检索结果-内蒙古大学图书馆

Analyzing the Impact of Scene Transitions on Indoor Camera Localization through Scene Change Detection in Real-Time

Intelligent Automation & Soft Computing 2024年第3期39卷 417-436页

作者： Muhammad S.Alam Farhan B.Mohamed Ali Selamat Faruk Ahmed AKM B.Hossain Department of Emergent Computing School of ComputingUniversiti Teknologi MalaysiaJohor Bahru81310Malaysia Malaysia-Japan International Institute of Technology(MJIIT) Universiti Teknologi MalaysiaKuala Lumpur54100Malaysia Media and Game Innovation Centre of Excellence(MaGICX) Universiti Teknologi MalaysiaJohor Bahru81310Malaysia Department of Engineering Technology University of MemphisMemphisTN38152USA Department of Computer Science and Artificial Intelligence College of Computing and Information TechnologyUniversity of BishaBisha61922Saudi Arabia School of Computing Faculty of EngineeringUniversiti Teknologi MalaysiaJohor Bahru81310Malaysia Department of Information System and Cyber Security College of Computing and Information TechnologyUniversity of BishaBisha61922Saudi Arabia

Real-time indoor camera localization is a significant problem in indoor robot navigation and surveillance *** scene can change during the image sequence and plays a vital role in the localization performance of robotic applications in terms of accuracy and *** research proposed a real-time indoor camera localization system based on a recurrent neural network that detects scene change during the image *** annotated image dataset trains the proposed system and predicts the camera pose in *** system mainly improved the localization performance of indoor cameras by more accurately predicting the camera *** also recognizes the scene changes during the sequence and evaluates the effects of these *** system achieved high accuracy and real-time *** scene change detection process was performed using visual rhythm and the proposed recurrent deep architecture,which performed camera pose prediction and scene change impact ***,this study proposed a novel real-time localization system for indoor cameras that detects scene changes and shows how they affect localization performance.

关键词： Camera pose estimation indoor camera localization real-time localization scene change detection simultaneous localization and mapping(SLAM)

来源：评论

学校读者我要写书评

暂无评论

Two-Layer SVM, Towards Deep Statistical Learning

Two-Layer SVM, Towards Deep Statistical Learning

引用

Electrical, Energy, and Artificial Intelligence (EICEEAI), International engineering Conference on

作者： Alireza Kazemi Reza Boostani Mahmoud Odeh Mohammad Rasmi AL-Mousa Mathematics Department Faculty of Science Shiraz University Shiraz Fars Iran CSE&IT Dept. Electrical and Computer Engineering School Shiraz University Shiraz Fars Iran Department of Management Information System Zarqa University Jordan Department of Cyber Security Faculty of Information Technology Zarqa University Zarqa Jordan

Support Vector Machine (SVM) is originally a binary large-margin classifier emerged from the concept of structural risk minimization. Multiple solutions such as one-versus-one and one-versus-all have been proposed for creating multi-class SVM using elementary binary SVMs. Also multiple solutions have been proposed for SVM model selection, adjusting margin-parameter C and the Gaussian kernel variance. Here, an improved classifier named SVM-SVM is proposed for multi-class problems which increases accuracy and decreases dependency to margin-parameter selection. SVM-SVM adopts two K-class one-vs-one SVMs in a cascaded two-layer structure. In the first layer, input features are fed to one-vs-one SVM with non-linear kernels. We introduce this layer as a large-margin non-linear feature transform that maps input feature space to a discriminative K*(K-1)/2 dimensional space. To assess our hierarchical classifier, some datasets from the UCI repository are evaluated. Standard one-vs-one SVM and one-vs-one fuzzy SVM are used as reference classifiers in experiments. Results show significant improvements of our proposed method in terms of test accuracy and robustness to the model (margin and kernel) parameters in comparison with the reference classifiers. Our observations suggest that a multi-layer (deep) SVM structures can gain the same benefits as is seen in the deep neural nets (DNNs).

关键词： Support vector machines Electric potential Statistical learning Neural networks Transforms Nonhomogeneous media Robustness

来源：评论

学校读者我要写书评

暂无评论

Optical Wireless Network Architecture

Optical Wireless Network Architecture

引用

2022 27th OptoElectronics and Communications Conference (OECC) and 2022 International Conference on Photonics in Switching and Computing (PSC)

作者： Vincent W.S. Chan Joan and Irwin Jacobs Chair Professor Department of Electrical Engineering and Computer Science Claude E. Shannon Communication and Network Group Research Laboratory of Electronics Steve Schwarzman College of Computing AI and Decision System Sector Massachusetts Institute of Technology. President IEEE Communications Society 2020&#x2013 2021.

ISBN: (数字)9784885523366

ISBN: (纸本)9781665486064

Optical wireless network has the potential to serve space-space, space-terrestrial/aircraft, aircraft-aircraft, data centers and metropolitan area networks. This paper addresses architecture features necessary for these networks. Free space optical (FSO) networks have two dimensions that are not encountered in fiber networks and that is: (1) its ability to connect without pre-deployment of infrastructures and (2) the ability to reconfigure its connection topology by beam steering in time scales of mS-S to adapt to traffic loads, switching node states and atmospheric conditions. This paper presents a multi-layer approach to optical wireless networks and how the architecture can be tuned to applications.

关键词： Optical fibers Network topology Metropolitan area networks Wireless networks Optical switches computer architecture Telecommunication traffic

来源：评论

学校读者我要写书评

暂无评论

Smart Lighting system for Children's Therapy to Prevent Nyctophobia Syndrome at Bedtime

Smart Lighting System for Children's Therapy to Prevent Nyct...

引用

International Conference on Cybernetics and Intelligent system (ICORIS)

作者： Andi Pramono Badrul Munir Muchammad Farchan Satrio Arif Budiman Baskoro Azis Wahyu Waskito Putra Interior Design Department School of Design Bina Nusantara University Jakarta Indonesia Departemen of Neurology Brawijaya University Malang Indonesia Department of Electrical Engineering Faculty of Intelligent Electrical and Informatics Technology Institut Teknologi Sepuluh Nopember Surabaya Indonesia Information System Computer Science faculty Brawijaya University Malang Indonesia

ISBN: (纸本)9781665453967

Everyone has a fundamental desire for sleep. By sleeping, humans can conserve energy and replenish their stamina to optimal levels. Lighting is one component that influences the quality of a person's sleep. One of them is a person who sleeps with the lights on, suffers from nyctophobia, has poor sleep quality, and may be responsible for several illnesses. This study aims to develop a smart lighting device that will aid in treating youngsters with nyctophobia to get used to sleeping with the lights off to improve their sleep quality. The case study methodology used in this study entails the development of a prototype. This method employs an oximeter as a heart rate detector and a sensor comparison as the measurement device. Arduino Uno circuit and heart rate sensor are the main devices in this research. At the same time, the NRF 24L01 is a communication medium between the two Arduino Uno boards. The experimental measurements in normal conditions indicate that the heart rate sensor was nearly the same as the value displayed by the oximeter. Similarly, after running for 1 minute, both devices produced almost identical results, with an average difference of 1 Beats Per Minute (BPM). According to experiments with a heart rate sensor, the switch-off condition can be activated if the heart rate hits 90 BPM. In this case, the light will switch off once the heart rate hits 70 BPM, which might be used for sleeping individuals.

关键词： Heart rate Phase measurement Prototypes Medical treatment Switches Turning Nanoscale devices

来源：评论

学校读者我要写书评

暂无评论

Improving the Ramp Rate of Thermal Power Units Based on Deep Utilization of Coal Powder in Milling systems 32

Improving the Ramp Rate of Thermal Power Units Based on Deep...

引用

第32届中国控制与决策会议

作者： GAO Yao-kui ZHANG Li-xia SHI Yu-wei HU Yong ZENG De-liang LI Geng-da LIU Miao State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power University School of Control and Computer Engineering North China Electric Power University Guodian New Energy Technology Research Institute Co. Ltd

ISBN: (数字)9781728158556

ISBN: (纸本)9781728158563

Improving the ramp rate of thermal power units is an important way to solve the problem of large-scale consumption of new energy in *** deep utilization of the coal powder in the milling system is one of the methods to accelerate the response rate of the boiler,thereby improving the ramp rate of thermal power *** on the analysis of the working principle and characteristics of a milling system,this paper considers the effect of primary air flow on the dynamics of the milling system,improves the simplest model of the milling system,and introduces the improved model into a drum boiler unit *** on the model,a new control strategy is designed based on the deep utilization of the coal powder in the milling *** strategy is based on the predictive control algorithm and combines the traditional feedforward and decoupling control *** importantly,the dynamic compensation of the primary air flow is used to achieve the deep utilization of the coal powder in the milling system,thus rapidly changing the amount of coal powder entering the *** results show that the strategy can better ensure the rapidity and stability of the thermal power unit when the load is changed.

关键词： Thermal Power Unit Milling system Ramp Rate Predictive Control

来源：评论

学校读者我要写书评

暂无评论

A smart torque control for a high efficiency 4WD electric vehicle

A smart torque control for a high efficiency 4WD electric ve...

引用

International Conference on Applications in Electronics Pervading Industry, Environment and Society, APPLEPIES 2018

作者： Cordopatri, Antonio Cocorullo, Giuseppe Department of Computer Science Modelling Electronic and System Engineering University of Calabria Arcavacata di Rende Italy

ISBN: (纸本)9783030119720

At the state-of-the-art, electric propulsion systems based on hub-motors allow mechanical components to be removed, increasing also the vehicle stability. However, since motors and wheels are directly coupled, when a high propulsion torque is delivered, in such a configuration the motors could work in low efficiency operative points, negatively affecting the vehicle consumptions. In this paper, a torque distribution strategy is defined to minimize these consumptions. The propulsion configuration under investigation is a four-wheel drive that adopts two different couples of Brushless DC (BLDC) hub motors. The proposed research highlights how the electric efficiency is improved when the propulsion torque required by the vehicle is delivered by the BLDCs in an asymmetric way, according to the motors operative conditions. Since this torque repartition dynamically changes while the vehicle is running, the effects on the vehicle stability are also evaluated. Such an analysis is performed considering, as reference, a Class A vehicle, principally designed for the urban mobility. © 2019, Springer Nature Switzerland AG.

关键词： Torque

来源：评论

学校读者我要写书评

暂无评论

Black soldier fly (BSF) farming in egg cycle based on IoT technology

引用

AIP Conference Proceedings 2024年第1期2867卷

作者： Abba Suganda Girsang Emil Robert Kaburuan Ezra Peranginangin Kevin Kristianto Ronaldo Vieri Lambert Rezky Yunanda Computer Science Department Bina Nusantara University Jakarta Indonesia Information System Management Department Bina Nusantara University Jakarta Indonesia Industrial Engineering Department Bina Nusantara University Jakarta Indonesia

Black Soldier Fly (BSF) or maggot (Indonesia language) has some cycles in its life. One of important phase is egg period. In this phase, the mature fly will produce egg. The success of this maggot livestock starts from the number of eggs produced. The egg produced is depend on the environment of the cage likes temperature, humidity and light. This study implements internet of things (IoT) to control the environment of the cage to get the ideal condition. This research aims to increase the number of egg produced by using IoT. Some sensors temperature, humidity and light are used to get the condition. The equipment, fan, lamp and misty water are used to control the environment cage. The system detects every ten minutes to decide whether equipment is turned on or not. This research uses two cages, type A using IoT, and type B natural (not using IOT). The result shows that cage type A produced egg more than type B.

关键词：

来源：评论

学校读者我要写书评

暂无评论

METER-ML: A Multi-Sensor Earth Observation Benchmark for Automated Methane Source Mapping

arXiv

引用

arXiv 2022年

作者： Zhu, Bryan Lui, Nicholas Irvin, Jeremy Le, Jimmy Tadwalkar, Sahil Wang, Chenghao Ouyang, Zutao Liu, Frankie Y. Ng, Andrew Y. Jackson, Robert B. Department of Computer Science Stanford University United States Department of Statistics Stanford University United States Department of Civil and Environmental Engineering Stanford University United States Department of Earth System Science Stanford University United States Woods Institute for the Environment and Precourt Institute for Energy Stanford University United States

Reducing methane emissions is essential for mitigating global warming. To attribute methane emissions to their sources, a comprehensive dataset of methane source infrastructure is necessary. Recent advancements with deep learning on remotely sensed imagery have the potential to identify the locations and characteristics of methane sources, but there is a substantial lack of publicly available data to enable machine learning researchers and practitioners to build automated mapping approaches. To help fill this gap, we construct a multi-sensor dataset called METER-ML containing 86,599 georeferenced NAIP, Sentinel-1, and Sentinel-2 images in the U.S. labeled for the presence or absence of methane source facilities including concentrated animal feeding operations, coal mines, landfills, natural gas processing plants, oil refineries and petroleum terminals, and wastewater treatment plants. We experiment with a variety of models that leverage different spatial resolutions, spatial footprints, image products, and spectral bands. We find that our best model achieves an area under the precision recall curve of 0.915 for identifying concentrated animal feeding operations and 0.821 for oil refineries and petroleum terminals on an expert-labeled test set, suggesting the potential for large-scale mapping. We make METER-ML freely available at this link to support future work on automated methane source mapping. © 2022, CC BY-SA.

关键词： Methane

来源：评论

学校读者我要写书评

暂无评论

Dynamic modeling of "kOSOVO A" power station synchronous generator 21

Dynamic modeling of "kOSOVO A" power station synchronous gen...

引用

21st International Symposium on Electrical Apparatus and Technologies, SIELA 2020

作者： Berisha, Nuri Avdiu, Nysret Stanev, Rad Stoilov, Dimo Morina, Shyqeri University of Prishtina Faculty of Electrical and Computer Engineering Prishtina Kosovo Serbia Techinical University of Sofia Sofia Bulgaria BAS Sofia Bulgaria KOSTT- Transimssion System and Market Operation J.S.C Prishtina Kosovo Serbia

ISBN: (纸本)9781728143460

This paper presents dynamic three-phase d-q axis modeling and simulation of "KOSOVO A"power station synchronous generator intended for transient analysis and relay protections parameters determination, taking into account the static and dynamic interactions between stator and rotor. A simplified and computationally efficient five order mathematical model is developed under the assumption that the Kirchhoff laws and the network equations are written as for stationary state. The generator is analyzed in "abc"coordinates to describe the physical inherent of three-phase short circuit. A system of differential equations representing the dynamic behavior of the machine is developed and implemented in Matlab/Simulink. The proposed model and case study provide important and valuable results for the generator relay protection settings, allowing an easy setup of the relay protections parameters by referring the results obtained in this work. © 2020 IEEE.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

A Novel and Highly Stable 840 MHz Repetition Rate Femtosecond Fiber Laser

A Novel and Highly Stable 840 MHz Repetition Rate Femtosecon...

引用

Pacific Rim Conference on Lasers and Electro-Optics (CLEO/Pacific Rim)

作者： Ruoao Yang Minghe Zhao Xingang Jin Qian Li Zhangyuan Chen Aimin Wang Zhigang Zhang State Key Laboratory of Advanced Optical Communication System and Networks School of Electronics Peking University Beijing P.R. China School of Electronic and Computer Engineering Peking University Shenzhen P.R.China Jiaxing Xurui Electronics Tech Co Ltd Jiaxing P.R.China

We demonstrate a novel and highly stable femtosecond fiber laser at a repetition rate of 840 MHz. Because the laser components are bonded on a silica glass, the repetition rate of the free running laser drifts within 1 kHz over 12 hrs. The timing jitter of the pulses measured by the balanced optical cross-correlation is 130 as for the integration range of 10 kHz to 1 MHz.

关键词：

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：