Parameter Tuning Process Research Articles

An Intelligent Metaheuristic Optimization with Deep Convolutional Recurrent Neural Network Enabled Sarcasm Detection and Classification Model

Sarcasm is a state of speech in which the speaker says something that is externally unfriendly with a purpose of abusing/deriding the listener and/or a third person. Since sarcasm detection is mainly based on the context of utterances or sentences, it is hard to design a model to proficiently detect sarcasm in the domain of natural language processing (NLP). Despite the fact that various methods for detecting sarcasm have been created utilizing statistical machine learning and rule-based approaches, they are unable of discerning figurative meanings of words. The models developed using deep learning approaches have shown superior performance for sarcasm detection over traditional approaches. With this motivation, this paper develops novel deep learning (DL) enabled sarcasm detection and classification (DLE-SDC) model. The DLE-SDC technique primarily involves pre-processing stage which encompasses single character removal, multispaces removal, URL removal, stop word removal, and tokenization. Next to data preprocessing, the preprocessed data is converted into the feature vector by Glove Embeddings technique. Followed by, convolutional neural network with recurrent neural network (CNN-RNN) technique is utilized to detect and classify sarcasm. In order to boost the detection outcomes of the CNN+RNN technique, a hyper parameter tuning process utilizing teaching and learning based optimization (TLBO) algorithm is employed in such a way that the classification performance gets increased. The DLE-SDC model is validated using the benchmark dataset and the performance is examined interms of precision, recall, accuracy, and F1-score.

Improved Harmony Search with Optimal Deep Learning Enabled Classification Model

Due to drastic increase in the generation of data, it is tedious to examine and derive high level knowledge from the data. The rising trends of high dimension data gathering and problem representation necessitates feature selection process in several machine learning processes. The feature selection procedure establishes a generally encountered issue of global combinatorial optimization. The FS process can lessen the number of features by the removal of unwanted and repetitive data. In this aspect, this article introduces an improved harmony search based global optimization for feature selection with optimal deep learning (IHSFS-ODL) enabled classification model. The proposed IHSFS-ODL technique intends to reduce the curse of dimensionality and enhance classification outcomes. In addition, the IHSFS-ODL technique derives an IHSFS technique by the use of local search method with traditional harmony search algorithm (HSA) for global optimization. Besides, ODL based classifier including quantum behaved particle swarm optimization (QPSO) with gated recurrent unit (GRU) is applied for data classification process. The utilization of HSA for the choice of features and QPSO algorithm for hyper parameter tuning processes helps to accomplish maximum classification performance. In order to demonstrate the enhanced outcomes of the IHSFS-ODL technique, a series of simulations were carried out and the results reported the betterment over its recent state of art approaches.

Autonomous Unmanned Aerial Vehicles Based Decision Support System for Weed Management

Recently, autonomous systems become a hot research topic among industrialists and academicians due to their applicability in different domains such as healthcare, agriculture, industrial automation, etc. Among the interesting applications of autonomous systems, their applicability in agricultural sector becomes significant. Autonomous unmanned aerial vehicles (UAVs) can be used for suitable site-specific weed management (SSWM) to improve crop productivity. In spite of substantial advancements in UAV based data collection systems, automated weed detection still remains a tedious task owing to the high resemblance of weeds to the crops. The recently developed deep learning (DL) models have exhibited effective performance in several data classification problems. In this aspect, this paper focuses on the design of autonomous UAVs with decision support system for weed management (AUAV-DSSWM) technique. The proposed AUAV-DSSWM technique intends to identify the weeds by the use of UAV images acquired from the target area. Besides, the AUAV-DSSWM technique primarily performs image acquisition and image pre-processing stages. Moreover, the Adam optimizer with You Only Look Once Object Detector-(YOLOv3) model is applied for the detection of weeds. For the effective classification of weeds and crops, the poor and rich optimization (PRO) algorithm with softmax layer is applied. The design of Adam optimizer and PRO algorithm for the parameter tuning process results in enhanced weed detection performance. A wide range of simulations take place on UAV images and the experimental results exhibit the promising performance of the AUAV-DSSWM technique over the other recent techniques with the of 99.23%.

Automated Deep Learning Empowered Breast Cancer Diagnosis Using Biomedical Mammogram Images

Biomedical image processing is a hot research topic which helps to majorly assist the disease diagnostic process. At the same time, breast cancer becomes the deadliest disease among women and can be detected by the use of different imaging techniques. Digital mammograms can be used for the earlier identification and diagnostic of breast cancer to minimize the death rate. But the proper identification of breast cancer has mainly relied on the mammography findings and results to increased false positives. For resolving the issues of false positives of breast cancer diagnosis, this paper presents an automated deep learning based breast cancer diagnosis (ADL-BCD) model using digital mammograms. The goal of the ADL-BCD technique is to properly detect the existence of breast lesions using digital mammograms. The proposed model involves Gaussian filter based pre-processing and Tsallis entropy based image segmentation. In addition, Deep Convolutional Neural Network based Residual Network (ResNet 34) is applied for feature extraction purposes. Specifically, a hyper parameter tuning process using chimp optimization algorithm (COA) is applied to tune the parameters involved in ResNet 34 model. The wavelet neural network (WNN) is used for the classification of digital mammograms for the detection of breast cancer. The ADL-BCD method is evaluated using a benchmark dataset and the results are analyzed under several performance measures. The simulation outcome indicated that the ADL-BCD model outperforms the state of art methods in terms of different measures.

A Q‐Learning‐Based Parameters Adaptive Algorithm for Formation Tracking Control of Multi‐Mobile Robot Systems

This paper proposes an adaptive formation tracking control algorithm optimized by Q‐learning scheme for multiple mobile robots. In order to handle the model uncertainties and external disturbances, a desired linear extended state observer is designed to develop an adaptive formation tracking control strategy. Then an adaptive method of sliding mode control parameters optimized by Q‐learning scheme is employed, which can avoid the complex parameter tuning process. Furthermore, the stability of the closed‐loop control system is rigorously proved by means of matrix properties of graph theory and Lyapunov theory, and the formation tracking errors can be guaranteed to be uniformly ultimately bounded. Finally, simulations are presented to show the proposed algorithm has the advantages of faster convergence rate, higher tracking accuracy, and better steady‐state performance.

Prescribed performance based sliding mode path-following control of UVMS with flexible joints using extended state observer based sliding mode disturbance observer

The accuracy and stability of an underwater vehicle manipulator system (UVMS) are essential for performing underwater tasks. However, exogenous disturbance and unmodeled dynamics will lead to poor UVMS performance in terms of degraded transient behavior and large steady-state errors. In this paper, the path following problem with prescribed performance of a UVMS with flexible joints is addressed. First, a terminal sliding mode control scheme with prescribed performance is presented along with a novel extended state observer (ESO) based sliding mode disturbance observer (SMDO). The proposed controller simplifies the parameter tuning process by ensuring the predefined system behaviors of interest right after the design. Subsequently, a path following scheme is designed for the UVMS such that the position of both base vehicle and robot arms can converge to the specified path in 3-D space. Finally, numerical simulations and comparisons are conducted to show the effectiveness of the proposed method in terms of trajectory tracking in the presence of environmental disturbances and modeling uncertainties.

Parameters optimization of central pattern generators for hexapod robot based on multi-objective genetic algorithm

In this article, a network of central pattern generators is used for the motion planning of a hexapod robot. There are many parameters in the planning network, which determine the motion performance of the hexapod robot. On the other hand, the network is a highly nonlinear coupling network, which is difficult to obtain optimal parameters by an analytical method. Optimizing these parameters to make the robot walk well is a multi-objective optimization process. There is a certain mutual exclusion relationship among the targets. To find a well-performing network as soon as possible, a multi-objective genetic algorithm is used for the process of parameter tuning. The hexapod robot simulation model is performed in Webots, and the motion performance parameters of the robot are obtained through built-in sensors and are also considered as mean values of the optimization algorithm. The optimization algorithm is written and run with MATLAB. Finally, the optimization algorithm and simulation results are proven by an experiment.

Travel time forecasting on a freeway corridor: a dynamic information fusion model based on the random forests approach

Purpose Metropolitan areas suffer from frequent road traffic congestion not only during peak hours but also during off-peak periods. Different machine learning methods have been used in travel time prediction, however, such machine learning methods practically face the problem of overfitting. Tree-based ensembles have been applied in various prediction fields, and such approaches usually produce high prediction accuracy by aggregating and averaging individual decision trees. The inherent advantages of these approaches not only get better prediction results but also have a good bias-variance trade-off which can help to avoid overfitting. However, the reality is that the application of tree-based integration algorithms in traffic prediction is still limited. This study aims to improve the accuracy and interpretability of the models by using random forest (RF) to analyze and model the travel time on freeways. Design/methodology/approach As the traffic conditions often greatly change, the prediction results are often unsatisfactory. To improve the accuracy of short-term travel time prediction in the freeway network, a practically feasible and computationally efficient RF prediction method for real-world freeways by using probe traffic data was generated. In addition, the variables’ relative importance was ranked, which provides an investigation platform to gain a better understanding of how different contributing factors might affect travel time on freeways. Findings The parameters of the RF model were estimated by using the training sample set. After the parameter tuning process was completed, the proposed RF model was developed. The features’ relative importance showed that the variables (travel time 15 min before) and time of day (TOD) contribute the most to the predicted travel time result. The model performance was also evaluated and compared against the extreme gradient boosting method and the results indicated that the RF always produces more accurate travel time predictions. Originality/value This research developed an RF method to predict the freeway travel time by using the probe vehicle-based traffic data and weather data. Detailed information about the input variables and data pre-processing were presented. To measure the effectiveness of proposed travel time prediction algorithms, the mean absolute percentage errors were computed for different observation segments combined with different prediction horizons ranging from 15 to 60 min.

An extended analysis on tuning the parameters of Adaptive Monte Carlo Localization ROS package in an automated guided vehicle

With a growth tendency, the employment of the Adaptive Monte Carlo Localization (AMCL) Robot Operational System (ROS) package does not reflect a more in-depth discussion on its parameters’ tuning process. The authors usually do not describe it. This work aims to extend the analysis of the package’s parameters’ distinct influence in an automated guided vehicle (AGV) indoor localization. The experiments test parameters of the filter, the laser model, and the odometry model. Extending the previous analysis of seven parameters, the present research discusses another ten from the 22 configurable parameters of the package. An external visual vehicle pose tracking is used to compare the pose estimation from the localization package. Although the article does not propose the best parameter tuning, its results discuss how each tested parameter affects the localization. The paper’s contribution is discussing the parameters’ variation impact on the AGV localization using the covariance matrix results. It may help new researchers in the AMCL ROS package parameter tuning process. The results show minor changes in the default parameters which can improve the localization results, even modifying one parameter at a time.

A federated interpretable scorecard and its application in credit scoring

In this paper, we propose a vertical federated learning (VFL) structure for logistic regression with bounded constraint for the traditional scorecard, namely FL-LRBC. Under the premise of data privacy protection, FL-LRBC enables multiple agencies to jointly obtain an optimized scorecard model in a single training session. It leads to the formation of scorecard model with positive coefficients to guarantee its desirable characteristics (e.g., interpretability and robustness), while the time-consuming parameter-tuning process can be avoided. Moreover, model performance in terms of both AUC and the Kolmogorov–Smirnov (KS) statistics is significantly improved by FL-LRBC, due to the feature enrichment in our algorithm architecture. Currently, FL-LRBC has already been applied to credit business in a China nation-wide financial holdings group.

Research on Control Design on PMSG Based on LSTM

The traditional control method of permanent magnet synchronous generator (PMSG) needs multiple rounds of tuning and test to ensure the dynamic characteristics of the PMSG to reach the standard. It is complex if there are a large number of PMSGs needs to design parameters of the control loops. In order to simplify the tuning and testing process of the control parameters of the PMSG, a data-driven based control method of a PMSG is proposed in this study. It can fit the standard dynamic characteristics by learning the inputs and outputs of the standard dynamic response curves using the long short term memory LSTM method. Subsequently, the proposed control method can be applied to multiple PMSGs, which is convenient and no staff is involved. Finally, a power system connected with a PMSG is as an example. It demonstrates that the dynamic of the PMSG adopted the proposed control method is same with that of the standard PMSG.

Volumetric appearance stylization with stylizing kernel prediction network

This paper aims to efficiently construct the volume of heterogeneous single-scattering albedo for a given medium that would lead to desired color appearance. We achieve this goal by formulating it as a volumetric style transfer problem in which an input 3D density volume is stylized using color features extracted from a reference 2D image. Unlike existing algorithms that require cumbersome iterative optimizations, our method leverages a feed-forward deep neural network with multiple well-designed modules. At the core of our network is a stylizing kernel predictor (SKP) that extracts multi-scale feature maps from a 2D style image and predicts a handful of stylizing kernels as a highly non-linear combination of the feature maps. Each group of stylizing kernels represents a specific style. A volume autoencoder (VolAE) is designed and jointly learned with the SKP to transform a density volume to an albedo volume based on these stylizing kernels. Since the autoencoder does not encode any style information, it can generate different albedo volumes with a wide range of appearance once training is completed. Additionally, a hybrid multi-scale loss function is used to learn plausible color features and guarantee temporal coherence for time-evolving volumes. Through comprehensive experiments, we validate the effectiveness of our method and show its superiority by comparing against state-of-the-arts. We show that with our method a novice user can easily create a diverse set of realistic translucent effects for 3D models (either static or dynamic), neglecting any cumbersome process of parameter tuning.

Static and dynamic solar photovoltaic models’ parameters estimation using hybrid Rao optimization algorithm

Photovoltaic (PV) modeling research is a growing area of interest. The accuracy of PV models pertains to the efficient design and control of PV systems. Subsequently, several static and dynamic models were developed to emulate the course of current in PV cells. Moreover, a novel fractional order dynamic PV model has been proposed to enhance the accuracy of the conventional integral order one. The parameter estimation of these models is a challenging task. Most of the existing methods designed for handling this problem require either time-consuming parameter tuning process, or malfunction for systems exposed to environmental fluctuation. Besides, there has been a lack of researches into fractional dynamic PV models. In these circumstances, a hybrid Rao_1 Optimization Algorithm, denoted as HROA, is proposed for addressing this parameter extraction problem. Its exploration capacity is enhanced by introducing a logistic chaotic map and an exploration operator from the Generalized Normal Distribution Optimization algorithm (GNDO). Then a performance learning mechanism is employed to realize an adaptive transition between exploration and exploitation. HROA stands out by being parameter-tuning-free and efficient on a wide range of PV models. For the static models, HROA offers the best performance. A comprehensive performance analysis reveals that HROA exhibits a higher accuracy and less deviation than many recent algorithms. For the dynamic models, HROA is among the 3 best algorithms, it is capable of emulating the experimental datasets with low deviation error. The results also confirm that fractional dynamic model has better fitting effect than integral one. All the evidence suggests that HROA is a promising alternative for dealing with parameter identification problems in PV systems.

Parameter Tuning of Brushless DC Motor for Improving Control Effect with Worm Algorithm

Aiming at the problem of low control precision and small applicable scope caused by adjusting control parameters in Ziegler-Nichols (ZN) method, a parameter tuning method based on Worm algorithm (WOA) is proposed for Brushless DC motor. Firstly, the model of speed control is established by proportional integral method for Brushless DC motor with two - phase conduction and three - phase full bridge drive. Then the fitness function of the controller is constructed by the Integral Absolute Error (IAE). Finally, the early optimization process, the later movement rule and the peak extraction rule are determined for WOA, and the controller parameter tuning process is designed. Simulation results under constant and sinusoidal conditions show the effectiveness of the proposed method. WOA was compared with ZN, genetic algorithm (GA), differential evolution algorithm (DE) and particle swarm optimization algorithm (PSO) in the experiment. The experimental results show that the control effect (CE) of WOA under uniform speed has been improved by 2.56% on average, and has been improved by 16.93% on average under sinusoidal speed. Compared with previous methods, this method can be used for parameter adjustment of complex control with higher control precision.

Parameter-free optimization algorithm for iterative wavefront shaping.

Optical focusing through scattering media has a significant impact on optical applications in biological tissues. Recently, iterative wavefront shaping (WFS) has been successfully used to focus light through or inside scattering media, and various heuristic algorithms have been introduced to improve the performance. While these results are encouraging, more efforts are needed to tune parameters towards robust and optimum optimization. Moreover, optimal parameters might differ for different scattering samples and experimental conditions. In this Letter, we propose a "smart" parameter-free algorithm by combining a traditional genetic algorithm with a bat algorithm, and the mutation rate can be automatically calculated through real-time feedback. Using this method in iterative WFS, one can achieve robust and optimum performance without a parameter tuning process.

OPTIMIZATION OF K-NEAREST NEIGHBOUR TO CATEGORIZE INDONESIAN'S NEWS ARTICLES

Text classification is the process of grouping documents based on similarity in categories. Some of the obstacles in doing text classification are many words appeared in the text, and some words come up with infrequent frequency (sparse words). The way to solve this problem is to conduct the feature selection process. There are several filter-based feature selection methods; some are Chi-Square, Information Gain, Genetic Algorithm, and Particle Swarm Optimization (PSO). Aghdam's research shows that PSO is the best among those methods. This study examined PSO to optimize the k-Nearest Neighbour (k-NN) algorithm's performance in categorizing news articles. k-NN is an algorithm that is simple and easy to implement. If we use the appropriate features, then the k-NN will be a reliable algorithm. PSO algorithm is used to select keywords (term features), and it is continued with classifying the documents using k-NN. The testing process consists of three stages. The stages are tuning the parameter of k-NN, the parameter of PSO, and measuring the testing performance. The parameter tuning process aims to determine the number of neighbours used in k-NN and optimize the PSO particles. Otherwise, the performance testing compares the performance of k-NN with and without using PSO. The optimal number of neighbours is 9, with the number of particles is 50. The testing showed that using the k-NN with PSO and a 50% reduction in terms. The results 20 per cent better accuracy than k-NN without PSO. Although the PSO's process did not always find the optimal conditions, the k-NN method can produce better accuracy. In this way, the k-NN method can work better in grouping news articles, especially in Indonesian language news articles

Particle Swarm Optimization Method Based Controller Tuning for Adaptive Cruise Control Application

Major developments in relevant technology make the advanced driver assistance systems and autonomous driving functions more attainable. Thus, conventional practices being applied in vehicle production evolves towards highly automated, safer, and more comfortable vehicles. Although advanced driver assistance systems and autonomous driving functions have many advantages, such as enhanced driver convenience, increased comfort, and fuel economy; concerns related to safety still exist. For instance, failures related to sensors or algorithms being used can lead to critical problems. Therefore, controller algorithms should be more robust and well-optimized in order to eliminate these safety issues. This requires the implementation of automated optimization algorithms for the controller parameter tuning process. The main objective of this study is to optimize the designed controller for an adaptive cruise control system by using the particle swarm optimization method, which is a swarm intelligence optimization technique. Based on the results, it is observed that the use of automated optimization techniques for adaptive cruise control systems leads to better accuracy and safety for driving control. Furthermore, the time consumed for the controller parameter tuning process is also decreased significantly. In conclusion, the adaptive cruise control system requirements can be easily and accurately ensured by the use of particle swarm optimization algorithm.

Fuzzy Adaptive Charged System Search for global optimization

This study proposes a new fuzzy adaptive Charged System Search (CSS) for global optimization. The suggested algorithm includes a parameter tuning process based on fuzzy logic with the aim of improving its performance. In this regard, four linguistic variables are defined which configures a fuzzy system for parameter identification of the standard CSS algorithm. This process provides a focus for the algorithm on higher levels of global searching in the initial iterations while the local search is considered in the last iterations. Twenty mathematical benchmark functions, the Competitions on Evolutionary Computation (CEC) regarding CEC 2020 benchmark, three well-known constrained, and two engineering problems are utilized to validate the new algorithm. Moreover, the performance of the new algorithm is compared and contrasted with other metaheuristic algorithms. The obtained results reveal the superiority of the proposed approach in dealing with different unconstraint, constrained, and engineering design problems.

Parameter tuning process for a closed-loop pneumatic actuator

Pneumatic drives are light weight, small-sizes, simple to install and to maintain. Pneumatic drives have a robust design and operation. They are clean and cheap, have no temperature limitation, and so, they are preferred in many branches of manufacturing and process industry. The well-known pneumatic actuators are widely used in closed-loop positioning systems because of their dynamic performance and mechanical flexibility in different electro-mechanical systems arrangements. The goal of the paper is to find the parameters of a closed-loop pneumatic actuator so that a good dynamic behaviour of the system is obtained. The parametric tuning process is developed by using numerical simulation technique. So, it was seen that using a proportional controller, the pneumatic actuator has an asymptotic stability for different values of the proportional gain K p . Starting with K p = 8 the system remains stable, but oscillations of low amplitude appears.

Decoupling Control of Cascaded Power Electronic Transformer Based on Feedback Exact Linearization

This article addresses the decoupling control design for the cascaded power electronic transformer (PET) in input-series–output-parallel connection. Due to the coupling and interaction between the submodules and between substages, in essence it is a complex nonlinear system. A nonlinear control strategy based on feedback exact linearization (FEL) is developed to decouple all the control objectives so as to realize the dc-link and output voltages fast stabilizing and the submodule balancing without coupling and interactions. Based on the separation of the ac current time-scale and dc voltage time-scale, the FEL control law is derived, and the specific tuning process of control parameters is given for desired control bandwidths. Taken the dynamic influences of the current-loop, filter, and delay into account, further analyses are made and compared with a dual active bridge (DAB) balancing control-based strategy to show the improvement on decoupling effect and dynamic performance of the proposed control. Finally, the simulation and experimental results verify the theoretical analysis, which exhibit better dynamic features and minimal coupling effect under the condition of bidirectional power changes and parameter inconsistency and uncertainty.