检索结果-内蒙古大学图书馆

Journal of Network Intelligence 2025年第2期10卷 845-858页

作者： Liu, Min Teng, Hua Zhang, Hong Li, Hao School of Computer Science and Software Engineering Southwest Petroleum University Nanchong637001 China Department of Computer China West Normal University Nanchong637009 China Faculty of Computer and Information Science SouthWest University Chongqing400700 China Krirk University Bangkok10220 Thailand

With the advancement of educational evaluation reform and the popularization of higher education, university teaching quality evaluation has been a research hotspot in the field of educational evaluation. In response to the issue of multimodal heterogene-ity gap in current university education evaluation data, which makes it tough to integrate evaluation data, this article suggests a Multimodal Data Fusion (MDF) method for university teaching evaluation relied on Generative Adversarial Network (GAN). Firstly, the MDF model is constructed from two aspects: establishing similarity network and designing regularization terms. By designing sparse regularization terms, the feature selection of multimodal samples is carried out to address the issue of large deviation of fusion data. Secondly, BERT pre-training model is adopted to extract the modal embedding features of teaching evaluation text, and Bi-LSTM is adopted to extract the audio and visual modal embedding features of teaching evaluation. Then, on the ground of the constructed MDF model, combined with the GAN and autoencoder, a multi-modal adversarial autoencoder learning model is established to reduce the heterogeneous gap between modes and form a unified representation. At last, the self-attention pretest network is established to achieve the automatic classification of multi-modal university teaching evaluation data. The experimental outcome implies that the accuracy, F1 value and determination coefficient R2 of the suggested method are 92.18%, 93.72% and 90.5%, respectively, which are superior to the comparison method, showing good classification performance. © 2025, J. Network Intell. All rights reserved.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Robust Optimization Under Decision Dependent Uncertainty

引用

IEEE/CAA Journal of Automatica Sinica 2022年第7期9卷 1295-1306页

作者： Yunfan Zhang Feng Liu Yifan Su Yue Chen Zhaojian Wang João P.S.Catalão State Key Laboratory of Power System and Generation Equipment the Department of Electrical EngineeringTsinghua UniversityBeijing 100084China Department of Mechanical and Automation Engineering the Chinese University of Hong KongHong Kong SARChina Ministry of Education Key Laboratory of System Control and Information Processing the Department of AutomationShanghai Jiao Tong Universityand also with Shanghai Engineering Research Center of Intelligent Control and ManagementShanghai 200240China Faculty of Engineering of the University of Porto and Institute for Systems and Computer Engineering Technology and Science(INESC TEC)Porto 4200-465Portugal IEEE

In the conventional robust optimization(RO)context,the uncertainty is regarded as residing in a predetermined and fixed uncertainty *** many applications,however,uncertainties are affected by decisions,making the current RO framework *** paper investigates a class of two-stage RO problems that involve decision-dependent *** introduce a class of polyhedral uncertainty sets whose right-hand-side vector has a dependency on the here-and-now decisions and seek to derive the exact optimal wait-and-see decisions for the second-stage problem.A novel iterative algorithm based on the Benders dual decomposition is proposed where advanced optimality cuts and feasibility cuts are designed to incorporate the uncertainty-decision *** computational tractability,robust feasibility and optimality,and convergence performance of the proposed algorithm are guaranteed with theoretical *** motivating application examples that feature the decision-dependent uncertainties are ***,the proposed solution methodology is verified by conducting case studies on the pre-disaster highway investment problem.

关键词： Benders decomposition decision-dependent uncertainty endogenous uncertainty robust optimization(RO)

来源：评论

学校读者我要写书评

暂无评论

Ensemble based unsupervised anomaly detection with concept drift adaptation for time series data

Ensemble based unsupervised anomaly detection with concept d...

引用

Smart World Congress (SWC), IEEE

作者： Danlei Li Nirmal Nair Kevin I-Kai Wang Kouichi Sakurai Department of Electrical Computer and Software Engineering University of Auckland Auckland New Zealand Department of Informatics Faculty of Information Science and Electrical Engineering Kyushu University Fukuoka Japan

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

Anomaly detection is the identification of instances that substantially deviate from the majority of the data and do not conform to a well-defined normal behavior. Investigating time series anomalies has become increasingly popular in recent years due to widely deployed IoT devices and sensors. Although most existing methods apply image anomaly detection algorithms directly on time series and commonly assume the data is IID (independent and identically distributed). However, in most realworld applications, the underlying data distribution alters over time. Changes in data over time are referred to as concept drift and can significantly degrade the efficacy of an anomaly detection model. Existing research also indicates that the majority of anomaly detection frameworks ignored concept drift, resulting in poor long-term model performance. This paper presents an ensemble-based, unsupervised anomaly detection framework that is adaptive to the concept drift in time series data. Both distribution and performance-based techniques are used to detect concept drift and update the model to ensure the framework’s longterm performance reliability. The proposed method is evaluated using a real-world univariate time series data that captures sea surface temperature data over a 2 -year period. By comparing our proposed framework to other state-of-the-art algorithms, we demonstrate our proposed method has obvious benefits in accuracy and long-term stability.

关键词： Adaptation models Accuracy Concept drift Time series analysis Stability analysis Sensors Sea surface temperature Reliability Anomaly detection Thermal stability

来源：评论

学校读者我要写书评

暂无评论

Preliminary Study on the Effect of Traffic Representation on Accuracy Degradation in Machine Learning-based IoT Device Identification

Preliminary Study on the Effect of Traffic Representation on...

引用

2022 IEEE International Conference on Computing, ICOCO 2022

作者： Aqil, Nik Afifi, Firdaus Zaki, Faiz Anuar, Nor Badrul Faculty of Computer Science and Information Technology Universiti Malaya Department of Computer System and Technology Kuala Lumpur50603 Malaysia Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Kuala Nerus Terengganu21030 Malaysia

ISBN: (纸本)9781665489966

The Internet of Things (IoT) has gained attention for its rapid growth in the past few years. IoT devices such as temperature and humidity sensors and voice controllers are implemented widely, from household appliances to industrial machines. However, with the rapid growth and benefits IoT offers, we are exposed to various security vulnerabilities, such as data breaches and IoT-specific malware. Researchers are using IoT device identification as a solution for IoT security issues. IoT device identification helps network administrators identify network traffic into its originating devices. However, researchers often overlook an important issue in IoT device identification, which is accuracy degradation over time. Thus, this paper explores the severity of accuracy degradation in IoT device identification on different traffic representation approaches, which are flow, sub-flow, and packet. This paper utilizes a private, and the UNSW IoT Traffic Traces public dataset. Based on the experimental findings, the sub-flow-based approach recorded the best overall performance, with only 8% degradation in the private dataset and 1% degradation in the public dataset. Meanwhile, even though the packet-based approach only degraded 5% on the private dataset, it recorded up to an 11% accuracy decrease in the public dataset. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

QoS Prediction Model of Cloud Services Based on Deep Learning

引用

IEEE/CAA Journal of Automatica Sinica 2022年第3期9卷 564-566页

作者： WenJun Huang PeiYun Zhang YuTong Chen MengChu Zhou Yusuf Al-Turki Abdullah Abusorrah Nanjing University of Information Science&Technology School of Computer and SoftwareNanjingChina IEEE New Jersey Institute of Technology Helen and John C.Hartmann Department of Electrical and Computer EngineeringNewarkUSA Center of Research Excellence in Renewable Energy and Power Systems Department of Electrical and Computer EngineeringFaculty of Engineeringand K.A.CARE Energy Research and Innovation CenterKing Abdulaziz UniversityJeddah 21589Saudi Arabia

Dear editor,This letter presents a deep learning-based prediction model for the quality-of-service(QoS)of cloud ***,to improve the QoS prediction accuracy of cloud services,a new QoS prediction model is proposed,which is based on multi-staged multi-metric feature fusion with individual *** multi-metric features include global,local,and individual *** results show that the proposed model can provide more accurate QoS prediction results of cloud services than several state-of-the-art methods.

关键词： services Services individual

来源：评论

学校读者我要写书评

暂无评论

A HybridManufacturing ProcessMonitoringMethod Using Stacked Gated Recurrent Unit and Random Forest

引用

Intelligent Automation & Soft Computing 2024年第2期39卷 233-254页

作者： Chao-Lung Yang Atinkut Atinafu Yilma Bereket Haile Woldegiorgis Hendrik Tampubolon Hendri Sutrisno Department of Industrial Management National Taiwan University of Science and TechnologyTaipeiTaiwanChina Faculty of Mechanical and Industrial Engineering Bahir Dar Institute of Technology(BiT)Bahir DarUniversityBahir Dar6000Ethiopia Department of Computer Science and Information Engineering National Taiwan University of Science and TechnologyTaipeiTaiwanChina Department of Information System Faculty of Engineering and Computer ScienceKridaWacana Christian UniversityJakartaIndonesia Department of Information Management National Dong Hwa UniversityHualienTaiwanChina

This study proposed a new real-time manufacturing process monitoring method to monitor and detect process shifts in manufacturing *** real-time production process monitoring is critical in today’s smart *** more robust the monitoring model,the more reliable a process is to be under *** the past,many researchers have developed real-time monitoring methods to detect process shifts ***,thesemethods have limitations in detecting process shifts as quickly as possible and handling various data volumes and *** this paper,a robust monitoring model combining Gated Recurrent Unit(GRU)and Random Forest(RF)with Real-Time Contrast(RTC)called GRU-RF-RTC was proposed to detect process shifts *** effectiveness of the proposed GRU-RF-RTC model is first evaluated using multivariate normal and nonnormal distribution ***,to prove the applicability of the proposed model in a realmanufacturing setting,the model was evaluated using real-world normal and non-normal *** results demonstrate that the proposed GRU-RF-RTC outperforms other methods in detecting process shifts quickly with the lowest average out-of-control run length(ARL1)in all synthesis and real-world problems under normal and non-normal *** experiment results on real-world problems highlight the significance of the proposed GRU-RF-RTC model in modern manufacturing process monitoring *** result reveals that the proposed method improves the shift detection capability by 42.14%in normal and 43.64%in gamma distribution problems.

关键词： Smart manufacturing process monitoring quality control gated recurrent unit neural network random forest

来源：评论

学校读者我要写书评

暂无评论

Combination of CRITIC and PROMETHEE II Methods as An Early Detection of Potential Dropout Students

Combination of CRITIC and PROMETHEE II Methods as An Early D...

引用

International Conference on information and Communications Technology (ICOIACT)

作者： Mochammad Yusa Funny Farady Coastera Deni Rahmadani Julia Purnama Sari Kusrini Kusrini Anggit Dwi Hartanto Department of Informatics Faculty of Engineering University of Bengkulu Bengkulu Indonesia Department of Information System Faculty of Engineering University of Bengkulu Bengkulu Indonesia Magister of Informatics Engineering Faculty of Computer Science Universitas AMIKOM Yogyakarta Yogyakarta Indonesia Department of Information System Faculty of Computer Science Universitas AMIKOM Yogyakarta Yogyakarta Indonesia

Dropout (DO) has negative implications for individuals and educational institutions. The field of education data mining (EDM) offers valuable contributions to prevent dropout cases and improve student retention. This study focuses on implementing EDM to identify students at risk of dropping out by integrating academic activity criteria with real-time data sources. Previous studies have encountered limitations in classification and clustering techniques, with classification relying on labeled training data (supervised learning) and clustering constrained by attribute or criteria weight (unsupervised learning). This study aims to address these limitations by combining the PROMETHEE II ranking approach and the CRITIC weighting method, producing a list of students with dropout potential. The results can aid stakeholders in implementing preventive measures. The study involves several steps: 1) Collecting data through integration with academic portals; 2) Filtering and selecting criteria for student academic activities; 3) Transforming and normalizing the data; 4) Applying automatic weighting using CRITIC; 5) Calculating criteria rankings using the PROMETHEE II technique; and 6) Validating the ranking outcomes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multi-Head Self-Attention Transformer-Based Method for Prediction of Drug-Drug Interactions

Enhanced Multi-Head Self-Attention Transformer-Based Method ...

引用

International Symposium on Digital Forensic and Security (ISDFS)

作者： Semih Cal Ramazan Ozgur Dogan Hulya Dogan Department of Engineering Computer Science & Physics Otterbein University Westerville OH USA Department of Artificial Intelligence Engineering Faculty of Computer and Information Sciences Trabzon University Trabzon Türkiye Department of Software Engineering Faculty of Engineering Karadeniz Technical University Trabzon Türkiye

ISBN: (数字)9798331509934

ISBN: (纸本)9798331509941

The usage of various drugs has increased significantly in recent years, leading to a higher possibility of drug-drug interactions (DDIs). The concurrent usage of multiple drugs can result in potentially hazardous interactions, making it crucial to foresee DDIs to prevent adverse effects and enhance patient safety. Traditional DDI prediction methods often require extensive examinations, which can be time consuming and resource intensive. As a result, automatic DDI prediction methods have gained attention in the literature, offering clinicians support for making more accurate decisions and designing effective treatment plans. Despite progress in DDI prediction studies, substantial challenges remain in the field. Our study addresses these challenges by proposing a deep learning-based model leveraging drug features. Specifically, this study introduces an enhanced multi-head self-attention transformer-based method, which incorporates pharmacological features to achieve improved performance. The proposed method consists of two primary stages: feature extraction and model design. To evaluate the efficacy of the proposed method, performance evaluation procedures -Accuracy (ACC), Precision (PRE), Recall (REC), and F -Score-are utilized. Comparative experiments are conducted with several state-of-the-art methods on a data set specifically created for this study. Out of all, the proposed method achieves mean values of ACC, PRE, REC, and F-Score as 87.49%, 87.19%, 82.76%, and 84.56 %, respectively, surpassing the performance of other methods. The results unequivocally demonstrate the effectiveness and superiority of the proposed method in predicting DDIs.

关键词： Drugs Learning systems Accuracy Predictive models Feature extraction Transformers Robustness Safety Matrix decomposition Security

来源：评论

学校读者我要写书评

暂无评论

Fitweet: Arduino-Based Smartwatch for Early Anticipatory Anxiety Notification system 9th

Fitweet: Arduino-Based Smartwatch for Early Anticipatory Anx...

引用

9th International Conference on Computational science and Technology, ICCST 2022

作者： Abdulmanab, Muhammad Rahiman Nor’Azman, Nur Faidz Hazirah Meon, Hasni Razak, Chempaka Seri Abdul Ab Hamid, Siti Hafizah Department of Software Engineering Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur Malaysia Department of Communication Faculty of Communication Visual Art and Computing Universiti Selangor Bestari Jaya Malaysia School of Pre-University Studies Taylor’s College Lakeside Campus Subang Jaya Malaysia

ISBN: (纸本)9789811984051

As anxiety becomes increasingly prevalent among youths especially university students, early prevention via anxiety disorder profiling is crucial. Nevertheless, most screening tools to date are not automated, labour-intensive and time-consuming. Mental health detection in online social networks (OSNs) using artificial intelligence (AI) can provide means for capturing overlooked behavioural attributes, but few are centred around anxiety detection. Internet of Things (IoT)’s increasing popularity enables bio-signals monitoring to aid in mental health care. However, minimum research has been devoted to IoT-based assistive technologies for anxiety, which currently are only used by individuals already diagnosed and actively monitored. This study proposes a novel approach to anticipatory anxiety detection for Malaysian university students aged between 18 and 25 inclusive as an early notification system using AI and IoT for bilingual Malay and English tweets and vital signs analysis respectively. Our result shows that Logistic Regression with Bag-of-Words (BoW) is the overall best performing model with 81.06% accuracy. The Arduino smartwatch sensor readings from the MAX30102 pulse oximeter sensor are used to determine different body conditions using a rule-based approach. The comparison test result between the prototype and conventional measuring devices shows the prototype’s ability to accurately distinguish vital signs with a relatively low Mean Absolute Percent Error (MAPE) rate of 10.92% and 1.51% for pulse rate and temperature respectively. Together, our proof-of-concept results indicate the potential of AI and IoT in deriving new measures of anxiety, by analysing social data combined with bio-signals monitoring to alert users regarding their anxiety state. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Code Smell Detection Using Whale Optimization Algorithm

引用

computers, Materials & Continua 2021年第8期68卷 1919-1935页

作者： Moatasem M.Draz Marwa S.Farhan Sarah N.Abdulkader M.G.Gafar Department of Software Engineering Faculty of Computers and InformationKafrelsheikh UniversityKafr ElsheikhEgypt Faculty of Informatics and Computer Science British University in EgyptCairoEgypt Department of Information Systems Faculty of Computers and Artificial IntelligenceHelwan UniversityCairoEgypt Department of Computer Science Faculty of Computers and Artificial IntelligenceHelwan UniversityCairoEgypt Faculty of Computer Studies Arab Open UniversityCairoEgypt Department of Computer Science College of Science and Humanities in Al-SulailPrince Sattam bin Abdulaziz UniversityKharjSaudi Arabia Department of Machine Learning and Information Retrieval Faculty of Artificial IntelligenceKafrelsheikh UniversityKafr ElsheikhEgypt

software systems have been employed in many fields as a means to reduce human efforts;consequently,stakeholders are interested in more updates of their *** smells arise as one of the obstacles in the software *** are characteristics of software source code that indicate a deeper problem in *** smells appear not only in the design but also in software *** smells introduce bugs,affect software maintainability,and lead to higher maintenance *** code smells can be formulated as an optimization problem of finding the best detection *** researchers have recommended different techniques to improve the accuracy of code smell detection,these methods are still unstable and need to be *** research has sought only to discover a few at a time(three or five types)and did not set rules for detecting their *** research improves code smell detection by applying a search-based technique;we use the Whale Optimization Algorithm as a classifier to find ideal detection *** this algorithm,the Fisher criterion is utilized as a fitness function to maximize the between-class distance over the withinclass *** proposed framework adopts if-then detection rules during the software development life *** rules identify the types for both medium and large *** are conducted on five open-source software projects to discover nine smell types that mostly appear in *** proposed detection framework has an average of 94.24%precision and 93.4%*** accurate values are better than other search-based algorithms of the same *** proposed framework improves code smell detection,which increases software quality while minimizing maintenance effort,time,and ***,the resulting classification rules are analyzed to find the software metrics that differentiate the nine code smells.

关键词： software engineering intelligence search-based software engineering code smell detection software metrics whale optimization algorithm fisher criterion

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：