Cloud model based sine cosine algorithm for solving optimization problems Abstract Sine cosine algorithm (SCA) is a recently developed optimization technique, which uses sine function and cosine function as operators to find the global optimal solution. However, proper parameter setting is a challenging task. Only using the number of iterations to adjust the algorithm parameters cannot fully reflect the convergence information in the evolution process, so SCA lacks the adaptability in solving different optimization problems. To address this issue, a cloud model based sine cosine algorithm (CSCA) is proposed. In CSCA, the cloud model is used to adjust the control parameter adaptively while keeping SCA algorithm framework unchanged. The performance of the presented CSCA method is evaluated using 13 benchmark test functions with different dimensions. Experimental results demonstrate that the proposed algorithm is superior to other SCA variants in terms of robustness and scalability.

A direct method for solving calculus of variations problems using the whale optimization algorithm Abstract A numerical algorithm for solving problems of calculus of variations is proposed and analyzed in the present paper. The method is based on direct minimizing the functional in its discrete form with finite dimension. To solve the resulting optimization problem , the recently proposed whale optimization algorithms is used and adopted. The method proposed in this work is capable of solving constrained and unconstrained problems with fixed or free endpoint conditions. Numerical examples are given to check the validity and accuracy of the proposed method in practice. The results show the superior accuracy and efficiency of the proposed technique as compared to other numerical methods.

A new genetically optimized tensor product functional link neural network: an application to the daily exchange rate forecasting Abstract The training speed for multilayer neural networks is slow due to the multilayering. Therefore, removing the hidden layers, provided that the input layer is endowed with additional higher order units is suggested to avoid such problem. Tensor product functional link neural network (TPFLNN) is a single layer with higher order terms that extend the network’s structure by introducing supplementary inputs to the network (i.e., joint activations). Although the structure of the TPFLNN is simple, it suffers from weight combinatorial explosion problem when its order becomes excessively high. Furthermore, similarly to many neural network methods, selection of proper weights is one of the most challenging issues in the TPFLNN. Finding suitable weights could help to reduce the number of needed weights. Therefore, in this study, the genetic algorithm (GA) was used to find near-optimum weights for the TPFLNN. The proposed method is abbreviated as GA–TPFLNN. The GA–TPFLNN was used to forecast the daily exchange rate for the Euro/US Dollar, and Japanese Yen/US Dollar. Simulation results showed that the GA–TPFLNN produced more accurate forecasts as compared to the standard TPFLNN, GA, GA–TPFLNN with backpropagation, GA-functional expansion FLNN, multilayer perceptron, support vector regression, random forests for regression, and naive methods. The GA helps the TPFLNN to find low complexity network structure and/or near-optimum parameters which leads to this better result.

MASCA–PSO based LLRBFNN model and improved fast and robust FCM algorithm for detection and classification of brain tumor from MR image Abstract A novel modified adaptive sine cosine optimization algorithm (MASCA) integrated with particle swarm optimization (PSO) based local linear radial basis function neural network (LLRBFNN) model has been proposed for automatic brain tumor detection and classification. In the process of segmentation, the fuzzy C means algorithm based techniques drastically fails to remove noise from the magnetic resonance images. So, for reduction of noise and smoothening of brain tumor magnetic resonance image an improved fast and robust fuzzy c means algorithm segmentation algorithm has been proposed in this research work. The gray level co-occurrence matrix technique has been employed to extract features from brain tumor magnetic resonance images and the extracted features are fed as input to the proposed modified ASCA–PSO based LLRBFNN model for classification of benign and malignant tumors. In this research work the LLRBFNN model’s weights are optimized by using proposed MASCA–PSO algorithm which provides a unique solution to get rid of the hectic task of radiologist from manual detection. The classification accuracy results obtained from sine cosine optimization algorithm, PSO and adaptive sine cosine optimization algorithm integrated with particle swarm optimization based LLRBFNN models are compared with the proposed MASCA–PSO based LLRBFNN model. It is observed that the result obtained from the proposed model shows better classification accuracy results as compared to the other LLRBFNN based models.

UCRLF: unified constrained reinforcement learning framework for phase-aware architectures for autonomous vehicle signaling and trajectory optimization Abstract Signaling and trajectory optimization work as contention and researchers have debated on what should be the best for the vehicle, but it seems that both components are complement to each other and there can be combined situations with bounds where maximum optimization can be achieved. This paper introduces a novel approach called Phase-Aware Deep Learning and Constrained Reinforcement Learning for optimization and constant improvement of signal and trajectory for autonomous vehicle operation modules for an intersection. It deals with all the components required for the signaling system to operate, communicate and also navigate the vehicle with proper trajectory so that it faces less waiting time and the overall system operates with minimum waiting time and comparable throughput rate. We have done analysis on the operating time and the vehicle movement as these are vital for pollution and energy consumption. Our methodologies are not only efficient in time and computation but also have incorporated highly optimized data representation to reduce the overhead of maintaining and accessing the data. This ensures very efficient time complexity and theoretical computation time and better lower bounds. Constrained Reinforcement Learning concept is the main contribution of this work and it helped in decreasing 84% of the waiting time for the vehicles.

Hybrid decision trees for data streams based on Incremental Flexible Naive Bayes prediction at leaf nodes Abstract Mining data over streams in one pass and using constant memory is a challenging task. Decision trees are one of the most popular classifiers for both batch and incremental learning due to their high degree of interpretability, ease of construction and good accuracy. The most popular decision tree for stream classification is Hoeffding Tree based on Hoeffding bound. Literature shows a few variants of decision trees based on different bounds. The default class prediction method adopted in decision tree is “majority class” approach. Later, the accuracy of prediction was scaled up by a hybrid decision tree where Naive Bayes classifier was used for prediction. Kernel Density Estimation (KDE) is employed in Flexible Naive Bayes for classification. However, it is suitable for modeling static data set. This paper proposes an Incremental Flexible Naive Bayes (IFNB) based hybrid decision tree paradigm that uses KDE to model continuous attributes at leaf nodes of the tree for improving the class prediction accuracy. Experimental results on both synthetic and real dataset show that the proposed IFNB based leaf classifiers achieves improvement over the class prediction methods adopted in existing decision trees for data streams.

Multi-moth flame optimization for solving the link prediction problem in complex networks Abstract Providing a solution for the link prediction problem attracts several computer science fields and becomes a popular challenge in researches. This challenge is presented by introducing several approaches keen to provide the most precise prediction quality within a short period of time. The difficulty of the link prediction problem comes from the sparse nature of most complex networks such as social networks. This paper presents a parallel metaheuristic framework which is based on moth-flame optimization (MFO), clustering and pre-processed datasets to solve the link prediction problem. This framework is implemented and tested on a high-performance computing cluster and carried out on large and complex networks from different fields such as social, citation, biological, and information and publication networks. This framework is called Parallel MFO for Link Prediction (PMFO-LP). PMFO-LP is composed of data preprocessing stage and prediction stage. Dataset division with stratified sampling, feature extraction, data under-sampling, and feature selection are performed in the data preprocessing stage. In the prediction stage, the MFO based on clustering is used as the prediction optimizer. The PMFO-LP provides a solution to the link prediction problem with more accurate prediction results within a reasonable amount of time. Experimental results show that PMFO-LP algorithm outperforms other well-regarded algorithms in terms of error rate, the area under curve and speedup. Note that the source code of the PMFO-LP algorithm is available at https://github.com/RehamBarham/PMFO_MPI.cpp.

Gender recognition using four statistical feature techniques: a comparative study of performance Abstract Nowadays, many applications use biometric systems as a security purpose. These systems use fingerprints, iris, retina, hand geometry, etc. that have unique patterns from person to another. The human face is one of the most important organs that has many physiological characteristics such as the subject gender, race, age, and mood. Determining the gender of the face can reduce the processing time of large-scale face-based systems and may improve the performance. Many studies were proposed for gender recognition, but several were evaluated using the accuracy as a performance metric which is improper for unbalanced data. Further, they used a grayscale color; and extracted features either from the whole image or equally divided blocks, as a grid. In this paper, novel methods are proposed based on statistical features that have the ability to represent the face landmarks. These features are GIST, pyramid histogram of oriented gradients, GIST based on discrete cosine transform and principal component analysis that are extracted using face local regions. The performances are evaluated using area-under-the-curve that is computed from the receiver operating characteristic or ROC curve. At the end, the acquired performance has been compared by two state-of-the-art techniques that shows that the proposed approaches enhance the performance between 1 and 3%, but the number of features is increased.

A hybridization of cuckoo search and particle swarm optimization for solving nonlinear systems Abstract In numerical computations, one of the most strenuous problems is to solve systems of nonlinear equations. It is known that traditional numerical methods such as Newton methods and their variants require differentiability and/or good initial guess for the solutions. In practice, it will be difficult to get this initial solution and costly in term of the time to compute Jacobian. Therefore, there is a need to develop an algorithm to avoid the requirements of these traditional methods. This study proposes a new hybrid algorithm by incorporating cuckoo search (CS) with particle swarm optimization (PSO), called CSPSO, for solving systems of nonlinear equations. The goal of the hybridization between CS and PSO is to incorporate the best attributes of two algorithms together to structure a good-quality algorithm. One of the disadvantages to CS, it requires a large number of function evaluations to get the optimal solution, and to PSO, it is trapped into local minima. Our proposed hybrid algorithm attempts to overcome the disadvantages of CS and PSO. Computational experiments of nine benchmark systems of nonlinear equations and 28 benchmark functions of CEC 2013 with various dimensions are applied to test the performance of CSPSO. Computational results show that CSPSO outperforms other existing algorithms by obtaining the optimum solutions for most of the systems of nonlinear equations and 28 benchmark functions of CEC 2013, and reveals its efficacy in the comparison with other algorithms in the literature.

Optimal FOPID/PID controller parameters tuning for the AVR system based on sine–cosine-algorithm Abstract To enhance the controller performance, an advanced sine–cosine-algorithm (SCA) is employed for Fractional order PID (FOPID) controller tuning in this paper. The SCA-FOPID controller is based on model-based controller design method of physical systems to get better performance. The FOPID controller is designed by SCA optimization technique using the time domain objective function for AVR system. The SCA technique is responsible to optimize five parameters of FOPID controller based on minimum value of objective function of the controller design. The proposed SCA-FOPID controller is design at a global optimum of objective function is acheived. Then, the AVR system has good regulation of terminal voltage at the output to meet desired performance. The proposed method has a good reference tracking ability and frequency responses. This method is compared with the PID and FOPID controller designs of AVR system in the recent years, the proposed SCA-FOPID controller gives an excellent performance from the extensive simulations studies.