检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Web Services, ICWS 2023

作者： Zhou, Renjie Jin, Zhenming Wan, Jian Zhang, Jilin Guo, Xingyu Liu, Qiang Hangzhou Dianzi University Key Laboratory of Complex Systems Modeling and Simulation of the Ministry of Education School of Computer Science and Technology Hangzhou China Hangzhou Dianzi University Key Laboratory of Complex Systems Modeling and Simulation of the Ministry of Education Itmo Joint Institute Hangzhou China Zhejiang University of Science and Technology School of Information and Electronic Engineering Hangzhou China Zhejiang Police College Dept. of Computer and Information Technology Hangzhou China

ISBN: (纸本)9798350304855

The rapid development of the Internet has revo-lutionized our lives, providing us with an array of convenient services. However, this revolution has also led to the problem of data overload. Personalized recommendation services have been widely recognized as an effective solution to this problem by both the industrial and academic communities. Accurate prediction of click-through rate (CTR) is a critical task in personalized recommendation systems since it can improve the user's shopping experience, ultimately increasing revenue for the platform. To achieve accurate CTR prediction, it is crucial to capture user interests. While several methods for interest modeling exist, challenges related to user interest evolution and user behavior noise need further attention. This paper proposes a novel CTR prediction model named the Evolutionary Interest Representation Network (EIRN), which learns the evolving interest representation of users from their behaviors, profiles, and environmental attributes. In the model, we introduce an advertisement correlation graph decomposition layer and a noise filter layer to enhance and purify the user behavior representation. An interest extraction layer is designed to capture sequential correlations and common characteristics between user behaviors, representing their interests. Additionally, as user interests evolve over time and their importance changes, an attention-based interest evolution layer is designed to track the evolution of user interests. Our proposed method is validated using four public datasets and an industrial dataset, showing its superiority over existing CTR prediction methods. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Reference Tracking Control of a Nonlinear Epidemiological Model with State Estimation 9

Reference Tracking Control of a Nonlinear Epidemiological Mo...

引用

9th International Conference on Control, Decision and information Technologies, CoDIT 2023

作者： Csutak, Balázs Szederkényi, Gábor Pazmany Peter Catholic University Faculty of Information Technology and Bionics Budapest Hungary Institute for Computer Science and Control Systems and Control Laboratory Kende u. 13-17 BudapestH-1111 Hungary

ISBN: (纸本)9798350311402

In this paper, a reference tracking controller for an 8-compartment epidemic model is proposed. The dynamical model describing the disease spread and progression is given in nonlinear input-affine form. The manipulable input is the transmission rate, while the output to be tracked is the number of infected people. The model parameters correspond to the COVID-19 pandemic. The control design uses a simple SEIR model and it is based on feedback linearization combined with extended Kalman filter for state estimation. Simulation results show good tracking performance even with model mismatch and significant parameter uncertainty. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Efficient multimodal cancelable biometric system based on steganography and cryptography

引用

Iran Journal of computer Science 2023年第2期6卷 109-121页

作者： Salama, Gerges M. El-Gazar, Safaa Nassar, Rana M. El-Shafai, Walid Khalaf, Ashraf A. M. El-Banby, Ghada M. Hamed, Hesham F. A. El-Samie, Fathi E. Abd Department of Electrical Engineering Faculty of Engineering Minia University Minia 61111 Egypt Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf 32952 Egypt Security Engineering Laboratory Department of Computer Science Prince Sultan University Riyadh 11586 Saudi Arabia Department of Industrial Electronics and Control Engineering Faculty of Electronic Engineering Menoufia University Menouf 32952 Egypt Department of Electrical Engineering Faculty of Engineering Egyptian-Russian University Cairo Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh 84428 Saudi Arabia

Due to the development of hacking programs, it has become easy to penetrate systems. Hence, there is a need for strong security mechanisms. The use of traditional passwords has become insufficient to secure systems. Biometric authentication is now widely used for security applications, and it has proven to be superior compared to traditional authentication methods. However, two issues need to be considered in biometric systems. The first is not to keep biometric data in its original form in the database. If biometric traits are hacked, they will no longer be of use. Biometric data should be kept in cancelable forms for reuse. The second issue is the reliance on a single biometric, which limits the verification accuracy. This can be solved by using a multimodal biometric system. Using steganography and cryptography, this paper introduces a cancelable multimodal biometric system. As voiceprints, facial images, and fingerprint images are used. In this paper, the verification is performed through the Mel frequency cepstral coefficients (MFCCs) of the voiceprints. Steganography is used as a tool to secure features extracted from voiceprints by embedding them into the facial image using block-based singular value decomposition (BSVD). Double random phase encoding (DRPE) is utilized as an encryption algorithm to generate the final cancelable templates. To increase the level of system security, fingerprint images are used as random phase masks (RPMs). Verification is performed by estimating the correlation between registered and test MFCCs. The correlation value is then compared with a threshold value, which is calculated using the distribution curves for the genuine and imposter correlations. Equal error rate (EER) values close to zero and an area under the receiver operator characteristic curve (AROC) that is close to one are obtained from the simulation results, demonstrating the outstanding performance of the suggested system. The proposed system achieves good performan

关键词： BSVD Cancelable biometrics DRPE MFCCs

来源：评论

学校读者我要写书评

暂无评论

Vision transformer-convolution for breast cancer classification using mammography images: A comparative study

引用

International Journal of Hybrid Intelligent systems 2024年第2期20卷 67-83页

作者： Abimouloud, Mouhamed Laid Bensid, Khaled Elleuch, Mohamed Aiadi, Oussama Kherallah, Monji National Engineering School of Sfax University of Sfax Laboratory of Electrical Engineering (LAGE) University of KASDI Merbah Ouargla National School of Computer Science (ENSI) University of Manouba Artifcial Intelligence and Information Technology Laboratory (LINATI) Kasdi Merbah University Faculty of Sciences University of Sfax Advanced Technologies for Environment and Smart Cities (ATES Unit) University of Sfax

Breast cancer is a significant global health concern, highlighting the critical importance of early detection for effective treatment of women's health. While convolutional networks (CNNs) have been the best for analysing medical images, recent interest has emerged in leveraging vision transformers (ViTs) for medical data analysis. This study aimed to conduct a comprehensive comparison of three systems a self-attention transformer (VIT), a compact convolution transformer (CCT), and a tokenlearner (TVIT) for binary classification of mammography images into benign and cancerous tissue. Thorough experiments were performed using the DDSM dataset, which consists of 5970 benign and 7158 malignant images. The performance accuracy of the proposed models was evaluated, yielding results of 99.81% for VIT, 99.92% for CCT, and 99.05% for TVIT. Additionally, the study compared these results with the current state-of-the-art performance metrics. The findings demonstrate how convolution-attention mechanisms can effectively contribute to the development of robust computer-aided systems for diagnosing breast cancer. Notably, the proposed approach achieves high-performance results while also minimizing the computational resources required and reducing decision time. © 2024 - IOS Press. All rights reserved.

关键词： Breast cancer (BC) computer-aided diagnosis (CAD) convolutional networks (CNN) DDSM mammography vision transformers (VIT)

来源：评论

学校读者我要写书评

暂无评论

Data Assimilation Enhances WRF-Chem Performance in Modeling Volcanic Ash Clouds from Hunga Tonga–Hunga Ha’apai Eruption

引用

Journal of Meteorological Research 2024年第6期38卷 1122-1140页

作者： Hosni SNOUN Mohammad Mosaed ALAHMADI Amirhossein NIKFAL Abderrazak ARIF William HATHEWAY Meznah A.ALAMRO Alaeddine MIHOUB Moez KRICHEN Numthaja Co. Ltd.Jeddah23345Saudi Arabia Jülich Supercomputing Centre(JSC) Forschungszentrum JülichJülich52428Germany Institut National de la Météorologie Tunis Carthage2035Tunisia Free Researcher AustinTexas78666USA Department of Information Technology College of Computer&Information SciencePrincess Nourah Bint Abdul Rahman UniversityRiyadh11564Saudi Arabia Department of Management Information Systems and Production Management College of Business and EconomicsQassim UniversityBuraidah51452Saudi Arabia Faculty of Computer Science and Information Technology(FCSIT) Al-Baha UniversityAl-Baha65528Saudi Arabia ReDCAD Laboratory University of SfaxSfax3038Tunisia

Volcanic eruptions release large amounts of ash clouds and gas aerosols into the atmosphere,which can be simulated by air quality prediction ***,the performance of these models remains unsatisfactory,even though both relevant physics and chemistry are ***,exploring the approaches for improvement such as inclusion of data assimilation is *** this study,we depict the modeling of the volcanic ash dispersion from the Hunga Tonga–Hunga Ha’apai underwater volcano,which erupted in a series of large explosions in late December 2021 and early January *** 15 January 2022,a particularly significant explosion sent a massive ash cloud high into the *** used the inline Weather Research and Forecasting model coupled with chemistry(WRF-Chem)and incorporated meteorological data assimilation within the Flux Adjusting Surface Data Assimilation System(FASDAS).We compared three forecast scenarios:one with only meteorology and no chemistry(OMET),one with gas and aerosol chemistry and no assimilation(NODA),and one with both chemistry and assimilation(FASDAS).We found that FASDAS resulted in lower planetary boundary layer height(PBLH),downward surface shortwave flux,and 2-m temperature by up to 800 m,200 W m^(−2),and 6℃ on the land portion,respectively,while the opposite was observed near the eruption *** validated the model against the observations and the results showed that FASDAS significantly enhanced the model performance in retrieving meteorological ***,the simulations also revealed significant biases in the concentration of volcanic ash around the ash *** from the Copernicus TROPOspheric Monitoring Instrument Sentinel-5 Precursor(TROPOMI-S5P)showed a westward trend of the total SO2 *** work demonstrates the significant contribution of data assimilation to the results of operational air quality predictions during violent volcanic eruption events.

关键词： Hunga Tonga-Hunga Ha’apai volcano WRF-Chem Flux Adjusting Surface Data Assimilation System(FASDAS) data assimilation SO2 TROPOspheric Monitoring Instrument Sentinel-5 Precursor(TROPOMI-S5P)

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

System for Predicting Heart Disease using Sophisticated Machine Learning Techniques

System for Predicting Heart Disease using Sophisticated Mach...

引用

2023 IEEE Global Conference on information Technologies and Communications, GCITC 2023

作者： Pandey, Trilok Nath Bhusan Dash, Bibhuti Barik, Lalbihari De, Utpal Chandra Tripathy, Abinash Patra, Sudhansu Shekhar Vellore Institute of Technology School of Computer Science and Engineering Tamil Nadu Chennai India Kiit Deemed to Be University School of Computer Applications Bhubaneswar India King Abdul Aziz University Faculty of Computing and Information Technology in Rabigh Department of Information Systems Saudi Arabia Kiit Deemed to Be University School of Computer Applications Odisha Bhubaneswar India

ISBN: (纸本)9798350308167

Cardiovascular illness stands as a significant global health issue, and timely identification of this condition holds paramount importance to ensure effective intervention. In this paper, we introduce a fused model for anticipating heart ailments. This amalgamation incorporates four distinct algorithms: LightGBM, XGBoost, Multilayer Perceptron, and AdaBoost. Through an assessment on the Cleveland dataset, AdaBoost emerged as the most accurate with a precision of 0.985. Subsequently, XGBoost followed closely with an accuracy of 0.980, succeeded by LightGBM at 0.956, and Multilayer Perceptron at 0.936. To harness the collective power of these models, we employed a weighted bagging technique that accords weights to predictions based on their individual accuracy rates. The resultant composite model attained an accuracy of 0.96. This outcome is slightly lower than the model with the highest accuracy, as it involves a weighted mean calculation across model predictions. This study indicates the potential utility of the proposed methodology in cardiac disease prediction, leveraging the ensemble approach to potentially outperform standalone models. © 2023 IEEE.

关键词： AdaBoost Ensemble model Heart Disease LightGBM Machine Learning Multilayer Perceptron XGBoost

来源：评论

学校读者我要写书评

暂无评论

Enhancing MANETs Security Against Black Hole Attacks through Time-Based Node Analysis in AOMDV Protocol

Enhancing MANETs Security Against Black Hole Attacks through...

引用

Emerging Smart Technologies and Applications (eSmarTA), International Conference on

作者： Abdullah A. Naji Mogeeb A. Saeed Ammar H. Almagashi Alaa M. Ahmed Hashem S. Al-Atefi Mohammed N. Khaled Olayan M. Rashed Computer Network & Distributed Systems Department Al-Saeed Faculty Of Engineering &IT Taiz University Computer Networks & Distributed Systems Al-Saeed Faculty Of Engineering &IT Taiz University Computer Center & Information Technology Taiz University

ISBN: (数字)9798350354133

ISBN: (纸本)9798350354140

Mobile ad-hoc networks (MANETs) rely solely on direct node communication and function without a fixed infrastructure. Due to their decentralized design, they are susceptible to numerous security risks, with black hole attacks posing significant threats to routing integrity and confidentiality. This paper proposes a technique to enhance the Ad hoc On-Demand Multi-path Distance Vector (AOMDV) routing protocol's security against black hole attacks. The method involves a time-based reply message analysis to identify and mitigate malicious nodes. This algorithm improves the protocol's ability to detect and prevent black hole attacks by closely analyzing response time differences between malicious and normal nodes. The results of the simulation show that the suggested solution greatly enhances network performance by lowering the Routing Overhead Ratio from 1388.04% to 0.73% and the Packet Loss Rate from 74% to 11% while keeping a high Packet Delivery Ratio—up to 93% in different scenarios. These enhancements sustain strong data transmission in dynamic MANET environments, supporting network integrity and reliability.

关键词： Protocols Packet loss Routing Ad hoc networks Vectors Security Time factors

来源：评论

学校读者我要写书评

暂无评论

Development of a visual programming tool called SmrAI for function testing to mitigate the shortage of programming personnel in the manufacturing

Computer Software

引用

computer Software 2022年第4期39卷 61-74页

作者： Sugiyama, Ko-Ichiro Okuda, Satsuki Tanabe, Tsubasa Takao, Kouji Higashi, Hirohito Tanaka, Kazuaki Dept. of Information Engineering National Institute of Technology Matsue College Japan NIPPO Co. Ltd. Japan Ruby Programming Shounendan Japan Shimane IT Open-innovation Center Japan Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology Japan

We have developed a visual programming tool called SmrAI for function testing, and investigated whether wrapping existing source code with Scratch Blocks is an effective means of mitigating the shortage of programming personnel in the manufacturing. SmrAI is based on Smalruby, which can convert Scratch Blocks into Ruby code. In addition, SmrAI introduces two new sets of Blocks that wrap existing Ruby libraries for function testing. Since existing tools and libraries were utilized, the cost of developing SmrAI was low, and there were no changes in the function testing procedure. We conducted a verification test using staff members who were familiar with the function testing process but had little or no programming experience, and confirmed that they were able to program using SmrAI and that they had confidence in its business applications. These results are expected to contribute to the diversification and increase of programming personnel responsible for function test programming. © 2022 Japan Society for Software Science and technology. All rights reserved.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

CAMRI Loss: Improving the Recall of a Specific Class without Sacrificing Accuracy

CAMRI Loss: Improving the Recall of a Specific Class without...

引用

作者： Nishiyama, Daiki Fukuchi, Kazuto Akimoto, Youhei Sakuma, Jun Master's Program in Computer Science Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba-shi305-8577 Japan RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Department of Computer Science Faculty of Engineering Information and Systems University of Tsukuba Tsukuba-shi305-8577 Japan

In real world applications of multiclass classification models, misclassification in an important class (e.g., stop sign) can be significantly more harmful than in other classes (e.g., no parking). Thus, it is crucial to improve the recall of an important class while maintaining overall accuracy. For this problem, we found that improving the separation of important classes relative to other classes in the feature space is effective. Existing methods that give a class-sensitive penalty for cross-entropy loss do not improve the separation. Moreover, the methods designed to improve separations between all classes are unsuitable for our purpose because they do not consider the important classes. To achieve the separation, we propose a loss function that explicitly gives loss for the feature space, called class-sensitive additive angular margin (CAMRI) loss. CAMRI loss is expected to reduce the variance of an important class due to the addition of a penalty to the angle between the important class features and the corresponding weight vectors in the feature space. In addition, concentrating the penalty on only the important class hardly sacrifices separating the other classes. Experiments on CIFAR-10, GTSRB, and AwA2 showed that CAMRI loss could improve the recall of a specific class without sacrificing accuracy. In particular, compared with GTSRB's second-worst class recall when trained with cross-entropy loss, CAMRI loss improved recall by 9%. © 2023 The Institute of Electronics, information and Communication Engineers.

关键词： Deep learning

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：