Applications of fractional calculus in computer vision: A survey

Sugandha,; Mathur, Trilok; Agarwal, Shivi; Tiwari, Kamlesh; Gupta, Phalguni

doi:10.1016/j.neucom.2021.10.122

Cited by 74 publications

(18 citation statements)

References 162 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore, in order to make better and more effective use of ground information, researchers can control the position of machine tools. The purpose of robot trajectory tracking is to minimize the uncertainty in the motion process, so as to ensure the overall performance of the system [15][16].…”

Section: Robot Track Trackingmentioning

confidence: 99%

Trajectory Tracking Control Method for Flexible Robot of Construction Machinery Based on Computer Vision

2023

KME

View full text Add to dashboard Cite

For the application of computer vision, this paper proposes a combination of machine language coding method and wavelet neural network positioning method to build a robot intelligent system based on the motion trajectory of the manipulator. The solution can well solve the problems encountered by traditional robots in line tracking control. Research shows that the computer vision theory is used to design a learning toolbox that meets the task requirements and minimizes the time required to complete the task quickly and accurately. The MATLAB software simulation proves that this scheme is feasible. The test results show that the robot needs about 20 seconds in planning the route time, the time to bypass obstacles is within 5 seconds, and the error rate is about 2%.

show abstract

Section: Robot Track Trackingmentioning

confidence: 99%

Trajectory Tracking Control Method for Flexible Robot of Construction Machinery Based on Computer Vision

2023

KME

View full text Add to dashboard Cite

show abstract

“…4 became gradient descent for output layer ( 7 ) So the updated weights for γ = 0.5 ( 8 ) In this algorithm we just only find formula for learning rate . As The fractional derivatives ensure noise resilience [16].…”

Section: Alsomentioning

confidence: 99%

Fractional Gradient Descent Learning of Backpropagation Artificial Neural Networks with Conformable Fractional Calculus

Saleh¹,

Ajarmah²

2022

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Conformable fractional calculus will be a promising area of research for information processing as natural language and material modelling due to its ease of implementation. In this paper, we propose a fractional gradient descent method for the backpropagation training of neural networks. In particular, the conformable fractional calculus is employed to evaluate the fractional differential gradient function instead of the classical differential gradient function. The results obtained on a large dataset with this approach provide a new optimized, faster and simpler implemented algorithm than the conventional one.

show abstract

“…Due to the memory property and availability of software and other tools, fractional calculus has been used in numerous applications of science and engineering. Tese have been widely used in viscoelasticity [33], biology [34], signal and image processing [35], stock market [27,36], economics [37], and in other domains with history dependency [38]. Moreover, the order of diferentiation acts as a degree of freedom in the optimization process.…”

Section: Preliminariesmentioning

confidence: 99%

Air Quality Prediction Using the Fractional Gradient-Based Recurrent Neural Network

Arora

Singh

et al. 2022

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

In this study, the air quality index (AQI) of Indian cities of different tiers is predicted by using the vanilla recurrent neural network (RNN). AQI is used to measure the air quality of any region which is calculated on the basis of the concentration of ground-level ozone, particle pollution, carbon monoxide, and sulphur dioxide in air. Thus, the present air quality of an area is dependent on current weather conditions, vehicle traffic in that area, or anything that increases air pollution. Also, the current air quality is dependent on the climate conditions and industrialization in that area. Thus, the AQI is history-dependent. To capture this dependency, the memory property of fractional derivatives is exploited in this algorithm and the fractional gradient descent algorithm involving Caputo’s derivative has been used in the backpropagation algorithm for training of the RNN. Due to the availability of a large amount of data and high computation support, deep neural networks are capable of giving state-of-the-art results in the time series prediction. But, in this study, the basic vanilla RNN has been chosen to check the effectiveness of fractional derivatives. The AQI and gases affecting AQI prediction results for different cities show that the proposed algorithm leads to higher accuracy. It has been observed that the results of the vanilla RNN with fractional derivatives are comparable to long short-term memory (LSTM).

show abstract

Applications of fractional calculus in computer vision: A survey

Cited by 74 publications

References 162 publications

Trajectory Tracking Control Method for Flexible Robot of Construction Machinery Based on Computer Vision

Trajectory Tracking Control Method for Flexible Robot of Construction Machinery Based on Computer Vision

Fractional Gradient Descent Learning of Backpropagation Artificial Neural Networks with Conformable Fractional Calculus

Air Quality Prediction Using the Fractional Gradient-Based Recurrent Neural Network

Contact Info

Product

Resources

About