In this paper, an improved bat optimization algorithm to solve sports video was proposed, which presented the concept of adjustment sequence to design the strategy of local searching, and added the maneuver flight in ...
详细信息
ISBN:
(纸本)9781510821934
In this paper, an improved bat optimization algorithm to solve sports video was proposed, which presented the concept of adjustment sequence to design the strategy of local searching, and added the maneuver flight in the global exchange of information. Experimental results indicate that, the proposed algorithm has more powerful search capability and more strong robustness in solving sports video.
Visual cryptography is a cryptographic technique that allows visual information to be encrypted so that the human optical system can perform the decryption without any cryptographic computation. The halftone visual cr...
详细信息
Visual cryptography is a cryptographic technique that allows visual information to be encrypted so that the human optical system can perform the decryption without any cryptographic computation. The halftone visual cryptography scheme (HVCS) is a type of visual cryptography (VC) that encodes the secret image into halftone images to produce secure and meaningful shares. However, the HVC scheme has many unsolved problems, such as pixel expansion, low contrast, cross-interference problem, and difficulty in managing share images. This article aims to enhance the visual quality and avoid the problems of cross-interference and pixel expansion of the share images. It introduces a novel optimization of color halftone visual cryptography (OCHVC) scheme by using two proposed techniques: hash codebook and construction techniques. The new techniques distribute the information pixels of a secret image into a halftone cover image randomly based on a bat optimization algorithm. The results show that these techniques have enhanced security levels and make the proposed OCHVC scheme more robust against different attacks. The OCHVC scheme achieves mean squared error (MSE) of 95.0%, peak signal-to-noise ratio (PSNR) of 28.3%, normalized cross correlation (NCC) of 99.4%, and universal quality index (UQI) of 99.3% on average for the six shares. Subsequently, the experiment results based on image quality metrics show improvement in size, visual quality, and security for retrieved secret images and meaningful share images of the OCHVC scheme. Comparing the proposed OCHVC with some related works shows that the OCHVC scheme is more effective and secure.
In the framework of fuel reduction and energy conservation, the electric vehicles (EV's) has been identified as a promising option in contrast to fuel-driven vehicles. EV's battery limits to require visiting a...
详细信息
In the framework of fuel reduction and energy conservation, the electric vehicles (EV's) has been identified as a promising option in contrast to fuel-driven vehicles. EV's battery limits to require visiting a greater number of times to the recharging stations, which must be viewed as in the route planning to keep away from inefficient vehicle routes with lengthy diversions. These problems have to consider, we propose an Efficient Electric Vehicle Route optimization with Time-of-Use Electricity Pricing using batalgorithm. Which can reduce the used vehicles as well as electricity-cost and total travel distance. Additionally, functional model and collective models are used to minimize the objectives: distance and cost. The computational assessment in light of the notable benchmarking test instances exhibits, proposed optimizationalgorithm electricity cost conservation on average 12.17% with Learnable Partheno-Genetic algorithm (Yang et al. in IEEE Trans Smart Grid 6:657-666, 2015) 8.45% with VNS/TS algorithm (Lin et al. in Trans Res Part-C 130:103285, 2021) and 5.15% with Mixed Integer Programming model (Ham and Park in IEEE Access 9:37220-37228, 2021).
Due to the fact that a huge amount of energy consumption takes place in today's city buildings, particularly in modern countries, this ought to be highlighted as one of the world's important issues, which will...
详细信息
Due to the fact that a huge amount of energy consumption takes place in today's city buildings, particularly in modern countries, this ought to be highlighted as one of the world's important issues, which will raise the requirement for developing a variety of evaluation methods so as to advance an optimal predictive device for consuming energies efficiently in buildings. On the one hand, Internet of Things (IoT) and its characteristics are the most popular research areas in real-life applications at present. On the other hand, machine learning (ML) techniques significantly has improved the Internet of things (IoT)'s capability to control energy consumption. To this end, this study, firstly, evaluated five models' performance in terms of predicting IoT-oriented energy consumption by dividing the studied dataset into 80% train and 20% test. The involved ML models were Adaptive Boosting, Histogram-based Gradient Boosting Machine (HistGBM), K-Nearest Neighbors, Light Gradient Boosting Machine, Extreme Gradient Boosting. The contrastive investigation of the applied models' evaluation metric criteria demonstrated the supremacy of HistGBM model before optimization process, with the highest R-2 and the lowest RMSE. For further investigation, we tuned the parameters of the abovementioned models with bat optimization algorithm (BOA) for IoT-based energy consumption forecast in city buildings. The results are then examined for the opted model's hyperparameters using the optimization techniques, obtaining the most accurate and reliable hybrid model. The results confirm that the proposed hybrid BOA-XGBoost approach significantly improves the efficiency of the ML methods' forecasting. In particular, the achieved highest R-2 values by 0.9999 and 0.9979, respectively as well as the lowest RMSE of 0.34 and 4.70 for both training and testing dataset in building energy consumption prediction proved that the hybrid BOA-XGBoost model outperform the other models. The spent testing time f
Reinforced concrete (RC) shear walls play a pivotal role in resisting seismic and lateral loads within structural frameworks. A thorough examination of the existing literature was undertaken, covering a range of exper...
详细信息
Reinforced concrete (RC) shear walls play a pivotal role in resisting seismic and lateral loads within structural frameworks. A thorough examination of the existing literature was undertaken, covering a range of experimental and theoretical studies related to the design of RC shear walls. It was emphasized that comprehending shear failure behavior and precisely predicting the shear strength of RC walls holds considerable significance. To address this, the study proposes two models that integrate the support vector regression method with meta-heuristic optimizationalgorithms (bat and GOA), utilizing 228 sets of experimental data. In identifying the parameters influencing the shear strength of RC shear walls, the study focused on eight influential factors. The comparison of the two proposed models in the current research with existing models and experimental data demonstrated their commendable accuracy, surpassing the performance of suggested empirical formulations. The prediction errors associated with the proposed models, when compared to experimental data, were notably low. An innovative approach was introduced in the research, presenting a novel method for predicting shear strength using the support vector regression method and the bat optimization algorithm. A notable advantage of this formulation lies in its capacity to predict the shear strength across various configurations, including squat, cylindrical, and thin RC shear walls. Unlike some existing equations for predicting shear strength, this formulation exhibits no limitations. Through a comparative analysis with established equations, the computational framework's results suggest its successful applicability in building codes and construction practices. The proposed method contributes to the accurate prediction of shear strength in diverse RC shear wall configurations, offering a valuable tool for structural engineering applications.
This research paper presents a comprehensive thermodynamic and heat transfer study on predicting the ternary solubility of Nystatin in SC-CO2-Ethanol (supercritical CO2 and ethanol). The employed process is a thermal-...
详细信息
This research paper presents a comprehensive thermodynamic and heat transfer study on predicting the ternary solubility of Nystatin in SC-CO2-Ethanol (supercritical CO2 and ethanol). The employed process is a thermal-based green processing for preparation of solid nanoparticles. The data collection, consisting of temperature and pressure as input features and ternary solubility as the target variable, was used to train and evaluate four different machine learning algorithms: Random Forest (RF), Extra Trees (ET), NU-SVR, and EPSILON-SVR. The hyper-parameter tuning process employed the bat optimization algorithm (BA), a nature-inspired optimization technique to fine-tune the models and enhance their predictive capabilities. The ET model had a notable R2 score of 0.98526, RMSE of 2.48774E-02, and MAE of 2.13417E-02. The RF model also yielded strong performance, achieving an R2 score of 0.98436, RMSE of 2.55130E-02, and MAE of 2.06314E-02. However, the NU-SVR model exhibited superior performance compared to other models, as evidenced by its remarkable R2 score of 0.99943, thereby showcasing its exceptional precision. The RMSE and MAE for NU-SVR were 4.92372E-03 and 3.94943E-03, respectively, underscoring its precision in predicting ternary solubility. The EPSILON-SVR model, while still respectable, obtained a score of 0.93574 in terms of R2, RMSE of 4.37434E-02, and MAE of 3.79800E-02.
The current study considers numerous renewable energy resources, distributed power generation units, energy storage, and plug-in hybrid electric vehicles (PHEV) in order to propose a reliable large-scale energy manage...
详细信息
The current study considers numerous renewable energy resources, distributed power generation units, energy storage, and plug-in hybrid electric vehicles (PHEV) in order to propose a reliable large-scale energy management framework that can be applied to islanded and grid-connected operations of renewable hybrid AC-DC microgrids (MGs). The framework uses a bat optimization algorithm (BOA) for minimizing the operating costs of the network and in addition introduces an intrusion detection system (IDS) according to the sequential hypothesis testing (SHT) method for detecting identity-enabled cyber-attacks (i.e classification of Sybil attacks, masquerading attacks) on the wireless-enabled advanced metering infrastructures (AMI). The suggested IDS uses the received signal strength (RSS) amount for distinguishing various signal resources and detecting cyberattacks. An IEEE 33-bus testing system has been used to construct a real-time hybrid MG in order to determine the reliability and efficiency of the suggested framework.
In recent times, controllers have been widely used for tuning the biological parameters of the human body. Biological parameters play a vital role in determining the health status of the human body. Any change/differe...
详细信息
In recent times, controllers have been widely used for tuning the biological parameters of the human body. Biological parameters play a vital role in determining the health status of the human body. Any change/difference in biological components leads the person to severe diseases and even death. Therefore, an effective tuning mechanism is necessary to tune these biological parameters optimally. Several tuning models were proposed in the past based on control systems, but those models require more resources for tuning the biological parameters. Also, those models are highly complex in design and computational time. To find a solution for this described issue, a novel hybrid controller named bat-based recurrent fractional-order system has been developed in this article. The bat fitness is incorporated into the controller to provide the finest tuning outcomes. Here, the designed model tunes the biological parameters such as glucose, insulin, and gene expression. Besides, the classification layer of the recurrent neural system is tuned by the bat functions that have afforded better biological parameter prediction outcomes in a very short time. Furthermore, the developed controller is executed in a MATLAB environment, and the performance has been checked for biological data acquisition. In addition, the outcomes were evaluated based on settling time, overshoot, accuracy, and error rate;sensitivity and stability assessments were made to prove the system's performance. Furthermore, to carry the present research work further, the unstable range of the proposed model has been discussed along with the error rate. Subsequently, the executed model's outcomes were compared with the existing controller to verify the results. The implementation and comparative assessment proved that the designed controller had earned the finest tuned results. Hence, the developed model is more suitable for the biological instrumentation application for predicting and tuning the parameters to the
The creation of new approaches to the design and configuration of smart buildings relies heavily on AI tools and Machine Learning (ML) algorithms, particularly optimization techniques. The widespread use of electronic...
详细信息
Wind power prediction (WPP) is necessary to the safe operation and economic dispatch of power systems. In order to improve the prediction accuracy of WPP, in this paper we propose a three-step model named SDAE-SVR-BA ...
详细信息
Wind power prediction (WPP) is necessary to the safe operation and economic dispatch of power systems. In order to improve the prediction accuracy of WPP, in this paper we propose a three-step model named SDAE-SVR-BA to be applied in short-term WPP based on stacked-denoising-autoencoder (SDAE) feature processing, batalgorithm (BA) optimization and support vector regression (SVR). First, we preprocessed the original NWP data input into the SDAE-SVR-BA model to adapt to the training and prediction of the proposed model. Second, we input the preprocessed features into the SDAE network, whose parameters are optimized by BA to obtain the depth-mapping features. Finally, we input the features of SDAE network mapping into SVR, whose parameters are optimized by BA for prediction, so as to obtain the SDAE-SVR-BA model. In this paper, we used BA during the training process to optimize the number of hidden layers and hidden layer nodes of SDAE, the penalty factor parameter C and the kernel function radius g of the SVR model. Additionally, we verified the model with a wind farm example and compared it to the traditional model. Based on the verification data applied in this article, in a forecast for the next twelve hours, the normalized root means square error (NRMSE) of SDAE-SVR was 11.97% and the NRMSE of SDAE-SVR-BA model was 11.54%, reduced by 1.24% compared with SDAE, which demonstrates the effectiveness of the proposed method.
暂无评论