检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Peng, Wei Ping, Zhihao Dai, Wei Fu, Xiaodong Liu, Li Liu, Lijun Yu, Ning Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming China Computer Technology Application Key Lab of Yunnan Province Kunming University of Science and Technology Kunming China State University of New York The College at Brockport Department of Computing Sciences BrockportNY14422 United States

ISBN: (纸本)9798350386226

Using deep learning models on spatial transcriptomics data to identify the spatial domain is crucial for uncovering the spatial distribution of cells and gene expression patterns within tissues, essential for understanding complex biological processes and disease mechanisms. Existing methods for spatial domain partitioning often rely on predefined adjacency relationships at a single scale, overlooking the hierarchical structure and functional characteristics of biological tissues. In this paper, we propose SpaNFM, a novel method that leverages sparse attention-based hierarchical node representation and multi-view contrastive learning for spatial domain identification in spatial transcriptomics data. The SpaNFM first treats each spot as a node and constructs two views using different data augmentation techniques based on tissue image information, gene expression profiles, and spatial coordinates of cells. Subsequently, SpaNFM utilizes a sparse attention-based hierarchical node fusion module to generate coarse-grained node representations. This fine-to-coarse hierarchical structure integrates complementary information from multi-granularity node features and reduces model complexity due to the decreased node size. The model parameters are updated using gene expression reconstruction loss and contrastive loss on the coarse-grained node representations from the two views. Finally, the learned node features are subjected to downstream clustering using the Leiden algorithm. We tested SpaNFM on the human dorsolateral prefrontal cortex dataset. The results demonstrate that SpaNFM outperforms other state-of-the-art methods in most cases. The data and code are available at: https://***/weiba/SpaNFM © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Single-Cell Language Model:A Survey

引用

Big Data Mining and Analytics 2024年第4期7卷 1169-1186页

作者： Wei Lan Guohang He Mingyang Liu Qingfeng Chen Junyue Cao Wei Peng Guangxi Key Laboratory of Multimedia Communications and Network Technology School of ComputerElectronic and InformationGuangxi UniversityNanning 530004China School of Computer and Electronic Information Guangxi UniversityNanning 530004China College of Life Science and Technology Guangxi UniversityNanning 530004China Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming 650500China

The transformers have achieved significant accomplishments in the natural language processing as its outstanding parallel processing capabilities and highly flexible attention *** addition,increasing studies based on transformers have been proposed to model single-cell *** this review,we attempt to systematically summarize the single-cell language models and applications based on ***,we provide a detailed introduction about the structures and principles of ***,we review the single-cell language models and large language models for single-cell data ***,we explore the datasets and applications of single-cell language models in downstream tasks,such as batch correction,cell clustering,cell type annotation,gene regulatory network inference,and perturbation ***,we discuss the challenges of single-cell language models and provide promising research *** hope this review will serve as an up-to-date reference for researchers who are interested in the direction of single-cell language models.

关键词： language model transformers deep learning single-cell data

来源：评论

学校读者我要写书评

暂无评论

User-Specified Conditional Preferences Driven Personalized Skyline Web Services Selection

User-Specified Conditional Preferences Driven Personalized S...

引用

IEEE International Conference on Software engineering and Service sciences (ICSESS)

作者： Senfu Ke Xiaodong Fu Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming Yunnan Province China Yunnan Key Laboratory of Computer Technology Application Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming Yunnan Province China

ISBN: (数字)9798350389166

ISBN: (纸本)9798350389173

The proliferation of web services with similar functionalities challenges selecting the most relevant service based on Quality of Service (QoS). Skyline queries help by reducing the candidate pool, but the resulting service skyline can still be extensive, making selection difficult. A personalized Skyline service selection method provides a smaller, more manageable set. Current approaches often overlook inter-dependencies between user preferences, complicating complex preference management. This paper introduces CP-Skyline, an efficient method leveraging Conditional Preference Networks (CP-Nets) to incorporate user-specific preferences and personalize the service selection process. We present a personalized conditional preference model based on CP-Nets to prune candidate services and compress the query space, defining a new dominance relation for CP-Skyline computation, and validate our approach through extensive experiments on synthetic and real-world datasets.

关键词： Web services Computational modeling Quality of service Software engineering

来源：评论

学校读者我要写书评

暂无评论

Brain-inspired artificial intelligence research: A review

引用

science China(Technological sciences) 2024年第8期67卷 2282-2296页

作者： WANG GuoYin BAO HuaNan LIU Qun ZHOU TianGang WU Si HUANG TieJun YU ZhaoFei LU CeWu GONG YiHong ZHANG ZhaoXiang HE Sheng Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and TelecommunicationsChongqing 400065China Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and TelecommunicationsChongqing 400065China College of Computer and Information Science Chongqing Normal UniversityChongqing 401331China State Key Laboratory of Brain and Cognitive Science Institute of BiophysicsChinese Academy of SciencesBeijing 100101China School of Psychological and Cognitive Sciences Peking UniversityBeijing 100871China State Key Laboratory of Multimedia Information Processing School of Computer SciencePeking UniversityBeijing 100871China Department of Computer Science School of ElectronicsInformation and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Faculty of Electronic and Information Engineering Xi’an Jiaotong UniversityXi’an 710049China The Center for Research on Intelligent Perception and Computing Institute of AutomationChinese Academy of SciencesBeijing 100190China Institute of Biophysics Chinese Academy of SciencesBeijing 100101China

Artificial intelligence(AI) systems surpass certain human intelligence abilities in a statistical sense as a whole, but are not yet the true realization of these human intelligence abilities and behaviors. There are differences, and even contradictions, between the cognition and behavior of AI systems and humans. With the goal of achieving general AI, this study contains a review of the role of cognitive science in inspiring the development of the three mainstream academic branches of AI based on the three-layer framework proposed by David Marr, and the limitations of the current development of AI are explored and analyzed. The differences and inconsistencies between the cognition mechanisms of the human brain and the computation mechanisms of AI systems are analyzed. They are found to be the cause of the differences and contradictions between the cognition and behavior of AI systems and humans. Additionally, eight important research directions and their scientific issues that need to focus on braininspired AI research are proposed: highly imitated bionic information processing, a large-scale deep learning model that balances structure and function, multi-granularity joint problem solving bidirectionally driven by data and knowledge, AI models that simulate specific brain structures, a collaborative processing mechanism with the physical separation of perceptual processing and interpretive analysis, embodied intelligence that integrates the brain cognitive mechanism and AI computation mechanisms,intelligence simulation from individual intelligence to group intelligence(social intelligence), and AI-assisted brain cognitive intelligence.

关键词： artificial intelligence cognitive science brain science intelligence science large language model

来源：评论

学校读者我要写书评

暂无评论

Exploiting hybrid features extracted from color spaces of dermoscopic images 28

Exploiting hybrid features extracted from color spaces of de...

引用

28th IEEE International Conference on Emerging Technologies and Factory automation, ETFA 2023

作者： Moldovanu, Simona Miron, Mihaela Culea-Florescu, Anisia Dunarea de Jos University of Galati Faculty of Automation Computers Electrical Engineering and Electronics Department of Computer Science and Information Technology 47 Domneasca Street 800008 Galaţi800008 Romania Dunarea de Jos University of Galati Faculty of Automation Computers Electrical Engineering and Electronics Department of Electronics and Telecommunications 47 Domneasca Street 800008 Galaţi800008 Romania

ISBN: (纸本)9798350339918

In the context of detecting dangerous illnesses of the patient affected by skin lesions, this study is focused on the problem of improving the classification of melanoma vs. normal nevus considering neural network and new proposed features based on high and low pixels intensity, and densities of the pattern detected with hit-or-miss (HoM) morphological transform. A large set of features from color spaces such as RGB (red, green, and blue), HSV (hue, saturation, and value) and L∗a∗b∗ (lightness variable L∗, chromaticity indices a∗ and b∗) were initially extracted and grouped in two parts: the first group includes first and second order features, and the second group contains hybrid features (a mix of first order, second order features and proposed features). The dimensionality of the features from these two groups is considerably reduced with principal component analysis (PCA) statistical method and fed three different types of neural network (NN): Radial Basis Function Neural Network (RBFNN), Cascade-Forward Neural Network (CFNN) and Pattern Recognition Neural Network (PRNN). From this corroboration of hybrid features, color space and NN, the L∗a∗b∗ color space with CFNN provided accuracy (ACC) of 0.897, F1-score of 0.91 and area under the ROC curve (AUC) of 0.896, respectively. © 2023 IEEE.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Research on Citrus Leaf Disease Recognition Using Class-Agnostic Contrastive Learning and Supervised Organizational Mapping

引用

IEEE Access 2025年

作者： Xiao, Wen Shang, Jinxia Li, Fan Ao, Ou Wang, Xin Tian, Shiyi Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming650500 China Kunming University of Science and Technology Yunnan Key Lab of Computer Technology Applications Kunming650500 China

Early detection of plant diseases is crucial for enhancing agricultural productivity and ensuring crop protection. While computer vision offers scalable alternatives to manual inspection, existing methods face two understudied challenges: (1) performance degradation in cluttered real-world conditions, and (2) ineffective feature separation for randomly distributed lesions with diverse symptoms. Notably, current research predominantly relies on controlled-environment datasets, lacking publicly accessible benchmarks with authentic field complexities. To address these, we present the first large-scale citrus leaf disease dataset (5,763 images, 6 categories) capturing complex field conditions including varying illumination, occlusion, multi-scale lesions, and deceptive backgrounds. Our key methodological innovations include a three-stage weakly supervised framework that systematically resolves background interference and feature redundancy: (i) Class-agnostic contrastive localization enabling precise lesion mapping without region annotations, (ii) Stable feature initialization through region-guided classification training, (iii) Sparse orthogonal mapping with experimentally-determined nodes introducing orthogonality constraints to enhance feature separation. Through feature alignment and feature fusion, an accuracy of 97.1% is achieved (+2.4% vs ResNet-18). Evaluations on citrus leaf and public datasets demonstrate superior accuracy and interpretable lesion localization, advancing plant disease diagnosis. © 2013 IEEE.

关键词： Citrus fruits

来源：评论

学校读者我要写书评

暂无评论

Prediction of rainfall-type debris flow in Jiangjiagou based on LSTM-Attention 3

Prediction of rainfall-type debris flow in Jiangjiagou based...

引用

3rd International Conference on computer Vision, Image and Deep Learning and International Conference on computer engineering and Applications, CVIDL and ICCEA 2022

作者： Gao, Yuan Li, Yingna Kunming University of Science and Technology College of Faculty of Information Engineering and Automation Kunming China Key Laboratory of Computer Technology Application of Yunnan Province Kunming China

ISBN: (纸本)9781665459112

Through the neural network model, the rainfall-type debris flow in Jiangjiagou is predicted. Based on seven meteorological factors with time series characteristics, such as daily rainfall, previous effective rainfall, ground temperature, and humidity, which have been screened by features, the Jiangjiagou rainfall debris flow prediction and early warning model based on LSTM-Attention is constructed. The results show that: (1) LSTM-Attention model is 0.02 higher than that of the Attention-LSTM model, and the prediction effect is better. (2) The prediction accuracy of LSTM-Attention model for Jiangjiagou rainfall-type debris flow can reach 0.88, which is 0.05, 0.07, 0.04, 0.25, 0.13 higher than that of LSTM model, RNN model, RNN-Attention model, SVM model, and BP model, respectively. Research results: It provides a new idea and method for the prediction and research of rainfall-type debris flow, which can be referenced by scholars. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

PP-SSL: Priority-Perception Self-Supervised Learning for Fine-Grained Visual Recognition

arXiv

引用

arXiv 2024年

作者： Li, Shuaiheng Cai, Qing Zhang, Fan Zhang, Menghuan Shu, Yangyang Liu, Zhi Li, Huafeng Liu, Lingqiao College of Computer Science and Technology Ocean University of China China School of Automation Northwestern Polytechnical University China School of Information Science and Engineering Shandong University China School of Computer Science The University of Adelaide Australia Faculty of Information Engineering and Automation Kunmimg University of Science and Technology China

Self-supervised learning is emerging in fine-grained visual recognition with promising results. However, existing self-supervised learning methods are often susceptible to irrelevant patterns in self-supervised tasks and lack the capability to represent the subtle differences inherent in fine-grained visual recognition (FGVR), resulting in generally poorer performance. To address this, we propose a novel Priority-Perception Self-Supervised Learning framework, denoted as PP-SSL, which can effectively filter out irrelevant feature interference and extract more subtle discriminative features throughout the training process. Specifically, it composes of two main parts: the Anti-Interference Strategy (AIS) and the Image-Aided Distinction Module (IADM). In AIS, a fine-grained textual description corpus is established, and a knowledge distillation strategy is devised to guide the model in eliminating irrelevant features while enhancing the learning of more discriminative and high-quality features. IADM reveals that extracting GradCAM from the original image effectively reveals subtle differences between fine-grained categories. Compared to features extracted from intermediate or output layers, the original image retains more detail, allowing for a deeper exploration of the subtle distinctions among fine-grained classes. Extensive experimental results indicate that the PP-SSL significantly outperforms existing methods across various datasets, highlighting its effectiveness in fine-grained recognition tasks. Our code will be made publicly available upon publication. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Frequency-Current Induction AC Electric Drive with Vector Correction of the Control Signal 4

Frequency-Current Induction AC Electric Drive with Vector Co...

引用

4th International Conference on Control Systems, Mathematical Modeling, automation and Energy Efficiency, SUMMA 2022

作者： Meshcheryakov, Victor Boikov, Andrei Muravyev, Artem Bobrov, Maxim Lipetsk State Technical University Automation and Computer Science Faculty Lipetsk Russia Ogarev Mordovia State University Department of Electronic & Electrical Engineering Saransk Russia

ISBN: (数字)9781665456593

ISBN: (纸本)9781665456593

The problems of creating controlled electric drive systems based on an induction motor with a phase rotor, easy to manufacture, cheap to maintain and economical, remain relevant due to their fairly wide application on lifting and transport mechanisms (LTM), for example, on bridge metallurgical cranes and conveyors. At the same time, one of the important tasks is to increase the efficiency of AC electric drives with energy saving, which is achieved through the introduction of a frequency converter. At the same time, the parametric start-up control and frequency control systems currently used, made on the basis of starting resistors and controllers, are not economical in terms of energy consumption and do not allow to provide the required dynamic indicators. Currently, frequency converters with a DC link implemented on fully controlled IGBT transistors are mainly used to power regulated AC electric drives. The development of control systems for AC electric motors has led to the emergence of new algorithms for controlling the power switches of the frequency converter, which improve the quality of the voltage feeding the stator winding, reduce the number of high-frequency harmonics in the generated voltage and current of the stator. A promising direction for the development of frequency asynchronous electric drive systems based on an asynchronous motor with a phase rotor, characterized by the ability to measure the instantaneous values of the phase currents of the rotor, is the use of scalar frequency-current control systems with additional correction circuits of moment-forming variables, allowing to implement scalar control with vector correction of the three-phase signal setting the instantaneous values of phase currents of the stator. © 2022 IEEE.

关键词： Induction motors

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection of Tuberculosis with the Help of Image Processing and Machine Learning Classifier 7

Automatic Detection of Tuberculosis with the Help of Image P...

引用

7th International Conference on Computing in engineering and Technology, ICCET 2022

作者： Sharma, Anshu Malhotra, Rahul Sharma, Anurag Department of Computer Science & Engineering CT University Ludhiana India Department of Electronics & Communication Engineering CT Group of Institutions Jalandhar India Faculty of Engineering Design and Automation GNA University Phagwara India

ISBN: (纸本)9781839537042

Tuberculosis is the substantial irresistible disease present in human that principally influences lungs, this tuberculosis is one the main ten noticeable reasons for death for human. It has very typical symptoms so without testing it isn't sure that patient has infected with TB. In this paper, an automated framework dependent on image handling is proposed to help specialists and radiologists in deciphering Chest X-beams (CXR) for early identification of lung Tuberculosis (TB). CXR can show the abnormalities in lungs as well as TB which helps to precisely and rapidly distinguish TB on the grounds that early treatment will provide to patients and disease will stop spreading in body. The proposed system comprised of preprocessing, segmentation, features extraction, and classification. In this paper proposed a strategy of image segmentation and AI to conclusion and characterize the tuberculosis (TB). These tool and procedures are utilized to earlier uncover of tuberculosis (TB) illness. Additionally arrange the sort of TB. The framework recognizes the tuberculosis with more prominent precision. © 2022 The Institution of engineering and Technology.

关键词： Diseases

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：