检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Smirnov, Evgeny Garaev, Nikita Galyuk, Vasiliy Lukyanets, Evgeny Speech Technology Center Saint Petersburg194044 Russia Department of Information Technologies and Programming ITMO University Saint Petersburg197101 Russia

Face representation learning using datasets with a massive number of identities requires appropriate training methods Softmax-based approach, currently the state-of-the-art in face recognition, in its usual "full softmax" form is not suitable for datasets with millions of persons Several methods, based on the "sampled softmax" approach, were proposed to remove this limitation These methods, however, have a set of disadvantages One of them is a problem of "prototype obsolescence": classifier weights (prototypes) of the rarely sampled classes receive too scarce gradients and become outdated and detached from the current encoder state, resulting in incorrect training signals This problem is especially serious in ultra-large-scale datasets In this paper, we propose a novel face representation learning model called Prototype Memory, which alleviates this problem and allows training on a dataset of any size Prototype Memory consists of the limited-size memory module for storing recent class prototypes and employs a set of algorithms to update it in appropriate way New class prototypes are generated on the fly using exemplar embeddings in the current mini-batch These prototypes are enqueued to the memory and used in a role of classifier weights for softmax classification-based training To prevent obsolescence and keep the memory in close connection with the encoder, prototypes are regularly refreshed, and oldest ones are dequeued and disposed of Prototype Memory is computationally efficient and independent of dataset size It can be used with various loss functions, hard example mining algorithms and encoder architectures We prove the effectiveness of the proposed model by extensive experiments on popular face recognition benchmarks. © 2021, CC BY.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Effective rectification of terahertz electromagnetic fields in a ferrimagnetic iron garnet

引用

Physical Review B 2023年第9期108卷 094439-094439页

作者： T. G. H. Blank E. A. Mashkovich K. A. Grishunin C. F. Schippers M. V. Logunov B. Koopmans A. K. Zvezdin A. V. Kimel Radboud University Institute for Molecules and Materials 6525 AJ Nijmegen Netherlands Department of Applied Physics Eindhoven University of Technology P.O. Box 513 Eindhoven 5600 MB Netherlands Institute of Physics II University of Cologne D-50937 Cologne Germany Kotel'nikov Institute of Radioengineering and Electronics 125009 Moscow Russia Prokhorov General Physics Institute of the Russian Academy of Sciences 119991 Moscow Russia Institute of Advanced Technology and Industrial Programming MIREA Russian Technological University 119454 Moscow Russia

It is found that single-cycle THz electromagnetic fields efficiently excite a GHz spin resonance mode in ferrimagnetic Tm3Fe5O12, despite the near absence of GHz spectral components in the exciting THz pulse. By analyzing how the efficiency of excitation depends on the orientation and strength of the THz electric field, we show that it can be explained in terms of the nonlinear THz inverse Cotton-Mouton effect. Here, the THz electric field gets effectively rectified and acts on the ferrimagnetic spins as a unipolar effective magnetic field pulse. This interpretation is confirmed by a theoretical model based on the phenomenological analysis of the effective magnetic field, combined with the equations of motion derived from the effective Lagrangian for a ferrimagnet. Moreover, by using the outcome of two-dimensional THz spectroscopy, we conjecture a quantum-mechanical interpretation of the observed effect in terms of impulsive stimulated Raman scattering of THz photons by the crystal-field split f−f electronic transitions of Tm3+.

关键词： Faraday effect Magnetism Magneto-optical effect Magneto-optics Nonlinear optics Ultrafast magnetization dynamics Ferrimagnets Magnetic insulators Ferromagnetic resonance Terahertz spectroscopy Ultrafast pump-probe spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Optimizing machine learning algorithms to enhance blood donation for liver patients: a case study

Optimizing machine learning algorithms to enhance blood dona...

引用

7th IET Smart Cities Symposium (SCS 2023)

作者： Maad M. Mijwil El-Sayed M. El-kenawy Indu Bala Mohammad Aljanabi Mostafa Abotaleb Abdelhameed Ibrahim Computer Techniques Engineering Department Baghdad College of Economic Sciences University Baghdad Iraq Department of Communications and Electronics Delta Higher Institute of Engineering and Technology Egypt School of Electrical and Electronics Engineering Lovely Professional University Punjab India Department of Computer Aliraqia University Baghdad Iraq Department of System Programming South Ural State University Chelyabinsk Russia Computer Engineering and Control Systems Department Faculty of Engineering Mansoura University Mansoura Egypt

Blood is vital for transporting oxygen, nutrients, and hormones to all body parts as it circulates through arteries and veins. It removes carbon dioxide, regulates body temperature, and maintains the body's immune system. Individuals constantly need blood and its derivatives to save their lives and improve their health through medical treatments and surgical operations. Liver diseases are one of the diseases that affects the health of individuals and requires blood to continue living. These diseases cause significant damage to people's health, and early diagnosis plays a crucial role in saving lives. In this paper, machine learning algorithms (support vector machine and random forest) are involved in detecting liver diseases and determining whether donors are suitable to donate blood from blood values. This paper is applied research that found that the performance measures of the random forest algorithm achieved excellent performance in identifying suitable people to donate blood.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Food resources in food system technology: Bifunctional food system technology based on pickering emulsions

Food resources in food system technology: Bifunctional food ...

引用

6th Smart Cities Symposium (SCS 2022)

作者： I. Potoroko A. Kadi A. Paymulina U. Bagale M. Abotaleb E. M. El-Kenawy Department of Food and Biotechnology South Ural State University Chelyabinsk Russia Siberian Federal Scientific Center of Agro-Bio Technologie Novosibirsk Russia Department of System Programming South Ural State University Chelyabinsk Russia Department of Communications and Electronics Delta Higher Institute of Engineering and Technology Mansoura Egypt

The development of domestically generated food additives based on eco-technologies with specified functionaltechnological and bioactive qualities is now a significant focus of contemporary study. Pickering emulsions are more stable both physically and chemically, making them a highly promising method of introducing biologically active chemicals into the body. The purpose of this research was to determine if ultrasound could be used to create a bioactive colloidal Pickering emulsion system using flax cellulose or brown algal polysaccharides as a stabilizer. Pickering emulsions stabilized with fucoidan, sodium alginate, or flax cellulose, based on a lipid fraction of sunflower oil and cinnamon oil blend, or a lipid fraction of linseed oil, were applied to the subjects, who were then subjected to ultrasound treatment at 630W/l for 16 min (4 min on, 3 min off) at a controlled temperature of 50°C. The results obtained demonstrate the effectiveness of using ultrasonic exposure to create bioactive Pickering emulsion colloidal systems. Fucoidan stabilizes pickering emulsion, with the highest AOA values (5.120±0.005 DPPH, %) and a rise in AOA values in linseed oil-based emulsion samples from 30% to 100% in comparison to emulsion samples based on a blend of lipid phases. The viscoelastic characteristics of Pickering emulsions with various oil fractions vary dramatically for the integrated structure-forming components.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Methodology of Teaching programming Science Through Online Platforms

Methodology of Teaching Programming Science Through Online P...

引用

Informatics, Electronics, and Radio Engineering (PIERE), International Conference Problems of

作者： Akram Nishanov Oybek Allamov Janar Yusupova Marks Matyakubov Baxtiyor Qalandarov Reyimberganov Bahrom Department of Systematic and Practical Programming Tashkent University of Information Technologies named after Muhammad al-Khwarizmi Tashkent Uzbekistan Department of Software Engineering Urgench Branch of Tashkent University of Information Technology named after Muhammad al-Khwarizmi Urgench Uzbekistan Master of Urgench branch of TATU named after Muhammad al-Khwarizmi Urgench Branch of Tashkent University of Information Technology named after Muhammad al-Khwarizmi Urgench Uzbekistan Student of Urgench branch of TATU named after Muhammad al-Khwarizmi Urgench Branch of Tashkent University of Information Technology named after Muhammad al-Khwarizmi Urgench Uzbekistan

ISBN: (数字)9798331516321

ISBN: (纸本)9798331516338

This article presents an experiment conducted among students of the Faculty of “Software Engineering” of the Urgench branch of TATU named after Muhammad al-Khwarizmi. Teaching programming using online platforms in education has shown promising results in improving student outcomes. This article discusses the methodology used, the comparative results, and the impact of the platform on software education. The rapid adoption of online platforms in education has changed the way programming is taught, providing students with an interactive, hands-on learning environment. This shift is especially relevant in teaching programming, where real-time feedback and practice are essential to mastering algorithms and coding concepts. The study compared two groups: one was trained using the https://***/platform and the assignments were checked using this system, and the second group was trained using traditional methods. The results showed that students who used the online platform had a high level of mastery, which highlighted the effectiveness of integrating https://***/into programming education.

关键词： Education Software algorithms Real-time systems Software Encoding Computer science education Problem-solving Informatics programming profession

来源：评论

学校读者我要写书评

暂无评论

Comparative Study for Classification Methods to Predict and Detect Epilepsy Seizure 5

Comparative Study for Classification Methods to Predict and ...

引用

5th IEEE Middle East and Africa Conference on Biomedical Engineering, MECBME 2020

作者： El Halabi, Nashaat Abi Zeid Daou, Roy Achkar, Roger Hayek, Ali Boercsoek, Josef American University of Science and Technology Department of Computer and Communications Engineering Faculty of Engineering Beirut Lebanon Faculty of Public Health Biomedical Technologies Department Jounieh Lebanon American University of Science and Technology Department of Computer and Communications Engineering Faculty of Engineering Beirut Lebanon Computer Science University of Kassel Department of Computer Architecture and System Programming Faculty of Electrical Engineering Germany Computer Science University of Kassel Department of Computer Architecture and System Programming Faculty of Electrical Engineering Germany

ISBN: (纸本)9781728123585

Epilepsy is a medical problem that tackles lots of patients. It limits the life activity of such patients due to the seizures that occur anytime and anywhere. Thus, creating a monitoring system that could make their life easier and allow them to perform daily life activities as safe as possible has been studied. This paper is a continuity for a project where a system monitors epileptic patients using a set of wearable sensors connected to several processing units, the main sensors are Electroencephalogram (EEG) for the electrical activity of the brain, electrocardiogram (ECG) for the electrical activity of the heart, and accelerometers to monitor the posture of the patient, features extracted from EEG and ECG signals are used for prediction/detection of seizures. Thus, the objective of this paper is to present a comparative study in order to choose the appropriate classification method for seizure prediction and detection. Five classification methods were studied: Decision Trees, Discriminant Analysis, Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Ensemble Learning. For each of the classification methods, the accuracy, the specificity, the sensitivity, the precision, the false detection rate and the Fmeasure were studied and compared. The results for seizure prediction system show that the highest accuracy, specificity and F-Measure, and lowest false detection rate were achieved with Bagged Trees Ensemble Learning, the highest sensitivity and precision were achieved with Quadratic Support Vector Machine. However, for seizure detection system, the highest accuracy and F-Measure were achieved with Linear Support Vector, the highest sensitivity and specificity were achieved with Fine Gaussian Support Vector Machine, and the highest precision and lowest false detection rate were achieved with Subspace Discriminant Ensemble Learning. © 2020 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Solution of the Retail Marketing Problem of Rational Choice of the Location of Trade Enterprises Using the Method of Hierarchy Analysis and Fuzzy Set Theory 1

引用

14th International Conference on Applications of Fuzzy Systems, Soft Computing, and Artificial Intelligence Tools, ICAFS 2020

作者： Veliyev, Ahmed Abdullayev, Tarlan Alekperov, Ramiz Salahli, Vuqar Odlar Yurdu Univercity BakuAZ1072 Azerbaijan Scientific Affairs Odlar Yurdu Univercity BakuAZ1072 Azerbaijan Informathion Technology and Programming Azerimed LLC BakuAZ1147 Azerbaijan Department of Computer Engineering Odlar Yurdu Univercity BakuAZ1072 Azerbaijan

ISBN: (数字)9783030640583

ISBN: (纸本)9783030640576

The principles of solving the multicriteria problem of retail marketing for the rational choice of the location of trade enterprises (alternatives) based on the classical method of analysis of Saaty hierarchies, using the theory of fuzzy sets, are considered. The choice of the best alternative is carried out on the basis of the arguments of the maxima (abbreviated arg max), as the arguments, which are evaluated based on the operation of intersection of fuzzy sets of criteria. This approach is very practical from the point of view of using the experience and intuition of marketing workers and requires minimal costs to solve similar problems. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Fuzzy set theory

来源：评论

学校读者我要写书评

暂无评论

The Regularization of Small Sub-Constraint Satisfaction Problems 22nd

The Regularization of Small Sub-Constraint Satisfaction Prob...

引用

22nd International Conference on Applications of Declarative programming and Knowledge Management, INAP 2019, the 33rd Workshop on Logic programming, WLP 2019, and the 27th Workshop on Functional and Constraint Logic programming, WFLP 2019

作者： Löffler, Sven Liu, Ke Hofstedt, Petra Department of Mathematics and Computer Science MINT Programming Languages and Compiler Construction Group Brandenburg University of Technology Cottbus-Senftenberg Konrad-Wachsmann-Allee 5 Cottbus03044 Germany

ISBN: (纸本)9783030467135

This paper describes a new approach on optimization of constraint satisfaction problems (CSPs) by means of substituting sub-CSPs with locally consistent regular membership constraints. The purpose of this approach is to reduce the number of fails in the resolution process, to improve the inferences made during search by the constraint solver by strengthening constraint propagation, and to maintain the level of propagation while reducing the cost of propagating the constraints. Our experimental results show improvements in terms of the resolution speed compared to the original CSPs and a competitiveness to the recent tabulation approach [1, 15]. Besides, our approach can be realized in a preprocessing step, and therefore wouldn’t collide with redundancy constraints or parallel computing if implemented. © 2020, Springer Nature Switzerland AG.

关键词： Constraint satisfaction problems

来源：评论

学校读者我要写书评

暂无评论

Design of Intelligent Decision Support System With Ensembled Machine Learning to Predict Students' Performance

Design of Intelligent Decision Support System With Ensembled...

引用

Communication, Computer Sciences and Engineering (IC3SE), International Conference on

作者： S Deepan Dineshkumar Rajendran Navdeep Dhaliwal K Praveena Melanie Lourens Anandhi R J School of CS & AI SR University Warangal Telangana India Computer Games Design and Programming School of Computing and Innovative Technologies British University Vietnam Vietnam Lovely Professional University Phagwara India Institute of Aeronautical Engineering Dundigal Hyderabad Deputy Dean Faculty of Management Sciences Durban University of Technology South Africa Department of Information Science Engineering New Horizon College of Engineering Bangalore

ISBN: (数字)9798350366846

ISBN: (纸本)9798350366853

Evaluating student performance is important for universities and institutions in the current student education landscape because it helps them create models that work better for students. The automation of various features related to fundamental student traits and behaviours that manage massive amounts of data efficiently processes these. To handle student records that included information about students' behaviour and how it related to their academic performance, the companies employed models of classification with mining concepts. Additionally, the quality of result classification can be substantially improved by using learning analytics and Educational Data Mining (EDM). The educational establishments are making an effort to lower the low student performance. To address this issue, numerous methods for assessing student performance have been devised, allowing the relevant faculties to intervene and enhance the final product. Three classes—Low Performance Student, Average Student, and Smart Student—were created using the K-Mean Clustering methodology for classifying student records. Features including grade point, number of deficits, student attendance, medium of education, and board of education are taken into account when classifying the data. In this case, the WEKA tool is also utilized for implementing the model and outcome assessments.

关键词： Deep learning Decision support systems Analytical models Data analysis Automation Education Companies

来源：评论

学校读者我要写书评

暂无评论

A Horizontal Federated Learning Approach to IoT Malware Traffic Detection: An Empirical Evaluation with N-BaIoT Dataset

A Horizontal Federated Learning Approach to IoT Malware Traf...

引用

International Conference on Advanced Communication technology (ICACT)

作者： Phuc Hao Do Tran Duc Le Vladimir Vishnevsky Aleksandr Berezkin Ruslan Kirichek The Bonch-Bruevich Saint-Petersburg State University of Telecommunications Saint-Petersburg Russia Danang Architecture University Da Nang Viet Nam Department of Communication Networks and Data Transmission at Bonch-Bruevich Saint-Petersburg State University of Telecommunications Russia University of Science and Technology - The University of Danang Da Nang Viet Nam Information Technology Faculty The University of Danang - University of Science and Technology Danang Vietnam V. A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences Moscow Russia Institute of Control Sciences of Russian Academy of Sciences Russia Department of Programming Engineering and Computer Science Bonch Bruevich Saint Petersburg State University of Telecommunications

The increasing prevalence of botnet attacks in IoT networks has led to the development of deep learning techniques for their detection. However, conventional centralized deep learning models pose challenges in simultaneously ensuring user data privacy and detecting botnet attacks. To address this issue, this study evaluates the efficacy of Federated Learning (FL) in detecting IoT malware traffic while preserving user privacy. The study employs N-BaIoT, a dataset of real-world IoT network traffic infected by malware, and compares the effectiveness of FL models using Convolutional Neural Network, Long Short-Term Memory, and Gated Recurrent Unit models with a centralized approach. The results indicate that FL can achieve high performance in detecting abnormal traffic in IoT networks, with the CNN model yielding the best results among the three models evaluated. The study recommends the use of FL for IoT malware traffic detection due to its ability to preserve data privacy.

关键词：

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：