检索结果-内蒙古大学图书馆

Topological Landau–Zener nanophotonic circuits

Advanced Photonics 2023年第3期5卷 127-134页

作者： Bing-Cong Xu Bi-Ye Xie Li-Hua Xu Ming Deng Weijin Chen Heng Wei Fengliang Dong Jian Wang Cheng-Wei Qiu Shuang Zhang Lin Chen Huazhong University of Science and Technology School of Optical and Electronic InformationWuhan National Laboratory for OptoelectronicsWuhanChina The Chinese University of Hong Kong School of Science and EngineeringShenzhenChina CAS Center for Excellence in Nanoscience National Center for Nanoscience and Technology of ChinaNanofabrication LaboratoryCAS Key Laboratory for Nanosystems and Hierarchical FabricationCAS Key Laboratory for Nanophotonic Materials and DevicesBeijingChina National University of Singapore Department of Electrical and Computer EngineeringSingapore University of Chinese Academy of Sciences Center of Materials Science and Optoelectronics EngineeringBeijingChina The University of Hong Kong Department of PhysicsHong KongChina Peking University School of PhysicsState Key Laboratory for Mesoscopic PhysicsBeijingChina

Topological edge states(TESs),arising from topologically nontrivial phases,provide a powerful toolkit for the architecture design of photonic integrated circuits,since they are highly robust and strongly localized at the boundaries of topological *** is highly desirable to be able to control TES transport in photonic *** the coupling between the TESs in a finite-size optical lattice is capable of exchanging light energy between the boundaries of a topological lattice,hence facilitating the flexible control of TES ***,existing strategies have paid little attention to enhancing the coupling effects between the TESs through the finite-size ***,we establish a bridge linking the interaction between the TESs in a finite-size optical lattice using the Landau–Zener model so as to provide an alternative way to modulate/control the transport of topological *** experimentally demonstrate an edge-to-edge topological transport with high efficiency at telecommunication wavelengths in silicon waveguide *** results may power up various potential applications for integrated topological photonics.

关键词： topological edge states finite-size effect Landau-Zener model edge-to-edge topological transport nanophotonic integrated circuits

来源：评论

学校读者我要写书评

暂无评论

Real-time Glass Recycling Quality Assurance and Contamination Reduction with IoT and Random Forest algorithm

Real-time Glass Recycling Quality Assurance and Contaminatio...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： K. Balasubadra B. Shadaksharappa Senthil Kumar Seeni V. Sridevi Thamizhamuthu R C. Srinivasan Department of Information Technology R.M.D. Engineering College Kavaraipettai Chennai Tamil Nadu India Department of Computer Science and Engineering Sri Sairam College of Engineering Anekal Bengaluru Karnataka India Department of Mobile Application Development Cognizant Technology Solutions Buffalo Grove Illinois United States of America Electrical and Electronics Engineering Academy of Maritime Education and Training Deemed to be University Chennai Tamil Nadu India Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur Campus-Chengalpattu Chennai 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)9798350359299

ISBN: (纸本)9798350359305

The recycling industry is crucial to environmental protection and resource conservation. Glass recycling has great sustainability potential, but quality assurance and contaminant reduction are major challenges. Integrating the Internet of Things (IoT) with the Random Forest algorithm, this work offers a new solution to these difficulties. IoT devices are used in glass recycling collection, transportation, sorting, and processing. These devices measure glass quality, contaminants, temperature, humidity, and other parameters in real-time. Data is sent to a central system for analysis and decision-making. Random Forest, a machine learning method that handles complicated, multidimensional datasets, powers the system. This algorithm learns from past data and updates with real-time data. It detects contaminants, foreign elements, and faults in recycled glass. This permits fast remedial action, enhancing recycled glass quality and decreasing contamination. Application of this mechanism yields two outputs. First, it improves glass recycling efficiency and produces high-quality glass for remanufacturing. Second, it significantly minimizes the environmental and economic implications of contamination and low-quality glass, which may limit recycling yields and increase waste disposal. In comparison to traditional approaches, the proposed approach that utilizes the IoT and the Random Forest algorithm reduces contamination and ensures the quality of glass recycling by 30%.

关键词： Temperature measurement Quality assurance Machine learning algorithms Data analysis Glass Real-time systems Recycling

来源：评论

学校读者我要写书评

暂无评论

AI-Based Risk Management in Financial Services

AI-Based Risk Management in Financial Services

引用

International Conference on Computational and Characterization Techniques in engineering & sciences (CCTES)

作者： Madhavi Katamaneni Prateek Agrawal Sathiesh Veera Ashok Kumar Sahoo Kawerinder Singh Sidhu Mohammed Faez Hasan Information Technology Vrsiddhartha Engineering College Masters of Computer Applications Gurukula Kangri (Deemed to be University) BTech: Bachelor of Engineering in Communications Science & Engineering Anna University Kalasalingam Academy of Research and Education (A Deemed University) Tamilnadu UIM Uttaranchal University Dehradun Uttarakhand Finance Finance and Banking Department Kerbala University Iraq

ISBN: (数字)9798350364699

ISBN: (纸本)9798350364705

When it comes to the financial services industry, efficient risk management is very necessary to guarantee stability and compliance in the face of constantly shifting market conditions. The purpose of this research study is to investigate the potential roles that artificial intelligence (AI) could play in improving risk management methods throughout financial organizations. To identify, evaluate, and mitigate financial risks, we investigate a variety of artificial intelligence techniques, such as machine learning algorithms, natural language processing procedures, and predictive analytics. Artificial intelligence models can deliver real-time insights and prediction skills that traditional approaches frequently lack. These capabilities are achieved through the analysis of historical data, transaction patterns, and market trends. Within the scope of this research project, the effectiveness of AI-driven approaches is compared to that of traditional risk management tactics. Particular attention is paid to enhancements in terms of accuracy, efficiency, and scalability. According to the findings, artificial intelligence dramatically improves risk detection and management, providing financial institutions with more powerful tools to tackle regulatory obstacles and uncertainties. This research highlights the revolutionary potential of artificial intelligence in redefining risk management frameworks, thereby paving the way for financial risk mitigation measures that are more proactive and data-driven.

关键词： Industries Uncertainty Scalability Predictive models Stability analysis Real-time systems Risk management Artificial intelligence Financial services Risk mitigation

来源：评论

学校读者我要写书评

暂无评论

Scale Up Composed Image Retrieval Learning via Modification Text Generation

arXiv

引用

arXiv 2025年

作者： Zhou, Yinan Wang, Yaxiong Lin, Haokun Ma, Chen Zhu, Li Zheng, Zhedong School of Electronics and Information Engineering Xi’an Jiaotong University Xi’an710049 China School of Electronics and Information Engineering Hefei University of Technology Hefei230009 China School of Artificial Intelligence University of the Chinese Academy of Sciences Beijing101408 China Department of Computer Science City University of Hong Kong 999077 Hong Kong Faculty of Science and Technology Institute of Collaborative Innovation University of Macau 999078 China

Composed Image Retrieval (CIR) aims to search an image of interest using a combination of a reference image and modification text as the query. Despite recent advancements, this task remains challenging due to limited training data and laborious triplet annotation processes. To address this issue, this paper proposes to synthesize the training triplets to augment the training resource for the CIR problem. Specifically, we commence by training a modification text generator exploiting large-scale multimodal models and scale up the CIR learning throughout both the pretraining and fine-tuning stages. During pretraining, we leverage the trained generator to directly create Modification Text-oriented Synthetic Triplets (MTST) conditioned on pairs of images. For fine-tuning, we first synthesize reverse modification text to connect the target image back to the reference image. Subsequently, we devise a two-hop alignment strategy to incrementally close the semantic gap between the multimodal pair and the target image. We initially learn an implicit prototype utilizing both the original triplet and its reversed version in a cycle manner, followed by combining the implicit prototype feature with the modification text to facilitate accurate alignment with the target image. Extensive experiments validate the efficacy of the generated triplets and confirm that our proposed methodology attains competitive recall on both the CIRR and FashionIQ benchmarks. © 2025, CC BY-SA.

关键词： Online searching

来源：评论

学校读者我要写书评

暂无评论

Ground Based-cloud Classification Based on Comparing Different Classification Models

Ground Based-cloud Classification Based on Comparing Differe...

引用

作者： Tao Zhang Yantian Ding Wangjiang Gong Zeyu Hou Department of Computer Science Purdue University School of Information Science and Engineering Lanzhou University Reading Academy Nanjing University of Information Science & Technology Beijing No.80 High School

Clouds are one of the most common things in our daily life,and different types of clouds will foreshadow different weather ***,accurately identifying and classifying them are important for human forecasting the local ***,artificially classifying clouds could possibly cause a minor *** the helping of machine learning classification model could avoid this situation as much as *** this study,our goal is to get sufficiently high accuracy of based-cloud *** used LBP as a preprocessing approach,and used KSVM,MLP,Custom Vision,and Resnet to compare each *** dataset contains around 15 thousand cloud images in 5 types in the same format and *** the implementation of four classification models,experiments showed that ResNet34 came out a great result with a test accuracy 94%.Therefore,this study demonstrates ResNet34 is a good image classification model in based-cloud classification field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Development of a Non-Invasive Glucose Monitoring Device Using Advanced Microcontroller

Design and Development of a Non-Invasive Glucose Monitoring ...

引用

Expert Clouds and Applications (ICOECA), International Conference on

作者： S. Divya P Karthikeyan M. Vaigundamoorthi D Ramya Manzoore Elahi M. Soudagar Rajendiran M Department of Biomedical Engineering Dr. N.G.P. Institute of Technology Coimbatore Tamil Nadu India Department of Electronics and Communication Engineering Velammal College of Engineering and Technology Madurai Tamil Nadu India Department of Electrical and Electronics Engineering Karpagam Academy of Higher Education Coimbatore Tamil Nadu India Department of Computer Science and Business Systems Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Department of VLSI Microelectronics Saveetha School of Engineering Saveetha Institute of Medical and Techinical Sciences Chennai Tamil Nadu India Department of Computer Science and Engineering Panimalar Engineering College Chennai Tamil Nadu India

ISBN: (数字)9798350385793

ISBN: (纸本)9798350385809

Millions of individuals all over the world are living with diabetes, a chronic condition that necessitates regular monitoring of Blood Glucose Levels (BGL). The present technique for minimal invasive BGL monitoring involves taking a small blood sample and transferring it to a glucometer. However, this procedure can be uncomfortable for the patient. This research presents a method for non-invasively monitoring BGL with the help of a powerful controller called the ARM Cortex-M4. For non-invasive applications, we use photoplethysmography (PPG) signals. Using a photodiode and an infrared LED light, PPG samples are received from a finger sensor. Signal processing and feature extraction are carried out using the Gray-Level Co-occurrence Matrix (GLCM) method. To predict the BGL, two ML models are developed: one employing a Linear Regression (LR) model and the other an Artificial Neural Network (ANN) model. The experimental findings show that the ANN model is quite effective, with an R2 score of 0.986. After careful consideration, the ARM Cortex-M4 microcontroller's processing capabilities were found to be optimal for running the ANN model. The model must be fine-tuned before deployment so it can communicate with the microcontroller and provide correct inference in real time. The finger sensor simplifies PPG sample collection, and the OLED display makes it simple to view BGL.

关键词： Strips Microcontrollers Artificial neural networks Predictive models Organic light emitting diodes Signal processing Glucose

来源：评论

学校读者我要写书评

暂无评论

L-CAD: Language-based Colorization with Any-level Descriptions using Diffusion Priors

arXiv

引用

arXiv 2023年

作者： Chang, Zheng Weng, Shuchen Zhang, Peixuan Li, Yu Li, Si Shi, Boxin School of Artificial Intelligence Beijing University of Posts and Telecommunications China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China National Engineering Research Center of Visual Technology School of Computer Science Peking University China International Digital Economy Academy

Language-based colorization produces plausible and visually pleasing colors under the guidance of user-friendly natural language descriptions. Previous methods implicitly assume that users provide comprehensive color descriptions for most of the objects in the image, which leads to suboptimal performance. In this paper, we propose a unified model to perform language-based colorization with any-level descriptions. We leverage the pretrained cross-modality generative model for its robust language understanding and rich color priors to handle the inherent ambiguity of any-level descriptions. We further design modules to align with input conditions to preserve local spatial structures and prevent the ghosting effect. With the proposed novel sampling strategy, our model achieves instance-aware colorization in diverse and complex scenarios. Extensive experimental results demonstrate our advantages of effectively handling any-level descriptions and outperforming both language-based and automatic colorization methods. The code and pretrained models are available at: https://***/changzheng123/L-CAD. Copyright © 2023, The Authors. All rights reserved.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Panicle-Cloud:An Open and Al-Powered Cloud Computing Platform for Quantifying Rice Panicles from Drone-Collected Imagery to Enable the Classification of Yield Production in Rice

引用

Plant Phenomics 2023年第4期5卷 905-916页

作者： Zixuan Teng Jiawei Chen Jian Wang Shuixiu Wu Riqing Chen Yaohai Lin Liyan Shen Robert Jackson Ji Zhou Changcai Yang Digital Fujian Research Institute of Big Data for Agriculture and Forestry College of Computer and Information SciencesFujian Agriculture and Forestry UniversityFuzhou 350002China State Key Laboratory of Crop Genetics&Germplasm Enhancement academy for Advanced Interdisciplinary StudiesNanjing Agricultural UniversityNanjing 210095China Ningxia Academy of Agriculture and Forestry Sciences Yinchuan 750002China College of Mechanical and Electrical Engineering Fujian Agriculture and Forestry UniversityFuzhou 350002China Cambridge Crop Research National Institute of Agricultural Botany(NIAB)Cambridge CB3 OLEUK Key Laboratory of Smart Agriculture and Forestry(Fujian Agriculture and Forestry University) Fujian Province UniversityFuzhou 350002China Center for Agroforestry Mega Data Science School of Future TechnologyFujian Agriculture and Forestry UniversityFuzhou 350002China

Rice(Oryza sativa)is an essential stable food for many rice consumption nations in the world and,thus,the importance to improve its yield production under global climate *** evaluate different rice varieties'yield performance,key yield-related traits such as panicle number per unit area(PNpM^(2))are key indicators,which have attracted much attention by many plant research ***,it is still challenging to conduct large-scale screening of rice panicles to quantify the PNpM^(2)trait due to complex field conditions,a large variation of rice cultivars,and their panicle morphological ***,we present Panicle-Cloud,an open and artificial intelligence(AI)-powered cloud computing platform that is capable of quantifying rice panicles from drone-collected *** facilitate the development of Al-powered detection models,we first established an open diverse rice panicle detection dataset that was annotated by a group of rice specialists;then,we integrated several state-of-the-art deep learning models(including a preferred model called Panicle-AI)into the Panicle-Cloud platform,so that nonexpert users could select a pretrained model to detect rice panicles from their own aerial *** trialed the Al models with images collected at different attitudes and growth stages,through which the right timing and preferred image resolutions for phenotyping rice panicles in the field were ***,we applied the platform in a 2-season rice breeding trial to valid its biological relevance and classified yield production using the platform-derived PNpM^(2)trait from hundreds of rice *** correlation analysis between computational analysis and manual scoring,we found that the platform could quantify the PNpM^(2)trait reliably,based on which yield production was classified with high ***,we trust that our work demonstrates a valuable advance in phenotyping the PNpM^(2)trait in rice,which provides a useful toolkit to enable rice br

关键词： breeding cultivar hundreds

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Salient Object Detection Using Point Supervision

arXiv

引用

arXiv 2022年

作者： Gao, Shuyong Zhang, Wei Wang, Yan Guo, Qianyu Zhang, Chenglong He, Yangji Zhang, Wenqiang Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University China Academy for Engineering & Technology Fudan University China

Current state-of-the-art saliency detection models rely heavily on large datasets of accurate pixel-wise annotations, but manually labeling pixels is time-consuming and labor-intensive. There are some weakly supervised methods developed for alleviating the problem, such as image label, bounding box label, and scribble label, while point label still has not been explored in this field. In this paper, we propose a novel weakly-supervised salient object detection method using point supervision. To infer the saliency map, we first design an adaptive masked flood filling algorithm to generate pseudo labels. Then we develop a transformer-based point-supervised saliency detection model to produce the first round of saliency maps. However, due to the sparseness of the label, the weakly supervised model tends to degenerate into a general foreground detection model. To address this issue, we propose a Non-Salient Suppression (NSS) method to optimize the erroneous saliency maps generated in the first round and leverage them for the second round of training. Moreover, we build a new point-supervised dataset (P-DUTS) by relabeling the DUTS dataset. In P-DUTS, there is only one labeled point for each salient object. Comprehensive experiments on five largest benchmark datasets demonstrate our method outperforms the previous state-of-the-art methods trained with the stronger supervision and even surpass several fully supervised state-of-the-art models. The code is available at: https://***/shuyonggao/PSOD. Copyright © 2022, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Approximation Algorithm for the Capacitated Correlation Clustering Problem with Penalties 15th

Approximation Algorithm for the Capacitated Correlation Cl...

引用

15th International Conference on Algorithmic Aspects in Information and Management, AAIM 2021

作者： Ji, Sai Li, Gaidi Zhang, Dongmei Zhang, Xianzhao Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China Department of Operations Research and Information Engineering Beijing University of Technology Beijing100124 China School of Computer Science and Technology Shandong Jianzhu University Jinan250101 China School of Mathematics and Statistics Linyi University Linyi276005 China

ISBN: (纸本)9783030931759

Correlation clustering problem is an elegant clustering problem and has many applications in protein interaction networks, cross-lingual link detection, etc. In this paper, we introduce the capacitated correlation clustering problem with penalties by combining the capacitated correlation clustering problem and the correlation problem with penalties. There are two main contributions in this paper. The first one is that we give an integer programming for the capacitated correlation clustering problem with penalties. The second one is that we provide an LP-based (4 / (4 - 5 α), 8 / α) -bi-criteria approximation algorithm for this problem, where parameter α∈ (0, 4 / 9 ]. © 2021, Springer Nature Switzerland AG.

关键词： Approximation algorithms

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：