检索结果-内蒙古大学图书馆

Effect of Laplacian Smoothing Stochastic Gradient Descent with Angular Margin Softmax Loss on Face Recognition 2nd

学校读者我要写书评

暂无评论

Effect of Laplacian Smoothing Stochastic Gradient Descent wi...

2nd International Conference on Intelligent Technologies and Applications, INTAP 2019

作者： Iqbal, Mansoor Rehman, Muhammad Awais Iqbal, Naveed Iqbal, Zaheer Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei China Department of Electrical and Computer Engineering Air University Islamabad Pakistan Mathematics Department Faculty of Science University of Hail Hail Saudi Arabia School of Sciences Tianjin University TJU Tianjin China

ISBN: (纸本)9789811552311

An important task in deep learning for face recognition is to use proper loss functions and optimization technique. Several loss functions have been proposed using stochastic gradient descent for this task. The main purpose of this work is to propose the strategy to use the Laplacian smoothing stochastic gradient descent with combination of multiplicative angular margin to enhance the performance of angularly discriminative features of angular margin softmax loss for face recognition. The model is trained on a most popular face recognition dataset CASIA-WebFace and it achieves the state-of-the-art performance on several academic benchmark datasets such as Labeled Face in the Wild (LFW), YouTube Faces (YTF), VGGFace1 and VGGFace2. Our method achieves a new record accuracy of 99.54% on LFW dataset. On YTF dataset it achieves 95.53% accuracy. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Face recognition

Fast Linear Speed Response Based on SMC with Finite-Control-Set Model Predictive Flux Control for Linear Induction Motor

学校读者我要写书评

暂无评论

Fast Linear Speed Response Based on SMC with Finite-Control-...

Conference Record of the IEEE Industry Applications Society Annual Meeting (IAS)

作者： Mahmoud F. Elmorshedy Md Rabiul Islam Wei Xu Fayez F. M. El-Sousy Syed Arslan Bukhari Faculty of Engineering Tanta University Tanta Egypt School of Electrical Computer and Telecommunications Engineering University of Wollongong NSW Australia School of Electrical and Electronic Engineering Huazhong University of Science and Technology Wuhan China Prince Sattam bin Abdulaziz University Al-Kharj Saudi Arabia

ISBN: (纸本)9781728164021

The fast response of linear speed for linear induction motors (LIMs) based on sliding mode control with finite-control-set model predictive flux control is proposed in this paper. In this proposed method, the linear speed is controlled using the sliding mode control (SMC) instead of the proportional-integral (PI) control. Besides, the finite-control-set (FCS) depends on the primary flux only, hence the weighting factor is eliminated. Furthermore, the calculation processes reduce as the primary flux is only required in the prediction stage. The proposed control method is applied to guarantee lower thrust ripples. All variables and states for estimation, prediction, and cost function are in the αβ-coordinates. During the modeling of the LIMs and the proposed control process, the end-effect is taken into consideration. The proposed SMC with the FCS-MPC is compared with the PI with the FCS-MPC under variable linear speed and load thrust variation. The proposed SMC with FCS-MPC can achieve a faster dynamic response over PI. A 3kW setup of the arc induction machine is used to verify the performance of the proposed control strategy.

关键词： PI control Induction motors Simulation Velocity control Industry applications Process control Estimation

Dress-up: Deep Neural Framework for Image-based Human Appearance Transfer

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2022年

作者： Ghodhbani, Hajer Neji, Mohamed Qahtani, Abdulrahman M. Almutiry, Omar Dhahri, Habib Alimi, Adel M. BP 1173 Sfax3038 Tunisia National School of Electronics and Telecommunications of Sfax Technopark BP 1163 SfaxCP 3018 Tunisia Department of Computer Science College of Computers and Information Technology Taif University P.O.Box. 11099 Taif21944 Saudi Arabia College of Applied Computer Science King Saud University Riyadh Saudi Arabia Department of Electrical and Electronic Engineering Science Faculty of Engineering and the Built Environment University of Johannesburg South Africa

The fashion industry is at the brink of radical transformation. The emergence of Artificial Intelligence (AI) in fashion applications creates many opportunities for this industry. Interesting to this matter, we proposed a flexible person generation system for virtual try-on, presented in this paper, and aiming to treat the task of human appearance transfer across images while preserving texture details and structural coherence of the generated outfit. This challenging task has drawn increasing attention and made huge development of intelligent fashion applications. However, this task requires different challenges, especially, in the case of a wide divergences between the source and target images. To solve this problem, we proposed a flexible person generation framework called Dress-up to treat the 2D virtual try-on task. Dress-up is an end-to-end generation pipeline with three modules based on the task of image-to-image translation aiming to sequentially interchange garments between images, and produce dressing effects not achievable by existing works. The core idea of our solution is to explicitly encode the body pose and the target clothes by a pre-processing module based on the segmentation process. Then, a conditional adversarial network is implemented to generate target segmentation feeding to the alignment and translation networks to generate the final output. Our experimental results on the widely used DeepFashion dataset demonstrate that Dress-up provides significant results over the state-of-the-art methods on the subject of output quality despite different interactions of garments, and handles the virtual try-on task with a weakly supervised manner. © 2022, CC BY.

关键词： Textures

On the utility of power spectral techniques with feature selection techniques for effective mental task classification in non-invasive BCI

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Gupta, Akshansh Agrawal, Ramesh Kumar Kirar, Jyoti Singh Andreu-Perez, Javier Ding, Wei-Ping Lin, Chin-Teng Prasad, Mukesh School of Computer and Systems Sciences Jawaharlal Nehru University New Delhi India School of Computer Science and Electronic Engineering University of Essex United Kingdom Faculty of Medicine Imperial College London United Kingdom School of Computer and Technology Nantong University Nantong China Centre for Artifical Intelligence School of Software Feit University of Technology Sydney Australia

In this paper classification of mental task-root Brain-computer Interfaces (BCI) is being investigated, as those are a dominant area of investigations in BCI and are of utmost interest as these systems can be augmented life of people having severe disabilities. The BCI model's performance is primarily dependent on the size of the feature vector, which is obtained through multiple channels. In the case of mental task classification, the availability of training samples to features are minimal. Very often, feature selection is used to increase the ratio for the mental task classification by getting rid of irrelevant and superfluous features. This paper proposes an approach to select relevant and non-redundant spectral features for the mental task classification. This can be done by using four very known multivariate feature selection methods viz, Bhattacharya's Distance, Ratio of Scatter Matrices, Linear Regression and Minimum Redundancy & Maximum Relevance. This work also deals with a comparative analysis of multivariate and univariate feature selection for mental task classification. After applying the above-stated method, the findings demonstrate substantial improvements in the performance of the learning model for mental task classification. Moreover, the efficacy of the proposed approach is endorsed by carrying out a robust ranking algorithm and Friedman's statistical test for finding the best combinations and comparing different combinations of power spectral density and feature selection methods. © 2021, CC BY-NC-ND.

关键词： Feature extraction

Phase chimera states on non-local hyperrings

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Muolo, Riccardo Njougouo, Thierry Gambuzza, Lucia Valentina Carletti, Timoteo Frasca, Mattia Department of Systems and Control Engineering Tokyo Institute of Technology Tokyo152-8552 Japan Department of Mathematics University of Namur NamurB5000 Belgium naXys Namur Institute for Complex Systems University of Namur NamurB5000 Belgium Faculty of Computer Science University of Namur NamurB5000 Belgium Department of Electrical and Electronic Engineering University of Buea P.O. Box 63 Buea Cameroon Department of Electrical Electronics and Computer Science Engineering University of Catania Catania95125 Italy Istituto di Analisi dei Sistemi ed Informatica "A. Ruberti" IASI-CNR Roma00185 Italy

Chimera states are dynamical states where regions of synchronous trajectories coexist with incoherent ones. A significant amount of research has been devoted to study chimera states in systems of identical oscillators, non-locally coupled through pairwise interactions. Nevertheless, there is an increasing evidence, also supported by available data, that complex systems are composed by multiple units experiencing many-body interactions, that can be modeled by using higher-order structures beyond the paradigm of classic pairwise networks. In this work we investigate whether phase chimera states appear in this framework, by focusing on a novel topology solely involving many-body, non-local and non-regular interactions, hereby named non-local d-hyperring, being (d + 1) the order of the interactions. We present the theory by using the paradigmatic Stuart-Landau oscillators as node dynamics, and show that phase chimera states emerge in a variety of structures and with different coupling functions. For comparison, we show that, when higher-order interactions are"flattened" to pairwise ones, the chimera behavior is weaker and more elusive. © 2023, CC BY.

关键词： Dynamics

Optimizing Global Genomic Surveillance for Early Detection of Emerging SARS-CoV-2 Variants

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Gu, Haogao Li, Jifan Sun, Wanying Li, Mengting Leung, Kathy Wu, Joseph T. Yuan, Hsiang-Yu Wang, Maggie H. Yang, Bingyi McKay, Matthew R. Ning, Ning Poon, Leo L.M. School of Public Health LKS Faculty of Medicine The University of Hong Kong Hong Kong Department of Statistics Texas A&M University United States Hong Kong Science and Technology Park Hong Kong HKJC Global Health Institute LKS Faculty of Medicine The University of Hong Kong Hong Kong Department of Biomedical Sciences Jockey Club College of Veterinary Medicine and Life Sciences City University of Hong Kong Hong Kong Centre for Applied One Health Research and Policy Advice Jockey Club College of Veterinary Medicine and Life Sciences City University of Hong Kong Hong Kong JC School of Public Health and Primary Care Faculty of Medicine the Chinese University of Hong Kong Hong Kong Department of Electrical and Electronic Engineering University of Melbourne ParkvilleVIC3010 Australia Department of Microbiology and Immunology The Peter Doherty Institute for Infection and Immunity University of Melbourne MelbourneVIC3000 Australia Victorian Infectious Diseases Reference Laboratory Royal Melbourne Hospital the Peter Doherty Institute for Infection and Immunity Victoria Australia Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Centre for Immunology & Infection Hong Kong Science and Technology Park Hong Kong HKU-Pasteur Research Pole School of Public Health LKS Faculty of Medicine The University of Hong Kong Hong Kong

The global spread of viruses underscores the critical need for effective genomic surveillance to detect emerging variants and guide interventions. However, high costs and uneven resource distribution hinder its global implementation. This study demonstrates that optimizing genomic surveillance by targeting resources on international travelers in travel hubs, significantly improves the early detection of SARS-CoV-2 variants. Using a metapopulation multiple-strain model calibrated with extensive data, we show that targeting travelers effectively reduces detection delays without additional costs in retrospective analyses of the Omicron variant outbreak. Further, simulations indicate that focusing surveillance on key travel hubs outperform baseline practices in detecting future variants, even with reduced resources. This approach also remains effective in future pandemic scenarios with varying reproductive numbers (Reff) and vaccine effectiveness. These findings provide a sustainable framework for strengthening health security, offering actionable insights for optimizing genomic surveillance and improving preparedness for emerging infectious threats. Copyright © 2025, The Authors. All rights reserved.

关键词： Coronavirus

Solar-powered automated fish-feeding boat: A cost-effective and sustainable solution for aquaculture

学校读者我要写书评

暂无评论

Aquacultural engineering 2025年 111卷

作者： Abdullah Al Fahim Tanzi Ahmed Chowdhury Mohammed Abdul Kader Mayeen Uddin Khandaker Department of Nuclear Engineering Faculty of Science & Technology Chittagong University of Engineering and Technology Chattogram 4349 Bangladesh Department of Computer Science & Engineering Faculty of Engineering BGC Trust University Bangladesh Chattogram 4318 Bangladesh Department of Electrical & Electronic Engineering Faculty of Engineering International Islamic University Chattogram Kumira Bangladesh Applied Physics and Radiation Technologies Group CCDCU Faculty of Engineering and Technology Sunway University Bandar Sunway Selangor 47500 Malaysia Faculty of Graduate Studies Daffodil International University Daffodil Smart City Birulia Savar Dhaka 1216 Bangladesh Department of Physics College of Science Korea University 145 Anam-ro Seongbuk-gu Seoul 02841 Republic of Korea

Aquaculture is a rapidly growing industry that is increasingly recognized as a vital source of nutrition for the world's expanding population. Traditional fish farming is labor-intensive and non-technical, with unskilled workers and unorganized feed distribution resulting in high costs and environmental deterioration. To address these concerns, a solar-powered, automated fish-feeding boat has been designed and implemented in this study. This innovative system utilizes machine learning and a microcontroller-based control unit (i.e., a memory and input/output interface with I2C communication protocol) to deliver feed at a predetermined time at precise intervals in each day without human intervention, ensuring optimal fish nutrition and growth. The integration of solar power into the boat's operation exemplifies a commitment to environmentally sustainable practices by significantly reducing its carbon footprint. Furthermore, the automation of the fish-feeding process not only minimizes reliance on manual labor but also contributes to substantial cost savings, heightened operational precision, and improved overall efficiency. Collectively, these advancements enhance the economic sustainability and efficient management of aquaculture ventures.

关键词：

AC-DC Cuk Converter: A State-of-the-Art topological review

学校读者我要写书评

暂无评论

Energy Conversion and Management: X 2025年 27卷

作者： Istiak Ahmed Asif Imties Alvy Irfan Rahman Md. Abdullah Al Hossain Showrov Rahman Abdullah Al-Hysam Abdur Razzak Department of Electrical and Electronic Engineering Independent University Bangladesh (IUB) Dhaka 1229 Bangladesh Department of Electrical and Electronic Engineering Islamic University of Technology Gazipur 1704 Dhaka Bangladesh Department of Electrical Computer & Biomedical Engineering University of Rhode Island RI USA Division of Industrial Electrical Engineering and Automation Faculty of Engineering Lund University Box 117 SE-221 00 Lund Sweden Department of Electric Power Engineering Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Mÿegyetem rkp. 3. H-1111 Budapest Hungary

AC-DC converters, which transform alternating current (AC) into controlled direct current (DC), are key instruments for systems requiring stable and efficient power conversion. Among various AC-DC topologies, the Cuk converter topology is increasingly used for power factor correction (PFC) applications, enabling efficient power conversion for various industrial and household devices. Despite its growing adoption in AC-DC applications, the existing literature does not thoroughly examine the technical aspects of the modern Cuk topologies. This paper seeks to fill this gap by comprehensively analyzing recent topological advancements in AC-DC Cuk converters, encompassing their categorizations, performance attributes, and applications. The evaluation and review of the prominent converter topologies have been summarized in a tabular format, presenting essential converter metrics, including component counts, operation modes, isolation and rectification styles, power ratings, power factor, and total harmonic distortion (THD). The paper aims to provide valuable insights for researchers, design engineers, and manufacturers through technical comparison and topology evaluation. In addition, the related technical issues and challenges regarding selecting a suitable converter topology are addressed in this article.

关键词： AC-DC converter Cuk converter Power factor Total harmonic distortion

Bugs in our pockets: The risks of client-side scanning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Abelson, Hal Anderson, Ross Bellovin, Steven M. Benaloh, Josh Blaze, Matt Callas, Jon Diffie, Whitfield Landau, Susan Neumann, Peter G. Rivest, Ronald L. Schiller, Jeffrey I. Schneier, Bruce Teague, Vanessa Troncoso, Carmela The Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology The University of Cambridge The University of Edinburgh Columbia University Affiliate Faculty Columbia Law School Microsoft Research The Paul G. Allen School of Computer Science and Engineering The University of Washington Department of Computer Science Georgetown University The Electronic Frontier Foundation The Fletcher School The School of Engineering Department of Computer Science Tufts University The Computer Science Laboratory SRI International Massachusetts Institute of Technology Harvard Kennedy School The Research School of Computer Science The Australian National University

Our increasing reliance on digital technology for personal, economic, and government affairs has made it essential to secure the communications and devices of private citizens, businesses, and governments. This has led to pervasive use of cryptography across society. Despite its evident advantages, law enforcement and national security agencies have argued that the spread of cryptography has hindered access to evidence and intelligence. Some in industry and government now advocate a new technology to access targeted data: client-side scanning (CSS). Instead of weakening encryption or providing law enforcement with backdoor keys to decrypt communications, CSS would enable on-device analysis of data in the clear. If targeted information were detected, its existence and, potentially, its source, would be revealed to the agencies;otherwise, little or no information would leave the client device. Its proponents claim that CSS is a solution to the encryption versus public safety debate: it offers privacy-in the sense of unimpeded end-to-end encryption-and the ability to successfully investigate serious crime. In this report, we argue that CSS neither guarantees efficacious crime prevention nor prevents surveillance. Indeed, the effect is the opposite. CSS by its nature creates serious security and privacy risks for all society while the assistance it can provide for law enforcement is at best problematic. There are multiple ways in which client-side scanning can fail, can be evaded, and can be abused. Its proponents want CSS to be installed on all devices, rather than installed covertly on the devices of suspects, or by court order on those of ex-offenders. But universal deployment threatens the security of law-abiding citizens as well as lawbreakers. Technically, CSS allows end-to-end encryption, but this is moot if the message has already been scanned for targeted content. In reality, CSS is bulk intercept, albeit automated and distributed. As CSS gives government agenc

关键词： Scanning