Search results

This study aims to explore the influence of Fourier-feature enhanced physics-informed neural networks (PINNs) on effectively solving two-dimensional local time-fractional anomalous diffusion equations with nonlinear thermal diffusivity. By tackling the shortcomings of conventional numerical methods in managing fractional derivatives and nonlinearities, this research addresses a significant gap in the literature regarding efficient solution strategies for complex diffusion processes.

This study uses a quantitative methodology featuring a feed-forward neural network architecture combined with a Fourier feature layer. Automatic differentiation is implemented to ensure precise gradient calculations for fractional derivatives. The effectiveness of the proposed approach is showcased through numerical simulations across various sub-diffusion and super-diffusion scenarios, with fractal space parameters adjusted to examine behavior. In addition, the training process is assessed using the Fisher information matrix to analyze the loss landscape.

The results demonstrate that the Fourier-feature enhanced PINNs effectively capture the dynamics of the anomalous diffusion equation, achieving greater solution accuracy than traditional methods. The analysis using the Fisher information matrix underscores the importance of hyperparameter tuning in optimizing network performance. These findings support the hypothesis that Fourier features improve the model’s capacity to represent complex solution behaviors, providing the relationship between model architecture and diffusion dynamics.

This research presents a novel approach to solving fractional anomalous diffusion equations through Fourier-feature enhanced PINNs. The results contribute to the advancement of computational methods in areas such as thermal engineering, materials science and biological diffusion modeling, while also providing a foundation for future investigations into training dynamics within neural networks.

The overall goal of this research is to develop algorithms for feature-based recognition of 2D parts from intensity images. Most present industrial vision systems are custom-designed systems, which can only handle a specific application. This is not surprising, since different applications have different geometry, different reflectance properties of the parts.

Computer vision recognition has attracted the attention of researchers in many application areas and has been used to solve many ranges of problems. Object recognition is a type of pattern recognition. Object recognition is widely used in the manufacturing industry for the purpose of inspection. Machine vision techniques are being applied in areas ranging from medical imaging to remote sensing, industrial inspection to document processing and nanotechnology to multimedia databases. In this work, recognition of objects manufactured in mechanical industry is considered. Mechanically manufactured parts have recognition difficulties due to manufacturing process including machine malfunctioning, tool wear and variations in raw material. This paper considers the problem of recognizing and classifying the objects of such mechanical part. Red, green and blue RGB images of five objects are used as an input. The Fourier descriptor technique is used for recognition of objects. Artificial neural network (ANN) is used for classification of five different objects. These objects are kept in different orientations for invariant rotation, translation and scaling. The feed forward neural network with back-propagation learning algorithm is used to train the network. This paper shows the effect of different network architecture and numbers of hidden nodes on the classification accuracy of objects as well as the effect of learning rate and momentum.

One important finding is that there is not any considerable change in the network performances after 500 iterations. It has been found that for data smaller network structure, smaller learning rate and momentum are required. The relative sample size also has a considerable effect on the performance of the classifier. Further studies suggest that classification accuracy is achieved with the confusion matrix of the data used. Hence, with these results the proposed system can be used efficiently for more objects. Depending upon the manufacturing product and process used, the dimension verification and surface roughness may be integrated with proposed technique to develop a comprehensive vision system. The proposed technique is also highly suitable for web inspections, which do not require dimension and roughness measurement and where desired accuracy is to be achieved at a given speed. In general, most recognition problems provide identity of object with pose estimation. Therefore, the proposed recognition (pose estimation) approach may be integrated with inspection stage.

This paper considers the problem of recognizing and classifying the objects of such mechanical part. RGB images of five objects are used as an input. The Fourier descriptor technique is used for recognition of objects. ANN is used for classification of five different objects. These objects are kept in different orientations for invariant rotation, translation and scaling. The feed forward neural network with back-propagation learning algorithm is used to train the network. This paper shows the effect of different network architecture and numbers of hidden nodes on the classification accuracy of objects as well as the effect of learning rate and momentum.

The field of machine vision, or computer vision, has been growing at fast pace. The growth in this field, unlike most established fields, has been both in breadth and depth of concepts and techniques. Machine vision techniques are being applied in areas ranging from medical imaging to remote sensing, industrial inspection to document processing and nanotechnology to multimedia databases. The goal of a machine vision system is to create a model of the real world from images. Computer vision recognition has attracted the attention of researchers in many application areas and has been used to solve many ranges of problems. The purpose of this paper is to consider recognition of objects manufactured in mechanical industry. Mechanically manufactured parts have recognition difficulties due to manufacturing process including machine malfunctioning, tool wear and variations in raw material. This paper considers the problem of recognizing and classifying the objects of such parts. RGB images of five objects are used as an input. The Fourier descriptor technique is used for recognition of objects. Artificial neural network (ANN) is used for classification of five different objects. These objects are kept in different orientations for invariant rotation, translation and scaling. The feed forward neural network with back-propagation learning algorithm is used to train the network. This paper shows the effect of different network architecture and numbers of hidden nodes on the classification accuracy of objects.

The overall goal of this research is to develop algorithms for feature-based recognition of 2D parts from intensity images. Most present industrial vision systems are custom-designed systems, which can only handle a specific application. This is not surprising, since different applications have different geometry, different reflectance properties of the parts.

Classification accuracy is affected by the changing network architecture. ANN is computationally demanding and slow. A total of 20 hidden nodes network structure produced the best results at 500 iterations (90 percent accuracy based on overall accuracy and 87.50 percent based on κ coefficient). So, 20 hidden nodes are selected for further analysis. The learning rate is set to 0.1, and momentum term used is 0.2 that give the best results architectures. The confusion matrix also shows the accuracy of the classifier. Hence, with these results the proposed system can be used efficiently for more objects.

After calculating the variation of overall accuracy with different network architectures, the results of different configuration of the sample size of 50 testing images are taken. Table II shows the results of the confusion matrix obtained on these testing samples of objects.

The purpose of this paper is to improve the performance of E-nose in the detection of wound infection. Feature extraction and selection methods have a strong impact on the performance of pattern classification of electronic nose (E-nose). A new hybrid feature matrix construction method and multi-objective binary quantum-behaved particle swarm optimization (BQPSO) have been proposed for feature extraction and selection of sensor array.

A hybrid feature matrix constructed by maximum value and wavelet coefficients is proposed to realize feature extraction. Multi-objective BQPSO whose fitness function contains classification accuracy and a number of selected sensors is used for feature selection. Quantum-behaved particle swarm optimization (QPSO) is used for synchronization optimization of selected features and parameter of classifier. Radical basis function (RBF) network is used for classification.

E-nose obtains the highest classification accuracy when the maximum value and db 5 wavelet coefficients are extracted as the hybrid features and only six sensors are selected for classification. All results make it clear that the proposed method is an ideal feature extraction and selection method of E-nose in the detection of wound infection.

The innovative concept improves the performance of E-nose in wound monitoring, and is beneficial for realizing the clinical application of E-nose.

The detection of H₂ concentrations in concentrations undetectable by the conventional detection method of surface acoustic wave (SAW) sensors based on frequency shift, by correlating analyte presence with Fourier spectra components.

Fast Fourier Transform (FFT) and autocorrelation analysis of phase noise in a SnO2-coated SAW sensor was performed. Fourier spectra were obtained by FFT from the SAW sensor resonance frequency instability, in the absence of analyte, and for H₂ concentrations between 0.08 and 0.4 per cent.

All analyte concentrations are below the sensor limit of detection, which is 0.8 per cent for H₂. Although these analyte concentrations caused no significant change in the resonance frequency of the SAW resonator, the FFT spectra presented several modifications, namely, the appearance of a new peak and the decrease of randomness. The authors consider that the effect is because of the chaotic behavior of the temporal dependence of the SAW resonance frequency. This explanation is substantiated by the decrease observed in the SAW oscillator autocorrelation function, which is an indication for a chaotic behavior.

As chaotic systems are extremely sensitive to perturbation, measurement methods based on chaos diagnosis could potentially greatly improve the SAW detection.

Fourier spectra components were correlated with analyte presence in concentrations undetectable by the conventional SAW detection method based on frequency shift.

The purpose of this study is to propose an alternative efficient 3D emotion recognition model for variable-length electroencephalogram (EEG) data.

Classical AMIGOS data set which comprises of multimodal records of varying lengths on mood, personality and other physiological aspects on emotional response is used for empirical assessment of the proposed overlapping sliding window (OSW) modelling framework. Two features are extracted using Fourier and Wavelet transforms: normalised band power (NBP) and normalised wavelet energy (NWE), respectively. The arousal, valence and dominance (AVD) emotions are predicted using one-dimension (1D) and two-dimensional (2D) convolution neural network (CNN) for both single and combined features.

The two-dimensional convolution neural network (2D CNN) outcomes on EEG signals of AMIGOS data set are observed to yield the highest accuracy, that is 96.63%, 95.87% and 96.30% for AVD, respectively, which is evidenced to be at least 6% higher as compared to the other available competitive approaches.

The present work is focussed on the less explored, complex AMIGOS (2018) data set which is imbalanced and of variable length. EEG emotion recognition-based work is widely available on simpler data sets. The following are the challenges of the AMIGOS data set addressed in the present work: handling of tensor form data; proposing an efficient method for generating sufficient equal-length samples corresponding to imbalanced and variable-length data.; selecting a suitable machine learning/deep learning model; improving the accuracy of the applied model.

The paper aims to build a new objective evaluation method of fabric pilling by combining an integrated image analysis technology with a deep learning algorithm.

Series of image analysis techniques were adopted. First, a Fourier transform transformed images into the frequency domain. The optimal resolution matrix of an exponential high-pass filter was determined by combining the energy algorithm. Second, the multidimensional discrete wavelet transform determined the optimal division level. Third, the iterative threshold method was used to enhance images to obtain a complete and clear pilling ball images. Finally, the deep learning algorithm was adopted to train data from pilling ball images, and the pilling levels were classified according to the learning features.

The paper provides a new insight about how to objectively evaluate fabric pilling grades. Results of the experiment indicate that the proposed objective evaluation method can obtain clear and complete pilling information and the classification accuracy rate of the deep learning algorithm is 94.2%, whose structures are rectified linear unit (ReLU) activation function, four hidden layers, cross-entropy learning rules and the regularization method.

Because the methodology of the paper is based on woven fabric, the research study’s results may lack generalizability. Therefore, researchers are encouraged to test other kinds of fabric further, such as knitted and unwoven fabrics.

Combined with a series of image analysis technology, the integrated method can effectively extract clear and complete pilling information from pilled fabrics. Pilling grades can be classified by the deep learning algorithm with learning pilling information.

The purpose of this study is to investigate the drivers behind the notable increase in red meat prices in Turkey, attributing the rise primarily to policy interventions within the dairy industry which result in a reduction of farm capacity for dairy farmers.

To analyze the factors that determine the price of carcass red meat, cattle fattening feed is identified as a variable that directly affects carcass pricing, while the ratio of farm gate milk prices to milk feed prices is assumed to have an indirect impact. Monthly data from January 2011 to December 2022 are used in the analysis. The time series examined is influenced by time-dependent nonlinear Fourier trends that are computed for use in the estimation part.

The study reveals that fluctuations in cattle fattening feed prices have an immediate impact on carcass prices, while changes in the ratio of raw milk prices to milk feed prices exhibit a time lag. Although short-term interventions to the farm gate milk prices can initially suppress carcass prices, it is important to consider their medium and long-term effects, as these can manifest as a decrease in the number of animals available.

The research sheds light on the intricate interplay between policy interventions in the dairy sector and their ripple effects on the broader red meat market, contributing valuable insights to both academic and policy discourse.

The quality of produced textile fibers plays a very important role in the textile industry, and detection and assessment schemes are the key problems. Therefore, the purpose of this paper is to propose a relatively simple and effective technique to detect and assess the quality of produced textile fibers.

In order to achieve automatic visual inspection of fabric defects, first, images of the textile fabric are pre-processed by using Block-Matching and 3-D (BM3D) filtering. And then, features of textile fibers image are respectively extracted, including color, texture and frequency spectrum features. The color features are extracted by using hue–saturation–intensity model, which is more consistent with the human vision perception model; texture features are extracted by using scale-invariant feature transform scheme, which is a quite good method to detect and describe the local image features, and the obtained features are robust to local geometric distortion; frequency spectrum features of textiles are less sensitive to noise and intensity variations than spatial features. Finally, for evaluating the quality of the fabric in real time, two quantitatively metric parameters, peak signal-to-noise ratio and structural similarity, are used to objectively assess the quality of textile fabric image.

Compared to the quality between production and pre-processing of textile fiber images, the BM3D filtering method is a very efficient technology to improve the quality of textile fiber images. Compared to the different features of textile fibers, like color, texture and frequency spectrum, the proposed detection and assessment method based on textile fabric image feature can easily detect and assess the quality of textiles. Moreover, the objective metrics can further improve the intelligence and performance of detection and assessment schemes, and it is very simple to detect and assess the quality of textiles in the textile industry.

An intelligent detection and assessment method based on textile fabric image feature is proposed, which can efficiently detect and assess the quality of textiles, thereby improving the efficiency of textile production lines.

This paper aims to describe the laminar flow of Maxwell fluid past a non-isothermal rigid plate with a stream wise pressure gradient. Heat transfer mechanism is analyzed in the context of non-Fourier heat conduction featuring thermal relaxation effects.

Flow field is permeated to uniform transverse magnetic field. The governing transport equations are changed to globally similar ordinary differential equations, which are tackled analytically by homotopy analysis technique. Homotopy analysis method-Padè approach is used to accelerate the convergence of homotopy solutions. Also, numerical approximations are made by means of shooting method coupled with fifth-order Runge-Kutta method.

The solutions predict that fluid relaxation time has a tendency to suppress the hydrodynamic boundary layer. Also, heat penetration depth reduces for increasing values of thermal relaxation time. The general trend of wall temperature gradient appears to be similar in Fourier and Cattaneo–Christov models.

An important implication of current research is that the thermal relaxation time considerably alters the temperature and surface heat flux.

Current problem even in case of Newtonian fluid has not been attempted previously.