检索结果-内蒙古大学图书馆

Artificial intelligent based wild fire fighting machine using internet of things

AIP Conference Proceedings 2023年第1期2690卷

作者： Anita Keshav Patil A. R. Rajini Vijaya Kumar Gudivada Neerugatti Varipallay Vishwanath S. Kayalvili Vikas Tripathi 1Department of Electronics and Telecommunication Dr.Vithalrao Vikhe Patil College of Engineering MIDC Vilad Ghat Ahmednagar -414111 Maharashtra India 2Department of Electronics and Communication Engineering Sri Sairam Engineering College Chennai Tamil Nadu -600044 India 3Department of Information Technology Nawab Shah Alam Khan College of Engineering and Technology New Malakpet Hyderabad-500024 Telangana India 4Department of Electronics and Communication Engineering St.Martins engineering college Hyderabad - 500003 Telangana India 5Department of Computer Science and Engineering Velalar College of Engineering and Technology Thindal Erode-638012 Tamilnadu India 6Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun-248002 Uttarakhand India

The WildFire is the most alarming threat in the ecosystem. Wildfire is one of the human-made or nature-made hazards. There is no such kind of propulsion methods involved in reducing this effect. The proposed system aims to resolve this problem by constructing a Fire fighting machine with an AI-based assistant model. It is now constructed as a field trial. The main aim of the Machine is to produce artificial rains through the drones which will be having the sodium bicarbonate for frosting the cloud to produce rain droplets and reduce the advent of the fire. Thus the data will be automatically be captured and stored in the cloud-based system through the Internet of Things. In this method, we are using Tensorflow for assisting the drones. According to the IoT cloud, the Think speaks is used because it is the open-source platform for accessing data module sets. It is the most efficient and reliable cloud database. The data stored in the cloud are used for providing the AI machines to train themselves with appropriate data to resolve the problem more accurately. The sensors are fixed in the soils and in the trees that tend to provide constant data’s about the change in the ecosystem so that the fire can be easily identified once it starts over.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semi-implicit multivalue almost collocation methods

引用

AIP Conference Proceedings 2022年第1期2425卷

作者： Dajana Conte Raffaele D’Ambrosio Maria Pia D’Arienzo Beatrice Paternoster 1Department of Mathematics University of Salerno Via Giovanni Paolo II 132 Fisciano - 84084 ITALY 2Department of Engineering and Computer Science and Mathematics University of L’Aquila Via Vetoio Loc. Coppito L’Aquila - 67100 ITALY

We propose a family of multivalue collocation methods for the numerical solution of differential problems, potentially candidate to be stiff. For this reason, the suggested numerical schemes have strong stability properties, such as A-stability. Moreover, in order to obtain an efficient implementation, it is desirable to impose the conditions gaining a structured coefficient matrix of the nonlinear system for the computation of the internal stages. The construction of these methods has been presented and the properties of the resulting formulae have been verified experimentally.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep feature augmentation for occluded image classification

arXiv

引用

arXiv 2020年

作者： Cen, Feng Zhao, Xiaoyu Li, Wuzhuang Wang, Guanghui Department of Control Science & Engineering College of Electronics and Information Engineering Tongji University Shanghai201804 China Department of Computer Science Ryerson University TorontoONM5B 2K3 Canada

Due to the difficulty in acquiring massive task-specific occluded images, the classification of occluded images with deep convolutional neural networks (CNNs) remains highly challenging. To alleviate the dependency on large-scale occluded image datasets, we propose a novel approach to improve the classification accuracy of occluded images by fine-tuning the pre-trained models with a set of augmented deep feature vectors (DFVs). The set of augmented DFVs is composed of original DFVs and pseudo-DFVs. The pseudo-DFVs are generated by randomly adding difference vectors (DVs), extracted from a small set of clean and occluded image pairs, to the real DFVs. In the fine-tuning, the back-propagation is conducted on the DFV data flow to update the network parameters. The experiments on various datasets and network structures show that the deep feature augmentation significantly improves the classification accuracy of occluded images without a noticeable influence on the performance of clean images. Specifically, on the ILSVRC2012 dataset with synthetic occluded images, the proposed approach achieves 11.21% and 9.14% average increases in classification accuracy for the ResNet50 networks fine-tuned on the occlusion-exclusive and occlusion-inclusive training sets, respectively. Copyright © 2020, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Driving monitoring system for concentration using computer vision and machine learning methods on mobile phone

引用

AIP Conference Proceedings 2022年第1期2425卷

作者： Chia-Liang Lin Jwu-Jenq Chen Yung-Gi Wu 1Huzhou Univeristy Huzhou 313000 China 2Department of Interaction Design Chang Jung Christian University Tainan 71101 Taiwan 3Department of Computer Science and Information Engineering Chang Jung Christian University Tainan 71101 Taiwan

The car crash caused by unconcentrated driving always happens. Meanwhile, these car accidents not only crash cars, but also hurt innocent people. In order to avoid the accidents mentioned above, this study refers to a number of methods to detect driving concentration. Moreover, we find that detecting driving concentration for vehicle drivers is an important research gap. Therefore, we combined the computer vision method and proposed the driving monitoring system for concentration on mobile devices.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Observation of quantum strong Mpemba effect

arXiv

引用

arXiv 2024年

作者： Zhang, Jie Xia, Gang Wu, Chun-Wang Chen, Ting Zhang, Qian Xie, Yi Su, Wen-Bo Wu, Wei Qiu, Cheng-Wei Chen, Ping-Xing Li, Weibin Jing, Hui Zhou, Yan-Li Institute for Quantum Science and Technology College of Science National University of Defense Technology Changsha410073 China Hunan Key Laboratory of Mechanism and technology of Quantum Information Changsha410073 China Hefei National Laboratory Anhui Hefei230088 China Key Laboratory of Low-Dimensional Quantum Structures and Quantum Control of Ministry of Education Hunan Normal University Changsha410081 China Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore School of Physics and Astronomy University of Nottingham NottinghamNG7 2RD United Kingdom Centre for the Mathematics and Theoretical Physics of Quantum Non-equilibrium Systems University of Nottingham NottinghamNG7 2RD United Kingdom College of Science National University of Defense Technology Changsha410073 China

An ancient and counterintuitive phenomenon known as the Mpemba effect showcases the critical role of initial conditions in relaxation processes. How to realize and utilize this effect for speeding up relaxation is an important but challenging task in purely quantum system till now. Here, we experimentally study the strong Mpemba effect in a single trapped ion system in which an exponentially accelerated relaxation in time is observed by preparing an optimal quantum initial state with no excitation of the slowest decaying mode. Also, we demonstrate that the condition of realizing such effect coincides with the Liouvillian exceptional point, featuring the coalescence of both the eigenvalues and the eigenmodes of the systems. Our work provides an efficient strategy to engineer the dynamics of open quantum system, and suggests a link unexplored yet between the Mpemba effect and the non-Hermitian physics. Copyright © 2024, The Authors. All rights reserved.

关键词： Trapped ions

来源：评论

学校读者我要写书评

暂无评论

A study on thermal characterisation of effective pyrotechnic flash compositions

引用

AIP Conference Proceedings 2022年第1期2520卷

作者： V. Ajith V. Arumugaprabu R. Ramalakshmi N. Indumathi 1Department of Mechanical Engineering Kalasalingam Academy of Research and Education Krishnankoil Tamil Nadu 626 126 India. 2Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Krishnankoil Tamil Nadu 626 126 India. 3Department of Computer Applications Kalasalingam Academy of Research and Education Krishnankoil Tamil Nadu 626 126 India.

The pyrotechnic mixtures are highly explosive in nature. In this research a mixture of flash powder composition is used. The mixture is prepared by mixing aluminium, potassium nitrate and sulphur. In the manufacturing process of flash powder composition, the total weight consist of 23% of aluminium (grade 999), 57% of potassium nitrate and 20% of sulphur are added. Till date various accidents were reported during the manufacturing process of the flash composition. As an alternate for of this, five different mixture proportions were taken by varying components percentage level in the mixture. Subjected to various study those five different composition mixture are taken determine their effective function and also to understand their performance during processing and burning. Impact sensitivity experiment is performed for five different mixtures in order to determine the minimum energy which is required to initiate the firing and it has been analysed. Thermal Characteristics of five different composition were analysed using Differential Scanning Calorimeter (DSC) to determine the rate of heat flow with respect to time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic-trigonometric tension B-spline Galerkin approach for the solution of Fisher equation

引用

AIP Conference Proceedings 2021年第1期2334卷

作者： Idris Dag Ozlem Ersoy Hepson 1Department of Computer Engineering Eskişehir Osmangazi University Eskişehir Turkey 2Department of Mathematics and Computer Sicence Eskişehir Osmangazi University Eskişehir Turkey

A Galerkin finite element method is constructed for computing solution of the Fisher equation. Hyperbolic-trigonometric tension (HTT) B-splines are used as weight and shape functions in the Galerkin approach. Fully discretization of the Fisher equation is fulfilled via Crank-Nicolson method in time and Galerkin method in space. Travelling wave front solution is studied to show robustness of the presented scheme on Fisher equation. The numerical results obtained with the present method are satisfactory with regard to its accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

control and decision method for overtaking problem in autonomous vehicles 16

Control and decision method for overtaking problem in autono...

引用

16th Mini Conference on Vehicle System Dynamics, Identification and Anomalies, VSDIA 2018

作者： Hegedűs, Tamás Németh, Balázs Bede, Zsuzsanna Department of Control for Transportation and Vehicle Systems Faculty of Transportation Engineering and Vehicle Engineering Budapest University of Technology and Economics Stoczek utca. 2 BudapestH-1111 Hungary Systems and Control Laboratory Institute for Computer Science and Control Kende utca 13-17 BudapestH-1111 Hungary

In this paper we deal with an overtaking and lane change strategy for autonomous vehicles. The algorithm is divided into two main layers. The upper layer is responsible for the decision making (e.g lane changing). Before decision-making we predict the motion of other participants and divide the road into discrete sets in each interval, then we compute the probability of occupancy. Considering the state of the motion of ego vehicle we can compute the probability of collision. After assigning a graph points to discrete elements, the probability of collision is ordered to the graph edges, then we determine the route with the smallest cost. The decision-making algorithm is not able to control the vehicle, so it is necessary to design a traceable trajectory for the vehicle. Since we have a series of points to be reached for the future, this can be used as a reference vector for the trajectory design algorithm. One Model Predicitve controller (MPC) is responsible for the design of the trajectory so we can obtain limitations to several states to ensure comfort and security. Extending the algorithm, we can compute the longitudinal movement as well. In this paper the decision-making and the trajectory planning algorithm is presented, and the whole model validated in CarMaker. © 2019 Budapest University of Technology and Economics. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Early diagnosis and monitoring of sleep apnea using desaturation index and respiration percentage

引用

AIP Conference Proceedings 2022年第1期2405卷

作者： P. Sinthia M. Malathi B. Sathya Sri K. Sankar M. Nalini 1Department of Biomedical Engineering Saveetha Engineering College Chennai 602105 India 2Department of Biomedical Engineering Rajalakshmi Institute of Technology Chennai 600 124 India 3Department of Electronics and Communication Engineering Vel Tech Rangarajan DrSagunthala R&D Institute of Science and Technology Chennai 600 062 India 4Department of Computer Science Engineering Saveetha School of Engineering Chennai 602105 India

Obstructive sleep apnea (OSA) is one of the underdiagnosed sleep disorders in which the respiratory airpaths are disturbed and weakens the respiration process. Apnea refers to the termination of flow of air to the lungs which persists at least for 10 seconds. It is a serious factor for several conditions like hypoxia, hypertension, cardiovascular diseases including stroke. Presently, Polysomnography (PSG) taken over full night duration is implemented as standard method for OSA assessment. Over hundred million people around the world suffer from sleep apnea. This includes, 3- 7% men and 2-5% women. Yet there is a lack of patient friendly medical devices for long term monitoring of OSA. This is because the current systems are rather bulky, expensive, intrusive and unavailable in a comfortable environment for patients. The proposed system aims at developing a wearable, convenient, inexpensive and compact device for long term monitoring of OSA. Our approach is based on monitoring the patient using a double channel system of respiration rate and saturation pressure of oxygen. The data regarding the occurrence of events is collected and generated as an overnight report which can be sent to the patient/caregiver/doctor. In emergency cases an alarm will be triggered and the patient will be woken up from sleep.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Master equations and quantum trajectories for squeezed wave packets

引用

Physical Review A 2022年第2期105卷 023721-023721页

作者： Jonathan A. Gross Ben Q. Baragiola T. M. Stace Joshua Combes Institut Quantique Université de Sherbrooke Sherbrooke Quebec Canada J1K 2R1 Center for Quantum Information and Control University of New Mexico Albuquerque New Mexico 87131-0001 USA Yukawa Institute for Theoretical Physics Kyoto University Kitashirakawa Oiwakecho Sakyo-ku Kyoto 606-8502 Japan Centre for Quantum Computation and Communication Technology School of Science RMIT University Melbourne Victoria 3000 Australia ARC Centre for Engineered Quantum System Department of Physics University of Queensland Brisbane Queensland 4072 Australia Department of Electrical Computer and Energy Engineering University of Colorado Boulder Boulder Colorado 80309 USA

The interaction between matter and squeezed light has mostly been treated within the approximation that the field-correlation time is small. Methods for treating squeezed light with more general correlations currently involve explicitly modeling the systems producing the light. We develop a general purpose input-output theory for a particular form of narrowband squeezed light, a squeezed wave-packet mode, that only concerns the statistics of the squeezed field and the shape of the wave packet. This formalism allows us to derive the input-output relations and the master equation. We also consider detecting the scattered field using photon counting and homodyne measurements, which necessitates the derivation of the stochastic master equation. The non-Markovian nature of the field manifests itself in the master equation as a coupled hierarchy of equations. We illustrate these with consequences for the decay and resonance fluorescence of two-level atoms in the presence of such fields.

关键词： Open quantum systems Squeezing of quantum noise Stochastic processes

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：