检索结果-内蒙古大学图书馆

4th International Conference on computer, Communication, Control and Information Technology, C3IT 2024

作者： Saha, Rounak Maity, Trishita Singh, Akanksha Kumari, Gracy Chakraborty, Arnab University of Engineering and Management Kolkata Computer Science & Engineering Kolkata India University of Engineering and Management Kolkata Kolkata India University of Engineering and Management Kolkata Kolkata India

ISBN: (纸本)9798350389128

This survey report identifies and evaluates various approaches that could contribute to success in drug development and tracking activities using Graph Neural Networks (GNN). This paper aims to determine the best drug discovery approach among several related papers to increase the efficiency and the quality of the product. GNNs were incorporated into all levels of the drug discovery process, from target molecule discovery to de novo drug design. GNNs have significantly advanced efficiency and reliability in these processes, though challenges like biased datasets persist, creating room for improvement of the existing GNN structures. It discusses the curation and categorization of existing literature that has helped us grasp the concept of GNNs in drug discovery processes. This paper presents a detailed analysis and results of various applications of GNNs in reducing health risks, refining drug formulations, and drug discovery. A collective comparison of theories from distinguished research papers is proposed, involving discussions and literature surveys on the implementation of the GNN approach to date. © 2024 IEEE.

关键词： Biased datasets De Novo Drug Design Drug discovery Graph Neural Networks Health risk reduction

来源：评论

学校读者我要写书评

暂无评论

Graph Based Keywords Extraction from Crime Data 16

Graph Based Keywords Extraction from Crime Data

引用

16th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2024

作者： Das, Priyanka Munshi, Anuvab Naha, Annwesha Dey, Adrija Chakraborty, Sriparno Dept. of Computer Application and Science Institute of Engineering & Management Kolkata University of Engineering and Management Kolkata India

ISBN: (纸本)9798331505264

It takes a lot of work to gather a large amount of data to help in criminal investigation and prevention of crimes. The most effective methods for reporting crimes are insufficient for both civilians and law enforcement. The police and witness narrative summaries are frequently deemed to be too lengthy to read. Hence, there exists many research works that represents summary of those descriptive reports. But to make it easier, there should be certain phrases or words so that Police investigators can quickly understand criminal scenarios saving them from having to read the entire report. This can be accomplished with the use of criminal information extraction. Here, the proposed study uses a graph-based methodology and natural language processing techniques to extract crimerelated keywords from in-depth police and witness narrative descriptions. Initially, the suggested work selected nouns, verbs, and adjectives from the crime reports and evaluated their importance scores. Based on the words' importance scores, a graph partitioning technique has been applied;following repeated runs of the algorithm, the words are classified into clusters. Each cluster in this instance, together with the words that reside within it, represent a different aspect of crime. These clustered words are considered as the keywords for representing the crime. © 2024 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Towards Precision Dementia Detection: Integrating ML and Clinical Data 2

Towards Precision Dementia Detection: Integrating ML and Cli...

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Kandula, Niravange Chakravarty, Sujata Kandula, Aksha Mohapatra, Sunil Kumar Centurion University of Technology & Management Computer Science & Engineering Vizianagaram India Centurion University of Technology & Management Computer Science & Engineering Bhubaneswar India Andhra University College of Engineering Computer Science & Engineering Andhra Pradesh Visakhapatnam India

ISBN: (纸本)9798350370188

The dominant pathology theory holds that dementia results from amyloid buildup, followed by tau protein aggregation and neurodegeneration. Current anti-amyloid and anti-tau therapies, however, show varied therapeutic success. Atypical Alzheimer's disease has radiologic and clinical symptoms with other medical conditions, making accurate diagnosis even more challenging. Our approach employs machine learning algorithms to analyze a dataset that includes clinical evaluations, neuropsychological assessment scores, and biomarker measures. The information was gathered from a broad group of people with varying cognitive states, including those in the preclinical and moderate cognitive impairment (MCI) phases as well as AD patients. This study has important implications for clinical practice, permitting prompt therapies, and advancing our understanding of the progression of Alzheimer's disease. When integrated with Boruta as a feature selector, random forest outperformed upon fine-tuning on both datasets. © 2024 IEEE.

关键词： Pathology

来源：评论

学校读者我要写书评

暂无评论

Advanced deep learning models for automatic detection of driver’s facial expressions, movements, and alertness in varied lighting conditions: a comparative analysis

引用

Multimedia Tools and Applications 2025年第6期84卷 2947-2983页

作者： Das, Shiplu Pratihar, Sanjoy Pradhan, Buddhadeb Computer Science and Engineering Indian Institute of Information Technology West Bengal Kalyani India University of Engineering and Management Kolkata West Bengal New Town India

Emotion recognition is vital in understanding human behavior and improving the driving experience. We present a systematic analysis of automatic detection of driver’s facial expressions and movements while crying, feeling sad, experiencing anger, drowsiness, fear and surprise to reduce road accident using a deep learning method in varied lighting conditions. The proposed approach aims to accurately detect and analyze driver emotions in real time, it would help in advancing the growth of smart driver assistance systems. To conduct our analysis, we create a comprehensive dataset comprising annotated facial images of drivers exhibiting crying, sadness, anger, drowsiness, fear and surprise. The dataset is carefully designed to encompass diverse lighting conditions, facial orientations, and driver demographics, ensuring the generalizability and robustness of the proposed method. The CNN-BiLSTM model is compared against the CNN, LSTM, CNN-LSTM, BiLSTM, and CNN-LSTM models in the research to perform precise localization of facial expressions and movements. The trial findings show how well our technique accurately identifies and evaluates a driver’s facial expressions. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

To Design and Implement Application for Bank Customer Churning Rate Prediction and Analysis using Machine Learning Algorithm

To Design and Implement Application for Bank Customer Churni...

引用

2024 MIT Art, Design and Technology School of Computing International Conference, MITADTSoCiCon 2024

作者： Maskale, Vikram Vaidya, Vivekanand Patil, Yash Bagal, Yogesh Dhamdhre, Vidya G H Raisoni College of Engineering and Management Computer Engineering Pune India

ISBN: (纸本)9798350362879

The banking industry faces a constant challenge in retaining customers and mitigating customer churn. To address this issue, this study presents the design and implementation of an innovative application aimed at predicting and analyzing bank customer churning rates. Leveraging state-of-The-Art machine learning algorithms, this application offers a comprehensive solution for identifying potential churners and devising effective retention strategies. The first phase of the project involves data collection and preprocessing, where historical customer data, including transaction history, demographics, and behavior patterns, is gathered and cleaned for analysis. Subsequently, various machine learning algorithms, including but not limited to logistic regression, random forests, and gradient boosting, are employed to build predictive models. These models are trained on the historical data and are fine-Tuned to achieve optimal predictive accuracy. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Privacy-Preserving Quantum Blockchain Technique for Electronic Medical Records

引用

IEEE engineering management Review 2023年第4期51卷 137-144页

作者： Venkatesh, Ranjitha Hanumantha, Brahmananda Savadatti Gandhi Institute of Technology and Management Department of Computer Science Engineering Bengaluru561203 India

Nowadays, electronic medical records are increasing rapidly. Electronic medical records consist of sensitive and confidential information. These pieces of information need to be protected from attackers during the exchange with patients. Blockchain technology can protect information from attackers during the exchange of information. There are various classical techniques to protect electronic medical records. These techniques can exchange information correctly but cannot resist collective and coherent attacks and have more communication and computation costs. In this article, we introduced a privacy-preserving quantum blockchain technique to protect electronic medical records. This technique can resist the intercept, intercept-resend, entangle-measure, man-in-the-middle, collective, and coherent attacks with less communication and computation costs. © 1973-2011 IEEE.

关键词： Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

TimeScram: Leveraging Temporal Randomization for Image Encryption, Data Hiding and Secure Visual Communications 12

TimeScram: Leveraging Temporal Randomization for Image Encry...

引用

12th International Conference on Internet of Everything, Microwave, Embedded, Communication and Networks, IEMECON 2024

作者： Jain, Aniket Khandelwal, Jyoti Singh, Sunny Pratap Khalkho, Manjusha Department of Computer Science & Engineering University of Engineering and Management Jaipur Jaipur India

ISBN: (纸本)9798350387315

Safeguarding visual data is crucial in today's digital world. This paper introduces an image encryption method based on time-seeded randomization, QR decomposition, and Discrete Wavelet Transform (DWT) methods. In contrast to the previously applied scrambling methods, the proposed scrambling method conversely implements dynamic scrambling using randomization on the current system time. This method ensures the security of the secret data. Experimental outcomes show that this method is efficient. The PSNR value of stego image is always >30 dB for different alpha values. This integrated methodology is a promising solution for image encryption, data hiding, and security of information in various practical cases. © 2024 IEEE.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

DentaGAN - Smart Dental Image Segmentation 8

DentaGAN - Smart Dental Image Segmentation

引用

8th IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics, DISCOVER 2024

作者： Ashwini, C.S. Fernandes, Sohan Shetty, Shrinidhi Pratap, Soorya Mesta, Sourav Sahyadri College of Engineering & Management Department of Computer Science & Engineering Mangaluru India

ISBN: (纸本)9798350350593

This project introduces a novel method for smart dental image segmentation by leveraging Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), and the U-net architecture. The process begins with thorough data preprocessing, employing techniques such as noise reduction and image enhancement to ensure dataset quality and consistency. Following this, individual CNN, GAN, and U-net models are developed and trained. CNNs extract features from dental images, GANs generate realistic images for training, and U - net performs the segmentation task. Detailed descriptions of hardware and software configurations in the experimental setup ensure reproducibility, while key training parameters provide insights into the training process. The results showcase the model's superior performance through quantitative metrics like accuracy, precision, and recall, along with qualitative assessments comparing the segmentation results to ground truth annotations. In summary, this project presents a comprehensive approach to dental image segmentation, combining advanced neural network architectures with meticulous data preprocessing and thorough experimental setup. The integration of CNNs, GANs, and U-net models leads to enhanced segmentation accuracy, validated through both quantitative evaluations and qualitative comparisons with ground truth annotations. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Registration of CT Images of Lung Using Fireworks Algorithm 1

引用

2nd International Conference on Human-Centric Smart Computing, ICHCSC 2023

作者： Nayak, Somen Mondal, Subhodip Obaid, Ahmed J. Department of Computer Application University of Engineering and Management Rajasthan Jaipur India Department of Computer Science and Engineering University of Engineering and Management Rajasthan Jaipur India Department of Computer Science and Mathematics Department of Computer Science University of Kufa Najaf Iraq

ISBN: (数字)9789819977116

ISBN: (纸本)9789819977109

The acquisition of medical images from various modalities can provide a number of practical challenges that can be addressed through medical image registration. Intensity-based registration methods, which are used in multi-modal registration, merge multiple images with the same content into a single representation by applying image transformation. It is essential to edit photographs as best as you can. It is highly important to improve the similarity measure between the various photographs. We introduce a new method for registering lung’s CT image affected with COVID-19 in this work since the image registration process is fundamentally an improvement problem. Lung computed tomography image registration is a technique for aligning pre- and post-contrast images for analysis the effect of COVID-19 virus in the lung. A meta-heuristics-based optimization technique called FWA-IATF was explored for registering lung CT images. Following that, the FWA-IATF algorithm successfully registers the images. The results of registration based on the FWA-IATF method and PSO approach are compared. The results indicate that the FWA-IATF-based registration methods outperform the PSO-based registration approach while registering lung CT images. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Classification of Breast Masses Using Ultrasound Images by Approaching GAN,Transfer Learning,and Deep Learning Techniques

引用

Journal of Artificial Intelligence and Technology 2023年第4期3卷 142-153页

作者： Sushovan Chaudhury Kartik Sau Department of Computer Science and Engineering University of Engineering and ManagementKolkataIndia

Breast cancer is a common cause of death among women *** imaging is a valuable diagnostic tool in breast cancer ***,the accuracy of computer-aided diagnosis systems for breast cancer classification is limited due to the lack of well-annotated *** study proposes a deep learning(DL)-based framework for breast mass classification using ultrasound images,which incorporates a novel data augmentation technique,generative adversarial network(GAN),and transfer learning(TL).Automating early tumor identification and classification in breast cancer diagnosis can save lives by improving the accuracy of diagnoses and reducing the need for invasive ***,the limited availability of wellannotated datasets for ultrasound images of breast cancer has hampered the development of accurate computer-aided diagnosis *** accuracy of breast mass classification using ultrasound images is limited due to the lack of well-annotated *** data augmentation techniques have limitations in applications with strict guidelines,such as medical ***,there is a need to develop a novel data augmentation technique to improve the accuracy of breast mass classification using ultrasound *** proposed framework can be extended to other medical imaging applications,where the availability of well-annotated datasets is *** GAN-based data augmentation technique and TL-based feature extraction can be used to improve the accuracy of classification models in other medical imaging ***,the proposed framework can be used to develop accurate computer-aided diagnosis systems for breast cancer detection in clinical *** proposed framework incorporates a DL-based approach for breast mass classification using ultrasound *** framework includes a GAN-based data augmentation technique and TL for feature *** dataset used for training and testing the model is the breast ultraso

关键词： breast masses breast ultrasound deep learning fully connected convolution generative adversarial network(GAN) transfer learning(TL)

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：