检索结果-内蒙古大学图书馆

26th International computer science and engineering Conference, ICSEC 2022

作者： Jamil, Muhammad Usman Ahmad, Irfan Buatoom, Uraiwan Assumption University Department of Electrical and Computer Engineering Samut Prakan Thailand Faculty of Science and Arts Chanthaburi Thailand

ISBN: (纸本)9781665491983

In this paper, a robust adaptive (RA) radial basis function (RBF) neural network (NN) based backstepping control design is proposed for multi-input multi-output (MIMO) electrically driven robot manipulators (EDRM) with completely unmodeled dynamics, unknown nonlinearities, disturbance, and virtual control inputs. The proposed research methodology guarantees the controller's resilience even in the presence of parameter changes. The main idea of the backstepping control design is to reduce the error to zero via the use of parameter adjustment rules and a virtual control technique. The recursive backstepping design method treats specific system signals as virtual inputs to smaller subsystems. This novel control strategy guarantees the boundedness of the trajectory tracking error and also weight updates of NN. The key advantage of our control strategy is that it eliminates the requirement for regression matrices, the linear in parameter (LIP) assumption, and an offline learning phase. The results of proposed robust adaptive control methodology with unknown disturbance are compared with conventional proportional-derivative (PD) control scheme, i.e., without backstepping. © 2022 IEEE.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

Improving DeepFake Video Detection Performance with a Noval Deep Learning Approach 3

Improving DeepFake Video Detection Performance with a Noval ...

引用

3rd IEEE International Conference on Electronic engineering, ICEEM 2023

作者： Fouda, Mona A. El-Shafai, Walid El-Rabaie, El-Sayed M. Menoufia University Faculty of Electronic Engineering Department of Electronics and Electrical Communications Engineering Menouf32952 Egypt Prince Sultan University Security Engineering Lab Computer Science Department Riyadh11586 Saudi Arabia

ISBN: (纸本)9798350323511

With the rise in both the quantity and sophistication of deepfake videos, the need for robust detection systems to identify potentially misleading content on social media and the internet has become paramount. However, current automated face forgery detection systems still face limitations, often demonstrating bias towards the training dataset. This research paper addresses this issue by proposing a novel approach for detecting deepfake media. We introduce a custom Visual Geometry Group (VGG16) deepfake detection method that leverages convolutional neural network architectures. To evaluate the effectiveness of our approach, we utilize the deepfake detection challenge (DFDC) dataset on Kaggle to build network models and compare the performance of our custom VGG16 method against the standard VGG16. Additionally, we investigate the impact of data augmentation techniques on the performance of Convolutional Neural Network (CNN)-based deepfake detectors, examining their effect on both VGG16 and our custom VGG16 approach using the DFDC dataset. Our results demonstrate a high level of accuracy, with precision, recall, and f1-score values of 0.983, 0.975, and 0.979, respectively, and an overall accuracy of 0.986 for deepfake detection. This study presents a promising approach to enhance the accuracy of deepfake video detection, representing a crucial step towards mitigating the potential negative impacts of deepfake technology. © 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

Comparison of Functionality of Non-Conventional Instrument Transformers and Conventional Current Transformers in Distribution Networks 5

Comparison of Functionality of Non-Conventional Instrument T...

引用

5th IEEE International Conference on Smart Systems and Technologies, SST 2022

作者： Burgund, Davorin Nikolovski, Srete Elektrogen Ltd. Zagreb Croatia Faculty of Electrical Engineering Computer Science and Information Technology Osijek Croatia

ISBN: (数字)9781665482158

ISBN: (纸本)9781665482158

In the development of electric, electronic, and information technologies in the medium and low voltage plants, designers reach out the moment of decision when it is necessary to choose equipment and systems that will be optimal for the set requirements. The smart grid concept in the power industry, especially at medium and low voltage, imposes the choice of equipment that will provide more data. The result of this development is the appearance of non-conventional instrument transformers and voltage sensors at medium and low voltage. Their dimensions, price, and functionality fit into these trends. Non-conventional instrument transformers (NCIT) and voltage sensors (VS) compete with conventional current transformers (CCT) and voltage transformers (VT). The paper discusses the specifics of replacing conventional with non-conventional instrument transformers and compares the measurement characteristics of both types, functionality, advantages, and disadvantages of both solutions. © 2022 IEEE.

关键词： Electric power distribution

来源：评论

学校读者我要写书评

暂无评论

Healthcare Management System to Improve Data Analytics Using Support Vector Machine Algorithm 4

Healthcare Management System to Improve Data Analytics Using...

引用

4th International Conference on Innovative Practices in Technology and Management, ICIPTM 2024

作者： Raj, A. Edwin Marin, V. Bini Balakrishnan, C. Elangovan, K. Meenakshi, R. Muthulekshmi, M. Hindustan Institute of Technology and Science Department of Mathematics Tamil Nadu Chennai India Srm Institute of Science and Technology Faculty of Management Studies Tamil Nadu Chennai India S.A.Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India Engineering Dhanalakshmi Srinivasan Engineering College Department of Mechanical Tamil Nadu Chennai India Chennai Institute of Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350307757

Knowledge discovery in databases (KDD) is concerned with progress in data analysis tools. Data mining is a crucial parts of the KDD process. Data mining is a method for discovering and extracting patterns from huge medical datasets. There are a number of benefits to using the Support Vector Machine (SVM) algorithm in healthcare systems. SVM is a strong and flexible machine learning algorithm that may excel at certain healthcare analytics applications. SVM is preferred in healthcare systems because of their adaptability, ability to manage imbalanced datasets, feature interpretability, handling of high-dimensional data, handling of classification, predictive modeling tasks, handling of non-linear relationships, resistance to overfitting and provision of a distinct margin of separation. It is essential to carefully consider the unique needs and features of the healthcare application when choosing an algorithm. Healthcare systems that use SVM algorithms do so with the intention of capitalizing on SVM's capabilities to tackle domain-specific problems and tasks. In light of this development, the relevant literature on this topic with regard to approach, SVM algorithm, and outcomes are surveyed. The publications evaluated in this study have been categorized according to their relevance to the disciplines, models, tasks, and approaches discussed. Data mining is the practice of sifting through massive amounts of unstructured data for meaningful patterns and insights. Results show 90% accuracy and 98% precision and F measures of the given medical dataset. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence for Monitoring and Evaluation of Cardiopulmonary Resuscitation

SSRN

引用

SSRN 2024年

作者： Momeny, Mohammad Marhamati, Mahmoud Esfarayen Faculty of Medical Science Esfarayen Iran Department of Computer Engineering Faculty of Engineering Yazd University Yazd Iran

CPR, cardiopulmonary resuscitation, is a life-saving technique that is given typically to someone who is in cardiac arrest. During the education process of CPR, the rescuer's performance is educated and evaluated by human tutors. Our aim is to use artificial intelligence for education and evaluation of rescuers during CPR. Among the criteria for proper CPR administration, the correct and incorrect position of a rescuer is more common and is tracked by human tutors/supervisors. The present study focuses on the detection of the correct and incorrect positions of rescuers for chest compression using deep transfer learning. To deal with the challenge of detecting the correctness of the rescuer’s position, we built a dataset of 76 sequences of the 30-second recorded video of CPR administration with both correct and incorrect positions. We applied the learning to augment strategy to generate new images for data augmentation in order to improve generalizability of deep networks. The proposed method uses a Bayesian optimizer to determine the optimal value of Gaussian and speckle noise parameters for generating new noisy variants of the original image. We trained six state-of-the-art deep networks, such as DarkNet19, EfficientNetB0, GoogleNet, MobileNet-v2, ShuffleNet, and NASNet-Mobile, with the best data augmentation policies to overcome the overfitting problem. Validation of the proposed method in detecting rescuers’ correct position demonstrated the best sensitivity (98.3%), specificity (95.4%), precision (95.5%), recall (98.3%), and F-measure (96.9%) for the pre-trained NASNet-Mobile network when incorporated with both learning-to-augment and conventional data augmentation strategies. © 2024, The Authors. All rights reserved.

关键词： Resuscitation

来源：评论

学校读者我要写书评

暂无评论

An Effective Cervical Cancer Detection Approaches - A Comparative Analysis 6

An Effective Cervical Cancer Detection Approaches - A Compar...

引用

6th International Conference on Recent Trends in Advance Computing, ICRTAC 2023

作者： Maheswari, S. Marimuthu, C.N. Deepa, B. Geetha, S. Anna University Faculty of Information and Communication Engineering Chennai600025 India Nandha Engineering College Department of Electronics and Communication Engineering Erode638052 India Nandha Engineering College Department of Computer Science and Engineering Erode638052 India

ISBN: (纸本)9798350394702

The chance to preserve a life is provided by early identification of cervical cancer, which is the fourth most common malignancy among women globally. Early diagnosis can lower its frequency. However, due to a number of variables, manual screening techniques are ineffective in detecting cervical cancer. However, this leads to incorrect diagnoses and excessive therapy. Therefore, researchers suggested cervical identification using both conventional and deep learning (DL) methods. This study examines future approaches for automated cervical cancer diagnosis and reviews prior work, focusing on the DL area. This is thought to ensure accurate diagnosis and may possibly lower the incidence of cervical cancer. The comparison chart is provided among various techniques in which EL-SVM model shows higher accuracy. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Inpainting Applied to Facade Images: A Comparison of Algorithms 3rd

Inpainting Applied to Facade Images: A Comparison of Algorit...

引用

3rd International Conference on Pattern Recognition and Artificial Intelligence, ICPRAI 2022

作者： Fritzsche, Willy Goebbels, Steffen Hensel, Simon Rußinski, Marco Schuch, Nils Faculty of Electrical Engineering and Computer Science iPattern Institute Niederrhein University of Applied Sciences Krefeld47805 Germany

ISBN: (纸本)9783031090363

Many municipalities provide textured 3D city models for planning and simulation purposes. Usually, the textures are automatically taken from oblique aerial images. In these images, walls may be occluded by building parts, vegetation and other objects such as cars, traffic signs, etc. To obtain high quality models, these objects have to be segmented and then removed from facade textures. In this study, we investigate the ability of different non-specialized inpainting algorithms to continue facade patterns in occluded facade areas. To this end, non-occluded facade textures of a 3D city model are equipped with various masks simulating occlusions. Then, the performance of the algorithms is evaluated by comparing their results with the original images. In particular, very useful results are obtained with the neural network "DeepFill v2" trained with transfer learning on freely available facade datasets and the "Shift-Map" algorithm. © 2022, Springer Nature Switzerland AG.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Synthesis of novel mesoporous polyvinylamine functionalized with 2-Mercapto-N-methylbenzamide for mercury ions removal from industrial wastewater effluent

引用

Journal of Industrial and engineering Chemistry 2025年 149卷 836-848页

作者： Zouli, Nasser Maslamani, Nujud Hassan, Mohamed Cheira, Mohamed F. Hassanein, Taha F. Chemical Engineering Department College of Engineering and Computer Sciences Jazan University Jazan45142 Saudi Arabia Department of Physical Sciences Chemistry Division College of Science Jazan University P.O. Box. 114 Jazan45142 Saudi Arabia Nuclear Materials Authority P.O. Box 530 Maadi Cairo Egypt Chemistry Department Faculty of Science Helwan University Cairo Helwan11795 Egypt

This research introduces a groundbreaking, high-efficiency adsorbent for the remediation of mercury ion contamination in industrial wastewater effluents. A novel chelating polymer, 2-Mercapto-N-methylbenzamide-functionalized polyvinyl amine (PVAm-MMB), was synthesized via a facile acid-catalyzed condensation reaction, strategically incorporating amine, imine, and thiol functionalities to facilitate robust mercury sequestration. Rigorous structural characterization was undertaken utilizing a comprehensive suite of analytical techniques, including elemental CHNS analysis, FTIR spectroscopy, NMR spectroscopy, SEM-EDX microscopy, BET surface area analysis, GC–MS spectrometry, TGA analysis, and XPS spectroscopy, definitively confirming the desired structural attributes of the synthesized material. Subsequent adsorption studies demonstrated the exceptional performance of the mesoporous PVAm-MMB, exhibiting a significant specific surface area (SBET) of approximately 73.7 m2/g, a total pore volume (Vm) of approximately 0.31 cm3/g, and an average pore width of approximately 21.4 nm. Remarkably, the PVAm-MMB achieved a maximum adsorption capacity of approximately 62.9 mg/g under optimized conditions (pH 4.5, 25 °C, 20 min contact time, 1 g/L adsorbent concentration, and 200 mg/L Hg2+ initial concentration). Langmuir isotherm modeling provided a superior fit to the experimental adsorption data compared to the Freundlich model, indicating a monolayer adsorption mechanism. Furthermore, pseudo-first-order kinetics accurately described the adsorption process;the calculated value for qe,1 was 49.88 mg/g, which is quite aligned with the actual value of 48.6 mg/g. Thermodynamic analyses revealed the adsorption process to be spontaneous, exothermic (ΔH = −88.07 kJ/mol), and thermodynamically favored at lower temperatures. A plausible adsorption mechanism is proposed, and importantly, the adsorbent demonstrated excellent reusability. The efficacy of the PVAm-MMB was validated through t

关键词： Condensation reactions

来源：评论

学校读者我要写书评

暂无评论

A low-cost buoyant force measurement device for monitoring sugar concentration in water solution

A low-cost buoyant force measurement device for monitoring s...

引用

Electrical, computer, Communications and Mechatronics engineering (ICECCME), International Conference on

作者： Luka Kaučić Ivana Kovačević Ivan Aleksi Tomislav Keser Josip Zidar Snježana Rimac-Drlje Department of Computer Engineering and Automation Faculty of Electrical Engineering Computer Science and Information Technology Osijek Osijek Croatia Department of Communications Faculty of Electrical Engineering Computer Science and Information Technology Osijek Osijek Croatia

Monitoring sugar concentration during fermentation is crucial for producing high-quality alcoholic beverages. Traditional methods for measuring sugar concentration can be costly and time-consuming, especially for small-scale producers. In this study, we developed a low-cost buoyant force measurement device for monitoring sugar concentration in water solutions. The device consists of a buoyant object fully submerged in the solution and connected to a load-cell sensor. As the sugar concentration in the liquid increases, the buoyant force on the object increases, and the load-cell measures this force. Proposed device is calibrated using solutions of known sugar concentrations and its high accuracy and precision is presented. The device is tested in controlled environment to ensure accurate tracking changes in sugar concentration over time. Proposed device can be a valuable tool for small-scale producers looking to optimize their fermentation processes while minimizing costs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automating Test Data Generation for Critical Paths in Programs Under Test Using an Improved Coati Optimization Algorithm

Automating Test Data Generation for Critical Paths in Progra...

引用

Iranian Conference on Intelligent Systems (ICIS)

作者： Erfaneh Khanmohammadi Mehdi Esnaashari Amirhossein Damia Hadi Bahrampoor Faculty of Computer Engineering AmirKabir University of Technology (Tehran Polytechnic) Tehran Iran Faculty of Computer Engineering K. N. Toosi University of Technology Tehran Iran Faculty of Computer Engineering Islamic Azad University Science and Research Branch Yasuj Iran

ISBN: (数字)9798331507565

ISBN: (纸本)9798331507572

The software testing process accounted for nearly forty percent of the total software development cost, and one of the most important parts of software testing was test data generation. Performing this process manually led to slowdowns, increased costs, and errors. Therefore, we sought an automated method for generating this set to identify the maximum number of defects. In the process of generating test data, the problem could be transformed into an optimization problem, as their ability to intelligently search in the vast input space and reduce costs and time was superior. Thus, search algorithms could be used to generate test data. Genetic algorithms, particle swarm optimization, etc. were among the most widely used algorithms in this field, but previous algorithms also had drawbacks. In recent years, newer optimization algorithms with better performance were introduced. In this paper, the Coati Optimization Algorithm (COA) was used. This algorithm had lower complexity, appropriate exploration and exploitation phases, and lacked initial parameters compared to previous algorithms. However, the Coati Optimization Algorithm also included weaknesses. Under certain conditions, a solution might never move towards the best solution. Therefore, in this paper, an idea was proposed to improve the performance of the Coati Optimization Algorithm in corrective search ability. Optimization algorithms also needed guidance for search, and the stronger and faster this guidance, the better the quality of the obtained solutions. In this paper, a new fitness function was introduced, which had better performance compared to other fitness functions. Before applying the search algorithm to the data generation problem, first, the control flow graph of the program under test had to be drawn. Then, the execution paths of this program were extracted from the graph, so that the algorithm could generate test data by running on it. However, it should be noted that we would not be able to cove

关键词： Software testing Costs Software algorithms Data collection Search problems Particle swarm optimization Optimization Standards Genetic algorithms Software development management

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：