The data-driven autonomous feedforward (FF) control design technique known as frequency-domain modelling-free iterative learning control (MFILC) has gained attention for its ability to achieve fine motion control perf...
详细信息
Background:Machine learning has enabled the automatic detection of facial expressions,which is particularly beneficial in smart monitoring and understanding the mental state of medical and psychological *** algorithms...
详细信息
Background:Machine learning has enabled the automatic detection of facial expressions,which is particularly beneficial in smart monitoring and understanding the mental state of medical and psychological *** algorithms that attain high emotion classification accuracy require extensive computational resources,which either require bulky and inefficient devices or require the sensor data to be processed on cloud ***,there is always the risk of privacy invasion,data misuse,and data manipulation when the raw images are transferred to cloud servers for processing facical emotion recognition(FER)*** possible solution to this problem is to minimize the movement of such ***:In this research,we propose an efficient implementation of a convolutional neural network(CNN)based algorithm for on-device FER on a low-power field programmable gate array(FPGA)*** is done by encoding the CNN weights to approximated signed digits,which reduces the number of partial sums to be computed for multiply-accumulate(MAC)*** is advantageous for portable devices that lack full-fledged ***:We applied our approximation method on MobileNet-v2 and ResNet18 models,which were pretrained with the FER2013 *** implementations and simulations reduce the FPGA resource requirement by at least 22%compared to models with integer weight,with negligible loss in classification ***:The outcome of this research will help in the development of secure and low-power systems for FER and other biomedical *** approximation methods used in this research can also be extended to other imagebasedbiomedicalresearchfields.
This paper analyses,simulates and verifies an experimental prototype of a four-phase interleaved DC-DC *** is based on a SEPIC-Cuk *** developed prototype has been used in single-input multiple-output(SIMO)*** combine...
详细信息
This paper analyses,simulates and verifies an experimental prototype of a four-phase interleaved DC-DC *** is based on a SEPIC-Cuk *** developed prototype has been used in single-input multiple-output(SIMO)*** combined converter allows obtaining dual output voltages of the same value,from a single input DC voltage and with only a power *** interleaved DC-DC converters achieve a better dynamic response and low ripple,maintaining their *** converter is connected in parallel,thereby managing their losses by distributing them between more components,which facilitates the thermal management of the multiphase converter and allows handling high power values in small sizes with respect to solutions for a single *** control strategies were applied:synchronous operation mode(SOM)and interleaved operation mode(IOM).The simulation results allow the comparison of both operational modes,verifying that the IOM presents advantages with respect to the ripple at the input and output *** experimental prototype was designed for a distributed power architecture and bipolar DC microgrid(MG).
This research study presents a practical and efficient solution for forest fire detection. The system proposed in this study utilizes a GSM network to transmit signals to remote locations where the user is located. Th...
详细信息
作者：
Balbino, L.S.Dantas, K.M.Neves, W.L.A.
Electrical Engineering Graduate Program Campina Grande Brazil
Department of Electrical Engineering PB Campina Grande Brazil
This paper presents an approach for choosing neutral reactors in transmission lines (TL) with shunt compensation. Data from the Brazilian Power Grid were used for digital simulations with ATPDraw, and a sensitivity an...
详细信息
High voltage direct current (HVDC) technology remains one of the key and preferred option when transmitting power, particularly over long distances when compared with high voltage alternating current (HVAC). It's ...
详细信息
作者：
Fizza, GhulamKadir, KushsairyNasir, HaidawatiShah, Asadullah
Department of Electrical and Electronic Engineering Selangort Malaysia
Department of Computer Engineering Kuala Lumpur Malaysia
Department of Information Systems Kuala Lumpur Malaysia
The increasing global energy demands highlight the need for improved energy management systems in smart buildings. Traditional systems are inadequate in resolving the dynamic interplay between energy consumption and o...
详细信息
This paper focuses on optimal voltage regulator(VR)planning to maximize the photovoltaic(PV)energy integration in distribution *** describe the amount of dynamic PV energy that can be integrated into the power system,...
详细信息
This paper focuses on optimal voltage regulator(VR)planning to maximize the photovoltaic(PV)energy integration in distribution *** describe the amount of dynamic PV energy that can be integrated into the power system,the concept of PV accommodation capability(PVAC)is introduced and modeled with *** proposed planning model is formulated as a Benders decomposition based bi-level stochastic optimization *** the upper-level problem,VR planning decisions and PVAC are determined via mixed integer linear programming(MILP)before considering *** in the lower-level problem,the feasibility of first-level results is checked by critical network constraints(*** magnitude constraints and line capacity constraints)under uncertainties considered by time-varying loads and PV *** this paper,these uncertainties are represented in the form of operational scenarios,which are generated by the Gaussian copula theory and reduced by a well-studied backward-reduction *** modified IEEE 33-node distribution grid is utilized to verify the effectiveness of the proposed *** results demonstrate that a PV energy integration can be significantly enhanced after optimal voltage regulator planning.
Due to the increasing implementation of high voltage direct current(HVDC)and the integration of renewable resources,frequency stability problems in power systems are drawing greater attention in recent *** has become ...
详细信息
Due to the increasing implementation of high voltage direct current(HVDC)and the integration of renewable resources,frequency stability problems in power systems are drawing greater attention in recent *** has become necessary to carry out online frequency security assessments to ensure the safe operation of power *** the low time-efficiency of simulation-based methods,analytical models,such as the frequency nadir prediction(FNP)model,are more suitable for online assessment,which requires calculating the worst frequency deviation under various *** on the FNP model,the FNP-L model for online frequency security assessment is proposed in this *** proposed model implements security assessment by calculating and checking the frequency features,including the nadir time and frequency,followed by *** effect of the governor,including nonlinear constraints,is approximated into polynomial functions so that the results are obtained by solving multiple polynomial *** studies are carried out using the New-England 39-bus system and a regional power grid,which shows that the proposed model could achieve both high speed and high accuracy,and can therefore be applied in online security assessment.
State estimation(SE)is essential for combined heat and electric networks(CHENs)to provide a global and selfconsistent solution for multi-energy flow *** paper proposes an SE approach for CHEN based on steady models of...
详细信息
State estimation(SE)is essential for combined heat and electric networks(CHENs)to provide a global and selfconsistent solution for multi-energy flow *** paper proposes an SE approach for CHEN based on steady models of electric networks(ENs)and district heating networks(DHNs).A range of coupling components are *** performance of the proposed estimator is evaluated using Monte Carlo simulations and case *** show that a relationship between the measurements from ENs and DHNs can improve the estimation accuracy for the entire network by using the combined SE model,especially when ENs and DHNs are strongly *** coupling constraints could also provide extra redundancy to detect bad data in the boundary injection measurements of both *** analysis of computation time shows that the proposed method is suitable for online applications.
暂无评论