Computational linguistics based text emotion analysis using enhanced beetle antenna search with deep learning during COVID-19 pandemic

Computational intelligence and nature-inspired computing have changed the way biologically and linguistically driven computing paradigms are made. In the last few decades, they have been used more and more to solve optimisation problems in the real world. Computational linguistics has its roots in linguistics, but most of the studies being done today are led by computer scientists. Data-driven and machine-learning methods have become more popular than handwritten language rules, which shows this shift. This study uses a new method called Computational Linguistics-based mood Analysis using Enhanced Beetle Antenna Search with deep learning (CLSA-EBASDL) to tackle the important problem of mood analysis during the COVID-19 pandemic. We sought to determine how people felt about the COVID-19 pandemic by studying social media texts. The method is made up of three main steps. First, data pre-processing changes raw data into a shape that can be used. After that, word embedding is done using the 'bi-directional encoder representations of transformers (BERT) process. An attention-based bidirectional long short-term memory (ABiLSTM) network is at the heart of mood classification. The Enhanced Beetle Antenna Search (EBAS) method, in particular, fine-tunes hyperparameters so that the ABiLSTM model works at its best. Many tests show that the CLSA-EBASDL method works better than others. Comparative studies show that it works, making it the best method for analysing opinion during the COVID-19 pandemic.

Automated tuning of denoising algorithms for noise removal in chromatograms

Different algorithms, such as the Savitzky-Golay filter and Whittaker smoother, have been proposed to improve the quality of experimental chromatograms. These approaches avoid excessive noise from hampering data analysis and as such allow an accurate detection and quantification of analytes. These algorithms require fine-tuning of their hyperparameters to regulate their roughness and flexibility. Traditionally, this fine-tuning is done manually until a signal is obtained that removes the noise while conserving valuable peak information. More objective and automated approaches are available, but these are usually method specific and/or require previous knowledge. In this work, the L-and V-curve, k-fold cross-validation, autocorrelation function and residual variance estimation approach are introduced as alternative automated and generally applicable parameter tuning methods. These methods do not require any previous information and are compatible with a multitude of denoising methods. Additionally, for k-fold cross-validation, autocorrelation function and residual variance estimation, a novel implementation based on median estimators is proposed to handle the specific shape of chromatograms, typically composed of alternating flat baselines and sharp peaks. These tuning methods are investigated in combination with four denoising methods; the Savitsky-Golay filter, Whittaker smoother, sparsity assisted signal smoother and baseline estimation and denoising using sparsity approach. It is demonstrated that the median estimators approach significantly improves the denoising and information conservation performance of relevant smoother-tuner combinations up to a factor 4 for simulated datasets and even up to a factor 10 for an experimental chromatogram. Moreover, the parameter tuning methods relying on residual variance estimation, k-fold cross-validation and autocorrelation function lead to similar small root-mean squared errors on the different simulated datasets and experimental chromatograms. The sparsity assisted signal smoother and baseline estimation and denoising using sparsity approach, which both rely on the use of sparsity, systematically outperform the two other methods and are hence most appropriate for chromatograms.

Design and parameter tuning of active disturbance rejection control for uncertain multivariable systems via quantitative feedback theory

This paper proposes a new parameter tuning approach for active disturbance rejection control (ADRC) of multi-input multi-output (MIMO) uncertain systems. Firstly, decentralized ADRC (DADRC), dynamic decoupling ADRC (DD-ADRC), and inverted decoupling ADRC (ID-ADRC) are introduced. Three control schemes are uniformly transformed into a two-degree-of-freedom (2DOF) equivalent structure for analysis. Then, a parameter tuning approach based on multivariable quantitative feedback theory (QFT) is proposed to achieve the desired performance. Considering the coupling effects, the QFT performance specifications are reformulated to reduce the conservatism in design, and the closed-loop stability conditions are studied to establish the robust stability performance specification. Finally, the control schemes and the proposed tuning approach are applied to a heat integrated distillation column (HIDiC) process. The effectiveness of the parameter tuning approach is verified, and the respective advantages of the ADRC control schemes are analyzed in parameter tuning and simulations.

Machine learning and the quest for objectivity in climate model parameterization

Parameterization and parameter tuning are central aspects of climate modeling, and there is widespread consensus that these procedures involve certain subjective elements. Even if the use of these subjective elements is not necessarily epistemically problematic, there is an intuitive appeal for replacing them with more objective (automated) methods, such as machine learning. Relying on several case studies, we argue that, while machine learning techniques may help to improve climate model parameterization in several ways, they still require expert judgment that involves subjective elements not so different from the ones arising in standard parameterization and tuning. The use of machine learning in parameterizations is an art as well as a science and requires careful supervision.

Generative adversarial network with radiomic feature reproducibility analysis for computed tomography denoising

BACKGROUND

Most computed tomography (CT) denoising algorithms have been evaluated using image quality analysis (IQA) methods developed for natural image, which do not adequately capture the texture details in medical imaging. Radiomics is an emerging image analysis technique that extracts texture information to provide a more objective basis for medical imaging diagnostics, overcoming the subjective nature of traditional methods. By utilizing the difficulty of reproducing radiomics features under different imaging protocols, we can more accurately evaluate the performance of CT denoising algorithms.

METHOD

We introduced radiomic feature reproducibility analysis as an evaluation metric for a denoising algorithm. Also, we proposed a low-dose CT denoising method based on a generative adversarial network (GAN), which outperformed well-known CT denoising methods.

RESULTS

Although the proposed model produced excellent results visually, the traditional image assessment metrics such as peak signal-to-noise ratio and structural similarity failed to show distinctive performance differences between the proposed method and the conventional ones. However, radiomic feature reproducibility analysis provided a distinctive assessment of the CT denoising performance. Furthermore, radiomic feature reproducibility analysis allowed fine-tuning of the hyper-parameters of the GAN.

CONCLUSION

We demonstrated that the well-tuned GAN architecture outperforms the well-known CT denoising methods. Our study is the first to introduce radiomics reproducibility analysis as an evaluation metric for CT denoising. We look forward that the study may bridge the gap between traditional objective and subjective evaluations in the clinical medical imaging field.

Hybridization of long short-term memory with Sparrow Search Optimization model for water quality index prediction

Water quality (WQ) analysis is a critical stage in water resource management and should be handled immediately in order to control pollutants that could have a negative influence on the ecosystem. The dramatic increase in population, the use of fertilizers and pesticides, and the industrial revolution have resulted in severe effects on the WQ environment. As a result, the prediction of WQ greatly helped to monitor water pollution. Accurate prediction of WQ is the foundation of managing water environments and is of high importance for protecting water environment. WQ data presents in the form of multi-variate time-sequence dataset. It is clear that the accuracy of predicting WQ will be enhanced when the multi-variate relation and time sequence dataset of WQ are fully utilized. This article presents the Water Quality Prediction utilising Sparrow Search Optimization with Hybrid Long Short-Term Memory (WQP-SSHLSTM) model. The presented WQP-SSHLSTM model intends to examine the data and classify WQ into distinct classes. To achieve this, the presented WQP-SSHLSTM model undergoes data scaling process to scale the input data into uniform format. Followed by, a hybrid long short-term memory-deep belief network (LSTM-DBN) technique is employed for the recognition and classification of WQ. Moreover, Sparrow search optimization algorithm (SSOA) is utilized as a hyperparameter optimizer of the proposed DBN-LSTM model. For demonstrating the enhanced outcomes of the presented WQP-SSHLSTM model, a sequence of experiments has been performed and the outcomes are reviewed under distinct prospects. The WQP-SSHLSTM model has achieved 99.84 percent accuracy, which is the maximum attainable. The simulation outcomes ensured the enhanced outcomes of the WQP-SSHLSTM model on recent methods.

Deep Learning-Based Model for Financial Distress Prediction

Predicting bankruptcies and assessing credit risk are two of the most pressing issues in finance. Therefore, financial distress prediction and credit scoring remain hot research topics in the finance sector. Earlier studies have focused on the design of statistical approaches and machine learning models to predict a company's financial distress. In this study, an adaptive whale optimization algorithm with deep learning (AWOA-DL) technique is used to create a new financial distress prediction model. The goal of the AWOA-DL approach is to determine whether a company is experiencing financial distress or not. A deep neural network (DNN) model called multilayer perceptron based predictive and AWOA-based hyperparameter tuning processes are used in the AWOA-DL method. Primarily, the DNN model receives the financial data as input and predicts financial distress. In addition, the AWOA is applied to tune the DNN model's hyperparameters, thereby raising the predictive outcome. The proposed model is applied in three stages: preprocessing, hyperparameter tuning using AWOA, and the prediction phase. A comprehensive simulation took place on four datasets, and the results pointed out the supremacy of the AWOA-DL method over other compared techniques by achieving an average accuracy of 95.8%, where the average accuracy equals 93.8%, 89.6%, 84.5%, and 78.2% for compared models.

Stability analysis based parameter tuning of Social Group Optimization

Swarm-based optimization algorithms have been popularly used these days for optimization of various real world problems but sometimes it becomes hard to estimate the associated characteristics due to their stochastic nature. To ensure a steady performance of these techniques, it is essential to have knowledge about the range of variables, in which a particular algorithm always provides stable performance and performing stability analysis of an algorithm can help in providing some knowledge regarding the same. Many researchers have performed the stability analysis of several optimization algorithms and analyzed their behavior. Social Group Optimization (SGO) is a newly developed algorithm which has been proven to yield promising results when applied to many real world problems but in literature no work can be found on stability analysis of SGO. In this paper, Von Neumann stability analysis approach has been used for performing stability analysis of Social Group Optimization (SGO) to analyze the behavior of its algorithmic parameters and estimate the range in which they always give stable convergence. The results obtained have been supported by sufficient experimental analysis and simulated using eight benchmark function suite along with their shifted and rotated variations which prove that the algorithm performs better within the stable range and hence convergence is ensured.

Multi-order cascade lag control for high precision tracking systems

Error attenuation capacity of a target tracking system is the key indicator for the system's tracking precision. Without changing the system's feedback control structure, the traditional first order integral control, which is widely used in traditional tracking systems, cannot meet a higher precision for those fast targets with high mobility. The work described in this paper concerns about this problem, and proposes a cascade lag control scheme with one or more order to level up the system's active error suppression capacity in low-frequency range. By substituting the cascade lag controllers for additional integral operator, a higher amplitude ratio system, which implies higher tracking precision, is obtained without loss of stability. As a difficult task for massive parameters' designing, a concept of relative order and a configuration proportion law is proposed to simplify the analysis as well as parameters tuning. Relationship between the relative order and system performance is given. The multi-order cascade lag control scheme's efficiency is proved in both theoretical analysis and experiments in an electro-optical tracking system.

High-performance state feedback controller for permanent magnet synchronous motor

Due to the outstanding characteristics of permanent magnet synchronous motor (PMSM), such as fast response speed, high torque and power density, it has been widely used in the automation industry. However, it remains a challenge to obtain high control performance caused by its dynamic complexity. In order to achieve favorable control performance, a novel state feedback control algorithm and parameter tuning method for permanent magnet synchronous motor is proposed in this paper. The development of the presented control method starts with the analyses of current state-space equation in rotor reference frame and then provides the design procedure of state feedback controller from the first-order to third-order system. An enhanced Proportional-Integral (PI) plus state feedback controller is designed, which includes the information of current, the error of current and the integral of the current error. The stability and convergence of the proposed control approach, as the extension of the conventional PI regulator, is mathematically justified in state feedback theory. The simulation and experimental results compared with the classical state feedback control method illustrate that the proposed PI plus state feedback control scheme can obtain better control performance in the presence of parameter changes and disturbance.

Tuning of linear active disturbance rejection controllers for second-order underdamped systems with time delay

Second-order plus dead-time systems are difficult to tune for a PID controller due to its special structure, especially the underdamped systems that have oscillatory responses. As a control technique with strong disturbance rejection ability, linear active disturbance rejection control is widely used as a substitute for PID controllers. This paper proposes a tuning formula for second-order linear active disturbance rejection control for underdamped second-order plus dead-time systems via internal model control. The formula is derived by minimizing the integral of time squared error index under certain robustness measure condition. Simulation results show that the linear active disturbance rejection controller tuned from the proposed formula can achieve satisfactory control performance for oscillatory systems.

Improving the estimation of alpine grassland fractional vegetation cover using optimized algorithms and multi-dimensional features

BACKGROUND

Fractional vegetation cover (FVC) is an important basic parameter for the quantitative monitoring of the alpine grassland ecosystem on the Qinghai-Tibetan Plateau. Based on unmanned aerial vehicle (UAV) acquisition of measured data and matching it with satellite remote sensing images at the pixel scale, the proper selection of driving data and inversion algorithms can be determined and is crucial for generating high-precision alpine grassland FVC products.

METHODS

This study presents estimations of alpine grassland FVC using optimized algorithms and multi-dimensional features. The multi-dimensional feature set (using original spectral bands, 22 vegetation indices, and topographical factors) was constructed from many sources of information, then the optimal feature subset was determined based on different feature selection algorithms as the driving data for optimized machine learning algorithms. Finally, the inversion accuracy, sensitivity to sample size, and computational efficiency of the four machine learning algorithms were evaluated.

RESULTS

(1) The random forest (RF) algorithm (R2: 0.861, RMSE: 9.5%) performed the best for FVC inversion among the four machine learning algorithms driven by the four typical vegetation indices. (2) Compared with the four typical vegetation indices, using multi-dimensional feature sets as driving data obviously improved the FVC inversion accuracy of the four machine learning algorithms (R2 of the RF algorithm increased to 0.890). (3) Among the three variable selection algorithms (Boruta, sequential forward selection [SFS], and permutation importance-recursive feature elimination [PI-RFE]), the constructed PI-RFE feature selection algorithm had the best dimensionality reduction effect on the multi-dimensional feature set. (4) The hyper-parameter optimization of the machine learning algorithms and feature selection of the multi-dimensional feature set further improved FVC inversion accuracy (R2: 0.917 and RMSE: 7.9% in the optimized RF algorithm).

CONCLUSION

This study provides a highly precise, optimized algorithm with an optimal multi-dimensional feature set for FVC inversion, which is vital for the quantitative monitoring of the ecological environment of alpine grassland.

Automatic configuration of the Cassandra database using irace

Database systems play a central role in modern data-centered applications. Their performance is thus a key factor in the efficiency of data processing pipelines. Modern database systems expose several parameters that users and database administrators can configure to tailor the database settings to the specific application considered. While this task has traditionally been performed manually, in the last years several methods have been proposed to automatically find the best parameter configuration for a database. Many of these methods, however, use statistical models that require high amounts of data and fail to represent all the factors that impact the performance of a database, or implement complex algorithmic solutions. In this work we study the potential of a simple model-free general-purpose configuration tool to automatically find the best parameter configuration of a database. We use the irace configurator to automatically find the best parameter configuration for the Cassandra NoSQL database using the YCBS benchmark under different scenarios. We establish a reliable experimental setup and obtain speedups of up to 30% over the default configuration in terms of throughput, and we provide an analysis of the configurations obtained.

Tuning of linear active disturbance rejection controller with robustness specification

Active disturbance rejection control (ADRC) treats all the model uncertainties and all the external disturbances as a generalized disturbance. It uses an extended state observer (ESO) to estimate the generalized disturbance in real time, and compensate it using a state-feedback control law, thus can achieve good disturbance rejection performance. For linear ADRC (LADRC), the parameters can be tuned via the bandwidths of the ESO and the feedback control, thus an LADRC can be regarded as a fixed-structured controller with several parameters to tune, just like a PID controller. To help tuning the parameters of LADRC, a tuning rule is proposed in this paper, with the aim to minimize the load disturbance attenuation performance in the integral of time square error sense, under the constraint of a specified robustness measure for the first-order processes with deadtime. The tuning rule is tested for a variety of benchmark systems and the gravity drained tanks case, and the performances are compared with the well-known PID tuning methods.

Investigating the parameter space of evolutionary algorithms

Evolutionary computation (EC) has been widely applied to biological and biomedical data. The practice of EC involves the tuning of many parameters, such as population size, generation count, selection size, and crossover and mutation rates. Through an extensive series of experiments over multiple evolutionary algorithm implementations and 25 problems we show that parameter space tends to be rife with viable parameters, at least for the problems studied herein. We discuss the implications of this finding in practice for the researcher employing EC.