检索结果-内蒙古大学图书馆

Atmosphere-dependent combustion of Ganoderma lucidum biomass toward its enhanced transformability into green energy

Environmental science and Pollution Research 2024年第29期31卷 42372-42387页

作者： Cao, Hanlin Zhan, Hongda Qi, Jianying Lin, Sen Ren, Mingzhong Liang, Jiayu Evrendilek, Fatih He, Yao Liu, Jingyong Technical Centre for Soil Agriculture and Rural Ecology and Environment Ministry of Ecology and Environment Beijing100012 China Guangdong Key Laboratory of Environmental Catalysis and Health Risk Control School of Environmental Science and Engineering Guangdong University of Technology Guangzhou510006 China Ministry of Ecology and Environment South China Institute of Environmental Sciences Guangzhou510275 China Department of Electrical and Computer Engineering College of Engineering Boston University BostonMA02215 United States

Globally, the circular efficiency of biomass resources has become a priority due to the depletion and negative environmental impacts of fossil fuels. This study aimed to quantify the atmosphere-dependent combustion of Ganoderma lucidum (GL) biomass and its thermodynamic and kinetic parameters toward enhancing its circularity and transformability characteristics. The GL combustion occurred in the three stages of moisture removal, volatile release, and coke combustion. Combustion performance characteristics were more favorable in the N2/O2 atmosphere than in the CO2/O2 atmosphere under the same heating rates. The rising heating rate facilitated the release of volatiles. According to the model-free methods of Ozawa-Flynn-Wall and Kissinger–Akahira–Sunose, the activation energies essential for the primary reaction were 283.09 kJ/mol and 288.28 kJ/mol in the N2/O2 atmosphere and 233.09 kJ/mol and 235.64 kJ/mol in the CO2/O2 atmosphere. The gaseous products of the GL combustion included CH4, H2O, C = O, CO, CO2, NH3, C = C, and C–O(H). Ash prepared in both atmospheres exhibited a tendency for slag formation, with oxy-fuel combustion lowering its risk. This study thus provides a theoretical and practical basis for transforming GL residues into a sustainable energy source. Graphical abstract: (Figure presented.) © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Combustion

来源：评论

学校读者我要写书评

暂无评论

Solar Wind Density Forecasting with U-Net and LSTM-based Neural Networks 8

Solar Wind Density Forecasting with U-Net and LSTM-based Neu...

引用

8th International Conference of Yearly Reports on Informatics, Mathematics, and engineering, ICYRIME 2023

作者： Iacobelli, Emanuele Fiani, Francesca Napoli, Christian Department of Computer Control and Management Engineering Sapienza University of Rome Roma00185 Italy Institute for Systems Analysis and Computer Science Italian National Research Council Roma00185 Italy Department of Computational Intelligence Czestochowa University of Technology Czestochowa42-201 Poland

Forecasting changes in solar wind properties accurately is crucial for predicting space weather, as it significantly impacts the majority of space operations and the telecommunication system. To meet this challenge, we introduce an architecture that combines U-Net’s capabilities for segmenting coronal holes from high-resolution sun images with the predictive abilities of Long Short-Term Memory (LSTM) and ConvLSTM models. This architecture predicts solar wind density using sun surface images obtained from the AIA 193 Å dataset (provided by NASA) and historical electron and proton density data from the OMNI and ELM2 datasets (also provided by NASA), covering the entire year 2012. Our findings demonstrate the system’s ability to generate reliable coronal hole segmentation maps and achieve good accuracy in forecasting solar wind density. © 2023 Copyright for this paper by its authors.

关键词： NASA

来源：评论

学校读者我要写书评

暂无评论

Binary Stochastic Flip Optimization for Training Binary Neural Networks

Binary Stochastic Flip Optimization for Training Binary Neur...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Tatsukichi Shibuya Nakamasa Inoue Rei Kawakami Ikuro Sato Department of Computer Science Institute of Science Tokyo Tokyo Japan Department of Systems and Control Engineering Institute of Science Tokyo Tokyo Japan Denso IT Laboratory Tokyo Japan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

For deploying deep neural networks on edge devices with limited resources, binary neural networks (BNNs) have attracted significant attention, due to their computational and memory efficiency. However, once a neural network is binarized, finetuning it on edge devices becomes challenging because most conventional training algorithms for BNNs are designed for use on centralized servers and require storing real-valued parameters during training. To address this limitation, this paper introduces binary stochastic flip optimization (BinSFO), a novel training algorithm for BNNs. BinSFO employs a parameter update rule based on Boolean operations, eliminating the need to store real-valued parameters and thereby reducing memory requirements and computational overhead. In experiments, we demonstrated the effectiveness and memory efficiency of BinSFO in fine-tuning scenarios on six image classification datasets. BinSFO performed comparably to conventional training algorithms with a 70.7% smaller memory requirement. Code is released at https://***/TatsukichiShibuya/ICASSP2025_BinSFO

关键词： Training Speech coding Memory management Signal processing algorithms Signal processing Classification algorithms Servers Speech processing Optimization Image classification

来源：评论

学校读者我要写书评

暂无评论

Estimating Chlorophyll Content from Hyperspectral Data Using Gradient Features 23rd

Estimating Chlorophyll Content from Hyperspectral Data Usin...

引用

23rd International Conference on Computational science, ICCS 2023

作者： Ruszczak, Bogdan Wijata, Agata M. Nalepa, Jakub Faculty of Electrical Engineering Automatic Control and Informatics Department of Informatics Opole University of Technology Opole Poland Faculty of Biomedical Engineering Silesian University of Technology Zabrze Poland Faculty of Automatic Control Electronics and Computer Science Department of Algorithmics and Software Silesian University of Technology Gliwice Poland KP Labs Gliwice Poland

ISBN: (纸本)9783031360206

Non-invasive estimation of chlorophyll content in plants plays an important role in precision agriculture. This task may be tackled using hyperspectral imaging that acquires numerous narrow bands of the electromagnetic spectrum, which may reflect subtle features of the plant, and inherently offers spatial scalability. Such imagery is, however, high-dimensional, therefore it is challenging to transfer from the imaging device, store and investigate. We propose a machine learning pipeline for estimating chlorophyll content from hyperspectral data. It benefits from the Savitzky-Golay filtering to smooth the (potentially noisy) spectral curves, and from gradient-based features extracted from such a smoothed signal. The experiments revealed that our approach significantly outperforms the state of the art according to the widely-established estimation quality metrics obtained for four chlorophyll-related parameters. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Complex Network Pinning control based on Adjacency Degree and Resistance Distance Algorithm 3

Complex Network Pinning Control based on Adjacency Degree an...

引用

3rd International Conference on Green Communication, Network, and Internet of Things, CNIoT 2023

作者： Zhong, Hao Jia, Haoran Jia, Yanting Sun, Haiyi School of Computer Science and Engineering Shenyang Jianzhu University Shenyang China School of Electrical and Control Engineering Shenyang Jianzhu University Shenyang China Office of Academic Affairs Shenyang Jianzhu University Shenyang China Department of Science Shenyang Jianzhu University Shenyang China

ISBN: (纸本)9781510668867

In this paper, a new strategy for pinning control node selection is proposed, namely: pinning control strategy based on ADRD (Adjacency Degree and Resistance Distance) algorithm. Firstly, the model of the undirected network and the sufficient conditions to achieve synchronization are given. Secondly, the steps of the pinning control strategy based on the ADRD algorithm are specifically given and applied to dolphins network, and by comparing the pinning control strategy based on the resistance distance, it is concluded that: the pinning control strategy based on the ADRD algorithm is better than the pinning control strategy based on the resistance distance. Finally, the correctness and effectiveness of the method are verified by numerical simulation. © 2023 SPIE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Pinning control of Complex Networks Based on the entropy of Betweenness centrality and Node strength 3

Pinning Control of Complex Networks Based on the entropy of ...

引用

3rd International Conference on Green Communication, Network, and Internet of Things, CNIoT 2023

作者： Sun, Haiyi Cai, Liang Lv, Chenxinxiao Jia, Yanting Department of Science Shenyang Jianzhu University Shenyang China School of Computer Science and Engineering Shenyang Jianzhu University Shenyang China School of Electrical and Control Engineering Shenyang Jianzhu University Shenyang China Office of academic affairs Shenyang Jianzhu University Shenyang China

ISBN: (纸本)9781510668867

In order to solve the problem of pinning node selection in undirected weighted networks, a pinning control strategy based on the entropy of betweenness centrality and node strength is proposed in this paper. Firstly, a complex network model is given where each node is the same dynamical system, secondly, sufficient conditions for the synchronization of this network are given, and specific steps of the betweenness centrality and node strength entropy-based pinning control strategy are proposed and applied to different networks. Finally, by comparing the neighborhood information entropy-based pinning control strategy, it is found that in order to synchronize the network, the number of key nodes pinned by the proposed pinning control strategy is smaller than the neighborhood information entropy-based pinning control strategy under different coupling strengths. © 2023 SPIE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Object Detection Robustness for Cross-Depiction Through Neural Style Transfer 8

Enhancing Object Detection Robustness for Cross-Depiction Th...

引用

8th International Conference of Yearly Reports on Informatics, Mathematics, and engineering, ICYRIME 2023

作者： Fiani, Francesca Puglisi, Adriano Napoli, Christian Department of Computer Control and Management Engineering Sapienza University of Rome Roma00185 Italy Institute for Systems Analysis and Computer Science Italian National Research Council Roma00185 Italy Department of Computational Intelligence Czestochowa University of Technology Czestochowa42-201 Poland

Modern neural networks models for computer vision are trained on millions of images. The idea is that models are able to increase generalization when the dataset contains well diversified images, e.g. with varied illumination and environmental conditions of the same objects. Generalization is particularly relevant in object detection, especially for what concerns the cross-depiction problem. In this work we explore the use of Neural Style Transfer as a novel technique to morph the original data, with the aim to enhance model generalization. To verify the effect on performances for object detection models, we selected the Faster R-CNN model to be applied on the Pascal VOC 2012 dataset. A number of tests were performed through style variations on images and by tuning Neural Style Transfer parameters to maintain the content of the original images. The experiments showed promising results, which effectively provide a foundation for future studies on cross-depiction via Neural Style Transfer. © 2023 Copyright for this paper by its authors.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

BigFeat: Scalable and Interpretable Automated Feature engineering Framework

BigFeat: Scalable and Interpretable Automated Feature Engine...

引用

2022 IEEE International Conference on Big Data, Big Data 2022

作者： Eldeeb, Hassan Amashukeli, Shota Elshawi, Radwa University of Tartu Institute of Computer Science Tartu Estonia Tanta University Faculty of Engineering Computers and Automatic Control Department Tanta Egypt

ISBN: (纸本)9781665480451

Feature engineering is a crucial step in building well-performing machine learning pipelines. However, manually constructing highly predictive features is time-consuming and requires domain knowledge. Although the research area of automated feature engineering has attracted much interest lately, both in academia and industry, the scalability and efficiency of the existing systems and tools are still practically unsatisfactory. This paper presents a scalable and interpretable automated feature engineering framework, BigFeat, that optimizes input features' quality to maximize the predictive performance according to a user-defined metric. BigFeat employs a dynamic feature generation and selection mechanism that constructs a set of expressive features that improve the prediction performance while retaining interpretability. Extensive experiments are conducted, and the results show that BigFeat provides superior performance compared to the state-of-the-art automated feature engineering framework, AutoFeat, on a wide range of datasets. We show that BigFeat significantly improves the F1-Score of 8 classifiers by 4.59%, on average. In addition, the performance improvement achieved by integrating BigFeat into different AutoML frameworks is higher than that achieved by integrating AutoFeat into the same frameworks. Besides, the scalability of BigFeat is confirmed by its linear complexity, parallel design, and execution time which is, on average, 22x faster than AutoFeat. © 2022 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Truthful Matching with Online Items and Offline Agents 50

Truthful Matching with Online Items and Offline Agents

引用

50th International Colloquium on Automata, Languages, and Programming, ICALP 2023

作者： Feldman, Michal Fusco, Federico Mauras, Simon Reiffenhäuser, Rebecca Blavatnik School of Computer Science Tel Aviv University Israel Microsoft Research Herzliya Israel Department of Computer Control and Management Engineering "Antonio Ruberti" Sapienza University of Rome Italy Institute for Logic Language and Computation University of Amsterdam Netherlands

ISBN: (纸本)9783959772785

We study truthful mechanisms for welfare maximization in online bipartite matching. In our (multiparameter) setting, every buyer is associated with a (possibly private) desired set of items, and has a private value for being assigned an item in her desired set. Unlike most online matching settings, where agents arrive online, in our setting the items arrive online in an adversarial order while the buyers are present for the entire duration of the process. This poses a significant challenge to the design of truthful mechanisms, due to the ability of buyers to strategize over future rounds. We provide an almost full picture of the competitive ratios in different scenarios, including myopic vs. non-myopic agents, tardy vs. prompt payments, and private vs. public desired sets. Among other results, we identify the frontier up to which the celebrated e/(e − 1) competitive ratio for the vertex-weighted online matching of Karp, Vazirani and Vazirani extends to truthful agents and online items. © Michal Feldman, Federico Fusco, Simon Mauras, and Rebecca Reiffenhäuser.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Delayed Transitions in GPenSIM 1st

Delayed Transitions in GPenSIM

引用

1st International Symposium on Systems Modelling and Simulation, SMS 2024

作者： Feng, Yuming Samolej, Slawomir Davidrajuh, Reggie School of Computer Science and Engineering Chongqing Three Gorges University Wenzhou China Department Computer and Control Engineering Rzeszow University of Technology Rzeszow Poland Department Electrical Engineering and Computer Science University of Stavanger Stavanger Norway

ISBN: (纸本)9789819646128

The General-purpose Petri Net Simulator (GPenSIM) is a tool for modeling, simulation, and performance analysis of discrete event systems. GPenSIM is specially designed to model real-life industrial systems. Hence, the transitions in GPenSIM represent real-life events, such as machines. However, this induces a problem, namely that an enabled transition consumes tokens from its input places immediately. This act of an enabled transition immediately consuming tokens gives only monetarily visibility to the tokens, which can be a problem for certain cases where we need to see the tokens in their input places for a while. This paper proposes a method to delay an enabled transition ("delayed transitions") so that the tokens it is supposed to consume from its input places will be visible for a while. This paper, after presenting the theory and the method, also presents an application (the cat and mouse problem) of the delayed transitions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Discrete event simulation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：