检索结果-内蒙古大学图书馆

18th international conference on Interfaces and Human computer Interaction 2024, IHCI 2024, the 17th international conference on Game and Entertainment Technologies 2024, GET 2024 and the 18th international conference on computer Graphics, Visualization, computer Vision and Image Processing 2024, CGVCVIP 2024, Part of the 18th multi conference on computer science and Information Systems 2024, MCCSIS 2024

作者： Kaziyeva, Nazym Kukharev, Georgy Maulenov, Kalybek Department of Radio Engineering Electronics and Telecommunications L.N. Gumilyov Eurasian National University Satpayev Str. 2 Nur-Sultan010008 Kazakhstan St. Petersburg Electrotechnical University "LETI" Professor Popov str. 5 litera F St. Petersburg197022 Russia Non-Profit Limited Company Akhmet Baitursynuly Kostanay Regional University Baytursynov Street 47 Kostanai110000 Kazakhstan

ISBN: (纸本)9789898704580

The article presents a new fast method for generating a biometric multimedia file consisting of a color image of a face with a color QR code embedded in it, containing biometric data about the face, as well as documentary information about the person to whom this face belongs. Embedding is implemented by simultaneously replacing three LSB slices in the RED, GREEN and BLUE components of a color face image with a color QR code. At the same time, the embedded QR code does not detect the fact of its existence in the multimedia file. To improve the understanding of the idea of the method, the proposed solutions and the algorithm implementing the method, the article presents graphic illustrations with appropriate descriptions and explanations. The solutions proposed in the article have a number of qualitative characteristics presented and discussed in the article. The areas of application of the proposed solutions are marked. © 2024 Interfaces and Human computer Interaction. All Rights Reserved.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

1st Paris Van Java international Seminar on computer, science, engineering, and Technology, PVJ ISComSET 2020

1st Paris Van Java International Seminar on Computer, Scienc...

引用

1st Paris Van Java international Seminar on computer, science, engineering, and Technology, PVJ ISComSET 2020

The proceedings contain 216 papers. The topics discussed include: temperature effects on plasma li-heparin and transaminase activity in children blood with tetralogy of fallot;optimization of polyethylene glycol concentration as an agglutination potentiator for examination of blood types of dry blood sample;stability test of coloring agent from pericarpium of red dragon fruit (hylocereus polyrhizus) extract in laboratory diagnostic of intestinal nematode eggs preparation;differences of bio (chemical) characterization of garlic and black garlic on antibacterial and antioxidant activities;the relationship of self-efficacy with adherence in restricting fluid intake in middle adult hemodialysis patients;the variation of ethanol concentration and Kombucha characterization on several incubation periods;analysis of drug effectiveness and efficiency of use of amlodipine-captopril combination compared to amlodipine-valsartan in the X hospital patients of Bogor;and the best pasteurization method in reducing the amount of bacteria in cow's milk on people dairy farm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

multi-Granularity Evolutionary Clustering Algorithm for Energy Efficiency in Industrial IoT

Multi-Granularity Evolutionary Clustering Algorithm for Ener...

引用

2025 IEEE international Students' conference on Electrical, Electronics and computer science, SCEECS 2025

作者： Rajkumar, S. Gopalakrishnan, R. Janarthanan, V Sabari Raagul, V.K. Suman, M. K. S. Rangasamy College of Technology Computer Science and Engineering 637 215 India K. S. Rangasamy College of Technology Electrical and Electronics Engineering 637 215 India

ISBN: (纸本)9798331529833

The evolutionary method facilitates adaptive clustering by investigating an extensive search space of possible configurations, guaranteeing optimal cluster formation for diverse Industrial Internet of Things (IIoT) scenarios. Comprehensive simulations illustrate the efficacy of the proposed MGECA framework in attaining substantial energy savings relative to conventional clustering techniques, including LEACH and KMeans. The findings demonstrate that the MGECA framework prolongs network longevity by an average of 28.5 hours, signifying a 27.8% enhancement compared to LEACH and an 18.2% enhancement relative to K-Means. The proposed method attained a data transmission efficiency of 95% at 50 hours, exceeding LEACH's 85% and K-Means' 75% efficiency rates. The frequency of cluster reconfiguration was optimised to 3.5 hours, representing a 32.7% reduction compared to LEACH. The results underscore the MGECA framework's potential as a robust and scalable solution for energy-efficient clustering in extensive IIoT networks, thereby enhancing the sustainability and reliability of industrial systems while improving performance metrics essential for effective IIoT implementations. © 2025 IEEE.

关键词： Industrial internet of things (IIoT)

来源：评论

学校读者我要写书评

暂无评论

multi-Domain Graph-Enhanced Joint Intent and Slot Learning

IAENG International Journal of Computer Science

引用

IAENG international Journal of computer science 2025年第2期52卷 374-382页

作者： Shi, Wu Yuan, Weihao Wang, Yang Dong, Yindong Xu, Gaojian School of Information and Artificial Intelligence Anhui Agricultural University Hefei230036 China School of Computer Science and Technology Xidian University Xi’an710126 China School of Engineering Anhui Agricultural University Hefei230036 China

Comprehension of spoken language is essential in dialog systems, as it supports two fundamental tasks: intent classification and slot filling. At present, federated modeling methodologies prevail in the domain of spoken language comprehension. Nevertheless, current models encounter constraints in accurately representing the interrelations among activities and utilizing cross-domain semantic data. This study introduces the multi-Domain Graph-Enhanced Joint Intent and Slot Learning (MDG-JISL) paradigm to tackle these difficulties. MDG-JISL amalgamates a pre-trained BERT model with a self-trained FastText model to create superior sentence-level and word-level representations. A syntactic dependency tree is employed to create graph structures among words, which are subsequently refined by the implementation of a Graph Convolutional Network (GCN) to more effectively capture relationship properties. A Conditional Random Field (CRF) model is utilized for decoding, enhancing the model’s efficacy in natural language processing tasks. Experimental findings indicate that MDG-JISL attains remarkable performance on cross-domain datasets, with Slot(F1), Intent (Acc), and Overall (Acc) metrics of 98.7%, 98.4%, and 92.4%, respectively. The results validate the model’s efficacy in intent classification and slot filling. © (2025), (international Association of Engineers). All rights reserved.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Enhanced Lane Detection for Autonomous Campus Shuttles Using Hybrid computer Vision Techniques

Enhanced Lane Detection for Autonomous Campus Shuttles Using...

引用

2024 international conference on science, engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Aderoba, Olugbenga Adegbemisola Ekezie, Gideon Onyinyechi Mpofu, Khumbulani Ajisegiri, Emmanuel Adediran, Adeolu A. Daniyan, Ilesanmi Afolabi Ogundokun, Roseline Oluwaseun Landmark University Department of Mechanical Engineering Omu-Aran Nigeria Tshwane University of Tech Dept. of Industrial Engineering Pretoria South Africa Tshwane University of Technology Department of Industrial Engineering Pretoria South Africa University of Johannesburg Department of Mechanical Engineering Science South Africa Achievers University Department of Mechanical and Mechatronics Engineering Owo Nigeria Landmark University Department of Computer Science Omu-Aran Nigeria Kaunas University of Technology Department of Multimedia Engineering Lithuania

ISBN: (纸本)9798350358155

Ensuring safe and efficient navigation in smart campus transportation systems is increasingly crucial with the integration of autonomous vehicles, making accurate and robust lane detection a paramount factor. This research presents a combined traditional computer vision algorithm with advanced deep learning techniques to enhance the precision and dependability of lane detection in diverse campus environments in autonomous campus shuttles. The system utilizes a multi-stage process, incorporating color segmentation, edge detection, and Convolutional Neural Network (CNN) for robust lane feature extraction. A dynamic region of interest adjustment mechanism that adapts to varying campus scenarios ensuring adaptability to lighting conditions and road layouts, was introduced. Experimental results using a miniature scaled-down autonomous campus shuttle demonstrated significant improvements in lane detection accuracy compared to conventional methods, validating the effectiveness of our enhanced approach. The proposed system enhances the safety and reliability of autonomous campus shuttles and contributes to the broader field of computer vision applications for intelligent transportation systems. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Design and Development of Chip Design for Digital Electronic System: Evolution and Trends 1

Design and Development of Chip Design for Digital Electronic...

引用

1st international conference on Advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Deep, Pragya Anand, John Rawat, Himani Kumar, Pankaj Kubba, Akshaya Karn, Ankriti IIMT College of Engineering Department of AI & DS Greater Noida India UP Greater Noida India Tula's Institute Department of Electronics and Communication Engineering Dehradun India Amity University Department of Statistics Kolkata India Chandigarh University Deparment of Computer Science Punjab Mohali India Tula's Institute Department of Computer Science & Engineering Dehradun India

ISBN: (纸本)9798331518578

System on-a-chip (SoC) achievement relies upon a very much planned, incorporated come nearer from a few disciplines, including application, plan, and gadget. From the viewpoint of the gadget, quick progressing VLSI innovation makes it conceivable to incorporate billions of semiconductors on a solitary chip, empowering the mix of various capabilities on a solitary chip. Since they rely upon these electrical interconnects at the actual level, on-chip correspondence models like transports and networks on-chip (NoC), which are utilized to empower between part correspondence in multi-processor systems on-chip (MPSoC) plans, are dependent upon the full scope of troubles and impediments that influence copper-based electrical interconnects. Various examination projects have begun looking at imaginative association choices, for example, on-chip optical interconnects, remote interconnects, and carbon nanotube-based interconnects, trying to beat the downsides of traditional copper-based electrical interconnects. An outline and flow research status for these three promising association advancements are introduced in this review. It additionally discusses the issues that should be fixed for every one of these advances before they can ultimately be utilized to supplant copper-based electrical interconnects. © 2025 IEEE.

关键词： Network-on-chip

来源：评论

学校读者我要写书评

暂无评论

Advances in multi-Spectral Image Categorization Through Convolutional Neural Networks with an Optimized Activation Function 2

Advances in Multi-Spectral Image Categorization Through Conv...

引用

2nd IEEE international conference on Data science and Network Security, ICDSNS 2024

作者： Raman, Ramakrishnan Kumar, Vikram Pillai, Biju G. Verma, Apurv Rastogi, Shailesh Meenakshi, R. India Srv Media Sri Balaji University Pune India Parul Institute of Technology Parul University Department of Computer Science & Engineering Engineering and Technology India Pune India Chennai Institute of Technology Computer Science and Engineering India

ISBN: (纸本)9798350373110

In recent years, deep learning technologies have significantly advanced the field of multi-spectral image analysis. This paper presents a novel advancement through the development of a specialized Convolutional Neural Network (CNN) architecture that incorporates an optimized activation function designed specifically for categorizing multi-spectral images. Our research introduces a CNN architecture with depth-wise separable convolutions, batch normalization, dropout layers, and fully connected layers, engineered to efficiently analyze both spatial and spectral dimensions of multi-spectral data. The cornerstone of this innovation is the optimized activation function, empirically refined to enhance learning dynamics and computational efficiency, effectively addressing common issues like vanishing and exploding gradients. Through extensive testing on a diverse dataset of environmental and man-made objects, our model demonstrated superior performance metrics such as accuracy (94.2%), precision (93.8%), recall (92.9%), and F1 score (93.3%), significantly outperforming conventional models. These results highlight the effectiveness of the tailored activation function in learning complex patterns in multi-spectral images, thus improving categorization capabilities. This study underscores the potential of tailored deep learning structures in enhancing the accuracy and robustness of multi-spectral image categorization, with profound implications for environmental monitoring, agriculture, and remote sensing. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Intrusion Detection System in Industrial Internet of Things(IIoT) using Deep Learning 1

An Adaptive Intrusion Detection System in Industrial Interne...

引用

1st international conference on Innovative Sustainable Technologies for Energy, Mechatronics and Smart Systems, ISTEMS 2024

作者： Jyothi, E.V.N. Kranthi, M. Sailaja, S. Sesadri, U. Koka, Sridhar N. Reddy, Pundru Chandra Shaker Rise Krishna Sai Prakasam Group of Institutions Computer Science and Engineering A.P Ongole India Karunya Institute of Technology and Sciences Computer Science and Engineering Tamilnadu Coimbattore India Rise Krishna Sai Prakasam Group of Institutions A.P Ongole India Vardhaman College of Engineering Computer Science and Engineering Telangana Hyderabad India Andhra University Computer Science and Engineering Andhra Pradesh Visakhapatnam India School of Computer Science and Artificial Intelligence Sr University Telangana Warangal India

ISBN: (纸本)9798350384246

The Industrial-Internet-of-Things (IIoT) is a product of the extensive use of the Internet-of-Things(IoT) in vital industries including manufacturing and industrial production. To improve industrial and manufacturing processes, the IIoT integrates sensors, actuators, and smart tools that can interact with each other. There are many advantages to IIoT for service providers and customers alike, but privacy and security are still major concerns. Cyberattacks in such a network have been reduced with the use of an intrusion detection system (IDS). Nevertheless, several current IIoT intrusion detection systems (IDS) suffer from issues such as an incomplete list of the network's attack kinds, an excessive number of features, models constructed using outdated datasets, and an absence of attention to the issue of imbalanced datasets. Our proposed intelligent recognition system can spot cyberattacks in IIoT-networks, which will help with the difficulties. Singular value decomposition (SVD) is employed by the suggested model to decrease data characteristics and enhance detection outcomes. If we want to keep our classifications from being biased due to over-fitting or under-fitting, we employ the SMOTE method. Data has been classified using a number of deep learning and machine learning techniques for both binary and multi-class purposes. We test the suggested intelligent model on the ToN_ IoT dataset to see how well it performs. With the suggested method, we were able to achieve a 99.98% accuracy rate and a lowered error rate of 0.016% for multi-class classification, and a 0.001 % reduction in the error rate for binary classification. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Design of intelligent test system for multi-way valve

Design of intelligent test system for multi-way valve

引用

2022 international conference on Electronic Information engineering and computer science, EIECS 2022

作者： Zhang, Lu Xing, Keli Jin, Xiajie School of Mechanical Engineering and Automation Shanghai University Shanghai China

ISBN: (纸本)9781510663312

In order to solve the problem that there are many multi-way valve test items and the test steps are cumbersome, a set of multi-way valve intelligent test system is designed in this *** to the test requirements, the corresponding hydraulic system and electronic control system are designed, and the measurement and control software with multiple functional modules is developed based on *** software has a login module, a sensor parameter setting module, a sub-menu module, a data query module, and a main menu *** test results show that the function of the test system is perfect, and the test results meet the user's requirements. © 2023 SPIE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

A study of fireworks algorithm for cold chain logistics path optimization in karst landscape 8

A study of fireworks algorithm for cold chain logistics path...

引用

8th international conference on Electrical, Mechanical and computer engineering, ICEMCE 2024

作者： Zheng, Wenjia Zhang, Lei Chen, Bo Qv, Rui Ye, Yunji He, Zhuangli Li, Min Kust Faculty of Mechanical and Electrical Engineering Dept. of Intelligent Manufacturing Engineering Kunming China Yunnan Provincial Tabacco Company Cntc Kunming China Honghe Branch of Yunnan Provincial Tabacco Company Cntc Mile China

ISBN: (纸本)9798331506230

In this study, the challenges of cold chain logistics path optimization under complex terrain conditions are explored against the background of karst landscape, and the Fireworks Algorithm (FWA) is proposed and improved to enhance the efficiency and reliability of cold chain logistics path scheduling. By analyzing the operation process of cold chain logistics in Enterprise H, a mathematical model containing multi-objective optimization of transportation cost, temperature control, time constraints and terrain complexity is constructed. The improved algorithm enhances the performance in path optimization, cost control, temperature compliance and computational efficiency by introducing dynamic spark generation strategy, multi-mode search mechanism and hybrid optimization strategy. Experimental results show that the algorithm is more applicable in multi-objective optimization problems, and can reduce transportation costs and optimize logistics paths. © 2024 IEEE.

关键词： Cost reduction

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：