检索结果-内蒙古大学图书馆

3rd International Conference on Innovative Mechanisms for Industry Applications, ICIMIA 2023

作者： Chandralekha, E. Vinodhini, S. Kandasamy, V. Rama, P. Ravikumar, S. Saravanan, T.R. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Dept.of CSE Chennai India Velammal Engineering College Dept. of Information Technology Chennai India Panimalar Engineering College Dept. of Information Technology Chennai India College of Engineering and Technology Faculty of Engineering and Technology SRM Institute of Science and Technology Dept. of Computing Technologies Chennai India SRM Institute of Science and Technology Dept. of Computational Intelligence Chennai India

ISBN: (纸本)9798350343632

Heart disease is a significant global health challenge, impacting many lives and often being a leading cause of mortality and illness. Detecting heart disease accurately and promptly is essential for effective medical care. Due to the complex interplay of risk factors and the intricate nature of diagnosis, advanced technologies like machine learning are being explored. This study introduces a comprehensive framework that employs machine learning techniques for heart disease detection. The framework involves critical stages such as data preprocessing, feature selection, and training ensemble classifiers. Experimental results highlight the importance of specific attributes in each classifier, offering insights into predictions. Notably, attributes like oldpeak, thalach, ca, cp, and thal are key features in the Random Forest classifier, while Gradient Boosting underscores ca, cp, thal, oldpeak, and age. AdaBoost and the Extra Trees Classifier reveal similar significant attributes. Evaluation metrics emphasize the models' robust performance, with the Extra Trees Classifier achieving the highest accuracy. This research contributes to a practical heart disease detection framework with potential for improving medical decision-making. © 2023 IEEE.

关键词： AdaBoost Extra Trees Classifier Gradient Boosting Machine Learning Random Forest

来源：评论

学校读者我要写书评

暂无评论

INN: A Deep Correction Network for High-Dynamic Inertial Navigation 4

INN: A Deep Correction Network for High-Dynamic Inertial Nav...

引用

4th International Conference on Industrial Automation, Robotics and control engineering, IARCE 2024

作者： Gu, Tao Cong, Li Yang, Jing Guo, Yuzhu Wang, Lina School of Automation Science and Electrical Engineering Beihang University Beijing China School of Electronic Information Beihang University Engineering dept. Beijing China National Key Laboratory of Science and Technology on Aerospace Intelligence Control Beijing China

ISBN: (纸本)9798350380323

Inertial navigation has gained extensive application because it solely relies on built-in Inertial Measurement Unit (IMU) devices. Nevertheless, due to its inherent accumulative integral error, inertial navigation is often integrated with other external devices in practical situations, which unfortunately leads to unavoidable privacy breaches. To address these issues, an Inertial Navigation Neural Network (INN) is designed to generate high-precision position estimations without relying on any other auxiliary information. The INN model consists of attitude correction and velocity regression modules. The attitude module employs a convolutional network to correct the attitude information, and the obtained rotation matrices are then fed into a recurrent neural network to regress incremental velocities and produce high-precision positions. The proposed model is validated on the simulated trajectories based on the Precise Strapdown Inertial Navigation System (PSINS) toolbox. Experimental studies demonstrated that the proposed method has a significant corrective effect on high-dynamic strapdown inertial navigation settings. The accumulated position errors are an order of magnitude smaller than those of traditional track reckoning algorithms and achieved a comparable performance with integrated navigation. © 2024 IEEE.

关键词： Inertial navigation systems

来源：评论

学校读者我要写书评

暂无评论

Next-Generation Intrusion Detection: Navigating Challenges and Embracing AI

Next-Generation Intrusion Detection: Navigating Challenges a...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Shivhare, Mani Dhir, Saru Shrivastava, Santosh Kumar Augn Amity School of Engineering and Technology Greater Noida India Amity University Dept. of Information Technology Noida India G L Bajaj Institute of Technology and Management Dept. of Artificial Intelligence and Machine Learning Greater Noida India

ISBN: (纸本)9798331508685

The emergence of networked autonomous systems has brought a new wave of security threats. Because of not be able to adopt the traditional intrusion detection approaches with the new threats, AIML based cybersecurity defences have gain more attention in recent times. The current state of AIML-based intrusion and abuse detection is examined in this paper, with a focus on significant scientific advancements and the real-world obstacles preventing its broad deployment. As cyberattacks become more sophisticated, one thing has remained the same: Intrusion Detection Systems are a must for protecting digital infrastructures, and they need to be robust. This review summarises the awareness of IDS from traditional signature-based methods to an upcoming disruptive focus on Artificial Intelligence, especially ML and DL. We present a comparison of the advantages and disadvantages of these techniques, emphasizing challenges such as dataset limitations, adaptability to operate in real-time and detecting unseen attacks. Forthcoming, we examine new research directions (hybrid methods, ensemble learning and challenging advanced datasets) to improve the efficacy of IDS on ever more complicated network landscapes. © 2025 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

RSM-NLP at BLP-2023 Task 2: Bangla Sentiment Analysis using Weighted and Majority Voted Fine-Tuned Transformers 1

RSM-NLP at BLP-2023 Task 2: Bangla Sentiment Analysis using ...

引用

1st Workshop on Bangla Language Processing, BLP 2023

作者： Seth, Pratinav Goel, Rashi Mathur, Komal Vemulapalli, Swetha Dept. of Data Science & Computer Applications Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Dept. of Computer Science & Engineering Dept. of Information and Communication Technology

ISBN: (纸本)9798891760585

This paper describes our approach to submissions made at Shared Task 2 at BLP Workshop - Sentiment Analysis of Bangla Social Media Posts(Hasan et al., 2023a;Islam et al., 2021;Hasan et al., 2023b). Sentiment Analysis is an action research area in the digital age. With the rapid and constant growth of online social media sites and services and the increasing amount of textual data, the application of automatic Sentiment Analysis is on the rise. However, most of the research in this domain is based on the English language. Despite being the world’s sixth most widely spoken language, little work has been done in Bangla. This task aims to promote work on Bangla Sentiment Analysis while identifying the polarity of social media content by determining whether the sentiment expressed in the text is Positive, Negative, or Neutral. Our approach consists of experimenting and finetuning various multilingual and pre-trained BERT-based models on our downstream tasks and using a Majority Voting and Weighted ensemble model that outperforms individual baseline model scores. Our system scored 0.711 for the multiclass classification task and scored 10th place among the participants on the leaderboard for the shared task. Our code is available at https://***/ptnv-s/RSM-NLP-BLP-Task2. © 2023 Association for Computational Linguistics.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Analysis of Neural Machine Translation for English to Hindi using Long Short-Term Memory Model and Transformer Model 4

Analysis of Neural Machine Translation for English to Hindi ...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Naveen, Rashmi Kumar, Archana Praveen Dept. of Information Science and Engineering India Manipal Institute of Technology Manipal Academy of Higher Education Department of Computer Science & Engineering Manipal India

ISBN: (纸本)9798331540364

By providing enhanced accuracy and fluency compared to traditional approaches, Neural Machine Translation (NMT) has transformed the area of machine translation. In this research paper, the specific task of translating English to Hindi using NMT techniques is discussed. Creation and assessment of NMT systems developed for this language pair, considering the linguistic complexities and cultural aspects inherent in English and Hindi is examined. Leveraging large-scale parallel corpora and advanced neural network architectures, this work proposes novel approaches to improve translation quality and efficiency. Experimental results evaluated using standard metrics such as BLEU score, shows the efficacy of the proposed NMT models in accurately capturing the semantics and preserving the naturalness of the translated text. Additionally, this study discusses the implications of findings for cross-language communication and access to information, particularly in the context of the growing importance of Hindi in a globalized digital domain. Overall, this research contributes to develop neural machine translation for English to Hindi to a higher level and highlights the potential of NMT in facilitating multilingual communication and knowledge dissemination. © 2024 IEEE.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Credit Card Fraud Detection through LSTM-Based Sequential Analysis with Early Stopping 2

Enhancing Credit Card Fraud Detection through LSTM-Based Seq...

引用

2nd IEEE International Conference on Networking and Communications, ICNWC 2024

作者： Jhansi Ida, S. Balasubadra, K. Skandarsini, R.R. Lakshmi Narayanaa, T. RMK Engineering College Dept. of Computer Science and Business Systems Thiruvallur India RMD Engineering College Department of Information Technology Thiruvallur India

ISBN: (纸本)9798350365269

There is still a serious problem with credit card fraud in the world of financial transactions, requiring innovative solutions to effectively detect and halt illicit behavior. This research presents a unique method of detecting credit card fraud by strategically implementing early pausing in a Long Short-Term Memory (LSTM) neural network. Leveraging the sequential dependencies inherent in transaction data, the LSTM model demonstrates remarkable efficacy in discerning fraudulent from legitimate transactions. The early stopping mechanism ensures that the model's training halts at the optimal epoch, preventing over fitting and enhancing generalization. Our thorough analysis highlights the model's versatility by demonstrating a dynamic compromise between recall and accuracy throughout training. Practical implications include enhanced fraud detection accuracy, reduced false alarms, and real-time decision support for financial institutions. The model's adaptability and generalization make it a valuable asset in the ongoing battle against credit card fraud, contributing to a more secure financial environment. Future research directions may explore additional features and alternative architectures to further advance fraud detection capabilities. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Classification of Skin Lesions using PyQt5 and Deep Learning Methods 5

Classification of Skin Lesions using PyQt5 and Deep Learning...

引用

5th IEEE International Conference on Communications, information, Electronic and Energy Systems, CIEES 2024

作者： Koishiyeva, Dina Bissembayev, Alibek Iliev, Teodor Kang, Jeong Won Mukasheva, Assel Almaty University of Power Engineering and Telecommunications Dept. of Information Technology Almaty Kazakhstan Kazakh-British Technical University School of Information Technology and Engineering Almaty Kazakhstan University of Ruse Dept. of Telecommunications Ruse Bulgaria Korea National University of Transportation Department of Transportation System Engineering Uiwang-Si Korea Republic of

ISBN: (纸本)9798350352863

This study presents the OncoScan system designed to assist dermatologists in classifying skin diseases using an improved DenseNet121 model. The system was tested on the large HAM10000 dataset of over 10,000 images of skin lesions in seven categories. The DenseNet121 model, characterized by dense connectivity and transient layers, was compared with the InceptionV3 and EfficientNetB7 models. The results demonstrated the superiority of the DenseNet121 model, with an accuracy of 86.04% and an AUC of 96.32%. The OncoScan interface, developed using PyQt5, supports multilingual functionality including English, Russian, and Kazakh, and offers image processing tools. The system's ability to handle image processing and classification with ease makes it a valuable asset for dermatologic diagnostics. © 2024 IEEE.

关键词： denseNet121 pyqt5 skin disease transient layers

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled Remote-controlled Raft for Enhanced Water Quality Assessment 20

IoT-Enabled Remote-Controlled Raft for Enhanced Water Qualit...

引用

20th IEEE International Colloquium on Signal Processing and Its Applications, CSPA 2024

作者： Surasak, Thattapon Kitchat, Kotcharat Jiteurtragool, Nattagit King Mongkut's University Of Technology North Bangkok Faculty Of Applied Science Dept. Of Computer And Information Science Bangkok Thailand National Central University Dept. Of Computer Science And Information Engineering Taoyuan Taiwan

ISBN: (纸本)9798350382310

Water is vital for all life, serving as the foundation for plants and aquatic creatures and promoting abundance among all living beings. This study introduces an innovative approach by combining the Internet of Things (IoT) with advanced sensing techniques to assess water quality. The IoT-powered water quality testing raft has been developed to significantly enhance the monitoring capabilities. Equipped with sensors measuring key parameters such as turbidity, pH, and temperature, the raft provides a comprehensive understanding of water quality. Its GPS module enables real-time tracking and maintains location history, ensuring precise sampling. The collected data undergoes robust processing by a Raspberry Pi, ensuring integrity before being showcased on the Thingsboard. The system's uniqueness lies in its capacity to promptly issue alerts via LINE Notify upon detecting water quality abnormalities, ensuring timely intervention. This IoT-powered raft represents a paradigm shift in water quality assessment, characterised by its precision, remote capabilities, and user-focused approach. Practical applications have been demonstrated through real-world testing in a private lake in Cha-choengsao province, Thailand. The seamless integration of IoT into environmental monitoring marks a significant advancement in ensuring water quality and ecosystem health. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Advanced Deep Learning Integration for IoT Ecosystem for Content Classification 11

Advanced Deep Learning Integration for IoT Ecosystem for Con...

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Rao, Sudesh Gongada, Taviti Naidu Khan, Huma Anand, Rohit Sindhwani, Nidhi Gupta, Ankur Karnataka India Dept. of Operations Andhra Pradesh Visakhapatnam India Rungta College of Engineering and Technology Dept. of Cse Chhattisgarh Bhilai India Dept. of Ece New Delhi India Amity Institute of Information Technology Amity University UP Noida India Vaish College of Engineering Dept. of Cse Haryana Rohtak India

ISBN: (纸本)9798350350357

The incorporation of sophisticated deep learning methods into the IoT ecosystem has great potential for improving content categorization skills in different IoT applications. This abstract presents a summary of the approaches, difficulties, and possible advantages linked to this integration. In the domain of IoT, a substantial volume of data is produced by sensors, devices, and other sources, requiring effective techniques for handling and examining this data. Deep learning is a strong method for content categorization in IoT contexts because it can automatically build hierarchical representations of data. The paper explores the essential elements of incorporating deep learning into the IoT ecosystem for content classification. These components include acquiring and preprocessing data, selecting and training models, performing edge computing and inference, optimizing models, enabling continuous learning and adaptation, and addressing security and privacy concerns. Moreover, it emphasizes the need for a smooth interface with IoT platforms and apps to allow developers to fully use these enhanced capabilities. Developers may simplify the process of deploying and using deep learning models for AI-powered IoT applications by using APIs, SDKs, and libraries. The incorporation of sophisticated deep learning methods into the IoT ecosystem for content categorization can transform a range of IoT applications, such as smart cities, industrial automation, healthcare, and others. This connection facilitates intelligent decision-making, automation, and optimization, hence creating a more efficient, responsive, and intelligent IoT infrastructure. © 2024 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

A study of vibration and current data characteristic analysis for motor mechanical fault level determination by deep learning

引用

Transactions of the Korean Institute of Electrical Engineers 2021年第10期70卷 1509-1516页

作者： Han, Ji-Hoon Park, Sang-Uk Hong, Sun-Ki Dept. of System and Control Engineering Hoseo University Korea Republic of Dept. of Information Control Engineering Hoseo University Korea Republic of

In the classic motor fault diagnosis system, a method of analyzing the differences between the normal and collected state signals of the motor to be diagnosed was used and the method can diagnose only the limited situations because the diagnosis is based on the frequency of the mechanical failure. In order to compensate for this, some studies on a system that performs more specialized fault diagnosis through deep learning algorithms were carried out. However, the level of failure cannot be determined because these studies consider only the signals that have a great influence on motor operation. To solve this problem, the characteristics of vibration and current signals are analyzed to develop a deep learning algorithm suitable for fault level determination. The characterized signals are used for fault diagnosis and prediction. Fault diagnosis based on vibration signal is carried out through DT-CNN (Decision Tree Convolutional Neural Network). In addition, it is checked whether the current signal in the initial failure state, which is relatively insensitive to failure, can be classified through a deep learning algorithm. The proposed data utilization performance was evaluated through an induction motor and the analyzed signal-based fault diagnosis system is expected to enable a more precise diagnosis compared to the existing system. Copyright © The Korean Institute of Electrical Engineers.

关键词： Failure analysis

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：