检索结果-内蒙古大学图书馆

Energy-Efficient Routing in Underwater Wireless Sensor Networks Through Cluster-Dragonfly Optimization

学校读者我要写书评

暂无评论

Energy-Efficient Routing in Underwater Wireless Sensor Netwo...

Distributed computing and Electrical Circuits and Electronics (ICDCECE), IEEE International Conference on

作者： Anitha D Saif O. Husain Srikanth Velpula Rajani N R. Dineshkumar Department of Computational Intelligence School of computing SRM Institute of Science and Technology Kattankulathur Tamilnadu India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Electrical and Electronics Engineering SR University Warangal India Dept.of ECE Nitte Meenakshi Institute of Technology Bengaluru India Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India

ISBN: (数字)9798350318609

ISBN: (纸本)9798350318616

In this paper, develop a power control scheme for underwater wireless sensor networks that takes into account the impact of communication ranges on network performance, including energy utilization and delay overhead. The primary objective of our scheme is to assign a differentiated optimal communication radius for each sensor node, enhancing overall network efficiency. The proposed method utilizes energy-aware Cluster-Dragonfly Optimization (CDFO), but it might face challenges in handling large-scale optimization, and the scalability of the algorithm may be limited when dealing with high-dimensional or complex optimization. Although the proposed CDFO method exhibits high performance compared to existing methods, such as Self-Adaptive Glow Worm Swarm Optimization (SA-GWO), Improved Coyote Optimization Algorithm (ICOA), Hybrid Cat Cheetah Optimization algorithm (HCCOA), and Chaotic Search-and-Rescue Optimization (CSRO), it may still face challenges in terms of handling large-scale optimization. Nevertheless, the proposed CDFO yields impressive results, achieving a Packet Delivery Ratio (PDR) of 99%, Packet Loss Ratio (PLR) of 4%, Energy Consumption of 9%, and Alive Node count of 330. These outcomes outperform existing methods in the context of Underwater WSN.

关键词： Wireless sensor networks Energy consumption Chaotic communication Clustering algorithms Packet loss Routing Particle swarm optimization

BioinspiredLLM: Conversational Large Language Model for the Mechanics of Biological and Bio-inspired Materials

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Luu, Rachel K. Buehler, Markus J. Massachusetts Institute of Technology 77 Massachusetts Avenue CambridgeMA02139 United States Department of Materials Science and Engineering Massachusetts Institute of Technology 77 Massachusetts Avenue CambridgeMA02139 United States Center for Computational Science and Engineering Schwarzman College of Computing Massachusetts Institute of Technology 77 Massachusetts Avenue CambridgeMA02139 United States

The study of biological materials and bio-inspired materials science is well established;however, surprisingly little knowledge has been systematically translated to engineering solutions. To accelerate discovery and guide insights, an open-source autoregressive transformer large language model (LLM), BioinspiredLLM, is reported. The model was finetuned with a corpus of over a thousand peer-reviewed articles in the field of structural biological and bio-inspired materials and can be prompted to recall information, assist with research tasks, and function as an engine for creativity. The model has proven that it is able to accurately recall information about biological materials and is further enhanced with enhanced reasoning ability, as well as with retrieval-augmented generation to incorporate new data during generation that can also help to traceback sources, update the knowledge base, and connect knowledge domains. BioinspiredLLM also has been shown to develop sound hypotheses regarding biological materials design and remarkably so for materials that have never been explicitly studied before. Lastly, the model showed impressive promise in collaborating with other generative artificial intelligence models in a workflow that can reshape the traditional materials design process. This collaborative generative artificial intelligence method can stimulate and enhance bio-inspired materials design workflows. Biological materials are at a critical intersection of multiple scientific fields and models like BioinspiredLLM help to connect knowledge domains. © 2023, CC BY-NC-SA.

关键词： Biological materials

Robust Sensor Fusion Algorithms for IoT

学校读者我要写书评

暂无评论

Robust Sensor Fusion Algorithms for IoT

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

作者： Sakthitharan Subramanian Gandrakoti Lokeshwari S. Jagadeesan S. Leela V. G Pratheep Murugesan Venkatasudhahar Department of Computational Intelligence Faculty of Engineering and Technology SRM Institute of Science and Technology School of Computing Chennai Tamil Nadu India Department of Cybersecurity Geethanjali College of Engineering and Technology Hyderabad Telangana India Department of Computer Science and Engineering Nandha Engineering college(Autonomous) Erode Tamil Nadu India Department of Computer Science and Business Systems Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Department of Mechatronics Engineering Kongu Engineering College Perundurai Tamil Nadu India Department of Mechanical Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

Sensor fusion is a critical component of the IoT ecosystem, as it combines a variety of data streams from multiple sensors to enhance the accuracy, reliability, and real-time decision-making. This research concentrates on the development of robust sensor fusion algorithms that are capable of effectively managing the heterogeneity, noise, and uncertainty that are inherent in data from Internet of Things (IoT) sensors. Our primary focus is on the ability of these algorithmic methodologies to manage data from multi-modal sensors. We investigate algorithms that are based on deep learning, Bayesian inference, and Kalman filtering. The proposed solutions aim to improve the performance of systems in sectors that are influenced by the Internet of Things (IoT), including healthcare, smart cities, industrial automation, and autonomous cars. This investigation investigates the scalability, energy efficiency, and computational burden of the Internet of Things (IoT) in the context of limited resources. Through simulations and practical applications, we demonstrate the enhancement of data precision, defect tolerance, and overall system dependability by these robust sensor fusion techniques.

关键词： Deep learning Uncertainty Smart cities Sensor fusion Inference algorithms Bayes methods Internet of Things Reliability Kalman filters Streams

LazyDINO: Fast, Scalable, and Efficiently Amortized Bayesian Inversion via Structure-Exploiting and Surrogate-Driven Measure Transport

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Cao, Lianghao Chen, Joshua Brennan, Michael O’Leary-Roseberry, Thomas Marzouk, Youssef Ghattas, Omar Center for Computational Science and Engineering Massachusetts Institute of Technology CambridgeMA02139 United States Department of Computing and Mathematical Sciences California Institute of Technology PasadenaCA91125 United States Oden Institute for Computational Engineering and Sciences The University of Texas at Austin 201 E. 24th Street C0200 AustinTX78712 United States Walker Department of Mechanical Engineering The University of Texas at Austin 204 E. Dean Keaton Street AustinTX78712 United States

We present LazyDINO, a transport map variational inference method for fast, scalable, and efficiently amortized solutions of high-dimensional nonlinear Bayesian inverse problems with expensive parameter-to-observable (PtO) maps. Our method consists of an offline phase in which we construct a derivative-informed neural surrogate of the PtO map using joint samples of the PtO map and its Jacobian. During the online phase, when given observational data, we seek rapid posterior approximation using surrogate-driven training of a lazy map [Brennan et al., NeurIPS, (2020)], i.e., a structure-exploiting transport map with low-dimensional nonlinearity. The trained lazy map then produces approximate posterior samples or density evaluations. Our surrogate construction is optimized for amortized Bayesian inversion using lazy map variational inference. We show that (i) the derivative-based reduced basis architecture [O’Leary-Roseberry et al., Comput. Methods Appl. Mech. Eng., 388 (2022)] minimizes the upper bound on the expected error in surrogate posterior approximation, and (ii) the derivative-informed training formulation [O’Leary-Roseberry et al., J. Comput. Phys., 496 (2024)] minimizes the expected error due to surrogate-driven transport map optimization. Our numerical results demonstrate that LazyDINO is highly efficient in cost amortization for Bayesian inversion. We observe one to two orders of magnitude reduction of offline cost for accurate posterior approximation, compared to simulation-based amortized inference via conditional transport and conventional surrogate-driven transport. In particular, LazyDINO outperforms Laplace approximation consistently using fewer than 1000 offline samples, while other amortized inference methods struggle and sometimes fail at 16,000 offline samples. © 2024, CC BY-NC-SA.

关键词： Inverse problems

An Improved Cuttlefish Optimization Algorithm Based Faster R-CNN for Brain Tumour Detection

学校读者我要写书评

暂无评论

An Improved Cuttlefish Optimization Algorithm Based Faster R...

Smart Electronics and Communication (ICOSEC), International Conference on

作者： AR Arunarani Vedant Bhenia T Abirami N Aparna Md. Abul Ala Walid Sharada K A Department of Computational and Intelligence School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Campus Chennai Tamilnadu India Department of Computer Science and Engineering IPS Academy Institute of Engineering and Science Indore Madhya Pradesh India Information Technology Kongu Engineering College Erode Tamilnadu India Department of Biomedical Engineering Dhaanish Ahmed Institute of Technology Coimbatore Tamilnadu India Department of Computer Science and Engineering Khulna University of Engineering & Technology (KUET) Khulna Bangladesh Department of CSE HKBK College of Engineering VTU Bengaluru Karnataka India

Brain tumor is caused due to the anomalous development of tissues in the brain. Precise identification of the tumor in premature stage is essential to provide effective medication and curtail further impact of the disease in affected individuals. This present research includes four main stages for the diagnosis of brain tumor including segmentation and classification based on deep learning approaches. The preprocessing stage makes use of filters to reduce the noise impact in the brain imagery. The segmentation stage is responsible to segment the tumor portions from the images using Enhanced Region Growth algorithm. Feature selection stage utilizes Improved Cuttlefish Optimization (ICO) algorithm to extricate the optimal features from the segmented images. The final stage is classification in which Faster R-CNN (FRCNN) algorithm is employed to categorize the brain images as tumor affected or not. BRA TS-2020 dataset is used for the experimental investigation of the proposed FRCNN-ICO method. Performance of this method is assessed using parameters such as Accurate Prediction Rate (APR), Imprecise Prediction Rate (IPR) and Imprecise Denial Rate (IDR). The proposed FRCNN-ICO produces the highest APR value of 99.2% compared to the existing researches on brain tumor detection and proves to perform superior than the methods considered for comparison purposes.

关键词：

Mathematical and numerical study of an inverse source problem for the biharmonic wave equation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chang, Yan Guo, Yukun Yin, Tao Zhao, Yue School of Mathematics Harbin Institute of Technology Harbin China LSEC Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China School of Mathematics and Statistics Central China Normal University Wuhan China

In this paper, we study the inverse source problem for the biharmonic wave equation. Mathematically, we characterize the radiating sources and non-radiating sources at a fixed wavenumber. We show that a general source can be decomposed into a radiating source and a non-radiating source. The radiating source can be uniquely determined by Dirichlet boundary measurements at a fixed wavenumber. Moreover, we derive a Lipschitz stability estimate for determining the radiating source. On the other hand, the non-radiating source does not produce any scattered fields outside the support of the source function. Numerically, we propose a novel source reconstruction method based on Fourier series expansion by multi-wavenumber boundary measurements. Numerical experiments are presented to verify the accuracy and efficiency of the proposed method. Copyright © 2023, The Authors. All rights reserved.

关键词： Wave equations

A class of refined implicit-explicit Runge-Kutta methods with robust time adaptability and unconditional convergence for the Cahn-Hilliard model

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liao, Hong-Lin Tang, Tao Wang, Xuping Zhou, Tao School of Mathematics Nanjing University of Aeronautics and Astronautics Nanjing211106 China MIIT Nanjing211106 China School of Electrical and Computer Engineering Guangzhou Nanfang College Institute for Advanced Study BNU-HKBU United International College China Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China

One of main obstacles in verifying the energy dissipation laws of implicit-explicit Runge-Kutta (IERK) methods for phase field equations is to establish the uniform boundedness of stage solutions without the global Lipschitz continuity assumption of nonlinear bulk. With the help of discrete orthogonal convolution kernels, an updated time-space splitting technique is developed to establish the uniform boundedness of stage solutions for a refined class of IERK methods in which the associated differentiation matrices and the average dissipation rates are always independent of the time-space discretization meshes. This makes the refined IERK methods highly advantageous in self-adaptive time-stepping procedures as some larger adaptive step-sizes in actual simulations become possible. From the perspective of optimizing the average dissipation rate, we construct some parameterized refined IERK methods up to third-order accuracy, in which the involved diagonally implicit Runge-Kutta methods for the implicit part have an explicit first stage and allow a stage-order of two such that they are not necessarily algebraically stable. Then we are able to establish, for the first time, the original energy dissipation law and the unconditional L2 norm convergence. Extensive numerical tests are presented to support our *** Codes 35K58, 65L20, 65M06, 65M12 © 2024, CC BY-NC-ND.

关键词： Runge Kutta methods

Revolutionizing Aquaculture Practices: IoT and Deep Learning-based Remote Monitoring for Sustainable Fish Farming

学校读者我要写书评

暂无评论

Revolutionizing Aquaculture Practices: IoT and Deep Learning...

Smart Electronics and Communication (ICOSEC), International Conference on

作者： S. Prince Chelladurai G.Susan Shiny S.V Jeevitha P Swapna R. Pavithra S Arulraj Department of Computational Intelligence Faculty of Engineering and Technology School of Computing SRM Institute of Science and Technology Kattankulathur Chennai Department of information technology Sethu institute of Technology Pulloor Kariapatti Virudhunagar Tamil Nadu Department of information technology Bannari Amman Institute of Technology Erode India Department of CSE Velammal college of engineering and technology Madurai Department of ECE Rathinam Technical Campus Coimbatore India

ISBN: (数字)9798331504403

ISBN: (纸本)9798331504410

Aquaculture plays a vital role in meeting the growing demand for seafood while addressing sustainability concerns in fisheries. To optimize fish growth and ensure efficient resource utilization an innovative IoT and Deep Learning-based remote monitoring system is proposed tailored for aquaculture operations. Our system integrates sensor technology, IOT connectivity, and Deep Learning algorithms to provide real-time monitoring and control of key environmental parameters such as water temperature, pH levels, oxygen concentration, and feeding behavior. By leveraging a network of sensors deployed in aquaculture facilities, our system collects and analyzes environmental data to optimize aquaculture practices and ensure optimal conditions for fish growth. Through a user-friendly interface accessible via web or mobile applications, aqua-culturists can remotely monitor the status of their facilities and adjust operational parameters as needed. Additionally, our system utilizes Deep Learning algorithms to analyze historical data and predict optimal feeding schedules, thereby enhancing feed efficiency and fish growth rates. Field trials demonstrate the effectiveness of our IOT and Deep Learning-based monitoring system in improving fish health and productivity while reducing environmental impacts and operational costs. Our findings highlight the potential of IoT and Deep Learning technologies in revolutionizing aquaculture practices, promoting sustainability, and enhancing food security in fisheries

关键词： Deep learning Temperature sensors Productivity Schedules Fisheries Real-time systems Feeds Sustainable development Remote monitoring Water resources

PROJECTION METHOD FOR QUASIPERIODIC ELLIPTIC EQUATIONS AND APPLICATION TO QUASIPERIODIC HOMOGENIZATION

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jiang, Kai Li, Meng Zhang, Juan Zhang, Lei Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China School of Mathematical Sciences Institute of Natural Sciences MOE-LSC Shanghai Jiao Tong University Shanghai200240 China

In this study, we address the challenge of solving elliptic equations with quasiperiodic coefficients. To achieve accurate and efficient computation, we introduce the projection method, which enables the embedding of quasiperiodic systems into higher-dimensional periodic systems. To enhance the computational efficiency, we propose a compressed storage strategy for the stiffness matrix by its multi-level block circulant structure, significantly reducing memory requirements. Furthermore, we design a diagonal preconditioner to efficiently solve the resulting high-dimensional linear system by reducing the condition number of the stiffness matrix. These techniques collectively contribute to the computational effectiveness of our proposed approach. Convergence analysis shows the spectral accuracy of the proposed method. We demonstrate the effectiveness and accuracy of our approach through a series of numerical examples. Moreover, we apply our method to achieve a highly accurate computation of the homogenized coefficients for a quasiperiodic multiscale elliptic *** Codes 65D05, 65D15, 65F08, 35B15, 35B27 Copyright © 2024, The Authors. All rights reserved.

关键词： Stiffness matrix