) and Wi-Fi etc, providing sufficient data throughput for moderate to high-frequency measurements (e.g., vibration analysis). Their adaptability allows rapid relocation, on-the-fly updates, and real-time data processing, reducing downtime and enhancing responsiveness in dynamic production workflows. Furthermore, the hybrid approach facilitates advanced analytics - such as machine learning algorithms and augmented reality (AR) overlays - without relying solely on dedicated, permanent instrumentation. Semi-permanent sensors address various operational challenges, including cost-effective deployment, compatibility with legacy systems, and centralized data management within ERP platforms. They are thus particularly beneficial for organizations aiming to accelerate digital transformation initiatives, improve predictive maintenance strategies, and minimize equipment failure risks. Although extremely harsh or specialized environments may still favor fully stationary or highly portable options, semi-permanent sensors strike an optimal balance of flexibility and reliability. As a result, they represent an effective foundation for modern condition-monitoring frameworks in Industry 4.0. © 2025 IEEE.

关键词： Data integration

来源：评论

学校读者我要写书评

暂无评论

A MATHEMATICAL MODEL ILLUSTRATING THE INHIBITORY EFFECT OF THE MICRO RNA ON THE PROTEIN PRODUCTION

引用

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2023年第4期85卷 101-106页

作者： Olteanu, Mircea Ştefan, Radu Department of Mathematical Methods and Models Faculty of Applied Sciences University "Politehnica" of Bucharest Romania Department of Automatic Control and Systems Engineering Faculty of Automatic Control and Computer Science University "Politehnica" of Bucharest Romania

The present paper introduces a mathematical model for the cross-talking between microRNA and Protein. Studying the qualitative properties of the proposed model, we infer that the microRNA is an inhibitor for the Prote... 详细信息

关键词： Proteins

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：