检索结果-内蒙古大学图书馆

14th International Conference Management of Large-Scale System Development, MLSD 2021

作者： Kamenev, Ivan G. Federal Research Center 'Computer Science and Control' Russian Academy of Sciences Department of Modeling of Economic Systems Moscow Russia

ISBN: (纸本)9781665412308

The article discusses human resource management problems in the quasi-public sector (education, healthcare, military industry, etc.). It is shown that the behavior of these organizations can be described as unproductive workers' payment maximization. The formalization of this task based on the model of the external and internal labor market is proposed. © 2021 IEEE.

关键词： Human resource management

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Russian Agricultural Research Organizations' Digital Footprint 14

Analysis of the Russian Agricultural Research Organizations'...

引用

14th International Conference Management of Large-Scale System Development, MLSD 2021

作者： Medennikov, Viktor Flerov, Yuri Federal Research Center 'Computer Science and Control Russian Academy of Sciences Information and Computing Systems Department Moscow Russia

ISBN: (纸本)9781665412308

This work analyzes domestic agricultural research organizations' ratings shaped by applying methodologies of generating such ratings with consideration to active, passive, and semiactive digital footprints in the internet space. A mathematical description of the methodologies is provided. The benchmarking analysis of the resulting ratings is presented. © 2021 IEEE.

关键词： Agriculture

来源：评论

学校读者我要写书评

暂无评论

Detecting Hallucinations in Large Language Models Using Machine Learning Classifiers: A Comparative Study

Detecting Hallucinations in Large Language Models Using Mach...

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Hazem Al-Najjar Nadia Al-Rousan Douaa Al-Rousan Department of Computer Science College of Information Technology University of Petra Amman Jordan Department of computer engineering College of Engineering AIBalqa Applied University Salt Jordan Department of Computer Engineering Faculty of Electrical Engineering and Information Systems German Jordanian University Amman Jordan School of Civil Engineering Universiti Sains Malaysia Nibong Tebal Pulau Pinang Malaysia

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

This study is concerned with the comprehensive evaluation of machine learning models intended for the detection of hallucination in Large Language Model output. The preprocessing of the prompt and answers using TF-IDF vectorization has been done as a preliminary step before developing a hallucination prediction model. Afterwards, the generated dataset was then divided into training and testing, with percentages equal to 70% and 30%, respectively. The selected machine learning models were trained with the dataset created. In this research, eight various classifiers are implemented and compared. To evaluate the results of our approach, multiple metrics were taken into consideration: accuracy, precision, recall, and Fl-score. While the training results showed exceptional performance with accuracies exceeding 99% in several models, the test results indicated huge challenges in generalization. Random Forest had the highest testing accuracy of 94.77% at 65% precision but with a very low recall of 4.85%. Besides, cross validation is used with random forest and decision tree, the results showed that the cross-validation is better than the test and train splitting model. The study shows the significant trade-offs between precision and recall in hallucination detection, which is especially problematic while working with imbalanced datasets.

关键词： Training Measurement Accuracy Large language models Computational modeling Predictive models Decision trees Random forests Computational intelligence Testing

来源：评论

学校读者我要写书评

暂无评论

Predicting the Hardness of Low Alloy Metal using Machine Learning Model

Predicting the Hardness of Low Alloy Metal using Machine Lea...

引用

International Conference on Computational Intelligence and Networks (CINE)

作者： K. Logeswaran S. Savitha P. Suresh Swati Sah B Priyanka R Ragav R S Vishal H Mohamed Arsath Department of Artificial Intelligence Kongu Engineering College Erode TamilNadu India Department of Database Systems School of Computer Science and Engineering Vellore Institute of Technology Vellore TamilNadu India Department of Computer Science and Engineering K.S.R College of Engineering Trichengode Tamilnadu India School of Engineering and Technology Sharda University Nodia India

ISBN: (数字)9798331516796

ISBN: (纸本)9798331516802

In industries like materials engineering and manufacturing, predicting the hardness of low alloy metals is crucial for ensuring quality and performance. Traditional methods, which often rely on formulas or manual testing, can be slow and inaccurate due to variations in material properties. This paper presents a new approach for predicting metal hardness using machine learning techniques, including Multi-linear Regression, Decision Tree Regression, Random Forest Regression, and Gradient Boosting Regression. These algorithms are used to improve the accuracy and reliability of hardness predictions compared to older methods. The paper covers how the data was collected, which features were chosen, and how the models were trained. It also compares the performance of these algorithms, looking at how accurate and effective they are in different situations. The results show that the machine learning models offer better predictions than traditional methods, leading to more consistent and reliable outcomes. Finally, the research discusses how these models can be used in real-world applications to make processes more efficient and reduce errors.

关键词： Analytical models Accuracy Metals Predictive models Prediction algorithms Data models Reliability Regression tree analysis Random forests Testing

来源：评论

学校读者我要写书评

暂无评论

Challenges and Emerging Issues for Generative AI and Hyper Intelligence

Challenges and Emerging Issues for Generative AI and Hyper I...

引用

Cyber science and Technology Congress (CyberSciTech), IEEE

作者： Jianhua Ma Qun Jin Hui-Huang Hsu John Paul C. Vergara Antonio Guerrieri Claudio Miceli Ao Guo Faculty of Computer and Information Sciences Hosei University Japan Department of Human Informatics and Cognitive Sciences Waseda University Japan Department of Computer Science and Information Engineering Tamkang University Taiwan Department of Information Systems and Computer Science Ateneo de Manila University Philippines ICAR-CNR Italy Graduate Program in Systems Engineering and Computer Science Federal University of Rio de Janeiro Brazil Graduate School of Informatics Nagoya University Japan

ISBN: (数字)9798331532093

ISBN: (纸本)9798331532109

Generative Artificial Intelligence (GenAI) represents a significant milestone in the development of artificial intelligence, bringing sophisticated AI capabilities into daily life and work. As we approach the era of Hyper Intelligence (Hyper-I), a variety of critical challenges and emerging issues have come to light, ranging from computational complexity to ethical concerns. This paper explores the evolution of AI from the perspective of human learning, comparing machine and human intelligence, and identifying key considerations for the development of future AI systems. It also highlights the growing importance of regulating advanced AI models, such as Reinforcement Learning-based Long-Term Planning Agents, to ensure that Hyper-I remains under human control. Additionally, the paper discusses the computational complexity of transformer-based models, their applicability to intractable problems, and their role in cognitive building systems and resource-constrained environments through TinyML. By analyzing these pressing challenges, this work provides insights into the future of AI and the path toward responsible innovation in generative and hyper-intelligent systems.

关键词： Hyper-intelligent systems Ethics Technological innovation Generative AI Computational modeling Tiny machine learning Pressing Transformers Regulation Computational complexity

来源：评论

学校读者我要写书评

暂无评论

A Deep Features Based Approach Using Modified ResNet50 and Gradient Boosting for Visual Sentiments Classification

A Deep Features Based Approach Using Modified ResNet50 and G...

引用

IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)

作者： Muhammad Arslan Muhammad Mubeen Arslan Akram Saadullah Farooq Abbasi Muhammad Salman Ali Muhammad Usman Tariq Department of Computer Science Loyola University Chicago Chicago USA Department of Computer Science University Of the People California USA Facultty of Computer Science and Information Technology The Superior University Lahore Lahore Pakistan Department of Electronic Electrical and Systems Engineering University of Birmingham Birmingham U. K.

ISBN: (数字)9798350351422

ISBN: (纸本)9798350351439

The versatile nature of Visual Sentiment Analysis (VSA) is one reason for its rising profile. It isn't easy to efficiently manage social media data with visual information since previous research has concentrated on Sentiment Analysis (SA) of single modalities, like textual. In addition, most visual sentiment studies need to adequately classify sentiment because they are mainly focused on simply merging modal attributes without investigating their intricate relationships. This prompted the suggestion of developing a fusion of deep learning and machine learning algorithms. In this research, a deep feature-based method for multiclass classification has been used to extract deep features from modified ResNet50. Furthermore, gradient boosting algorithm has been used to classify photos containing emotional content. The approach is thoroughly evaluated on two benchmarked datasets, CrowdFlower and GAPED. Finally, cutting-edge deep learning and machine learning models were used to compare the proposed strategy. When compared to state-of-the-art approaches, the proposed method demonstrates exceptional performance on the datasets presented.

关键词： Deep learning Visualization Sentiment analysis Machine learning algorithms Social networking (online) Merging Information processing Feature extraction Boosting Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

An improved side-slip estimation algorithm based on ultra-local model technique for autonomous vehicles

An improved side-slip estimation algorithm based on ultra-lo...

引用

International Conference on control, Decision and Information Technologies (CoDIT)

作者： Dániel Fényes Tamás Hegedűs Balázs Németh Vu Van Tan Péter Gáspár HUN-REN Institute for Computer Science and Control (SZTAKI) Budapest Hungary Department of Automotive Mechanical Engineering Faculty of Mechanical Engineering University of Transport and Communications Hanoi Vietnam

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

The paper presents a novel observer design method for estimating the front and rear wheel slips of the vehicle. The proposed observer design technique consists of two parts: A simple linear observer algorithm, which uses a reformulated lateral vehicle model to estimate the tire slips. The second part is based on an ultra-local model. The main goal of the ultra-local model is to eliminate the nonlinear, unmodeled, uncertain dynamics of the lateral vehicle model. In this way, the performance level of the linear observer can be significantly increased especially under critical circumstances such as high lateral acceleration maneuvers or driving on a low µ surface. The proposed observer algorithm is implemented in MATLAB/Simulink environment connected to the high-fidelity simulation software, CarMaker. The operation and the effectiveness of the proposed observer are demonstrated through several simulation examples.

关键词： Heuristic algorithms Software algorithms Wheels Observers Mathematical models Tires Software Vehicle dynamics MATLAB Information technology

来源：评论

学校读者我要写书评

暂无评论

Novel Hand Gesture Classification based on Empirical Fourier Decomposition of sEMG Signals*

Novel Hand Gesture Classification based on Empirical Fourier...

引用

Data science and engineering in Healthcare, Medicine and Biology, IEEE EMBS Special Topic Conference on

作者： Sai Praveen Kadiyala Ke Chen Ziyang Guo Parthan Olikkal Andrew Catlin Ashwin Satyanarayana Ramana Vinjamuri Katz school of Health and Science Yeshiva University New York Department of Computer Science and Engineering UMBC Baltimore MD Department of Computer Systems Technology CUNY New York

Major challenge in building models for stroke rehabilitation stems from the non stationarity of the EMG signals. In this work we present a methodology for improved classification of hand gestures using Empirical Fourier Decomposition (EFD). First we apply the EFD technique on a set of publicly available dataset and later we reduce the dimensionality to collect most significant components. Finally we extract features from these components and perform hand gesture classifications using different machine learning (ML) *** Relevance: Compared to the state-of-art Empirical Wavelet Transform (EWT), the EFD technique reduced the total significant components considerably. To capture 90% of information from original data, the EFD approach needed 5.96% and 23.21% less number of components compared to EWT approach for original and dimensionally reduced data sets respectively. The classification models using EFD components gave an average 3.4% accuracy improvement compared to that of EWT components.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A comprehensive review of deep learning power in steady-state visual evoked potentials

引用

Neural Computing and Applications 2024年第27期36卷 16683-16706页

作者： Al-Qaysi, Z.T. Albahri, A.S. Ahmed, M.A. Hamid, Rula A. Alsalem, M.A. Albahri, O.S. Alamoodi, A.H. Homod, Raad Z. Shayea, Ghadeer Ghazi Duhaim, Ali M. Tikrit Iraq Technical College Imam Ja’afar Al-Sadiq University Baghdad Iraq Baghdad Iraq Department of Management Information Systems College of Administration and Economics University of Mosul Mosul Iraq Australian Technical and Management College Melbourne Australia Computer Techniques Engineering Department Mazaya University College Nasiriyah Iraq Applied Science Research Center Applied Science Private University Amman Jordan Department of Oil and Gas Engineering Basra University of Oil and Gas Basra1004 Iraq Ministry of Education Thi-Qar Education Directorate Thi Qar Iraq MEU Research Unit Middle East University Amman Jordan Baghdad Iraq

Brain–computer interfacing (BCI) research, fueled by deep learning, integrates insights from diverse domains. A notable focus is on steady-state visual evoked potential (SSVEP) in BCI applications, requiring in-depth assessment through deep learning. EEG research frequently employs SSVEPs, which are regarded as normal brain responses to visual stimuli, particularly in investigations of visual perception and attention. This paper tries to give an in-depth analysis of the implications of deep learning for SSVEP-adapted BCI. A systematic search across four stable databases (Web of science, PubMed, scienceDirect, and IEEE) was developed to assemble a vast reservoir of relevant theoretical and scientific knowledge. A comprehensive search yielded 177 papers that appeared between 2010 and 2023. Thence a strict screening method from predetermined inclusion criteria finally generated 39 records. These selected works were the basis of the study, presenting alternate views, obstacles, limitations and interesting ideas. By providing a systematic presentation of the material, it has made a key scholarly contribution. It focuses on the technical aspects of SSVEP-based BCI, EEG technologies and complex applications of deep learning technology in these areas. The study delivers more penetrating reporting on the latest deep learning pattern recognition techniques than its predecessors, together with progress in data acquisition and recording means suitable for SSVEP-based BCI devices. Especially in the realms of deep learning technology orchestration, pattern recognition techniques, and EEG data collection, it has effectively closed four important research gaps. To increase the accessibility of this critical material, the results of the study take the form of easy-to-read tables just generated. Applying deep learning techniques in SSVEP-based BCI applications, as the research shows, also has its downsides. The study concludes that a radical framework will be presented which, include

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Autonomous Surveillance Breakthrough by Implementing Facial Recognition in Dog Robots

Autonomous Surveillance Breakthrough by Implementing Facial ...

引用

Intermountain engineering, Technology and Computing (IETC)

作者： Amir Hafezi Minhaz Zibran Taher Deemyad Department of Mechanical and Measurement & Control Engineering Idaho State University Pocatello ID USA Department of Computer Science Idaho State University Pocatello ID USA

ISBN: (数字)9798350373073

ISBN: (纸本)9798350373080

As the importance of security in today's world continues to escalate, technology's role in its enhancement has evolved significantly. From the inception of fixed security cameras monitored by individuals, advancements have steered towards autonomous threat recognition systems and the deployment of mobile robots for proactive security measures. Despite these technological strides, the exploration of autonomous robots in security has been relatively scant. This study takes a novel approach by repurposing the commercial GO2 Edu dog robot for security purposes, equipping it with a thermal camera and custom software for robust face detection in varying lighting conditions, aimed at achieving safer and more reliable face recognition. Furthermore, the mapping and navigational capabilities are studied by conducting experiments with a Turtlebot outfitted with a 2D RPLIDAR and depth camera using SLAM, laying the groundwork for the GO2 robot's autonomous operations. The results of these enhancements have shown to be promising in the context of bolstering security measures. The paper concludes with a discussion on potential future enhancements, paving the way for more sophisticated and autonomous security robots.

关键词： Simultaneous localization and mapping Navigation Face recognition Robot vision systems Lighting Dogs Cameras

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：