检索结果-内蒙古大学图书馆

15th IFIP Wireless and Mobile Networking Conference, WMNC 2024

作者： Bouras, Christos Diasakos, Damianos Kokkinos, Vasileios Prodromos, Nikolaos Gkamas, Apostolos Pouyioutas, Philippos University of Patras Computer Engineering and Informatics Department Patras Greece University of Ioannina Department of Chemistry Ioannina Greece University of Nicosia Computer Science Department Nicosia Cyprus

ISBN: (纸本)9783903176683

The integration of drone technology with 5G networks presents novel opportunities for enhancing wireless communication systems. This paper explores the application of beamforming optimization techniques in dynamic environments, specifically focusing on moving drones in a simulated environment based on the DeepMIMO O1 scenario. By leveraging the unique properties of the O1 drone setup of DeepMIMO simulation environment, which simulates realistic urban mobility patterns at millimeter-wave (mmWave) frequencies, we propose a novel beamforming algorithm designed to optimize the signal quality and stability in highly mobile aerial networks. Key performance metrics used in this study include Signal-to-Noise Ratio (SNR), battery consumption, and power consumption of both the drones and the base station. Our findings indicate that the adaptive beamforming algorithm not only enhances the SNR and reduces power consumption but also optimizes battery usage compared to conventional beamforming methods. This study enhances the understanding of mmWave beamforming dynamics in aerial scenarios but also lays the groundwork for future advancements in drone-based communication networks. © 2024 IFIP.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

DeBERTa-GRU: Sentiment Analysis for Large Language Model

引用

computers, Materials & Continua 2024年第6期79卷 4219-4236页

作者： Adel Assiri Abdu Gumaei Faisal Mehmood Touqeer Abbas Sami Ullah Department of Informatics for Business College of BusinessKing Khalid UniversityAbha61421Saudi Arabia Department of Computer Science College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia School of Electrical and Information Engineering Zhengzhou UniversityZhengzhou450001China Department of Computer Science and Technology Beijing University of Chemical TechnologyBeijing100029China Department of Computer Science Government College University FaisalabadFaisalabadPunjab38000Pakistan

Modern technological advancements have made social media an essential component of daily *** media allow individuals to share thoughts,emotions,and *** analysis plays the function of evaluating whether the sentiment of the text is positive,negative,neutral,or any other personal emotion to understand the sentiment context of the *** analysis is essential in business and society because it impacts strategic *** analysis involves challenges due to lexical variation,an unlabeled dataset,and text distance *** execution time increases due to the sequential processing of the sequence ***,the calculation times for the Transformer models are reduced because of the parallel *** study uses a hybrid deep learning strategy to combine the strengths of the Transformer and Sequence models while ignoring their *** particular,the proposed model integrates the Decoding-enhanced with Bidirectional Encoder Representations from Transformers(BERT)attention(DeBERTa)and the Gated Recurrent Unit(GRU)for sentiment *** the Decoding-enhanced BERT technique,the words are mapped into a compact,semantic word embedding space,and the Gated Recurrent Unit model can capture the distance contextual semantics *** proposed hybrid model achieves F1-scores of 97%on the Twitter Large Language Model(LLM)dataset,which is much higher than the performance of new techniques.

关键词： DeBERTa GRU Naive Bayes LSTM sentiment analysis large language model

来源：评论

学校读者我要写书评

暂无评论

An Integrated Platform for Educational and Research Management Using Institutional Digital Resources 3rd

An Integrated Platform for Educational and Research Manageme...

引用

3rd International Conference on Novel and Intelligent Digital Systems, NiDS 2023

作者： Chytas, Konstantinos Tsolakidis, Anastasios Triperina, Evangelia Karanikolas, Nikitas N. Skourlas, Christos University of West Attica department of Informatics and Computer Engineering Athens12243 Greece

ISBN: (纸本)9783031441455

Currently, universities not only offer technologically enhanced education and automated processes, but also provide a wide spectrum of online services, especially after COVID19. We propose e-EDURES, an integrated platform for educational and research management in tertiary education to further benefit the stakeholders by relying on the data of university online services to enable strategic planning and decision making. More specifically, in this paper, we focus on the presentation of an interactive system that utilizes the data derived by university’s synchronous and asynchronous e-learning services to gain insights about the educational performance of the students. It employs Educational Data Mining techniques to ultimately boost the educational process, by assessing the previous performance, monitoring the provided services and predicting future performance of the students, in order to avoid potential pitfalls. The proposed solution merges the current advances in smart education and educational data mining to offer an advanced and updated version of online services provided by universities that respond better to the current needs in academia. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Gamification Interaction Design for Membatik Application in Mixed Reality 25

Gamification Interaction Design for Membatik Application in ...

引用

25th International Electronics Symposium, IES 2023

作者： Hanifati, Kirana Rante, Hestiasari Sukaridhoto, Sritrusta Politeknik Elektronika Negeri Surabaya Department of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350314731

Batik is an Indonesian traditional craft that has high artistic value. Indonesian society, especially the younger generation such as students, plays an important role in preserving Indonesian culture such as batik to ensure it remains attached to Indonesia and does not disappear. However, the interest and enthusiasm of students in preserving batik is still lacking, so new strategies are needed to increase their interest and enthusiasm in preserving batik. One of the new strategies is utilizing immersive technology such as Mixed Reality (MR) with the implementation of gamification interaction to enhance students' interest because learning is done as if playing a game. MR technology can provide users with a more complex experience by using MR glasses. The Membatik application is a batik-making simulation application using MR technology where users can simulate with hand gestures and there are quizzes at each stage with a point system as a gamification implementation. The application has been tested with initial user testing. During the testing phase, users were asked to try the application and provide feedback on the overall user experience. The outcomes demonstrated that the MR application might raise students' interest in and involvement in their study. The users also found the quiz feature to be interactive and challenging, which added to their learning experience. By combining gamification elements with MR technology, the application has the potential to improve learning outcomes and increase student motivation. © 2023 IEEE.

关键词： Mixed reality

来源：评论

学校读者我要写书评

暂无评论

Scenario-Based Cross-Site Request Forgery (CSRF) Attack Simulation 6

Scenario-Based Cross-Site Request Forgery (CSRF) Attack Simu...

引用

6th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2024

作者： Saleh, Taj Malkawi, Malek Elgammal, Ziad Calayir, Arzu Kilitci Alhajj, Reda Department of Computer Engineering Istanbul Medipol University Istanbul Turkey Department of Computer Engineering Marmara University Istanbul Turkey Department of Computer Science University of Calgary Alberta Canada Department of Heath Informatics University of Southern Denmark Odense Denmark

ISBN: (纸本)9798331529987

In the dynamic realm of technology, where new advancements consistently transform our online interactions, maintaining the security of web apps is crucial. This study explores the area of web security by investigating Cross-Site Request Forgery (CSRF) vulnerabilities in great detail. We untangle the complexities of CSRF attacks and highlight their possible risks and implications by using advanced simulations in a controlled environment. To carefully and correctly mimic CSRF attacks, the process entails creating a legitimate web application along with a malicious counterpart. The study carefully assesses the effectiveness of custom headers, SameSite cookie characteristics, and anti-CSRF tokens as defense strategies. In addition to its technological focus, the research emphasizes participant involvement's ethical implications and stresses the significance of user safety. The results provide practical advice for developers and security experts to strengthen web apps in addition to furthering our theoretical understanding of CSRF issues. We show why there is a need for strong security measures to be put in place as soon as possible, acknowledge the ever-changing nature of cyber threats, and call for ongoing research to keep ahead of the curve in terms of protecting digital ecosystems. In conclusion, this study is an invaluable tool for understanding and resolving the urgent problems caused by CSRF vulnerabilities, demonstrating its importance in strengthening the security framework of our globalized digital society. © 2024 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Mobile Application for Early Screening of Skin Cancer Using Dermoscopy Image Data Based on Convolutional Neural Network 25

Mobile Application for Early Screening of Skin Cancer Using ...

引用

25th International Electronics Symposium, IES 2023

作者： Fariza, Arna Muliawati, Tri Hadiah Wibowo, Mohamad Akbar Fadlika Setiowati, Yuliana Politeknik Elektronika Negeri Surabaya Department of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350314731

The dermoscopy image produced by the dermatoscope represents the skin surface structure in more detail than clinical images because the imaging technique uses optical magnification and liquid immersion lighting or cross-polarization. Detection of skin cancer is a challenge for several reasons. Doctors find it difficult to detect the presence of cancer on the skin only with dermoscopy images. Sometimes further tests are needed to confirm the results of the diagnosis, such as a biopsy or pathology examination, that is relatively time-consuming. Mobile skin screening technology can be used as an early screening tool for the early detection of melanoma, allowing patients to share images of their lesions with their skin specialists quickly. In this study, a novel method for early skin cancer detection based on dermoscopy pictures and the convolution neural network (CNN) algorithm is proposed. Three convolution layers, two average pooling layers, and a batch normalization layer make up the five feature extraction layers of CNN's proprietary design. The ISIC Archive, which has a collection of skin lesion photos, was the dataset utilized to create the model. Four thousand dermoscopy images in JPG format are used in this study and are divided into two classes: benign and malignant. The dataset is divided randomly into 80% training data and 20% test data. The experiments found that the model with the best performance resulted in a training data accuracy of 99.3% and a test data accuracy of 97.63%. It concludes that the model with batch normalization can distinguish the benign and malignant well. The model requires a small enough space to be easily accessible through mobile devices. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

The combination of the NDBI and machine learning algorithms to classification the development of urban areas in Surabaya uses Landsat 8 Imagery. 25

The combination of the NDBI and machine learning algorithms ...

引用

25th International Electronics Symposium, IES 2023

作者： Wibowo, Prasetyo Fariza, Arna Saputra, Ferry Astika Politeknik Elektronika Negeri Surabaya Department of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350314731

Development is a transformation that occurs in order to better people's lives. In this instance, efforts are required to monitor development progress swiftly and efficiently so that outcomes that support the government's new policies are obtained. With a population of 2,848,583 people, Surabaya is the largest metropolitan city in Eastern Indonesia. An increase in population can impact Surabaya's development and generate potential issues with urban planning development. Through these issues, remote sensing technology can efficiently and swiftly detect advances in Surabaya. This research study employs Landsat 8 image data with a combination of Normalized Build-Up Index (NDBI) as pre-processed pixels to segment into urban areas. It employs machine learning to classify urban areas to separate class types in depth. The findings show that the method successfully classified subclasses in residential and industrial areas. Random Forest (RF) outputs have an overall accuracy of 85%, whereas Decision Tree (DT) outputs have an overall accuracy of 84%. This study's findings also indicate the possibility for practical applicability to various case studies, such as conducting detections in forests, plantations, mining, and coastal environments. © 2023 IEEE.

关键词： Landsat

来源：评论

学校读者我要写书评

暂无评论

Stunting Program Classification in East Java, Indonesia from Internet News Using Location-Based and SVM 25

Stunting Program Classification in East Java, Indonesia from...

引用

25th International Electronics Symposium, IES 2023

作者： Ananta, Caesar Jalu Fariza, Arna Asmara, Rengga Politeknik Elektronika Negeri Surabaya Department of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350314731

Stunting is a serious health problem for toddlers in Indonesia, especially in East Java, which makes the Indonesian government seriously try to overcome it to achieve the Golden Generation of Indonesia. To reduce the prevalence of stunting, programs related to stunting are held regularly. This research aims to compile and classify information regarding stunting programs in East Java from internet news. The solution is to create a website that visualizes the prevalence of stunting and stunting programs in East Java, Indonesia, in the form of a map that is divided into several districts in East Java. Stunting prevalence data is taken from SSGI data that has been collected by the Indonesian Ministry of Health, while information about the stunting program is taken from mined internet news, filtered using the SVM machine learning algorithm, and classified based on the location of the stunting program reported. The SVM filtering model created can classify and filter news with an accuracy rate of up to 87%. With this website, it is hoped that the public can easily get information about stunting programs in their location and that the government can conduct an interactive analysis of stunting data in East Java. © 2023 IEEE.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Evaluation and Prediction of Resource Usage for multi-parametric Deep Learning training and inference 27

Evaluation and Prediction of Resource Usage for multi-parame...

引用

27th Pan-Hellenic Conference on Progress in Computing and informatics with International Participation, PCI 2023

作者： Tsalera, Eleni Stratogiannis, Dimitrios Papadakis, Andreas Voyiatzis, Ioannis Samarakou, Maria Department of Informatics and Computer Engineering University of West Attica Greece Athens Greece

ISBN: (纸本)9798400716263

Deep learning is increasingly used in diverse application fields with results typically surpassing those of traditional machine learning techniques. The portfolio of available neural networks is wide, consisting of the full range in terms of complexity, from compact networks to large ones with multiple layers and parameters. This heterogeneity in the model topology is reflected, not necessarily linearly, on the required computational resources for training and inference. Similarly, the environments where the neural networks are trained and executed are transformed from fully-fledged centralized nodes to distributed architectures with constrained resources. In this view, computational resource requirements can be one of the criteria for resource usage management and neural network selection. In this work we measure the training times for a set of five convolutional neural networks of varying complexity and age (GoogleNet, ShuffleNet, VGGish, YAMNet) under different training configurations, considering the batch size, the number of epochs and the learning rate. These measurements are used to create a CPU-time-training dataset of more than 500 values. This dataset is used to train and evaluate models, based on neural networks, for estimating and predicting training times depending on the models employed and the training parameters. Five regression models have been trained and evaluated in terms of correlation coefficient and root mean square error. In addition, we measure the CPU times needed for inference for a subset of the trained models, which prove to be uncorrelated with the corresponding training times. © 2023 Owner/Author.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Enhancing Spectral Efficiency in 5G MIMO Networks Through Adaptive Beamforming Techniques 7

Enhancing Spectral Efficiency in 5G MIMO Networks Through Ad...

引用

7th International Conference on Advanced Communication Technologies and Networking, CommNet 2024

作者： Konstantinos, Tsachrelias Katsigiannis, Chrisostomos-Athanasios Kokkinos, Vasileios Gkamas, Apostolos Bouras, Christos Pouyioutas, Philippos University of Patras Computer Engineering and Informatics Department Patras Greece University of Ioannina Department of Chemistry Ioannina Greece University of Cyprus Computer Science Department Nicosia Cyprus

ISBN: (纸本)9798350367027

The evolution of 5G networks is driving advancements in data rates, latency reduction, and connectivity, with adaptive beamforming emerging as a core technology to enhance spectral efficiency. This study demonstrates how integrating beamforming with spatial filtering can effectively optimize signal quality in 5G MIMO networks. Through simulations, we show that our approach achieves significant improvements in Signal-To-Noise Ratio (SNR) by optimizing beam directions. Specifically, results indicate that optimal beamforming angles can yield SNR values as high as 78 dB, substantially outperforming lower SNRs observed at less favorable angles. These findings underscore the potential of combined beamforming and spatial filtering to enhance communication reliability and network performance, particularly in high-density settings. © 2024 IEEE.

关键词： 5G mobile communication 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：