International Journal of Wavelets, Multiresolution and Information Processing

Trustworthy and reliable applications built using intelligent software agents aim to provide improved performance using its characteristics. Agents introduced in various architectures represent its functionality as functional elements of the architecture and shows the interaction between other components present in the architecture. The Internet of things (IoT) reveals as a frequent technology that allows accessing the physical objects present in the world. IoT systems utilize wireless sensor network to transmit and receive data by establishing communication. Wireless Sensor Networks transmits digital signals to the cyber-world for analyzing and processing the information into useful data by either formulating or communicating with the intelligent and innovative system. While talking about IoT and WSN, agents introduced in such environments assist in making decisions quickly by perceiving the input from the environment. The number of agents needed for an application depends upon the complexity of the problem. Multi-Agent architectures discussed in the article describe their association, roles, functionality and interaction. This paper gives a detailed survey of various agent/multi-agent learning architectures introduced over IoT and WSN. Moreover, this survey with the performance and the SWOT analysis on the Agent-based learning architecture helps the reader and paves a way to pursue research on Agent-based architectural deployment over IoT and WSN paradigms.

The appropriate setting of hyperparameter is a key factor to determine the performance of the deep learning model. Efficient hyperparametric optimization algorithm can not only improve the efficiency and speed of model hyperparametric optimization, but also reduce the application threshold of deep learning model. Therefore, we propose a parameter learning algorithm-based co-evolutionary for remote sensing scene classification. First, a co-evolution framework is proposed to optimize the optimizer’s hyperparameters and weight parameters of the convolutional neural networks (CNNs) simultaneously. Second, with the strategy of co-evolution with two populations, the hyperparameters can learn within the population and the weights of CNN can be updated by utilizing information between the populations. Finally, the parallel computing mechanism is adapted to speed up the learning process, as the two populations can evolve simultaneously. Extensive experiments on three public datasets demonstrate the effectiveness of the proposed approach.

In this paper, we first establish a general lower bound for the multivariate wavelet leaders Rényi dimension valid for any pair $(f_1,f_2)$ of functions on ${ℝ}^m$ where $f_1$ belongs to the Besov space $B_{t_1}^{s_1,\infty }({ℝ}^m)$ with $s_1>\frac{m}{t_1}$ and $f_2$ belongs to $B_{t_2}^{s_2,\infty }({ℝ}^m)\cap C^{\gamma }({ℝ}^m)$ with $0<\gamma <s_2<\frac{m}{t_2}$. We then prove the optimality of this result for quasi all pairs $(f_1,f_2)$ in the Baire generic sense. Finally, we compute both iso-mixed and upper-multivariate Hölder spectra for all pairs $(f_1,f_2)$ in the same $G_{\delta }$-set. This allows to prove (respectively, study) the Baire generic validity of the upper-multivariate (respectively, iso-multivariate) multifractal formalism based on wavelet leaders for such pairs.

We present an optimization approach to wavelet architecture that hinges on the Zak transform to formulate the construction as a minimization problem. The transform warrants parametrization of the quadrature mirror filter in terms of the possible integer sample values of the scaling function and the associated wavelet. The parameters are predicated to satisfy constraints derived from the conditions of regularity, compact support and orthonormality. This approach allows for the construction of nearly cardinal scaling functions when an objective function that measures deviation from cardinality is minimized. A similar objective function based on a measure of symmetry is also proposed to facilitate the construction of nearly symmetric scaling functions on the line.

Navigation at sea requires accurate velocity measurement of a vehicle relative to the seabed. Correlation velocity measurement techniques are efficiently used to measure the velocity of underwater vehicles because they are not affected by sound speed compared to Doppler techniques, have several advantages such as small size and power consumption and tracking deep seabed. We consider the relationship of maximum correlation coefficient and signal-to-noise ratio (SNR), which are important parameters in correlation velocity measurement and present the maximum correlation coefficient equation according to SNR. Next, we propose a method of the noise robustness enhancement using discrete wavelet transform (DWT) in correlation velocity measurement. In addition, we evaluate the noise robustness of the proposed method and various methods of correlation velocity measurement through simulation, and present the maximum correlation coefficient equation according to SNR of our method. Simulation results show that new method of correlation velocity measurement using wavelet thresholding proposed in this paper improves the noise robustness of correlation velocity measurement more than various methods. In addition, in correlation velocity log (CVL) operating under low SNR below 6 dB, the maximum correlation coefficient of new method increases more than 0.1 than the classical method. Simulation results show that the new method of correlation velocity measurement considerably improved the noise robustness of spatial CVL than classical method, and the noise robustness of new method is highest among various methods of correlation velocity measurement.

In this paper, we study the continuous fractional wavelet transform (CFrWT) in $n$-dimensional Euclidean space ${ℝ}^n$ with scaling parameter $a=(a_1,a_2,\dots ,a_n)\in {ℝ}^n$ such that $a_i\ne 0,\forall i=1(1)n$. We obtain inner product relation and reconstruction formula for the CFrWT depending on two wavelets along with the reproducing kernel function, involving two wavelets, for the image space of CFrWT. We obtain Heisenberg’s uncertainty inequality and Local uncertainty inequality for the CFrWT. Finally, we prove the boundedness of CFrWT on the Morrey space $L_M^{1,\nu }({ℝ}^n)$ and estimate $L_M^{1,\nu }({ℝ}^n)$-distance of the CFrWT of two argument functions with respect to different wavelets.

The e-learning platform gains significant attraction in the current scenario due to the outbreak of the epidemic COVID-19 as e-learning ensures the students continue their studies in the safest environment while maintaining the educational standard. The performance prediction is one of the significant tasks to be carried out in the e-learning platform to sort out the students who require immediate attention to enhance their grades before the final assessment. This paper proposes a prediction model that effectively predicts the learners’ performance in the e-khool learning management system (e-khool LMS) based on the proposed wolf-swarm optimization dependent Deep Long Short-term (wolf-swarm optimization-based Deep-LSTM) approach. The optimization algorithm tunes the optimal weights of the Deep-LSTM classifier, which inherits the hybrid characteristics of the traitors and particles. Initially, the learner data from the e-khool database is employed for classification based on the proposed wolf-swarm optimization dependent Deep-LSTM classifier. The effectiveness of the proposed prediction model is analyzed in terms of MSE and RMSE with the value of 5.93 and 2.426, respectively.

In this paper, we introduce the concept of linear canonical wave packet transform (LCWPT) based on the idea of linear canonical transform (LCT) and wave packet transform (WPT). Parseval’s identity and some properties of LCWPT are discussed. The inversion formula of LCWPT is formulated. Moreover, the composition of LCWPTs is defined and some properties are studied related to it. The LCWPTs of Mexican hat wavelet function are obtained.

In this paper, the definition of a periodic discrete multiresolution analysis is provided. The characterization of such systems is obtained in terms of properties of scaling sequences. Wavelet systems generated by such multiresolution analyses are defined and described. Decomposition and reconstruction formulas for the associated discrete wavelet transform are provided.

It is no secret today that quality software has a higher superiority than leading technology solutions in computer vision. Remarkable advancement has been achieved in ultrasound image classification, essentially because of the availability of large-scale annotated datasets and deep convolutional neural networks (CNN). Applying CNN in the sphere of medicine is also becoming an active and attractive research area for researchers. In this paper, we introduce an efficient method for the classification of fetal ultrasound images using CNN. To classify these images, we collected four types of fetal ultrasound images from hospitals and internet sources. We first analyze and evaluate various CNN models such as AlexNet, Inception_v3, and MobileNet_v1 for training and testing. Then, the results of these CNN models are quantitatively compared with the proposed model in accuracy and speed. The results show that the proposed classification method can be recognized faster without compromising performance and adjust the ultrasound image parameters quickly and automatically. The proposed CNN model’s weight size is less than 1Mb and can be used on mobile or embedded operating systems. We also developed and tested the application on the Android operating system-based mobile device.

In this paper, sufficient conditions on non-stationary periodic wavelet systems to provide good approximation properties of wavelet expansions are established. The approximation error is estimated in terms of modulus of continuity in $L_p$-spaces.

In this paper, we introduce a wavelet-based method for estimating the effective dimension reduction (EDR) space in the semiparametric regression model introduced by Li [Sliced inverse regression for dimension reduction, J. Amer. Statist. Assoc. 86 (1991) 316–327]. This method is obtained by using linear wavelet estimators of the density and regression functions that are involved in the covariance matrix of conditional expectation whose eigenvectors span the EDR space. Then, consistency of the proposed estimators is proved. A simulation study that allows one to evaluate the performance of the proposal with comparison to existing methods is presented.