检索结果-内蒙古大学图书馆

Air Purification Robotics using Cloud and Deep Q Networks for Autonomous Systems

学校读者我要写书评

暂无评论

Air Purification Robotics using Cloud and Deep Q Networks fo...

Innovative Sustainable Technologies for Energy, Mechatronics, and Smart Systems (ISTEMS), International Conference on

作者： Elangovan Guruva Reddy T. S. Balaji Damodhar Yuvaraj S B. Santha Vathani S. Sivakumar N. Malathi Department of Artificial Intelligence and Data Science Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India Department of Electrical and Electronics Engineering Madanapalle Institute of Technology & Science Madanapalle Andhra Pradesh India Department of Electronics and Communication Engineering Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu India Department of Management Studies Mahalashmi Women's College of Arts and Science Chennai Tamil Nadu India Department of Computer Science Thanthai Hans Roever College (Autonomous) Perambalur Tamil Nadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798350384246

ISBN: (纸本)9798350384253

Rising urban air pollution poses serious health dangers. Through robots, cloud computing, and deep reinforcement learning, this research proposes a new air purification method. The suggested autonomous system analyzes real-time air quality parameters and optimizes air purification tactics using cloud-based data processing. Advanced sensors and purification processes allow robotic agents to intelligently adapt to shifting pollution patterns in dynamic settings. Robots use Deep Q Networks (DQN) to learn and change their purifying tactics based on past data and environmental input. Cloud computing and deep learning improve air purification efficiency and enable real-time pollution response decision-making. The autonomous system is scalable and adaptable to varied urban environments since it requires little human involvement. The cloud-based design lets autonomous agents communicate and coordinate to improve air quality. Experimental findings show that the suggested strategy improves air purification over previous approaches. This system advances environmental robotics and lays the groundwork for intelligent, autonomous systems that handle urban air quality and pollution issues.

关键词： Cloud computing Technological innovation Purification Autonomous systems Robot kinematics Decision making Urban areas

Feature selection in linear support vector machines via a hard cardinality constraint: A scalable conic decomposition approach

学校读者我要写书评

暂无评论

European Journal of Operational Research 2025年

作者： Bomze, Immanuel D'Onofrio, Federico Palagi, Laura Peng, Bo Faculty of Mathematics and Research Network Data Science University of Vienna Oskar-Morgenstern-Platz 1 Wien1090 Austria Department of Computer Control and Management Engineering Sapienza University of Rome Via Ariosto 25 Rome00185 Italy VGSCO University of Vienna Oskar-Morgenstern-Platz 1 Wien1090 Austria

In this paper, we study the embedded feature selection problem in linear Support Vector Machines (SVMs), in which a cardinality constraint is employed, leading to an interpretable classification model. The problem is NP-hard due to the presence of the cardinality constraint, even though the original linear SVM amounts to a problem solvable in polynomial time. To handle the hard problem, we first introduce two mixed-integer formulations for which novel semidefinite relaxations are proposed. Exploiting the sparsity pattern of the relaxations, we decompose the problems and obtain equivalent relaxations in a much smaller cone, making the conic approaches scalable. To make the best usage of the decomposed relaxations, we propose heuristics using the information of its optimal solution. Moreover, an exact procedure is proposed by solving a sequence of mixed-integer decomposed semidefinite optimization problems. Numerical results on classical benchmarking datasets are reported, showing the efficiency and effectiveness of our approach. © 2025

关键词： Mixed-integer linear programming

Apple Leaf Disease Identification Using Resnet50

学校读者我要写书评

暂无评论

Apple Leaf Disease Identification Using Resnet50

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： S. Karthigaiveni R. Archana Vasanth Ravi P Salma Khatoon Department of Electronics and Communication Engineering Chennai Institute of Technology Chennai Department of Artificial intelligence and Data science St. Joseph's Institute of technology OMR Chennai Department of Computer Science and Engineering Faculty of Engineering and Technology Jain Deemed to be University Jain Global Campus Department of CSE-DS MLR Institute of Technology Hyderabad India

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

Apple leaf disease is a primary issue limiting apple yield and quality. The standard diagnostic approach requires considerable time for illness detection, causing farmers to frequently miss the optimal period for prevention and treatment. The detect of leaf diseases through leaf imagery is a vital study area in computer vision, with the primary objective being to devise an effective method for representing images of sick leaves. The efficient diagnosis and categorization of plant diseases constitutes a significant research aim in agriculture. This paper proposes a novel deep learning, ResNet. To evaluate the efficacy of the ResNet model, a number of comparative experiments were performed with leading transfer learning methodologies. This demonstrates that the proposed method is both possible and successful.

关键词： Plant diseases Accuracy Limiting Prevention and mitigation Transfer learning Feature extraction Mobile handsets Reliability Standards Residual neural networks

Virtual entanglement purification via noisy entanglement

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yamamoto, Kaoru Matsuzaki, Yuichiro Suzuki, Yasunari Tokunaga, Yuuki Endo, Suguru NTT Computer and Data Science Laboratories NTT Corporation Musashino180-8585 Japan Department of Electrical Electronic and Communication Engineering Faculty of Science and Engineering Chuo University 1-13-27 Kasuga Bunkyo-ku Tokyo112-8551 Japan JST PRESTO 4-1-8 Honcho Kawaguchi Saitama332-0012 Japan

Distributed quantum computation (DQC) is a promising approach for scalable quantum computing, where high-fidelity non-local operations among remote devices are required for universal quantum computation. These operations are typically implemented through state and gate teleportation with the consumption of high-fidelity entanglement prepared via entanglement purification. However, noisy local operations and classical communication (LOCC) limit the fidelity of purified entanglement, thereby degrading the quality of non-local operations. Meanwhile, circuit knitting and cutting, which simulate non-local operations by preparing separable states along with LOCC, has been considered for DQC as an alternative. Although this approach needs no entanglement among remote devices, it requires excessive circuit runs. Here, we present a protocol utilizing virtual operations that purifies noisy entanglement at the level of expectation values. Our protocol offers the following advantages over conventional methods: surpasses the fidelity limit of entanglement purification in the presence of noise in LOCC, requires fewer sampling shots than circuit knitting, and exhibits robustness against infidelity fluctuations in shared noisy Bell states, unlike probabilistic error cancellation. Our protocol bridges the gap between the entanglement-based and circuit-knitting DQC methods, offering a flexible approach to achieve further scalability despite hardware limitations. Copyright © 2024, The Authors. All rights reserved.

关键词： Quantum computers

Bounding the Width of Neural Networks via Coupled Initialization - A Worst Case Analysis

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Munteanu, Alexander Omlor, Simon Song, Zhao Woodruff, David P. Dortmund Data Science Center Faculties of Statistics and Computer Science TU Dortmund University Dortmund Germany Faculty of Statistics TU Dortmund University Dortmund Germany Adobe Research United States Department of Computer Science Carnegie Mellon University PittsburghPA15213 United States

A common method in training neural networks is to initialize all the weights to be independent Gaussian vectors. We observe that by instead initializing the weights into independent pairs, where each pair consists of two identical Gaussian vectors, we can significantly improve the convergence analysis. While a similar technique has been studied for random inputs [Daniely, NeurIPS 2020], it has not been analyzed with arbitrary inputs. Using this technique, we show how to significantly reduce the number of neurons required for two-layer ReLU networks, both in the under-parameterized setting with logistic loss, from roughly γ−8 [Ji and Telgarsky, ICLR 2020] to γ−2, where γ denotes the separation margin with a Neural Tangent Kernel, as well as in the over-parameterized setting with squared loss, from roughly n4 [Song and Yang, 2019] to n2, implicitly also improving the recent running time bound of [Brand, Peng, Song and Weinstein, ITCS 2021]. For the under-parameterized setting we also prove new lower bounds that improve upon prior work, and that under certain assumptions, are best possible. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

Implicit Neural Representation in Medical Imaging: A Comparative Survey

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Molaei, Amirali Aminimehr, Amirhossein Tavakoli, Armin Kazerouni, Amirhossein Azad, Bobby Azad, Reza Merhof, Dorit School of Computer Engineering Iran University of Science and Technology Tehran Iran School of Electrical Engineering Iran University of Science and Technology Tehran Iran South Dakota State University BrookingsSD United States Faculty of Electrical Engineering and Information Technology RWTH Aachen University Aachen Germany Institute of Image Analysis and Computer Vision Faculty of Informatics and Data Science University of Regensburg Regensburg Germany Fraunhofer Institute for Digital Medicine MEVIS Bremen Germany

Implicit neural representations (INRs) have gained prominence as a powerful paradigm in scene reconstruction and computer graphics, demonstrating remarkable results. By utilizing neural networks to parameterize data through implicit continuous functions, INRs offer several benefits. Recognizing the potential of INRs beyond these domains, this survey aims to provide a comprehensive overview of INR models in the field of medical imaging. In medical settings, numerous challenging and ill-posed problems exist, making INRs an attractive solution. The survey explores the application of INRs in various medical imaging tasks, such as image reconstruction, segmentation, registration, novel view synthesis, and compression. It discusses the advantages and limitations of INRs, highlighting their resolution-agnostic nature, memory efficiency, ability to avoid locality biases, and differentiability, enabling adaptation to different tasks. Furthermore, the survey addresses the challenges and considerations specific to medical imaging data, such as data availability, computational complexity, and dynamic clinical scene analysis. It also identifies future research directions and opportunities, including integration with multimodal imaging, real-time and interactive systems, and domain adaptation for clinical decision support. To facilitate further exploration and implementation of INRs in medical image analysis, we have provided a compilation of cited studies along with their available open-source implementations on GitHub. Finally, we aim to consistently incorporate the most recent and relevant papers regularly. © 2023, CC BY.

关键词： Medical imaging

Predicting Deterioration in Mild Cognitive Impairment with Survival Transformers, Extreme Gradient Boosting and Cox Proportional Hazard Modelling

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Musto, Henry Stamate, Daniel Logofatu, Doina Stahl, Daniel Data Science and Soft Compuputing Lab Goldsmiths University of London London United Kingdom School of Health Sciences The University of Manchester Manchester United Kingdom Faculty of Computer Science and Engineering Frankfurt University of Applied Sciences Frankfurt Germany Department of Biostatistics Institute of Psychiatry Psychology and Neuroscience King's College London London United Kingdom

The paper proposes a novel approach of survival transformers and extreme gradient boosting models in predicting cognitive deterioration in individuals with mild cognitive impairment (MCI) using metabolomics data in the ADNI cohort. By leveraging advanced machine learning and transformer-based techniques applied in survival analysis, the proposed approach highlights the potential of these techniques for more accurate early detection and intervention in Alzheimer's dementia disease. This research also underscores the importance of non-invasive biomarkers and innovative modelling tools in enhancing the accuracy of dementia risk assessments, offering new avenues for clinical practice and patient care. A comprehensive Monte Carlo simulation procedure consisting of 100 repetitions of a nested cross-validation in which models were trained and evaluated, indicates that the survival machine learning models based on Transformer and XGBoost achieved the highest mean C-index performances, namely 0.85 and 0.8, respectively, and that they are superior to the conventional survival analysis Cox Proportional Hazards model which achieved a mean C-Index of 0.77. Moreover, based on the standard deviations of the C-Index performances obtained in the Monte Carlo simulation, we established that both survival machine learning models above are more stable than the conventional statistical model. © 2024, CC BY.

关键词： Risk assessment

A Survey of Machine Learning Methods for Analyzing Synovitis Arthritis in Human Joints 19thth

学校读者我要写书评

暂无评论

A Survey of Machine Learning Methods for Analyzing Synovit...

19th International Conference on computer Aided Systems Theory, EUROCAST 2024

作者： Bąk, Artur Klempous, Ryszard Segen, Jakub Nikodem, Jan Rozenblit, Jerzy Chaczko, Zenon Kulbacki, Michal Gruszecka, Katarzyna Skoczyńska, Marta Atsushi, Ito Bożejko, Wojciech Jagielski, Dariusz Panejko, Anna Kowalczyk, Hubert Kluwak, Konrad Wojciechowski, Konrad Kulbacki, Marek Wroclaw University of Technology Wroclaw Poland Wroclaw University of Science and Technology Wroclaw Poland School of Electrical and Data Engineering University of Technology Sydney Ultimo Australia Department of Electrical and Computer Engineering University of Arizona Tucson United States Polish-Japanese Academy of Information Technology Warsaw Poland DIVE IN AI Wroclaw Poland Mathematical Institute University of Wroclaw Wroclaw Poland Faculty of Economics Chuo University Tokyo Japan Department of Rheumatology and Internal Diseases Lower Silesian Specialist Hospital Wroclaw Poland

ISBN: (纸本)9783031829598

Synovitis, characterized by inflammation of the synovial membrane in human joints, poses significant diagnostic and treatment challenges. This review presents methods and recent machine learning (ML) developments to analyze synovial arthritis in joints that help overcome these challenges. The methods described in the review include traditional ML algorithms, novel deep learning architectures and recent medical imaging techniques. Key challenges are discussed including the need for large and diverse datasets, model interpretability, generalization to different patient populations, dealing with data variability, and reducing computational complexity. The review also examines integrating multimodal data sources, advances in transfer learning, and developing robust, interpretable models as future directions. It includes enhancing early diagnostic capabilities, leveraging joint-on-a-chip simulations, and investigating signaling pathways in rheumatoid arthritis. This study aims to provide a consolidated resource for interdisciplinary researchers, clinicians and practitioners in the fields of rheumatology and medical imaging as it synthesizes current research to understand better ML methods in the detection of synovitis in human joints, paving the way for improved diagnostic and care capabilities over the patient. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

BGTplanner: Maximizing Training Accuracy for Differentially Private Federated Recommenders via Strategic Privacy Budget Allocation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Xianzhi Zhou, Yipeng Hu, Miao Wu, Di Liao, Pengshan Guizani, Mohsen Sheng, Michael The School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China The Department of Computing Faculty of Science and Engineering Macquarie University Sydney Australia The Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates

To mitigate the rising concern about privacy leakage, the federated recommender (FR) paradigm emerges, in which decentralized clients co-train the recommendation model without exposing their raw user-item rating data. The differentially private federated recommender (DPFR) further enhances FR by injecting differentially private (DP) noises into clients. Yet, current DPFRs, suffering from noise distortion, cannot achieve satisfactory accuracy. Various efforts have been dedicated to improving DPFRs by adaptively allocating the privacy budget over the learning process. However, due to the intricate relation between privacy budget allocation and model accuracy, existing works are still far from maximizing DPFR accuracy. To address this challenge, we develop BGTplanner (Budget Planner) to strategically allocate the privacy budget for each round of DPFR training, improving overall training performance. Specifically, we leverage the Gaussian process regression and historical information to predict the change in recommendation accuracy with a certain allocated privacy budget. Additionally, Contextual Multi-Armed Bandit (CMAB) is harnessed to make privacy budget allocation decisions by reconciling the current improvement and long-term privacy constraints. Our extensive experimental results on real datasets demonstrate that BGTplanner achieves an average improvement of 6.76% in training performance compared to state-of-the-art baselines. Copyright © 2024, The Authors. All rights reserved.

关键词： Differential privacy