检索结果-内蒙古大学图书馆

Malignant tumor identification with custom activated deep CNN architecture: TumorNet

AIP Conference Proceedings 2024年第1期2853卷

作者： Ajay Balakrishnan K. R. Sri Preethaa N. Yuvaraj K. Kathiresan B. Karthikeyan Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore Tamilnadu India Department of Artificial Intelligence and Data Science KPR Institute of Engineering and Technology Coimbatore Tamilnadu India

Brain Cancer is the most dangerous type of cancer, which affects hundreds of thousands of people worldwide every year. Early identification of brain tumor is essential for timely treatment, which is crucial for the patient’s survival. Researchers have found it challenging to develop Computer-Aided Diagnosis (CAD) for Brain Tumor Identification. Many studies have discussed the feasibility of Deep Convolutional Neural Network algorithms like ResNet, Inception, VGG in Brain Tumor Classification and Detection. These Deep Learning algorithms seem to have struggled from vanishing gradient, model bias with overfitting due to smaller medical datasets available. The proposed model TumorNet adopts a custom activated Deep CNN Architecture for classifying the more dangerous malignant tumors from benevolent tumors. The proposed model is trained from scratch and able to train with a smaller dataset consisting of MRI scans. It is evaluated, and it gives an impressive accuracy of 98.24%, outperforming other state-of-the-art CNN models, ResNet-101 and EfficientNet-B0. In comparison, the F1 scores of the proposed model are estimated at 98.05%, significantly higher than the other two models, which are 82.46 and 88.33%, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Pipeline Blockage Identification Model Learning from Unbalanced datasets Based on Random Forest

A Pipeline Blockage Identification Model Learning from Unbal...

引用

第33届中国控制与决策会议

作者： Fang Mingyue Feng Zao Wang Xiaodong Ma Jun Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Province Key Laboratory of Artificial Intelligence Kunming University of Science and Technology

Aiming at the problem of decreased accuracy of operating state recognition caused by the unbalanced data acquisition between the normal and blocked failure states of urban drainage pipelines,a new method of pipeline blockage state recognition based on unbalanced data is *** experimental results show that the random forest algorithm,which uses bootstrap sampling and simple voting methods to integrate decision trees,has a good effect on the pipeline blocking state recognition of unbalanced data.

关键词： Unbalanced data Drainage pipes Blockage status identification Random forest

来源：评论

学校读者我要写书评

暂无评论

SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models

arXiv

引用

arXiv 2023年

作者： Huang, Yuzhou Xie, Liangbin Wang, Xintao Yuan, Ziyang Cun, Xiaodong Ge, Yixiao Zhou, Jiantao Dong, Chao Huang, Rui Zhang, Ruimao Shan, Ying School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China ARC Lab Tencent PCG China University of Macau China Tencent AI Lab China Shenzhen Institute of Advanced Technology China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shanghai Artificial Intelligence Laboratory China Tsinghua University China

Current instruction-based editing methods, such as InstructPix2Pix, often fail to produce satisfactory results in complex scenarios due to their dependence on the simple CLIP text encoder in diffusion models. To rectify this, this paper introduces SmartEdit, a novel approach to instruction-based image editing that leverages Multimodal Large Language Models (MLLMs) to enhance their understanding and reasoning capabilities. However, direct integration of these elements still faces challenges in situations requiring complex reasoning. To mitigate this, we propose a Bidirectional Interaction Module that enables comprehensive bidirectional information interactions between the input image and the MLLM output. During training, we initially incorporate perception data to boost the perception and understanding capabilities of diffusion models. Subsequently, we demonstrate that a small amount of complex instruction editing data can effectively stimulate SmartEdit’s editing capabilities for more complex instructions. We further construct a new evaluation dataset, Reason-Edit, specifically tailored for complex instruction-based image editing. Both quantitative and qualitative results on this evaluation dataset indicate that our SmartEdit surpasses previous methods, paving the way for the practical application of complex instruction-based image editing. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

LGDB-Net: Dual-Branch Path for Building Extraction from Remote Sensing Image

LGDB-Net: Dual-Branch Path for Building Extraction from Remo...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Ronghuan Zhang Jing Zhao Ming Li Qingzhi Zou Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China School of Intelligence and Information Engineering Shandong University of Traditional Chinese Medicine Jinan China

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Extracting buildings from remote sensing images using deep learning techniques is a widely applied and crucial task. Convolutional Neural Networks (CNNs) adopt hierarchical feature representation, showcasing powerful capabilities in extracting local information but facing challenges in capturing global features. Transformers can address this limitation, but they perform poorly in extracting local features and significantly increase memory requirements and computational complexity. To overcome these challenges, we propose a method for building extraction from remote sensing images called LGDB-Net (Local-Global Dual-Branch Network), employing a dual-branch approach. Firstly, inspired by Swin Transformer, we designed GB-Former(Global Branch-Former) as the backbone network to model global information. We use a linear multi-head self-attention mechanism to reduce time and memory complexity while maintaining a large global receptive field. Additionally, we replace the traditional multi-layer perceptron with a convolution-enhanced multi-layer perceptron to improve channel feature representation, reduce model parameters, and enhance segmentation performance. Secondly, we use multiple Depth-wise Conv3×3 + LN (Layer Normalization) + GeLU (Gaussian Error Linear Unit) modules as the auxiliary branch for local detailed feature extraction. Finally, we adopt a multi-scale feature fusion strategy to integrate feature information from both branches. We conduct a series of experiments on three datasets: WHU, Massachusetts, and Inria. The experimental results demonstrate that the proposed method not only effectively improves segmentation accuracy with lower building omission and commission rates but also significantly reduces model parameters and computational complexity.

关键词： Accuracy Computational modeling Memory management Neural networks Feature extraction Transformers Sensors data mining Computational complexity Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Deep Adaptively Feature Extracting Network for Cervical Squamous Lesion Cell Detection 4th

Deep Adaptively Feature Extracting Network for Cervical Squ...

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Peng, Zhonghua Hu, Rong Wang, Fuen Fan, Haoyi Eng, Yee Wei Li, Zuoyong Zhou, Liwei Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fujian University of Technology Fujian Fuzhou350118 China School of Computer and Artificial Intelligence Zhengzhou University Henan Zhengzhou450001 China School of Computer Sciences Universiti Sains Malaysia Penang11800 Malaysia Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fujian Fuzhou350121 China Department of Nutrition The First Affiliated Hospital of Zhengzhou University Henan Zhengzhou450052 China

ISBN: (纸本)9783031200984

Cervical cancer is one of the most widespread malignancies affecting women’s health worldwide today. However, the task of detection is particularly difficult due to the complex background of the cervical smear, where cells are previously stacked in clusters. To address this problem, we utilize the YOLOv5 as the baseline and build on YOLOv5 by using the simple Transformer Block which only combines with multi-head self attention layers and MLP to better extract cell features as well as to obtain global information. In addition, we allow the model to refine features adaptively to assist with detection by using Convolutional Block Attention Module (CBAM), an attention module being simple and effective for feed-forward convolutional neural networks, in the complex background information. Finally, we compare the model with YOLOv5 as baseline. In CDetector dataset, our model obtains 52.5% mAP@.5, which is 6% better than baseline. In transfer learning, it is 62.2%, which outperforms baseline by 3.2%. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

Gap Minimization for Knowledge Sharing and Transfer

arXiv

引用

arXiv 2022年

作者： Wang, Boyu Mendez, Jorge A. Shui, Changjian Zhou, Fan Wu, Di Xu, Gezheng Gagné, Christian Eaton, Eric Department of Computer Science University of Western Ontario Canada Computer Science & Artificial Intelligence Laboratory Massachusetts Institute of Technology United States Institute Intelligence and Data Université Laval Canada School of Transportation Science and Engineering Beihang University China Department of Electrical and Computer Engineering McGill University Canada Department of Computer and Information Science University of Pennsylvania United States

Learning from multiple related tasks by knowledge sharing and transfer has become increasingly relevant over the last two decades. In order to successfully transfer information from one task to another, it is critical to understand the similarities and differences between the domains. In this paper, we introduce the notion of performance gap, an intuitive and novel measure of the distance between learning tasks. Unlike existing measures which are used as tools to bound the difference of expected risks between tasks (e.g., H-divergence or discrepancy distance), we theoretically show that the performance gap can be viewed as a data- and algorithm-dependent regularizer, which controls the model complexity and leads to finer guarantees. More importantly, it also provides new insights and motivates a novel principle for designing strategies for knowledge sharing and transfer: gap minimization. We instantiate this principle with two algorithms: 1. gapBoost, a novel and principled boosting algorithm that explicitly minimizes the performance gap between source and target domains for transfer learning;and 2. gapMTNN, a representation learning algorithm that reformulates gap minimization as semantic conditional matching for multitask learning. Our extensive evaluation on both transfer learning and multitask learning benchmark data sets shows that our methods outperform existing baselines. © 2022, CC0.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

ICT: Iterative Clustering with Training: Preliminary Results

ICT: Iterative Clustering with Training: Preliminary Results

引用

International Conference on New Trends in Computing sciences (ICTCS)

作者： Ahmad B. Hassanat Ahmad S. Tarawneh Ahmad S. Alhasanat Mansoor Alghamdi Khalid Almohammadi Zakaria Tarawneh Dept. Computer Science Faculty of Information Technology Mutah University Karak Jordan Dept. Data Science and Artificial Intelligence Mutah University Karak Jordan School of Foundation Studies and Mathematics Oryx Universal College Doha Qatar Dept of Mathematics Al-Hussein Bin Talal University Maan Jordan Dept. of Computer Science Applied College University of Tabuk Tabuk Saudi Arabia CiTIUS Universidade de Santiago de Compostela (USC) Spain

ISBN: (数字)9798331523411

ISBN: (纸本)9798331523428

We introduce Iterative Clustering with Training (ICT), a hybrid approach that combines clustering with iterative classifier-based refinement. Unlike traditional clustering methods, ICT leverages supervised learning to reassign ambiguous boundary points, improving cluster quality. The proposed approach starts with an initial clustering phase, followed by the computation of silhouette scores to separate high-confidence core points from uncertain boundary points. A classifier (e.g., Random Forest) is then trained on core points to predict labels for boundary points, refining clusters in an iterative process until convergence is achieved. To avoid trivial clusters, minimum cluster ratio constraints are implemented. Experimental results on multiple benchmark datasets show that ICT outperforms traditional clustering methods such as k-means, HDBSCAN, and spectral clustering across several evaluation metrics, such as Adjusted Rand Index, Normalized Mutual Information, and Accuracy. ICT particularly excels at handling clusters that overlap, have noise, and complex geometries, where standard methods often fail. Key advantages include adaptive core selection, iterative refinement, and classifier flexibility, making ICT suitable for applications in customer segmentation, anomaly detection, and biological data analysis.

关键词： Training Measurement Clustering methods Roads Refining Supervised learning Semisupervised learning Iterative methods Standards Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Study of the splicing/coupling influence of cabling to fibers test links measurements

引用

Journal of Optical Communications 2024年第0期45卷 s1369-s1381页

作者： Rashed, Ahmed Nabih Zaki Babu, Gade Harish Nagendram, Sanam Anwer, Twana Mohammed Kak Ahammad, Shaik Hasane Hossain, Md. Amzad Ibrahim, Anas Electronics and Electrical Communications Engineering Department Faculty of Electronic Engineering Menoufia University Menouf32951 Egypt Department of VLSI Microelectronics Institute of Electronics and Communication Engineering Saveetha School of Engineering SIMATS Tamilnadu Chennai602105 India Department of ECE CVR College of Engineering Hyderabad India Department of Artificial Intelligence KKR & KSR Institute of Technology and Sciences Guntur India Department of Physics College of Education Salahaddin University-Erbil Kurdistan Region Erbil44002 Iraq Department of ECE Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522302 India Faculty of Electrical Engineering and Information Technology Institute of Theoretical Electrical Engineering Ruhr University Bochum Bochum44801 Germany Department of Electrical and Electronic Engineering Jashore University of Science and Technology Jashore7408 Bangladesh

This article has analyzed the splicing and coupling influence of cabling to fibers test links measurements. The simulative study for different free/forced vibration mechanics in MEMS is performed. Relative amplitude frequency plot for a cantilever beam, a double clamped beam (DCB), a cantilever beam with end mass, normal vibration of a clamped beam mass, a double clamped beam with axial force, normal vibration of a clamped beam mass are demonstrated by using MEMSolver simulation version 3.3. The frequency shift for DCB with axial force is clarified. The lowest modal frequencies of a square and round diaphragm are also reported. The lowest modal frequency of a bent beam suspension is simulated also. The dependence of mid-section of the folded beam on the resonance frequency and on the short leg of the serpentine beam are clarified. The displacement plot for a structure under free vibration with damping, the displacement plot for vibration under a step force with damping, amplitude frequency plot for vibration under harmonic force with damping and amplitude frequency plot for the vibration driven by the base excitation are also outlined in this work. © 2023 Walter de Gruyter GmbH, Berlin/Boston.

关键词： Natural frequencies

来源：评论

学校读者我要写书评

暂无评论

Software Product Quality Models, Developments, Trends, and Evaluation

引用

SN Computer science 2020年第3期1卷 1-24页

作者： Galli, Tamas Chiclana, Francisco Siewe, Francois Institute of Artificial Intelligence (IAI) Faculty of Computing Engineering and Media De Montfort University Leicester United Kingdom Andalusian Research Institute on Data Science and Computational Intelligence (DaSCI) University of Granada Granada Spain Software Technology Research Laboratory (STRL) Faculty of Computing Engineering and Media De Montfort University Leicester United Kingdom

Software product quality models have evolved in their abilities to capture and describe the abstract notion of software quality since the 1970s. Many models constructed deal with a specific part of software quality only which makes them ineligible to assess the quality of software products as a whole. Former publications failed to thoroughly examine and list all the available models which attempt to describe each known property of software product quality. This paper discovers such complete software product quality models published since 2000;moreover, it endeavours to measure the relevance of each model quantitatively by introducing indicators with regard to the scientific and industrial community. The identified 23 software product quality model classes differ significantly in terms of publication intensity, publication range, quality score average, relevance score and the 12-month average of the Google Relative Search Index. The results offer a foundation for selecting the appropriate software product quality model for use or for extension if newly identified quality properties need to be connected to a general context. Furthermore, the experiences accumulated on the field of software product quality modelling motivated researchers to successfully transfer the concepts to other areas where abstract entities need to be compared or assessed including the quality of higher educational teaching and business processes, which is also briefly highlighted in the paper. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Execution tracing Quality assessment software engineering Software product quality model

来源：评论

学校读者我要写书评

暂无评论

Semantic Feature Division Multiple Access for Digital Semantic Multiple Access Channels

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Shen, Bin Ma, Shuai Chen, Rui Wu, Youlong Li, Hang Shi, Guangming Li, Shiyin Al-Dhahir, Naofal China University of Mining and Technology School of Information and Control Engineering Xuzhou221116 China Xidian University State Key Laboratory of Integrated Service Networks School of Telecommunications Engineering Shaanxi Xi'an710071 China ShanghaiTech University School of Information Science and Technology Shanghai201210 China Shenzhen Research Institute of Big Data Guangdong Shenzhen518172 China Xidian University School of Artificial Intelligence Shaanxi Xi'an710071 China Peng cheng Laboratory Shenzhen518066 China The University of Texas at Dallas Department of Electrical and Computer Engineering RichardsonTX75080 United States

To solve the multi-user semantic communication network capacity bottlenecks, this paper proposes a semantic feature domain multiple access (SFDMA) scheme. By extracting and encoding semantic features and jointly processing multi-user data, the scheme can realize the encoding and transmission of multi-user semantic information in the separated feature subspace. Based on this scheme, a semantic digital multiple access network model is proposed to perform multi-user inference tasks, and an efficient semantic encoding and decoding scheme is developed by using variational information bottleneck (VIB) theory to ensure both the orthogonality in the feature domain and the classification accuracy. Furthermore, a SFDMA model for image reconstruction is designed based on the Swin Transformer. The modified model also considers the reconstruction quality and orthogonality of semantic feature domain. In addition, we design an optimization target for multiple access to implement an adaptive power allocation method for multi-user semantic communications. Simulation results show that our proposed SFDMA scheme exhibits semantic feature domain orthogonality in different applications, and the adaptive power allocation method shows excellent performance in the classification task, and effectively guarantee the quality of service (QoS) of the semantic communications. © 2015 IEEE.

关键词： Image reconstruction

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：