检索结果-内蒙古大学图书馆

2023 IEEE International Conference on computer, Information, and Telecommunication Systems, CITS 2023

作者： Nadeem, Adnan Ashraf, Muhammad Mehmood, Amir Siddiqui, Muhammad Shoaib Almoamari, Hani Abbasi, Qammer H. Islamic University of Madinah Faculty of Computer and Information Systems Madinah42351 Saudi Arabia Federal Urdu University of Arts Science and Technology Department of Physics Karachi75300 Pakistan Sir Syed University of Engineering and Technology Department of Computer Science and Information Technology Karachi75300 Pakistan James Watt School of Engineering University of Glasgow Glasgow United Kingdom

ISBN: (纸本)9798350336092

The Kingdom of Saudi Arabia is one of the world's leading fresh date producers. Identifying damaged date palm trees on the farm is important for saving water and stopping the spread of pest which has caused the damage. In this paper, we aim to evaluate the performance of IoT-based thermal image camera input for the automatic detection of damaged trees in a Date Tree farm. The thermal images will be obtained by an IoTbased thermal camera attached to UAV. Then the temperature histogram vector will be generated which will be fed to the SVM for identification of the damaged tree. The system will raise the alarm along with the coordinates of the damaged tree for the farmer to proactively deal with the issue. The initial results of the tested scenario are encouraging for its detailed implementation in the future. © 2023 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-based Characterization of COPD Progression from Spirometry Data 10

Machine Learning-based Characterization of COPD Progression ...

引用

10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and computer engineering, UPCON 2023

作者： Varshney, Neeraj Bordoloi, Dibyhash Michaelson, Jacob Laxminarayanamma, K. Yadav, Vijay Kumar Srivastava, Amit Gla University Department of Computer Engineering and Applications Mathura India Computer Science & Engineering Graphic Era Deemed to Be University Uttarakhand Dehradun India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Institute of Aeronautical Engineering Department of Information Technology Telangana Hyderabad India Lloyd Institute of Engineering & Technology Greater Noida India Lloyd Law College Greater Noida India

ISBN: (纸本)9798350382471

This study represents a substantial advance in regard to the application of machine learning to the treatment of chronic obstructive pulmonary disease (COPD). Recurrent neural networks (RNNs) incorporating Long Short-Term Memory (LSTM) units were used in the study, which was centered on the interpretivism concept, to mimic the time-dependent aspect of COPD development. During training, the model's prediction of COPD development was optimized, significantly outperforming current diagnostic techniques. Although encouraging, the study recommends increased data gathering, and multidisciplinary cooperation, including a diversification of data sources, particularly unstructured data. To fully utilize machine learning in the management of COPD, future efforts should look into real-time patient data integration, and telemedicine applications, including user-friendly technologies. © 2023 IEEE.

关键词： Chronic Obstructive Pulmonary Disease (COPD) data integration Long Short-Term Memory (LSTM) machine learning recurrent neural networks telemedicine

来源：评论

学校读者我要写书评

暂无评论

GA-Net: Gated Attention Mechanism Based Global Refinement Network for Image Inpainting 29

GA-Net: Gated Attention Mechanism Based Global Refinement Ne...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Qiu, Ran Zhao, Shengrong Liang, Hu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9798350330717

Underwater images are often affected by problems such as light attenuation, color distortion, noise and scattering, resulting in image defects. A novel image inpainting method is proposed to intelligently predict and fill damaged areas for complete and continuous visualization of the image. First, in order to effectively solve the problem of color distortion caused by light refraction in underwater environments, the improved gated attention mechanism is used. This mechanism improves the local details by learning and weighting the important features of the image. Second, gated convolution automatically determines the degree of restoration for each pixel based on local features of the original image. It eliminates distractions such as low contrast and scattering, retaining more original detailed information. By doing so, image inpainting techniques improve the quality and visualization of underwater images. © 2023 IEEE.

关键词： Gated convolution Image inpainting Underwater images

来源：评论

学校读者我要写书评

暂无评论

An Optimized Deep Learning Model for Emotion Classification in Tweets

引用

computers, Materials & Continua 2022年第3期70卷 6365-6380页

作者： Chinu Singla Fahd NAl-Wesabi Yash Singh Pathania Badria Sulaiman Alfurhood Anwer Mustafa Hilal Mohammed Rizwanullah Manar Ahmed Hamza Mohammad Mahzari Department of Computer Science and Engineering Thapar Institute of Engineering and TechnologyPatialaIndia Department of Computer Science King Khalid UniversityMuhayel AseerKingdom of Saudi Arabia Faculty of Computer and IT Sana’a UniversitySana’aYemen Department of Computer Science College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversitySaudi Arabia Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlkharjSaudi Arabia Department of English College of Science&HumanitiesPrince Sattam bin Abdulaziz UniversityAlkharjSaudi Arabia

The task of automatically analyzing sentiments from a tweet has more use now than ever due to the spectrum of emotions expressed from national leaders to the average *** this data can be critical for any *** are often expressed with different intensity and topics which can provide great insight into how something affects *** analysis in Twittermitigates the various issues of analyzing the tweets in terms of views expressed and several approaches have already been proposed for sentiment analysis in *** used for analyzing tweet emotions are also briefly presented in literature survey *** this paper,hybrid combination of different model’s LSTM-CNN have been proposed where LSTMis Long Short TermMemory andCNNrepresents ConvolutionalNeural ***,the main contribution of our work is to compare various deep learning and machine learning models and categorization based on the techniques *** main drawback of LSTM is that it’s a timeconsuming process whereas CNN do not express content information in an accurate way,thus our proposed hybrid technique improves the precision rate and helps in achieving better *** step of our mentioned technique is to preprocess the data in order to remove stop words and unnecessary data to improve the efficiency in terms of time and accuracy also it shows optimal results when it is compared with predefined approaches.

关键词： Meta level features lexical mistakes sentiment analysis count vector natural language processing deep learning machine learning naive bayes

来源：评论

学校读者我要写书评

暂无评论

CARM:Context Based Association Rule Mining for Conventional Data

引用

computers, Materials & Continua 2021年第9期68卷 3305-3322页

作者： Muhammad Shaheen Umair Abdullah Faculty of Engineering&Information Technology Foundation UniversityIslamabadPakistan Department of Computer Science Barani Institute of Information TechnologyRawalpindiPakistan

This paper is aimed to develop an algorithm for extracting association rules,called Context-Based Association Rule Mining algorithm(CARM),which can be regarded as an extension of the Context-Based Positive and Negative Association Rule Mining algorithm(CBPNARM).CBPNARM was developed to extract positive and negative association rules from Spatiotemporal(space-time)data only,while the proposed algorithm can be applied to both spatial and non-spatial *** proposed algorithm is applied to the energy dataset to classify a country’s energy development by uncovering the enthralling interdependencies between the set of variables to get positive and negative *** association rules related to sustainable energy development are extracted by the proposed algorithm that needs to be pruned by some pruning *** context,in this paper serves as a pruning measure to extract pertinent association rules from non-spatial *** Probability Increment Ratio(CPIR)is also added in the proposed algorithm that was not used in *** inclusion of the context variable and CPIR resulted in fewer rules and improved robustness and ease of ***,the extraction of a common negative frequent itemset in CARM is different from that of *** rules created by the proposed algorithm are more meaningful,significant,relevant and *** accuracy of the proposed algorithm is compared with the Apriori,PNARM and CBPNARM *** results demonstrated enhanced accuracy,relevance and timeliness.

关键词： Association rules context CBPNARM non-spatial data CPIR support confidence interestingness

来源：评论

学校读者我要写书评

暂无评论

Recognition of Wh-Question Sign Gestures in Video Streams using an Attention Driven C3D-BiLSTM Network

引用

Procedia computer science 2024年 235卷 2920-2931页

作者： Arnab Dey Samit Biswas Dac-Nhuong Le Dept. of Computer Science and Technology Indian Institute of Engineering Science and Technology Shibpur Howrah 711103 India Faculty of Information Technology Haiphong University Haiphong 180000 Vietnam

Human sign language is a visual and gestural means of communication used by people with hearing impairments to interact with others. It has the potential to enable interaction between individuals who struggle with verbal communication and those who lack the essential proficiency to comprehend sign language. Wh-questions constitute a substantial portion of daily sign language interactions. Automatic recognition of Wh-question words in sign language, encompassing interrogative words, has received limited attention in gesture recognition. In this context, a novel dataset named the American Question Sign Video dataset (AQSVd) has been introduced as a significant contribution. Recognizing Wh-question signs in video streams empowers individuals to effectively convey messages through hand movements and gestures, fostering inclusivity and accessibility in communication for deaf and hearing-impaired individuals. The paper proposes a Deep Convolutional-3D BiLSTM Multi-head Attention network for recognizing American Wh-Question word sign gestures in video streams. Incorporating Multi-head attention in the proposed model enhances its ability to capture intricate spatial and temporal features, essential for accurate gesture recognition. The proposed model is thoroughly evaluated across a range of datasets, such as INCLUDE50, WLASL-100, and our AQSVd dataset, achieving remarkable results. Specifically, our model demonstrated an outstanding 98.91% validation accuracy on the AQSVd dataset. The C3D-BiLSTM MHAttention model outperforms other state-of-the-art models, demonstrating its superiority in sign language recognition tasks. The proposed dataset and C3D-BiLSTM Multi-head Attention model contribute significantly to this field, offering potential benefits in education, human-robot interaction, and overall communication for the hearing-impaired community.

关键词： Gesture Recognition Wh-Question American Sign Language Video Streams Multi-head Attention C3D-BiLSTM

来源：评论

学校读者我要写书评

暂无评论

Key Logger for Recording the Keystroke of the Targeted Machine

Key Logger for Recording the Keystroke of the Targeted Machi...

引用

Computing and Data science (ICCDS), International Conference on

作者： S. Gnanavel M. Sreekrishna P. Shivaramakrishnan R. Yaswanth G.S. Gopika S. Supriya Dept of Computing Technologies Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur India Dept of Computer Science Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (数字)9798350365337

ISBN: (纸本)9798350365344

In the recent digital era security has become more challenging. There is a plethora of ways to find solution to ensure monitor the system and provide required security. Key logger is one of the cyber attacks which record the key strokes of the targeted systems or devices from the host person. In other words, the program retrieves vital information such as login credentials, passwords and other sensitive information. There are many types of key logger, software key loggers is one of the key logger type which use software applications to collect the information from the targeted machine to host machine. It is indeed difficult to trace the software key logger because it runs in background without any noticeable signs. However, there are some signs like network traffic and unexpected activity. This paper concentrates on the implementation of key logger and its observation using python file, JavaScript file and etc.

关键词： computer hacking Telecommunication traffic Passwords Software Recording Security Servers

来源：评论

学校读者我要写书评

暂无评论

Comparison Between Bi-Directional LSTM And Transfer Learning in Correcting Typing Errors on Twitter Social Media Posts 11

Comparison Between Bi-Directional LSTM And Transfer Learning...

引用

11th International Conference on Cyber and IT Service Management, CITSM 2023

作者： Lubis, Arif Ridho Prayudani, Santi Hamzah, Muhammad Luthfi Politeknik Negeri Medan Department of Computer Engineering and Informatics Medan Indonesia Universitas Islam Negeri Sultan Syarif Kasim Riau Faculty of Science and Technology Pekanbaru Indonesia

ISBN: (纸本)9798350305968

Typing errors are a behavior that often occurs in communication via short messages or posts on social media platforms. In communicating on social media, many individuals without realizing it often make typing errors that can affect the meaning of sentences. This research will apply a model that can check typing errors using Bi-Directional LSTM and transfer learning which results in the Bi-Directional LSTM model achieving an accuracy of 78% after being trained for 20 epochs with a batch size of 64. On the other hand, the transfer learning model achieves an accuracy of 80% with the same epoch and batch size settings. Furthermore, when the Bi-Directional LSTM model was set with 20 epochs and batch size 64, the accuracy increased to 83%, while the transfer learning model achieved 87% accuracy. Finally, with 20 epochs and a batch size of 64, the Bi-Directional LSTM model achieved 87% accuracy, while the transfer learning model achieved an impressive accuracy of 93%. © 2023 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Coordinated Virtual Inertial Control of DFIG with BESS for Frequency Support 18

Coordinated Virtual Inertial Control of DFIG with BESS for F...

引用

18th International Conference on Intelligent Systems and Knowledge engineering, ISKE 2023

作者： Chen, Shengyu Zhang, Guidong Yu, Samson Shenglong Zhang, Yun Li, Zhong School of Automation Guangdong University of Technology Guangzhou China School of Engineering Deakin University Melbourne Australia FernUniversitaet in Hagen Faculty of Mathematics and Computer Science Hagen Germany

ISBN: (纸本)9798350318401

As the installed capacity of wind turbines increases, the overall inertia of the system decreases, which reduces the ability of the system to support the frequency. Due to the tendency to operate in a maximum power tracking state and the lack of an active power reserve, doubly-fed induction generator (DFIG), a type of the current popular wind turbine, are unable to efficiently utilize the rotor kinetic energy to engage in frequency regulation in the face of grid frequency variations. To address this issue, virtual inertia control (VIC) is introduced to release the kinetic energy of the DFIG provide dynamic frequency support to the grid. In addition, a properly designed control strategy for the battery energy storage system (BESS) can store the excess energy of the DFIG system and release it as needed to assist frequency regulation. In this paper, we propose a coordinated control strategy for virtual inertial regulation with BESS for DFIG frequency support. We design a charge-discharge switching control strategy for the BESS. Time-domain simulations are conducted to verify the effectiveness of the proposed method in suppressing frequency disturbances. © 2023 IEEE.

关键词： Asynchronous generators

来源：评论

学校读者我要写书评

暂无评论

Implementation and Evaluation of a Deep Neural Network for Spam Detection: An Empirical Study of Accuracy and Efficiency

Implementation and Evaluation of a Deep Neural Network fo...

引用

International Symposium on Innovative and Interdisciplinary Applications of Advanced Technologies, IAT 2023

作者： Varga, Luka Livada, Časlav Baumgartner, Alfonzo Šojo, Robert Faculty of Electrical Engineering Computer Science and Information Technology Osijek Josip Juraj Strossmayer University in Osijek Kneza Trpimira 2B Osijek31000 Croatia

ISBN: (纸本)9783031430558

The problem of spam emails is a widespread issue that creates a lot of inconvenience for individuals and organizations. According to statistics, approximately 84% of emails received on a daily basis are recognized as spam. This paper aims to present a solution to this problem by proposing the use of a neural network capable of identifying and classifying potential spam emails. The neural network was developed using Python, TensorFlow, Keras, Google Colaboratory, and Jupyter. These tools were chosen because they are widely used and well-suited for the task of creating a deep learning model. The results of the network were found to be satisfactory, with an accuracy rate of approximately 99%. This is comparable to the results achieved by large companies such as Google and Yahoo! who are known to use similar methods to combat spam. Overall, this paper demonstrates that neural networks can be a powerful tool for addressing the problem of spam emails and that the proposed solution has the potential to improve the efficiency and effectiveness of spam filtering for individuals and organizations. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Electronic mail

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：