检索结果-内蒙古大学图书馆

Dealing with Unbalanced Data in Leaf Disease Detection: A Comparative Study of Hierarchical Classification, Clustering-based Undersampling and Reweighting-based Approaches

学校读者我要写书评

暂无评论

Procedia computer science 2023年 225卷 4891-4900页

作者： Haythem Ghazouani Walid Barhoumi Ezzeddine Chakroun Abdellah Chehri Université de Tunis El Manar Institut Supérieur d'Informatique d'El Manar Research Team on Intelligent Systems in Imaging and Artificial Vision (SIIVA) LR16ES06 Laboratoire de recherche en Informatique Mode´lisation et Traitement de l'Information et de la Connaissance (LIMTIC) 2 Rue Abou Rayhane Bayrouni 2080 Ariana Tunisia Université de Carthage Ecole Nationale d'Ingénieurs de Carthage 45 Rue des Entrepreneurs 2035 Tunis-Carthage Tunisia Department of Mathematics and Computer Science Royal Military College of Canada Girouard Building Room 320

Precision agriculture plays a crucial role in optimizing crop yield, reducing environmental impact, and ensuring sustainable agricultural practices. Early detection and accurate diagnosis of leaf diseases are essential for preventing significant losses in crop production and maintaining food security. However, the inherent challenge of class imbalance in leaf disease datasets poses a significant obstacle for machine learning algorithms. In this paper, we explore and compare different techniques for handling class imbalance in leaf disease detection to improve the accuracy and reliability of machine learning models in the context of precision agriculture. We investigated the performance of different methods for leaf disease detection using the challenging New Plant Diseases Dataset (NPDD), which consists of image-based plant leaves. Our experiments reveal promising results, particularly with the hierarchical approach, achieving an accuracy of 97.17%. The outcomes of our study contribute to the growing body of knowledge in precision agriculture by providing a comprehensive analysis of techniques for handling class imbalance in leaf disease detection. Furthermore, our findings serve as a valuable resource for researchers and practitioners in the field, offering guidance on selecting and implementing the most effective approaches to tackle class imbalance challenges and improving the overall performance and reliability of machine learning models in the domain of precision agriculture.

关键词： Leaf disease detection unbalanced data Clustering-based undersampling, Reweighting-based training, Hierarchical classification

The Efficacy of Semantics-Preserving Transformations in Self-Supervised Learning for Medical Ultrasound

学校读者我要写书评

暂无评论

arXiv 2025年

作者： VanBerlo, Blake Wong, Alexander Hoey, Jesse Arntfield, Robert Cheriton School of Computer Science University of Waterloo ONN2L 3G1 Canada Department of Systems Design Engineering University of Waterloo ONN2L 3G1 Canada Schulich School of Medicine and Dentistry Western University ONN6A 3K7 Canada

Data augmentation is a central component of joint embedding self-supervised learning (SSL). Approaches that work for natural images may not always be effective in medical imaging tasks. This study systematically investigated the impact of data augmentation and preprocessing strategies in SSL for lung ultrasound. Three data augmentation pipelines were assessed: (1) a baseline pipeline commonly used across imaging domains, (2) a novel semantic-preserving pipeline designed for ultrasound, and (3) a distilled set of the most effective transformations from both pipelines. Pretrained models were evaluated on multiple classification tasks: B-line detection, pleural effusion detection, and COVID-19 classification. Experiments revealed that semantics-preserving data augmentation resulted in the greatest performance for COVID-19 classification - a diagnostic task requiring global image context. Cropping-based methods yielded the greatest performance on the B-line and pleural effusion object classification tasks, which require strong local pattern recognition. Lastly, semantics-preserving ultrasound image preprocessing resulted in increased downstream performance for multiple tasks. Guidance regarding data augmentation and preprocessing strategies was synthesized for practitioners working with SSL in ultrasound. Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

Bias-tailored quantum LDPC codes

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Roffe, Joschka Cohen, Lawrence Z. Quintavalle, Armanda O. Chandra, Daryus Campbell, Earl T. Dahlem Center for Complex Quantum Systems Freie Universität Berlin Berlin14195 Germany Department of Physics and Astronomy University of Sheffield SheffieldS3 7RH United Kingdom Centre for Engineered Quantum Systems School of Physics University of Sydney SydneyNSW2006 Australia Riverlane CambridgeCB2 3BZ United Kingdom School of Electronics and Computer Science University of Southampton SouthamptonSO17 1BJ United Kingdom AWS Center for Quantum Computing CambridgeCB1 2GA United Kingdom

Bias-tailoring allows quantum error correction codes to exploit qubit noise asymmetry. Recently, it was shown that a modified form of the surface code, the XZZX code, exhibits considerably improved performance under biased noise. In this work, we demonstrate that quantum low density parity check codes can be similarly bias-tailored. We introduce a bias-tailored lifted product code construction that provides the framework to expand bias-tailoring methods beyond the family of 2D topological codes. We present examples of bias-tailored lifted product codes based on classical quasi-cyclic codes and numerically assess their performance using a belief propagation plus ordered statistics decoder. Our Monte Carlo simulations, performed under asymmetric noise, show that bias-tailored codes achieve several orders of magnitude improvement in their error suppression relative to depolarising noise. © 2022, CC BY.

关键词： Belief propagation

Feature Extraction and Classification from Planetary science Datasets enabled by Machine Learning

学校读者我要写书评

暂无评论

Feature Extraction and Classification from Planetary Science...

IEEE Conference on Aerospace

作者： Conor A. Nixon Zachary Yahn Ethan Duncan Ian Neidel Alyssa C. Mills Benoît Seignovert Andrew Larsen Kathryn Gansler Charles Liles Catherine C. Walker Douglas M. Trent John Santerre Planetary Systems Laboratory NASA Goddard Space Flight Center Greenbelt MD Computer Science Department University of Virginia Charlottesville VA School of Information University of California Berkeley Berkeley CA Yale University Timothy Dwight College New Haven CT Geosciences Department Baylor University Waco TX Nantes Université Laboratoire De Planétologie Et Géosciences Nantes France Business Intelligence Division Inntopia Stowe VT Department of Geology University of Maryland College Park MD NASA Langley Research Center Center Operations Directorate Virginia Department of Applied Ocean Physics and Engineering Woods Hole Oceanographic Institution Massachusetts OCIO Information Data & Analytics Services SAIC | East-2 NASA Langley Research Center Virginia

In this paper we present two examples of recent investigations that we have undertaken, applying Machine Learning (ML) neural networks (NN) to image datasets from outer planet missions to achieve feature recognition. Our first investigation was to recognize ice blocks (also known as rafts, plates, polygons) in the chaos regions of fractured ice on Europa. We used a transfer learning approach, adding and training new layers to an industry-standard Mask R-CNN (Region-based Convolutional Neural Network) to recognize labeled blocks in a training dataset. Subsequently, the updated model was tested against a new dataset, achieving 68% precision. In a different application, we applied the Mask R-CNN to recognize clouds on Titan, again through updated training followed by testing against new data, with a precision of 95% over 369 images. We evaluate the relative successes of our techniques and suggest how training and recognition could be further improved. The new approaches we have used for planetary datasets can further be applied to similar recognition tasks on other planets, including Earth. For imagery of outer planets in particular, the technique holds the possibility of greatly reducing the volume of returned data, via onboard identification of the most interesting image subsets, or by returning only differential data (images where changes have occurred) greatly enhancing the information content of the final data stream.

关键词： Training Earth Image recognition Transfer learning Streaming media Feature extraction Ice

Sliding Mode Control of the PUMA 560 Robot

学校读者我要写书评

暂无评论

Sliding Mode Control of the PUMA 560 Robot

International Conference on Control, Automation and Diagnosis (ICCAD)

作者： Arezki Fekik Ahmad Taher Azar Mohamed Lamine Hamida Hakim Denoun Dyhia Kais Sabrina Mohand Saidi Amar Bousbaine Nashwa Ahmad Kamal Ammar K. Al Mhdawi Chakib Ben Njima Department of Electrical Engineering University Akli Mohand Oulhadj-Bouria Bouira Algeria Electrical Engineering Advanced Technology Laboratory (LATAGE) Algeria Automated Systems & Soft Computing Lab (ASSCL) Prince Sultan University Riyadh Saudi Arabia College of Computer & Information Sciences Prince Sultan University Riyadh Saudi Arabia Faculty of Computers and Artificial Intelligence Benha University Egypt Department of Electrical Engineering L2CSP Laboratory Mouloud Mammeri University Algeria University of Derby College of Science and Engineering UK Faculty of Engineering Cairo University Giza Egypt Edge Hill University U.K University of Sousse Tunisia

The purpose of this article is to present the application of the sliding mode control and investigate its effectiveness when applied to a three-dimensional robotic manipulator model. The analysis is based on the application of the sliding mode control law for the PUMA 560 model, three degrees of freedom, through the development of a dynamic simulation model. The simulation results show the effectiveness of this proposed method for the automation of industrial applications, such as assembly, machining (deburring, trimming), and surface tracking (polishing). This technique provides a useful insight into the advantages of using sliding mode control laws in robotics applications.

关键词：

Non-Volatile Resistive Switching of Polymer Residues in 2D Material Memristors

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Braun, Dennis Ganeriwala, Mohit D. Völkel, Lukas Ran, Ke Lukas, Sebastian Marín, Enrique G. Hartwig, Oliver Prechtl, Maximilian Wahlbrink, Thorsten Mayer, Joachim Duesberg, Georg S. Godoy, Andrés Daus, Alwin Lemme, Max C. Electronic Devices RWTH Aachen University Otto-Blumenthal-Str. 2 Aachen52074 Germany Department of Electronics and Computer Science Universidad de Granada Avenida de la Fuente Nueva S/N Granada18071 Spain RWTH Aachen University Ahornstr. 55 Aachen52074 Germany Forschungszentrum Jülich Jülich52425 Germany Center for Integrated Sensor Systems University of the Bundeswehr Munich Neubiberg85577 Germany AMO GmbH Advanced Microelectronic Center Aachen Otto-Blumenthal-Str. 25 Aachen52074 Germany

Two-dimensional (2D) materials are popular candidates for emerging nanoscale devices, including memristors. Resistive switching (RS) in such 2D material memristors has been attributed to the formation and dissolution of conductive filaments created by the diffusion of metal ions between the electrodes. However, the area-scalable fabrication of patterned devices involves polymers that are difficult to remove from the 2D material interfaces without damage. Remaining polymer residues are often overlooked when interpreting the RS characteristics of 2D material memristors. Here, we demonstrate that the parasitic residues themselves can be the origin of RS. We emphasize the necessity to fabricate appropriate reference structures and employ atomic-scale material characterization techniques to properly evaluate the potential of 2D materials as the switching layer in vertical memristors. Our polymer-residue-based memristors exhibit RS typical for a filamentary mechanism with metal ion migration, and their performance parameters are strikingly similar to commonly reported 2D material memristors. This reveals that the exclusive consideration of electrical data without a thorough verification of material interfaces can easily lead to misinterpretations about the potential of 2D materials for memristor applications. Copyright © 2023, The Authors. All rights reserved.

关键词： Memristors

Cheating monitoring and detection in examination from face movement recognition

学校读者我要写书评

暂无评论

AIP Conference Proceedings 2022年第1期2400卷

作者： Salah Sleibi Al-Rawi Khattab M. Ali Alheeti Sameera Abdul-Kader Muzhir Shaban Al-Ani 1College of Computer and Information Technology Information Systems Dept. University of Anbar Anbar Iraq 2College of Computer and Information Technology Computer Networking Systems Department University of Anbar Anbar Iraq 3Department of Computer Science Faculty of Education for Pure Sciences University of Diyala Iraq 4Department of Information Technology College of Science and Technology University of Human Development Sulaymaniyah KRG Iraq

Cheating behaviour is one of the problems in the education field during an online exam. In this paper, anti-cheating system is proposed to enhance learning environment of various educational institutions. The appearances and potential ways of cheating are analyzed during the exam process. A novel anti-cheating system is proposed to prevent illegal access based on these two points. It is heavily based on face movement recognition technique. Simulation results of the suggested detection scheme demonstrate that our system possesses outstanding rate of detection with low false alarms rate.

关键词：

A modified observer/Kalman filter identification (OKID) algorithm employing output residuals

学校读者我要写书评

暂无评论

International Journal of Dynamics and Control 2019年第2期7卷 636-643页

作者： Alenany, Ahmed Westwick, David Shang, Helen Department of Computer and Systems Engineering Zagazig University Zagazig44519 Egypt Department of Computer Science Nahda University in Beni Suef New Benisuef City Egypt Department of Electrical and Computer Engineering University of Calgary 2500 University Dr. NW CalgaryABT2N 1N4 Canada School of Engineering Laurentian University 935 Ramsey Lake Road SudburyP3E 2C6 Canada

The observer/Kalman filter identification (OKID) is an algorithm widely used for the identification of state space models. The standard OKID algorithm involves the estimation of the Kalman filter and system Markov parameters, followed by the realization of a state space model of the system using the eigensystem realization algorithm (ERA). In this paper, a modified and conceptually simple version of the OKID algorithm, termed the residual-based observer/Kalman filter identification (ROKID), is proposed. The ROKID algorithm uses ordinary least square method twice to solve two linear regression problems yielding the Kalman filter residuals and the system Markov parameters, respectively. Finally, the ERA algorithm is used to obtain a state space model of the system. The efficacy of the proposed algorithm is examined and compared with the standard OKID algorithm and the recently proposed OKID with deterministic projection (OKID/DP) algorithm via a simulation example. The results show that the proposed algorithm outperforms the standard OKID algorithm. Although its performance is less than that of the OKID/DP algorithm, due to its simplicity, the proposed algorithm represents a useful tool for linear state space model identification. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Linear systems

Entanglement in quantum field theory via wavelet representations

学校读者我要写书评

暂无评论

arXiv 2022年

作者： George, Daniel J. Sanders, Yuval R. Bagherimehrab, Mohsen Sanders, Barry C. Brennen, Gavin K. Department of Physics and Astronomy Macquarie University SydneyNSW2109 Australia Sydney Quantum Academy SydneyNSW2000 Australia ARC Centre of Excellence in Engineered Quantum Systems Macquarie University SydneyNSW2109 Australia Centre for Quantum Software and Information University of Technology Sydney SydneyNSW2007 Australia Institute for Quantum Science and Technology University of Calgary CalgaryABT2N 1N4 Canada Chemical Physics Theory Group Department of Chemistry University of Toronto TorontoONM5G 1Z8 Canada Department of Computer Science University of Toronto TorontoONM5S 2E4 Canada

Quantum field theory (QFT) describes nature using continuous fields, but physical properties of QFT are usually revealed in terms of measurements of observables at a finite resolution. We describe a multiscale representation of free scalar bosonic and Ising model fermionic QFTs using wavelets. Making use of the orthogonality and self-similarity of the wavelet basis functions, we demonstrate some well-known relations such as scale-dependent subsystem entanglement entropy and renormalization of correlations in the ground state. We also find some new applications of the wavelet transform as a compressed representation of ground states of QFTs which can be used to illustrate quantum phase transitions via fidelity overlap and holographic entanglement of purification. © 2022, CC BY.

关键词： Ground state