International Journal of Swarm Intelligence (6 papers in press)
Fractional order ant colony control with genetic algorithm assisted initialisation
by Ambreesh Kumar, Varun Upadhyaya, Ayush Singh, Paras Pandey, Rajneesh Sharma
Abstract: The task of parameter initialisation of ant colony optimisation (ACO) has gained much attention in recent years. For the systems using ACO-based control, the technique used was generally hit and trial. But in order to be able to obtain better and faster response, along with better convergence, for control of fractional order (FO) systems, it became imperative to formulate some approach. In this paper, we have used genetic algorithm (GA) to initialise the ACO parameters for a systematic design of ACO-based fractional order controllers. The GA-based ACO fractional order PID controller is developed by minimisation of a multi-objective function using a nested GA technique. The effectiveness of the method used is verified using seven FO systems. The results are compared with the controllers based on ACO and GA. The proposed GA-based ACO controller yields reasonably better performance as compare to
the existing techniques with a slight weakness of higher computational complexity. This limitation can be easily overcome by use of high performance machines.
Keywords: fractional order system; ant colony optimisation; ACO; genetic algorithm; GA-based ACO.
Special Issue on: Design, Analysis and Applications of Recent Swarm Intelligence-based Optimisation Algorithms
A comprehensive review of hidden Markov model applications in prediction of human mobility patterns
by Neha Hada, Navneet Gupta, Soniya Lalwani
Abstract: Proposed work reviews the research and development of HMM, used to find out the mobility patterns, keeping the main focus on state of the arts. Concepts related to Markov chains are explained and then the ideas are extended to the class of HMMs using several simple examples the mathematics of the HMM is presented, beginning with the Markov chain and then including the three main constituent algorithms: the Viterbi algorithm, the Forward algorithm, and the Baum-Welch or EM algorithm for unsupervised (or semi-supervised) learning. Throughout the text the description of the theory is intertwined with real-world applications.
Keywords: hidden Markov model; human mobility patterns; Viterbi algorithm; Forward algorithm; Baum-Welch algorithm.
Landmark operator inspired artificial bee colony algorithm for optimal vector control of induction motor
by Fani Bhushan Sharma, Shashi Raj Kapoor
Abstract: In recent years, soft computing strategies have played a vital role to solve optimization problems associated with the real world. In this paper, an efficient soft computing strategy namely, artificial bee colony algorithm (ABC_algo) is modified with incorporating landmark operator. The proposed modified ABC algorithm is named as land mark inspired ABC (LMABC). The performance of LMABC is evaluated on benchmark functions. Further, the proposed LMABC is applied for vector control of induction motor (IM) and subsequently to improve its efficiency. The vector control of IM includes control of magnitude and phase of each phase current and voltage. In this research paper, the field orientated control, a digital implementation which demonstrates the capability of performing direct torque control, of handling system limitations and of achieving higher power conversion efficiency is considered. The obtained outcomes are significantly better than other state-of-art algorithms available in the literature.
Keywords: Swarm intelligence; Landmark; Induction motor; Metaheuristics; Real world optimization.
Special Issue on: ICEODS-2019 Recent Advances in Engineering Optimisation and Data Science for Sustainable Future Development
Design and implementation of bi-level artificial bee colony algorithm to train hidden Markov models for performing multiple sequence alignment of proteins
by Soniya Lalwani
Abstract: Multiple sequence alignment (MSA) is an NP-complete problem that is a challenging area from bioinformatics. Implementation of hidden Markov Model (HMM) is one of the most effective approach for executing MSA, that performs training and testing of the sequence data so as to obtain alignment scores with accuracy. The training of HMM is again an NP-hard problem, hence it requires the implementation of metaheuristic methods. Proposed work presents a bi-level artificial bee colony (BL-ABC) algorithm to train hidden Markov models (HMMs) for multiple sequence alignment (MSA) of proteins i.e. BLABC-HMM. The trained stochastic model created by BL-ABC basically yields position-dependent probability matrices at higher prediction ratios. The performance of proposed algorithm is compared with the competitive state-of-the-art algorithms and different variants of particle swarm optimization (PSO) algorithm on protein benchmark datasets from pfam and BAliBASE database, and BLABC-HMM is found yielding better alignment scores and prediction accuracy.
Keywords: Hidden Markov model; Proteins; Artificial bee colony; Multiple sequence alignment.
Optimization of EDM process parameters by application of Genetic Algorithm
by Sumit Sharma, Love Kishore Sharma, Dheeraj Joshi, Mohammad Israr, Ritesh Mathur, Deepak Sharma
Abstract: The EDM efficiency can be strengthen by suitably defining the critical factors and their values for obtaining desired responses. In present research work, Response surface methodology (RSM) with Face Centered Cubic (FCC) approach is implemented for correlating the response i.e. material removal rate (MRR) with control factors i.e. voltage, peak current, pulse on time. These factors provide maximum MRR of 230.6 gm/sec. To obtain the optimal solution, genetic algorithm (GA) is coupled with the obtained mathematical model. The dielectric fluid used is kerosene oil. ANOVA and F-test are used to check for model validation. R2 and adjusted R2 which confirms the validity of proposed model. The work piece material used in research work is AISI 4140 steel.
Keywords: EDM; response surface methodology; FCC; material removal rate; genetic algorithm; ANOVA.
Special Issue on: Building Intelligent Applications Using Machine Learning
Hybrid ARIMA-deep belief network model using PSO for stock price prediction
by Shaikh Sahil Ahmed, Mahesh Kankar, Nagaraj Naik, Biju R. Mohan
Abstract: Forecast analysis is in very high demand in many fields for improving sales and operation planning in various industries and enterprises. So, accuracy is a significant factor in forecasting stock market prices. We already know there are existing deep learning models for stock market prediction such as gated recurrent unit (GRU), support vector machine (SVM), multilayer perceptron (MLP), etc. This paper enhanced the prediction of stock prices using series hybrid models over single deep learning models. The models we used are autoregressive integrated moving average (ARIMA), deep belief network (DBN), long short-term memory (LSTM), and performed analysis on hybrid models in comparison with single models. We have chosen a model as ARIMA, LSTM, and hybrid as ARIMA-DBN and ARIMA-LSTM. For finding the best fit parameter for ARIMA and DBN, the particle swarm optimisation (PSO) technique is used. We compared the various models based on performance errors like MSE, RMSE, MAPE, etc. As already existing ARIMA and LSTM is not good enough for forecasting
and so we worked over the ARIMA-DBN model to overcome the limitations of other models. After research, we found out that series hybrid ARIMA-DBN is effectively better than other single models for stock market prediction.
Keywords: deep learning; time series forecasting; autoregressive integrated moving average; ARIMA; linear and nonlinear models; particle swarm optimisation; PSO.