检索结果-内蒙古大学图书馆

Real-Time Stress Detection via Photoplethysmogram Signals: implementation of a Combined Continuous Wavelet Transform and Convolutional Neural Network on Resource-Constrained microcontrollers 32

Real-Time Stress Detection via Photoplethysmogram Signals: I...

引用

32nd International Conference on Electrical Engineering (ICEE)

作者： Hasanpoor, Yasin Rostami, Amin Tarvirdizadeh, Bahram Alipour, Khalil Ghamari, Mohammad Univ Tehran Adv Serv Robots ASR Lab Fac New Sci & Technol Dept Mech Engn Tehran Iran Kettering Univ Dept Elect & Comp Engn Flint MI USA

ISBN: (纸本)9798350376357;9798350376340

This paper introduces a robust stress detection system utilizing a Convolutional Neural Network (CNN) designed for the analysis of Photoplethysmogram (PPG) signals. Employing the WESAD dataset, we applied Continuous Wavelet Transform (CWT) to extract informative features from wrist PPG signals, demonstrating enhanced stress detection and learning compared to conventional techniques. Notably, the CNN achieved an impressive accuracy of 93.7% after five epochs, post-implementation on a resource-constrained microcontroller. The optimization process, including pruning and Post-Train Quantization, was crucial to reduce the model size to 1.6 megabytes, overcoming the microcontroller's limited resources of 2 megabytes of Flash memory and 512 kilobytes of RAM. This optimized model not only addresses resource constraints but also outperforms traditional signal processing methods, positioning it as a promising solution for real-time stress monitoring on wearable devices.

关键词： Stress Detection Photoplethysmogram (PPG) microcontroller implementation Convolutional Neural Network (CNN) Continuous Wavelet Transform (CWT)

来源：评论

学校读者我要写书评

暂无评论

microcontroller-based simple maximum power point tracking controller for single-stage solar stand-alone water pumping system

引用

PROGRESS IN PHOTOVOLTAICS 2013年第4期21卷 462-471页

作者： Packiam, P. Jain, N. K. Singh, I. P. Indian Inst Technol Delhi Instrument Design Dev Ctr New Delhi 110016 India

A simple microcontroller-based maximum power point tracking controller is proposed for a single-stage solar stand-alone water pumping system for remote, isolated, and nonelectrified population, where less maintenance, low cost, and an efficient system is of prime interest. It consists of a photovoltaic (PV) module, a DCAC converter utilizing space-vector pulse-width modulation, an induction motor coupled with a water pump, a voltage sensor, and a current sensor. A space-vector pulse-width modulation-controlled DCAC converter aided by a fast-acting onoff supervisory controller with a modified perturb-and-observe algorithm performs both the functions of converting PV output voltage to a variable voltage, variable frequency output, as well as extracting the maximum power. A limited variable step size is preferred during transient state, and a steady frequency, which is calculated on the basis of steady-state oscillation, is set during steady state. A fast-acting onoff supervisory controller regulates DC link voltage during steady state and enables maximum power point tracking algorithm only during transient state to draw a new voltage reference. In the event of low voltage, the controller switches off the motor but continuously scans for an available PV voltage. The system is not protected against an overcurrent because the maximum current is equal to its short circuit current. The 16-bit microcontroller dsPIC6010A (Microchip Technology, Inc., Chandler, AZ, USA) is used to implement the control functions. The proposed controller is verified through simulation as well as tested in the laboratory prototype model. The simulation and experimental results show good correlation. Copyright (c) 2011 John Wiley & Sons, Ltd.

关键词： DCAC inverter induction motor microcontroller implementation MPPT controller PV water pumping system single stage steady and transient performance SVPWM

来源：评论

学校读者我要写书评

暂无评论

Shelf control in retail stores via ultra-low and low power microcontrollers

引用

JOURNAL OF REAL-TIME IMAGE PROCESSING 2022年第4期19卷 751-762页

作者： Yucel, M. Erkin Unsalan, Cem Migros AS Istanbul Turkey Marmara Univ Fac Engn Dept Elect & Elect Engn Istanbul Turkey

Smart retail stores started to take place in our lives. Several computer vision and sensor-based systems are working together to achieve such a complex and automated operation. Besides, the retail sector has several open and challenging problems which can be solved by embedded computer vision systems. One important problem to be tackled is shelf control or stock out detection. Here, shelves in a store should be controlled regularly such that no item is missing in the shelf. In this study, we propose an embedded computer vision system to solve this problem. To do so, we frame the shelf control operation as change detection. Due to the constraints posed by the retail sector, we formed the system by an ultra-low or low power microcontroller with an embedded camera attached to it. We provided all the implementation details of the system both from software and hardware perspectives. We also tested the proposed shelf control system from different perspectives. Hence, the reader can form such a system for retail sector or for a broad class of change detection problems in which stand-alone embedded system usage is mandatory.

关键词： Shelf control Retail sector Change detection microcontroller implementation

来源：评论

学校读者我要写书评

暂无评论

Jeffrey fluid saturating a heated porous layer: Dynamical and microcontroller execution probing

引用

PHYSICA SCRIPTA 2024年第7期99卷

作者： Muthukumar, Deiva Sundari Kibanya, Noel Nyang Metsebo, Jules Sekhar, D. Chandra Kuiate, Gaetan Fautso Chennai Inst Technol Ctr Nonlinear Syst Chennai 600069 Tamil Nadu India Univ Bamenda Fac Sci Dept Phys POB 39 Bamenda Cameroon Univ Maroua Natl Adv Sch Engn Dept Hydraul & Water Management POB 46 Maroua Cameroon Vemu Inst Technol Dept Elect & Elect Engn Chithoor India Univ Bamenda Higher Teacher Training Coll Dept Phys POB 39 Bamenda Cameroon Univ Bamenda Natl Higher Polytech Inst Dept Mech & Ind Engn POB 39 Bamenda Cameroon

In this paper, a dynamical investigation and microcontroller execution on a Jeffrey fluid saturating a porous layer with bottom heating and periodic modulation of gravity is carried out. The continuity equation, the energy conservation equation and the Boussinesq-Darcy approximation are used to describe the Jeffrey fluid saturating a porous layer with bottom heating and periodic gravity modulation. Thanks to the truncated Galerkin expansion method, the partial differential equations obtained from the modelling is reduced to four first order ordinary differential equations. This four-dimensional system without gravity modulation has three or one steady states depending on the scaled thermal Rayleigh number and the non-dimensional ratio of relaxation time to the retardation time of the fluid. From the stability analysis of the obtained equilibrium points in the four-dimensional system without gravity modulation, it is revealed that the steady states are stable or unstable depending on the non-dimensional ratio of relaxation time to retardation time of the fluid. Without gravity modulation, the four-dimensional system experiences Hopf bifurcation, steady convection, periodic convections, seven different shapes of chaotic convections, bistable period-1-convection, bistable period-3-convections and coexisting convections. With the sinusoidal periodic gravity modulation, the four-dimensional system displays Hopf bifurcation, steady convections, periodic convections, bursting convections, quasiperiodic convections and three different shapes of chaotic convections. A microcontroller execution of the four-dimensional system is used to establish the convection characteristics spotted in the four-dimensional system without and with sinusoidal periodic gravity modulation during the numerical simulations.

关键词： Jeffrey fluid saturating a porous medium truncated Galerkin expansion method Hopf bifurcation bistable and coexisting convections bursting and chaotic convections microcontroller implementation

来源：评论

学校读者我要写书评

暂无评论

Medical image cryptosystem using a new 3-D map implemented in a microcontroller

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第31期83卷 75955-75994页

作者： Ayemtsa Kuete, Gideon Pagnol Heucheun Yepdia, Lee Mariel Tiedeu, Alain Mboupda Pone, Justin Roger Univ Yaounde I Natl Adv Sch Engn Yaounde Instrumentat Signal & Image Lab POB 8390 Yaounde Cameroon Univ Dschang Elect Engn Dept IUT FV Bandjoun Res Unit Automat & Appl Comp RU AIA POB 134 Bandjoun Cameroon Univ Yaounde I Natl Adv Sch Engn Ingenierie Math & Syst Informat POB 8390 Yaounde Cameroon

Medical images make up for more than 25% of global attacks on privacy. Securing them is therefore of utmost importance. Chaos based image encryption is one of the most method suggested in the literature for image security due to their intrinsic characteristic, including ergodicity, aperiodicity, high sensitivity to initials conditions and system parameters. Dynamic systems such as bridge circuit, jerk circuit, Van der Pol circuit, Colpitts oscillator and many other pseudo-random numbers generators have been used in the process of encrypting images. Among them, are the jerk oscillators that have been used with different nonlinearities. In this paper, a new, simple, off-shell component of jerk oscillator (jerk quintic) with an interesting nonlinear function is proposed. Its dynamical behaviors are investigated using classical tools like bifurcation diagrams, Maximum Lyapunov exponent plot, basin of attraction, phase portraits. We showed that the nonlinear function is responsible of complex nonlinear behaviors displayed by the novel circuit, including symmetric/asymmetric bifurcation and coexisting bubbles, multistability just to name a few. The real implementation of the interesting circuit is embedded in a microcontroller verifies these dynamics. As an application of this contribution in multimedia, an encryption algorithm built on a new confusion-diffusion architecture using pseudo random number generated in high chaoticity regime of the new circuit is proposed. The cryptosystem underwent thorough security tests and proved to be fast thanks to the 3D map used, given its complex dynamical behaviors and large chaotic area. This approach yields a robust cipher that underwent thorough security tests better than the one in the literature like average NPCR=99.61, UACI=33.48, key space-sensitivity, entropy=7.9994, average correlation=0.0040. Furthermore, it proved to be robust in terms of noise and data loss in the transmission channel, offering a large key space of 10180

关键词： Novel quintic jerk circuit Coexisting bubbles Bifurcation Multistability Chaos microcontroller implementation Image encryption Key space Cryptanalysis test Differential attacks

来源：评论

学校读者我要写书评

暂无评论

A neural network implemented microcontroller system for quantitative classification of hazardous organic gases in the ambient air

引用

INTERNATIONAL JOURNAL OF ENVIRONMENT AND POLLUTION 2009年第1-3期36卷 151-165页

作者： Gulbag, Ali Temurtas, Feyzullah Tasaltin, Cihat Ozturk, Zafer Ziya Sakarya Univ Dept Comp Engn TR-54187 Adapazari Turkey TUBITAK Marmara Res Ctr TR-41470 Gebze Turkey Gebze Inst Technol Dept Phys TR-41400 Gebze Turkey

In this study, a microcontroller-based gas mixture classification system is proposed to use real-time analyses of the trichloroethylene and acetone binary mixture. A Feed Forward Neural Network (FFNN) structure is performed for quantitative identification of individual gas concentrations (trichloroethylene and acetone) in their gas mixtures. The phthalocyanine-coated Quartz Crystal Microbalance (QCM) type sensors were used as gas sensors. A calibrated Mass Flow Controller (MFC) was used to control the flow rates of carrier gas and trichloroethylene and acetone gas mixtures streams. The components in the binary mixture were quantified by applying the sensor responses from the QCMs sensor array as inputs to the FFNN. The microcontroller-based gas mixture classification system performs Neural Network (NN)-based estimation, the data acquisition and user interface tasks. This system can estimate the gas concentrations of trichloroethylene and acetone with the average errors of 0.08% and 0.97%, respectively.

关键词： NN neural network microcontroller implementation quantitative gas classification binary mixture QCM quartz crystal microbalance sensors FFNNs feed forward neural networks

来源：评论

学校读者我要写书评

暂无评论

Nonlinear dynamics of a Josephson junction coupled to a diode and a negative conductance

引用

JOURNAL OF COMPUTATIONAL ELECTRONICS 2024年第5期23卷 1000-1013页

作者： Kakpo, M. A. Miwadinou, C. H. Univ Natl Sci Ecole Doctorale Sci Technol Ingenierie & Math ED S Abomey Benin Inst Math & Sci Phys Lab Mecan Fluides Dynam Nonlineaire & Modelisat Sy Porto Novo Benin UNSTIM Dept Phys ENS Natitingou Abomey Benin

We studied the nonlinear dynamics of a shunted inductive Josephson junction coupled to a diode and a negative conductance. Taking into account the non-harmonicity of the junction, based on Kirchhoff's laws, we have developed the mathematical model which governs the dynamics of the circuit. The fixed points of the system are determined, and their stabilities are analyzed using the Routh-Hurwitz criterion. The bifurcation and transition to chaos of the model are studied using the the fourth-order Runge-Kutta method;the system displays a rich dynamics. The range of values of each parameter leading to periodic and chaotic electrical oscillations is obtained through the analysis of the effect of these parameters on each type of dynamics. Finally, the implementation by microcontroller is carried out in order to experimentally verify the different dynamics obtained numerically.

关键词： Josephson junction Negative conductance Bifurcation Chaos microcontroller implementation

来源：评论

学校读者我要写书评

暂无评论

Fractional-order-induced symmetric multi-scroll chaotic attractors and double bubble bifurcations in a memristive coupled Hopfield neural networks

引用

CHAOS SOLITONS & FRACTALS 2024年 178卷

作者： Biamou, Arsene Loic Mbanda Tamba, Victor Kamdoum Tagne, Francois Kapche Takougang, Armand Cyrille Nzeukou Univ Dschang Dept Telecommun & Network Engn IUT Fotso Victor Bandjoun POB 134 Bandjoun Cameroon Univ Dschang Dept Elect Engn Res Unit Automat & Appl Comp IUT FV Bandjoun POB 134 Bandjoun Cameroon Univ Dschang Fac Sci Dept Phys Res Unit Condensed Matter POB 67 Dschang Cameroon

The multi-state memristor is a type of memristor capable of memorizing multiple conductance states. This special feature is successfully used to mimic the behavior of neural synapses and simulate the influences of electro-magnetic induction and radiation in artificial neural networks such as Hopfield neural networks. This paper introduces and examines a novel fractional-order Hopfield neural network model consisting of two non-identical sub-Hopfield neural networks coupled by a multi-stable flux controlled memristor (MCFHNN). The pinched hysteresis loops of the multi-stable flux controlled memristor are analyzed via numerical simulations. The equilibrium points of MCFHNN model and their stability are investigated. The introduced MCFHNN model is solved by using Adomian Decomposition Method (ADM). By using some examination methods such as spectral entropy complexity, bifurcation diagrams, phase portraits, maximum Lyapunov exponent and basins of attrac-tion, we analyze the dynamic behaviors of MCFHNN model associated with coupling strength, fractional-order and initial states. Numerical results demonstrate that the proposed MCFHNN model is capable to develop abundant and complicated dynamics including, chaos, multiple transient transition behaviors, double bubble bifurcations, initial-boosted behavior and symmetric multi-scroll chaotic attractors. It is found that the complexity results are in agreement with those obtained from the bifurcation diagrams. This proves that the complexity can well reflect the dynamic behaviors of MCFHNN model. In order to support theoretical and nu-merical results, the designed MCFHNN model is implemented with the help of an Arduino-Due microcontroller board based on the Atmel SAM3X8E ARM Cortex-M3 processor. The results are in very good agreement with those obtained from computational simulations.

关键词： MCFHNN model Initial-boosted behavior Multiple transient transition behaviors Symmetric double-scroll chaotic attractors Double bubble bifurcations microcontroller implementation

来源：评论

学校读者我要写书评

暂无评论

A review on development of photovoltaic water pumping system

引用

RENEWABLE & SUSTAINABLE ENERGY REVIEWS 2015年 43卷 918-925页

作者： Periasamy, Packiam Jain, N. K. Singh, I. P. Indian Inst Technol Instrument Design Dev Ctr New Delhi 110016 India

Photovoltaic (PV) water pumping system has been becoming increasingly important in remote, isolated, and non-electrified population, where either accessibility to the grid is difficult to establish or implementation cost is indeed very high. In such location, PV water pumping application is significant area of interest for sustainable development. In this article, DC and induction motor as part of multi and single stage water pumping system has been reviewed. The maximum power point (MPP) at which PV system is to be operated is tracked by peak power tracker to utilize solar power. Therefore, the peak power tracking algorithms with voltage, current, duty cycle, and frequency as perturbation parameters under uniform and non-uniform insolation are also presented. Review reports on PV emulators used for evaluation of new MPPT control techniques, and microcontroller based implementations of MPPT controller are also presented. Thus, this article becomes reference document for developing DC/AC PV water pumping system. (C) 2014 Elsevier Ltd. All rights reserved.

关键词： DC motor Induction motor microcontroller implementation MPPT Partial shaded insolation Single stage photovoltaic Water pum

来源：评论

学校读者我要写书评

暂无评论

Dynamic compensation of Nonlinear sensors by a learning-from-examples approach

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2008年第8期57卷 1689-1694页

作者： Marconato, Anna Hu, Mingqing Boni, Andrea Petri, Dario Univ Trent Dept Informat & Commun Technol I-38100 Trento Italy Chinese Acad Sci Inst Comp Technol Beijing 100080 Peoples R China

In this paper, we address the problem of nonlinear sensor dynamic compensation that will be performed on board wireless sensor network nodes. To this aim, we design suitable reduced-complexity learning-from-example algorithms and implement them on resource-constrained devices, namely, 8-bit microcontrollers. The proposed approach is validated with simulations on different examples of nonlinear sensor models.

关键词： dynamic compensation low power microcontroller implementation reduced-set methods support vector machines for regression (SVRs) wireless sensor networks (WSNs)

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：