Applications of real-time median filtering with fast digital and analog sorters

Leeb, Steven B.; Ortiz, Alberto García; Lepard, R.F.; Shaw, Steven R.; Kirtley, J.L.

doi:10.1109/3516.588633

Cited by 18 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a general behavior, the raw signals were altered by filtering in the sense of removing the impulse noise to a degree, which depended on the median filter used. As a fact, this is one of the important properties of the median filters, along with their ability to preserve the edges of the data and avoid truncation [ 40 , 41 ]. One of median filter drawbacks is that some datapoints will be lost; data loss increased by the filter size, from two observations for M3 to 20 for the M21.…”

Section: Methodsmentioning

confidence: 99%

Improving the Event-Based Classification Accuracy in Pit-Drilling Operations: An Application by Neural Networks and Median Filtering of the Acceleration Input Signal Data

Pérez

Borz

2021

Sensors

View full text Add to dashboard Cite

Forestry is a complex economic sector which is relying on resource and process monitoring data. Most of the forest operations such as planting and harvesting are supported by the use of tools and machines, and their monitoring has been traditionally done by the use of pen-and-paper time studies. Nevertheless, modern data collection and analysis methods involving different kinds of platforms and machine learning techniques have been studied lately with the aim of easing the data management process. By their outcomes, improvements are still needed to reach a close to 100% activity recognition, which may depend on several factors such as the type of monitored process and the characteristics of the signals used as inputs. In this paper, we test, thought a case study on mechanized pit-drilling operations, the potential of digital signal processing techniques combined with Artificial Neural Networks (ANNs) in improving the event-based classification accuracy in the time domain. Signal processing was implemented by the means of median filtering of triaxial accelerometer data (window sizes of 3, 5, and up to 21 observations collected at 1 Hz) while the ANNs were subjected to the regularization hyperparameter’s tunning. An acceleration signal processed by a median filter with a window size of 3 observations and fed into an ANN set to learn and generalize by a regularization parameter of α = 0.01 has been found to be the best strategy in improving the event-based classification accuracy (improvements of 1% to 8% in classification accuracy depending on the type of event in question). Improvement of classification accuracy by signal filtering and ANN tuning may depend largely on the type of monitored process and its outcomes in terms of event duration; therefore, other monitoring applications may need particular designs of signal processing and ANN tuning.

show abstract

Section: Methodsmentioning

confidence: 99%

Improving the Event-Based Classification Accuracy in Pit-Drilling Operations: An Application by Neural Networks and Median Filtering of the Acceleration Input Signal Data

Pérez

Borz

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…The major portions of the spikes in the output voltage and gate signal of the ballast load are due to noise. Applying a median filter [21] gives a better waveform of the output voltage, which is shown in Fig. 9.…”

Section: Experimental Set-upmentioning

confidence: 99%

Reduction of output capacitance in dc-dc converters using anticipated load transients

Khaligh

Chapman

2008

2008 Twenty-Third Annual IEEE Applied Power Electronics Conference and Exposition

View full text Add to dashboard Cite

This paper presents a control strategy for low-voltage high-current microprocessor applications. The proposed idea supposes that computer-based loads could possibly provide an indicator to the power supply that a transient is soon to occur. It is shown that if such information is available, then it is possible to reduce the size of the bulk filter capacitance. The proposed anticipatory control tightly maintains output voltage of the converter within the required output voltage ripple band during transients. The proposed technique uses a temporary ballast load to precharge the inductor. Therefore, the dynamic response of the converter to the load changes is fast. A 12/1.5-V, 25-A dc-dc converter is used to validate this concept.Index Terms-Anticipatory control, dc-dc converter, microprocessor, load transient analysis, voltage regulator module (VRM).

show abstract

“…Filtering of initial data has been done by the use of a median filter (MF) and a window size (kernel) of 3 seconds (MFk = 3). The choice of a median filter was related to its ability to preserve the edges at transitions in the amplitude's range [24], therefore to preserve the correct timing of the observed events. The choice of the kernel size set at k = 3 was also a trade-off between preserving the acceleration signal's shape in the time domain and enhancing the signal-to-noise ratio, with the first one trying to preserve short spikes that characterized real event changes (see, for instance, the acceleration magnitude at time frame 660, Figure 2).…”

Section: Fig 2 Variation Of Acceleration's Magnitude Data In the Timentioning

confidence: 99%

Effect of Training Parameters on the Ability of Artificial Neural Networks to Learn: A Simulation on Accelerometer Data for Task Recognition in Motor-Manual Felling and Processing

Cheţa¹,

Marcu²,

Borz³

2020

FWIAFE

View full text Add to dashboard Cite

Producing dynamic, real-time reliable data on the performance of timber harvesting operations has gained lately a lot of momentum due to the necessity to proactively manage the fleets of machines and machine allocation and to better monitor them in different operational environments to be able to understand their capability and performance. Techniques of Artificial Intelligence (AI) have been used recently to get accurate data at a low cost in many fields of science. In particular, the use of Artificial Neural Networks (ANN) has been proved to enhance classification accuracy in many applications. This work deals with the effect of factors that are typically used to set up an ANN on the performance of classification, by a case time-and-motion study implemented for motor-manual tasks under an experimental approach. A protocol was designed to vary the number of neurons in a hidden layer, number of iterations to train the ANN and the number of folds for cross-validation of data during training. The protocol was applied to a set of median-filtered vector-magnitude data collected at a 1Hz sampling rate by a triaxial accelerometer which was documented by a video approach to encompass five types of events. The results were promising, showing that it is possible to accurately classify the data by various performance metrics. The overall recall, for instance, may be as high as 98%. However, the number of iterations and neurons used to train the ANN are factors that significantly affect the classification performance. We conclude that implementing the ANN architectures to learn from filtered acceleration data has a lot of potential in longterm monitoring of motor-manual work and that future studies should be implemented to resemble the variation of operational conditions.

show abstract

Applications of real-time median filtering with fast digital and analog sorters

Cited by 18 publications

References 13 publications

Improving the Event-Based Classification Accuracy in Pit-Drilling Operations: An Application by Neural Networks and Median Filtering of the Acceleration Input Signal Data

Improving the Event-Based Classification Accuracy in Pit-Drilling Operations: An Application by Neural Networks and Median Filtering of the Acceleration Input Signal Data

Reduction of output capacitance in dc-dc converters using anticipated load transients

Effect of Training Parameters on the Ability of Artificial Neural Networks to Learn: A Simulation on Accelerometer Data for Task Recognition in Motor-Manual Felling and Processing

Contact Info

Product

Resources

About