检索结果-内蒙古大学图书馆

16th Pacific Rim Conference on Lasers and Electro-Optics, CLEO-PR 2024

作者： Balčytis, Armandas Dinh, Hiep Ozawa, Tomoki Ota, Yasutomo Baba, Toshihiko Iwamoto, Satoshi Mitchell, Arnan Nguyen, Thach G. Integrated Photonics and Applications Centre Rmit University MelbourneVIC3000 Australia Advanced Institute for Materials Research Tohoku University Sendai980-8577 Japan Keio University Department of Applied Physics and Physico-Informatics Yokohama223-8522 Japan Yokohama National University Department of Electrical and Computer Engineering 79-5 Tokiwadai Hodogaya-ku Yokohama240-8501 Japan Research Center for Advanced Science and Technology The University of Tokyo 4-6-1 Komaba Meguro-ku Tokyo153-8904 Japan

We use electro-optically modulated ring cavities, integrated on thin-film lithium niobate, to model frequency dimension tight-binding lattices with versatile connectivity. Inter-mode coupling range, strength, and hopp... 详细信息

ISBN: (纸本)9798350372076

关键词： Photonics

来源：评论

学校读者我要写书评

暂无评论

Improving Smart Agriculture Through the Use of Machine Learning to Offer Tailored Crop Forecasts

引用

Remote Sensing in Earth Systems sciences 2024年第1期8卷 74-83页

作者： Patil, R.N. Maroor, Jnaneshwar Pai Dhanke, Jyoti A. Chunduru, Madhava Rao Singh, Mangal Jangir, Pradeep Upadhyay, Shrikant Department of Mechanical Engineering Bharati Vidyapeeth’s College of Engineering Lavale Pune India Department of Business Administration Nitte Institute of Professional Education Nitte (Deemed to Be University) Karnataka Mangaluru India Department of Engineering Science (Mathematics) Bharati Vidyapeeth’s College of Engineering Lavale Pune India Department Of Computer Science And Engineering Koneru Lakshmaiah Educational Foundation Vaddeswaram AP Guntur District India Department of Electronics and Telecommunication Engg. Symbiosis Institute of Technology Pune Campus Symbiosis International (Deemed University) Pune India Department of Biosciences Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman 19328 Jordan Department of Electronics and Communication Engineering MLR Institute of Technology Hyderabad India

It is not possible to identify crop illnesses by examining each disease independently. Users may only get forecasts for the most anticipated illnesses with the use of a robust analytic methodology. This study presents a method that can collect, analyze, and identify crop health information all on one platform using an IoT and machine learning-based approach. Food security and the provision of essential raw materials for several industries are both supported by agriculture, which is the most important and basic vocation. Improved crop yields, thanks to new innovative agricultural practices, mean less water wasted and more money in the bank. An intelligent irrigation system that uses a machine learning algorithm to forecast a crop’s water needs is the suggested model. One such rapidly evolving invention is the Internet of Things (IoT), which is now spreading its wings across all geographies. Technological innovation is reaching a new level of practicality in agriculture with the rise of embedded PCs like Arduino. Soil quality monitoring using Arduino, several sensors, and an Android app is shown and accomplished in this study. Temperature, soil moisture level, ammonia, and carbon content limit soil quality in this study. Arduino is used as both a worker and an information processing device, and it is in charge of sensor security. The terminal device is an Android phone. Producers may improve agricultural yields by collecting and analyzing data on weather, soil, seed, and yields of crops, moisture, and gusts of wind in specific areas. Furthermore, a flask-built GUI was used to present crop forecasts derived from a bespoke recommender system. Because of its adaptable design, the system may one day be able to discover the suggested items of other areas. This article uses targeted agricultural data to create five machine-learning approaches that are comparable to one another and to compare and contrast them. © The Author(s), under exclusive licence to Springer Nature Swit

关键词： Decision navigation systems Internet of Things (IoT) Irrigation systems Machine learning algorithms Sensors

来源：评论

学校读者我要写书评

暂无评论

A Novel Fluorescence Tool for Monitoring Agricultural Industry Chain Based on AIEgens

引用

Chemical research in Chinese Universities 2021年第1期37卷 38-51页

作者： CHEN Mingyu XIANG Song LV Panpan Ql Chunxuan FENG Hai-Tao TANG Ben Zhong AIE Research Center Shaanxi Key Laboratory of PhytochemistryCollege of Chemistry and Chemical EngineeringBaoji University of Arts and SciencesBaoji721013P.R.China Department of Chemistry Hong Kong Branch of Chinese National Engineering Research Center for Tissue Restoration&ReconstructionInstitute for Advanced StudyDepartment of Chemical and Biomedical EngineeringDivision of Life ScienceState Key Laboratory of Molecular Neurosciencethe Hong Kong University of Science and TechnologyHong KongP.R.China

With the development of the global economy,the safety of agricultural production has attracted intense *** minimize the risk of harmful ingredients in the whole industry chain,it is very necessary to cover the entire process of safety inspections from planting to production to environmental *** sensing as a promising and powerful screening tool is widely used for the detection of ions,toxic gases,biological molecules and so ***,traditional fluorescent probes often suffer from aggregation-induced quenching(ACQ)effects,which limits their practical *** this regard,aggregation-induced emission luminogens(AIEgens)can perfectly address this notorious issue and have shown great potential in agricultural safety *** this review,we briefly summarize their applications in agricultural safety monitoring,including the fabrication of agricultural film,agricultural sewage treatment and selective detection of harmful residues in agricultural *** challenge and future development of AIEgens in this field are also discussed and ***,this review can inspire more researchers to participate in this fascinating area.

关键词： Aggregation induced emission Agricultural film Agricultural sewage Agricultural residue Fluorescence probe

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of CNN-based Deep Learning Approaches on Complex Activity Recognition 7

Comparative Analysis of CNN-based Deep Learning Approaches o...

引用

7th International Conference on Digital Arts, Media and Technology, DAMT 2022 and 5th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, NCON 2022

作者： Mekruksavanich, Sakorn Jantawong, Ponnipa Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Faculty of Applied Science Department of Mathematics Bangkok Thailand

ISBN: (纸本)9781665495103

For those with Parkinson's disease, freezing of gait (FOG) could be a distressing condition. In individuals with diabetes, FOG could have a significant influence on their quality of life and cause falls, which can be dangerous. A questionnaire has traditionally been used to measure the severity of FOG symptoms;nevertheless, this technique is subjective and can not accurately reflect the intensity of this illness. The adoption of sensor-based devices may give reliable and objective information to follow the progression of symptoms, allowing for better Parkinson's disease management and therapy. A compact deep convolutional neural network comprising squeeze and excitation components, which we called SE-DeepConV model, was designed to identify FOG utilizing wearable data from the sensors. The SE-DeepConV model was constructed and evaluated using a publicly accessible standard FOG dataset, particularly the Daphnet dataset. The SE-DeepConV model outperforms other benchmark deep learning models in terms of accuracy, with the most outstanding accuracy of 95.65%, according to research observations. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Unified Approach for Binary-Class and Multi-Class Data Augmented Generation

A Unified Approach for Binary-Class and Multi-Class Data Aug...

引用

Artificial Intelligence (CAI), IEEE Conference on

作者： Frederic Rizk Rodrigue Rizk Dominick Rizk Patrick Rizk Chee-Hung Henry Chu The Center for Advanced Computer Studies University of Louisiana at Lafayette Lafayette LA U.S.A. Department of Computer Science University of South Dakota Vermillion SD U.S.A. Department of Electrical Engineering and Computer Science The Catholic University of America Washington DC U.S.A. Department of Mechanical Engineering University of Quebec at Trois-Rivières Drummondville QC Canada The Center for Advanced Computer Studies Informatics Research Institute University of Louisiana at Lafayette Lafayette LA U.S.A.

ISBN: (数字)9798350354096

ISBN: (纸本)9798350354102

Deep neural networks excel in a wide range of tasks but require diverse datasets to prevent overfitting. Overfitting occurs when a network fits training data too precisely, leading to poor generalization. Data Augmentation is often used to mitigate overfitting aiming at enlarging and improving the quality of training datasets, facilitating the construction of superior deep learning models. MAGAN algorithm emerges as an innovative approach that functions as a Meta-Analysis of Generative Adversarial Networks (GANs). MAGAN harnesses the latent space capabilities of GANs to confront the challenges presented by binary-class, multi-class, grayscale, and RGB images, effectively covering a wide spectrum of scenarios. In this paper, we propose the use of MAGAN algorithm for binary-class and multi-class data augmented generation. We also undertake an in-depth experimental analysis, evaluating the performance of the proposed MAGAN-based approach in comparison to two alternative baseline scenarios: one without any augmentation and another utilizing a conventional augmentation method. To gauge the effectiveness of the proposed technique, we employed diverse classification metrics, including accuracy, loss, precision, recall, F1-score, and the confusion matrix. Our results demonstrate that the proposed approach surpasses the other two scenarios achieving improvements in terms of accuracy by a factor of x1.15 and x1.03, respectively. This underscores the significant advantages of harnessing MAGAN, a meta-analysis of GANs, for data augmentation across a range of image types and classification tasks.

关键词： Deep learning Measurement Accuracy Training data Artificial neural networks Gray-scale Data augmentation

来源：评论

学校读者我要写书评

暂无评论

Reinforcing Spatiotemporal Correlation: Learning Comprehensive Feature Representations for Gait Recognition

SSRN

引用

SSRN 2024年

作者： Chen, Jianyu Wang, Zhongyuan Zeng, Kangli Zou, Qin Liang, Chao Xu, Zengmin Wu, Gang National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China School of Mathematics and Computing Science Guilin University of Electronic Technology Guilin541004 China College of Information Engineering Tarim University Alar843300 China Shenzhen518060 China

Gait recognition attracts extensive attention as biotechnology for identifying subjects from a distance without their cooperation. Since gait is not easily camouflaged and successive motion trajectories facilitate the identification of subjects, capturing critical temporal information is particularly important for gait recognition. Compared with architectures that extract temporal features individually and then perform late fusion, 3D CNNs are more suitable for extracting continuous relationships between frames in gait sequences. Hence, in this paper, we propose a novel 3D architecture called robust spatiotemporal 3D convolutional neural network (RST3D) to collaboratively extract spatiotemporal correlations in gait sequences. Specifically, we propose a full-scale 3D convolutional block that fully considers the orthogonal relationships in multiple dimensions based on the original 3D convolution, thus it can extract more potential gait spatiotemporal features. Next, to further enhance the temporal modeling capability of the network, we propose a temporal pyramidal attention block to capture the most discriminative motion representations from different ranges of gait silhouettes. Experiments on CASIA-B, OUMVLP, GREW and Gait3D datasets demonstrate that our proposed method outperforms the state-of-the-art gait methods. Furthermore, compared to the existing 3D CNN-based gait recognition methods, our approach exhibits superior performance in several complex gait conditions. © 2024, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Modified Convolutional Neural Network Algorithm for Categorization of Solar PV Panel Soiling

Modified Convolutional Neural Network Algorithm for Categori...

引用

Smart Technologies for Power and Renewable Energy (SPECon), International Conference on

作者： Abhyudoy Chaki Rachna Bhatia Pallavi Mishra R. Raja Singh N. Rajasekar School of Computer Science Vellore Institute of Technology Vellore India Dept. of Mathematics School of Advanced Sciences Vellore Institute of Technology Vellore India Automotive Research Center Vellore Institute of Technology Vellore India School of Electrical Engineering Vellore Institute of Technology Vellore India

ISBN: (数字)9798350383041

ISBN: (纸本)9798350383058

The identification and categorization of soiling using artificial intelligence is essential for improving solar photovoltaic (PV) system efficiency. It is possible to use focused and effective cleaning techniques on solar panels by classifying and comprehending the particular types of pollutants. This research proposes a modified convolutional neural network (CNN) approach to efficiently classify soiling on solar PV panels. In contrast to the conventional method, the suggested CNN model is created using simple images rather than images plus time series data. As a result, processing speed is increased. Additionally, the suggested model achieved 96.91 percent accuracy. This success establishes our suggested methodology as a ground-breaking development in soiling type detection, providing improved accuracy and a unique strategy in contrast to current approaches. The trained and tested model is deployed on the web using the Flask. Flask is a powerful and flexible microweb framework for Python, Finally, a comparison is made between the existing method and the proposed method.

关键词： Renewable energy sources Time series analysis Data models Cleaning Classification algorithms Convolutional neural networks Solar panels

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable intelligent surface assisted grant-free massive access

引用

Intelligent and Converged Networks 2022年第1期3卷 134-143页

作者： Xingyu Zhou Keke Ying Shicong Liu Malong Ke Zhen Gao Mohamed-Slim Alouini School of Information and Electronics Beijing Institute of TechnologyBeijing 100081China. the Advanced Research Institute of Multidisciplinary Sciences Beijing Institute of TechnologyBeijing 100081Chinaand also with National Mobile Communications Research LaboratorySoutheast UniversityNanjing 210096China. Computer Electrical and Mathematical Sciences and Engineering DivisionKing Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Kingdom of Saudi Arabia.

Massive machine-type communications(mMTC)is envisioned to be one of the pivotal scenarios in the fifth-generation(5G)wireless communication,where the explosively emerging Internet-of-Things(IoT)applications have triggered the demand for services with low-latency and *** this end,grant-free random access paradigm has been proposed as a promising enabler in simplifying the connection procedure and significantly reducing access *** this paper,we propose to leverage the burgeoning reconfigurable intelligent surface(RIS)for grant-free massive access working at millimeter-wave(mmWave)frequency to further boost access *** attaching independently controllable phase shifts,reconfiguring,and refracting the propagation of incident electromagnetic waves,the deployed RISs could provide additional diversity gain and enhance the access channel *** this basis,to address the challenging active device detection(ADD)and channel estimation(CE)problem,we develop a joint-ADDCE(JADDCE)method by resorting to the existing approximate message passing(AMP)algorithm with expectation maximization(EM)to extract the structured common sparsity in traffic behaviors and cascaded channel ***,simulations are carried out to demonstrate the superiority of our proposed scheme.

关键词： reconfigurable intelligent surface(RIS) massive machine-type communications(mMTC) grant-free random access(GF-RA) active device detection channel estimation approximate message passing(AMP)

来源：评论

学校读者我要写书评

暂无评论

3D printing of hierarchical structures made of inorganic silicon-rich glass featuring self-forming nanogratings

arXiv

引用

arXiv 2024年

作者： Huang, Po-Han Chen, Shiqian Hartwig, Oliver Marschner, David E. Duesberg, Georg S. Stemme, Göran Li, Jiantong Gylfason, Kristinn B. Niklaus, Frank Division of Micro and Nanosystems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden Division of Electronics and Embedded Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Kista16440 Sweden Institute of Physics EIT 2 Faculty of Electrical Engineering and Information Technology University of the Bundeswehr Munich & SENS Research Center Neubiberg85577 Germany

Hierarchical structures are abundant in nature, such as in the superhydrophobic surfaces of lotus leaves and the structural coloration of butterfly wings. They consist of ordered features across multiple size scales, and their unique properties have attracted enormous interest in wide-ranging fields, including energy storage, nanofluidics, and nanophotonics. Femtosecond lasers, capable of inducing various material modifications, have shown promise for manufacturing tailored hierarchical structures. However, existing methods such as multiphoton lithography and 3D printing using nanoparticle-filled inks typically involve polymers and suffer from high process complexity. Here, we demonstrate 3D printing of hierarchical structures in inorganic silicon-rich glass featuring self-forming nanogratings. This approach takes advantage of our finding that femtosecond laser pulses can induce simultaneous multiphoton crosslinking and self-formation of nanogratings in hydrogen silsesquioxane (HSQ). The 3D printing process combines the 3D patterning capability of multiphoton lithography and the efficient generation of periodic structures by the self-formation of nanogratings. We 3D-printed micro-supercapacitors with large surface areas and a remarkable areal capacitance of 1 mF/cm2 at an ultrahigh scan rate of 50 V/s, thereby demonstrating the utility of our 3D printing approach for device applications in emerging fields such as energy storage. Copyright © 2024, The Authors. All rights reserved.

关键词： 3D printing

来源：评论

学校读者我要写书评

暂无评论

Multi-Layer Feature Extraction with Deformable Convolution for Fabric Defect Detection

引用

Intelligent Automation & Soft Computing 2024年第4期39卷 725-744页

作者： Jielin Jiang Chao Cui Xiaolong Xu Yan Cui School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China State Key Lab.for Novel Software Technology Nanjing UniversityNanjing210023China Engineering Research Center of Digital Forensics Ministry of EducationNanjing University of Information Science and TechnologyNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science and TechnologyNanjing210044China College of Mathematics and Information Science Nanjing Normal University of Special EducationNanjing210038China

In the textile industry,the presence of defects on the surface of fabric is an essential factor in determining fabric ***,identifying fabric defects forms a crucial part of the fabric production *** fabric defect detection algorithms can only detect specific materials and specific fabric defect types;in addition,their detection efficiency is low,and their detection results are relatively *** learning-based methods have many advantages in the field of fabric defect detection,however,such methods are less effective in identifying multiscale fabric defects and defects with complex ***,we propose an effective algorithm,namely multilayer feature extraction combined with deformable convolution(MFDC),for fabric defect *** MFDC,multi-layer feature extraction is used to fuse the underlying location features with high-level classification features through a horizontally connected top-down architecture to improve the detection of multi-scale fabric *** this basis,a deformable convolution is added to solve the problem of the algorithm’s weak detection ability of irregularly shaped fabric *** this approach,Roi Align and Cascade-RCNN are integrated to enhance the adaptability of the algorithm in materials with complex patterned *** experimental results show that the MFDC algorithm can achieve good detection results for both multi-scale fabric defects and defects with complex shapes,at the expense of a small increase in detection time.

关键词： Fabric defect detection multi-layer features deformable convolution

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：