检索结果-内蒙古大学图书馆

Advances in AI-based genomic data analysis for cancer survival prediction

Multimedia Tools and Applications 2025年第14期84卷 14139-14166页

作者： Deepali Goel, Neelam Padmavati Khandnor University Institute of Engineering and Technology Panjab University Chandigarh160014 India Chandigarh160012 India Department of Computer Science Guru Nanak College Budhlada151502 India

Problem: Cancer is one of the deadliest diseases prevalent in the world. Survivability, early diagnosis, and accurate prognosis are of utmost importance for the therapeutics and clinical management of cancer patients. To achieve accurate and timely prediction of the survival of cancer patients, several machine-learning models based on genomic data have been proposed but a comprehensive review of recent applications in cancer survival prediction is lacking. This paper represents a review of the most recent application of machine learning and deep learning on cancer survival prediction, with a particular focus on the use of genomic data. It specifically targets the most prominent cancer types such as breast cancer, glioblastoma, lung cancer, renal cell cancer, and oral cancer. Methods: A systematic review approach is employed to analyze recent studies on machine learning techniques applied to cancer survival prediction. Emphasis is placed on methodologies utilizing genomic data due to its effectiveness in predicting survival outcomes. Results: This review highlights the efficacy of different machine/deep learning-based techniques in predicting survival outcomes for different cancer types with genomic data. It also provides a summary of the contributions made by different research groups, critically examines the associated challenges, and suggests potential areas for further investigation. Conclusion: Machine learning and deep learning techniques, especially those utilizing genomic data, hold significant promise for accurate cancer survival prediction across diverse cancer types. Despite advancements, challenges such as data heterogeneity and model interpretability still persist. Further research is warranted to address these challenges and develop a comprehensive framework for cancer survival prediction applicable to various cancer types. This review lays the foundation for future investigations in the area of cancer research. © The Author(s), under exclusive licence

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Pulmonary Nodule Detection in Computed Tomography Images Using Deep Learning 1

Pulmonary Nodule Detection in Computed Tomography Images Usi...

引用

1st IEEE International Conference on Advances in Electronics, Communication, Computing and Intelligent Information Systems, ICAECIS 2023

作者： Longkumer, Akumlong Walling, Supongmen Kalita, Shobhanjana Icfai University Department of Computer Science Dimapur India National Institute of Technology Department of Computer Science and Engineering Dimapur India Tezpur University Department of Computer Science and Engineering Tezpur India

ISBN: (纸本)9798350348057

the well-being of individuals is seriously threatened by lung cancer, which has one of the highest fatality rates of all cancers. Therefore, to increase patient life expectancies, early diagnosis of lung nodules is essential. For many years, the science of machine vision and medical diagnostics has used convolution neural networks. Early diagnosis can significantly lower the patient's mortality, and computer-aided diagnosis has emerged as a vital tool for medical professionals. computer-aided diagnosis depends on the ability to identify pulmonary nodules in computed tomography images. In the Computed Tomography scans, it is difficult to find the lump inside the lungs. This project uses U-Net to implement automated lung nodule identification. Furthermore, the data sets used for pulmonary nodule recognition from CT scan images are from the freely accessible LIDC/IDRI database. © 2023 IEEE.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

A Novel Replication-Less Image Retrieval Method from Cloud Platforms using Divergence Features 2

A Novel Replication-Less Image Retrieval Method from Cloud P...

引用

2nd International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2023

作者： Usharani, S. Dhanalakshmi, K. IFET College of Engineering Department of Computer Science and Engineering Tamilnaldu Villupuram India Psna College of Engineering and Technology Department of Computer Science and Engineering Tamilnaldu Dindigul India

ISBN: (纸本)9798350348002

Real-time multimedia applications provide visual and audible services collaborated with the cloud platform for heterogeneous user requirements. Multi-source information storage and fusion satisfy the user demands through the applications. Contrarily, replication is a common issue demanding high space and time, increasing computation and retrieval time. For addressing the retrieval issues in replicated image storage, this article introduces a Divergent Feature-induced Extension (DFIE) method for large cloud platforms. The proposed method identifies the divergences alone in the input features correlated with the stored ones, in different feature extracted instances. In the feature divergent analysis, the deep recurrent learning paradigm is utilized. The iterations are used for identifying non-correlating features and their deviation for verifying non-replicable images. The process pursues region-based segmentation for a feature and edge-based divergence and similarity identification. The proposed method's performance is analyzed using the metrics detection accuracy, complexity, and computing time. © 2023 IEEE.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

A Real-Time computer Vision-Based Green Intensity Estimation Method for the Arecanut Tree Pesticide Spraying System

A Real-Time Computer Vision-Based Green Intensity Estimation...

引用

International Conference on VLSI, Signal Processing, Power Electronics, IoT, Communication and Embedded Systems, VSPICE 2023

作者： Nagaraja Hebbar, N. Sandeep, Bhat Artificial Intelligence and Data Science Department Srinivas Institute of Technology Mangaluru India Computer Science and Engineering Department Srinivas Institute of Technology Mangaluru India

ISBN: (纸本)9789819746569

In India, one of the commercial crops is arecanut. The majority of arecanut growers depend on the arecanut production. However, they are also having a great deal of difficulty finding skilled workers to do pesticide spraying jobs. This effort uses computer vision technologies to address the aforementioned problem. This work compares the HSV estimation with the green pixel estimate approach. This makes it easier to position the robot at the right height, where the pesticide spray will work best. In this case, the HSV estimation identified a better way to manage the robot’s motion. Using a wireless camera, the experimental setup achieves an incredibly innovative performance to capture an image of the arecanut crop. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Comparison of different pseudo-linear estimators for vision-based target motion estimation

引用

Control Theory and technology 2023年第3期21卷 448-457页

作者： Zian Ning Yin Zhang Shiyu Zhao Department of Computer Science and Technology Zhejiang UniversityHangzhou 310058ZhejiangChina School of Engineering Westlake UniversityHangzhou 310024ZhejiangChina

Vision-based target motion estimation based Kalman filtering or least-squares estimators is an important problem in many tasks such as vision-based swarming or vision-based target *** this paper,we focus on a problem that is very specific yet we believe *** is,from the vision measurements,we can formulate various *** and how the measurements should be used?These problems are very fundamental,but we notice that practitioners usually do not pay special attention to them and often make *** by this,we formulate three pseudo-linear measurements based on the bearing and angle measurements,which are standard vision measurements that can be *** estimators based on Kalman filtering and least-squares estimation are established and compared based on numerical *** is revealed that correctly analyzing the covariance noises is critical for the Kalman filtering-based *** the variance of the original measurement noise is unknown,the pseudo-linear least-squares estimator that has the smallest magnitude of the transformed noise can be a good choice.

关键词： Pseudo-linear measurements Kalman filter Least-squares estimator Vision-based target motion analysis Fisher information

来源：评论

学校读者我要写书评

暂无评论

The deep learning applications in IoT-based bio- and medical informatics: a systematic literature review

引用

Neural Computing and Applications 2024年第11期36卷 5757-5797页

作者： Amiri, Zahra Heidari, Arash Navimipour, Nima Jafari Esmaeilpour, Mansour Yazdani, Yalda Department of Computer Engineering Tabriz Branch Islamic Azad University Tabriz Iran Department of Software Engineering Haliç University Istanbul34060 Turkey Department of Computer Engineering Kadir Has University Istanbul Turkey Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou64002 Taiwan Computer Engineering Department Hamedan Branch Islamic Azad University Hamedan Iran Immunology Research Center Tabriz University of Medical Sciences Tabriz Iran

Nowadays, machine learning (ML) has attained a high level of achievement in many contexts. Considering the significance of ML in medical and bioinformatics owing to its accuracy, many investigators discussed multiple solutions for developing the function of medical and bioinformatics challenges using deep learning (DL) techniques. The importance of DL in Internet of Things (IoT)-based bio- and medical informatics lies in its ability to analyze and interpret large amounts of complex and diverse data in real time, providing insights that can improve healthcare outcomes and increase efficiency in the healthcare industry. Several applications of DL in IoT-based bio- and medical informatics include diagnosis, treatment recommendation, clinical decision support, image analysis, wearable monitoring, and drug discovery. The review aims to comprehensively evaluate and synthesize the existing body of the literature on applying deep learning in the intersection of the IoT with bio- and medical informatics. In this paper, we categorized the most cutting-edge DL solutions for medical and bioinformatics issues into five categories based on the DL technique utilized: convolutional neural network, recurrent neural network, generative adversarial network, multilayer perception, and hybrid methods. A systematic literature review was applied to study each one in terms of effective properties, like the main idea, benefits, drawbacks, methods, simulation environment, and datasets. After that, cutting-edge research on DL approaches and applications for bioinformatics concerns was emphasized. In addition, several challenges that contributed to DL implementation for medical and bioinformatics have been addressed, which are predicted to motivate more studies to develop medical and bioinformatics research progressively. According to the findings, most articles are evaluated using features like accuracy, sensitivity, specificity, F-score, latency, adaptability, and scalability. © The Author(s

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Comparative Methods of Implementation for Different Question Answering Systems 5

Comparative Methods of Implementation for Different Question...

引用

5th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2024

作者： Naveen, C. Amutha, B. Srm Institute of Science and Technology Department of Computer Science and Engineering Kattankulathur Chennai India Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur Chennai India

ISBN: (纸本)9798350385649

This research introduces an innovative Question Answering (QA) system tailored explicitly for government department inquiries regarding individuals. Harnessing the prowess of cutting-edge language models such as BERT and T5 (Text-to-Text Transfer Transformer), the system excels in understanding complex queries within diverse governmental domains. Moreover, it incorporates a specialized Knowledge Graph meticulously curated with interconnected information about people across various departments. By integrating BERT and T5 for versatile query comprehension and answer generation alongside a comprehensive People-centric Knowledge Graph, this system aims to revolutionize information retrieval within government entities. The seamless fusion of these technologies promises accurate, contextually rich responses, optimizing operational efficiency across government departments and fostering streamlined access to crucial information. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

A Transformer-based approach for Fake News detection using Time Series Analysis 7

A Transformer-based approach for Fake News detection using T...

引用

7th International Multi-Topic ICT Conference: IMTIC 2023

作者： Ur Rahman, Aniq Chaudhry, Hassan Nazeer Asim, Malik Muhammad Kulsoom, Farzana University of Engineering and Technology Computer Department Taxila Pakistan Barani Institute of Technology Computer Science Department Rawalpindi Pakistan University of Engineering and Technology Telecommunication Engineering Department Taxila Pakistan

ISBN: (纸本)9798350338461

Fake news is a growing problem in the digital age, spreading misinformation and affecting public opinion. Existing fake news detection is based on style analysis or news generator's behavior analysis, the former fails if the content is generated using existing news corpus while the latter requires a very specific data set. In this research, we aim to address the issue of fake news detection by employing deep learning-based time series analysis (TSA). We propose a TSA method to gauge the authenticity of the news based on previously available news content of a similar genre. We employed pre-trained models for encoding including GloVe and BERT and transformer-based sequence-to-sequence (Seq2Seq) for TSA. The results demonstrate 98% accuracy of pre-trained models, such as GloVe and BERT, over traditional encoding approaches having accuracy between 77% and 93%. Our study also compares the effectiveness of various deep learning methods, including Long-Short Term Memory (LSTM), Gated Recurrent Unit (GRU), LSTM with attention, GRU with attention, and Transformers with 8 and 16 multi-heads. The results show that Transformers with 8 and 16 multi-heads achieve 98% and 97% accuracy respectively as compared to LSTM (87%) and GRU (88%). Our work is useful for future research in TSA-based fake news detection and proposes to use GloVe and BERT-based encoding and multi-head transform architecture. © 2023 IEEE.

关键词： Harmonic analysis

来源：评论

学校读者我要写书评

暂无评论

A Novel Vision Transformer Approach for Driver Fatigue Detection from EEG Signal with Correlation-Based Channel Selection

A Novel Vision Transformer Approach for Driver Fatigue Detec...

引用

2024 IEEE International Conference on Computing, Applications and Systems, COMPAS 2024

作者： Khan, Robiul Roy, Dipon Ali, Md. Wajed Refat, Kawsar Ahmed Naziullah, Shekh Pabna University of Science and Technology Department of Electrical and Electronic Engineering Pabna Bangladesh Daffodil International University Department of Computer Science Engineering Dhaka Bangladesh

ISBN: (纸本)9798331529765

Driver fatigue poses a critical threat to road safety, necessitating the development of robust detection methods to minimize traffic accidents and societal burdens. Deep neural networks have recently been effectively applied to Electroencephalography (EEG)-based driving fatigue detection. Nevertheless, most of the existing models, particularly those relying on extensive pooling, often struggle to capture long-range dependencies within images. To address this issue, we propose a Correlation-based Channel Selection (CCS) with a Vision Transformer (ViT) approach for driver fatigue detection using an EEG. Our methodology integrates a pioneering Channel Selection (CS) block to extract discriminative channels via CCS. This mechanism systematically identifies the most informative EEG channels crucial for fatigue detection. Subsequently, we leverage Continuous Wavelet Transform (CWT) to convert the selected EEG channels into a time-frequency spectral image. Finally, the resulting time-frequency spectral images, encompassing both temporal and spectral information, are concatenated and fed into the Vision Transformer (ViT) model to classify them as either normal or fatigued. The proposed model is evaluated on a publicly available EEG dataset containing recordings from twelve subjects. The model achieved superior accuracy: 95.83% for the effective selected combined subject and 99.925% for the average accuracy of each subject, demonstrating its potential for robust driver fatigue detection. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Detection using YOLO v7 and YOLO v8

Brain Tumor Detection using YOLO v7 and YOLO v8

引用

2024 IEEE International Conference on Modeling, Simulation and Intelligent Computing, MoSICom 2024

作者： Vaghela, Rohan Sarda, Jigar Thakkar, Amit Vaishnani, Darsh Khokhariya, Avani Mehta, Pooja Charotar University of Science & Technology Department of Computer Science & Engineering Anand India Charotar University of Science & Technology Department of Artificial Intelligence & Machine Learning Anand India

ISBN: (纸本)9798331533311

The architecture of the brain is incredibly complex, with multiple areas managing various parts of the nervous system. An adult's health is greatly at risk from brain tumors because of their ability to severely impair organ function or possibly cause death due to their rapid growth of abnormal brain cells. Brain tumors can develop in any area of the skull or brain, including the protective layer around the brain and many other areas. Since these tumors can have a wide range of shapes, sizes, and locations, magnetic resonance imaging (MRI) is an essential tool for locating malignant tumors. MRIs are examined manually in order to diagnose brain tumors. However, manually identifying brain tumors is a challenging and time-consuming task that may result in errors. As a result, computer-aided brain tumor detection has been considered a crucial area of study in biomedical engineering. However, because tumor sizes and shapes vary enormously throughout subjects, developing a reliable brain tumor detector remains difficult. Thus, for the purpose of accurately identifying brain tumors in MRI scans, two popular deep learning detection algorithms - YOLO v7 and YOLO v8 - were tested and compared in this study. From the results, YOLO v8 model has achieved highest validation accuracy of 96.50% with average precision and recall value of 95.9% and 93.3% respectively, while YOLO v7 has validation accuracy of 87.6% with average precision and recall value of 81.9% and 85.4% respectively. © 2024 IEEE.

关键词： Deep learning

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：