检索结果-内蒙古大学图书馆

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 984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

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

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

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

InputJump: Augmented reality-facilitated cross-device input fusion based on spatial and semantic information

引用

虚拟现实与智能硬件（中英文） 2024年第6期6卷 502-526页

作者： Xin ZENG Xiaoyu WANG Tengxiang ZHANG Yukang YAN Yiqiang CHEN Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 101408China Goertek Inc. Bejing 261031China The Hong Kong University of Science and Technology Hong Kong 999077China Department of Computer Science Hajim School of Engineering and Applied SciencesUniversity of RochesterRochesterNY 14627US

The proliferation of computing devices requires seamless cross-device *** reality(AR)headsets can facilitate interactions with existing computers owing to their user-centered views and natural *** this study,we propose InputJump,a user-centered cross-device input fusion method that maps multi-modal cross-device inputs to interactive elements on graphical *** input jump calculates the spatial coordinates of the input target positions and the interactive elements within the coordinate system of the AR *** also extracts semantic descriptions of inputs and elements using large language models(LLMs).Two types of information from different inputs(e.g.,gaze,gesture,mouse,and keyboard)were fused to map onto an interactive *** proposed method is explained in detail and implemented on both an AR headset and a desktop *** then conducted a user study and extensive simulations to validate our proposed *** results showed that InputJump can accurately associate a fused input with the target interactive element,enabling a more natural and flexible interaction experience.

关键词： Mixed reality Spatial Semantic Large language models

来源：评论

学校读者我要写书评

暂无评论

Region-adaptive Concept Aggregation for Few-shot Visual Recognition

引用

Machine Intelligence Research 2023年第4期20卷 554-568页

作者： Mengya Han Yibing Zhan Baosheng Yu Yong Luo Han Hu Bo Du Yonggang Wen Dacheng Tao School of Computer Science National Engineering Research Center for Multimedia SoftwareWuhan UniversityWuhan430072China Hubei Luojia Laboratory Wuhan430072China School of Computer Science The University of SydneySydney2006Australia JD Explore Academy Beijing101116China School of Information and Electronics Beijing Institute of TechnologyBeijing100081China School of Computer Science and Engineering Nanyang Technological UniversitySingapore639798Singapore

Few-shot learning (FSL) aims to learn novel concepts from very limited examples. However, most FSL methods suffer from the issue of lacking robustness in concept learning. Specifically, existing FSL methods usually ignore the diversity of region contents that may contain concept-irrelevant information such as the background, which would introduce bias/noise and degrade the performance of conceptual representation learning. To address the above-mentioned issue, we propose a novel metric-based FSL method termed region-adaptive concept aggregation network or RCA-Net. Specifically, we devise a region-adaptive concept aggregator (RCA) to model the relationships of different regions and capture the conceptual information in different regions, which are then integrated in a weighted average manner to obtain the conceptual representation. Consequently, robust concept learning can be achieved by focusing more on the concept-relevant information and less on the conceptual-irrelevant information. We perform extensive experiments on three popular visual recognition benchmarks to demonstrate the superiority of RCA-Net for robust few-shot learning. In particular, on the Caltech-UCSD Birds-200-2011 (CUB200) dataset, the proposed RCA-Net significantly improves 1-shot accuracy from 74.76% to 78.03% and 5-shot accuracy from 86.84% to 89.83% compared with the most competitive counterpart.

关键词： Few-shot learning metric-based meta learning concept learning region-adaptive concept-aggregation

来源：评论

学校读者我要写书评

暂无评论

Hybrid Models for Plant Disease Detection using Transfer Learning Technique 10

Hybrid Models for Plant Disease Detection using Transfer Lea...

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Sharma, Pavan Yadav, Rakesh Kumar Rawat, Sur Singh Iftm University Department of Computer Science and Engineering Moradabad244102 India Maharishi University of Information Technology Department of Computer Science and Engineering Lucknow226013 India Jss Academy of Technical Education Department of Computer Science and Engineering Noida201301 India

ISBN: (纸本)9789380544472

Plant diseases can sometimes be so bad that there is no grain harvest at all. Consequently, there is a great need for automatic plant disease identification and diagnosis in the realm of agricultural informatics. Many approaches have been put forth to solve this problem, but deep learning is quickly winning popularity due to its outstanding results. In this study, we assess the transfer learning capabilities of deep convolutional neural networks for the diagnosis of plant leaf diseases. We also consider how well the trained model will perform when applied to the specific task identified by our own data. One of the deep learning methods, the convolutional neural network algorithm (CNN), has been successfully applied to solve computer vision issues such as image classification, object segmentation, picture analysis, etc. In our study, we apply the Densenet201, Xception, InceptionResnetv2, NasNetMobile and VGG-16, hybrid with Support vector machine (SVM) along with a transfer learning approach to recognize diseases in images of different leaves. Instead of starting the training from scratch and arbitrarily initializing the weights, we use the pre-trained networks on the large labelled dataset, ImageNet, to build the weights. The proposed method's validity is supported by experimental findings, and it effectively detects plant diseases. The suggested method significantly outperforms other cutting-edge approaches in terms of performance like (F-scores of 0.93) for VGGG16+SVM, (F-score: 0.97) for DenseNet201+SVM, (F-score: 0.87) for Xception+SVM, (F-score: 0.97) for InceptionResnetv2+SVM, and (F-score: 0.93) NasNetMobile+SVM hybrid model on the dataset of plant images. © 2023 Bharati vidyapeeth, New Delhi.

关键词： Deep neural networks

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：