检索结果-内蒙古大学图书馆

Faster R-CNN Deep Learning Model for Pedestrian Detection from Drone Images

SN computer Science 2020年第2期1卷 1-9页

作者： Hung, Goon Li Sahimi, Mohamad Safwan Bin Samma, Hussein Almohamad, Tarik Adnan Lahasan, Badr Intelligent Biometric Group School of Electrical and Electronic Engineering Engineering Campus Universiti Sains Malaysia Penang Nibong Tebal 14300 Malaysia Department of Computer Programming Faculty of Education–Shabwa University of Aden Shabwa Yemen School of Information Science and Technology Xiamen University Malaysia Jalan Sunsuria Bandar Sunsuria Selangor Darul Ehsan Sepang 43900 Malaysia

Pedestrian detection from a drone-based images has many potential applications such as searching for missing persons, surveillance of illegal immigrants, and monitoring of critical infrastructure. However, it is considered as a very challenge computer vision problem due to the variations in camera point of view, distance from pedestrian, changes in illuminations and weather conditions, variation in the surrounding objects, as well as present of human-like objects. Recently, deep learning-based models are getting more attention, and they have proven a great success in many object detection problems such as the detection of faces, breast masses, and vehicles. As such, this work aims to develop a deep learning-based model that will be applied for the problem of pedestrian detection from a drone-based images. Particularly, faster region-based convolutional neural network (Faster R-CNN) will be used to search for the present of a pedestrian inside the captured drone-based images. To assess the performances, a total of 1500 images were collected by S30W drone and these images were captured at different places, with various views and weather conditions, and at daytime and night-time. Results show that Faster R-CNN was able to achieve a promising result with 98% precision, 99% recall, and 98% F1 measure. Further analysis has been conducted by comparing the outcomes of Faster R-CNN with YOLO deep model on UAV123 publicly available dataset. The reported results indicated that both detection models almost reported very similar results. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Deep learning Drone images Faster R-CNN Pedestrian detection

来源：评论

学校读者我要写书评

暂无评论

Structure and Functioning of Information Systems of Background Monitoring of Landscape Elements of Gorgany Nature Reserve 10

Structure and Functioning of Information Systems of Backgrou...

引用

10th International Conference on Advanced computer Information Technologies, ACIT 2020

作者： Nykolaychuk, Yaroslav Petrashchuk, Yaroslav Slobodian, Olena Pitukh, Ihor Grynchyshyn, Taras Nykolaychuk, Lyubov Hryha, Volodymyr Ternopil National Economic University Department of Specialized Computer Systems Ternopil Ukraine Gorgany Nature Reserve Nadvirna Ukraine Nadvirna College by National Transport University Department of Programming and Information Technologies Nadvirna Ukraine Ivano-Frankivsk National Technical University of Oil and Gas Department of Social Communication and Law Ivano-Frankivsk Ukraine Vasyl Stefanyk Precarpathian National University Department of Computer Engineering and Electronics Ivano-Frankivsk Ukraine

This paper discusses the structural organization of the background monitoring system (BMS) of the transboundary UNESCO World Heritage Site 'Beech forests of the Carpathians and ancient beech forests of Germany' using actual data and information from Gorgany Nature Reserve in Ivano-Frankivsk, Ukraine. The features of the structure and functions of background monitoring of the protected natural resources, forests and wildlife of Gorgany Nature Reserve is based on modern methods of collecting and processing of digital data, implementation of the principles of Internet of Things and cloud technologies, combined with GPS-systems, sensor networks with the use of optical and fiber-optic telecommunication channels. The information technology of the background monitoring system is based on figurative cluster models of monitoring objects according to theoretical principles of statistical, correlatory, spectral, cluster, logic-statistical and entropy analysis. © 2020 IEEE.

关键词： Sensor networks

来源：评论

学校读者我要写书评

暂无评论

Functorial string diagrams for reverse-mode automatic differentiation

arXiv

引用

arXiv 2021年

作者： Alvarez-Picallo, Mario Ghica, Dan R. Sprunger, David Zanasi, Fabio Programming Languages Laboratory Huawei Research Centre 2 Semple Str. EdinburghEH3 8BL United Kingdom Computer Science and University of Birmingham Birmingham EnglandB15 2TT United Kingdom Computer Science University College London London EnglandWC1E 6BT United Kingdom

We enhance the calculus of string diagrams for monoidal categories with hierarchical features in order to capture closed monoidal (and cartesian closed) structure. Using this new syntax we formulate an automatic differentiation algorithm for (applied) simply typed lambda calculus in the style of [Pearlmutter and Siskind 2008] and we prove for the first time its soundness. To give an efficient yet principled implementation of the AD algorithm we define a sound and complete representation of hierarchical string diagrams as a class of hierarchical hypergraphs we call hypernets. Copyright © 2021, The Authors. All rights reserved.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

A Horizontal Federated Learning Approach to IoT Malware Traffic Detection: An Empirical Evaluation with N-BaIoT Dataset

A Horizontal Federated Learning Approach to IoT Malware Traf...

引用

International Conference on Advanced Communication Technology (ICACT)

作者： Phuc Hao Do Tran Duc Le Vladimir Vishnevsky Aleksandr Berezkin Ruslan Kirichek The Bonch-Bruevich Saint-Petersburg State University of Telecommunications Saint-Petersburg Russia Danang Architecture University Da Nang Viet Nam Department of Communication Networks and Data Transmission at Bonch-Bruevich Saint-Petersburg State University of Telecommunications Russia University of Science and Technology - The University of Danang Da Nang Viet Nam Information Technology Faculty The University of Danang - University of Science and Technology Danang Vietnam V. A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences Moscow Russia Institute of Control Sciences of Russian Academy of Sciences Russia Department of Programming Engineering and Computer Science Bonch Bruevich Saint Petersburg State University of Telecommunications

The increasing prevalence of botnet attacks in IoT networks has led to the development of deep learning techniques for their detection. However, conventional centralized deep learning models pose challenges in simultaneously ensuring user data privacy and detecting botnet attacks. To address this issue, this study evaluates the efficacy of Federated Learning (FL) in detecting IoT malware traffic while preserving user privacy. The study employs N-BaIoT, a dataset of real-world IoT network traffic infected by malware, and compares the effectiveness of FL models using Convolutional Neural Network, Long Short-Term Memory, and Gated Recurrent Unit models with a centralized approach. The results indicate that FL can achieve high performance in detecting abnormal traffic in IoT networks, with the CNN model yielding the best results among the three models evaluated. The study recommends the use of FL for IoT malware traffic detection due to its ability to preserve data privacy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Synthesis, structural and optical properties of CdO nanocrystalline prepared by sol–gel method

引用

AIP Conference Proceedings 2022年第1期2660卷 020141页

作者： Salah Abdul-Jabbar Jassim Eman Mohammed Ali Nassar College of Dentistry Al Maaqal private university Basrah Iraq Department of computer programming Al-Thawra Technical Institute Ministry of Technical Education & Vocational Training Hajjah Yemen

CdO Thin Film and powder nanoparticles have been produced using the sol-gel method. The X-ray diffraction technique is used to evaluate structural properties of powder CdO at different annealing temperatures 623, 673, 723 (K). It indicates that CdO nanoparticles in nature have a polycrystalline cubic structure. The size of the crystallite (D) is in the middle of the range 23.14-46.65 (nm). As the annealing temperature increases, the crystallite size increases. Also, dislocation density (δ), strain (ε), and texture coefficient TC(hkl) were calculated. The energy band-gap and refractive index were estimated. Band gap energy decreases with increasing annealing temperature and refractive index increases with increasing annealing temperature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A non-potential Target Function for Controlling the UAVs Group Flight in Presence of Concave Obstacles

A non-potential Target Function for Controlling the UAVs Gro...

引用

IEEE International Conference on Actual Problems of Unmanned Air Vehicles Developments Proceedings (APUAVD)

作者： Olexiy M. Glazok Computer and programming engineering National Aviation University Kyiv Ukraine

ISBN: (纸本)9781728125930

A solution for the problem of controlling the unmanned quadrotor vehicles group flight in presence of obstacles of complex form is proposed. A traditional approach to construction of the target function does not solve the problem of control at presence of concave obstacles; the UAVs may get trapped in such a situation. The proposed target function contains the three terms. The first of them controls the UAVs' behavior with respect to attitude. The second is built on the base of a moving coordinate system bound to the trajectory of the group motion. The third addend is a standard sum that performs the function of repelling the UAVs one from another. Also, in the proposed approach the motion is bound to the virtual center of the group, instead of one UAV that is chosen to be a leader. This approach helps to avoid a discrepancy between desired and actual states of the group in case that the leader UAV experiences some problems with its motion.

关键词： Unmanned aerial vehicles Trajectory Acceleration Mathematical model Collision avoidance Standards Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Modelling the Decision Making Process on Legal Conducting the Surrogate Motherhood

Modelling the Decision Making Process on Legal Conducting th...

引用

IEEE International Conference on Dependable Systems, Services and Technologies (DESSERT)

作者： Tetiana Hovorushchenko Alla Herts Yelyzaveta Hnatchuk Computer Engineering & System Programming Department Khmelnytskyi National University Khmelnytskyi Ukraine Civil Law and Legal Proceedings Department Ivan Franko National University of Lviv Lviv Ukraine

ISBN: (数字)9781728199573

ISBN: (纸本)9781728199580

Currently, there is a need in Ukraine for the design and development of multidisciplinary decision support systems (DSSs) for the medical and other related spheres - for example, the medical law sector, in particular, the DSS for the surrogacy's legal regulation field. This DSS will be able to protect doctors from potentially wrong decisions by taking into account all available information when making the decisions. For design such DSS, it's necessary to conduct the modelling of the decision-making process on surrogacy's legal conducting, that is the goal of this research. In this paper, there are the theoretical foundations of using the ontologies for the decision-making process on surrogacy's legal conducting, a model of base ontology with the necessary requirements and recommendations for conducting the surrogate motherhood, and ontology-based model of the decision-making process on surrogacy's legal conducting. The conducted modelling is a theoretical basis for the development of methods and design of DSS in the field of legal regulation of surrogate motherhood.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modern Information Technologies in Scientific Research and Educational Activities

arXiv

引用

arXiv 2024年

作者： Malakhov, Kyrylo Kaverinskiy, Vladislav Ivanova, Liliia Romanyuk, Oleksandr Romaniuk, Oksana Voinova, Svitlana Kotlyk, Sergii Sokolova, Oksana V. M. Glushkov Institute of Cybernetics The National Academy of Sciences of Ukraine Kyiv Ukraine Department of Wear-Resistant and Corrosion-Resistant Powder Construction Materials Frantsevic Institute for Problems in Material Science The National Academy of Sciences of Ukraine Kyiv Ukraine Separated Structural Subdivision «Odesa Technical Professional College of Odesa National University of Technology» Odessa Ukraine Vinnytsia National Technical university Vinnytsia Ukraine Vinnytsia National Technical university Vinnytsia Ukraine Odesa National University of Technology Odessa Ukraine The Institute of Computer Engineering Automation Robotics and Programming Odesa National University of Technology Odessa Ukraine Odesa National University of Technology Odessa Ukraine

This article presents a comprehensive methodology for enhancing the capabilities of conversational AI systems, focusing on ChatGPT, through the integration of ontology-driven structured prompts and meta-learning techniques. The proposed approach, exemplified by the RDWE OntoChatGPT system, demonstrates significant potential for improving productivity and expanding knowledge bases in specific subject domains and languages. By formalizing methods for creating and configuring structured prompts and context ontologies, the system enables ChatGPT to provide specific information using selected contexts, thereby enhancing its performance in handling data across diverse linguistic and domain contexts. Through empirical testing, the study evaluates the system’s effectiveness in providing accurate responses while also highlighting areas for further refinement. The methodology’s adaptability to other conversational AI systems based on large language models underscores its potential for broader application in natural language processing and dialogue systems. Future enhancements aim to refine structured prompts and incorporate additional input data to further improve system performance and accuracy. Overall, this research contributes to advancing the capabilities of conversational AI systems, paving the way for more sophisticated and effective human-computer interactions in various domains. © 2024, CC BY-SA.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Escape from Escape Analysis of Golang

Escape from Escape Analysis of Golang

引用

IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice Track (ICSE-SEIP)

作者： Cong Wang Mingrui Zhang Yu Jiang Huafeng Zhang Zhenchang Xing Ming Gu KLISS BNRist School of Software Tsinghua University Beijing China Compiler and Programming Language Lab Huawei Technologies Hangzhou China College of Engineering and Computer Science ANU Canberra Australia

ISBN: (数字)9781450371230

ISBN: (纸本)9781728165240

Escape analysis is widely used to determine the scope of variables, and is an effective way to optimize memory usage. However, the escape analysis algorithm can hardly reach 100% accurate, mistakes of which can lead to a waste of heap memory. It is challenging to ensure the correctness of programs for memory *** this paper, we propose an escape analysis optimization approach for Go programming language (Golang), aiming to save heap memory usage of programs. First, we compile the source code to capture information of escaped variables. Then, we change the code so that some of these variables can bypass Golang's escape analysis mechanism, thereby saving heap memory usage and reducing the pressure of memory garbage collection. Next, we present a verification method to validate the correctness of programs, and evaluate the effect of memory optimization. We implement the approach to an automatic tool and make it open-source 1 . For evaluation, we apply our approach to 10 open-source projects. For the optimized Golang code, the heap allocation is reduced by 8.88% in average, and the heap usage is reduced by 8.78% in average. Time consumption is reduced by 9.48% in average, while the cumulative time of GC pause is reduced by 5.64% in average. We also apply our approach to 16 industrial projects in Bytedance Technology. Our approach successfully finds 452 optimized cases which are confirmed by developers.

关键词： Optimization Memory management Heuristic algorithms computer languages Open source software Tools Software engineering

来源：评论

学校读者我要写书评

暂无评论

Erratum to “Bipolar fuzzy graphs” [Information Sciences 181 (2011) 5548-5564]

引用

Information Sciences 2019年 477卷 546-548页

作者： Ganesh Ghorai Department of Applied Mathematics with Oceanology and Computer Programming Vidyasagar University Midnapore 721 102 India

In this erratum, it is shown that Proposition 5.4 and Proposition 5.5 in [1] are not correct. Accordingly, the updated results are established.

关键词： Bipolar fuzzy graphs Semi-strong bipolar fuzzy graphs Counterexample

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：