检索结果-内蒙古大学图书馆

Informatica (Slovenia) 2025年第11期49卷 149-164页

作者： Khaleel, Z.S. Lakizadeh, Amir Computer Engineering and Information Technology Department University of Qom Qom Iran Department of mathematic Open Educational College Basra Study Center Iraq

Alzheimer's Disease (AD) is a neurological disorder marked by cognitive deterioration and neurological impairment that affects cognition, memory, and behavioral patterns. Alzheimer's is an incurable disease that predominantly impacts individuals over the age of 40. A patient's MRI (Magnetic Resonance Imaging) scan and cognitive assessment are manually analyzed to diagnose Alzheimer's disease. Recently, Artificial Intelligence (AI), particularly through Deep Learning, has pioneered innovative techniques for automated medical image identification. We devised a deep learning methodology for Alzheimer's disease identification utilizing Magnetic Resonance Imaging (MRI) data. The suggested method, termed Res+FSBILSTM, employs ResNet50 as a pre-trained model for feature extraction from MRIs, thereafter identifying Alzheimer's disease through a Fully-Stack Bidirectional Long-Short Term Memory deep learning model. The experimental results demonstrate that the suggested method surpasses state-of-the-art techniques across all evaluation metrics, rendering it a viable tool for medical professionals in identifying Alzheimer's disease using brain radiological images. Ultimately, we achieved results with an accuracy of 99.6%, an F1-score of 97.7%, an area under the curve of 99%, a recall of 97.3%, and a precision of 99.6%. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Control of Active and Reactive Power for a Single-Phase Grid-Connected Photovoltaic system Using Integral Sliding Mode Control with a Fixed Switching Frequency 50

Control of Active and Reactive Power for a Single-Phase Grid...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Lamkharbach, Youssef Bennani, Hakim Chebak, Ahmed Mohammed VI PolytechnicUniversity Ben Guerir Morocco Mathematic Computer and Engineering Department University of Quebec Rimouski Canada

ISBN: (纸本)9781665464543

This paper introduces a novel approach for controlling the active and reactive power output photovoltaic single-stage Single-Phase Grid-Connected with LCL filter. The proposed method regulates power through the injection of current utilizing a nonlinear integral sliding mode control (ISMC) with a constant switching frequency which significantly reduces current tracking error and achieves a Total Harmonic Distortion (THD) in the vicinity of 1,4%. The performance of the proposed method is tested against tracking of maximum PV power and regulate the power reactive injected into or absorbed from the grid via a simulation in MATLAB/Simulink. © 2024 IEEE.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Undercover Disruption: Stealth Jamming Attacks on 5G Synchronization Stages

Undercover Disruption: Stealth Jamming Attacks on 5G Synchro...

引用

2025 Joint National Conference on Cybersecurity, ITASEC and SERICS 2025

作者： Alaimo, Rosolino Corallo, Roberto Schilleci, Silvia Dino, Alessandra Mangione, Stefano Tinnirello, Ilenia Garlisi, Domenico University of Palermo Engineering Department Palermo Italy University of Palermo Mathematic and Computer Science Department Palermo Italy CNIT Parma Italy

This paper presents a comprehensive study on selective jamming, focusing on its impact on the synchronization phases of the 5G New Radio (NR). We introduce STORM, a novel framework tool designed to assess jamming attacks on the cell search phases of 5G User Equipment (UE). The research incorporates both simulation and experimental evaluations, providing a detailed account of the methodology employed. A unique aspect of the proposed approach is the implementation of a jamming technique that remains undetectable to external entities due to its synchronization with the gNB’s Synchronization Signal Block (SSB). Furthermore, the implemented jamming operates at a duty cycle of 3.55% of continuous jamming, leading to significant optimization in terms of energy consumption and computational resources. STORM underscores that the success rate of jamming attacks and the necessary Signal to Interference Ratio (SIR) for effective disruption are significantly influenced by the specific configurations of the jamming signal. The paper discovers that the Primary Synchronization Signal (PSS) exhibits a higher degree of resilience compared to the Secondary Synchronization Signal (SSS), requiring a greater jammer transmission power to interfere with the cell search procedure. © 2025 Copyright for this paper by its authors.

关键词： 5G 5G security Jamming Attacks PSS Selective Jamming SSS User Equipment

来源：评论

学校读者我要写书评

暂无评论

Automatic Adjustment in Newton Power Flow for Including Voltage Control in Wind Farm

Automatic Adjustment in Newton Power Flow for Including Volt...

引用

2023 IEEE PES/IAS PowerAfrica, PowerAfrica 2023

作者： Bennani, Hakim Chebak, Ahmed Ouafi, Abderrazak El University of Quebec at Rimouski Mathematic Computer and Engineering Department Rimouski Canada Green Teck Institute Mohamed Vi Polytechnic University Benguerir Morocco

ISBN: (纸本)9798350337556

This paper addresses in a Newton-based power flow algorithm the automatic adjustment of control variables when a bus voltage is simultaneously controlled by multiple wind turbines (WTs). The objective is to properly handle in Newton's algorithm the centralized voltage control in a wind farm (WF) to achieve effective voltage regulation at the point of common coupling (PCC). The proposed solution is automatically adjusted in a coordinated and simultaneous manner and allows a direct solution of the control variables by incorporating the adjustment equality constraints of the control strategy into the Jacobian matrix. It is demonstrated that the proposed solution provides accurate results and significantly improves the numerical performance of the power flow solution. © 2023 IEEE.

关键词： Voltage control

来源：评论

学校读者我要写书评

暂无评论

The Development of Multibeam Quarter-Cut Radial Line Slot Array (RLSA) Antennas

引用

Progress in Electromagnetics Research Letters 2024年 123卷 7-13页

作者： Purnamirza, Teddy Shardarbekovich, Junisbekov M. Yusma, Muhammad Reynaldi Ibrahim, Muhammad I. Batyrbekovich, Kabanbayev A. Rahmi, Depriwana Electrical Engineering Department Universitas Islam Negeri Sultan Syarif Kasim Pekanbaru Indonesia Taraz Regional University named after M. Kh. Dulaty Taraz Kazakhstan Faculty of Electronic and Computer Engineering Universiti Teknikal Malaysia Malaka Malaka Malaysia Department of Mathematic Educations Faculty of Educations and Teachers Training Universitas Islam Negeri Sultan Syarif Kasim Pekanbaru Indonesia

This research aimed to introduce multibeam quarter-cut Radial Line Slot Array (RLSA) antennas for the first time. These antennas are distinct from the multibeam full-circle RLSA due to the use of quarter RLSA, making it suitable for small devices. To achieve beams directed to the backside, an unconventional approach was taken by placing slots on the antenna’s background. A technique comprising the deletion of specific slot pairs in the radiating element was introduced to balance the gain and beam shape. Furthermore, thirty-six multibeam quarter RLSA models were designed and simulated. The best model was then fabricated and measured to validate the simulation results. Consequently, the results showed the possibility of designing multibeam antennas with symmetrical beams in terms of gain, direction, and beamwidth, which were 6.23 dBi, 37◦, 145◦, and 34◦, respectively. The gain of 6.23 dBi was 3 dB less than the single-beam antennas, consistent with the theory of beam splitting. Additionally, antennas exhibited low reflection and a broad bandwidth suitable for Wi-Fi needs. Finally, the agreement between measurement and simulation validated the design of antennas. © 2024, Electromagnetics Academy. All rights reserved.

关键词： Multibeam antennas

来源：评论

学校读者我要写书评

暂无评论

Prediction of Drug-Target Interactions Through the Application of Supervised Machine Learning Algorithms 1

Prediction of Drug-Target Interactions Through the Applicati...

引用

1st IEEE International Conference on Emerging Research in Computational Science, ICERCS 2023

作者： Mahammad Rafi, D. Chandrashekar, Rakesh Veena, C.H. Dutt, Amit Waghmare, Shwetambari Pandurang Yamini Supriya, B. Institute of Aeronautical Engineering Department of Computer Science and Engineering Telangana Hyderabad India New Horizon College of Engineering Department of Mechanical Engineering Bangalore India Institute of Aeronautical Engineering Hyderabad India Lovely Professional University Phagwara India Bharati Vidyapeeth College of Engineering Department of Mathematic Navi Mumbai India Koneru Lakshmaiah Education Foundation Department of Cse AP Vaddeswaram India

ISBN: (纸本)9798350359756

Numerous machine learning strategies have been utilized and evaluated to improve and optimize predictions of drug-target interactions. The Support Vector Machines (SVM) demonstrated exceptional performance, with an accuracy of 92.3% and an AUC-ROC of 0.97. Random Forests, applying the capability of ensemble researching, established fantastic overall performance with an accuracy of 94.1% and an AUC-ROC of 0.98. The Neural Networks executed a 93.5% accuracy and an AUC-ROC of 0.98 proving its capacity to capture complicated data patterns. Meanwhile, Gradient Boosting Machines (GBM) attained an accuracy of 93.8% and an AUC-ROC rating of 0.97. In addition, three distinct approaches have been tested to benefit comparative insights. Linear Regression (LR) gave an accuracy of 88.7% and an AUC-ROC of 0.94, conveying an understanding on the limitations of linear patterns on this topic. The k-Nearest Neighbors (okay-NN) set of rules done an accuracy of 90.2% and an AUC-ROC of Emphasizing the virtues and ability downsides of instance-primarily based gaining knowledge of, the textual content addresses the significance of 0.95. Decision Trees (DT) finished a 91.5% accuracy price with an AUC-ROC price of 0.96, proving their usefulness in making informed decisions. To recap, at the same time as each set of regulations displayed mind-blowing effectiveness, ensemble solutions, notably Random Forests, only barely passed the overall performance of diverse techniques. The outcomes underscore the modern potential of machine learning algorithms in drug-goal interaction predictions, giving a hopeful trajectory for the destiny of drug discovery. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Control of Active and Reactive Power for a Single-Phase Grid-Connected Photovoltaic system Using Integral Sliding Mode Control with a Fixed Switching Frequency

Control of Active and Reactive Power for a Single-Phase Grid...

引用

Annual Conference of Industrial Electronics Society

作者： Youssef Lamkharbach Hakim Bennani Ahmed Chebak Green Tech Institute (GTI) Mohammed VI PolytechnicUniversity Morocco Mathematic Computer and Engineering Department University of Quebec Rimouski Canada

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

关键词： Photovoltaic systems Robust control Industrial electronics Reactive power Total harmonic distortion Switching frequency Complexity theory MATLAB Sliding mode control Power harmonic filters

来源：评论

学校读者我要写书评

暂无评论

Implementation of Preprocessing in Text Summarization Techniques for Indonesian Language Documents Using the Flax T5 Approach 11

Implementation of Preprocessing in Text Summarization Techni...

引用

11th International Conference on Cyber and IT Service Management, CITSM 2023

作者： Lubis, Arif Ridho Safitri, Habibi Ramdani Irvan Lubis, Muharman Al-Khowarizmi Nugroho, Okvi Politeknik Negeri Medan Department of Computer Engineering and Informatics Medan Indonesia Universitas Muhammadiyah Sumatera Utara Department of Mathematic Education Medan Indonesia Telkom University School of Industrial Engineering Bandung Indonesia Universitas Muhammadiyah Sumatera Utara Department of Information Technology Medan Indonesia Kulkas It Medan Indonesia

ISBN: (纸本)9798350305968

As information develops, many individuals or communities change their habits in obtaining information, which is usually consumed in large quantities, so that sometimes it is difficult to understand, it becomes easier to get information in summary form, so this research applies the text summarization technique to Indonesian language documents using the Flax T5 model. is the development of transformer-based google. The results of this study are the use of parameters from the Flax T5 model that can affect the performance of text summaries, evidenced by the number of epochs 20, batch size 64 producing ROUGE-1 of 0.24. the ROUGE-2 value is 0.3 and the ROUGE-L value is 0.31, while the epoch value is 60, batch size 128 makes ROUGE-1 0.35, ROUGE-2 value is 0.38 and the ROUGE-L value is 0.36. while the epoch value of 100 and the batch size value of 256 produce a ROUGE-1 value of 0.5, a ROUGE-2 value of 0.54, and a ROUGE-L value of 0.55. However, this model has limitations in text lengths of more than 150 because it will make the training time so long that it is highly recommended not to use text lengths that exceed 150 words. © 2023 IEEE.

关键词： Flax

来源：评论

学校读者我要写书评

暂无评论

Causal loop and Stock-Flow Modeling of Signal Transduction Pathways

arXiv

引用

arXiv 2024年

作者： Sulaimany, Sadegh Bidkhori, Gholamreza Khoshnaw, Sarbaz H.A. Department of Computer Engineering University of Kurdistan Sanandaj Iran Science for Life Laboratory Sweden Department of Mathematic University of Raparin Kurdistan Region Ranya Iraq

System dynamics is a popular approach in many fields of science and technology, but it has not been investigated for cell signaling pathways yet. It is a well formulated methodology used to analyze the components of a system considering the cause-effect relationships. The two main components of system dynamics modeling, Causal Loop and Stocks-Flow diagrams, make possible to model the dynamics of the system with the ability to analyze it both qualitatively and quantitatively. In this paper, after introducing the system dynamics modeling approach, and giving a simple example from its usage for Michaelis Menton reactions, a three-step process is proposed for signal transduction modeling. Then in a complete example, it is applied to a case study in cell signaling pathways, namely the RKIP Influence on the ERK signaling pathway and the results is compared with an integrative modeling approach based on Petri net and ODEs. Computational simulations show the success of the system dynamic in easier and effective modeling of the cell signaling pathways, in addition to its diverse options for understanding and testing the pathway quantitatively and quantitatively at the same time in relation to other methods. More intestinally, the suggested approach here helps one to identify all biochemical reaction paths and loops for complex cell signaling pathways. It will be a good step forward to define dominant systems for such complex cell signaling pathways. © 2024, CC BY.

关键词： System theory

来源：评论

学校读者我要写书评

暂无评论

New insight in cervical cancer diagnosis using convolution neural network architecture

arXiv

引用

arXiv 2024年

作者： Khozaimi, Ach Mahmudy, Wayan Firdaus Department of Computer Science Faculty of Engineering Universitas Trunojoyo Madura Indonesia Department of Mathematics Faculty of Mathematic and Natural Sciences Brawijaya University Malang Indonesia Department of Informatics Engineering Faculty of Computer Science Brawijaya University Malang Indonesia

The Pap smear is a screening method for early cervical cancer diagnosis. The selection of the right optimizer in the convolutional neural network (CNN) model is key to the success of the CNN in image classification, including the classification of cervical cancer Pap smear images. In this study, stochastic gradient descent (SGD), root mean square propagation (RMSprop), Adam, AdaGrad, AdaDelta, Adamax, and Nadam optimizers were used to classify cervical cancer Pap smear images from the SipakMed dataset. Resnet-18, Resnet-34, and VGG-16 are the CNN architectures used in this study, and each architecture uses a transfer-learning model. Based on the test results, we conclude that the transfer learning model performs better on all CNNs and optimization techniques and that in the transfer learning model, the optimization has little influence on the training of the model. Adamax, with accuracy values of 72.8% and 66.8%, had the best accuracy for the VGG-16 and Resnet-18 architectures, respectively. Resnet-34 had 54.0%. This is 0.034% lower than Nadam. Overall, Adamax is a suitable optimizer for CNN in cervical cancer classification on Resnet-18, Resnet-34, and VGG-16 architectures. This study provides new insights into the configuration of CNN models for Pap smear image analysis. © 2024, CC BY-SA.

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：