检索结果-内蒙古大学图书馆

2024 Asia Pacific Conference on Innovation in technology, APCIT 2024

作者： Himasree, J. Jeevitha, P.L. Deekshitha, K. Kolisetty, Aashrita Naveen, Soumyalatha REVA University School of Computer Science & Information Technology Bangalore India Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Department of Computer Science & Engineering Manipal India

ISBN: (纸本)9798350361537

Effective communication is essential for all individuals, yet it can be particularly challenging for the deaf community, as sign language is their major means of communication. We are researching how to create a reliable and effective system that can understand sign language motions correctly without the help of a human, realizing the importance of this *** this research work we have chosen to construct our own dataset rather than depending on pre-existing ones that may be accessed online because we understand how important authenticity and relevance are. This method gives us more control over the quality of the data and guarantees that the dataset closely matches our study goals. In addition, our system can be readily expanded and recognizes a wide range of hand motions and signs, including the alphabet. We can support a broad variety of sign language expressions thanks to this versatility, which improves inclusivity and usability. Random Forest is used to encode temporal variations among motions in sign language. The system's overall accuracy and reliability are increased thanks to this methodology, which enables it to detect minute variations in hand gestures and movements. Using the Keras and OpenCV libraries in conjunction with the Python programming language, we build a strong foundation for sign language recognition. In addition to streamlining the development process, these technological tools open the system to a larger developer and research community. In alignment with the research, the proposed work achieved an accuracy of 97% with overall precision, recall and F1 score of 99%. © 2024 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Ground-Glass Lung Nodules Recognition Based on CatBoost Feature Selection and Stacking Ensemble Learning

引用

Journal of Shanghai Jiaotong University (Science) 2024年 1-10页

作者： Miao, Jun Chang, Yiru Chen, Chen Zhang, Maoxuan Liu, Yan Qi, Honggang Guo, Zhijun Xu, Qian School of Computer Science Beijing Information Science and Technology University Beijing100101 China Pathological Information Engineering Technology Center Jinan Supercomputing Technology Research Institute Jinan250100 China School of Computer Science and Technology University of the Chinese Academy of Sciences Beijing100049 China Department of Radiology Tianjin Kanghui Hospital Tianjin300385 China Department of Radiology Huabei Petroleum General Hospital Hebei Renqiu062550 China

Aimed at the issue of high feature dimensionality, excessive data redundancy, and low recognition accuracy of using single classifiers on ground-glass lung nodule recognition, a recognition method based on CatBoost feature selection and Stacking ensemble learning was proposed. First, the method uses a feature selection algorithm to filter important features and remove features with less impact, achieving the effect of data dimensionality reduction. Second, random forests classifier, decision trees, K-nearest neighbor classifier, and light gradient boosting machine were used as base classifiers, and support vector machine was used as meta classifier to fuse and construct the ensemble learning model. This measure increases the accuracy of the classification model while maintaining the diversity of the base classifiers. The experimental results show that the recognition accuracy of the proposed method reaches 94.375%. Compared to the random forest algorithm with the best performance among single classifiers, the accuracy of the proposed method is increased by 1.875%. Compared to the recent deep learning methods (ResNet+GBM+Attention and MVCSNet) on ground-glass pulmonary nodule recognition, the proposed method’s performance is also better or comparative. Experiments show that the proposed model can effectively select features and make recognition on ground-glass pulmonary nodules. © Shanghai Jiao Tong University 2024.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Evaluation of CatBoost for Diabetes Prevention in Comparison to XGBoost: To avert mortality by developing an AI model capable of predicting the onset of diabetes

Evaluation of CatBoost for Diabetes Prevention in Comparison...

引用

2024 IEEE International Conference on Electronic Systems and Intelligent Computing, ICESIC 2024

作者： Gifta Jerith, G. Jagadeesh, S. Ponmathi Jeba Kiruba, P. Mahesh, C. Anantha Babu, S. Samsudeen Shaffi, S. Hyderabad India Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Department of Computer Science and Engineering Chennai India Saveetha Engineering College Department of Computer Science and Engineering Chennai India Panimalar Engineering College Department of Information Technology Chennai India GITAM University GITAM School of Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798331522988

Diabetes is a metabolic condition defined by consistently elevated blood glucose levels. Hyperglycemia is characterized by heightened hunger, thirst, and urination. Numerous consequences may arise from untreated diabetes. Diabetic ketoacidosis, hyperosmolarity, hyperglycemia, and even mortality may occur as acute consequences. Heart disease, stroke, chronic renal failure, foot ulcers, and eye impairment are some of the worst long-term consequences. A total of 463 million individuals were found to have diabetes in 2019, according to the worldwide diabetes organisation. Assuming predictions come true, that number will soar to 700 million by 2045, up 578 million by 2030. It has modern medical applications, allowing for the rapid and precise diagnosis of illness. Thus, we may use machine learning to avert mortality by developing an AI model capable of predicting the onset of diabetes;to determine which algorithm is most suited for this task, we will compare the CatBoost and XGBoost methods. In the end, the research compared two diabetes prediction models, XGBoost and CatBoost, using a variety of health indicators from the dataset. Using a real-world dataset obtained from Kaggle, our suggested system is trained and built using Python. Performance assessment criteria such as precision, recall, F1score and accuracy measurements are used to thoroughly analyse our methods. In comparison to XGBoost's 88.33% accuracy rate, 85.25 percent precision, 85.63 percent recall, and an F1 Score of 86.50. CatBoost's 91.08% percent accuracy, 85.25 percent precision, 85.63 percent recall, and 87.38 F1 Score. CatBoost marks it as the most successful ensemble approach. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Using Blue Whale technology: An ML Edge Self-Adaptable Vehicle Slowdown Earliest Warning Information System 8th

Using Blue Whale Technology: An ML Edge Self-Adaptable Vehic...

引用

8th International Conference on Microelectronics Electromagnetics and Telecommunications, ICMEET 2023

作者： Murali, N. David, D. Beulah Research Scholar Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Tamilnadu Chennai India Department of Data Analytics Institute of Information Technology Saveetha School of Engineering SIMATS Tamilnadu Chennai India

ISBN: (纸本)9789819784219

Human life is challenged by this main work’s ultimate goal of reducing accidents and ensuring life safety due to the enormous growth of vehicles and those based on safety. Here, cases of suspected drunk driving, reckless driving, etc., are present. In this scenario, vehicles are traveling at full speed and irresponsibly using technology on all roads. An early warning system is used to stop auto accidents. In order to accommodate the city's steadily increasing automobile population, intelligent traffic systems must be designed in a resourceful and sustainable manner using all available technology in both light and dark. The advanced ML's work on unexpected traffic flow and all road conditions resulted in significant real-time changes in the flow of traffic for every significant issue that arose. Here, the Blue Whale technology makes use of clever intelligence to quickly identify, detect, and modify warning systems. The primary objective of the study was to train CNN/BWT on the collected data sets in order to operationalize the unsupervised approach for the prediction of critical situations. Additionally, it makes an effort to clarify the situation so that guests can feel more at ease and help them decide on transfers in time-sensitive situations. IOT is a practical way to locate the nearest object using machine learning methods that are accurate and apply received data sets, resulting in significant findings that support object recognition. The paperwork fully focuses on improving driving knowledge and offering new approaches for quick object recognition. The Fast Warning System Initiative, which aims to increase daytime safety and security, is providing a prior warning system. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Backward wave tubes

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

ResAT: Visual Tracking with Residual Attention 24

ResAT: Visual Tracking with Residual Attention

引用

4th International Conference on Artificial Intelligence, Automation and High Performance Computing, AIAHPC 2024

作者： Ding, Shuyan Song, Chunlin Yao, Yu Guo, Jianhui Li, Lunbo School of Electronic and Optical Engineering Nanjing University of Science and Technology China Hangzhou Zhiyuan Research Institute Co. Ltd China School of Computer Science and Engineering Nanjing University of Science and Technology China

ISBN: (纸本)9798400710049

Transformer has successfully replaced the CNN-based crosscorrelation operation on visual tracking tasks, significantly improving tracking performance. The attention mechanism, the core module of Transformer, can get rid of the long-range dependency dilemma while the CNN-based method cannot. However, the tracking performance is very susceptible to the interference from secondary background information since the global-level attention mechanism cannot concentrate on the primary target information. In our work, we propose a residual self-attention mechanism appropriate for object tracking tasks to concentrate on the primary target information. Furthermore, we design ResAT, an effective and concise tracker that adopts a residual attention mechanism and a residual strategy specifically tailored for object tracking tasks. Our tracker ResAT outperforms all previous SOTA trackers on challenging large-scale benchmarks, including GOT-10k, LaSOT, TrackingNet, and UAV123, while running at 45 FPS. © 2024 Copyright held by the owner/author(s).

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Unraveling Disease-Specific Diffusion Patterns in Human Brain Using Diffusion Tensor Image Analysis 5th

Unraveling Disease-Specific Diffusion Patterns in Human Brai...

引用

5th International Conference on Data Science, Machine Learning and Applications, ICDSMLA 2023

作者： Prajapati, Sandhya Bhagawati, Rupam Alam, Intekhab Jebakumari, S. Adlin Department of Electrical Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Navgaon Manduwala Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bangalore India

ISBN: (纸本)9789819780426

Diffusion tensor imaging (DTI) is a feasible approach to have a look at the structural connectivity of neuronal networks in vivo, as it presents insights into the microstructural and molecular properties of white depend fiber bundles. On this study, we used superior DTI and diffusion tensor image evaluation to analyze the unique diffusion patterns of several distinct diseases in human mind. We obtained statistics from healthful controls and cohorts of sufferers with a range of sicknesses, along with stroke, annoying mind injury, Alzheimer’s ailment, and Parkinson’s ailment, in addition to from postmortem brains of each wholesome and diseased people. Our findings emphasize the capability of the use of this technique to increase ailment-precise structural networks biomarkers for diagnosis and control of neurological illnesses. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Diffusion tensor imaging

来源：评论

学校读者我要写书评

暂无评论

A multimodal feature fusion model for depression diagnosis based on BiLSTM+ViT

A multimodal feature fusion model for depression diagnosis b...

引用

2024 International Conference on Image Processing and Artificial Intelligence, ICIPAl 2024

作者： Li, Muyao Xing, Yan He, Yitan Wang, Yuhe Yu, Zhouyang Wang, Xiaoyu Linghu, Pingchuan School of Mathematics Hefei University of Technology Hefei230009 China School of Management Hefei University of Technology Hefei230009 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China

ISBN: (纸本)9781510681514

A thorough diagnosis of depression, a mental illness that affects many people worldwide, must be made in light of the patient's medical background, present symptoms, and pertinent examination findings. In recent years, scholars have increasingly favored machine learning algorithms for depression diagnosis or prediction models. However, achieving higher prediction accuracy in prediction models remains challenging when relying solely on one modality. This research suggests a multi-modal feature fusion model for predicting depression tendency that is based on bi-directional LSTM and vision transformer (ViT). The model demonstrates an accuracy of 70.00%, surpassing that of single-modal depression tendency prediction models and presenting a novel approach to depression tendency prediction. © 2024 SPIE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Multi-layered access control based auto tuning relational key implications in enterprise-level multi-tenancy

引用

Multimedia Tools and Applications 2025年第17期84卷 17805-17836页

作者： Henge, Santosh Kumar Rajakumar, R. Prasanna, P. Parivazhagan, A. Hu, Yu-Chen Chen, Wu-Lin Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation KL University AP Vaddeswaram India Centre for Automation School of Computer Science and Engineering Vellore Institute of Technology Chennai India Department of Computer Science and Engineering Veltech Rangarajan Dr Sagunthala R &D Institute of Science and Technology Chennai India Department of CSE Kalasalingam Academy of Research and Education Tamilnadu Krishnankoil India Department of Computer Science Xitun District Tunghai University No. 1727 Sec. 4 Boulevard Taichung City407224 Taiwan Department of Computer Science and Information Management Providence University Taichung City Taiwan

This article discusses the importance of cloud-based multi-tenancy in private–public-private secure cloud environments, which is achieved through the isolation of end-user data and resources into tenants to ensure data confidentiality and integrity. Maintaining secure access control is a complex and critical task in multi-tenant cloud environments, and researchers have proposed innovative methods for implementing security, privacy, and authenticity. However, several challenges remain. The proposed research addresses these challenges by presenting a layered approach to multi-tenancy in an enterprise-level cloud environment. The study has three main objectives: (1) to describe and analyze the complexities of enterprise-based multi-tenancy and proposed technical solutions in a tabular format;(2) to propose multi-tenant test cases across application, software, infrastructure, and network as a service environment;and (3) to present a collaborative, relational optimal key-based multi-tenancy access control model. The proposed access control model involves integrating various secure layers, such as intranet, extranet, intra-extranet, and using feasible relational optimal keys to provide secure multi-tenant access control among various tenants of single and multiple enterprises. This model provides secure data transmission by integrating various multi-layer data filters and secure blades. The layered multi-tenancy approach offers many benefits and technical feasibilities to avoid security and privacy issues in enterprise-based multi-tenant environments. The process achieved a 93% secure mapping rate to authenticate all IN and OUT data access transactions among the various multi-tenancy of similar and distinct enterprises. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Virtualization

来源：评论

学校读者我要写书评

暂无评论

Explainable AI for Epileptic Seizure Prediction: A SHAPE and LIME Approach 25

Explainable AI for Epileptic Seizure Prediction: A SHAPE and...

引用

25th International Arab Conference on Information technology, ACIT 2024

作者： Talukder, Md. Simul Hasan Mondal, Sohag Kumar Aditi, Oyshi Tabassum Aljaidi, Mohammad Sulaiman, Rejwan Bin Al-Qerem, Ahmad Dhaka University of Engineering & Technology Gazipur Bangladesh Khulna University of Engineering and Technology Khulna Bangladesh Daffodil International University Department of Computer Science and Engineering Savar Bangladesh Zarqa University Faculty of Information Technology Department of Computer Science Zarqa Jordan University of Business and Technology College of Engineering Jeddah21448 Saudi Arabia Northumbria University School of Computer Science & Technology Newcastle Tayne United Kingdom

ISBN: (纸本)9798331540012

Epilepsy is a neurological chaos typified by frequent, spontaneous seizures. Early recognition of epilepsy by utilising AI techniques to scan EEG signals can enhance the prevention and management of it. This study aims to improve the classification of epileptic seizures by using the preprocessed version of the Epileptic Seizure (ERS) dataset. The preprocessed dataset is subjected to multiple stages in order to improve its quality and achieve balanced class representation. Data cleaning, outlier management, merging, and oversampling are those. After that, an 80:20 split of the dataset is made into subsets for testing and training. Next, training, testing, and evaluation are performed on the models of Gradient Boosting Classifier (GBC), Decision Tree Classifier (DTC), Random Forest Classifier (RFC), CatBoost Classifier (CBC), and ExtraTree Classifier (ETC). The ExtraTree Classifier is remarkably accurate, with a 99.51% accuracy rate, which is the highest accuracy. Finally, explainable artificial intelligence (SHAP and LIME) is used to clarify the ExtraTree Classifier's decision-making procedure. By providing a visual representation of significant variables and their influence on the model's predictions, this interpretability tool improves comprehension of the classification results. © 2024 IEEE.

关键词： Neurology

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：