The Impact of Filter Size and Number of Filters on Classification Accuracy in CNN

Ahmed, Wafaa Shihab; Karim, Abdul Amir Abdullah

doi:10.1109/csase48920.2020.9142089

Cited by 46 publications

(20 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A few filters cannot extract discriminative features from the input data to achieve a higher generalization accuracy, but having more filters is computationally expensive [24]. In general, the number of filters increases as a CNN network grows [28]. Experiments were conducted to select the best possible number of filters to adopt.…”

Section: Number Of Convolution Filtersmentioning

confidence: 99%

One-Dimensional Convolutional Neural Network for Drill Bit Failure Detection in Rotary Percussion Drilling

Senjoba

Sasaki

Kosugi

et al. 2021

Mining

View full text Add to dashboard Cite

Drill bit failure is a prominent concern in the drilling process of any mine, as it can lead to increased mining costs. Over the years, the detection of drill bit failure has been based on the operator’s skills and experience, which are subjective and susceptible to errors. To enhance the efficiency of mining operations, it is necessary to implement applications of artificial intelligence to produce a superior method for drill bit monitoring. This research proposes a new and reliable method to detect drill bit failure in rotary percussion drills using deep learning: a one-dimensional convolutional neural network (1D CNN) with time-acceleration as input data. 18 m3 of granite rock were drilled horizontally using a rock drill and intact tungsten carbide drill bits. The time acceleration of drill vibrations was measured using acceleration sensors mounted on the guide cell of the rock drill. The drill bit failure detection model was evaluated on five drilling conditions: normal, defective, abrasion, high pressure, and misdirection. The model achieved a classification accuracy of 88.7%. The proposed model was compared to three state-of-the-art (SOTA) deep learning neural networks. The model outperformed SOTA methods in terms of classification accuracy. Our method provides an automatic and reliable way to detect drill bit failure in rotary percussion drills.

show abstract

Section: Number Of Convolution Filtersmentioning

confidence: 99%

One-Dimensional Convolutional Neural Network for Drill Bit Failure Detection in Rotary Percussion Drilling

Senjoba

Sasaki

Kosugi

et al. 2021

Mining

View full text Add to dashboard Cite

show abstract

“…Lastly, based on the predicted model, we got the predicted class of every data point. The filter size that used in this paper is 3x3 in every convolutional layer, it refers to the previous research that resulted that the small size of filter will help in increasing the accuracy [26]. Figure 4 shows the summary of the CNN Architecture Used, starting with input values of 152x152x1.…”

Section: The Proposed Methodsmentioning

confidence: 99%

A hybrid model based on convolutional neural networks and fuzzy kernel K-medoids for lung cancer detection

Saragih

Rustam

Aurelia

2021

IJEECS

View full text Add to dashboard Cite

Lung cancer is the deadliest cancer worldwide. Correct diagnosis of lung cancer is one of the main tasks that is challenging tasks, so the patient can be treated as soon as possible. In this research, we proposed a hybrid model based on convolutional neural networks (CNN) and fuzzy kernel k-medoids (FKKM) for lung cancer detection, where the magnetic resonance imaging (MRI) images are transmitted to CNN, and then the output is used as new input for FKKM. The dataset used in this research consist of MRI images taken from someone who had lung cancer with the treatment of anti programmed cell death-1 (anti-PD1) immunotherapy in 2016 that obtained from the cancer imaging archive. The proposed method obtained accuracy, sensitivity, precision, specificity, and F1-score 100% by using radial basis function (RBF) kernel with sigma of {10-8, 10-4, 10-3, 5x10-2, 10-1, 1, 104} in 20-fold cross-validation. The computational time is only taking less than 10 seconds to forward dataset to CNN and 3.85 ± 0.6 seconds in FKKM model. So, the proposed method is more efficient in time and has a high performance for detecting lung cancer from MRI images.

show abstract

“…The optimization of filters deviates from best practice, which suggest increasing the filters progressively after each convolution [35].…”

Section: Hyperparameter Tuning Inner B-pillar Regression Modelmentioning

confidence: 98%

Application of optimized convolutional neural network to fixture layout in automotive parts

Toro

Wiberg²,

Tarkian³

2022

Preprint

View full text Add to dashboard Cite

Fixture layout has aroused substantial interest in the research community during recent decades. It affects the design and production of fixtures, and hence manufacturing costs. While fixturing may seem simple in conception, it requires expertise and well-trained engineers. A general principle, usually called the 3-2-1 locating principle, ensures fixing an object, restringing its degrees of freedom. Fixtures must always comply with the principle. While most research approaches automation of the fixture layout using optimization or rule-based frameworks, this paper proposes supervised learning. The presented framework solves the 3-2-1 locating principle for sheet metal designs based on the experience of previous designs, using automotive b-pillars as a test study. There are three main contributions: 1. A novel idea to introduce sheet metal design data in a convolutional neural network (CNN), projecting the geometry over a plane. The Z coordinate transforms into gray-scale pixel values, generating a topographic map. 2. The framework reuses knowledge about fixturing to lay out new workpieces. The framework is an add-in integrated with the CAD environment. 3. A hyperparameter-tuned CNN for regression generates the final output. The results show high accuracy (≈ 100%) in classifying b-pillars and fast convergence in regression, proving model usability for industrial cases.

show abstract

The Impact of Filter Size and Number of Filters on Classification Accuracy in CNN

Cited by 46 publications

References 10 publications

One-Dimensional Convolutional Neural Network for Drill Bit Failure Detection in Rotary Percussion Drilling

One-Dimensional Convolutional Neural Network for Drill Bit Failure Detection in Rotary Percussion Drilling

A hybrid model based on convolutional neural networks and fuzzy kernel K-medoids for lung cancer detection

Application of optimized convolutional neural network to fixture layout in automotive parts

Contact Info

Product

Resources

About