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

Synthesis Algorithm for a Continuous Robust Regulator on a Manifold for a Manipulator under Non-Random Noise Conditions

Synthesis Algorithm for a Continuous Robust Regulator on a M...

引用

International Russian Automation Conference (RusAutoCon)

作者： A. A. Kolesnikov S. I. Kolesnikova Institute of Computer Technology and Information Security South Federal University Taganrog Russia Institute of Computational Systems and Programming St.Petersburg State University of Aerospaсe Instrumentation St. Petersburg Russia

ISBN: (数字)9781728161303

ISBN: (纸本)9781728161310

The nonlinear adaptation algorithm is considered as applied to stabilization of the center of mass of a moving object subject to nonrandom noise in the control variable. An unknown disturbance is a bounded and continuous function of time. To solve the problem of its modeling and suppression, the following result is used: continuous functions can be described as partial solutions of some differential equations. The developed control algorithm guarantees full compensation of the external disturbance under certain conditions. The simulation result of the obtained control is applied to a manipulation object.

关键词： Mathematical model Regulators Manifolds Automation Aerospace electronics Gold

来源：评论

学校读者我要写书评

暂无评论

Using the Model of a Functional Rationalizer of Consumer Behavior in Recommendation Systems for Managing the Transport Activity of the Urban Population 23

Using the Model of a Functional Rationalizer of Consumer Beh...

引用

23rd International Conference on Soft Computing and Measurements, SCM 2020

作者： Seliverstov, Yaroslav A. Seliverstov, Svytoslav A. Podoprigora, Nikolay V. Starichenkov, Alexey L. Naryshkin, Roman S. Solomenko Institute of Transport Problems Russian Academy of Sciences Institute of Computer Science and Technology Peter the Great St.Petersburg Polytechnic University Laboratory of Intelligent Transport Systems St. Petersburg Russia Saint Petersburg State University of Architecture and Civil Engineering Department of Ground Transportation Technological Machines St. Petersburg Russia Saint Petersburg Electrotechnical University 'LETI' Department of Ship Control Systems St. Petersburg Russia Saint Petersburg State University Department of Programming Technology St. Petersburg Russia

ISBN: (纸本)9781728196923

An overview of existing urban software mobile applications of the transport and economic direction is given. A model of a functional rationalizer of consumer behavior is being built. The software model of the functional rationalizer of consumer behavior (SM FRCB) was developed for the first time. PMFRCB allows the user to expand the number of his preferred needs (occupations, activities) during the daily cycle through intelligent recommendations. Also, SM FRCB allows you to optimize needs (activities, activities) at the cost and rate of their use. The SM FRCB is made in Python_3 using the libraries matplotlib, collections, numpy, pyplot, mplot3d. The analysis of consumer behavior before and after using the functional rationalizer model is carried out. The graphical results of a structural analysis of the costs of old and new consumer behavior, analysis of consumer behavior within the boundaries of the theory of possibilities and the model of transport behavior of a resident before and after applying the functional rationalizer model are presented. The prospects of further improving the SM FRCB are considered. © 2020 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Multithreaded Parallel Sequence Alignment Based on Needleman-Wunsch Algorithm

Multithreaded Parallel Sequence Alignment Based on Needleman...

引用

IEEE Symposium on Bioinformatics and Bioengineering (BIBE)

作者： Veska Gancheva Ivaylo Georgiev Department of Programming and Computer Technology Technical University of Sofia Sofia Bulgaria The Stephan Angeloff Institute of Microbiology Sofia Bulgaria

ISBN: (纸本)9781728146188

Biocomputing and molecular biology are areas that change knowledge and skills for acquisition, storing, management, analysis, interpretation and dissemination of biological information. This requires the utilization of high performance computers and innovative software tools for management of the vast information, as well as deployment of innovative algorithmic techniques for analysis, interpretation and prognostication of data in order to get to insight of the design and validation of life-science experiments. Sequence alignment is an important method in DNA and protein analysis. The paper describes the computational challenges in biological sequence processing. The great challenges are to propose parallel computational models and parallel program implementations based on the algorithms for biological sequence alignment. An investigation of the efficiency of sequence alignment based on parallel multithreaded program implementation of Needleman-Wunsch algorithm is presented in this paper. Parallel computational model based on Needleman-Wunsch algorithm is designed. The proposed parallel model is verified by multithreaded parallel program implementation utilizing OpenMP. A number of experiments have been carried out for the case of various data sets and a various number of threads. Parallel performance parameters execution time and speedup are estimated experimentally. The performance estimation and scalability analyses show that the suggested model has good scalability both in respect to the workload and machine size.

关键词： Heuristic algorithms Proteins Computational modeling Dynamic programming Bioinformatics Software algorithms

来源：评论

学校读者我要写书评

暂无评论

Prevention of Japanese encephalitis with different control strategies considering environmental effects: A mathematical study

引用

AIP Conference Proceedings 2023年第1期2718卷

作者： K. Barman K. Maity R. N. Giri A. De Department of Mathematics Prabhat Kumar College Contai Purba Medinipur - 721404 West Bengal India Department of Mathematics Mugberia Gangadhar Mahavidyalaya Bhupatinagar Purba Medinipur-721425 W.B. India Department of Applied Mathematics with Oceonology and Computer Programming Vidyasagar University Midnapore 721102 India Department of Applied Sciences Haldia Institute of Technology Purba Medinipur - 721657 West Bengal India

Japanese encephalitis (JE), a public health problem for the entire world, is caused by a virus called Japanese encephalitis virus (JEV) which is spread by mosquitoes. According to WHO’s report, nearly 68000 clinical cases of JE are reported globally each year and approximately 13600 to 20400 are deaths. Here, a mathematical model of JE is formulated considering different control measures such as vaccination, treatment, insecticide and efforts to reduce environmental discharges. An explicit expression of basic reproduction number is formulated and the stability of disease-free and endemic equilibrium of the system is analyzed. In this paper, we have formulated an optimal control problem and analyzed different strategies considering the minimum cost for applying such strategies. We have investigated the results of fixed control for endemic equilibrium both numerically and graphically. We have solved the optimal problem numerically when control parameters are time-dependent by applying Runge-Kutta 4th order forward and backward method and presented graphically. In our present work, we discussed the best cost-effective control strategy to prevent Japanese encephalitis when we consider environmental discharges have a positive impact on the breeding of mosquitoes and the growth of the pig population.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Model of Deep Neural Network for Iris Classification With Different Activation Functions

A Model of Deep Neural Network for Iris Classification With ...

引用

2018 International Conference on Artificial Intelligence and Data Processing, IDAP 2018

作者： Eldem, Ayşe Eldem, Hüseyin Üstün, Deniz Department of Computer Engineering Karamanoǧlu Mehmetbey University Karaman Turkey Department of Technology and Computer Programming Karamanoǧlu Mehmetbey University Karaman Turkey

ISBN: (纸本)9781538668788

In recent years, deep neural network (DNN) has been frequently used for classification. In this study, iris flowers having 3 different types are classified by using DNN which are utilized the width and length of petal and sepal features as input. Some experiments are made for the iris dataset by using different activation functions and different epoch numbers. Then, the activation function which gives the best result is determined. The classification success of the developed model is achieved 96% for the iris dataset. © 2018 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Cyber-Typhon: An Online Multi-task Anomaly Detection Framework 15th

Cyber-Typhon: An Online Multi-task Anomaly Detection Framewo...

引用

15th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2019

作者： Demertzis, Konstantinos Iliadis, Lazaros Kikiras, Panayiotis Tziritas, Nikos School of Engineering Department of Civil Engineering Faculty of Mathematics Programming and General Courses Democritus University of Thrace Kimmeria Xanthi Greece School of Science Department of Computer Science University of Thessaly Lamia Greece Research Center for Cloud Computing Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (纸本)9783030198220

According to the Greek mythology, Typhon was a gigantic monster with one hundred dragon heads, bigger than all mountains. His open hands were extending from East to West, his head could reach the sky and flames were coming out of his mouth. His body below the waste consisted of curled snakes. This research effort introduces the "Cyber-Typhon" (CYTY) an Online Multi-Task Anomaly Detection Framework. It aims to fully upgrade old passive infrastructure through an intelligent mechanism, using advanced Computational Intelligence (COIN) algorithms. More specifically, it proposes an intelligent Multi-Task Learning framework, which combines On-Line Sequential Extreme Learning Machines (OS-ELM) and Restricted Boltzmann Machines (RBMs) in order to control data flows. The final target of this model is the intelligent classification of Critical Infrastructures’ network flow, resulting in Anomaly Detection due to Advanced Persistent Threat (APT) attacks. © 2019, IFIP International Federation for Information Processing.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Correction to: Multi-item two-stage fixed-charge 4DTP with hybrid random type-2 fuzzy variable

引用

Soft Computing 2021年第1期26卷 463-463页

作者： Devnath, Sudeshna Giri, Pravash Kumar Mondal, Seema Sarkar Maiti, Manoranjan Department of Mathematics National Institute of Technology Durgapur Durgapur India Department of Mathematics Government General Degree College Kashmuli India Department of Applied Mathematics with Oceanology and Computer Programming Vidyasagar University Midnapore India

来源：评论

学校读者我要写书评

暂无评论

Monitoring System for Prediction and Detection of Epilepsy Seizure

Monitoring System for Prediction and Detection of Epilepsy S...

引用

International Conference on Advances in Computational Tools for Engineering Applications, ACTEA

作者： Nashaat el Halabi Roy Abi Zeid Daou Roger Achkar Ali Hayek Josef Börcsök Department of Computer and Communications Engineering American University of Science and Technology Beirut Lebanon MART Learning Education and Research Center Chananir Lebanon Department of Computer Architecture and System Programming University of Kassel Germany

Epilepsy is a neurological disorder associated with abnormal electrical activity in the brain, which causes seizures. The occurrence of seizure is not predictable; the duration between seizures, as well as the symptoms, varies from patient to another. Since the seizures are not predictable, and most of epileptic patients suffer from physical risky symptoms during the seizure, such patients are not able to perform daily work activities. The objective of this project is to design and implement a monitoring system for epileptic patients; the system should continuously check some vital signs, analyze the measurements, and decide whether the patient is nearly to have a seizure or not. Whenever a seizure is predicted, the system initiates an alarm. In addition, a notification should be sent to the health care responsible, as well as one preferred contact. By implementing the monitoring system, people who suffer from epilepsy will have more chance to work and live a normal life. Thus, this paper presents the concept of the overall system and shows results of the implemented systems: EEG, ECG and Fall Detection system. Results have shown that the fall detection accuracy reached 99.89% whereas the accuracy of the prediction using the ANN was about 97.34%.

关键词： Electroencephalography Epilepsy Feature extraction Tools Monitoring Artificial neural networks Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Correction to: Fully fuzzy multi-item two-stage fixed charge four-dimensional transportation problems with flexible constraints

引用

Granular Computing 2021年第4期7卷 799-799页

作者： Devnath, Sudeshna Giri, Pravash Kumar Sarkar Mondal, Seema Maiti, Manoranjan Department of Mathematics National Institute of Technology Durgapur Durgapur India Department of Mathematics Government General Degree College Dantan-II Kashmuli India Department of Applied Mathematics with Oceanology and Computer Programming Vidyasagar University Midnapore India

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：