检索结果-内蒙古大学图书馆

Electronic and Electrical engineering and Intelligent System (ICE3IS), International Conference on

作者： Erman Arif Suherman Suherman Aris Puji Widodo Doctoral Program of Information System School of Postgraduate Studies Diponegoro University Semarang Indonesia Department of Chemical Engineering Faculty of Engineering Diponegoro University Semarang Indonesia Department of Informatics Faculty of Science and Mathematics Diponegoro University Semarang Indonesia

ISBN: (数字)9798350378368

ISBN: (纸本)9798350378375

Our article presents a comprehensive analysis of trends and directions in the application of machine learning in the FinTech sector. By utilizing data from academic databases such as Scopus, our objective is to showcase the advancements in this interdisciplinary research area. The study identifies key trends, influential authors, leading journals, and significant collaborative networks that shape the field. The methodology employed involves quantitative bibliometric analysis to evaluate publications from the past five years. The results indicate a substantial increase in the number of studies during this period, highlighting the importance of machine learning in addressing critical financial challenges, including fraud detection, algorithmic trading, credit scoring, and risk management. Additionally, we delve into the main themes, countries, and institutions that dominate the current research agenda. This analysis provides valuable insights into the present state and future direction of machine learning in FinTech, serving as a resource for researchers and practitioners seeking to comprehend and contribute to this dynamic and rapidly evolving field. We also discuss implications for future research, emphasizing the necessity for continuous innovation and interdisciplinary collaboration to maximize the potential of machine learning in transforming financial services.

关键词： Symbiosis Technological innovation Machine learning algorithms Bibliometrics Collaboration Machine learning Market research Dynamic scheduling Fraud Risk management

来源：评论

学校读者我要写书评

暂无评论

Thermal reaction characteristics and microstructure evolution of aluminium nano-powder in various mixtures of oxygen and nitrogen atmosphere

引用

Process Safety and Environmental Protection 2023年 170卷 45-53页

作者： Qu, Jiao Deng, Jun Luo, Zhen-Min Xiao, Yang Shu, Chi-Min Post-doctoral Program Research Centre Xi'an University of Science and Technology No. 58 Yanta Mid. Rd. Shaanxi Xi'an710054 China School of Safety Science and Engineering Xi'an University of Science and Technology No. 58 Yanta Mid. Rd. Shaanxi Xi'an710054 China Shaanxi Key Laboratory of Prevention and Control of Coal Fire No. 58 Yanta Mid. Rd. Shaanxi Xi'an710054 China Department of Safety Health and Environmental Engineering National Yunlin University of Science and Technology Yunlin 64002 Taiwan

Aluminium nano-powder has a small particle size, large specific surface area, and high surface energy, therefore when using it, the risk of fires or explosions is high. In this study, synchronous thermal analyser was used to determine the thermal reaction characteristics of aluminium nano-powder for various oxygen and nitrogen mixtures. The results showed that the oxidation behaviour of aluminium nano-powder could be considered to occur in four stages, according to the characteristic temperature points and polymorphic phase changes. Under experimental heating rates of 5, 10, 15, and 20 K/min, the mass gain and thermal effects of the samples were tested, and also for different oxygen concentrations of 9, 15, and 21 vol%. Changes in the microstructure of the samples were analysed. Oxide layer thickness was found to increase as temperature increased, and this trend was the same for mass change. Surface morphology images of the aluminium particles exhibited agglomeration, melting deformation, rupture, and fragmentation at the different pretreated temperatures of 500, 650, 800, and 900 °C. The results of this study could be used as a basis for exploring oxidation kinetics, and had significance for explosion-proofing technology, particularly with respect to aluminium nano-powder. © 2022 The Institution of Chemical Engineers

关键词： Surface morphology

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Diagnosis Based on Object Detection Technology 14th

Lung Cancer Diagnosis Based on Object Detection Technology

引用

14th International Conference on Frontier Computing, FC 2024

作者： Xu, Jia-Lang Wang, Pei-Yun Huang, Tzu-Hsuan Hsu, Ying-Lin Huang, Kuo-Yang Chen, Mu-Yen Artificial Intelligence Development Center Changhua Christian Hospital Changhua Taiwan Doctoral Program in Data Science and Industrial Analytics National Chung Hsing University Taichung Taiwan Department of Applied Mathematics and Institute of Statistics National Chung Hsing University Taichung Taiwan Division of Chest Medicine Department of Internal Medicine Changhua Christian Hospital Changhua Taiwan Department of Engineering Science National Cheng Kung University Tainan Taiwan

ISBN: (纸本)9789819623945

With the rise of artificial intelligence, many people nowadays use artificial intelligence to help solve some problems in life, and the medical field is also with the rise of artificial intelligence, many people are slowly applying artificial intelligence to medical images to assist in decision-making, this study proposes a Yolov8 algorithm for object tracking of CT images of lung cancer, which can quickly tell the doctor where the cancer is and what the type of cancer is. The results of this study show that the Box_Loss, Cls_Loss, and Dfl_loss of the Yolov8 algorithm in detecting the location of lung cancer are 1.3689, 0.4552, and 1.5569 in the validation data, respectively, and thus this study suggests that this method can help physicians know the location of the tumor and what kind of tumor it belongs to. Therefore, this study suggests that this method can help physicians know the location of the tumor and the type of tumor. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Novel spent bleaching earth industrial waste as low-cost ceramic membranes material: Elaboration and characterization

Novel spent bleaching earth industrial waste as low-cost cer...

引用

3rd International Conference on Chemical engineering and Applied Sciences, ICChEAS 2022

作者： Rahma, Aulia Elma, Muthia Roil Bilad, Muhammad Isnasyauqiah Rahman Wahid, Abdul Sirajul Huda, Muhammad Resa Lamandau, Dwi Doctoral Program of Environemntal Science Postgraduate Program Lambung Mangkurat University Jl Brigjen H. Hasan Basri Kayutangi South Kalimantan Banjarmasin70123 Indonesia Chemical Engineering Department Engineering Faculty Lambung Mangkurat University Jl A. Yani Km 36 South Kalimantan Banajrbaru70714 Indonesia Faculty of Integrated Technologies Universiti Brunei Darussalam Gedung BE1410 Brunei Lambung Mangkurat University Jl A. Yani Km 36 South Kalimantan Banajrbaru70714 Indonesia

Ceramic membrane support derived from spent bleaching earth (SBE) become a novel study due to their low-cost, sustainable features, abundance material, and there is not yet applicated as membrane. In this study, flat disk ceramic membrane configuration was fabricated and characterized from solid waste of crude palm oil bleaching process by pressing method in different SBE loading mass (38-42 %wt.). The SBE as raw material was deoiled using n-hexane and acetone solvent, followed by fabricated it become flat disk SBE membranes. Afterward, the SBE flat disk membranes was characterized through fourier-transform infrared spectroscopy (FTIR) and X-ray fluorescence (XRF) analyzer. The result exhibits the flat disk SBE ceramic membrane has dimension of 41 and 6 mm for diameter and thickness, respectively. SBE membranes indicating have montmorillonite structure due to presence of silica as main component materials of SBE. Besides that, the existence of siloxane vibration band in SBE membranes for the sample after regeneration with n-hexane and acetone were dominated over using raw SBE. It concludes the oil residue was removed and produced SBE membrane properties become robust with less organic contaminant. © 2023 Elsevier Ltd. All rights reserved.

关键词： Acetone

来源：评论

学校读者我要写书评

暂无评论

Processing Speed Comparison of the Least Significant Bit (LSB) Steganography Algorithm on FPGA and Matlab 6

Processing Speed Comparison of the Least Significant Bit (LS...

引用

6th International Conference on Informatics and Computing, ICIC 2021

作者： Yakti, Bayu Kumoro Madenda, Sarifuddin Sudiro, Sunny Arief Musa, Purnamawan Gunadarma University Information Tech. Doctoral Program Jakarta Indonesia STMIK Jakarta STIK Electrical Engineering Jakarta Indonesia

ISBN: (纸本)9781665421553

Digital images are images in digital formats or digital media such as hard drives. Digital images consist of bits (0 or 1) called pixels and have a high capacity for storing data and information. Steganography techniques try to hide the existence of confidential data. The Steganography technique perfectly closes secret messages in carrier images with high level security. Information and data will be manipulated so that it can be detected by human eyes. Least Significant Bit (LSB) is the method used in this study. The embedding and extracting processes in the proposed algorithms are performed using Matlab software and FPGA-based hardware simulation using Xilinx ISE. The purpose of this study is to compare the process speed of the LSB steganography algorithm in the two implementations. The input data on the encryption used is data in binary form and Red Green Blue (RGB) images and output data in stego images. Meanwhile, the input data in the decryption is a stego image and the output data is in the form of binary data. The experimental results showed that the steganography algorithm had been successfully performed on FPGA and Matlab. However, the process on FPGA is faster than the process on Matlab. The result of the encryption process is 696000 times faster than Matlab. Meanwhile, the decryption process is 236000 times faster than Matlab. © 2021 IEEE.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Model for Pauses in the Synthesized Speech of Mathematical Expressions in MathML 22

A Dynamic Model for Pauses in the Synthesized Speech of Math...

引用

Proceedings of the 14th International Conference on Education Technology and Computers

作者： Adriana Souza Diamantino Freitas Bahia Federal Institute of Education Science and Technology Brazil and Doctoral Program in Digital Media Faculty of Engineering Faculty of Engineering of University of Porto Portugal Department of Electrical and Computer Engineering Faculty of Engineering of University of Porto Portugal

ISBN: (纸本)9781450397766

Voice synthesizers still present several challenges in the speech of mathematical content, as spoken mathematics has quite peculiar rules. In the synthesized speech, pauses help blind and visually impaired students identify the limits of mathematical operators and subexpressions. However, most studies on pauses define them uniformly or use simple punctuation marks to force the synthesizer to introduce pauses in certain parts of the expression. Speech is a dynamic process and pauses in expressions also need to be dynamic to make the synthetic speech of expressions more natural, as this can help in memorizing this type of content. This work proposed a dynamic model of pauses for mathematical expressions. Collected math expressions spoken by teachers were used to create the model. These expressions were useful for identifying patterns and creating a linear regression model. Blind and visually impaired students evaluated the model. Some improvements were observed when we compared the synthesized mathematical expressions with the model and Audiomath, the parameter tool used in this study.

关键词： Accessibility Synthesized Speech Mathematics Visual Impairment

来源：评论

学校读者我要写书评

暂无评论

The influence of different camera perspectives and display devices on Beyond Visual Line of Sight (BVLOS) UAV operations

The influence of different camera perspectives and display d...

引用

SICE Annual Conference

作者： Nianzi Tu Sungju Maeng Makoto Itoh Doctoral Program in Risk and Resilience Engineering University of Tsukuba Tsukuba Ibaraki Japan Institute of Systems and Information Engineering Center for Artificial Intelligence Research University of Tsukuba Tsukuba Ibaraki Japan

With the growth of the use of drones especially in populated areas, Beyond the Visual Line of Sight (BVLOS) operation is expected as a challenge for drone operation. The layout of the Ground Control System (GCS) interface and the drone camera screen via display devices are anticipated to be crucial to the performance of the BVLOS operation. Moreover, the camera perspectives may influence the behavior of operators as the situation. In this study, participants (n=29) in a variety of situations involving multiple takeoff and landing sites, obstacles, and weather were grouped according to the display devices and camera perspectives used. The result shows the Head Mounted Display (HMD) is physically uncomfortable with the possibility of VR sickness, which is more prevalent with the first-person view than the third-person view, but it crashes less and has a straighter flight path. Landing in a narrow area has a high crash rate but is safer with HMD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online 3D Bin Packing for Novel Objects Based on Deep Reinforcement Learning

Online 3D Bin Packing for Novel Objects Based on Deep Reinfo...

引用

International Conference on Advanced Robotics and Intelligent Systems (ARIS)

作者： Shao-Yu Chien Ching-Chang Wong Doctoral Program in Robotics College of Engineering Tamkang University New Taipei City 25137 Taiwan Electrical and Computer Engineering Department Tamkang University New Taipei City 25137 Taiwan

In this paper, a method using deep reinforcement learning is proposed to deal with the 3D online bin packing problem. The packing objects are not limited to several specific or fixed cuboid objects, but are composed of more than a thousand objects and randomly generated cuboids, which make the trained policy network can handle novel unknown objects. In addition, the posture of the object in the box can be any angle, not limited to horizontal and vertical. In the proposed method, four voxel maps are used as inputs, and a Soft Actor-Critic (SAC) algorithm is used to train a policy network. On the other hand, in order to deal with various objects with irregular shapes, a packing task simulator with physics engine enable the policy network to learn the state of falling and stacking objects. In terms of training environment of deep reinforcement learning, the proposed method can be applied to boxes of different sizes because of the scalable image information. Moreover, a reward function and a training strategy with gradually increasing difficulty are proposed to effectively improve the learning of policy network. In terms of experimental results, the results on a random object bin packing task in a simulator illustrate the effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Polyethersulfone membrane coated with Dragon blood resin: Effect of input parameters and optimization using response surface methodology

引用

South African Journal of Chemical engineering 2023年 45卷 30-41页

作者： Ambarita, Aulia Chintia Arahman, Nasrul Bilad, Muhammad Roil Gül, Bahar Yavuztürk Korkut, Sevde Yüksekdağ, Ayşe Teber, Oğuz Orhun Koyuncu, İsmail Mulyati, Sri Doctoral Program School of Engineering Science Syiah Kuala University Banda Aceh Jalan Syeh Abdur Rauf 23111 Indonesia Department of Chemical Engineering Syiah Kuala University Banda Aceh Jalan Syeh Abdur Rauf 23111 Indonesia Faculty of Integrated Technologies Universiti Brunei Darussalam Jalan Tungku Link Bandar Seri Begawan BE1410 Brunei Darussalam National Research Center on Membrane Technologies Istanbul Technical University Istanbul Maslak 34469 Turkey

This study investigates the effectiveness of dragon blood resin (DBR) as a hydrophilic additive to prevent fouling on membrane surfaces. The input parameters, including DBR, Fe³⁺, NMP concentration, and coating time were studied to understand their correlation with response variables, such as permeability, selectivity, and fouling recovery. A central composite design (CCD) to analyze the twenty-one sets of experimental designs. The selected membrane was characterized for hydrophilicity, functional group, morphology, and mechanical properties. The ANOVA result indicates that the p-value for all response models is significant, except for humic acid rejection. The study found that a higher concentration of DBR and NMP, as well as a longer coating time, result in lower permeability, greater humic acid rejection, and higher contact angle, while Fe³⁺ concentration does not have a significant effect. The membrane's surface characteristics did not change significantly after coating, such as chemical function and morphology, while the tensile strength decreased with increasing DBR concentration, NMP, and coating time. The membranes demonstrated good selectivity and antifouling properties, with the optimal condition being 0.223 mg/L DBR, 5 min coating time, 1.65 mg/L Fe³⁺, and 46.19% NMP, resulting in 30.34 L/m².*** of humic acid permeability and 119.6% of fouling recovery. © 2023 The Author(s)

关键词： Antifouling Central composite design Dragon blood resin Polyethersulfone

来源：评论

学校读者我要写书评

暂无评论

Technology-Enhanced Learning for User Security Awareness Using AI-based Naive RAG: A Design and Prototype

Technology-Enhanced Learning for User Security Awareness Usi...

引用

Advancement in Data Science, E-learning and Information Systems (ICADEIS), International Conference on

作者： I Putu Agus Eka Pratama I Made Oka Widyantara Linawati Nyoman Gunantara Sinung Suakanto Eka Tresna Irawan Doctoral Program of Engineering Sciences Faculty of Engineering Udayana University Badung Bali Indonesia dept. of Electrical Engineering Faculty of Engineering Udayana University Badung Bali Indonesia dept. of Information System Telkom University Bandung West Java Indonesia Mayar International Pte. Ltd. Singapore

ISBN: (数字)9798331513320

ISBN: (纸本)9798331513337

The increasing use of Information Technology (IT) in all areas of life, followed by increasing cybersecurity threats on the user side, makes cybersecurity awareness among users an obligation that must be met. Several solutions currently available (guides, discussion forums, workshops) have not been able to provide good results and are lacking in terms of user engagement, adaptability, and optimizing available resources, so technology-based learning is needed, especially AI. This paper introduces the design and prototype of an AI-based learning system, especially with the Naive Retrieval-Augmented Generation (Naive RAG) method with three steps, including Retrieval, Augmented, and Generation. The system combines contextual user questions and answers with internal and domain knowledge systems to explain cybersecurity awareness to users dynamically and personally. The prototype that has been developed is then tested using the Black Box Testing method to evaluate functionality and usability. The test results show that the functionality of the system built has run well with a percentage of success of 100%, so it can be used as a technologybased learning medium for education and learning of user security awareness.

关键词： Electronic learning Retrieval augmented generation Knowledge based systems Prototypes Learning (artificial intelligence) Computer security Usability Information technology Testing Information systems

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：