检索结果-内蒙古大学图书馆

2024 International Telecommunications Conference, ITC-Egypt 2024

作者： Abdelmalak, Mark Emad Sobhi Khodadadi, Nima Zaki, Ahmed Mohamed Eid, Marwa M. Rizk, Faris H. Ibrahim, Abdelhameed Abdelhamid, Abdelaziz A. Abualigah, Laith El-Kenawy, El-Sayed M. Delta Higher Institute of Engineering and Technology Department of Communications and Electronics Mansoura35111 Egypt University of Miami Department of Civil and Architectural Engineering Coral GablesFL United States Computer Science and Intelligent Systems Research Center BlacksburgVA24060 United States Delta University for Science and Technology Faculty of Artificial Intelligence Mansoura35111 Egypt Bahrain Polytechnic Faculty of Engineering Isa Town Bahrain Ain Shams University Faculty of Computer and Information Sciences Department of Computer Science Cairo11566 Egypt Al al-Bayt University Computer Science Department Mafraq25113 Jordan Middle East University MEU Research Unit Amman11831 Jordan Jadara University Jadara Research Center Irbid Jordan

ISBN: (纸本)9798350351408

The research article described in this paper puts forward a novel method of using an integrated software approach and high-end hardware devices for adaptive and intelligent detection of potholes on asphalt roads. The Pothole Detection Dataset is used for the dataset analysis, and we put VGG19Net, ResNet-50, GoogLeNet, and AlexNet among the computer vision models to analyze the applicability of these models. Different types of networks were compared, and AlexNet showed the best results as it achieved 92.15% accuracy, 91.38 % sensitivity (TPR), and a surprisingly high F-score, which reached 96.52%. Furthermore, by using its time of 279.35 seconds, which might be considered very fast, AlexNet shows many strengths in helping to do this, as well as identifying road anomalies, making it a perfect candidate for real-world utilization. This research demonstrates the emergence of sophisticated integrated pothole repair solutions, emphasizing the importance of both software and hardware in developing sophisticated pothole detection. Practices and this research could be an example for further surveying road inspection technologies. © 2024 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

A Study on a New Pseudorandom Number Generator with Deterministic Maze Construction

A Study on a New Pseudorandom Number Generator with Determin...

引用

IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)

作者： Takeru Miyazaki Shunsuke Araki Satoshi Uehara Faculity of Management and Information Sciences Kyushu Inst. of Information Sciences Fukuoka Japan Faculty of Computer Science and Systems Engineering Kyushu Inst. of Technology Fukuoka Japan Faculty of Environmental Engineering The Univ. of Kitakyushu Fukuoka Japan

ISBN: (数字)9798350386844

ISBN: (纸本)9798350386851

In this paper, we propose a new pseudorandom number generator (PRNG), which uses a new deterministic maze construction for our maze-based PRNG [1]. We evaluate some relations between a size and a number of shapes for the mazes generated by our maze construction. Then, we also estimate a number of shapes and the maximum duplicate number of mazes by the size of the maze. By using the asymptotic equations of these estimated values, we can derive the minimum required maze size for the required number of sequences in which most or all sequences are different.

关键词： Shape Generators Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

The Effect of Imbalanced Data and Parameter Selection via Genetic Algorithm Long Short-Term Memory (LSTM) for Financial Distress Prediction

引用

IAENG International Journal of Applied Mathematics 2023年第3期53卷 25页

作者： Adisa, Juliana Adeola Ojo, Samuel Owolawi, Pius Adewale Pretorius, Agnieta Ojo, Sunday Olusegun Tshwane University of Technology Department of Computer Systems Engineering Soshanguve Campus South Africa Department of Computer Systems Engineering Tshwane University of Technology Soshanguve Campus South Africa Faculty of ICT Tshwane University of Technology Soshanguve Campus South Africa Computer Science Department of Information Technology Durban University of Technology Durban South Africa

Financial companies are grappling with a burning issue about bankruptcy prediction. There are many methods for bankruptcy prediction, including statistical models and machine learning. Real-life datasets are often imbalanced with high dimensionality. Therefore, it is challenging to train a robust model to predict bankruptcy. Thus, we first applied an oversampling technique known as the Synthetic Minority Oversampling Technique (SMOTE) to reduce the skewness of the data. The balanced data was trained with the baseline models, the ensemble classifiers using different combination methods and the long short-term memory (LSTM) model. In addition, we employed an optimization technique called a genetic algorithm (GA) to optimize and determine the learning parameters of an LSTM network. We further determine the effects of using different training/testing ratios on the developed models. An autoencoder long short-term memory (LSTM) model was developed to extract the best feature representation of the input data. A comparative analysis was carried out between the LSTM-GA and autoencoder-LSTM. The results show that the improved LSTM-GA model with an accuracy of 98.11% performs better than other models. Overall, the research work concluded that all models and LSTM have good performances, while the optimized LSTM model via genetic algorithm outperforms the classical machine learning models. © (2023), (International Association of Engineers). All Rights Reserved.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Multi - Aspect Evaluation of DL-based SQLi Attack Detection Models

A Multi - Aspect Evaluation of DL-based SQLi Attack Detectio...

引用

International Conference on Software engineering Research, Management and Applications (SERA)

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

ISBN: (数字)9798350391343

ISBN: (纸本)9798350391350

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.

关键词： Support vector machines Costs SQL injection Predictive models Internet Random forests Tuning

来源：评论

学校读者我要写书评

暂无评论

Improved Archimedes Optimization Algorithm with Deep Learning Empowered Fall Detection System

引用

computers, Materials & Continua 2022年第8期72卷 2713-2727页

作者： Ala Saleh Alluhaidan Masoud Alajmi Fahd N.Al-Wesabi Anwer Mustafa Hilal Manar Ahmed Hamza Abdelwahed Motwakel Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Computer Science College of Science&Arts at MahayilKing Khalid UniversityMuhayel Aseer62529Saudi Arabia Faculty of Computer and IT Sana’a UniversitySana’a61101Yemen Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAl-Kharj16278Saudi Arabia

Human fall detection(FD)acts as an important part in creating sensor based alarm system,enabling physical therapists to minimize the effect of fall events and save human ***,elderly people suffer from several diseases,and fall action is a common situation which can occur at any *** this view,this paper presents an Improved Archimedes Optimization Algorithm with Deep Learning Empowered Fall Detection(IAOA-DLFD)model to identify the fall/non-fall *** proposed IAOA-DLFD technique comprises different levels of pre-processing to improve the input image ***,the IAOA with Capsule Network based feature extractor is derived to produce an optimal set of feature *** addition,the IAOA uses to significantly boost the overall FD performance by optimal choice of CapsNet ***,radial basis function(RBF)network is applied for determining the proper class labels of the test *** showcase the enhanced performance of the IAOA-DLFD technique,a wide range of experiments are executed and the outcomes stated the enhanced detection outcome of the IAOA-DLFD approach over the recent methods with the accuracy of 0.997.

关键词： Fall detection intelligent model deep learning archimedes optimization algorithm capsule network

来源：评论

学校读者我要写书评

暂无评论

Resource Assessment of Wind Energy Potential of Mokha in Yemen with Weibull Speed

引用

computers, Materials & Continua 2021年第10期69卷 1123-1140页

作者： Abdulbaset El-Bshah Fahd N.Al-Wesabi Ameen M.Al-Kustoban Mohammad Alamgeer Nadhem Nemri Majdy M.Eltahir Hany Mahgoub Noha Negm Department of Electronic Engineering Faculty of EngineeringUniversity of Science and Technology UST-Sana’aYemen Department of Computer Science King Khalid UniversityMuhayel AseerKingdom of Saudi Arabia Faculty of Computer and IT Sana’a UniversitySana’aYemen Department of Electronic Faculty of EngineeringUSTSana’aYemen Department of Information Systems King Khalid UniversityMayahel AseerKSA Department of Computer Science King Khaled UniversityKSA&Faculty of Computers and InformationMenoufia UniversityEgypt Department of Computer Science King Khaled UniversityKSA&Faculty of ScienceDepartment of Mathematics and Computer ScienceMenoufia UniversityEgypt

The increasing use of fossil fuels has a significant impact on the environment and ecosystem,which increases the rate of *** the high potential of renewable energy sources in Yemen and other Arabic countries,and the absence of similar studies in the *** study aims to examine the potential of wind energy in Mokha *** was done by analyzing and evaluating wind properties,determining available energy density,calculating wind energy extracted at different altitudes,and then computing the capacity factor for a few wind turbines and determining the *** speed was verified as the closest to the average actual wind speed using the cube root,as this was verified using 3 criteria for performance analysis methods(R^(2)=0.9984,RMSE=0.0632,COE=1.028).The wind rose scheme was used to determine the appropriate direction for directing the wind turbines,the southerly direction was appropriate,as the winds blow from this direction for 227 days per year,and the average southerly wind velocity is 5.27 m/s at an altitude of 3 *** turbine selected in this study has a tower height of 100m and a rated power of 3.45 *** capacitance factor was calculated for the three classes of wind turbines classified by the International Electrotechnical Commission(IEC)and compared,and the turbine of the first class was approved,and it is suitable for the study site,as it resists storms more than *** daily and annual capacity of a single,first-class turbine has been assessed to meet the needs of 1,447 housing units in Mokha *** amount of energy that could be supplied to each dwelling was around 19 kWh per day,which was adequate to power the basic loads in the home.

关键词： Wind energy system probability density wind speed Weibull velocity Rayleigh velocity wind rose

来源：评论

学校读者我要写书评

暂无评论

Speech-Gesture GAN: Gesture Generation for Robots and Embodied Agents

Speech-Gesture GAN: Gesture Generation for Robots and Embodi...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Carson Yu Liu Gelareh Mohammadi Yang Song Wafa Johal Faculty of Engineering School of Computer Science and Engineering University of New South Wales Sydney NSW Australia Faculty of Engineering and Information Technology School of Computing Information Systems University of Melbourne Melbourne VIC Australia

Embodied agents, in the form of virtual agents or social robots, are rapidly becoming more widespread. In human-human interactions, humans use nonverbal behaviours to convey their attitudes, feelings, and intentions. Therefore, this capability is also required for embodied agents in order to enhance the quality and effectiveness of their interactions with humans. In this paper, we propose a novel framework that can generate sequences of joint angles from the speech text and speech audio utterances. Based on a conditional Generative Adversarial Network (GAN), our proposed neural network model learns the relationships between the co-speech gestures and both semantic and acoustic features from the speech input. In order to train our neural network model, we employ a public dataset containing co-speech gestures with corresponding speech audio utterances, which were captured from a single male native English speaker. The results from both objective and subjective evaluations demonstrate the efficacy of our gesture-generation framework for Robots and Embodied Agents.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Smart irrigation system using IoT and machine learning methods

Smart irrigation system using IoT and machine learning metho...

引用

Novel Intelligent and Leading Emerging Sciences Conference (NILES)

作者： Ahmed A. Esmail Manar A. Ibrahim Sayed M. Abdallah Ahmed E. Radwan Haya k. Elsonbaty Mohamed A. Elsayed Noure A. Elnakeib Merit Samir Dawoud Amir El-Ghamry Khaled M. Fouad Ibrahim F. Moawad Artificial Intelligence Science Faculty of Computer Science and Engineering New Mansoura University Dakhlia Egypt Information Technology Faculty of Computer and Information Sciences Mansoura University. Faculty of Computer Science and Engineering New Mansoura University Egypt Faculty of Computer and Information Sciences Mansoura University. Faculty of Computer Science and Engineering New Mansoura University Egypt School of Engineering and Computer Science University of Hertfordshire Hosted by Global Academic Foundation Egypt Information Systems Faculty of Computers and Artificial Intelligence Benha University Egypt Faculty of Computer Science and Engineering New Mansoura University Dakhlia Egypt Information Systems Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt

Water loss and improper scheduling are problems with traditional irrigation techniques, making it difficult to meet the growing demand for food production while also preserving precious water resources. To address these challenges, this paper introduces a cutting-edge smart irrigation system that leverages the power of the Internet of Things (IoT), data analysis, and machine learning to determine the most efficient way to apply and schedule water for irrigation. The cornerstone of this innovative system is the utilization of a carefully curated dataset, "Crop Irrigation Scheduling," sourced from Kaggle. This dataset comprises six crucial attributes: Crop Type, Crop Days, Soil Moisture, Temperature, Humidity, and Irrigation. These attributes, described in detail in the dataset’s metadata, provide the foundational information required for precise irrigation management. The system operates seamlessly by deploying IoT sensors to collect real-time data from the field. This data is then preprocessed to ensure its quality and consistency. Subsequently, a machine learning model is trained using this dataset to make intelligent irrigation decisions in real time. The model’s predictions are seamlessly integrated with control mechanisms that govern the irrigation process. Moreover, the system offers an intuitive API for easy data access and management, allowing agricultural professionals to monitor and adjust irrigation strategies effortlessly. Experimental findings validate the system’s utility, with particular emphasis on the decision tree model, which demonstrates the best balance of accuracy, precision, recall, and F1 score. This system maximizes crop yield and minimizes water waste, contributing to a more sustainable and productive agricultural ecosystem.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Digital Learning Ecosystem: Online Concept for engineering Education

Digital Learning Ecosystem: Online Concept for Engineering E...

引用

International Scientific Conference on Power and Electrical engineering of Riga Technical University (RTUCON)

作者： Anatolijs Zabasta Volodymyr Kazymyr Nadezhda Kunicina Oleksandr Velihorskyi Faculty of Computer Science Information Technology and Energy Riga Technical University Riga Latvia Information and Computer Systems Department Chernihiv Polytechnic National University Chernihiv Ukraine Radio Engineering and Embedded Systems Department Chernihiv Polytechnic National University Chernihiv Ukraine

ISBN: (数字)9798350365771

ISBN: (纸本)9798350365788

This article examines the development of a Digital Learning Ecosystem (DLE) for engineering education, supported by online learning, within the framework of Erasmus+ international educational projects. We hypothesize that a DLE can address the challenges posed by rapid technological changes associated with Industry 4.0 and digital transformation, thus transforming engineering education to meet modern industry needs. Building on the earlier Erasmus+ CybPhys project, which established a Sharing Modelling and Simulation Environment (SMSE) for digitalizing online technical courses, the DIGITRANS project aims to enhance this architecture to include remote laboratories through the Sharing Remote Experiment Environment (SREE) platform. The project involves acquiring hardware and open-source software for SREE and establishing two physical remote laboratories. A study conducted in spring 2023, using the technology Acceptance Model framework, indicated positive student perceptions of SMSE, with students believing it would enhance learning outcomes and expressing intentions to use the platform frequently. The efficacy of the DLE in addressing technological advancement challenges will be further evaluated through post-ante assessments and feedback from prospective employers and stakeholders, focusing on the implementation of industry recommendations and the correlation between pre- and post-implementation survey responses from industry and academic experts.

关键词： Training Surveys Remote laboratories Biological system modeling Ecosystems Hardware Stakeholders engineering education Kernel Programming profession

来源：评论

学校读者我要写书评

暂无评论

Explaining Learned Reward Functions with Counterfactual Trajectories

arXiv

引用

arXiv 2024年

作者： Wehner, Jan Oliehoek, Frans Siebert, Luciano Cavalcante CISPA Helmholtz Center for Information Security Germany Department of Intelligent Systems Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft Netherlands

Learning rewards from human behavior or feedback is a promising approach to aligning AI systems with human values but fails to consistently extract correct reward functions. Interpretability tools could enable users to understand and evaluate possible flaws in learned reward functions. We propose Counterfactual Trajectory Explanations (CTEs) to interpret reward functions in Reinforcement Learning by contrasting an original and a counterfactual trajectory and the rewards they each receive. We derive six quality criteria for CTEs and propose a novel Monte-Carlo-based algorithm for generating CTEs that optimizes these quality criteria. To evaluate how informative the generated explanations are to a proxy-human model, we train it to predict rewards from CTEs. CTEs are demonstrably informative for the proxy-human model, increasing the similarity between its predictions and the reward function on unseen trajectories. Further, it learns to accurately judge differences in rewards between trajectories and generalizes to out-of-distribution examples. Although CTEs do not lead to a perfect prediction of the reward, our method, and more generally the adaptation of XAI methods, are presented as a fruitful approach for interpreting learned reward functions and thus enabling users to evaluate them. © 2024, CC BY.

关键词： Contrastive 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：