检索结果-内蒙古大学图书馆

11th International Conference on Electrical engineering, computer Science and Informatics, EECSI 2024

作者： Bachtiar, Fitra Abdurrachman Nainggolan, Cesilia Natasya Soetedjo, Riza Setiawan Rokhmawati, Retno Indah Muflikhah, Lailil Brawijaya University Department of Informatics Engineering Faculty of Computer Science Malang Indonesia Brawijaya University Faculty of Computer Science Department of Information Systems Malang Indonesia

ISBN: (纸本)9798350355314

The e-Iearning system or distance learning system has become important, especially during the COVID-19 pan-demic. Several tertiary institutions have made the e-Iearning system an alternative teaching and learning activity. Research on the use of e-Iearning needs to be explored to obtain innovative, creative, and fun learning. One aspect that can be examined in e-learning is students' emotional response to the learning activities. The emotional state of students directly or indirectly affects the learning process. The student's emotional responses can be measured by their facial expressions. In this study, an exploration was carried out on the facial expressions shown by students in HSS Learning, an e-Iearning for learning web programming. The student's facial expressions were extracted using 68 pairs of facial landmarks and additional 6 facial feature vectors. The total number of features used is 142. Machine learning methods for classification are applied to determine the performance of several classification models, including the k-Nearest Neighbor (k- NN) algorithm, Logistic Regression, and Support Vector Machine (SVM). Machine learning performance evaluation is done using the Fl-score and confusion matrix. The results show that the accuracy of the k-NN, Logistic Regression, and SVM are 91.4%, 92.2%, and 92.1 %, respectively. However, the Fl-score macro values are relatively low due to data imbalance with the k- NN, Logistic Regression, and SVM models are 0.250, 0.272, and 0.243, respectively. While the study provides insight into the student learning experience in e-Iearning settings, this study needs to be explored more. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Atmospheric Attenuation at mmWave below 57GHz Based on Measurement in Tropical Region 16

Atmospheric Attenuation at mmWave below 57GHz Based on Measu...

引用

16th IEEE Malaysia International Conference on Communication, MICC 2023

作者： Li, Lu Sali, Aduwati Wali, Sangin Qahtan Universiti Putra Malaysia Faculty of Engineering Department of Computer and Communication Systems Engineering Selangor Serdang43400 Malaysia

ISBN: (纸本)9798350304343

According to ITU-R P.676-12, a modified prediction model of mmWave atmospheric attenuation suitable for tropical areas is proposed in this paper, named AA-mmWave. Combined with Malaysia's air humidity, temperature, and atmospheric pressure measured data in 2020 and 2021 via sensors, the mmWave atmospheric attenuation characteristic curve below 57GHz is simulated and calculated. The results show that the attenuation rate generally increases with frequency, especially from 55GHz to 57GHz, which increases until reaching the highest point of 5.937dB/km. Additionally, the atmospheric attenuation rate of a mmWave is inversely proportional to temperature and pressure. The lowest value of attenuation rate at 32°C achieves 0.3157 dB/km. Finally, there is a proportional correlation between water vapour density and mmWave atmospheric attenuation rate. This finding has essential and indelible reference value for developing mmWave transmission technology in the tropical region. © 2023 IEEE.

关键词： Atmospheric pressure

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Data Analytics Approach for Crisis Management in Healthcare systems

An Intelligent Data Analytics Approach for Crisis Management...

引用

2024 International Conference on computer and Applications, ICCA 2024

作者： Madian, Fatma A. Ebrahim, Gamal A. Salah, Mostafa M. Abdelaal, Marwa A. Ain Shams University Faculty of Engineering Computer and Systems Engineering Department Cairo Egypt Future University in Egypt Electrical Engineering Department Cairo Egypt Faculty of Computers and Information Sadat Academy for Management Sciences Computer Science Department Cairo Egypt

ISBN: (纸本)9798350367560

Crisis management is preparing for and managing possible crises that may impact organizations and individuals at different levels. It involves effective communication, quick decision-making, and strategic planning to minimize the negative impact of a crisis and ensure swift recovery. It plays a vital role in healthcare systems, especially in virus outbreaks. Its role is to monitor and manage the spread of viruses. Moreover, it can use Machine Learning (ML) techniques to achieve this goal. This paper discusses how to apply ML approaches to daily reports of infection cases. The adopted ML approaches are Auto Regressive Integrated Moving Average (ARIMA) model and the Long Short-Term Memory (LSTM) model. Furthermore, it uses Root Mean Square Error (RMSE) as a performance measure to evaluate the applied models. Simulation results show that ARIMA model performs better as compared to other models, which can provide a prediction accuracy of more than 99%. © 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

Extractive Text Summarization of Long Documents Using Word and Sentence Encoding 5

Extractive Text Summarization of Long Documents Using Word a...

引用

5th International IEEE Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023

作者： Abdelrahman, Amany A. El-Kassas, Wafaa S. Mohamed, Hoda K. Ain Shams University Faculty of Engineering Department of Computer and Systems Engineering Cairo Egypt Faculty of Computers and Information Technology Giza Egypt

ISBN: (纸本)9798350381030

Automatic Text Summarization (ATS) for long documents is a very challenging task. A long document includes more than one topic, so it is required to construct a summary that covers the most important contextual information from the different topics in the input document. There are many ATS techniques, but the produced summaries are much less accurate than the human summaries. This paper proposes a supervised extractive Neural-based summarization model that focuses on long documents summarization by integrating both the local and global contexts of the document. The proposed system employs two bidirectional Gated Recurrent Units (GRUs) as word and sentence encoders, respectively, and uses Word2Vec embeddings as word representation. Two ensembles are proposed by applying the average ensemble method to the proposed system with two other Neural-based systems. The proposed system uses the PubMed dataset to evaluate the two ensembles using the ROUGE evaluation metrics. The results of the evaluation show that there are promising and remarkable improvements of 0.14% and 0.97% for ROUGE-1, 0.33% and 1.12% for ROUGE-2, and 0.25% for ROUGE-L. © 2023 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Static Analysis and Machine Learning Approaches for Detecting Android Banking Malware 3

Comparative Study of Static Analysis and Machine Learning Ap...

引用

3rd International Conference on Emerging Smart Technologies and Applications, eSmarTA 2023

作者： Ahmed, Alaa M. Saeed, Mogeeb A. Hamood, Amr A. Alazab, Abduljabar A. Ahmed, Kamel A. Computer Networks & Distributed Systems Al-saeed It Taiz University Faculty of Engineering Taiz Yemen Taiz University Al-saeed Faculty of Engineering & It Computer Networks & Distributed Systems Department Taiz Yemen

ISBN: (纸本)9798350305333

Android currently dominates the smartphone market, accounting for an impressive market share of over 70%. However, because of its widespread acceptance, mobile operating systems have become a prime target for bad actors looking to profit from them. Particularly Android has been subjected to an increasing barrage of malware assaults, including the infamous Android Banking Trojans. This study investigates the effectiveness of static analysis in locating Android banking malware in order to counter this threat. It does so by utilizing a wide range of features, including permissions, application programming interface (API) calls, opcodes, API packages, system commands, intents, strings, services, receivers, and activities. The study suggests using machine learning techniques to assess the detection of Android malware by utilizing various sets of classifiers in order to achieve this goal. The study also uses a feature selection approach to determine which features are most useful for telling malicious code apart from good code. 500 samples of malicious code and 500 samples of benign code make up the dataset that was used. The XGboost algorithm outperforms others in terms of accuracy, achieving an impressive accuracy value of 99.5% in malware detection after conducting a thorough comparison of various classifier sets. These results demonstrate the potential of static analysis and machine learning as useful tools in fending off the growing threats posed by Android malware. © 2023 IEEE.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

Social and Non-social Reward Learning Contexts for Detection of Major Depressive Disorder Using EEG: A Machine Learning Approach 16th

Social and Non-social Reward Learning Contexts for Detecti...

引用

16th International Conference on Brain Informatics, BI 2023

作者： Ghattas, Philopateer Gamal, Mai Eldawlatly, Seif Computer Science and Engineering Department Faculty of Media Engineering and Technology German University in Cairo Cairo Egypt Computer and Systems Engineering Department Faculty of Engineering Ain Shams University Cairo Egypt Computer Science and Engineering Department The American University in Cairo Cairo Egypt

ISBN: (纸本)9783031430749

Major Depressive Disorder (MDD) is a leading cause of disability globally and a major cause of suicide deaths. Improving our understanding of MDD is expected to inspire better objective diagnostic and treatment tools which may decrease the burden of disease worldwide. MDD is associated with social impairments and reward processing aberrations. However, the interaction between social cognition and reward learning in MDD is not well understood. In this work, we aim to study the effect of integrating social information with reward learning in MDD using an EEG-based machine learning approach. We recorded EEG data from subjects during their participation in a reward learning experiment in social and non-social contexts. We then extracted linear and nonlinear features from the EEG data to detect MDD using Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) classifiers. Our results show that the data collected during social contexts achieved broadly higher classification accuracies compared to non-social contexts reaching 80% using multi-channels. Moreover, single-channel data achieved comparable and even better accuracies than multi-channels with also superior performance in social contexts reaching 85.7%. In the sub-band classification analysis, beta and alpha bands were considerably better than theta and delta bands. Surprisingly, the non-social context had the highest accuracy in the beta band while the social context had the highest accuracy in the alpha band. The results were consistent when using single features compared to combining the features. These findings show the notable role of social information with reward processing in advancing our understanding of MDD and its subtypes which can guide the improvement of diagnostic and personalized treatment tools. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Enhancing Extractive Text Summarization of Long Documents Using Features Dimensionality Reduction 3

Enhancing Extractive Text Summarization of Long Documents Us...

引用

3rd International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2023

ISBN: (纸本)9798350306231

Automatic Text Summarization (ATS) task is considered one of the most challenging tasks in Natural Language Processing field, especially for long documents. There are many techniques for ATS, including Artificial Intelligence (AI) approaches, statistical-based approaches, graph-based approaches, etc., but the generated summaries are still less accurate than human summaries. This research presents an extractive Neural-based model to summarize long documents using both attentive global and local contexts, Word2Vec embeddings, and a bidirectional Gated Recurrent Unit (GRU) as a Sentence Encoder. The proposed model uses a Multi-Layer Perceptron (MLP) that consists of two linear layers with Rectified Linear Activation Units (RELUs) to reduce features dimensionality. The proposed model is evaluated on PubMed and arXiv datasets using ROUGE metrics, and the evaluation results show remarkable and promising improvements for ROUGE-1, ROUGE-2, and ROUGE-L. © 2023 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Determining the Critical Factors of Antenatal Care Follow-Up Using Two-Phase Machine Learning 27

Determining the Critical Factors of Antenatal Care Follow-Up...

引用

27th International Conference on Soft Computing and Measurements, SCM 2024

作者： Bessmertny, Igor A. Enkomaryam, Bidru C. Mamuye, Adane L. Itmo University Faculty of Software Engineering and Computer Systems Saint Petersburg Russia University of Gondar Department of Computer Science Gondar Ethiopia

ISBN: (纸本)9798350363708

Determining the critical factors affecting antenatal visits will greatly contribute to reducing maternal and infant mortality. This study, thus attempted to construct a cluster-based predictive model to determine the critical factors of antenatal care follow-up among women in Ethiopia using two-step machine learning techniques. The 5,990 preprocessed obstetric dataset with 13 selected attributes were used that was collected from the Dabat Research Center at the University of Gondar, Ethiopia. To solve the study problem, six cluster models were developed using K-means, Expectation Maximization and Make Density clustering algorithms, which are well-suited for analyzing health datasets, providing scalability, flexibility, robustness to noise, and the ability to handle uneven cluster sizes. K-means out-formers Density based and Expectation Maximization clustering algorithms with minimum number of sum of square errors (17094) and number of iteration (3). Then, output of the K-means cluster model was used as input to segment the dataset and build a total of 21 predictive models using the tree-based J48 classifier, PART and JRip rule generators while adjusting their parameters. The model for predicting antenatal care follow-up is constructed by induction of the truncated PART rule (accuracy of 99.93%) and extracts attributes of interest such as antenatal care attendance, antenatal care location, antenatal care frequency, current vaccination, woman's age, and HIV testing to predict antenatal care follow-up in the study area. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A NOTE ON THE QUALITATIVE BEHAVIOUR OF AN ODE MODEL RELATED TO ENDOTOXIN TOLERANCE

引用

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2024年第4期86卷 127-130页

作者： Olteanu, Mircea Ştefan, Radu Department of Mathematical Methods and Models Faculty of Applied Sciences University "Politehnica" of Bucharest Romania Department of Automatic Control and Systems Engineering Faculty of Automatic Control and Computer Science University "Politehnica" of Bucharest Romania

关键词： Differential equations

来源：评论

学校读者我要写书评

暂无评论

HDLIDP: A Hybrid Deep Learning Intrusion Detection and Prevention Framework

引用

computers, Materials & Continua 2022年第11期73卷 2293-2312页

作者： Magdy M.Fadel Sally M.El-Ghamrawy Amr M.T.Ali-Eldin Mohammed K.Hassan Ali I.El-Desoky Computer Engineering and Systems Department Faculty of EngineeringMansoura UniversityMansoura35516DKEgypt Head of Communications and Computer Engineering Department MISR Higher Institute for Engineering and TechnologyMansoura35111DKEgypt Mechatronics Department Faculty of EngineeringHours University in Egypt(HUE)New Damietta34517DTEgypt

Distributed denial-of-service(DDoS)attacks are designed to interrupt network services such as email servers and webpages in traditional computer ***,the enormous number of connected devices makes it difficult to operate such a network *** defined networks(SDN)are networks that are managed through a centralized control system,according to *** controller is the brain of any SDN,composing the forwarding table of all data plane network *** the advantages of SDN controllers,DDoS attacks are easier to perpetrate than on traditional *** the controller is a single point of failure,if it fails,the entire network will *** paper offers a Hybrid Deep Learning Intrusion Detection and Prevention(HDLIDP)framework,which blends signature-based and deep learning neural networks to detect and prevent *** framework improves detection accuracy while addressing all of the aforementioned *** validate the framework,experiments are done on both traditional and SDN datasets;the findings demonstrate a significant improvement in classification accuracy.

关键词： Software defined networks(SDN) distributed denial of service attack(DDoS) signature-based detection whale optimization algorism(WOA) deep learning neural network classifier

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：