Development and Performance Analysis of Fireworks Algorithm-Trained Artificial Neural Network (FWANN)

Financial time series are highly nonlinear and their movement is quite unpredictable. Artificial neural networks (ANN) have ample applications in financial forecasting. Performance of ANN models mainly depends upon its training. Though gradient descent-based methods are common for ANN training, they have several limitations. Fireworks algorithm (FWA) is a recently developed metaheuristic inspired from the phenomenon of fireworks explosion at night, which poses characteristics such as faster convergence, parallelism, and finding the global optima. This chapter intends to develop a hybrid model comprising FWA and ANN (FWANN) used to forecast closing prices series, exchange series, and crude oil prices time series. The appropriateness of FWANN is compared with models such as PSO-based ANN, GA-based ANN, DE-based ANN, and MLP model trained similarly. Four performance metrics, MAPE, NMSE, ARV, and R2, are considered as the barometer for evaluation. Performance analysis is carried out to show the suitability and superiority of FWANN.

Transmitter Positioning of Distributed Large-Scale Metrology Within Line-Less Mobile Assembly Systems

In Line-less Mobile Assembly Systems (LMAS) the mobilization of assembly resources and products enables rapid physical system reconfigurations to increase flexibility and adaptability. The clean-floor approach discards fixed anchor points, so that assembly resources such as mobile robots and automated guided vehicles transporting products can adapt to new product requirements and form new assembly processes without specific layout restrictions. An associated challenge is spatial referencing between mobile resources and product tolerances. Due to the missing fixed points, there is a need for more positioning data to locate and navigate assembly resources. Distributed large-scale metrology systems offer the capability to cover a wide shop floor area and obtain positioning data from several resources simultaneously with uncertainties in the submillimeter range. The positioning of transmitter units of these systems becomes a demanding task taking visibility during dynamic processes and configuration-dependent measurement uncertainty into account. This paper presents a novel approach to optimize the position configuration of distributed large-scale metrology systems by minimizing the measurement uncertainty for dynamic assembly processes. For this purpose, a particle-swarm-optimization algorithm has been implemented. The results show that the algorithm is capable of determining suitable transmitter positions by finding global optima in the assembly station search space verified by applying brute-force method in simulation.

Mass Integration for Rigorous Process Modelling: A Sequential Approach for Direct Recycling

Mass integration has been used for reducing the amount of process waste and environmental impact. Despite its long history, new challenges constantly arise with the use of process simulation tools offering platforms for rigorous process models. Therefore, the typical mass integration framework requires modifications to accurately account for the process performance. In this work, a novel sequential methodology is presented to realize a recycle network with rigorous process models. Initially, under the hypothesis of constant compositions of the process sources, an optimal ranking of the process sinks is determined. The optimal recycling network thus obtained is then used for a sequential methodology considering rigorous process models. The violations of process constraints are handled at each sequential step through the concept of “tightening constant”. The application of the sequential methodology to two case studies proves its ability to provide good approximations of the global optima with low computational effort.

Algorithms for Bidding Strategies in Local Energy Markets: Exhaustive Search through Parallel Computing and Metaheuristic Optimization

The integration of different energy resources from traditional power systems presents new challenges for real-time implementation and operation. In the last decade, a way has been sought to optimize the operation of small microgrids (SMGs) that have a great variety of energy sources (PV (photovoltaic) prosumers, Genset CHP (combined heat and power), etc.) with uncertainty in energy production that results in different market prices. For this reason, metaheuristic methods have been used to optimize the decision-making process for multiple players in local and external markets. Players in this network include nine agents: three consumers, three prosumers (consumers with PV capabilities), and three CHP generators. This article deploys metaheuristic algorithms with the objective of maximizing power market transactions and clearing price. Since metaheuristic optimization algorithms do not guarantee global optima, an exhaustive search is deployed to find global optima points. The exhaustive search algorithm is implemented using a parallel computing architecture to reach feasible results in a short amount of time. The global optimal result is used as an indicator to evaluate the performance of the different metaheuristic algorithms. The paper presents results, discussion, comparison, and recommendations regarding the proposed set of algorithms and performance tests.

True power loss reduction by mountain zebra, augmented bat and improved kidney search algorithms

<p>In this paper optimal reactive power problem is solved by mountain zebra algorithm (MZA), augmented bat algorithm (AB) and improved kidney search (IKS) algorithm. In the proposed algorithm, an intermediate state has been established at first, and then explores the intermediate state in order to obtain the global optima. Iterative local search implemented in this proposed algorithm. This technique enhances the search procedure in rapid mode. Then in this work, IKS algorithm has been proposed for solving optimal reactive power problem. In initial phase, a random population of probable solutions is created and re-absorption, secretion, excretion are imitated in the search process to check various conditions entrenched to the algorithm. The algorithm has been built to advance the search even a potential solution moved to waste (W) and it will be brought back to the filtered blood (FB). Glomerular filtration rate (GFR) test is utilized to verify the fitness of kidneys. Better efficiency of the proposed MZA, AB and IKS algorithm confirmed by successful evaluation in standard IEEE 14-bus, 118-bus, and 300-bus test systems. The results show that active power loss has been reduced.</p><p> </p>

BESA: BERT-based Simulated Annealing for Adversarial Text Attacks

Modern Natural Language Processing (NLP) models are known immensely brittle towards text adversarial examples. Recent attack algorithms usually adopt word-level substitution strategies following a pre-computed word replacement mechanism. However, their resultant adversarial examples are still imperfect in achieving grammar correctness and semantic similarities, which is largely because of their unsuitable candidate word selections and static optimization methods. In this research, we propose BESA, a BERT-based Simulated Annealing algorithm, to address these two problems. Firstly, we leverage the BERT Masked Language Model (MLM) to generate contextual-aware candidate words to produce fluent adversarial text and avoid grammar errors. Secondly, we employ Simulated Annealing (SA) to adaptively determine the word substitution order. The SA provides sufficient word replacement options via internal simulations, with an objective to obtain both a high attack success rate and a low word substitution rate. Besides, our algorithm is able to jump out of local optima with a controlled probability, making it closer to achieve the best possible attack (i.e., the global optima). Experiments on five popular datasets manifest the superiority of BESA compared with existing methods, including TextFooler, BAE, BERT-Attack, PWWS, and PSO.

Robust Orthogonal-View 2-D/3-D Rigid Registration for Minimally Invasive Surgery

Intra-operative target pose estimation is fundamental in minimally invasive surgery (MIS) to guiding surgical robots. This task can be fulfilled by the 2-D/3-D rigid registration, which aligns the anatomical structures between intra-operative 2-D fluoroscopy and the pre-operative 3-D computed tomography (CT) with annotated target information. Although this technique has been researched for decades, it is still challenging to achieve accuracy, robustness and efficiency simultaneously. In this paper, a novel orthogonal-view 2-D/3-D rigid registration framework is proposed which combines the dense reconstruction based on deep learning and the GPU-accelerated 3-D/3-D rigid registration. First, we employ the X2CT-GAN to reconstruct a target CT from two orthogonal fluoroscopy images. After that, the generated target CT and pre-operative CT are input into the 3-D/3-D rigid registration part, which potentially needs a few iterations to converge the global optima. For further efficiency improvement, we make the 3-D/3-D registration algorithm parallel and apply a GPU to accelerate this part. For evaluation, a novel tool is employed to preprocess the public head CT dataset CQ500 and a CT-DRR dataset is presented as the benchmark. The proposed method achieves 1.65 ± 1.41 mm in mean target registration error(mTRE), 20% in the gross failure rate(GFR) and 1.8 s in running time. Our method outperforms the state-of-the-art methods in most test cases. It is promising to apply the proposed method in localization and nano manipulation of micro surgical robot for highly precise MIS.

Chaotic Fitness Dependent Optimizer for Planning and Engineering Design

Fitness Dependent Optimizer (FDO) is a recent metaheuristic algorithm that mimics the reproduction behavior of the bee swarm in finding better hives. This algorithm is similar to Particle Swarm Optimization (PSO) but it works differently. The algorithm is very powerful and has better results compared to other common metaheuristic algorithms. This paper aims at improving the performance of FDO, thus, the chaotic theory is used inside FDO to propose Chaotic FDO (CFDO). Ten chaotic maps are used in the CFDO to consider which of them are performing well to avoid local optima and finding global optima. New technic is used to conduct population in specific limitation since FDO technic has a problem to amend population. The proposed CFDO is evaluated by using 10 benchmark functions from CEC2019. Finally, the results show that the ability of CFDO is improved. Singer map has a great impact on improving CFDO while the Tent map is the worst. Results show that CFDO is superior to GA, FDO, and CSO. Both CEC2013 and CEC2005 are used to evaluate CFDO. Finally, the proposed CFDO is applied to classical engineering problems, such as pressure vessel design and the result shows that CFDO can handle the problem better than WOA, GWO, FDO, and CGWO. Besides, CFDO is applied to solve the task assignment problem and then compared to the original FDO. The results prove that CFDO has better capability to solve the problem.