检索结果-内蒙古大学图书馆

Class Distribution Pyramid Experts for Long-tailed Visual Recognition

Class Distribution Pyramid Experts for Long-tailed Visual Re...

Information technology,Big Data and Artificial Intelligence (ICIBA), International Conference on IEEE International Conference on

作者： Yijie Li Xiao Huang Yifan Zhang Lin Li Jie Ma School of Artificial Intelligence and Automation Huazhong University of Science and Technology (HUST) Wuhan China China Ship Development and Design Center Wuhan China

Deep long-tailed visual recognition is a challenging task due to its extreme imbalance in classes. Existing methods improve the overall performance by making a trade-off between head and tail classes. We conduct experiment find that in this way, not only the performance of the head classes is compromised, but also the performance of the tail classes is not maximized. Based on these observations, we propose Class Distribution Pyramid Experts(CDPE), a clean and simple framework for end-to-end training.T each expert are calculated by insta hrough the idea of divide and conquer, we maximize the representation of classes at different quantitative levels by different experts and further propose a novel instance-aware aggregation network that dynamically integrates the predictions of different experts. We conducted extensive experiments on CIFAR10/100-LT, ImageNet-LT and iNaturalist2018 datasets to demonstrate our method’s effectiveness, practicability, and state-of-the-art performance. We hope this simple method will motivate people to rethink the divide-and-conquer strategy in long-tailed visual recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simulation and Analysis of Congestion in Vehicle Networks by Using Machine Learning Framework 2

Simulation and Analysis of Congestion in Vehicle Networks by...

引用

2nd IEEE International Conference on Advances in Computing, Communication and Applied Informatics, ACCAI 2023

作者： Gupta, Raj Kumar Kumari, R. Krishna Anbu, C. Meganathan, R. Rajah, A. Joseph Lourdu Dobhal, Dinesh Chandra Sardar Vallabhbhai Patel College Department of Physics Bihar Bhabua821101 India College of Engineering and Technology Srm Institute of Science and Technology Department of Career Development Centre Tamil Nadu Kattankulathur603203 India Kongu Engineering College Department of Mechatronics Engineering Tamil Nadu Erode638060 India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Vaddeswaram22302 India Department of English Tamil Nadu Dindigul624622 India Graphic Era Deemed to Be University Department of Computer Science and Engineering Uttarakhand Dehradun248002 India

ISBN: (纸本)9798350315905

The bottleneck networks of the progression of vehicular traffic need an exhaustive cognizance and bits of knowledge of the factors that cause congestion, which characterizes the second and spot of traffic breakdown. The organization becomes clogged because of the rising number of vehicles out and about. Many exploration studies have been directed to resolve the issues. Functional examination, specifically the plan, investigation, and the board of the traffic stream dynamic, appears to esteem re-enactment and demonstrating to the connected difficulties. To reduce gridlock for a smooth and low-thickness traffic stream framework, this work focused on a reproduction model for vehicular traffic stream. In this review, a congestion-mindful message (CAM) in view of vehicle ID is introduced for guide signals in a vehicle setting. The overhauled vehicle ID-based investigation model is introduced at first at the Macintosh convention of the vehicle climate. The model loads the randomized back-off numbers chosen by the autos taking part in the back-off strategy utilizing the vehicle ID implanted in every one of their one-of-a-kind CAMs. Because of the indistinguishable back-off number, this outcome in the recognizable proof of a vehicle ID-based randomized ease-off code, which brings down the gamble of a crash. In this review, traffic thickness-based congestion the board calculation (TDCCA) using machine learning is proposed. While only one-fourth of the congestion window is utilized in the trial, the better numerical method beats the prior work's general parcel dormancy. To expand the viability of the model boundaries, the exploration utilizes the congestion the board method that changes the pace of CAM broadcast across the host controller. © 2023 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Finger-wrist Gesture Recognition based on Surface Electromyography and Inertial Signals

Finger-wrist Gesture Recognition based on Surface Electromyo...

引用

Rehabilitation Engineering and Assistive technology (i-CREATe), International Convention on

作者： Bin Wen Sihong Wei Sinan Li Lianchi Huang Jin Xu Key Laboratory of Biomedical Information Engineering of Ministry of Education Institute of Health and Rehabilitation Science School of Life Science and Technology Xi'an Jiaotong University Xi'an China Sichuan Digital Economy Industry Development Research Institute Chengdu China

ISBN: (数字)9798350355154

ISBN: (纸本)9798350355161

Surface electromyography (sEMG) is often used as an ideal control source to drive an intelligent prosthetic hand. The study aims to distinguish 24 types of finger-wrist joint movements based on 8-channel sEMG signals and 6-channel inertial signals. Considering the dynamic characteristics of signal, we proposed a new method named segmented sliding window (SSW) for feature extraction. Compared with fixed window (FW) and sliding window (SW), the new method performed better. Then fisher score (FS) and sequential forward selection (SFS) were employed for feature selection. And a support vector machine (SVM) incorporating majority voting method was adopted as a classifier. The results from 14 subjects indicated that the combination of SSW and SFS got best performance, whose classification accuracy can achieve to 96.61% only base on sEMG signals within length of 300ms. Classification accuracy could be raised to 97.56 % with inertial signals added, which verified inertial signal is helpful for motion recognition.

关键词： Support vector machines Accuracy Gesture recognition Assistive technologies Feature extraction Electromyography Vectors Prosthetic hand

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Machine Learning and Deep Learning Models for Microplastic Classification using FTIR Spectra

A Comparative Study of Machine Learning and Deep Learning Mo...

引用

International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)

作者： Aeint Shune Thar Seksan Laitrakun Somrudee Deepaisarn Pakorn Opaprakasit Pattara Somnuake Krit Athikulwongse Sirindhorn International Institute of Technology (SIIT) Thammasat University Pathum Thani 12120 Thailand National Electronics and Computer Technology Center (NECTEC) National Science and Technology Development Agency (NSTDA) Pathum Thani 12120 Thailand

Microplastic contamination is a pressing environmental challenge, necessitating advanced detection and effective classification methods. As the prevalence of microplastics continues to rise globally, the need for innovative and accurate solutions becomes paramount. Aquatic ecosystems, in particular, are increasingly bearing the brunt of this contamination, emphasizing the urgency to address plastic pollution in our waters. Fourier-transform infrared (FTIR) spectroscopy, a widely recognized technique, offers promise but contends with spectral noise, particularly from membrane filters. In this context, our study contrasts machine learning (ML) and deep learning (DL) models for their ability to classify microplastics via FTIR spectra interfered by membrane filter noise. Utilizing an FTIR dataset from multiple sources, we rigorously assessed multiple ML algorithms and convolutional neural networks (CNNs). While ML models, specifically Support Vector Classification (SVC) and K-Nearest Neighbors (KNN), recorded accuracies of 95.99% and 95.55%, respectively, the DL model, LeNet5, surpassed them with 96.93%. Conversely, certain DL models underperformed, shedding light on the intricate nature of the identification task. Our findings provide valuable insights into the capabilities and constraints of ML and DL methodologies in the realm of microplastic classification through FTIR, encouraging further refinement and research in this critical environmental domain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mineralogical and Geochemical Characterisation of Rocks and Geothermal Fluids in the Olkaria Geothermal Field, Kenya: Potential for Epithermal Deposits

引用

International Journal of Geosciences 2024年第12期15卷 1113-1133页

作者： Christine Jerotich Kiptoo Isaac Kanda Nicholas Mariita Patrick Kariuki Patrick Kirita Gevera Geothermal Energy Training Institute (GeTRI) Dedan Kimathi University of Technology Nyeri Kenya Geothermal Development Company (GDC) Nakuru Kenya Department of Civil Engineering University of South Africa (Florida Science Campus) Johannesburg South Africa

The Kenyan Olkaria geothermal field has incredibly high geothermal potential in the East African Rift, the Kenyan Rift Valley. While the Olkaria geothermal area has been primarily attributed to electricity generation and direct uses, this research investigates the potential of epithermal deposits in the geothermal systems with particular interests in base metals (Zn, Pb, and Fe) and alkali metals (Li, Na, K) in geothermal rocks and fluids. The study employed geochemical, geological, and well-logging analyses to characterise and assess the conditions in the geothermal system suitable for forming and depositing epithermal minerals. Rock cuttings and fluid samples were collected from geothermal wells, fumaroles, and hot springs. Findings indicate that the mineralisation in the Olkaria wells occurs in microveins and disseminations in the rock matrix, majorly sulfides, and oxides in hydrothermal alteration zones. The reported Zn, Pb, and Fe mineralisation mainly relates to low sulphidation type from the characterised sulphur metal complexes and oxides. Fluid samples recorded the metals as follows: Fe (0.12 - 3.9 ppm), Zn (4.21 - 5.23 ppm), Pb (1.55 - 2.04 ppm), and lithium concentrations at ≤ 3 ppm, which is lower than extractible values in geothermal brines in the Salton Sea and geothermal fields of Europe. The economic characterisation of rocks and fluid samples in our area indicates that the concentration of base and alkali metals has not yielded economically viable values compared to other geothermal systems with economic grades. Detailed studies are recommended to quantify mineralisation in Olkaria geothermal fields and their extractability for sustainable management of the geothermal resource.

关键词： East Africa Rift System (EARS) Epithermal Deposits Geochemistry Geothermal Systems

来源：评论

学校读者我要写书评

暂无评论

Research on Automatic Spine Labeling Algorithm Based on IMAA-Unet

Research on Automatic Spine Labeling Algorithm Based on IMAA...

引用

Chinese Automation Congress (CAC)

作者： Hanwen Dai Lin Dong Xinyang Jiang Science and Technology Development Department Shanghai Electric Holding Group Co. Ltd. Zhihui Healthcare Equipment Branch Shanghai China

Magnetic resonance imaging (MRI) is one of the commonly used inspection methods in clinical imaging diagnosis of human spinal diseases. Rapid and accurate localization and segmentation of vertebrae are helpful to the clinical diagnosis and treatment of spinal diseases. In this paper, according to Nash equilibrium principle, the training data is selectively augmented to obtain more comprehensive training data. Combine traditional Unet network with InceptionV2, Attention Gate, Atrous Spatial Pyramid Pooling to reduce contextual information loss. Then, the Merge module is added to enable the network to learn context features more fully. During marking and positioning, the vertebral body label is set to the coccygeal vertebra (S), the rest of the vertebral body, and the non-vertebral body. Then, the image data is used for training and the recognition model is generated. When it is necessary to mark and locate the spine, the image is recognized according to the trained spine recognition model, and the spatial position information between the recognized vertebrae is calculated. Based on the identification and positioning of coccygeal vertebra, the labeling and positioning of other vertebral bodies are completed. Compared with the results of traditional Unet and Unet++, the algorithm used in this paper has better recognition accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Visualizing and Tracking Ph Fluctuation in Living Systems and Real Food Samples with a Novel Dual-Site Modulated Reversible Ratiometric Fluorescent Probe

SSRN

引用

SSRN 2024年

作者： Zhao, Xiongjie Xiao, Jiajing Tang, Dongfang Zhou, Liyi Qin, Zuodong Wang, Zongcheng College of Chemistry and Biological Engineering Hunan University of Science and Engineering Hunan Yongzhou425199 China College of Food Science and Engineering Central South University of Forestry and Technology Hunan Changsha410004 China Hunan Engineering Technology Research Center for Comprehensive Development and Utilization of Biomass Resources Hunan University of Science and Engineering Hunan Yongzhou425199 China

Acid-base balance in cellular environment is closely related to serious of biological events, and abnormal intracellular pH has been recognized as a trigger of numerous disorders. Additionally, pH is also an important parameter in the process of food spoilage. Therefore, the development of monitoring techniques for pH fluctuation in living systems and food samples is of great significance, and also has attracted tremendous interest over the past decades. Fluorescence probe has been turned into a great powerful tool for the monitoring of intracellular pH for its advantages of convenience, high sensitivity, and free of invasion. In the present work, a reversible ratiometric fluorescent probe (Cou-Dcm-pH) based on ICT-PET-FRET strategy was fabricated by 7-hydroxycoumarin as donor and dicyanoisophorone derivative as acceptor through non-conjugated linker. The probe Cou-Dcm-pH was capable of monitoring pH in the wide range of 4.00-5.00 and 5.75-7.25 by analyzing of ratio of I655/I455 and the reverse ratio of I455/I655, respectively. Additionally, Cou-Dcm-pH showed excellent anti-interference capability, good reversibility, outstanding cell permeability, and low cytotoxicity. More importantly, Cou-Dcm-pH was further successfully utilized to monitoring pH variation in metamorphic process of real protein-rich food samples and ratiometric fluorescence imaging of pH fluctuation in HeLa cells and zebrafish. The above performances of Cou-Dcm-pH ensure it can be further practically applied in monitoring pH variation in food storage and pH-relative physiological and pathological processes in biological systems. © 2024, The Authors. All rights reserved.

关键词： Probes

来源：评论

学校读者我要写书评

暂无评论

Logic-Aware Knowledge Graph Reasoning for Structural Sparsity under Large Language Model Supervision 25

Logic-Aware Knowledge Graph Reasoning for Structural Sparsit...

引用

34th ACM Web Conference, WWW 2025

作者： Pan, Yudai Hong, Jiajie Zhao, Tianzhe Song, Lingyun Liu, Jun Shang, Xuequn School of Computer Science Northwest Polytechnical University Shaanxi Xi’an China Key Laboratory of Big Data Storage and Management Northwestern Polytechnical University Shaanxi Xi’an China School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an China Research & Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen China National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Shaanxi Xi’an China

ISBN: (纸本)9798400712746

Knowledge Graph (KG) reasoning aims to predict missing entities in incomplete triples, which requires adequate structural information to derive accurate embeddings. However, KGs in the real world are not as dense as the idealized benchmarks, where sparse graph structures restrict the comprehensive structural information for superior performance. Although the logical semantics in KGs shows its potential in alleviating the impact of structural sparsity, there still exist some challenges. The deficient supervision and the semantic gap of logic make it difficult to introduce logical semantics in sparse KG reasoning. To this end, we propose a novel KG reasoning approach LoLLM injecting logic with the supervised information supplied by the Large Language Model (LLM), which is proved to be effective in evaluating and scoring. Firstly, LoLLM derives structural embeddings employing a graph convolutional network (GCN) with relation-aware and triple-aware attention. LoLLM secondly constructs reasoning paths instantiated from the first-order logic rules extracted from sparse KGs, and injects the logical semantics by a designed LLM-enhanced tuning strategy. We propose a textual loss (TL) and a logical loss (LL) in the optimization and obtain logical tuning embeddings of KG in this process. Finally, LoLLM fuses structural embeddings from the GCN and logical tuning embeddings from the LLM-enhanced tuning for scoring and incomplete triple prediction. Extensive experiments on two sparse KGs and a benchmark show that LoLLM outperforms state-of-the-art structure-based and Language Model (LM)-augmented baselines. Moreover, the logic rules with corresponding confidences provide explicit explanations as an interpretable paradigm. © 2025 Copyright held by the owner/author(s).

关键词： Structural analysis

来源：评论

学校读者我要写书评

暂无评论

Intelligent DNA methylation biomarker selection for colorectal cancer

Intelligent DNA methylation biomarker selection for colorect...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Tsai, Yi-Hsuan Lai, Lucy Yi-Hsuan Liao, Yun-Te Chen, Shu-Jen Pai, Tun-Wen Chang, Margaret Dah-Tsyr National Taipei University of Technology Department of Computer Science and Information Engineering Taipei Taiwan Act Genomics Co. Ltd. Department of Product Development Taipei Taiwan National Tsing Hua University Institute of Molecular and Cellular Biology College of Life Science Hsinchu Taiwan

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

DNA methylation plays an important role in the regulation of gene expression, and aberrant changes in epigenetic regulation can be detected in cancer development or progress. In this study, genome-wide DNA methylation profiles and electronic medical records were combined to identify effective DNA methylation biomarkers for colorectal cancer (CRC). Statistical analytics and deep learning approaches were integrated to explore associated novel biomarkers. These identified biomarkers could facilitate accurate diagnosis of CRC and monitor disease progression for a testing subject, and provide suggestions for appropriate medical treatments. Firstly, DNA methylation profiles were analyzed through a standard pipeline to discover significantly differential methylation biomarkers as primary biomarkers. Incorporating Taiwan's National Health Insurance Research Database (NHIRD), associated comorbidities of CRC were identified and associated disease genes were considered as secondary biomarkers. The intersection of primary and secondary biomarkers was performed to obtain CRC-relevant biomarker candidates, and gene ontology annotations were used to calculate candidate biomarker-to-biomarker distances. Based on the formulated gene-pair distance matrix for all candidate biomarkers, we applied clustering algorithms to categorize candidate biomarkers into different functional groups. Corresponding coefficients for each biomarker within a functional cluster were ranked through an attention-based recurrent neural network. The weighting coefficient for each biomarker was further taken as a reference for designing a practical testing toolkit. Finally, we obtained 11 important biomarkers from 5 functional clustered groups which were established by the 141 biomarker candidates screened from 450k DNA methylation probes. © 2022 IEEE.

关键词： Alkylation

来源：评论

学校读者我要写书评

暂无评论

Mass imbalance and electron-phonon correlation impact on the excitonic insulator state in semimetal/semiconducting materials

引用

Physical Review B 2024年第8期109卷 085105-085105页

作者： Thi-Hong-Hai Do Thi-Hau Nguyen Van-Nham Phan Department of Physics Hanoi University of Mining and Geology Duc Thang Bac Tu Liem Hanoi 10072 Vietnam Faculty of Physics Graduate University of Science and Technology Vietnam Academy of Science and Technology Hanoi 10072 Vietnam Institute of Research and Development Duy Tan University 3-Quang Trung Danang 550000 Vietnam Faculty of Natural Sciences Duy Tan University 3-Quang Trung Danang 550000 Vietnam

Signatures of the excitonic insulator in the mass-imbalance extended Falicov-Kimball model with the electron-phonon correlation are investigated. Based on the unrestricted Hartree-Fock approximation, we derive a set of self-consistent equations specifying the excitonic insulator order parameter and then construct the complex phase diagram of the excitonic insulator states. For a given intermediate Coulomb interaction, the excitonic insulator states at nearly zero temperature are found if the electronic hybridization-phonon coupling is sufficiently large. The window of the excitonic insulator states expands as suppression of the mass anisotropy. The influence of the mass imbalance and electron-phonon correlations on the nature of the BCS-BEC crossover of the condensation states is also addressed in the signatures of the optical conductivity. The preformed excitonic bound states in the normal semiconducting side are inspected in the features of the imaginary part of the dynamical excitonic susceptibility function. By increasing the electronic hybridization-phonon coupling or suppressing the mass imbalance, we find the dominance of the excitonic coherent bound states. The compact influence of the mass imbalance and electron-phonon correlations on the whole picture of the excitonic insulator state thus has been discussed.

关键词： Excitons Fermionic condensates Many-body techniques

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：