检索结果-内蒙古大学图书馆

2023 International Conference on Artificial Intelligence and Smart Communication, AISC 2023

作者： Geetha, S. Shetty, Sahana Deemed-to-be University Faculty of Engineering and Technology Jain Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350322309

The purpose of a brain-computer interface, also known as a BCI, is to create a communication channel that converts human intention into a control signal for an output device using a brain signal, such as an electroencephalogram (EEG). In addition, artefacts are undesired potentials that helps to process the signals (EEG), with the majority of originate outside signal of the cerebral cortex. Regrettably, they have the ability to alter the form of neurological phenomena that is used to operate a BCI device. They also carry the risk of inadvertently and it can lead to the device which is being controlled in a manner that was not intended. As a result, it is necessary to steer clear of, disregard, or get rid of artefacts in the recordings of brain signals. The origin of artefacts can be traced back to both physiological and non-physiological processes. The different signals are monitored and compared for the better conclusion. © 2023 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Improving the Performance of the K-Nearest Neighbors Algorithm with Parallelization in Dask 20

Improving the Performance of the K-Nearest Neighbors Algorit...

引用

20th CSI International Symposium on Artificial Intelligence and Signal Processing, AISP 2024

作者： Rezanejad, Amin Danesh, Amir Seyed University of Guilan Computer Engineering Rasht Iran University of Guilan Faculty of Technology and Engineering East of Guilan Rudsar Vajargah Iran

ISBN: (纸本)9798350383942

This study implements the K-Nearest Neighbors (K-NN) algorithm for classification tasks using the Python programming language in both serial and parallel modes. The execution times are measured and compared between the serial and parallel implementations, demonstrating a performance improvement in the parallel execution. The research aims to emphasize the significance of parallelization and computational efficiency enhancement in machine learning algorithms, specifically focusing on K-NN, using Python and tools such as DASK. Such studies are valuable for enhancing the performance of tasks related to data scientists and data analysts, benefiting from the accessibility and ease of parallelization offered by Python and related frameworks. © 2024 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Lunar Impact Crater Detection Based on Yolo V7 Using Muti-source Data

Lunar Impact Crater Detection Based on Yolo V7 Using Muti-so...

引用

2023 IEEE International Conference on Control, Electronics and computer technology, ICCECT 2023

作者： Zhu, Jionghao Liang, Jiarui Tian, Xiaolin Macau University of Science and Technology School of Computer Science and Engineering/ Faculty of Innovation Engineering China

ISBN: (纸本)9798350399028

This paper demonstrates that Yolo V7, the latest version of the single-stage neural network Yolo, has good recognition of lunar impact craters on the Lunar CCD data and DEM data provided by the LROC camera which carried by NASA's Lunar Reconnaissance Orbiter (LRO) used for the experiments. The results show that Yolo V7 has good results in detecting lunar impact craters based on two data types. The best identification results are based on CCD data exceeding 70%. © 2023 IEEE.

关键词： NASA

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Techniques for Diabetes Prediction: A Comparative Analysis

Machine Learning Techniques for Diabetes Prediction: A Compa...

引用

2023 International Conference on Sustainable Computing and Smart Systems, ICSCSS 2023

作者： Mythili, J. Surendhar, T. Suryaprakash, P. Suresh Kumar, K. Faculty of Computer Science and Engineering K S Rangasamy College of Technology Department of Computer Science and Engineering Tiruchengode India Computer Science and Engineering K S Rangasamy College of Technology Department of Computer Science and Engineering Tiruchengode India

ISBN: (纸本)9798350333602

As the prevalence of diabetes mellitus rises, more families are being impacted. Most diabetics don't know much about their health situation or the risks they face before getting a diagnosis. A unique data mining-based method was suggested for the prediction of type 2 diabetes mellitus (T2DM) in this study. The accuracy and robustness of the prediction model are the primary priorities, ensuring flexibility so that it may be used to other datasets. The model is made up of two parts: the enhanced Logistic Regression with Multilayer Perception (LRMLP) and Naïve Bayes (NB) method with a set of preprocessing techniques. To compare the findings with those of other studies, the Diabetes Dataset for Pima Indians was used with the Environment for Knowledge Analysis toolkit. According to the findings, the model's prediction accuracy is higher than that of earlier research. Additionally, this approach guarantees that the dataset quality is enough. The system was applied to two more diabetes datasets in order to assess its effectiveness further. Both research findings show strong performance. The model is shown to be helpful for managing diabetic health in a realistic manner as a result. For experimental analysis, data from the University of California, Irvine's (UCI) machine learning repository's Pima Indian Diabetes Database (PIDD) is used. These classification algorithms' performance is evaluated using a variety of statistical metrics, including sensitivity (recall), precision, F-score, and accuracy. The measurement of correctly and erroneously classified cases is called accuracy. According to the testing findings, LR-MLP outscored other classification algorithms and provides the maximum accuracy of 96.3%. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Application of Deep Learning in Lunar Volcanic Dome Identification 23

Application of Deep Learning in Lunar Volcanic Dome Identifi...

引用

8th International Conference on Multimedia and Image Processing, ICMIP 2023

作者： Sun, Chen Faculty of Innovation Engineering School of Computer Science and Engineering Macau University of Science and Technology China

ISBN: (纸本)9781450399586

Lunar domes have always been one of the important windows to understand lunar volcanic activity, however traditional identification methods for geological domes are expensive, so this study attempts to establish an automatic identification method for lunar volcanic domes. Given that no previous research in this area has attempted to automate the identification of lunar volcanic domes, our team attempted to automate the process for the first time. To achieve the purpose of this research, the researchers first obtained the dome coordinates from the list of known lunar domes and intercepted the data we needed from the corresponding coordinates on the CCD and DEM moon pictures. Subsequently, the researchers screened the data to find data with more obvious features and used these data to train 9 mainstream image recognition models and compared their accuracy rates to verify the feasibility of this study. Finally, the researchers counted the mAP and AP (IoU=0.5) of the nine models and found that the highest of them could reach 0.64 (mAP) and 0.74 (AP). Therefore, this study can conclude that an automated method for identifying lunar volcanic domes should be feasible. © 2023 ACM.

关键词： Domes

来源：评论

学校读者我要写书评

暂无评论

A 2-Bit Beam-Steering Coding Array With High Beam Pointing Accuracy and Side Lobe Level For Wide-Angle Beam Scanning

引用

IEEE Internet of Things Journal 2025年第13期12卷 23434-23443页

作者： Xu, Jifei Wang, Kai Lu, Yunlong Mei, Lin Wang, Ye Ding, Chaofeng Yu, Ming Pengcheng Laboratory Shenzhen518000 China Southern University of Science and Technology Shenzhen518000 China Ningbo University Faculty of Electrical Engineering and Computer Sciences Zhejiang Ningbo315211 China

We present a 2-bit coding array that features high beam-pointing accuracy and side-lobe-level (SLL) performance for wide-angle beam scanning. By symmetrically exciting a circular ring patch antenna and integrating a 90° phase shifter into the feeding line, a 2-bit characteristic is obtained. Four positive-intrinsic-negative (PIN) diodes are deployed in each antenna element and are controlled by a field-programmable gate array (FPGA) for switching the states of PINs. The 2-bit circular ring patch element is subsequently used for building a 1×12 array. Apart from introducing a set of initial phases, we add initial amplitudes to the array for the first time to further improve the array performance. Both initial phases and amplitudes are obtained from the invasive weed optimization (IWO) algorithm by setting the goals of desired beam pointing accuracy and SLL performance. In addition, the active element pattern (AEP) that accounts for the mutual coupling between elements is used in the optimization process to provide an accurate array response. The simulated and measured results agree well, and both show that the proposed array can achieve a scanning range of ± 50° with a beam pointing error (BPE) within ±1°, yet the simulated maximum SLL (MSLL), 9.2 dB, deteriorates to 8.3 dB in the measurement. The measured peak aperture efficiency is 43.2% with a peak gain as 13.2dBi. The proposed array, which features low cost, low profile, and low power consumption, is well suited for intelligent Internet of Things (IoT) applications where space and power are limited. © 2014 IEEE.

关键词： Slot antennas

来源：评论

学校读者我要写书评

暂无评论

Harnessing Long Short Term Memory Networks for Stock Market Forecasts

Harnessing Long Short Term Memory Networks for Stock Market ...

引用

2024 International Conference on engineering and Computing, ICECT 2024

作者： Faheem, Alishba Arshad, Usama Ghulam Ishaq Khan Institute of Engineering Sciences and Technology Faculty of Computer Science and Engineering Department of Artificial Intelligence Topi Pakistan

ISBN: (纸本)9798350349719

Stock market trend prediction is a classical re-gression problem with effects on stock exchange. This research is presenting a detailed exploration of how Long Short Term Memory (LSTM) networks may be used for predicting stock market trends. The LSTM model was employed instead of the conventional Recurrent Neural Networks (RNNs), to learn from historical financial data. The study examines the operations of the LSTM model and the optimization of hyper parameters that lead to accurate prediction outcomes from the given dataset. Our model gave encouraging results that underlined the LSTM model's prowess in capturing intricate temporal dependencies in data. The model's result were in a low Root Mean Square Error (RMSE) score and an impressively high accuracy level that were good indicators of the model's adaptability at trend identification. Our study amplifies the need for advanced machine learning algorithms like LSTM that increase prediction accuracy while offering insights into decision-making processes for both investors and financial analysts at the same time. Further, it also hints at the potential of deep learning within the stock market. The paper concludes by discussions on all possible improvements to the existing model, future directions, and how incorporating additional data types can increase our predictive accuracy. This research primarily underscores the significant role LSTM plays in deciphering complex financial data trends accurately. © 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

MRI techniques using image processing Brain Tumor Detection

MRI techniques using image processing Brain Tumor Detection

引用

2023 International Conference on Artificial Intelligence and Smart Communication, AISC 2023

作者： Mahesh, T.R. Geetha, G. Deemed-to-be University Faculty of Engineering and Technology Jain Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350322309

A brain tumor develops when cells in the brain divide in an abnormal way that is not controlled by the body. This results in the growth of the tumor. Manual dissection of brain tumors identified by MRI is a process that is both necessary and time-consuming. However, it is also an extremely important step. Identifying the precise location of a brain tumor as well as its size is of the utmost importance when it comes to the efficient screening of patients and the treatment of tissue. Because of this, a proper diagnosis of a brain tumor needs to be carried out with as much promptness and accuracy as is humanly *** detection of a brain tumor using imaging technology for medical purposes is thought to be a challenging task because of the nature of the disease being investigated. The goal of this study is to provide a method that will assist in the treatment of brain tumors. This strategy will make use of the covert operations of VGG19 as well as the process of transfer learning. The approach that has been suggested will be improved throughout the course of this inquiry, with the ultimate objective being the development of a hybrid methodology. Utilizing the VGG19 and Transfer learning approaches, the purpose of this study is to develop an algorithm for the identification of tumors using magnetic resonance imaging (MRI). These methods have been applied to a wide variety of data collections that pertain to patients. They have the ability to organize their cooling effect on the final portion of the body tissues that are associated with the tissues, while at the same time keeping better the borders between the various components of the ti © 2023 IEEE.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Healthcare Monitoring System 1

IoT-Based Healthcare Monitoring System

引用

1st International Conference on Emerging Technologies for Dependable Internet of Things, ICETI 2024

作者： Al-Hadi, Marwa Abdulrahman Al-Gaphari, Ghaleb Hamoud Al-Baltah, Ibrahim Ahmed Julian, Francisco Bacallao Al-Hadi, Ahmed Abdulrahman Department of Computer Science Faculty of Computer Science and IT Sana’a University Sana’a Yemen Department of Information Technology Faculty of Computer Science and IT Sana’a University Sana’a Yemen Faculty of Science and Engineering Al-Hikma University Sana’a Yemen Cardiac-Center Military Hospital Yemen Department of Science and Technologies Faculty of Engineering and Technology Mohamed Boudiaf University M'sila Algeria Department of Industrial Electronic and Automatic Engineering Faculty of Higher Polytechnic Technology Burgos University Burgos Spain

ISBN: (纸本)9798331533557

In an era when healthcare was becoming increasingly crucial, many developing nations, including Yemen, struggled to provide basic medical services. Nearly half of Yemen's population lacked access to adequate healthcare, with the situation being even more dire in rural and remote areas. While sectors such as industry, agriculture, and environmental science rapidly embraced technological advancements, healthcare systems in these regions lagged, with limited research addressing affordable and accessible solutions. This gap was further highlighted by the global healthcare crisis and the urgent need for innovative, cost-effective approaches. In response, this study outlined the creation and deployment of a cost-effective health monitoring system utilizing Internet of Things (IoT) technology to address these challenges. The system was designed to monitor vital signs, specifically heart rate (HR), using an Arduino Uno and ECG sensor, at a meager total cost of $27.25. It provided real-time monitoring for situations requiring immediate intervention. Power consumption tests demonstrated that the system operated efficiently, consuming between 1.061 and 1.35 watts, making it practical and affordable. Additionally, the potential integration of deep learning techniques promises to enhance the system's accuracy and efficiency. Although this study focused on IoT-based health monitoring, its potential extended beyond this, offering broader implications for future healthcare technology solutions. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

A Comparison and Evaluation of Named Entity Recognition Methods in Thai Traditional Medicine Texts 13

A Comparison and Evaluation of Named Entity Recognition Meth...

引用

13th International Electrical engineering Congress, iEECON 2025

作者： Phungjununt, Warodom Lee, Wilaiporn Prayote, Akara Pipanmekaporn, Luepol Srisomboon, Kanabadee King Mongkut's University of Technology North Bangkok Faculty of Engineering Department of Electrical and Computer Engineering Bangkok10800 Thailand King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Computer and Information Science Bangkok10800 Thailand

ISBN: (纸本)9798331543952

The knowledge extraction and transliteration processes for the Thai traditional medicine documents requires experts to extract information from the textbook and spend a plenty of time. To reduce the complexity of these processes, the named entity recognition (NER) from the machine learning principle is applied to extract the key information from the document. In this work, three NER models including, CRFSuite, Bi-LSTM-CRF, and pre-trained model (WangchanBERTa) are considered the accuracy of each model of NER for the Thai traditional documents. After the testing process, the experimental results show that CRFSuite model is the most computationally efficient model and deliver high precision and recall. Moreover, CRFSuite model has the highest scores of each entity. While the accuracy of the WangchanBERTa model is the highest and faster convergence in the training process. Although the results from the Bi-LSTM-CRF model provide moderate accuracy, the Bi-LSTM-CRF can detect the common entities higher than other models. © 2025 IEEE.

关键词： Natural language processing systems

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：