检索结果-内蒙古大学图书馆

An Enhanced Approach to Intelligent computer-Assisted Localization of Liver Tumor on Computed Tomography Images

SN computer science 2024年第7期5卷 1-10页

作者： Arakeri, Megha Lakshmana Reddy, Raghavendra Ravishankar, H. Deepa, K.R. Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Karnataka Manipal India Seamovations Labs Pvt Ltd Karnataka Bengaluru India School of Computer Science and Engineering REVA University Karnataka Bengaluru India School of Computer Science and Information Technology REVA University Karnataka Bengaluru India School of Electrical and Electronics Engineering REVA University Karnataka Bengaluru India

Computed Tomography (CT) Imaging is frequently used to find liver cancer. CT imaging of the liver generates cross-sectional images of the abdominal region. The task of segmenting a liver tumor on CT images is tedious due to the anatomic complexity of the liver. Therefore, liver tumor detection has been performed manually or semi-automatically which is an exhaustive process. Further, a tumor may be present on only some slices of the CT scan and hence there is a need to automatically identify images that contain tumors from acquired CT images and then locate a region of the tumor on those images for further diagnosis. Automatic detection helps the radiologist to obtain fast, accurate, and effective results. Accordingly, in this paper, an enhanced approach is proposed based on deep learning, efficient fuzzy c-means (EFCM) clustering, and a region-based algorithm for the detection of a liver tumor. A deep learning model built on a convolutional neural network is used to identify whether the CT image contains a tumor. If it contains the tumor, then the proposed EFCM and region-based algorithms are applied to locate the tumor on the CT image. The EFCM algorithm is combined with a region-based technique to automatically determine the initial pixel and threshold values required to segment the liver tumor. The proposed method is applied to several CT abdominal images. The results of the tumor segmentation are validated by comparing them with the tumor regions detected by radiologists. The estimated results of the experiment show that the proposed technique successfully detects the liver tumor on the CT image with less than 2% relative error. © The Author(s) 2024.

关键词： Computed tomography computer-aided detection Healthcare Liver tumor Medical image Segmentation

来源：评论

学校读者我要写书评

暂无评论

FedIERF: Federated Incremental Extremely Random Forest for Wearable Health Monitoring

引用

Journal of computer science & technology 2023年第5期38卷 970-984页

作者：胡春雨忽丽莎袁林陆佃杰吕蕾陈益强 Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center(National Supercomputer Center in Jinan)Qilu University of Technology(Shandong Academy of Sciences)Jinan 250353China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer ScienceJinan 250000China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan 25000China Institute of Information Technology Hebei University of Economics and BusinessShijiazhuang 050061China School of Information Science and Engineering Shandong Normal UniversityJinan 250358China Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China

Wearable health monitoring is a crucial technical tool that offers early warning for chronic diseases due to its superior portability and low power ***,most wearable health data is distributed across dfferent organizations,such as hospitals,research institutes,and companies,and can only be accessed by the owners of the data in compliance with data privacy *** first challenge addressed in this paper is communicating in a privacy-preserving manner among different *** second technical challenge is handling the dynamic expansion of the federation without model *** address the first challenge,we propose a horizontal federated learning method called Federated Extremely Random Forest(FedERF).Its contribution-based splitting score computing mechanism significantly mitigates the impact of privacy protection constraints on model *** on FedERF,we present a federated incremental learning method called Federated Incremental Extremely Random Forest(FedIERF)to address the second technical *** introduces a hardness-driven weighting mechanism and an importance-based updating scheme to update the existing federated model *** experiments show that FedERF achieves comparable performance with non-federated methods,and FedIERF effectively addresses the dynamic expansion of the *** opens up opportunities for cooperation between different organizations in wearable health monitoring.

关键词： federated learning incremental learning random forest wearable health monitoring

来源：评论

学校读者我要写书评

暂无评论

Rethinking Guidance Information to Utilize Unlabeled Samples: A Label Encoding Perspective 41

Rethinking Guidance Information to Utilize Unlabeled Samples...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhang, Yulong Yao, Yuan Chen, Shuhao Jin, Pengrong Zhang, Yu Jin, Jian Lu, Jiangang Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China College of Control Science and Engineering Zhejiang University Hangzhou China Beijing Teleinfo Technology Company Ltd. China Academy of Information and Communications Technology Beijing China Research Institute of Industrial Internet of Things China Academy of Information and Communications Technology Beijing China

Empirical Risk Minimization (ERM) is fragile in scenarios with insufficient labeled samples.A vanilla extension of ERM to unlabeled samples is Entropy Minimization (EntMin), which employs the soft-labels of unlabeled samples to guide their ***, EntMin emphasizes prediction discriminability while neglecting prediction *** alleviate this issue, in this paper, we rethink the guidance information to utilize unlabeled *** analyzing the learning objective of ERM, we find that the guidance information for labeled samples in a specific category is the corresponding label *** by this finding, we propose a Label-Encoding Risk Minimization (LERM).It first estimates the label encodings through prediction means of unlabeled samples and then aligns them with their corresponding ground-truth label *** a result, the LERM ensures both prediction discriminability and diversity, and it can be integrated into existing methods as a ***, we analyze the relationships between LERM and ERM as well as ***, we verify the superiority of the LERM under several label insufficient *** codes are available at https://***/zhangyl660/LERM. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Particle Swarm Optimization based Detection of Diabetic Retinopathy using a Novel Deep CNN 3

Particle Swarm Optimization based Detection of Diabetic Reti...

引用

3rd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2023

作者： Revathi, B. Elizabeth, S.K.Kezial Nagaraj, P. Birunda, S.Selva Nithya, D. Ramco Institute of Technology Department of Artificial Intelligence and Data Science Virudhunagar India Mangayarkarasi College of Engineering Department of Computer Science and Engineering Madurai India Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Virudhunagar India Theni Kammavar Sangam College of Technology Department of Computer Science and Engineering Theni India

ISBN: (纸本)9781665462167

Diabetic Retinopathy (DR) is a disease. Diabetic patients are mostly affected by this disease. This causes damage to the eyes. Most probably the disease affects both the back of the eye and the blood vessels of the light-sensitive. Initially, this DR disease causes only minor problems with vision. But eventually, the eyesight will go away. This condition may occur in any diabetic patient. When the disease is more affected, the blood sugar level is high. DR detection is the application of image processing to medical examinations. To diagnose DR the retinal images should be evaluated. However, it takes a lot of time and resources to physically assess the images so that the severity of the DR can be removed. The blood vessels in the retina are damaged due to this problem can be noticed. When it starts to bleed the small vessels, then it forms a way on the retina. To overcome the challenges of DR, CNN with PSO is introduced. There are different stages implicated in the diabetic retinopathy detection technique. They are pre-processing, optimization and classification. The main objective of the proposed work is to use the CNN algorithm to analyze the disease that seems to be most affected and classify and report only that area from the given input. PSO is used to optimize the given classified images, and then finally PSO with CNN technique will produce accurate results. © 2023 IEEE.

关键词： Blood vessels

来源：评论

学校读者我要写书评

暂无评论

Detection of Melanoma Insitu Using Trained CNN Model

引用

SN computer science 2024年第8期5卷 1-13页

作者： SethuMadhavi, R. Premkumar, Anitha Satheesha, T.Y. Bhasker, B. DharmaTheja, M. Asha, P.N. School of Computer Science Engineering REVA University Bengaluru 560064 India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education (MAHE) Karnataka Bangalore 560064 India School of Science and Technology Department of Engineering University of London London United Kingdom School of Computing and Information Technology REVA University Bengaluru 560064 India Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R & amp D Institute of Science and Technology Chennai India

Being the most deadly kind of skin cancer, melanoma presents a serious risk to life and is increasingly prevalent, particularly among men. It is characterized by aggressive cell multiplication that can spread within the body if left untreated, making early detection crucial for successful treatment. While machine learning techniques have been used for melanoma diagnosis, they often have limitations in performance. To address this, we propose an advanced deep learning framework incorporating a novel hybrid architecture that combines Convolutional Neural Networks (CNNs) with attention mechanisms. This framework also incorporates advanced techniques for model interpretability, such as visualizing the areas of the image that the model focuses on for its decision-making, to enhance transparency and trustworthiness for medical professionals and leverages transfer learning with pre-trained networks to boost performance. We utilized a range of optimization techniques, including AdaBelief and dynamic learning rates, to enhance model training. Our evaluation metrics included accuracy, sensitivity, specificity, and precision. Comparative results demonstrated that our model outperformed traditional techniques, with the ResNet50 architecture combined with the Adam optimizer achieving an accuracy of 92%, sensitivity of 90%, and specificity of 94%. These findings demonstrate the efficacy of our deep learning strategy by showing a notable improvement in melanoma detection performance. It is imperative to underscore that actual clinical trials or pilot studies are required to validate the model's effectiveness and reliability in real-world scenarios. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Cancer detection Convolutional Neural Network (CNN) Deep learning Dermatology Melanoma Skin cancer detection Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent Monitoring System for Automatic Air Conditioning System 5

Intelligent Monitoring System for Automatic Air Conditioning...

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Manikandan, P. Swedheetha, C. Ram Mohan, R.L. Kumar, Sandala Likith Reddy, Peram Damodar Sri Sai, Pachabotla Adithya Kalasalingam Academy of Research and Education Department of Electronics and Communication Engineering Krishnankoil India Velammal College of Engineering and Technology Department of Computer Science and Engineering Madurai India

ISBN: (纸本)9798331518097

In order to improve indoor air quality, optimize energy consumption and avoid the accidents due to gas leakage, this paper proposes an intelligent air conditioning system that integrates several sensors such as DHT11, PIR sensors, MG6 Gas sensor and PMS7003 sensor and control mechanisms. An Arduino Mega, the system's central component, synchronizes data from several sensors to efficiently control the air conditioner and other linked equipment. This system keeps track of how many people enter and leave the space, enabling the air conditioning system to modify its settings in real time according to occupancy. When the room is empty, this feature saves energy. If gas leakage is present, system notifies users through a buzzer and turn off the AC. Many users often forget to clean their AC filters regularly, which can lead to reduced efficiency, higher energy consumption, and poorer air quality. Our innovative AC system addresses this common issue. Once the dust level crosses a predefined threshold, the system triggers a clean filter alert, reminding to act before it affects performance. Also, the air conditioner kicks on to cool the room if the outside temperature is high and the inside temperature is higher than an acceptable level. In contrast, the air conditioner is shut off to avoid needless cooling if the inside temperature is low. A display unit shows temperature, humidity, occupancy, gas levels, and dust concentration. This integrated technique automatically modifies the system's operation based on conditions, ensuring not only a more hygienic and comfortable environment but also improved energy efficiency © 2024 IEEE.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

A Neural Architecture Search Method with Multi-Dimensional Correlation Representation for Fault Diagnosis 9

A Neural Architecture Search Method with Multi-Dimensional C...

引用

9th IEEE Smart World Congress, SWC 2023

作者： Liu, Yumeng Wang, Tingqi Zheng, Xu Tian, Ling Wang, Hongan Institute of Software Chinese Academy of Sciences Beijing Key Laboratory of Human-Computer Interaction Beijing China University of Chinese Academy of Sciences School of Computer Science and Technology Beijing China University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu China

ISBN: (纸本)9798350319804

As deep learning has become more widely used for fault diagnosis, the shortcomings of model transferability and human model design costs are growing increasingly evident. The current work has tackled each of these two issues. Domain adaptation methods can provide transportability by mapping data to a common domain. For the consumption of manually constructed networks, Neural Architecture Search (NAS) is an intelligent solution that automatically select the ideal network structure. Unfortunately, there is little work to connect these two methodologies in fault diagnosis. Furthermore, these approaches are incapable in extracting internal correlations from instrumental signal data. In this paper, we propose a transferrable NAS fault diagnosis method, which maximizes savings in manual costs. We also integrate graph neural networks (GNN) in a stepwise manner into the NAS and domain adaptation to provide a multi-dimension correlation representation. Firstly, we structure the signal data into graph based on temporal relationships. Then, NAS designs automatically for selecting the optimal network structure and useful features. In NAS, graph encoder of GNN is used to establish internal relationships. Finally, domain adaptation provides transferability. At the same time, GNN's weights in domain adaptation help to further mine data internal associations. We tested our method on two publicly available datasets and performed comparisons. The experimental results show the proposed method has superior performance. © 2023 IEEE.

关键词： Domain Adaptation Fault Diagnosis Graph Neural Network Neural Architecture Search

来源：评论

学校读者我要写书评

暂无评论

Titanic Survivors Prediction Analysis Using Machine Learning Algorithms 1

Titanic Survivors Prediction Analysis Using Machine Learning...

引用

1st International Conference on Computational Intelligence for Security, Communication and Sustainable Development, CISCSD 2024

作者： Devamane, Shridhar B. Abhijith, B.H. Purushotham, Bhushan Ravindranath, R.C. Lakshmikantha, G.C. Udayaprasad, P.K. Global Academy of Technology Department of Computer Science and Engineering Bangalore India Global Academy of Technology Department of Artificial Intelligence and Machine Learning Bangalore India Global Academy of Technology Department of Ai and Ml Bangalore India

ISBN: (纸本)9798350365405

Machine learning algorithms are computational models that allow computers to acquire knowledge and improve performance on a task by automatically learning patterns and rules from input data provided by the user. In this work we are predicting the Titanic disaster survivors based on a particular dataset. Based on characteristics such as age, sex, ticket class, etc., we applied the Support Vector Machine, K-Nearest Neighbors, Decision Tree, and Random Forest algorithm to identify which passenger would survive. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Investigating the Utility of Data Mining for Automated Credit Scoring 15

Investigating the Utility of Data Mining for Automated Credi...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Yadav, Dhyan Garima Soni, Rudransh Anandhasilambarasan, D. Sasirekha, R. Prema, S. Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Karnataka Bangalore India Department of Computer Science Engineering Karpagam Academy of Higher Education Coimbatore641021 India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai127 India Department of Artificial Intelligence & Data Science Vishwakarma Institute of Technology Pune India

ISBN: (纸本)9798350370249

Data mining is a powerful device for automatic credit scoring. This paper will look into the application of statistics mining for automated credit score scoring by discussing its advantages and downsides. The form may even look at cutting-edge research in the location and discuss the demanding situations that information mining techniques pose while used for automatic credit score scoring. Similarly, the paper will provide pointers on how statistics mining techniques can improve the effectiveness of computerized credit score scoring. Subsequently, a precis of the paper's conclusions and implications for future studies could be supplied. © 2024 IEEE.

关键词： Conclusions Implications Improve Information Scoring

来源：评论

学校读者我要写书评

暂无评论

ISCR - Integrative Intelligent Semantically Driven Scheme for Online Course Recommendation 2

ISCR - Integrative Intelligent Semantically Driven Scheme fo...

引用

Joint 2nd International Workshop on Multilingual Semantic Web and 2nd International Workshop on Deep Learning for Question Answering and 1st International Workshop on Semantic Reasoning and Representation in IoT with CEUR-WS, MSW-DLQ-SIOT 2022

作者： Sharma, Harshal Deepak, Gerard Birla Institute of Technology and Science Pilani Vidya Vihar Rajasthan Pilani India Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

The easy access of Internet has caused an exponential increase in the availability of courses on a variety of platforms. The increasing popularity and demand of these online courses subsequently create a need for better and more efficient course recommendation systems. The development of WEB 3.0 has also added to this need as the current course recommendation systems are not semantically compliant. The system is user knowledge-centric. It uses Decision Trees to classify the dataset. The semantic similarities have been computed with the help of normalized compression distance, normalized google distance and Gini-index. The performance has been evaluated and compared with other approaches like OPCR, CRFL, CRQCA and hierarchical clustering plus Jaccard similarity. A clear observation has been made that the proposed, knowledge centric ISCR course recommendation system performs superiorly and attains an average Recall, and F-measure of 98.48. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0)

关键词： Decision trees

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：