检索结果-内蒙古大学图书馆

3rd International Conference on Pervasive Computing and Social Networking, ICPCSN 2023

作者： Kumari, Prity Tiwari, Rakesh Kumar Technocrats Institute of Technology and Science Dept. of Computer Science Engineering Bhopal India

ISBN: (纸本)9798350322842

Predicting intrusion detection in a wireless sensor network (WSN) involves using machine learning algorithms to analyze network traffic data and predict whether an intrusion or security breach will occur. The goal of intrusion prediction is to provide advanced warning of potential attacks and allow for proactive measures to be taken to prevent or mitigate the attack's impact. Several machines and deep learning algorithms can be used for intrusion prediction in WSNs. This research describes a practical deep-learning approach for Intrusion Detection in WSN based on artificial neural networks. Spyder IDE of python with version 3.7 is used for the simulation work. The results of the simulations demonstrate that the anticipated model is accurate 99.99% of the time. © 2023 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Adaptive Contour Noise Generation Network for Semi-supervised Medical data Segmentation 6

Adaptive Contour Noise Generation Network for Semi-supervise...

引用

6th International Conference on Artificial Intelligence and Big data, ICAIBD 2023

作者： Ye, Shunlong Nanjing University of Science and Technology Dept. of Computer Science and Engineering Nanjing China

ISBN: (纸本)9781665491259

When training convolutional neural networks, noise distribution in data can affect segmentation accuracy. Therefore, many neural networks will strengthen the segmentation ability of the model by artificially adding noise. However, because the noise distribution of the input data is not known, the model training process can only generate random noise, e.g., gaussian noise, but cannot simulate real-world noise. In the medical imaging domain, more attention is paid to the image contours, which can also be used for noising simulation. Meanwhile, considering the existence of rich unlabeled data sets in medical images, this paper proposes a semi-supervised framework for uncertainty estimation by using Monte Carlo Dropout and generates adaptive noise using the uncertainty map. Specifically, the framework consists of three parts, including a noise generation model, a teacher model, and a student model. The noise generation part processes the data input to the other two parts and uses the contour feature identified by the posteriori uncertainty map to simulate priori noise to guide the process of training segmentation model. Meanwhile, the student model updates its parameters based on the teacher model output and the ground truth annotations by minimizing a joint loss. Segmentation experiments on left atrium 3D data show that our method has competitive results with other SOTA semi-supervised methods. © 2023 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Beyond the Blink: IoT's Next-Gen Drowsiness Detection System for Drivers 3

Beyond the Blink: IoT's Next-Gen Drowsiness Detection System...

引用

3rd IEEE International Conference on Industrial Electronics: Developments and Applications, ICIDeA 2025

作者： Routray, Sidheswar Patel, Nachiket Patel, Dhruv Srivastava, Jyoti Dash, Rudra Narayan Pandit Deendayal Energy University Dept. of Computer Science & Engg. Gandhinagar India Indrashil University Dept. of Computer Science & Engg. Mehsana India Ganpat University Dept. of Computer Engineering Mehsana India School of Electrical Engineering KIIT University Bhubaneswar India

ISBN: (纸本)9798331533205

Drowsiness during driving includes high risks for the driver, the co-passengers, and the other people on the road. Advance Driver Assistance Systems (ADAS) have been proposed to reduce these risks. This work introduces a new Internet of Things (IoT) seizure detection system to improve driver safety using Raspberry Pi, which is equipped with various sensors and utilizes machine learning for real-time monitoring and analysis. Using sensor fusion technology, including monitoring yawning and eye-closing patterns, the system aims to detect early signs of driver sleepiness. Being a low-cost, versatile, and tiny device, it becomes an ideal core processor for integration into an in-car environment. Additionally, the simplicity enables seamless communication with various sensors and facilitates effective data collection. Extensive tests and simulations were conducted to evaluate the effectiveness and reliability of the proposed system for real-world driving situations. The result outcomes prove the system's accuracy and efficiency in detecting early signs of driver fatigue to enhance driver safety. The integration of Raspberry Pi and sensor fusion technology makes it economical as well as scalable approaches supporting multiple platforms. © 2025 IEEE.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

A Novel Multi-Objective Model for Feature Selection in Cancer data 1

A Novel Multi-Objective Model for Feature Selection in Cance...

引用

1st International Conference on Cognitive, Green and Ubiquitous Computing, IC-CGU 2024

作者： Panigrahi, Himanshu Sekhar Mishra, Itishree Mishra, Pritish Piri, Jayashree Silicon University Data Science Bhubaneswar India Silicon University Dept. of CSE Bhubaneswar India

ISBN: (纸本)9798350361780

Cancer is a vital disease taking several lives every year. Early detection can prevent lots of terrible cases. Traditional methods frequently don't achieve the best possible accuracy of diagnosis in the detection of cancer. This paper presents a complete framework to improve the feature selection process for cancer detection by integrating a multi-objective optimization approach. Developing a strong multi-objective feature selection method that optimizes computing efficiency, sensitivity, and specificity is one of the main goals. The proposed methodology leverages multi-objective feature selection and the Crayfish Optimization Algorithm (COA), using clues from crayfish behavior to improve exploration and exploitation at different phases. Thorough research and analysis have shown that the hybrid technique works well for optimizing feature subsets. When multi-objective optimization and COA are used, interpretability is enhanced as well as the precision of classification. The study's findings indicate positive advancements in the field of cancer, and the suggested design holds great potential for streamlining feature selection procedures and lowering the complexity of cancer data. MO-COA excels over MOGA and MOPSO, achieving 96.7% average accuracy in breast cancer with 3 average features, surpassing MOGA's 95.3% (2 features) and MOPSO's 95.7% (4 features). In lung and cervical cancer, MO-COA achieves 60.5% (10 features) and 95.5% (5 features) accuracies respectively, outperforming MOGA (52.2% lung, 95.2% cervical) and MOPSO (52.4% lung, 94.2% cervical). The average is taken for total non-dominated solutions for each algorithm over different datasets. These findings underscore MO-COA's efficiency over other algorithms in enhancing cancer diagnosis accuracy with minimal features, benefiting both research and clinical practice. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Detection and Classification of Human Brain Tumor: A Survey 5

Machine Learning for Detection and Classification of Human B...

引用

5th International Conference on Information Technology, Applied Mathematics and Statistics, ICITAMS 2023

作者： Al Hussen, Sara Ali Alsaadi, Elham Mohammed Thabit A. University Of Karbala College Of Computer Science And Information Technology Dept. Of Computer Science Karbala Iraq University Of Karbala College Of Computer Science And Information Technology Dept. Of Information Technology Karbala Iraq

ISBN: (纸本)9798350335118

Intracranial solid tumors arise due to uncontrolled and abnormal cell division. Classification of brain tumors depends on factors such as the tumor's location, the type of tissue it consists of, its malignant or benign nature, and other factors. Magnetic resonance imaging (MRI) is one of the techniques frequently used to detect tumors in the brain Magnetic resonance imaging (MRI). It provides important detail that is used in accurately scanning the human body's internal organization. problem with brain tumors is the complexity and variations in tumor location, shape, size, and intensity from patient to patient. Also, tumor boundaries are usually unclear and irregular. Some studies have appeared in the detection and classification of human brain tumors. Therefore, some of these studies will be discussed in this paper. Humans have developed many algorithms to get better results in brain tumor detection. They used the latest machine-learning techniques to solve this problem. Through these studies, we conclude that the best accuracy was achieved using deep learning techniques like Deep Auto-Encoder (DAE) based on Jaya Optimization Algorithm (JOA) for classification and Bayesian Fuzzy clustering (BFC) to segment up to 98.5%. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Enhanced Deep Learning-Based Malware Classification Using MobileNetV2 4

Enhanced Deep Learning-Based Malware Classification Using Mo...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Manasa, V.Gnana Sri Gopinath, M. Ram, M.Aditya Khan, Md.Sajid Velagapudi Ramakrishna Siddhartha Engineering College Dept. of Artificial Intelligence and Data Science Kanuru India

ISBN: (纸本)9798331529635

In the rapidly evolving landscape of cybersecurity, the classification of malware has become increasingly critical due to the exponential growth in the volume of malware, which poses significant security threats to financial institutions, businesses, and individuals. Traditional signature-based detection methods have struggled to keep up with the growing variety and complexity of new threats, making it necessary to use more advanced techniques. Among these, deep learning has emerged as a promising approach for malware detection, particularly through the classification of malware images by transforming binary files into grayscale representations. While previous research has predominantly utilized deep learning architectures for this task. However, in this research work, we developed a model with Mobilenet to enhance classification accuracy. The results of this research demonstrate the revolutionary potential of deep learning-based methods for malware family classification. © 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

Revolutionizing Education for Visually Impaired Students Using Augmented Reality 5

Revolutionizing Education for Visually Impaired Students Usi...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Janapati, Malathi Naveen, Budamcharla Venkata Sanuth Reddy, Mettu Sai Dinesh, Balabomma Sai Velagapudi Ramakrishna Siddhartha Engineering College Dept. of Artificial Intelligence and Data Science Vijayawada India

ISBN: (纸本)9798331530013

This research explores the use of Augmented Reality (AR) to enhance learning experiences for visually impaired students. By utilizing an Android application, the system captures images of classroom boards and processes them using the EasyOCR library for text extraction. The extracted text is then rendered in 3D using Unity, allowing visually impaired students to interact with the content more effectively. The AR experience enables students to zoom in on the text, adjust font sizes, and explore the information at their own pace. This innovative approach integrates the power of AR to overcome the challenges faced by visually impaired students in traditional classroom settings, promoting inclusivity and enhancing their learning experience. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Hate and Non Hate Speech Detection in Online Social Media 3

Deep Learning Approach for Hate and Non Hate Speech Detectio...

引用

3rd International Conference on Technological Advancements in Computational sciences, ICTACS 2023

作者： Sharma, Parshuram Tiwari, Rakesh Kumar Technocrats Institute of Technology & Science Dept. of Computer Science Engineering Bhopal India

ISBN: (纸本)9798350342338

People's ability to freely and anonymously share their thoughts and feelings online on social media platforms is contributing to a rising issue of hate speech. Hate speech has the potential to hurt both people and groups, contribute to the polarisation of society, and even provoke acts of physical violence. Therefore, identifying and removing hate speech from online social media is an important task for the purpose of maintaining an online environment that is healthy and respectful. A method based on deep learning is proposed in this study for differentiating between hate speech and other types of communication that may be found in online social media. The solution that has been developed makes use of a natural language processing (NLP) and long term short memory (LSTM) model that is trained on a huge dataset consisting of tweets that have been annotated. Tweets that include hate speech and tweets that do not contain hate speech were both included in the dataset and were labelled by human annotators. Python software with IDE of Spyder version 3.7 is used to carry out the simulation work. The accuracy level reached overall is 91.14%. © 2023 IEEE.

关键词： Hate LSTM Machine Learning NLP Social Media Speech Twitter

来源：评论

学校读者我要写书评

暂无评论

Graph-based Named Entity Information Retrieval from News Articles using Neo4j 18

Graph-based Named Entity Information Retrieval from News Art...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Chaudhary, Shikha Vyas, Hirenkumar Arora, Naveen D'Mello, Sejal Vidyavardhini's College of Engineering and Technology Dept. of Artificial Intelligence and Data Science Mumbai India

ISBN: (纸本)9789380544519

The internet, social media, and other cutting-edge technologies are all contributing to the exponential growth of digital information. This makes interpreting and applying this enormous amount of data both possible and challenging. Our research proposes a smart system that can convert unprocessed text into a knowledge graph in order to address this. This system makes use of the graph database Neo4j. Although there are currently available tools for linking entities and models to extract relationships, such as Spacy, NLTK, and Flair, their combined use is inefficient. Our suggested method seeks to efficiently blend entity linkage and relation extraction, allowing us to convert raw data into a knowledge graph. There are many real-world uses for this strategy, particularly in data analysis and decision-making. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Cypher Queries Graph database Information Retrieval Named Entity Recognition Neo4j News Articles Relation extraction

来源：评论

学校读者我要写书评

暂无评论

The Cubic Bipolar Neutrosophic Sets theory and Uncertainty Management in Environmental data Analysis

引用

Neutrosophic Sets and Systems 2024年 72卷 60-133页

作者： Salama, A.A. Khalid, Huda E. Mabrouk, Ahmed G. Dept. of Math and Computer Sci. Faculty of Science Port Said Univ. Egypt Dean of higher Institute of Computer Science and Information Systems Ministry of Higher Education October City Egypt Telafer University Telafer Iraq Higher Institute of Computer Science and Information Systems Ministry of Higher Education October City Egypt

Environmental data analysis often faces uncertainties in measurements. Cubic Bipolar Neutrosophic Sets (CBN Sets) provide a powerful framework to address this challenge. This paper explores the mathematical foundations of CBN Sets and highlights their practical applications through illustrative examples. We demonstrate how CBN Sets effectively capture varying degrees of certainty, possibility, and impermanence in environmental parameters. The concept of inclusion relations facilitates comparisons and information fusion. Fundamental set operations (intersection, union, complement) are explored for manipulating and analyzing uncertain environmental data. We present the application of CBN Sets in water quality assessment, highlighting their ability to analyze parameters while accounting for measurement uncertainties. The potential for air quality monitoring using CBN Sets is also discussed. Finally, distance measures and similarity coefficients are introduced to quantify relationships between air quality characteristics from different stations. By leveraging CBN Sets and their associated operations, researchers can gain a more nuanced understanding of environmental data, enabling informed decision-making for a healthier planet. © 2024, University of New Mexico. All rights reserved.

关键词： Environmental monitoring

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：