检索结果-内蒙古大学图书馆

22nd IEEE/ACIS International Conference on Software engineering Research, Management and Applications, SERA 2024

作者： Leelaprute, Pattara Kase, Yuki Amasaki, Sousuke Aman, Hirohisa Yokogawa, Tomoyuki Kasetsart University Department of Computer Engineering Faculty of Engineering Bangkok Thailand Okayama Prefectural University Department of Systems Engineering Soja Japan Center for Information Technology Ehime University Matsuyama Japan

ISBN: (纸本)9798350391343

CONTEXT: Web applications are exposed to malicious accesses through the Internet. SQL injection (SQLi) attacks are still a typical threat to web application providers. Although recent studies proposed deep learning-based SQLi attack detection models with high performance, those studies were not evaluated under the same conditions. Crucial aspects other than the predictive performance were also overlooked. OBJECTIVE: To evaluate SQLi attack detection models from multi-aspects related to its operation. METHOD: Three aspects, namely, predictive performance, detection speed, and operation costs, were applied to deep learning-based SQLi attack detection models. RESULTS: No DL-based model beaten a conventional machine learning-based model, Random Forests. CONCLUSION: Researchers must evaluate DL-based SQLi attack detection models with conventional ones with hyper-parameter tuning. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Development of a Lower Limb Gait Asymmetry Index with Cyclogram Analysis Using Image Processing 12

Development of a Lower Limb Gait Asymmetry Index with Cyclog...

引用

12th RSI International Conference on Robotics and Mechatronics, ICRoM 2024

作者： Etaati, Sepideh Javaherat, Fatemeh Delrobaei, Mehdi K. N. Toosi University of Technology Faculty of Electrical Engineering Department of Mechatronics Tehran Iran K. N. Toosi University of Technology Advanced Robotics and Automated Systems lab. Faculty of Mechanical Engineering Tehran Iran

ISBN: (纸本)9798331529734

Ahstract- This study focuses on developing a gait asymmetry index and applying image processing techniques to cyclogram analysis. We evaluated gait asymmetry under different walking conditions, specifically examining the effects of wearing a knee brace and holding a weight in hand. Using inertial measurement units (IMUs), we collected gait data to analyze knee, hip, and ankle angles in the sagittal plane. The joint kinematics data were assessed using our proposed asymmetry index, which combines image processing techniques and linear regression models. The proposed asymmetry index incorporates cyclogram area, trend symmetry, and the longest length of the cyclogram shape, effectively capturing variations in symmetry and providing a comprehensive measure. The results demonstrate that the proposed asymmetry index can effectively distinguish between different gait conditions. The findings potentially offer insights for researchers and clinicians in human biomechanics, aiding in the planning of interventions and the assessment of motion patterns, as well as for developers of bipedal walking robots in the field of robotic locomotion, enhancing their ability to design hardware and evaluate motion patterns. © 2024 IEEE.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Leveraging UAV-assisted communications to improve secrecy for URLLC in 6G systems

引用

Digital Communications and Networks 2023年第6期9卷 1458-1464页

作者： Hemant Kumar Narsani Ali Ranjha Kapal Dev Fida Hussain Memon Nawab Muhammad Faseeh Qureshi Faculty of Engineering and Technology University of SindhPakistan Department of Electrical Engineering Ecole de Technologie Superieure Montreal QCCanada Department of Institute of Intelligent Systems University of JohannesburgSouth Africa Department of Electrical Engineering Sukkur IBA UniversityPakistan Department of Computer Education Sungkyunkwan UniversitySeoulRepublic of Korea

Unmanned Aerial Vehicles(UAVs)will be essential to support mission-critical applications of Ultra Reliable Low Latency Communication(URLLC)in futuristic Sixth-Generation(6G)***,several security vulnerabilities and attacks have plagued previous generations of communication systems;thus,physical layer security,especially against eavesdroppers,is vital,especially for upcoming 6G *** this regard,UAVs have appeared as a winning candidate to mitigate security *** this paper,we leverage UAVs to propose two *** first method utilizes a UAV as Decode-and-Forward(DF)relay,whereas the second method utilizes a UAV as a jammer to mitigate eavesdropping attacks for URLLC between transmitter and receiver ***,we present a low-complexity algorithm that outlines the two aforementioned methods of mitigating interception,*** secrecy rate,and we compare them with the benchmark null method in which there is a direct communication link between transmitter and receiver without the UAV DF ***,simulation results show the effectiveness of such methods by improving the secrecy rate and its dependency on UAV height,blocklength,decoding error probability and transmitter-receiver separation ***,we recommend the best method to enhance the secrecy rate in the presence of an eavesdropper based on our simulations.

关键词： URLLC UAV-Assisted communications 6G systems Secrecy rate

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach for Detecting Diabetic Retinopathy

A Deep Learning Approach for Detecting Diabetic Retinopathy

引用

2024 International Conference on Computer and Applications, ICCA 2024

作者： Nabil, Mohamed Hossam Hassan Hammam, Laila Bastawrous, Hany Ayad Ebrahim, Gamal A. The British University in Egypt Electrical Engineering Department Cairo Egypt Delft University of Technology Faculty of Electrical Engineering Mathematics and Computer Science Delft Netherlands Ain Shams University Faculty of Engineering Computer and Systems Engineerig Department Cairo Egypt

ISBN: (纸本)9798350367560

The World Health Organization (WHO) reports that diabetic retinopathy affects one-third of diabetics, regardless of their stage of the disease. Several research efforts are focused on its automated detection and diagnosis. Identifying diabetic retinopathy is crucial due to the damage that occurs to the blood vessels of the eye retina, leading to vision blur or even complete blindness. Thus, an annual checkup is needed for people with diabetes. Moreover, uncontrolled sugar levels for diabetes patients could worsen the current stage of diabetic retinopathy. Consequently, automated detection can greatly contribute to the treatment of disease. This can be carried out through several algorithms, including deep learning models and support vector machines, in addition to transfer learning. This contribution proposes a new approach for diabetic retinopathy automated detection based on convolutional neural network (CNN) models. The proposed model provides both binary and multi-class detection. Both scenarios have shown promising results, where the training accuracies of both the binary classification and the multi-class are 92% and 94%, respectively. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Design of 5G 28 GHz Beam-steerable Series-Fed Array Antenna with 4x4 Butler Matrix 25

Design of 5G 28 GHz Beam-steerable Series-Fed Array Antenna ...

引用

25th International Seminar on Intelligent technology and Its Applications, ISITIA 2024

作者： Rahayu, Yusnita Yamada, Yoshihide Syam, Ahmad Mudhhirulhaq Universitas Riau Faculty of Engineering Department of Electrical Engineering Pekanbaru Indonesia Universiti Teknologi Malaysia Malaysia-Japan International Institute of Technology Department of Electronic Systems Engineering Kuala Lumpur Malaysia

ISBN: (纸本)9798350378573

Base station 5G antennas in the 28 GHz frequency spectrum must have strong gain to account for severe propagation loss. Focusing high gain in one radiation direction increases coverage distance. Using CST Studio Suite, this research constructs a beam-steerable series-fed array antenna. The design combines a butler matrix circuit to adjust beam radiation angle and a 64-element series-array antenna to create a huge centralized gain. RT Duroid 5880 (0.254 mm) is the substrate. Simulated antenna results show a 28 GHz operating frequency, -10 dB reflection coefficient (S11), and 18.16-18.6 dBi gain. Beam-steering simulations reveal that the antenna design may create four successive beam angles of -7°, +20°, -20°, and +7°. © 2024 IEEE.

关键词： Microwave antennas

来源：评论

学校读者我要写书评

暂无评论

Bridging the Gap: Secure Northbound Interface in SDN with gRPC 5

Bridging the Gap: Secure Northbound Interface in SDN with gR...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Rathnayake, R.M.K.G. Kalana, K.A.V. Dharmakeerthi, Uditha Senarathne, Amila Sri Lanka Institute of Information Technology Faculty of Computing Department of Computer Systems Engineering Malabe Sri Lanka

ISBN: (纸本)9798350358131

Software Defined Networking (SDN) promises to introduce flexibility and programmability into networks by offering developers a northbound interface (NBI) to create SDN applications. However, current designs and implementations have drawbacks, including the lack of Proper Standardization, Controller-Lock-In Situation, and Loss of Compatibility with SDN applications. Using Google Remote Procedure Call (gRPC) Application Programming Interface (API), the SDN controller can offer network resources, such as statistics, flow information, or topology data, to registered SDN applications. Furthermore, the gRPC enables controller-agnostic and language-agnostic development to enable proactive and reactive applications and services to interact with controller services. Transport Layer Security (TLS) enables confidentiality with encryption, authenticity with mutual authentication, and integrity with Message Authentication Code (MAC). Finally, Attribute-based Access Control (ABAC) and Logging capability for controller services allow fine-grained access control and accountability enforcement to ensure the security goals of the NBI. This research paper provides a complete architecture to converge different Northbound API streams into one secure, language-agnostic, controller-agnostic API stream with the help of the gRPC framework. © 2023 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

NUMERICAL ASPECTS OF THE CO-ROTATING VORTEX PAIR PROBLEM IN AEROACOUSTICS 10

NUMERICAL ASPECTS OF THE CO-ROTATING VORTEX PAIR PROBLEM IN ...

引用

10th Convention of the European Acoustics Association, EAA 2023

作者： Ulveczki, Mihály Ádám Rucz, Péter Faculty of Electrical Engineering and Informatics Dept. of Networked Systems and Services Budapest University of Technology and Economics Hungary

ISBN: (纸本)9788888942674

The co-rotating vortex pair is a well-known test problem for validating aeroacoustic computational frameworks. Both the flow field and the radiated acoustic far-field can be determined analytically, which allows for the direct comparison of all associated quantities. However, in order to simulate the vortex pair using numerical methods, several approximations must be made. One problem is caused by the singular velocity field at the center of the potential vortex, which must be treated by desingularization that also affects the resulting source terms. Another challenge in finite element formulations is the handling of the unbounded domain, which needs to be artificially truncated. In our paper, the numerical aspects of the vortex pair problem are examined. The effects of the necessary approximations including the desingularization of the vortex-core and discretization to different computational methods are investigated. A method relying on the direct integration of the source terms is compared to different finite element solution strategies. Convergence tests are carried out and discussed for formulations of Lighthill's equation and the perturbed convective wave equation in the frequency domain. © 2023 Ulveczki and Rucz. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

"Phrasefluent" - An Automated Solution for Children's Speech Disorders Identification and Therapy Treatment 5

"Phrasefluent" - An Automated Solution for Children's Speech...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Karunasekara, Pasan Deshitha, Sheshan De Alwis, Dinuja Karunarathna, Desan Lokuliyana, Shashika Gamage, Narmada Sri Lanka Institute Information Technology Faculty of Computing Department of Computer Systems Engineering Malabe Sri Lanka

ISBN: (纸本)9798350358131

PhraseFluent is a project to develop a complete web-based solution to help people who are suffering from speech disorders. This application is specifically designed for people who are suffering from articulation and stuttering speech disorders. There are few solutions available for speech disorders identification and speech therapies. Those available applications have several drawbacks that lead to the research gap for this research. Those findings do not have any disorder-specific speech detection methods. Those applications generally detect speech disorders not the type of the disorder. Also, the speech therapy exercises suggest applications are practicing words according to the order of the alphabet. Those solutions are not based on the sounds that need to be practiced in order to cure speech disorders. Also, applications that have detection mechanisms are not currently available for wide access. This application mainly contains React-based interactive interfaces and a Python-programmed backend with machine-learning algorithms for functionality. This application can help to automate the process of detecting speech disorders and suggest therapy activities. Also, this application can track the patient's progress with the therapies. Used datasets contain the data with 70% accuracy and the test results gave a 68% percent success rate. This approach will be the first step in automating the complete process of speech disorder diagnosis. © 2023 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

More (Enough) Is Better: Towards Few-Shot Illegal Landfill Waste Segmentation 27

More (Enough) Is Better: Towards Few-Shot Illegal Landfill W...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Molina, Matías Veloso, Bruno Ferreira, Carlos Abreu Ribeiro, Rita P. Gama, João Institute for Systems and Computer Engineering Technology and Science Portugal Faculty of Economics University of Porto Porto4200-464 Portugal Faculty of Sciences University of Porto Porto4169-007 Portugal Institute of Engineering of Porto Portugal

ISBN: (纸本)9781643685489

Image segmentation for detecting illegal landfill waste in aerial images is essential for environmental crime monitoring. Despite advancements in segmentation models, the primary challenge in this domain is the lack of annotated data due to the unknown locations of illegal waste disposals. This work mainly focuses on evaluating segmentation models for identifying individual illegal landfill waste segments using limited annotations. This research seeks to lay the groundwork for a comprehensive model evaluation to contribute to environmental crime monitoring and sustainability efforts by proposing to harness the combination of agnostic segmentation and supervised classification approaches. We mainly explore different metrics and combinations to better understand how to measure the quality of this applied segmentation problem. © 2024 The Authors.

关键词： Aerial photography

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection of Some Tajweed Rules 20

Automatic Detection of Some Tajweed Rules

引用

20th International Learning and technology Conference, L and T 2023

作者： Omran, Dahlia Fawzi, Sahar Kandil, Ahmed Cairo University Systems and Biomedical Engineering Faculty of Engineering Giza Egypt Nile University Information Technology & Computer Science Giza Egypt

ISBN: (纸本)9798350300307

correct understanding of the Holy Quran is an essential duty for all Muslims. Tajweed rules guide the reciter to perform Holy Quran reading exactly as it was uttered by Prophet Muhammad peace be upon him. This work focused on the recognition of one Quranic recitation rule. Qalqalah rule is applied to five letters of the Arabic Alphabet (Baa/Daal/Jeem/Qaaf/Taa) having sukun vowelization. The proposed system used the Mel Frequency Cepstral Coefficients (MFCC) as the feature extraction technique, and the Convolutional Neural Networks (CNN) model was used for recognition. The available dataset consists of 3322 audio samples from different surahs of the Quran for four professional readers (Sheihk) AlHussary, AlMinshawy, Abdel Baset, and Ayman Swayed. The best results were gained using Ayman Swayed audio samples with a validation accuracy of 90.8%. © 2023 IEEE.

关键词： Convolutional neural networks

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：