检索结果-内蒙古大学图书馆

HistoMSC: Density and topology analysis for AI-based visual annotation of histopathology whole slide images

Computers in Biology and Medicine 2025年 190卷 109991-109991页

作者： Ahmad, Zahoor Al-Thelaya, Khaled Alzubaidi, Mahmood Joad, Faaiz Gilal, Nauman Ullah Mifsud, William Boughorbel, Sabri Pintore, Giovanni Gobbetti, Enrico Schneider, Jens Agus, Marco Division of Information and Computing Technology College of Science and Engineering Hamad Bin Khalifa University Qatar Foundation Doha Qatar Kite Pharma Santa MonicaCA United States Visual and Data-intensive Computing CRS4 Italy Qatar Computing Research Institute Hamad Bin Khalifa University Qatar Foundation Doha Qatar

We introduce an end-to-end framework for the automated visual annotation of histopathology whole slide images. Our method integrates deep learning models to achieve precise localization and classification of cell nuclei with spatial data aggregation to extend classes of sparsely distributed nuclei across the entire slide. We introduce a novel and cost-effective approach to localization, leveraging a U-Net architecture and a ResNet-50 backbone. The performance is boosted through color normalization techniques, helping achieve robustness under color variations resulting from diverse scanners and staining reagents. The framework is complemented by a YOLO detection architecture, augmented with generative methods. For classification, we use context patches around each nucleus, fed to various deep architectures. Sparse nuclei-level annotations are then aggregated using kernel density estimation, followed by color-coding and isocontouring. This reduces visual clutter and provides per-pixel probabilities with respect to pathology taxonomies. Finally, we use Morse–Smale theory to generate abstract annotations, highlighting extrema in the density functions and potential spatial interactions in the form of abstract graphs. Thus, our visualization allows for exploration at scales ranging from individual nuclei to the macro-scale. We tested the effectiveness of our framework in an assessment by six pathologists using various neoplastic cases. Our results demonstrate the robustness and usefulness of the proposed framework in aiding histopathologists in their analysis and interpretation of whole slide images. © 2025 The Authors

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

An Enhanced CNN Model for Motor Imagery-Based Brain Computer Interface

An Enhanced CNN Model for Motor Imagery-Based Brain Computer...

引用

International Conference on Computational Intelligence and Knowledge Economy (ICCIKE)

作者： Balasubramanian Prabhu Kavin Jeeva Selvaraj Velliangiri Sarveshwaran Prakash B Department of Data Science and Business Systems SRM Institute of Science and Technology Tamilnadu India Department of Computational Intelligence SRM Institute of Science and Technology Tamilnadu India Department of Computing Technologies SRM Institute of Science and Technology Chennai India

An essential Brain-Computer Interface (BCI) paradigm, Motor Imagery (MI) based BCI calls for robust classifiers. In recent years, deep learning technology has been widely adopted, and numerous attempts have been made to apply it to the field of BCI. As much progress has been made in improving the accuracy of deep learning-based MI-BCI systems in comparison to more conventional methods, there is still a significant challenge in accurately interpreting the deep learning models. This study offers an Optimized Complex Structure based 1-D Convolutional Neural Network (OCS-1D-CNN) model for automatic detection using MI image classification to overcome these concerns. Enhancing its properties for distinguishing normal conditions and other levels, 2D maps can be turned into feature signals using two-round 1D convolutional procedures in the layer. Gray Relational Analysis (GRA) investigation classifiers are used to screen the different layers in the classification layer due to their simple mathematical operation. The Artificial Jellyfish Search Algorithm (AJSO) finds the best combination of summation layer weight and GRA weight. Using two big, publicly available databases containing data on 42 and 62 people, the suggested model is put through its paces. Based on the findings, the models outperformed conventional methods.

关键词： Deep learning Biological system modeling Computational modeling Imaging Brain modeling Nonhomogeneous media Mathematical models

来源：评论

学校读者我要写书评

暂无评论

LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition

arXiv

引用

arXiv 2024年

作者： Hu, Youbing Cheng, Yun Lu, Anqi Cao, Zhiqiang Wei, Dawei Liu, Jie Li, Zhijun AIoT Lab. Faculty of Computing Harbin Institute of Technology China Swiss Data Science Center Zurich Switzerland School of Cyber Engineering Xidian University China

The Vision Transformer (ViT) excels in accuracy when handling high-resolution images, yet it confronts the challenge of significant spatial redundancy, leading to increased computational and memory requirements. To address this, we present the Localization and Focus Vision Transformer (LF-ViT). This model operates by strategically curtailing computational demands without impinging on performance. In the Localization phase, a reduced-resolution image is processed;if a definitive prediction remains elusive, our pioneering Neighborhood Global Class Attention (NGCA) mechanism is triggered, effectively identifying and spotlighting class-discriminative regions based on initial findings. Subsequently, in the Focus phase, this designated region is used from the original image to enhance recognition. Uniquely, LF-ViT employs consistent parameters across both phases, ensuring seamless end-to-end optimization. Our empirical tests affirm LF-ViT’s prowess: it remarkably decreases Deit-S’s FLOPs by 63% and concurrently amplifies throughput twofold. Code of this project is at https://***/edgeai1/***. Copyright © 2024, The Authors. All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection System in Industrial Cyber-Physical System Using Clustered Federated Learning

引用

SN Computer science 2023年第5期4卷 452页

作者： Jayagopal, Vellingiri Elangovan, Mohanraj Singaram, Saranya Sathasivam Shanmugam, Kavitha Bharathi Subramaniam, Balu Bhukya, Srinivasarao School of Information Technology and Engineering Vellore Institute of Technology Tamil Nadu Vellore 632014 India Department of Artificial Intelligence and Data Science K.S.Rangasamy College of Technology Tamil Nadu Tiruchengode 637215 India Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur Campus Tamil Nadu Chennai 603203 India Department of Computer Technology Kongu Engineering College Tamil Nadu Perundurai Erode 638060 India Department of Computer Science and Engineering Vivekanandha College of Engineering for Women Tamil Nadu Tiruchengode Namakkal 637205 India Department of Computer Science and Engineering Koneru Lakshmayya Education Foundation Andhra Pradesh Vaddeswaram 520002 India

The quick convergence in the industrial infrastructure with computing and networking has proliferated the attacks of industry-based Cyber-Physical Systems (CPS). Protecting such massive, sophisticated, and varied industrial CPSs from cyber-attacks is difficult. This research proposed a novel Clustered Federated Learning (CFL) technique that identifies cyber-attacks against industrial CPSs. A CFL architecture enables many industrial CPS to create an extensive model for maintaining privacy. The contribution of the research is to identify the intrusion in the CPS using CFL that is highly effective in terms of accuracy, error rate, and MCC. CFL is a Federated Multi-Task Learning (FMTL) paradigm that groups the attacks into clusters with simultaneously trainable data distributions by taking advantage of geometric features of the Federated Learning (FL) loss surface. Extensive tests on an industrial CPS dataset show their proposed CFL technique's high efficacy in identifying cyber-attacks on industrial CPSs and its advantages over cutting-edge solutions. Experiments are conducted on gas pipelining system-based datasets. In this research study, the data resource is split into two main categories: training is 80%, and testing is 20%. The proposed CFL method is effective by attaining the highest accuracy of 99.3%, the minimal error rate of 86%, and the highest Mathews Coefficient Correlation (MCC) of 0.7994 for communication round 10. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Blockchain Industry 4 Learning Privacy Security Smart objects

来源：评论

学校读者我要写书评

暂无评论

Design and Development of an IoT Based Smart Irrigation System to Enhance Agricultural Productivity Using ESP8266 Wi-Fi Enabled Controller 5

Design and Development of an IoT Based Smart Irrigation Syst...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Parashar, Vivek Singh, Megha Senthamarai, M. Poonkuzhali, P. Vadar, Parashuram Shankar Swapna, B. School of Computing Science and Engineering Vit Bhopal University Bhopal India Oriental University Department of Computer Science and Engineering Indore India Nandha Engineering College Department of Artificial Intelligence and Data Science Tamilnadu Erode India R.M.D. Engineering College Department of Ece Kavaraipettai India Yashwantrao Chavan School of Rural Development Shivaji University Maharashtra Kolhapur India Dr Mgr Educational and Research Institute Chennai India

ISBN: (纸本)9798350379945

Innovative solutions in many fields, including agriculture, have been made possible by the widespread use of Internet of Things (IoT) technology. Our goal in this research was to increase crop yields by developing a smart irrigation system that would use the IoT. An ESP8266 Wi-Fi-enabled controller serves as the center of the system, collecting data and making decisions all at once. Important parts include sensors for soil moisture, air temperature and humidity, light intensity, water level, a pump to move water, and the ability to connect to a cloud service for data storage and analysis. Water level, soil moisture, temperature, humidity, and light intensity are some of the environmental characteristics that must be continuously monitored in order for the system to function. The data is sent to the main controller in real-time by the sensors using Wi-Fi. Based on predefined thresholds and algorithms, the system dynamically adjusts irrigation schedules to optimize water usage and enhance crop growth. To evaluate the system's performance, sensor readings from multiple trials were analyzed. Results indicate that the system effectively maintains optimal environmental conditions for plant growth, leading to improved agricultural productivity. The integration with a cloud platform enables remote monitoring and control, facilitating efficient water resource management and decision-making for farmers. © 2024 IEEE.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler

arXiv

引用

arXiv 2024年

作者： Peng, Hongyi Yu, Han Tang, Xiaoli Li, Xiaoxiao College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Computer Engineering The University of British Columbia VancouverBC Canada Vector Institute Canada

Federated learning (FL) enables collaborative machine learning across distributed data owners. However, this approach poses a significant challenge for model calibration due to data heterogeneity. While prior work focused on improving accuracy for non-iid data, calibration remains under-explored. This study reveals existing FL aggregation approaches lead to sub-optimal calibration, and theoretical analysis shows despite constraining variance in clients’ label distributions, global calibration error is still asymptotically lower bounded. To address this, we propose a novel Federated Calibration (FedCal) approach, emphasizing both local and global calibration. It leverages client-specific scalers for local calibration to effectively correct output misalignment without sacrificing prediction accuracy. These scalers are then aggregated via weight averaging to generate a global scaler, minimizing the global calibration error. Extensive experiments demonstrate that FedCal significantly outperforms the best-performing baseline, reducing global calibration error by 47.66% on average. Copyright © 2024, The Authors. All rights reserved.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Defeasible-PROV: Conflict Resolution in Smart Building Devices

Defeasible-PROV: Conflict Resolution in Smart Building Devic...

引用

IEEE Annual International Computer Software and Applications Conference (COMPSAC)

作者： Abdullah Al Farooq Zac Taylor Kyle Ruona Thomas Moyer School of Computing and Data Science Wentworth Institute of Technology Boston MA Department of Software and Information System The University of North Carolina Charlotte

Programmable Logic Controllers (PLCs) are an integral component for managing automation processes of smart buildings. PLCs use protocols which make these control systems vulnerable to many common attacks due to which it is possible to create conflicts on certain devices of smart buildings thereby disrupting functionality. In this paper, we propose DEFEASIBLE-PROV, a system for resolving conflicts in the system by detecting the conflict creating sensors and conflict impacted actuators. Our tool is capable of blocking conflict creating rules in the system. Our evaluation results show that our proposed methodology contributes significantly to conflict resolution in the system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the physics of nested Markov models: a generalized probabilistic theory perspective

arXiv

引用

arXiv 2024年

作者： Zhang, Xingjian Wang, Yuhao QICI Quantum Information and Computation Initiative School of Computing and Data Science University of Hong Kong Hong Kong Institute for Interdisciplinary Information Sciences Tsinghua University China

Determining potential probability distributions with a given causal graph is vital for causality studies. To bypass the difficulty in characterizing latent variables in a Bayesian network, the nested Markov model provides an elegant algebraic approach by listing exactly all the equality constraints on the observed variables. However, this algebraically motivated causal model comprises distributions outside Bayesian networks, and its physical interpretation remains vague. In this work, we inspect the nested Markov model through the lens of generalized probabilistic theory, an axiomatic framework to describe general physical theories. We prove that all the equality constraints defining the nested Markov model hold valid theory-independently. Yet, we show this model generally contains distributions not implementable even within such relaxed physical theories subjected to merely the relativity principles and mild probabilistic rules. To interpret the origin of such a gap, we establish a new causal model that defines valid distributions as projected from a high-dimensional Bell-type causal structure. The new model unveils inequality constraints induced by relativity principles, or equivalently high-dimensional conditional independences, which are absent in the nested Markov model. Nevertheless, we also notice that the restrictions on states and measurements introduced by the generalized probabilistic theory framework can pose additional inequality constraints beyond the new causal model. As a by-product, we discover a new causal structure exhibiting strict gaps between the distribution sets of a Bayesian network, generalized probabilistic theories, and the nested Markov model. We anticipate our results will enlighten further explorations on the unification of algebraic and physical perspectives of causality. © 2024, CC BY.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Improving VTE Identification through Language Models from Radiology Reports: A Comparative Study of Mamba, Phi-3 Mini, and BERT

Improving VTE Identification through Language Models from Ra...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jamie Deng Yusen Wu Yelena Yesha Phuong Nguyen Department of Computer Science University of Miami Miami FL USA Frost Institute for Data Science & Computing University of Miami Miami FL USA Department of Radiology University of Miami Miami FL USA

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Venous thromboembolism (VTE) is a critical cardio-vascular condition, encompassing deep vein thrombosis (DVT) and pulmonary embolism (PE). Accurate and timely identification of VTE is essential for effective medical care. This study builds upon our previous work, which addressed VTE detection using deep learning methods for DVT and a hybrid approach combining deep learning and rule-based classification for PE. Our earlier approaches, while effective, had two major limitations: they were complex and required expert involvement for feature engineering of the rule set. To overcome these challenges, we utilize the Mamba architecture-based classifier. This model achieves remarkable results, with a 97% accuracy and F1 score on the DVT dataset and a 98% accuracy and F1 score on the PE dataset. In contrast to the previous hybrid method on PE identification, the Mamba classifier eliminates the need for hand-engineered rules, significantly reducing model complexity while maintaining comparable performance. Additionally, we evaluated a lightweight Large Language Model (LLM), Phi-3 Mini, in detecting VTE. While this model delivers competitive results, outperforming the baseline BERT models, it proves to be computationally intensive due to its larger parameter set. Our evaluation shows that the Mamba-based model demonstrates superior performance and efficiency in VTE identification, offering an effective solution to the limitations of previous approaches.

关键词： Deep learning Training Accuracy Computational modeling Biological system modeling Computer architecture Feature extraction Complexity theory Thrombosis Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

MORE: Multi-mOdal REtrieval Augmented Generative Commonsense Reasoning

arXiv

引用

arXiv 2024年

作者： Cui, Wanqing Bi, Keping Guo, Jiafeng Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Since commonsense information has been recorded significantly less frequently than its existence, language models pre-trained by text generation have difficulty to learn sufficient commonsense knowledge. Several studies have leveraged text retrieval to augment the models' commonsense ability. Unlike text, images capture commonsense information inherently but little effort has been paid to effectively utilize them. In this work, we propose a novel Multi-mOdal REtrieval (MORE) augmentation framework, to leverage both text and images to enhance the commonsense ability of language models. Extensive experiments on the Common-Gen task have demonstrated the efficacy of MORE based on the pre-trained models of both single and multiple modalities. © 2024, CC BY-NC-SA.

关键词： Computational linguistics

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：