检索结果-内蒙古大学图书馆

3rd International Conference on Advance Computing and Innovative Technologies in Engineering, ICACITE 2023

作者： Naidu, K. Venkatagurunatham Pillai, Anchu Krishnan Rajaprabha, C.E. Sharma R, Rajesh Ul Islam, Atowar Khasimbee, Shaik Dr M.G.R Educational and Research Institute Dept. of Computer Science and Engineering Chennai India Xavier Institute of Engineering Applied Science and Humanities Maharashtra Mumbai India Hindusthan Institute of Technology Department of Computer Science and Engineering Coimbatore India Adama Science and Technology University School of Electrical Engineering and Computing Department of Computer Science and Engineering Nazareth1888 Ethiopia University of Science and Technology Meghalaya Department of Computer Science and Electronics Meghalaya Baridua793101 India Aditya College of Engineering Department of Computer Science and Engineering Andhra Pradesh Surampalem533437 India

ISBN: (纸本)9798350399264

Technology is getting better day by day and human beings are using the latest technology possible for their needs and safety. Many devices have been invented that use the internet and with this human safety issues are also taken care of up to a great extent. GPS tracking devices, SHE (Society Harnessing Equipment), AESHS (Advanced Electronic System for Human Safety), ILA Systems are one of the most useful applications and devices that are used for human safety. Human safety and especially the safety of girls have become an emerging and sensitive issue in the present world scenario. This article deals with the role of the Internet of Things in advancing smart security. The issues are taken care of with the help of these upgraded devices that are easily accessible from a remote location with an internet connection. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

引用

14th International Conference on Education Technology and computers, ICETC 2022

作者： Segarra-Faggioni, Veronica Ratté, Sylvie De Jong, Frank Dept. Software and IT Engineering École de Technologie Supérieure Montreal Canada Dept. Computer Science and Electronics Universidad Tecnica Particular de Loja Loja Ecuador Dept. Learning and Innovation Aeres Wageningen Applied University Wageningen Netherlands

ISBN: (纸本)9781450397766

Knowledge Building as a pedagogy supports collaborative work between students to improve ideas. The result of knowledge-building discourse in student communities is the development of academic artifacts. Student reports are academic artifacts that can result from a knowledge-building process during their learning. However, the automatic analysis of student reports is quite challenging due to the documents' length and written language. Given this context, our goal is to analyze the semantic similarity between student reports and curriculum literature using the information coverage measure based on the Skip-gram word2vec model. Word2vec is a well-known set of techniques that provides a way to create a representation of words to predict the nearby words between every word and its context to capture the internal semantic and syntactic information. In this work, through the experimental comparison between the vocabulary list, the best similarity value is 0.90 using word2vec. The results show that each student report was aligned with each document in the curriculum literature using the information coverage measure based on word2vec. © 2022 ACM.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A Novel Flow Priority and Continuity Control Mechanism in SDN Network

A Novel Flow Priority and Continuity Control Mechanism in SD...

引用

Innovative Engineering sciences and Technological Research (ICIESTR), International Conference on

作者： Fouad A. Yaseen Nahlah Abdulrahman Alkhalidi Fawziya Nasser Al Wahaibi Electronic and Communications Dept College of Engineering University of Baghdad Computer Science Dept. College of Science University of Baghdad Elecrical and Electronics Dept College of Engineering University of Technology and Applied Science

ISBN: (数字)9798350348637

ISBN: (纸本)9798350348644

In recent days, the escalating need to seamlessly transfer data traffic without discontinuities across the Internet network has exerted immense pressure on the capacity of these networks. Consequently, this surge in demand has resulted in the disruption of traffic flow continuity. Despite the emergence of intelligent networking technologies such as software-defined networking, network cloudification, and network function virtualization, they still need to improve their performance. Our proposal provides a novel solution to tackle traffic flow continuity by controlling the selected packet header bits (Differentiated Services Code Point (DSCP)) that govern the traffic flow priority. By setting the DSCP bits, we can determine the appropriate precedence level for the data traffic flow. The control and modification of the DSCP bits directly impact the priority assigned to data packets, thereby shaping the traffic flow continuity accordingly. The evaluation and performance analysis of the proposed network were conducted using the Mininet simulator and the MATLAB platform. The outcomes of the comprehensive testing demonstrate that the implementation of our novel priority management technique has successfully reduced queuing delay and minimized packet loss. As a result, the overall data traffic continuity has been significantly enhanced. The obtained results demonstrate that the traffic flow continuity, handled by the Software-Defined Networking (SDN) controller with the support of DSCP modification, has increased by approximately 65% when implementing the proposed priority management based on DSCP bits modification in the SDN network.

关键词： Performance evaluation Scalability Packet loss Quality of service Scheduling Performance analysis Proposals Software defined networking Surges Testing

来源：评论

学校读者我要写书评

暂无评论

TransTraffic: Predicting Network Traffic using Low Resource Data 13

TransTraffic: Predicting Network Traffic using Low Resource ...

引用

13th International Conference on Information and Communication Technology Convergence, ICTC 2022

作者： Kang, Chaewon Yoon, Jeewoo Choi, Daejin Park, Eunil Pack, Sangheon Han, Jinyoung Sungkyunkwan University Dept. of Applied Artificial Intelligence Seoul Korea Republic of Incheon National University Dept. of Computer Science and Engineering Incheon Korea Republic of Sungkyunkwan University Dept. of Interaction Science Seoul Korea Republic of School of Electrical Engineering Korea University Seoul Korea Republic of

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

In private 5G/6G networks, an adequate and accurate resource management is essential. In this paper, we propose a traffic prediction model, TransTraffic, that utilizes transfer learning for low resource data. Our evaluation demonstrates that leveraging prior knowledge from a similar traffic domain helps predict network traffic for a new domain or service. © 2022 IEEE.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

Automating Neural Model Selection in Spiking Neural Networks Using AutoML Techniques*

Automating Neural Model Selection in Spiking Neural Networks...

引用

Learning and Technology Conference (L&T)

作者： Sanaullah Hirotada Honda Kaushik Roy Axel Schneider Joachim Waßmuth Thorsten Jungeblut Dept. of Mathematics and Engineering University of Applied Sciences and Arts Bielefeld Germany Dept. of Information Networking Toyo University Tokyo Japan Dept. of Computer Science A&T State University North Carolina USA

ISBN: (数字)9798331532215

ISBN: (纸本)9798331532222

The selection of optimal neural models in Spiking Neural Networks (SNNs) traditionally depends on a trial-and-error approach, which is both time-consuming and sometimes tends to suboptimal selection of the neural model. This research study explores the integration of Automated Machine Learning (AutoML) techniques into SNNs to simplify the process of designing an SNN model by automatically selecting the most optimal neural model. For example, in traditional neural networks, AutoML proves that it has the potential to significantly reduce the time and effort required to identify the best-performing architectures, by automating the selection and updating of loss functions and hyper-parametric values. To this end, we present a stand-alone framework for applying AutoML in SNNs, highlighting how this approach can improve accuracy, efficiency, and reliability in the selection process of optimal neural models, as these neural models are the core principle of designing SNN architecture. The proposed method not only accelerates the development of SNN models but also enhances their performance by systematically identifying optimal configurations that might be overlooked through manual methods. Therefore, to validate our approach, the proposed architecture was tested using different well-known benchmarks with different sets of neurons, ranging from 100 to 3000 neurons, and demonstrated state-of-the-art results in image classification tasks.

关键词： Hands Accuracy Computational modeling Neurons Spiking neural networks computer architecture Manuals Automated machine learning Reliability engineering Image classification

来源：评论

学校读者我要写书评

暂无评论

Classification of Depression, Anxiety and Stress from Handwriting and Drawing with Stacking Models

Classification of Depression, Anxiety and Stress from Handwr...

引用

Innovative Approaches in Smart Technologies (ISAS), International Symposium on

作者： Semra Bayrak Sedat Golgiyaz Murat Aykut Dept. of Computer Engineering Graduate School of Natural and Applied Science Karadeniz Technical University Trabzon Türkiye Dept. of Computer Engineering Bingöl University Bingöl Türkiye Dept. of Computer Engineering Karadeniz Technical University Trabzon Türkiye

ISBN: (数字)9798331540104

ISBN: (纸本)9798331540111

Recently, emotion analysis from online handwriting and drawings has become an important research topic. This study aims to determine the optimal model combination using dynamic and statistical features obtained from handwriting and drawings for detecting emotional states. The feature vectors are derived from physical (kinematic), statistical and signal processing (spectral, cepstral and frequency domain) analyses. To address the class imbalance problem, ADASYN (Adaptive Synthetic Sampling) and Tomek Links methods were applied together. In this way, the number of samples of the minority class has been increased, while over-sampled classes have been reduced. Dimensionality reduction was realized using PCA, and Gradient Boosting Classifier (GBC) feature selection. After determining the fewest and most effective features, the samples were classified using the two-level stacking ensemble method. eXtreme Gradient Boosting (XGBoost), Light Gradient-Boosting Machine (LightGBM), GBC, Random Forest (RF) methods are selected for base and meta models. Model and hyperparameter optimization was carried out by Optuna frameork. The performance of the models is evaluated through experiments in publicly available EMOTion recognition from HAndWriting and draWing (EMOTHAW) database. The aim was to determine the emotional states of depression, anxiety and stress with the data obtained from 7 different drawing/writing tasks of 129 people. The results obtained from accuracy, f1-score, precision and recall metrics show that the model provides remarkable performance.

关键词： Measurement Analytical models Anxiety disorders Stacking Signal processing Feature extraction Depression Boosting Vectors Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

BGP Typo: A Longitudinal Study and Remedies

arXiv

引用

arXiv 2023年

作者： David, Liron Shavitt, Yuval Dept. of Computer Science and Applied Mathematics Weizmann Institute of Science School of Electrical Engineering Tel-Aviv University

BGP is the protocol that keeps Internet connected. Operators use it by announcing Address Prefixes (APs), namely IP address blocks, that they own or that they agree to serve as transit for. BGP enables ISPs to devise complex policies to control what AP announcements to accept (import policy), the route selection, and what AP to announce and to whom (export policy). In addition, BGP is also used to coarse traffic engineering for incoming traffic via the prepend mechanism. However, there are no wide-spread good tools for managing BGP and much of the complex configuration is done by home-brewed scripts or simply by manually configuring router with bare-bone terminal interface. This process generates many configuration mistakes. In this study, we examine typos that propagates in BGP announcements and can be found in many of the public databases. We classify them and quantify their presence, and surprisingly found tens of ASNs and hundreds of APs affected by typos on any given time. In addition, we suggest a simple algorithm that can detect (and clean) most of them with almost no false positives. © 2023, CC BY.

关键词： Border Gateway Protocol

来源：评论

学校读者我要写书评

暂无评论

Real-Time Human Body Sensors Data Classification using Supervised Machine Learning

Real-Time Human Body Sensors Data Classification using Super...

引用

Business Analytics for Technology and Security (ICBATS), International Conference on

作者： Muhammad Sajid Farooq Muhammad Farhan Khan Dept. of Computer Science Lahore Garrison University Lahore Pakistan Applied Science Research Center Applied Science Private University Amman Jordan Dept. of Forensic Sciences University of Health Sciences Lahore Pakistan

Supervised learning algorithms have recently been brought to the classification of medical data in an effort to boost diagnostic throughput and eliminate human-caused diagnostic errors. This measure was taken to improve diagnostic precision. To be carried out, the fully supervised learning process needs a large amount of accurately labelled data. Annotating data material, on the other hand, demands a large expenditure of time, effort, and resources. Using the self- supervised learning approach to solve this challenge has the potential to provide a variety of beneficial outcomes for everyone. When there is no direct supervision, pretext projects are regularly employed in independent study scenarios. This is done so that massive volumes of unsupervised data may be utilized to obtain supervised knowledge. Furthermore, by utilizing specialized, supervised information, the network is prepared to obtain representations that will be beneficial for still-growing professions. The two-step CPC-based classification framework (TCC) model is built completely using contrastive predictive coding and is divided into two distinct phases that are carried out in sequential order. Making use of the contrastive predictive coding (CPC) model, the initial step is to build a fictional position. It must be completed as quickly as possible. This activity must utilize the encoder to extract appropriate features from a broad variety of classes in order to achieve the goal that it has set out to achieve. The encoder will employ the skills they learned while working on the pretext in the second half, which will take place in a training setting under the guidance of an expert teacher. Finally, we assess the proposed framework by comparing it to the most recent and innovative research in the field. This allows us to highlight the framework’s success by displaying how well it compares to other cutting-edge and current industry efforts. Experiments will be conducted to compare the efficacy of the pr

关键词： Training Adaptation models Supervised learning Machine learning Predictive coding Predictive models Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Models for Foreign Worker Prediction in Thailand: A Study of Linear Regression and Decision Tree

Machine Learning Models for Foreign Worker Prediction in Tha...

引用

2024 International Conference on Measurement, Communication, and Virtual Reality, MCVR 2024

作者： Jomsri, P. Prangchumpol, D. Eamthanakul, B. Poonsilp, K. Pudprommarat, C. Dept. of Information Technology Suan Sunandha Rajabhat University Dusit Bangkok10300 Thailand Dept. of Computer Science Suan Sunandha Rajabhat University Dusit Bangkok10300 Thailand Dept. of Applied Science Faculty of Science and Technology Suan Sunandha Rajabhat University Bangkok Thailand

ISBN: (纸本)9781510691773

This study proposed to predict the immigration patterns of foreign workers in Thailand using machine learning techniques. The primary focus is to analyze how factors such as the year, month, area, and legal immigration type (MOU) influence the number of foreign workers entering the country. MOU represents the Memorandum of Understanding, a legal framework for foreign migration. By utilizing two distinct machine learning models—Linear Regression and Decision Tree—this research seeks to identify the most effective method for forecasting immigration trends. This study analyzes foreign worker immigration in Thailand using data collected from 2560 to 2561 B.E. The data used in this study includes key variables that are indicative of immigration movements, providing a comprehensive view of the factors influencing foreign migration. The findings reveal that the Decision Tree model outperforms Linear Regression in terms of accuracy at 0.99. This analysis is crucial for policymakers and stakeholders as it provides insights into the patterns of foreign worker immigration, enabling better planning and management of foreign worker resources. Understanding these patterns is essential for developing effective immigration policies and ensuring that foreign worker market needs are met in a regulated and orderly manner. The comparative analysis demonstrates the importance of selecting appropriate machine learning models for accurate predictions in the domain of foreign immigration. © 2025 SPIE.

关键词： Linear regression

来源：评论

学校读者我要写书评

暂无评论

Dual-Encoding Y-ResNet for generating a lens flare effect in images

Dual-Encoding Y-ResNet for generating a lens flare effect in...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Dawid Połap Antoni Jaszcz Gautam Srivastava Faculty of Applied Mathematics Silesian University of Technology Gliwice Poland Dept. of Math and Computer Science Brandon University Brandon Canada

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Taking photos against the light generates a certain visual effect. Taking a photo in the direction where the sun is located also results in a change in the temperature of the photo as well as the appearance of a visual effect in the form of the flare of light. In this article, we present an innovative neural network model called Y-ResNet, whose input consists of two samples and the output consists of one. This solution makes it possible to train the network by providing the original image and the flare effect, which will result in a modified sample. The training was conducted on a commonly known CityScapes dataset, where, by using classic data processing methods and the k-means algorithm, it was possible to add a flare if there was a visible portion of the sky in the input image. The proposed solution was described and tested to demonstrate the capabilities of the proposed method. The results show the superiority of the approach against the traditional ResNet without a second encoding path, generating better results, and creating a better impression of the lens-flare effect.

关键词： Training Image segmentation Rain Image coding Databases Neural networks Visual effects

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：