检索结果-内蒙古大学图书馆

Grapenet_Lv1 for the Prediction of Optimum Hand-Picking Time of Nagano Purple Grapes

学校读者我要写书评

暂无评论

SSRN

SSRN 2025年

作者： Islam, Md. Parvez Shinagawa, K. Hatou, K. Abdurrakhman, Arief Dian, K. Department of Biomechanical Systems Faculty of Agriculture Ehime University 3-5-7 Tarumi Matsuyama790-8566 Japan United Graduate School of Agriculture Ehime University 3-5-7 Tarumi Matsuyama790-8566 Japan Department of Instrumentation Engineering Institut Teknologi Sepuluh Nopember Surabaya60111 Indonesia Business Mathematics Program Study School of Applied STEM Universitas Prasetiya Mulya BSD Campus BSD City Kav. Edutown I.1 Tangerang15339 Indonesia Indonesia

We investigated the optimum hand-picking time of Nagano Purple, a rare Japanese table grape variety. The color sensitivity between pure red–purple–black and pure purple–black makes it difficult for farmers to harvest these fruits at the right time while maintaining high sweetness level. We manually extracted 13 color parameters, namely, X, Y, Z, x, y, L*, a*, b*, L, a, b, C*, and h, from 355 grape skin samples using a colorimeter, which is a time-consuming and expensive process. In addition, we developed a 15-layer shallow long short-term memory (LSTM) and bidirectional long short-term memory (BLSTM) neural network, namely, GrapeNet_Lv1, with a learnable parameter of 1.39E+06. This network is compact and requires low computational cost for training. Furthermore, it has the ability to prevent the problems of vanishing gradient and overfitting. The combination of all the 13 aforementioned parameters yielded promising results in predicting color and sweetness levels, with test accuracies of 0.83 and 0.76, respectively. In the prediction of color level, our proposed network GrapeNet_Lv1 achieves a high validation accuracy of 0.92, F1 score of 0.88, recall of 0.87, low validation loss of 0.39, and RMSE of 0.31. However, in the prediction of sweetness level, GrapeNet_Lv1 achieves a relatively low validation accuracy of 0.79, F1 score of 0.70, recall of 0.69, high validation loss of 0.72, and RMSE of 0.33. Further research can help improve the accuracy. GrapeNet_Lv1 can be applied to other crops, where, predicting the whose optimal hand-picking time is difficult to predict based on color recognition. Keywords: Neural network;LSTM-BLSTM;Nagano Purple, color, sweetness © 2025, The Authors. All rights reserved.

关键词： Long short-term memory

Combining imitation and deep reinforcement learning to accomplish human-level performance on a virtual foraging task

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Giammarino, Vittorio Dunne, Matthew F. Moore, Kylie N. Hasselmo, Michael E. Stern, Chantal E. Paschalidis, Ioannis Ch. Division of Systems Engineering Boston University BostonMA02446 United States Dept. of Electrical and Computer Engineering Boston University BostonMA02446 United States Dept. of Biomedical Engineering Boston University BostonMA02215 United States Cognitive Neuroimaging Center Boston University BostonMA02215 United States Graduate Program for Neuroscience Boston University BostonMA02215 United States Center for Systems Neuroscience Boston University BostonMA02215 United States

We develop a simple framework to learn bio-inspired foraging policies using human data. We conduct an experiment where humans are virtually immersed in an open field foraging environment and are trained to collect the highest amount of rewards. A Markov Decision Process (MDP) framework is introduced to model the human decision dynamics. Then, Imitation Learning (IL) based on maximum likelihood estimation is used to train Neural Networks (NN) that map human decisions to observed states. The results show that passive imitation substantially underperforms humans. We further refine the human-inspired policies via Reinforcement Learning (RL) using the on-policy Proximal Policy Optimization (PPO) algorithm which shows better stability than other algorithms and can steadily improve the policies pretrained with IL. We show that the combination of IL and RL can match human results and that good performance strongly depends on combining the allocentric information with an egocentric representation of the environment. © 2022, CC BY.

关键词： Reinforcement learning

Lightweight equivariant model for efficient machine learning interatomic potentials

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Ziduo Wang, Xian Li, Yifan Lv, Qiujie Chen, Calvin Yu-Chian Shen, Lei Department of Mechanical Engineering National University of Singapore Singapore117575 Singapore Artificial Intelligence Medical Research Center School of Intelligent Systems Engineering Shenzhen Campus of Sun Yat-sen University Shenzhen518107 China Department of Physics National University of Singapore Singapore117551 Singapore -Preferred Program School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Shenzhen518055 China State Key Laboratory of Chemical Oncogenomics School of Chemical Biology and Biotechnology Peking University Shenzhen Graduate School Shenzhen518055 China Guangdong L-Med Biotechnology Co. Ltd Guangdong Meizhou514699 China Research Institute Chongqing401123 China

In modern computational materials science, deep learning has shown the capability to predict interatomic potentials, thereby supporting and accelerating conventional simulations. However, existing models typically sacrifice either accuracy or efficiency. Moreover, lightweight models are highly demanded for offering simulating systems on a considerably larger scale at reduced computational costs. Here, we introduce a lightweight equivariant interaction graph neural network (LEIGNN) that can enable accurate and efficient interatomic potential and force predictions for molecules and crystals. Rather than relying on higher-order representations, LEIGNN employs a scalar-vector dual representation to encode equivariant features. By learning geometric symmetry information, our model remains lightweight while ensuring prediction accuracy and robustness through the equivariance. Our results show that LEIGNN consistently outperforms the prediction performance of the representative baselines and achieves significant efficiency across diverse datasets, which include catalysts, molecules, and organic isomers. Furthermore, we conduct molecular dynamics (MD) simulations using the LEIGNN force field across solid, liquid, and gas systems. It is found that LEIGNN can achieve the accuracy of ab initio MD across all examined systems. Copyright © 2023, The Authors. All rights reserved.

关键词： Prediction models

Using Online Grocery Applications during the COVID-19 Pandemic: Their Relationship with Open Innovation

学校读者我要写书评

暂无评论

Journal of Open Innovation: Technology, Market, and Complexity 2022年第2期8卷

作者： Gumasing, Ma. Janice J. Prasetyo, Yogi Tri Persada, Satria Fadil Ong, Ardvin Kester S. Young, Michael Nayat Nadlifatin, Reny Redi, Anak Agung Ngurah Perwira School of Industrial Engineering and Engineering Management Mapúa University 658 Muralla St. Intramuros Manila 1002 Philippines School of Graduate Studies Mapúa University 658 Muralla St. Intramuros Manila 1002 Philippines Entrepreneurship Department BINUS Business School Undergraduate Program Bina Nusantara University Malang 65154 Indonesia Department of Information Systems Institut Teknologi Sepuluh Nopember Kampus ITS Sukolilo Surabaya 60111 Indonesia Industrial Engineering Department BINUS Graduate Program—Master of Industrial Engineering Bina Nusantara University Jakarta 11480 Indonesia

This present research examines the behavioral intentions of Filipinos to use online grocery applications during the novel COVID-19 pandemic. The study proposes an integration of the health belief model (HBM) and the Unified Theory of Acceptance and Use of Technology (UTAUT2) to identify the factors affecting the acceptance and usage of Filipinos of online grocery applications in terms of the impact of health risk for COVID-19. To accurately measure the factors and their relationship to behavioral intentions and usage behavior, a questionnaire was developed and distributed to 373 residents in the Philippines. Partial least squares structural equation modeling (PLS-SEM) was applied as an analytical method for this study. The results revealed that performance expectancy, perceived benefits, perceived severity, and cues to action significantly influenced the behavioral intentions and usage of online grocery apps during the COVID-19 pandemic. The study’s findings can be utilized as a theoretical framework for future researchers of consumer behavior;e-commerce developers;and grocery industry retailers, to enhance the innovation and services of online grocery applications. The results of this study may also be used and capitalized on by investors and managers to apply in strategizing when developing and marketing online grocery applications among con-sumers. Moreover, the framework of this study may be adopted and utilized by other online markets, even in different counties. Further theoretical and practical aspects are discussed in this paper. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.

关键词： health belief model online grocery applications structural equation modeling UTAUT2

Deep-Learning-based MR Compressed Sensing using Non-randomly Under-sampled Signal in Nonlinear Phase Encoding Imaging

学校读者我要写书评

暂无评论

Deep-Learning-based MR Compressed Sensing using Non-randomly...

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Satoshi ITO Shohei OUCHI Graduate Program in Information Electrical and Electronic Systems Engineering Graduate School of Regional Development and Creativity Utsunomiya University Tochigi Japan

ISBN: (数字)9789881476883

ISBN: (纸本)9781728181301

Optional image scaling, and hence aliasless image reconstruction, is feasible using a signal that violates the sampling theorem in MR phase scrambling Fourier transform imaging. In this method, the main and aliased image components are separated in the scaled space when a large scaling factor is selected. In the present study, a new fast imaging method, in which aliasing artifacts caused by undersampling of the signal, are removed in two steps: in the downscaled space introduced by aliasless reconstruction and through de-aliasing using a deep convolution neural network. The proposed method is shown to provide higher PSNR images compared to random sampling compressed sensing and has an advantage in terms of lowsampling-rate image acquisition.

关键词： Image reconstruction Spatial resolution Magnetic resonance imaging Fourier transforms Image coding Convolutional neural networks Acceleration

Exploring Collaborative Distributed Diffusion-Based AI-Generated Content (AIGC) in Wireless Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Du, Hongyang Zhang, Ruichen Niyato, Dusit Kang, Jiawen Xiong, Zehui Kim, Dong In Shen, Xuemin Poor, H. Vincent The School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The School of Computer Science and Engineering Nanyang Technological University Singapore The School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of The Department of Electrical and Computer Engineering University of Waterloo Canada The Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States

Driven by advances in generative artificial intelligence (AI) techniques and algorithms, the widespread adoption of AI-generated content (AIGC) has emerged, allowing for the generation of diverse and high-quality content. Especially, the diffusion model-based AIGC technique has been widely used to generate content in a variety of modalities. However, the real-world implementation of AIGC models, particularly on resource-constrained devices such as mobile phones, introduces significant challenges related to energy consumption and privacy concerns. To further promote the realization of ubiquitous AIGC services, we propose a novel collaborative distributed diffusion-based AIGC framework. By capitalizing on collaboration among devices in wireless networks, the proposed framework facilitates the efficient execution of AIGC tasks, optimizing edge computation resource utilization. Furthermore, we examine the practical implementation of the denoising steps on mobile phones, the impact of the proposed approach on the wireless network-aided AIGC landscape, and the future opportunities associated with its real-world integration. The contributions of this paper not only offer a promising solution to the existing limitations of AIGC services but also pave the way for future research in device collaboration, resource optimization, and the seamless delivery of AIGC services across various devices. Our code is available at https://***/HongyangDu/DistributedDiffusion. © 2023, CC BY.

关键词： Wireless networks

Electrodynamics of Photonic Temporal Interfaces

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Galiffi, Emanuele Solís, Diego Martinez Yin, Shixiong Engheta, Nader Alù, Andrea Photonics Initiative Advanced Science Research Center City University of New York New York United States Departamento de Tecnología de los Computadores y de las Comunicaciones University of Extremadura Cáceres10003 Spain Department of Electrical Engineering City College of The City University of New York New YorkNY10031 United States Department of Electrical and Systems Engineering University of Pennsylvania PhiladelphiaPA19104 United States Physics Program Graduate Center of the City University of New York New YorkNY10016 United States

Exotic forms of wave control have been emerging by engineering matter in space and time. In this framework, temporal photonic interfaces, i.e., abrupt changes in the electromagnetic properties of a material, have been shown to induce temporal scattering phenomena dual to spatial reflection and refraction, at the basis of photonic time crystals and space-time metamaterials. Despite decades-old theoretical studies on these topics, and recent experimental demonstrations, the careful modeling of these phenomena has been lagging behind. Here, we develop from first principles a rigorous model of the electrodynamics of temporal photonic interfaces, highlighting the crucial role of the mechanisms driving time variations. We demonstrate that the boundary conditions and conservation laws associated with temporal scattering may substantially deviate from those commonly employed in the literature, based on their microscopic implementation. Our results open new vistas for both fundamental investigations over light-matter interactions in time-varying structures and for the prospect of their future implementations and applications in optics and photonics. © 2024, CC BY.

关键词： Light sensitive materials

Functional observability and target state estimation in large-scale networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Montanari, Arthur N. Duan, Chao Aguirre, Luis A. Motter, Adilson E. Department of Physics and Astronomy Northwestern University EvanstonIL60208 United States Graduate Program in Electrical Engineering Federal University of Minas Gerais Belo HorizonteMG 31270-901 Brazil Luxembourg Centre for Systems Biomedicine University of Luxembourg BelvauxL-4367 Luxembourg Departament of Electronic Engineering Federal University of Minas Gerais Belo HorizonteMG 31270-901 Brazil Northwestern Institute on Complex Systems Northwestern University EvanstonIL60208 United States

The quantitative understanding and precise control of complex dynamical systems can only be achieved by observing their internal states via measurement and/or estimation. In large-scale dynamical networks, it is often difficult or physically impossible to have enough sensor nodes to make the system fully observable. Even if the system is in principle observable, high-dimensionality poses fundamental limits on the computational tractability and performance of a full-state observer. To overcome the curse of dimensionality, we instead require the system to be functionally observable, meaning that a targeted subset of state variables can be reconstructed from the available measurements. Here, we develop a graph-based theory of functional observability, which leads to highly scalable algorithms to i) determine the minimal set of required sensors and ii) design the corresponding state observer of minimum order. Compared to the full-state observer, the proposed functional observer achieves the same estimation quality with substantially less sensing and computational resources, making it suitable for large-scale networks. We apply the proposed methods to the detection of cyber-attacks in power grids from limited phase measurement data and the inference of the prevalence rate of infection during an epidemic under limited testing conditions. The applications demonstrate that the functional observer can significantly scale up our ability to explore otherwise inaccessible dynamical processes on complex networks. Copyright © 2022, The Authors. All rights reserved.

关键词： State estimation

Addressing challenges for operating electrochemical solar fuels technologies under variable and diurnal conditions

学校读者我要写书评

暂无评论

Frontiers in Energy Research 2024年 12卷

作者： Yap, Kyra M. K. Lee, Sol A. Kistler, Tobias A. Collins, Darci K. Warren, Emily L. Atwater, Harry A. Jaramillo, Thomas F. Xiang, Chengxiang Nielander, Adam C. Department of Chemical Engineering Stanford University StanfordCA United States SUNCAT Center for Interface Science and Catalysis SLAC National Accelerator Laboratory Menlo ParkCA United States Department of Applied Physics and Materials Science California Institute of Technology PasadenaCA United States Chemical Sciences Division Lawrence Berkeley National Laboratory BerkeleyCA United States Chemistry and Nanoscience Center National Renewable Energy Laboratory GoldenCO United States Advanced Energy Systems Graduate Program Colorado School of Mines GoldenCO United States

The outdoor operation of electrochemical solar fuels devices must contend with challenges presented by the cycles of solar irradiance, temperature, and other meteorological factors. Herein, we discuss challenges associated with these fluctuations presented over three timescales, including the effects of diurnal cycling over the course of many days, a single diurnal cycle over the course of hours, and meteorological phenomena that cause fluctuations on the order of seconds to minutes. We also highlight both reaction-independent and reaction-specific effects of variable conditions for the hydrogen evolution reaction and CO2 reduction reaction. We identify key areas of research for advancing the outdoor operation of solar fuels technology and highlight the need for metrics and benchmarks to enable the comparison of diurnal studies across systems and geographical locations. Copyright © 2024 Yap, Lee, Kistler, Collins, Warren, Atwater, Jaramillo, Xiang and Nielander.

关键词： Hydrogen fuels