The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper focuses on identification of vulnerable lines and nodes of the power grid (PG) network whose removal disrupt on its operational capability. Here the topological parameters are derived from CN theory, and these are used to identify the most important elements i.e., lines and nodes of the PGs. Based on this concept, the number of attack strategies are illustrated and also applied to different...
In this paper, an impedance control strategy is proposed for a rigid robot collaborating with human by considering impedance learning and human motion intention estimation. The least square method is used in human impedance identification, and the robot can adjust its impedance parameters according to human impedance model for guaranteeing compliant collaboration. Neural networks (NNs) are employed...
Process operating performance assessment judges the optimal degree of the production online. The assessment result guides the production to achieve the maximal benefit. Hence, the study on operating performance assessment is of great significance. To extract the most correlations between the process variables and the assessment indices, an operating performance assessment method based on canonical...
UF-EMG test, in which non-invasive uroflowmetry (UF) and electromyography (EMG) signals are simultaneously recorded, is frequently used in children diagnosed with lower urinary tract dysfunction disease (AUSD) and its treatment. In the literature, independent (single) UF signals and integrated (dual) UF-EMG signals are graded many times but there is no classification study of UF-EMG integrated signals...
In this paper, we describe a capacitance-based strain field sensor. The device is interrogated at a single location, and uses multiple excitation frequencies to resolve the spatial distribution of strain. The system we model is representative of a capacitor composed of a graphite-based conductive elastomer composite in a silicone binder with a silicone dielectric layer. We utilize an artificial neural...
An image-reconstruction approach for optical tomography is presented, in which a layered back-propagation neural network is used to reconstructs two-dimensional images of two-phase gas-liquid flow using wire-mesh sensor data as target by means of Levenberg-Marquardt algorithm. The network learns the relationship between the reference sensor measurements and optical tomography projections. Results...
In order to detect the pedestrian by using a low resolution LiDAR with a low-end processor, we proposed a method to calculate independent results for each scan line before integrating them. For verifying the effectiveness of the proposed method, we tried to classify point cloud data taken at a 3 m, 4 m, 5 m, 6 m and 7 m position apart from pedestrians, bicycles, motorbikes and vehicle. We confirmed...
Electrocardiogram (ECG) diagnosis is a widely-used clinical approach because it has been proven as an efficient way to diagnose cardiac disease. However, to get an accurate ECG diagnosis is a challenging task because it is a nonlinear problem. Therefore, many Neural Network (NN)-based ECG analysis approaches were proposed to analyzes ECG signal in time domain in recent years which can improve the...
In the case of the presence of ferroresonance in distribution transformer due to a faulty switching operation, ferroresonance signals should be discriminated among its initiations due to opened single-phase, opened two-phases, and opened three-phases, so that ferroresonance mitigation can be conducted appropriately. However, the performance of mitigation system itself is highly determined by its accuracy...
This paper proposes a novel hybrid position estimation strategy based on merging two self-sensing techniques according to the operating speed. High-frequency (HF) signal injection algorithm is deployed for zero and low-speeds, while the Machine Learning (ML) method is adopted for medium and high speeds. The proposed position estimator is intended for the fault-tolerant control of an interior permanent-magnet-synchronous...
This paper presents a two-stage optimization approach to mitigate the rapid voltage fluctuations and minimize the power losses of distribution systems due to the high penetration of photovoltaic (PV) generation. The first stage is a day-ahead optimal strategy which aims to minimize the total voltage deviations and power losses within the constraints of the daily maximum allowable number of operations...
Wearable and mobile medical devices provide efficient, comfortable, and economic health monitoring, having a wide range of applications from daily to clinical scenarios. Health data security becomes a critically important issue. Electrocardiogram (ECG) has proven to be a potential biometric in human recognition over the past decade. Unlike conventional authentication methods using passwords, fingerprints,...
This paper presents the application of artificial neural-network (ANN) algorithm to control the light of multi-color light-emitting-diode (LED) system. Compared with conventional control methods, the proposed method has the merits of 1) not requiring an accurate system model, 2) achieving quality lighting with higher color rendering index (CRI), 3) requiring only one red-green-blue (RGB) color sensor...
As heterogeneous systems become more ubiquitous, computer architects will need to develop novel CPU scheduling techniques capable of exploiting the diversity of computational resources. Accurately estimating the performance of applications on different heterogeneous resources can provide a significant advantage to heterogeneous schedulers seeking to improve system performance. Recent advances in machine...
Deep learning is a subfield of machine learning which uses artificial neural networks that is inspired by the structure and function of the human brain. Despite being a very new approach, it has become very popular recently. Deep learning has achieved much higher success in many applications where machine learning has been successful at certain rates. In particular It is preferred in the classification...
We propose herein a data-driven dead-zone (DZ) compensation strategy using a model-free Virtual Reference Feedback Tuning (VRFT) approach. The VRFT tuning scheme is accommodated for two controller structures: the first one which explicitly includes a model of the DZ inverse to be identified and the second one which uses a Neural Network (NN) to model the controller to be identified. The main question...
A new training scheme for neural-network-based controller for power electronics systems is proposed. It utilizes the circuit model of the power conversion stage (PCS) in the training process. The training algorithm is a distributed form of evolutionary computation, being able to run on a computer cluster equipped with multiple graphics processing units (GPUs). As a design example, a boost converter...
For automotive applications, accurate torque production capability and high efficiency of the traction motor is very important. However, the performance of widely used interior permanent magnet (IPM) machine is influenced by temperature variation. In this paper, a control algorithm is proposed to compensate the performance variations in IPM machines due to temperature change utilizing current pulse...
Deep Learning is appealing for learning from large amounts of unlabeled/unsupervised data, making it attractive for extracting meaningful representations and patterns from big data. Deep learning, by its simplest definition, is expressed as the application of machine learning methods to the big data. In this study, it was investigated how to apply hierarchical deep learning models for the problems...
This paper discusses the elimination of C.I. Acid Yellow 23 (AY23) using UV/Ag-TiO2 process. To anticipate the photocatalytic elimination of AY23 with the existence of Ag-TiO2 nanoparticles processed under desired circumstances, two computational techniques namely neural network (NN) and particle swarm optimization (PSO) modeling are developed. A summed up of 100 data are used to establish the models,...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.