Improvement In MSE Research Articles

A novel hybrid GRU-CNN and residual bias (RB) based RB-GRU-CNN models for prediction of PTB Diagnostic ECG time series data

Time series analysis is crucial in the field of medical sciences. Recently, it has become crucial to comprehend the intricacies of data to forecast and assess the likelihood of survival in patients with different ailments. The study employs diverse datasets from multiple PTB electrocardiogram (ECG) datasets, which exhibit a high degree of uncorrelation. These datasets include patients with various heart diseases and age groups, ensuring dataset diversity. The paper presents two models that utilize deep learning and residual bias. The primary approach proposed is a hybrid GRU-CNN model. In contrast, the second model incorporates residual bias (RB) to improve upon the first model, referred to as the RB-GRU-CNN model. The hybrid GRU-CNN model has been compared to conventional deep learning models across multiple metrics, achieving the highest average percentage of improvement in RMSE (46.73%), MSE (67.46%), MAPE (43.92%), and MAE (48.52%) compared to LSTM. The RB-GRU-CNN proposed model demonstrated greater efficacy than the GRU-CNN proposed model, as confirmed by non-parametric statistical Friedman ranking and their corresponding Holm’s p-values. The comprehensive study of the results proves that the proposed models outperformed the performance of the traditional models.

LSB‐XOR technique for securing captured images from disaster by UAVs in B5G networks

SummaryRecently, unmanned aerial vehicles (UAV) technology has been utilized to monitor and capture images from disasters to analyze, process, and take action in real‐time for a speedy recovery. UAVs represent one of the critical technologies used beyond the fifth generation (B5G) of heterogeneous networks. Due to the sensitive data captured from disaster areas by UAVs, security has become a significant concern. Therefore, effective methods are needed to defend collected data against hackers and fictional activity by untrusted users. Audio encryption technologies can be applied to military communication, multimedia, medical, telemedical, and the internet. The present work introduces a novel Steganographic technique of converting an image to audio using LSB coding with XOR operation, ensuring the audio signal is protected using a key and maintains the excellent quality of the signal regenerated. Python3 is used for the implementation of the proposed technique. The findings show significant improvement in MSE and SSIM contexts.

Enhanced prediction of parking occupancy through fusion of adaptive neuro-fuzzy inference system and deep learning models

While predicting parking occupancy is crucial for managing urban congestion, existing models often exhibit gaps in accuracy, uncertainty handling, and integration potential. This study introduces an innovative combination of adaptive neuro-fuzzy inference system (ANFIS) and deep learning (DL) techniques to address these shortcomings. Specifically, ANFIS is utilized for its proficiency in uncertainty representation via fuzzy set theory, whereas DL models excel in automatic feature learning, non-linear modeling, and identifying long-term dependencies in time-series parking data. By integrating ANFIS with recurrent neural networks (RNN), long short-term memory (LSTM), and gated recurrent units (GRU), we formulated the ANFIS-RNN, ANFIS-LSTM, and ANFIS-GRU fusion models, testing them on real-world parking datasets. Subsequent experiments highlighted the dominance of these fusion models over individual and benchmark counterparts. ANFIS-RNN achieved a 30.61% improvement in MSE, 16.70% in RMSE, 21.21% in MAE, 21.58% in MAPE, and a 1.03% elevation in R2 over the standalone RNN. The ANFIS-LSTM surpassed LSTM by 34.04% in MSE, 18.76% in RMSE, 26.16% in MAE, 27.71% in MAPE, with a 1.04% R2 increment. ANFIS-GRU exceeded GRU metrics by 27.54% in MSE, 14.85% in RMSE, 19.27% in MAE, 20.01% in MAPE, and boosted R2 by 1.03%. These outcomes underline the potential of integrated models in refining prediction precision. By leveraging the combined strengths of ANFIS and DL, this research offers a significant leap in parking occupancy forecasting. Its implications extend to data-centric urban planning and traffic regulation, marking a pivotal step for future endeavors in hybrid predictive modeling incorporating soft computing and deep learning paradigms.

PWDformer: Deformable transformer for long-term series forecasting

Long-term forecasting is of paramount importance in numerous scenarios, including predicting future energy, water, and food consumption. For instance, extreme weather events and natural disasters can profoundly impact infrastructure operations and pose severe safety concerns. Traditional CNN-based models often struggle to capture long-distance dependencies effectively. In contrast, Transformers-based models have shown significant promise in long-term forecasting.This paper investigates the long-term forecasting problem and identifies a common limitation in existing Transformer-based models: they tend to reduce computational complexity at the expense of time information aggregation capability. Moreover, the order of time series plays a crucial role in accurate predictions, but current Transformer-based models lack sensitivity to time series order, rendering them unreasonable.To address these issues, we propose a novel Deformable-Local (DL) aggregation mechanism. This mechanism enhances the model’s ability to aggregate time information and allows the model to adaptively adjust the size of the time aggregation window. Consequently, the model can discern more complex time patterns, leading to more accurate predictions. Additionally, our model incorporates a Frequency Selection module to reinforce effective features and reduce noise. Furthermore, we introduce Position Weights to mitigate the order-insensitivity problem present in existing methods.In extensive evaluations of long-term forecasting tasks, we conducted benchmark tests on six datasets covering various practical applications, including energy, traffic, economics, weather, and disease. Our method achieved state-of-the-art (SOTA) results, demonstrating significant improvements. For instance, on the ETT dataset, our model achieved an average MSE improvement of approximately 19% and an average MAE improvement of around 27%. Remarkably, for predicted lengths of 96 and 192, we achieved outstanding MSE and MAE improvements of 32.1% and 30.9%, respectively.

The Evaluation Technology of Manufacturer Intelligence Regarding the Selection of the Decision Support System of Smart Manufacturing Technologies: Analysis of China–South Africa Relations

With the development of international cooperation, South Africa (SA) has been China’s largest trading partner in Africa for several consecutive years. China and SA can build the digital “Belt and Road” to modernize the manufacturing system locally and optimize process control by benchmarking with the best-in-class manufacturers in each country. In this research, an evaluation technology of manufacturer intelligence regarding the selection of decision support system (DSS) of smart manufacturing technologies, analyzing China–South Africa relations, is described. Firstly, the three keys aspects that enable the technologies of DSS are discussed in detail. Then, one key technology, the manufacturers’ intelligent evaluation system with 15 indexes, was built. The indexes and their measurements are also proposed. Finally, a fusion method based on boosting with multi-kernel function (online sequential extreme learning machine based on boosting, Boosting-OSELM) is introduced. The purpose of Boosting-OSKELM is to combine several weak learners into a strong learner (lower mean square error, MSE) through an acceptable time delay. Finally, the case study is presented to demonstrate the improvement on the MSE and process time, showing a relative MSE improvement of 96.19% and a relative time delay ratio of 31.46%. Totally, the largest contribution of the proposed evaluation method in this study is the conversion of the history data saved by the manual scoring method into knowledge in accessible MES and resealable time delay, which will free up the expert workforce in the entire process. We expect this paper will help future research in this field.

A new deep learning architecture with inductive bias balance for transformer oil temperature forecasting

Ensuring the optimal performance of power transformers is a laborious task in which the insulation system plays a vital role in decreasing their deterioration. The insulation system uses insulating oil to control temperature, as high temperatures can reduce the lifetime of the transformers and lead to expensive maintenance. Deep learning architectures have been demonstrated remarkable results in various fields. However, this improvement often comes at the cost of increased computing resources, which, in turn, increases the carbon footprint and hinders the optimization of architectures. In this study, we introduce a novel deep learning architecture that achieves a comparable efficacy to the best existing architectures in transformer oil temperature forecasting while improving efficiency. Effective forecasting can help prevent high temperatures and monitor the future condition of power transformers, thereby reducing unnecessary waste. To balance the inductive bias in our architecture, we propose the Smooth Residual Block, which divides the original problem into multiple subproblems to obtain different representations of the time series, collaboratively achieving the final forecasting. We applied our architecture to the Electricity Transformer datasets, which obtain transformer insulating oil temperature measures from two transformers in China. The results showed a 13% improvement in MSE and a 57% improvement in performance compared to the best current architectures, to the best of our knowledge. Moreover, we analyzed the architecture behavior to gain an intuitive understanding of the achieved solution.

A modified LSTM neural network model for stock price prediction based on auxiliary information and model average

LSTM neural network has been widely used in stock price forecasting, but it has some problems such as difficulty in selecting superparameters, insufficient information of original price sequence, etc. Based on this, the model propose an improved method based on functional principal component analysis and distance covariance weighted model averaging. On the one hand, the method solves the problem that the original stock price information may not be sufficient to predict future price trends by using the functional principal component basis expansion coefficient of the intraday price to capture the residual sequence between the LSTM neural network predicted value and the real stock price. On the other hand, for the superparameter selection of LSTM neural network, the method uses a model averaging method based on distance covariance, which effectively balances the variance and bias of the prediction model. Furthermore, the regression method between the residuals sequence and the basis expansion coefficient of the functional principal component is model free. The actual data analysis shows that the proposed method has a greater improvement in MSE and BE than the original LSTM. Finally, the proposed method can be viewed as an optimization framework. This method can also modify ARIMA, GARCH and other models, and it can also be applied to other time series data prediction background.

High‐accuracy mean circuits design by manipulating correlation for stochastic computing

AbstractStochastic computing (SC) encodes numerical values into probabilistic binary bitstreams to enable complex arithmetic operations to be transformed into simple bit operations. Different operations can be performed through the same SC element by adjusting the correlation between bitstreams. In this work, two stochastic mean circuits (MCs) are proposed by manipulating positively and negatively correlated bitstreams, respectively named PCMC and NCMC, to improve computing accuracy, lower area, and power consumption. Furthermore, a general structure for MCs, denoted as GMC, is also proposed to generalize their design approach. Compared with the existing multiplexer (MUX)‐based stochastic MCs, the proposed circuits have approximately 50%, 59%, 61%, and 64% reduction in area, and 100×, 10×, 151×, and 12 × improvement in MSE, for 2‐, 3‐, 4‐, and 5‐input situations, respectively. With applications to edge detection and mean filtering, the proposed designs are superior to the existing counterparts in terms of accuracy and hardware cost.

A James-Stein-type adjustment to bias correction in fixed effects panel models

This paper proposes a James-Stein-type (JS) adjustment to analytical bias correction in fixed effects panel models that suffer from the incidental parameters problem. We provide high-level conditions under which the infeasible JS adjustment leads to a higher-order MSE improvement over the bias-corrected estimator, and the former is asymptotically equivalent to the latter. To obtain a feasible JS adjustment, we propose a nonparametric bootstrap procedure to estimate the JS weighting matrix and provide conditions for its consistency. We apply the JS adjustment to two models: (1) the linear autoregressive model with fixed effects, (2) the nonlinear static fixed effects model. For each application, we employ Monte Carlo simulations which confirm the theoretical results and illustrate the finite-sample improvements due to the JS adjustment. Finally, the extension of the JS procedure to a more general class of models and other policy parameters are illustrated.

Polycystic Ovarian Syndrome Detection by Using Two-Stage Image Denoising

The requirement of imaging methods in the medical field is vivid. If the capturing devices are not sophisticated, the acquired images will have a significant amount of noise. These noises are hazardous and cannot be entertained. Polycystic Ovarian Syndrome (PCOS) caused the state of affairs in girls if not diagnosed and look after early stages. Tran's epithelial duct ultrasound machine could be a non-invasive technique of imaging the human ovary to show salient options necessary for PCOS identification. Numbers of follicles and their sizes area unit the most options that characterize ovarian pictures. Hence, PCOS is diagnosed by investigating the numbers of follicles and measurement their sizes manually. conflict in medical aid is essentially created by technical advances in modalities that resulted from fruitful interactions among the essential science, bioscience, and manufacturer. Hence, PCOS is diagnosed by investigating the numbers of follicles and measurement their sizes manually. This paper attempts to identify the noise & try to generate a noise-free image by evaluation of noise properties. The noise pattern information thus provides an upper hand in the second stage filtering with specific filters i.e. fuzzified. A median filter for salt and pepper noise; and an adaptive wiener filter for Gaussian noise. 46.2%, 15.1%, and 12.4% improvement in MSE for salt & pepper, Gaussian, and speckle noise as compared to best existing methods.

RG Hyperparameter Optimization Approach for Improved Indirect Prediction of Blood Glucose Levels by Boosting Ensemble Learning

This paper proposes an RG hyperparameter optimization approach, based on a sequential use of random search (R) and grid search (G), for improving the blood glucose level prediction of boosting ensemble learning models. An indirect prediction of blood glucose levels in patients is performed, based on historical medical data collected by means of physical examination methods, using 40 human body’s health indicators. The conducted experiments with real clinical data proved that the proposed RG double optimization approach helps improve the prediction performance of four state-of-the-art boosting ensemble learning models enriched by it, achieving 1.47% to 24.40% MSE improvement and 0.75% to 11.54% RMSE improvement.

Deep neural networks architecture driven by problem-specific information

Deep learning provides a variety of neural network-based models, known as deep neural networks (DNNs), which are being successfully used in several domains to build highly accurate predictors. A key factor which usually makes DNNs to outperform traditional machine learning models is the amount of data that is nowadays accessible and available. Nevertheless, there are other factors linked to DNNs topologies that may also have influence on the predictive performance of DNN models. In particular, fully connected deep neural networks (fc-DNNs) typically struggle in achieving good performance rates when applied to small datasets. This is due to the high number of parameters which need to be learned when training this kind of models, which makes them prone to over-fitting issues. In this paper, authors propose the use of problem-specific information in order to impose constraints to network architecture so that a fc-DNN is transformed into a partially connected DNN (pc-DNN), in such a way that network topology is driven by prior knowledge. This work compares two baseline models, the elastic net and fc-DNNs, to pc-DNNs applied on three synthetic datasets with different number of samples. Synthetic data was generated to estimate the goodness of using problem-specific information to drive network architectures. Furthermore, a similar analysis is performed herein on a real-world problem dataset to show the benefits of pc-DNN models in term of predictive performance. The results of the analysis showed that pc-DNNs with built-in problem-specific information clearly outperformed the elastic net and fc-DNNs in most of the datasets used, in either synthetic or real-world problems. The pc-DNNs turned out to be a useful model, especially when it is applied to small- or medium-size datasets, on which it significantly outperformed the baseline models considered in this study. Specifically, the pc-DNNs achieved AUC and MSE improvement rates of ( $$8.21\%$$ , $$19.79\%$$ ) and ( $$6.65\%$$ , $$20.54\%$$ ) in small- and medium-size datasets for both case studies analyzed, the synthetic and real-world problem, respectively.

Subspace-Based Estimation of Rapidly Varying Mobile Channels for OFDM Systems

It is well-known that time-varying channels can provide time diversity and improve error rate performance compared to time-invariant fading channels. However, exploiting time diversity requires very accurate channel estimates at the receiver. In order to reduce the number of unknown channel coefficients while estimating the time-varying channel, basis expansion models can be used along with long transmission frames that contain multiple orthogonal frequency division multiplexing (OFDM) symbols that experience the channel variation. The design of these OFDM frames need to judiciously incorporate training and data insertions in the transmitted signal while maintaining orthogonality. In this work, we propose an inter channel interference (ICI)-free training model depending on pilot symbols only and provide a corresponding time-varying channel estimation method. This scheme relies on an algorithm to determine the number of OFDM symbols per frame and the number of basis functions per path with minimal information about the Doppler bandwidth. As a performance benchmark, Bayesian Cramer Rao lower bound (CRLB) and the corresponding MSE bound are derived analytically for the proposed training model. Theoretical MSE expressions of the proposed estimation scheme are also derived as well as the MSE expressions in the presence of Doppler frequency mismatch. Simulations exhibit substantial MSE improvement and the corresponding Symbol Error Rate (SER) performances of the low complexity estimation scheme. They also corroborate that, unlike the common results in the literature, an OFDM system can perform better as the Doppler frequency increases with judicious design of training and channel estimation schemes.

Estimating the drivers of species distributions with opportunistic data using mediation analysis

AbstractEcological occupancy modeling has historically relied on high‐quality, low‐quantity designed‐survey data for estimation and prediction. In recent years, there has been a large increase in the amount of high‐quantity, unknown‐quality opportunistic data. This has motivated research on how best to combine these two data sources in order to optimize inference. Existing methods can be infeasible for large datasets or require opportunistic data to be located where designed‐survey data exist. These methods map species occupancies, motivating a need to properly evaluate covariate effects (e.g., land cover proportion) on their distributions. We describe a spatial estimation method for supplementarily including additional opportunistic data using mediation analysis concepts. The opportunistic data mediate the effect of the covariate on the designed‐survey data response, decomposing it into a direct and indirect effect. A component of the indirect effect can then be quickly estimated via regressing the mediator on the covariate, while the other components are estimated through a spatial occupancy model. The regression step allows for use of large quantities of opportunistic data that can be collected in locations with no designed‐survey data available. Simulation results suggest that the mediated method produces an improvement in relative MSE when the data are of reasonable quality. However, when the simulated opportunistic data are poorly correlated with the true spatial process, the standard, unmediated method is still preferable. A spatiotemporal extension of the method is also developed for analyzing the effect of deciduous forest land cover on red‐eyed vireo distribution in the southeastern United States and find that including the opportunistic data do not lead to a substantial improvement. Opportunistic data quality remains an important consideration when employing this method, as with other data integration methods.

Performance Analysis of Hardware Impairment Aware MMSE Receiver With Channel and CFO Estimation Error Statistics for a Large MIMO-OFDM System

In this treatise, we conceive a hardware impairment aware receiver design of a large multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) system, taking into account the error statistics of parameter estimations. The hardware impairment includes the quantization noise, phase noise etc. There are two key contributions in this work. Firstly, consideration of error statistics of residual parameters in the receiver design improves receiver performance. In this work, we propose a linear equalizer based data detector at the receiver for a large MIMO-OFDM system and the parameters of interest are the channel impulse response (CIR) and carrier frequency offset (CFO) along with the hardware impairments awareness both at transmitter and receiver. The design criterion chosen for designing the detector equalizer is based on the linear minimum mean square error (LMMSE) one and it will consider the statistics of estimation error and hardware impairments. However, in any practical communication system, the availability of statistics for these parameter errors is inconceivable. Hence, we propose further to consider the Bayesian Crammer Rao lower bound (BCRLB) as the variance of the error with the key assumption of zero mean. Numerical simulation demonstrates that, consideration of such statistics attains an SNR gain of $2$ dB with respect to a fixed symbol error ratio (SER). It also shows that the SER performance with BCRLB matches very closely with the case, when exact error variance is used. For the second contribution, an extensive theoretical analysis has been performed to evaluate the MSE improvement of data detection with the LMMSE criterion with parameter estimation error statistics consideration in the large MIMO-OFDM system. This theoretical analysis of improved MSE has been conceived with the usage of large dimension random matrix theory and a closed-form expression has been obtained. Numerical simulation demonstrates that the theoretical analysis for MSE improvement matches closely with the simulated one.

Image Denoising Using Discrete Wavelet Transform : A Theoretical Framework

Noise is a random variation in brightness and color in image or simply we can say that unwanted signals are called noise. The noise is mixed with original signal and cause may troubles. Due to the presence of noise, quality of image is reduced and other features like edge sharpness and pattern recognition are badly affected. In image denoising methods to improve the results a hybrid filter is used for better visualization. The hybrid filter is composed with the combination of three filters connected in series. The hybridization has performed much better in case of salt and pepper type of noise and for most of the medical image type, either MRI, CT, SPECT, Ultra Sound. PSNR values show major improvement in comparison of other existing methods. Future, the results obtained from the presented denoising experiments would be tried to be improved further by using this method with other transform domain methods. Finally, the results are concluded that the proposed approach in terms of PSNR, MSE improvement is outperformed.

ANFIS based Control Scheme for Binary Distillation Column

Abstract In distillation process, composition control is very important. A continuous column has to be operated as precisely as possible to meet the purity specifications. In this work, ANFIS controllers are designed to control the methanol composition in BDC. The controller controls the methanol composition in BDC by the variation of reflux flow-rate and reboiler heat duty. Two separate ANFIS controllers namely: ANFIS A and ANFIS B are designed for the reflux flow-rate and the reboiler heat duty respectively. Each ANFIS controller has three inputs. The performance of this ANFIS control scheme is compared with NN-IMC control scheme on the basis of considered performance indicators (rise time, settling time, MSE). Performance of the ANFIS control scheme is evaluated for reference tracking and disturbance rejection cases. A perturbation of +10 % is incorporated in feed flow-rate for disturbance rejection case. In case of reference tracking, the obtained result shows that there is an improvement of 7 % in the settling time whereas, 14 % improvement in MSE with ANFIS scheme as compared to NN-IMC scheme. In case of disturbance rejection, the obtained result shows that there is an improvement of 14 % in the rise time, 41 % improvement in settling time whereas, 7 % improvement in MSE with ANFIS scheme as compared to NN-IMC scheme.

Small sample GEE estimation of regression parameters for longitudinal data.

Longitudinal (clustered) response data arise in many bio-statistical applications which, in general, cannot be assumed to be independent. Generalized estimating equation (GEE) is a widely used method to estimate marginal regression parameters for correlated responses. The advantage of the GEE is that the estimates of the regression parameters are asymptotically unbiased even if the correlation structure is misspecified, although their small sample properties are not known. In this paper, two bias adjusted GEE estimators of the regression parameters in longitudinal data are obtained when the number of subjects is small. One is based on a bias correction, and the other is based on a bias reduction. Simulations show that the performances of both the bias-corrected methods are similar in terms of bias, efficiency, coverage probability, average coverage length, impact of misspecification of correlation structure, and impact of cluster size on bias correction. Both these methods show superior properties over the GEE estimates for small samples. Further, analysis of data involving a small number of subjects also shows improvement in bias, MSE, standard error, and length of the confidence interval of the estimates by the two bias adjusted methods over the GEE estimates. For small to moderate sample sizes (N ≤50), either of the bias-corrected methods GEEBc and GEEBr can be used. However, the method GEEBc should be preferred over GEEBr, as the former is computationally easier. For large sample sizes, the GEE method can be used.

A Robust Noise Detector for High Density Impulse Noise

We propose a robust adaptive algorithm for detecting random-valued impulse noise even for highly corrupted images. A variant of Rank-Ordered Absolute Difference (ROAD) called Hybrid Dynamical ROAD (HDROAD) is proposed to improve the accuracy of noise detection. A dynamic window selector chooses the size and shape of the window depending on the density and orientation of noise such as in edges. A considerable amount of PSNR and MSE improvement can be done if the noise detector is accurate in finding out the noisy pixel correctly and if it is efficient enough to misclassify the noiseless pixel as corrupted. Also the rank or length parameter used in ROAD is varied according to the need of the noise detector and a cumulative rank (CR) is used to further improve the performance. We validate the performance of our noise detector using two widely used parameters namely Nf and Nm. A Detailed analysis of the algorithm and the simulation results show that the proposed algorithm is robust for detecting noises significantly even for noise level as high as 80%.

Restoration of Poisson noise corrupted digital images with nonlinear PDE based filters along with the choice of regularization parameter estimation

In this paper, the reconstruction of three nonlinear partial differential equation (PDE) based filters adapted to Poisson noise statistics have been proposed in a variational framework for restoration and enhancement of digital images corrupted with Poisson noise. The proposed and examined PDE based filters include total variation adapted to Poisson noise in L-1 framework; anisotropic diffusion; and complex diffusion based methods adapted to Poisson noise in L-2 framework. The resulting filters contain two terms namely data fidelity and regularization or smoothing function. The data fidelity term is Poisson likelihood term and the regularization functions are PDE based filters. Other choices for the regularization functions have also been presented. The two terms in the proposed filters are coupled with a regularization parameter lambda which makes a proper balance between the two terms during the filtering process. The choice of method for estimation of regularization parameter lambda plays an important role. In this study, the various regularization parameter estimation methods for Poisson noise have also been presented and their suitability has been examined. The resulting optimization problems are further investigated for efficient implementation for large scale problems. For estimating the regularization parameter, three choices are considered for Poisson noise case which are discrepancy principles, generalized cross validations (GCV), and unbiased predictive risk estimate (UPRE). GCV and UPRE functions are further other optimization problems in addition to main image reconstruction problem. For minimizing the GCV and UPRE functions, the methods of Conjugate Gradients (CG) is used. For digital implementations, all schemes have been discretized using finite difference scheme. The comparative analysis of the proposed methods are presented in terms of relative norm error, improvement in SNR, MSE, PSNR, CP and MSSIM for an adaptive value of regularization parameter calculated by every methods in consideration. Finally, from the obtained results it is observed that the anisotropic diffusion based method adapted to Poisson noise gives better results in comparison to other methods in consideration along with choice of GCV for regularization parameter selection.