International Journal of Bio-Inspired Computation (41 papers in press)
Special Issue on: Artificial Intelligence Facilities Smart Cities Development
by Peiming Ren, Lin Wang, Wei Fang
Abstract: Real-time people counting based on videos is one of the most popular projects in the construction of smart cities. To develop an accurate people counting approach, deep learning can be used as it greatly improves the accuracy of machine learning based approaches. To this end, we have previously proposed an accurate YOLO (You Only Look Once) based People Counting approach, dubbed YOLO-PC. However, the model of YOLO-PC was very large with an excessive number of parameters, thus it requires large storage space on the device and makes transmission on Internet a time consuming task. In this paper, a new real-time people counting method named as Squeeze YOLO-based People Counting (S-YOLO-PC) is proposed. S-YOLO-PC uses the fire layer of SqueezeeNet to optimize the network structure, which reduces the number of parameters used in the model without decreasing its accuracy. Based on the obtained the experimental results, S-YOLO-PC reduces the number of model parameters by 11.5% and 9% compared to YOLO and YOLO-PC, respectively. S-YOLO-PC can also detect and count people with 41 frames per second (FPS) with the average precision (AP) of person of 72%.
Keywords: Model compression; People counting; Boundary-selection; YOLO; SqueezeNet.
SmartGC: A Software Architecture for Garbage Collection in Smart Cities
by Miguel Ramalho, Rosaldo Rossetti, Nelio Cacho, Arthur Souza
Abstract: With populations in cities increasing in a very accelerated pace, the problem of collecting and handling the waste produced becomes a major concern to governmental authorities. Indeed, the amount of garbage they create is increasing even faster than their populations, worsening the problem and turning garbage collection into a very challenging task. In this paper, we see garbage collection through the spectacles of the emerging concept of Smart Cities, accounting for new performance measures defined on the grounds of sustainability, energy efficiency, optimum resource allocation, and low carbon emission and footprint. We thus devise a smart garbage collection management system, coined SmartGC, whose architecture is detailed and explained. Abstracting out garbage collection from a smart mobility perspective, the underlying methodology supporting the proposed architecture relies on the concept of Artificial Transportation Systems. For the sake of demonstration, we have implemented a routing strategy to generate improved itineraries accounting for the content of garbage containers, which are continuously monitored through IoT-based smart meters. Also, we discuss on how the architecture is instantiated and integrated into the smart city agenda of Natal, a medium-size capital in Northeastern Brazil.
Keywords: smart cities; garbage collection; artificial transportation systems; software architecture.
Time-to-Contact Control: Improving Safety and Reliability of Autonomous Vehicles
by Liang Wang, Berthold K.P. Horn
Abstract: Under traditional car-following control, i.e. human drivers' behavior, the stability condition of traffic system is not satisfied in general. For safety and reliability of autonomous vehicles, additional danger warning system must be used in the adaptive cruise control system to prevent inevitable potential collisions. One reasonable quantity of evaluating potential collisions is time to contact (TTC): how soon will potential collision occur? In this paper, we provide TTC feedback control to improve safety and reliability of autonomous vehicles, and show the effectiveness of TTC feedback. TTC can be estimated by machine vision technics with single uncelebrated camera (i.e. passive sensors). We provide detailed mathematical analysis and algorithmic implementation. The machine vision based TTC algorithm is pretty fast such that the whole system can be implemented on Android smart phones running in real-time. Moreover, it's not trial to estimate relative velocity by differentiating the measured distance between cars with respect to time, because inevitable measurement noise in the distance measurements will be amplified by the derivative operation. The time-to-contact based algorithm provides an alternative approach to estimating the relative velocity, which can also be fused with measurements from other active sensors, if desired.
Keywords: Autonomous vehicles; time to contact (TTC); danger detection; machine visionp; android smartphones.
Hybrid Cuckoo Search Algorithm with Covariance Matrix Adaption Evolution Strategy for Global optimisation Problem
by Xin Zhang, Xiangtao Li, Minghao Yin
Abstract: Cuckoo search algorithm (CS) is an efficient bio-inspired algorithm and has been studied on global optimisation problems extensively. It is expert in solving complicated functions but converges slowly. Another optimisation algorithm, covariance matrix adaption evolution strategy (CMA_ES) can speed up the convergence rate via self-adaptation of the mutation distribution and cumulation of the evolution path, whereas it performs badly in complex functions. Therefore, in this paper, we devise a hybridization of CS and CMA_ES and name it CS_CMA, to enhance the convergence speed and performance for the different optimisation problems. An evolved population is initialised at the beginning of iteration, using the information of previous evolution. During the whole evolution process, self-adaptive parameter adjustments are employed through the successful parameter values. To validate the performance of CS_CMA, comparative experiments are conducted based on seven high-dimensional benchmark functions provided for CEC 2008 and an engineering optimisation problem chosen from CEC 2011, and the computational results demonstrate that CS_CMA outperforms other competitor algorithms.
Keywords: Cuckoo Search; Covariance Matrix Adaptation Evolutionary Strategy; Global optimisation; Self-adaptive method; Cumulation.
TTPA: A Two Tiers PSO Architecture for Dimensionality Reduction
by Shikha Agarwal, Prabhat Ranjan
Abstract: Particle swarm optimization (PSO) is a popular nature inspired computing method due to its fast & accurate performance, exploration & exploitation capability, cognitive & social behaviour and has fewer parameters to adjust. Recently an improved binary PSO (IBPSO) was proposed by Chuang et. al. to avoid getting trapped in local optimum and they have shown that it outperforms all other variants of PSO. Even though many variants of PSO exists independently to improve the performance of PSO, to escape from local optimum and to deal with dimensionality reduction, there still needs an integrated approach to handle it. Hence in this paper two tiers PSO architecture (TTPA) is proposed to find the maximum classification accuracy with minimum number of selected features. The proposed method is used to classify nine benchmarking gene expression data sets. The results show the merits of TTPA.
Keywords: Dimensionality Reduction; Binary Particle Swarm Optimization; FeaturernSelection; Microarray Gene Expression Profile Data.
COMPUTER AIDED DIAGNOSIS OF DRUG SENSITIVE PULMONARY TUBERCULOSIS WITH CAVITIES, CONSOLIDATIONS AND NODULAR MANIFESTATIONS ON LUNG CT IMAGES
by Dhalia Sweetlin J, H. Khanna Nehemiah, Kannan Arputharaj
Abstract: In this work, a Computer-aided diagnosis (CAD) system to improve the diagnostic accuracy and consistency in image interpretation of pulmonary tuberculosis is proposed. The lung fields are segmented using region growing and edge reconstruction algorithms. Texture features are extracted from the diseased regions manifested as consolidations, cavitations and nodular opacities. A wrapper approach that combines cuckoo search optimization and one-against-all SVM classifier is used to select optimal feature subset. Cuckoo search algorithm is implemented first using entropy and second without using entropy measure. Training is done with the selected features using one-against-all (SVM) classifier. Among the 98 features extracted from the diseased regions, 47 features are selected with entropy measure giving 92.77% accuracy. When entropy measure is not used, 51 features are selected giving 91.89% accuracy. From the results, it is inferred that selecting appropriate features for training the classifier has an impact on the classifier performance.
Keywords: Computer aided diagnosis; Pulmonary Tuberculosis; Tuberculosis manifestations; Binary Cuckoo Search; one-against-all SVM classification; Drug sensitive TB; Miliary TB; Cavitary TB; Nodular TB.
Constrained optimisation by solving equivalent dynamic loosely-constrained multiobjective optimisation problem
by Sanyou Zeng, Ruwang Jiao, Changhe Li, Rui Wang
Abstract: A constrained optimisation problem (COP) is solved by solving an equivalent dynamic loosely-constrained multiobjective optimisation problem in this paper. Two strategies are considered. i) An additional objective (constrained-violation objective) is introduced to obtain a twoobjective optimisation problem. This provides a framework for adopting multi-objective techniques to solve the COP. ii) A dynamic constraint boundary is introduced to obtain an equivalent dynamic loosely-constrained multiobjective optimisation problem since a broad boundary is gradually slightly reduced to the original constraint boundary. This suggests that an dynamic constrained multiobjective evolutionary algorithm (DCMOEA) can performs as effective as that of a multiobjective evolutionary algorithm (MOEA) in solving an unconstrained multiobjective optimisation problem. The idea is implemented into three major types of MOEAs, i.e., Pareto ranking based method, decomposition based method, preference-inspired co-evolutionary method. These three instantiations are tested on two sets of benchmark problems. Experimental results show that they are better than or competitive to two state-of-the-art constraint optimizers, especially for the problems with high dimensions.
Keywords: evolutionary algorithm; constrained optimisation; multi-objective optimisation; dynamic optimisation.
Swarm Intelligent Based Congestion Management Using Optimal Rescheduling of Generators
by Surender Reddy Salkuti, Wajid S.A.
Abstract: Congestion Management (CM) refers to the controlling of transmission system such that the power transfer/flow limits are observed. In the restructured electrical system, the challenges of CM for the System Operator (SO) is to maintain the desired level of system reliability and security in the short and long terms, while improving the market/system efficiency. In this paper, the CM problem is tackled by using the centralized optimization i.e., optimal rescheduling of generators, which in turn is solved by using the Swarm intelligent techniques. Here, the CM problem is solved by using the Particle Swarm Optimization (PSO), Fitness Distance Ratio PSO (FDR-PSO) and Fuzzy Adaptive-PSO (FA-PSO). First, the generators are selected based on sensitivity to the over-loaded transmission line, and then these generators are rescheduled to remove the congestion in the transmission line. The suitability and effectiveness of the proposed CM approach is examined on the standard IEEE 30 bus and practical Indian 75 bus systems.
Keywords: Congestion management; Generation rescheduling; Optimal power flow; Generator sensitivity; Evolutionary algorithms; Particle swarm optimization.
Intelligent Swarm Firey Algorithm for the Prediction of China's National Electricity Consumption
by Guangfeng Zhang, Yi Chen
Abstract: China's energy consumption is the world's largest and is still rising, leading to concerns of energy shortage and environmental issues. It is, therefore, necessary to estimate the energy demand and to examine the dynamic nature of the electricity consumption. In this paper, we develop a nonlinear model of energy consumption and utilise a computational intelligence approach, specifically a swarm firefly algorithm with a variable population, to examine China's electricity consumption with historical statistical data from 1980 to 2012. Prediction based on these data using the model and the examination is verified with a bivariate sensitivity analysis, a bias analysis and a forecasting exercise, which all suggest that the national macroeconomic performance, the electricity price, the electricity consumption efficiency and the economic structure are four critical factors determining national electricity consumption. Actuate prediction of the consumption is important as it has explicit policy implications on the electricity sector development and planning for power plants.
Keywords: energy consumption; nonlinear modelling ; swarm firefly algorithm; parameters determination.
A Moving Block Sequence-based Evolutionary Algorithm for Resource-Constrained Project Scheduling Problems
by Xingxing Hao, Jing Liu, Xiaoxiao Yuan, Xianglong Tang, Zhangtao Li
Abstract: In this paper, a new representation for resource-constrained project scheduling problems (RCPSPs), namely moving block sequence (MBS), is proposed. In RCPSPs, every activity has fixed duration and resource demands, therefore, it can be modeled as a rectangle block whose height represents the resource demand and width the duration. Naturally, a project that consists of N activities can be represented as the permutation of N blocks that satisfy the precedence constraints among activities. To decode an MBS to a valid schedule, four move modes are designed according to the situations that how every block can be moved from its initial position to an appropriate location that can minimize the makespan of the project. Based on MBS, the multiagent evolutionary algorithm (MAEA) is used to solve RCPSPs. The proposed algorithm is labeled as MBSMAEA-RCPSP, and by comparing with several state-of-the-art algorithms on benchmark J30, J60, J90 and J120, the effectiveness of MBSMAEA-RCPSP is clearly illustrated.
Keywords: Moving block sequence; Resource-constrained project scheduling problems; Evolutionary algorithms.
Cloud service composition using an inverted ant colony optimization algorithm
by Saied Asghari, Nima Jafari Navimipour
Abstract: In recent years, clouds are becoming an important platform for scientific applications. Service composition is a growing approach that increases the number of applications of cloud computing by reusing attractive services. However, more available approaches focus on producing composite services from a single cloud, limiting the benefits derived from other clouds. Furthermore, in many traditional service composition methods, there is a key problem called load balancing that was inefficient among cloud servers. Therefore, this paper proposes the inverted ant colony optimization (IACO) algorithm, a variation of the basic ant colony optimization (ACO) algorithm, to solve this problem. This method inverts its logic by converting the effect of pheromone on the selected path by ants in order to improve load balancing among cloud servers. In this method, ants begin to traverse the graph from the start node and each ant selects the best node for moving, then other ants may not follow the track travelled by the previous ants. We evaluate the performance of the proposed method in comparison with the ACO, greedy and COM2 algorithms in terms of the obtained optimal cloud composition, load balancing, waiting time, cost and execution time. The results show that the proposed method improves load balancing, reduces waiting time and cost that are the advantages of the proposed method and also increases execution time that is a disadvantage of the proposed method.
Keywords: Cloud computing; Inverted ant colony; Service composition; Load balancing; Optimal cloud composition.
Markov Approach for Quantifying the Software Code Coverage Using Genetic Algorithm in Software Testing
by Sujatha Ramalingam, Boopathi Muthusamy, Senthil Kumar C, Narasimman S, Rajan A
Abstract: Markov Chain approach to quantify the coverage of dd-graph representingrnthe software code using genetic algorithm (GA) is presented in this paper. Initially the ddgraph is captured from the control flow graph. In this technique, test software code coverage is carried out by applying GA through sufficient number of feasible linearly independent paths. These paths have been decided in a software code depending on computational uses and predicate uses. Automatic test cases have been produced for the three mixed data type variables namely, integer, float, Boolean and GA is applied. Transition Probability of the Markov Chain is attained from gcov coverage analysis tool of the initial test suite. Fitness function of GA is measured using path coverage metric; as the product of node coverage and TPM values. Highest fitness value represent the most critical paths among these independent paths with aim to increase testing efficiency of the software code.
Keywords: Software testing; Test adequacy; Cyclomatic complexity; Markov Chain; dd-rngraph; Genetic Algorithm.
Solving many-objective optimization problems by an improved particle swarm optimization approach and a normalized penalty method
by Dexuan Zou, Fei Wang, Nannan Yu, Xiangyong Kong
Abstract: The problem with more than three objectives is commonly known as many-objective optimization problem (MOP), and it has drawn much attention from researchers because of its big potential in the real word. In this paper, a novel modified particle swarm optimization (NMPSO) approach is presented to handle a kind of MOP called many-objective knapsack (MOK) problem. NMPSO relies on the global best particle to guide the search of all particles in each generation, which can enhance the convergence of NMPSO. Furthermore, a randomization-based mutation is adopted to overcome the premature convergence which usually occurs in the late evolutionary optimization process. In addition to many objective functions, MKP consists of several inequality constraints, and all the objective functions should be minimized under the precondition that all the inequality constraints are satisfied. A normalized penalty method (NPM) is devised to reach a compromise between objective functions and inequality constraints, which enables particles to explore solution space more precisely. In summary, the contribution of our work can be summarized in two aspects: (1) A more powerful approach called NMPSO is proposed. (2) A reasonable NPM is devised. Five improved PSOs are used to handle the MOKs with different number of objective functions and dimensions. Experimental results show that NMPSO has higher efficiency than the other four approaches. It uses the lowest computational cost, and achieves the smallest penalty function values for most MKPs.
Keywords: Many-objective optimization problem; Novel modified particle swarm optimization; Many-objective knapsack problem; Randomization-based mutation; Normalized penalty method.
Quantum Inspired Monarch Butterfly Optimization for UCAV Path Planning Navigation Problem
by Jiao-Hong Yi
Abstract: As a complicated high-dimensional optimization problem, path planning navigation problem for Uninhabited Combat Air Vehicles (UCAV) is to obtain a shortest safe flight route with different types of constrains under complicated combating environments. Monarch butterfly optimization (MBO) is a highly promising swarm intelligence algorithm. Since then, though it has successfully solved several challenging problems, MBO may be trapped into local optima sometimes. In order to improve the performance of MBO, quantum computation is firstly incorporated into the basic MBO algorithm, and a new quantum inspired MBO algorithm is then proposed, called QMBO. In QMBO, certain number of the worst butterflies are updated by quantum operators. In this paper, the UCAV path planning navigation problem is modeled into an optimization problem, and then its optimal path can be obtained by the proposed QMBO algorithm. In addition, B-Spline curves are utilized to further smoothen the obtained path and make it more feasible for UCAV. The UCAV path obtained by QMBO is compared with the basic MBO, and the experimental results show that QMBO can find much shorter path than MBO.
Keywords: Unmanned combat air vehicle; Path planning navigation; Monarch butterfly optimization; Quantum computation; B-Spline curve.
ABC_DE_FP: A Novel Hybrid Algorithm for Complex Continuous Optimization Problems
by Parul Agarwal, Shikha Mehta
Abstract: Artificial bee colony algorithm (ABC) evolved as one of the efficient swarm intelligence based algorithm in solving various global optimization problems. Though many variants of ABC have evolved, still algorithm depicts poor convergence rate in many situations. Therefore, maintaining balance between intensification and diversification of the algorithm still needs attention. In this context, a novel hybrid ABC algorithm has been developed by integrating FPA and DE in original ABC algorithm. To assess the efficacy of proposed hybrid algorithm, it is primarily compared with contemporary ABC variants such as GABC, IABC and AABC over simple benchmark problems. Thereafter, it is compared with original ABC, FPA, hybrid of ABC_FP, ABC_DE and ABC_SN over complex problems of CEC2014 for up to 100 dimensions. Results reveal that proposed algorithm outperforms its counterparts in terms of minimum error value attained and convergence speed for majority of global numerical optimization functions.
Keywords: Artificial bee colony algorithm; CEC 2014 benchmark functions; nature inspired algorithms; flower pollination algorithm; differential evolution; convergence speed.
Trust Aware Nature Inspired Optimized Routing in Clustered Wireless Sensor Networks
by Edwin Prem Kumar Gilbert, K. Baskaran, Elijah Blessing Rajsingh, M. Lydia, A. Immanuel Selvakumar
Abstract: Wireless sensor networks (WSN) consist of sensor nodes which have capabilities of sensing, computation and communication. Routing algorithms are required in a WSN when a node is unable to send a data to the base station directly. In this paper, a trust aware optimized compressed sensing based data aggregation and routing algorithm has been proposed for clustered WSN. Compressed sensing is used for data aggregation from sensor nodes with reduced overhead. Nature inspired optimization has been implemented to obtain trade-off between transmission distance, hop-count, number of transmitted message and most trusted path using artificial bee colony algorithm, ant colony optimization, differential evolution, firefly algorithm and particle swarm optimization. Trust based reconstruction of the compressed data is done at the base station in the presence of malicious nodes.
Keywords: artificial bee colony algorithm; ant colony optimization; differential evolution; firefly algorithm; multi-objective optimization; particle swarm optimization; trust management.
A modified harmony search algorithm applied to capacitor placement of radial distribution networks considering voltage stability index
by A.R. Askarzadeh, Meysam Montazeri, Leandro Coelho
Abstract: In power system, capacitor placement of distribution networks is a complex combinatorial optimization problem. In this paper, in order to effectively solve optimal capacitor placement (OCP), an aggregate harmony search (AHS) optimizer, a stochastic population-based metaheuristic algorithm, is proposed which introduces a new pitch adjustment mechanism for harmony search (HS). The objective function contains three goals: (1) minimization of the power losses, (2) minimization of the capacitor installation cost and (3) improvement of the voltage stability index at the weakest bus. On two case studies, 23 kV nine-section feeder and 33-bus radial system, simulation results show that the proposed AHS not only finds more accurate results than the other investigated HS variants and particle swarm optimization (PSO) techniques but also has the best robustness. Promising performance of AHS makes this technique as an efficient alternative to solve capacitor placement problem.
Keywords: Capacitor allocation; power loss; voltage stability index; aggregate harmony search.
A fuzzy-based method for task scheduling in the cloud environments using inverted ant colony optimization algorithm
by Poopak Azad, Nima Jafari Navimipour, Mehdi Hosseinzadeh
Abstract: Cloud computing is the latest emerging trend of distributed computing, in which distributed resources are delivered based on user's demand. In the cloud environment, computing resources need to be scheduled so that providers make the most use of the resources and users will find the applications they need at the lowest cost. So, scheduling is one of the most important issues in the cloud. Among the cloud challenges, balancing has been neglected over the rest, since balancing compliance can affect other parameters as well. The complexity of the scheduling, by considering its corresponding parameters, transforms it into an NP-hard problem. In this paper, an Inverted Ant Colony Optimization (IACO) algorithm has been used to solve the task scheduling problem in the cloud environment with the goal of reducing runtime and increasing load balancing. In the proposed method, pheromone repellent is used instead of pheromone gravity, so the effect of pheromone prevent the wrong choice. In order to observe load balance and the effect of pheromone repulsion, fuzzy logic and weight definition have been used. Finally, the proposed method has compared with First Come First Serve (FCFS), Round-Robin (RR) and Ant Colony Optimization (ACO) algorithms. The simulation results have shown that by increasing the number of tasks, the proposed algorithm while reducing the total time and cost of execution, could also increase load balance.
Keywords: Cloud computing; scheduling; inverted ant colony algorithm; makespan; load balancing; cloudsim.
Analysis of PID controller for the Load Frequency Control of Static Synchronous Series Compensator & Capacitive Energy Storage Source based Multi-area Multi-source Interconnected Power System with HVDC link
by Rajendra Khadanga, Amit Kumar
Abstract: In this research work, a maiden approach is made by using the SSSC and CES devices as a frequency damping controller in the most realistic scenario of Automatic Generation Control (AGC) of a multi-area multi-source (Thermal-Hydro-Gas) interconnected power system along with the consideration of HVDC and AC parallel tie-lines. At first, the performance of the HVDC with AC Parallel tie line is investigated for the considered power system. A PID controller is utilized to control each of the generating units in all the areas and shows its superior performance compared to other conventional controllers. A Hybrid Particle Swarm Optimization (PSO) and Gravitational search Algorithm (GSA) is proposed for tuning the gains of the PID controller and is compared with some conventional controllers. Later the effect of SSSC and CES when added as a damping controller to the power system is analyzed. It is observed that, with the addition of the SSSC and CES as a damping controller along with the optimized PID controller, the dynamic performance of the proposed interconnected power system is improved.
Keywords: Automatic Generation Control (AGC);rnLoad Frequency Control (LFC);rnMulti area multi source power system;rnFlexible A.C Transmission System (FACTS);rnCapacitive Energy Source (CES);rnHybrid PSO-GSA algorithm.
An adaptive Reinforcement Learning based Bat Algorithm for structural design problems
by Xian-Bing Meng, Han-Xiong Li, Xiao-Zhi Gao
Abstract: A Reinforcement Learning based bat algorithm is proposed for solving structural design problems. By incorporating Reinforcement Learning, the algorithms performance feedback is formulated to adaptively select between algorithms different operators. To improve the solution diversity, a new metric of individual difference is designed. The individual difference based strategies are proposed to adaptively tune the algorithms parameters. The variations of the pulse rates and loudness are newly designed to formulate their effects on the local search and foraging efficiency. Simulations and comparisons based on ten structural design problems with continuous/discrete variables demonstrate the superiority of the proposed algorithm.
Keywords: Bat Algorithm; Reinforcement Learning; Individual difference; Adaptive tuning.
A Review of Multiobjective Optimization and Decision Making Using Evolutionary Algorithms
by Muneendra Ojha, Krishna Pratap Singh, Pavan Chakraborty, Shekhar Verma
Abstract: Research in the field of Multiobjective Optimization Problem (MOP) has garnered ample interest in the last two decades. Majority of methods developed for solving the problem belong to the class of Evolutionary Algorithms (EA) which are population-based evolution search strategies involving exploration and exploitation in general. Multi-Criteria Decision Making (MCDM) is another aspect of MOP which involves finding methods to help a Decision Maker (DM) in making most optimal decisions in a conflicting scenario. In this paper, we present a brief review of the methods and techniques developed in the last 15 years which try to solve the MOP and MCDM problems. The strengths and weaknesses of methods have been discussed to present a holistic view. This paper covers challenges associated with MOEAs, different solution approaches such as Pareto based methods and non-Pareto methods, indicator-based methods, aggregation methods, decomposition based methods, methods using reference sets, MOEAs involving DM, a priori, interactive and a posteriori preference incorporation methods. It also discusses most of the quality metrics and performance indicators proposed in the literature along with benchmark problems. In addition, some future research issues and directions are also presented.
Keywords: Multiobjective Optimization Review;Genetic Algorithm;Evolutionary Algorithms;Multi-Criteria Decision Making.
Reconstruction of Gene Regulatory Network using S-system with Genetic Algorithm and Flower Pollination Algorithm (GA-FPA) Hybrid
by Sudip Mandal, Goutam Saha, Rajat Kumar Pal
Abstract: Accurate reconstruction of gene regulatory networks from time-series gene expression data is a significant challenge for computer scientists. In this paper, we have proposed a Genetic Algorithm and Flower Pollination Algorithm hybrid for the reverse engineering of gene regulatory network based on decoupled S-systems. Here, Genetic Algorithm has been used to select the best combination of genes, which act as regulators in the network. Flower Pollination Algorithm has been used to calculate the best possible S-system parameters for which the training error is minimum for those regulators. The proposed method has been tested on small-scale and medium-scale, synthetic benchmark networks and in-slico benchmark networks extracted from the Gene Net Weaver database, as well as the real-world experimental datasets of the yeast IMRA and DNA SOS Repair network of Escherichia coli. The experiments reveal that the proposed hybrid methodology is capable of inferring gene regulatory networks more accurately with lesser training data and in lesser computational time compared to other existing methods.
Keywords: gene regulatory networks; gene expression data; S-system; genetic algorithm; flower pollination algorithm; GeneNetWeaver; microarray; metaheuristics; reverse engineering; optimisation; cardinality; genetic regulation.
An Overview on Structural Health Monitoring: From the Current State-of-the-Art to New Bio-inspired Sensing Paradigms
by Maria-Giovanna Masciotta, Alberto Barontini, Luis F. Ramos, Paulo Amado-Mendes, Paulo B. Lourenco
Abstract: In the last decades, the field of structural health monitoring (SHM) has grown exponentially. Yet, several technical constraints persist, which are preventing full realization of its potential. To upgrade current state-of-the-art technologies, researchers have started to look at natures creations giving rise to a new field called biomimetics, which operates across the border between living and non-living systems. The highly optimised and time-tested performance of biological assemblies keeps on inspiring the development of bio-inspired artificial counterparts that can potentially outperform conventional systems. After a critical appraisal on the current status of SHM, this paper presents a review of selected works related to neural, cochlea and immune-inspired algorithms implemented in the field of SHM, including a brief survey of the advancements of bio-inspired sensor technology for the purpose of SHM. In parallel to this engineering progress, a more in-depth understanding of the most suitable biological patterns to be transferred into multimodal SHM systems is fundamental to foster new scientific breakthroughs. Hence, grounded in the dissection of three selected human biological systems, a framework for new bio-inspired sensing paradigms aimed at guiding the identification of tailored attributes to transplant from nature to SHM is outlined.
Keywords: Structural health monitoring (SHM); nature-inspired sensing paradigms; bio-inspired algorithms; bio-inspired SHM sensors; biomimicry.
Multidirectional harmony search algorithm for solving integer programming and minimax problems
by Mohamed Tawhid
Abstract: Integer programming and minimax problems are important tools in solving various problems that arise in data mining and machine learning such as multi-class data classification and feature selection problems. In this paper, we propose a new hybrid harmony search algorithm by combining the harmony search algorithm with the multidirectional search method in order to solve the integer programming and minimax problems. The proposed algorithm is called Multidirectional Harmony Search Algorithm (MDHSA). MDHSA starts the search by applying the standard harmony search for number of iteration then the best obtained solution is passing to the multidirectional search method as an intensification process in order to accelerate the search and overcome the slow convergence of the standard harmony search algorithm. The proposed algorithm is balancing between the global exploration of the harmony search algorithm and the deep exploitation of the multidirectional search method. MDHSA algorithm is tested on 7 integer programming problems and 10 minimax problems and compared against 5 algorithms for solving integer programming problems and 4 algorithms for solving minimax problems. The experiments results show the efficiency of the proposed algorithm and its ability to solve integer programming and minimax problems in reasonable time.
Keywords: Evolutionary computation; global optimization; harmony search algorithm; direct search algorithm; multidirectional search; integer programming problems; minimax problems.
Intelligent Diagnosis of Cardiac Valve Calcification in ESRD Patients with Peritoneal Dialysis Based on Improved Takagi-Sugeno-Kang Fuzzy System
by Jing Xue, Yue Zhang, Jia Hua, Weiwei Li, Zhijian Zhang, Liang Wang, Zhuxing Sun
Abstract: Without a B-ultrasound result, if a doctor diagnoses a suspected patient using only the basic clinical features, such as age, gender, serum calcium, and urea clearance index (KT/V), the diagnostic accuracy will be very low (even less than 50%). To solve this problem, a machine learning technology is proposed to intelligently diagnose cardiac valve calcification in end-stage renal disease (ESRD) patients with peritoneal dialysis. Compared with classical classification technologies, the proposed method aims to develop a model that has both medical interpretability and high recognition performance. In terms of interpretability, the Takagi-Sugeno-Kang fuzzy system is considered a basic model due to its built-in interpretable ability. In addition, because the distribution of the positive class (cardiac valve calcification is positive) and negative class (cardiac valve calcification is negative) in the peritoneal dialysis patient dataset is unbalanced, a novel unbalanced TSK (Takagi-Sugeno-Kang) fuzzy system (B-TSK-FS) is developed using a novel unbalanced fuzzy learning mechanism. The corresponding results reveal that the B-TSK-FS method obtains promising results (the max testing accuracy is over 98%) compared with classical machine learning methods for intelligently diagnosing cardiac valve calcification in ESRD patients with peritoneal dialysis.
Keywords: machine learning; intelligent diagnosis; cardiac valve calcification; peritoneal dialysis; TSK fuzzy system.
Adaptive discrete cat swarm optimization algorithm for the flexible job shop problem
by Tianhua Jiang
Abstract: Cat swarm optimization (CSO) is a new nature-inspired algorithm, which was originally proposed to solve continuous optimization problems. However, in the actual life, many practical problems show the discrete features. Flexible job shop scheduling problem (FJSP) is a typical discrete combinatorial optimization
Keywords: flexible job shop scheduling; combinatorial optimization; discrete cat swarm optimization; adaptive adjustment strategy; local search.
An ISO/IEC 24745 compliant ECG template protection based on linear prediction coding
by Emna Kalai, Adel Benzina
Abstract: An ECG (ElectroCardioGram) biometric system can be wearable and offers continuous authentication. It is suitable for medical applications and has proved its benefits over traditional biometric systems. In this paper, we propose a solution to protect the ECG reference template from eavesdroppers spying the wireless link (between the wearable device and the target application) to preserve the privacy of the ECG reference template. The scheme fulfills the ISO/IEC 24745 biometric template protection requirements. The proposed solution is based on linear prediction coding of the ECG extracted features. We add a specifc secret key to enhance unlinkability and renewability of the protected template. We evaluate the authentication performance of the unprotected and the protected system with a large database. Theoretical and empirical evaluations show that the proposed system outstands the fuzzy commitment scheme in terms of algorithmic complexity and energy consumption while preserving the same authentication performances proving its effectivness, and effciency.
Keywords: E-health; Authentication; ECG security and privacy; ISO/IEC 24745; Time complexity; Energy consumption.
An Ant Based New Clustering Model for Graph Proximity Construction
by Nesrine Masmoudi, Hanene Azzag, Mustapha Lebbah, Cyrille Bertelle, Maher Ben Jemaa
Abstract: This paper presents a new concept for an artificial ant model to build proximity graphs. We tried first to introduce the state of art of different clustering methods relying on the swarm intelligence and the ants numerous abilities. Our new bio-inspired model is based on artificial ants over a dynamic graph of clusters using colonial odors and pheromone based reinforcement process. Our non-hierarchical algorithm, called CL-Ant, where each ant represents one datum and its moves aim to create homogeneousrndata groups that evolve together in a proximity graph environment. In this model, the artificial ant performs two steps: following the maximum pheromone path rate, and then, integrating to neighbors clusters using simple localization rules. Afterwards we present an incremental extension, called CL-AntInc to treat data streams, which allows building graphs in an incremental way. Our survey properties were studied thoroughly and a detailed analytical comparison of our results with those obtained by other methods was provided. These algorithms were evaluated and validated using real databases extractedrnfrom the Machine Learning Repository.
Keywords: swarm intelligence; artificial ants; data clustering; data streams; proximityrngraph.
Bio-Inspired Innovative Green Fault Recovery Modelling For Macro-Femtocell Mobile Network
by Sourav Hati, Debashis De, Anwesha Mukherjee
Abstract: In an overlay macro-femtocell mobile network, the femtocells are allocated within the macrocell coverage in order to provide good Quality of Service at indoor environment. Within this network, when a femtocell gets damaged, the adjacent lightly loaded femtocells are searched and the users of the damaged cell are handed over to those lightly loaded adjacent femtocells. However, this increases latency, power consumption and the probability of call dropping. To overcome these difficulties, we propose a Red Blood Cell life cycle based fault recovery management method which utilizes femtocell-to-macrocell and then macrocell-to-femtocell handover to reduce the probability of call dropping, power consumption and latency. We introduce a new database, femtoDB which is stored inside the cloud to be used as a potential repertoire capable to store the femtocell IDs with their users information in an overlay macro-femtocell network. Based on the information maintained in femtoDB, the macrocell decides to which femtocell the users of the damaged femtocell to be handed over. Simulation results illustrate that the proposed recovery management method reduces the probability of call dropping, power consumption and latency by approximately ~3%, ~75% and ~60% respectively.
Keywords: Red Blood Cell; Femtocell; Macrocell; Call dropping; Power consumption; Latency;.
Dynamic Economic Emission Dispatch Problem with Renewable Integration Focusing on Deficit Scenario in India
by Hithu Anand, Rengaraj Ramasubbu
Abstract: Present scenario power grid has increased penetration of renewable energy sources (RESs). RESs are clean sources of energy and power production from them with minimal emission is a national target. Already, increased carbon footprint has put nations into jeopardy. Nowadays to study the benefits due to RESs in power system is of greater importance. Stochastic nature of RESs made it difficult to manage power dispatch scenario. Dynamic power demand added even more difficulty in obtaining real time economic schedule of generation dispatch. A test system of ten generator and emission dispatch with wind turbine (WT) and photo voltaic (PV) having dynamic load for 24 hours is economized. Stochastic method of particle swarm optimization (PSO) is compared with anti-predatory particle swarm optimization (APSO). It is identified that APSO method gives a better economy with reduced emission for the given problem.
Keywords: renewable energy; dynamic economic emission dispatch; wind power; solar power; anti-predatory particle swarm optimization.
Integrated deteriorating maintenance and patient scheduling for single medical device with heuristic algorithm
by Liu Qinming
Abstract: This paper aims to propose a two-phase model integrated patient scheduling and medical device maintenance to improve their reliability, reduce operating costs, and increase operating efficiency. In this paper, one patient scheduling problem with time-window deteriorating maintenance is studied. The objective is to minimize the maximum tardiness of all patients. First, a two-phase mathematical model is developed to characterize the problem. One model is used to solve the lower bound of the number of maintenance activities, and the other is used to obtain the patient scheduling solution. Then, one heuristic is developed for the problem. Finally, numerical experiments can be performed to indicate the efficiency and effectiveness of the proposed methods. The results show that the proposed methods have a better performance for the patient scheduling problem and can be able to obtain one good solution in a short computation time. Few studies have been carried out to integrate decisions between patient scheduling and device maintenance. Their considerations are either incomplete or not realistic enough. A more comprehensive and realistic two-phase model is proposed in this paper.
Keywords: Patient scheduling; Maximum tardiness; Medical device; Time-window deteriorating maintenance; Virtual maintenance.
Machine vision for characterization of some phenomic features of plant parts in distinguishing varieties A review
by Nachiket Kotwaliwale, Karan Singh, Shyamal Kumar Chakrabarty, Monika Joshi, Abhimannyu Kalne, Krishna Kumar Gangopadhyay, Nabarun Bhattacharyya, Amitava Akuli, Gopinath Bej, Madhvi Tiwari, Divya Aggarwal
Abstract: Phenomic features of plant parts are important varietal traits for all crops and form part of the DUS (Distinctiveness, Uniformity and Stability) characterization protocols. Manual methods for measurement of these traits are expensive, less consistent and time consuming hence machine vision has been used in recent researches. The machine vision systems employed for this purpose consist of acquisition systems (hardware) and image processing and analysis system (software). The area of machine vision has developed during last few decades during which there have been many improvements in the employed hardware and software. Major work has been reported on use of seed and fruit images; however images of other plant parts like leaves, roots, flowers etc. have also been used. A variety of techniques have been reported for analysis of features in order to distinguish among different crop varieties.
Keywords: Machine vision; crop variety identification; phenomic traits.
Performance Analysis of Intrinsic Embedded Evolvable Hardware using Memetic and Genetic Algorithms
by Ranjith Chandrasekharan, Joy Vasantha Rani S.P
Abstract: This paper discusses the performance analysis of memetic and genetic algorithms (GA and MA) as the optimising strategy for the design of embedded evolvable hardware. The optimisation algorithm with the fitness evaluation searches for the best configuration to evolve the hardware model. Here, an experimental setup is carried to intrinsically evolve combinational circuits to test the performance of MA and GA. The complete evaluation and evolution is built on a single Virtex 6 (XC6VLX240T-1FFG1156) ML605 Evaluation Kit FPGA. A Virtual Reconfigurable Architecture (VRA) with the hardware fitness circuit is modelled as a second reconfigurable layer over the Field Programmable Gate Array (FPGA) to configure the target combinational logic. A FPGA soft core processor evaluates the search algorithm and the best solutions are utilised for the hardware evolution. The experimentation results showed that convergence and evolution time of MA was faster compared to GA when the search space was large. Thus, proving MA is a better option for large search space evaluations for evolvable hardware architectures.
Keywords: evolvable hardware; EHW; embedded evolvable hardware; evolutionary algorithm; genetic algorithm; memetic algorithm; MicroBlaze processor; VRA; Virtual Reconfigurable Architecture; evolution speed; evaluation time; combinational circuits; intrinsic evolution; Bio-Inspired algorithm.
Weight Learning from Cost Matrix in Weighted Least Squares Model Based on Genetic Algorithm
by Hong Zhu, Peng Yao, Xizhao Wang
Abstract: In real life, it is a common phenomenon that different misclassification causes different cost. Given a misclassification cost matrix (MCM), cost-sensitive learning is aiming at decreasing the overall misclassification cost rather than simply reducing the misclassification rate. Weighted Least Squares (WLS) model is acknowledged as an effective way of cost sensitive learning. However, the weights in WLS model are generally unknown and finding these weights is usually difficult. In this paper we put forward a new approach to learning these weights of WLS model from a given MCM based on a genetic algorithm. A comparative study shows that our proposed approach has an overall cost of misclassification significantly smaller than the existing cost-sensitive learning methods.
Keywords: cost-sensitive learning; misclassification cost matrix; weighted least squares model; genetic algorithm.
A Memetic Imperialist Competitive Algorithm with Chaotic Maps for Multilayer Neural Network Training
by Seyed Jalaleddin Mousavirad, Azam Asilian Bidgoli, Hossein Ebrahimpour-komleh, Gerald Schaefer
Abstract: The performance of artificial neural networks (ANNs) is largely dependent on the success of the training process. Gradient descent-based methods are the most widely used training algorithms but have drawbacks such as ending up in local minima. One approach to overcome this is to use population-based algorithms such as the imperialist competitive algorithm (ICA) which is inspired by the imperialist competition between countries. In this paper, we present a new memetic approach for neural network training to improve the efficacy of ANNs. Our proposed approach -- Memetic Imperialist Competitive Algorithm with Chaotic Maps (MICA-CM) -- is based on a memetic ICA and chaotic maps, which are responsible for exploration of the search space, while back-propagation is used for an effective local search on the best solution obtained by ICA. Experiment results confirm our proposed algorithm to be highly competitive compared to other recently reported methods.
Keywords: Imperialist competitive algorithm; Neural network training; Chaotic map; Back-propagation algorithm; memetic computing.
FEATURE SELECTION USING IMPROVED LION OPTIMIZATION ALGORITHM FOR BREAST CANCER CLASSIFICATION
by Sudha M N, Selvarajan S, Suganthi M
Abstract: Feature selection plays an important role in breast cancer classification. Feature selection identifies the most informative feature subset from feature set that can accurately classify the given data. The texture features, intensity histogram features, shape features and radial distance features have been extracted from Mammogram image and the optimal feature set has been obtained using improved lion optimization algorithm (ILOA). The overall accuracy of a classifier is used as a fitness value for ILOA. In the proposed work minimum distance classifier, K-Nearest Neighbor Classifier and Support Vector machine have been used. The proposed ILOA technique can efficiently find small feature subsets and able to classify the breast cancer data set with a very excellent accuracy. The performance of the ILOA is compared with the Cuckoo Search and Harmony Search. Experimental result shows that the result obtained from minimum distance classifier through ILOA is more accurate than the other algorithm. These algorithms can provide valuable information to the physician in medical pathology.
Keywords: Breast Cancer Classification; Feature Extraction; Improved Lion Optimization Algorithm; Cuckoo Search and Harmony Search.
A New Replica Placement Strategy Based on Multi-objective Optimization for HDFS
by Wang Yang, Zhang Qingfu, Li Yangyang, Dhish Saxena
Abstract: Distributed storage systems like the Hadoop Distributed File System (HDFS) constitute the core infrastructure of cloud platforms which are well poised to deal with big-data. An optimized HDFS is critical for effective data management in terms of reduced file service time and access latency, improved file availability and system load balancing. Recognizing that the file-replication strategy is key to an optimized HDFS, this paper focuses on the file-replica placement strategy while simultaneously considering storage and network load. Firstly, the conflicting relationship between storage and network load is analyzed and a bi-objective optimization model is built, following which a multi-objective optimization memetic algorithm based on decomposition (MOMAD) and its improved version are used. Compared to the default strategy in HDFS, the file-replica placement strategies based on multi-objective optimization provide more diverse solutions. And competitive performance could be obtained by the proposed algorithm.
Keywords: Hadoop; HDFS; replica placement; multi-objective optimization; memetic algorithm.
Adaptive Neighborhood Size Adjustment in MOEA/D-DRA
by Meng Xu
Abstract: The multiobjective optimization algorithms based on decomposition(MOEA/D) is a well-known multiobjective optimization algorithms(MOEAs). MOEA/D was proposed by Zhang and Li in 2007s. MOEA/D decomposes a multiobjective problem into a set of scalar single objective subproblems using the aggregation function and the evolutionary operator. The variant of the dynamic resource allocation strategy in MOEA/D(MOEA/D-DRA) has the outstanding performance on CEC2009, the MOEA/D-DRA using the strategy of resource allocation. It cares about the convergence and ignores the diversity. MOEA/D-DRA is very sensitive to the neighbourhood size. In this paper, we present a new enhanced MOEA/D-DRA strategy based on the adaptive neighbourhood size adjustment(MOEA/D-DRA) to increase the diversity. It focuses on the solutions density around of subproblems. The experiment results demonstrate that MOEA/D-ANA strategy performs the best compared with other five classical MOEAs on the CEC2009 test instances.
Keywords: MOEA/D; diversity; Neighborhood; CEC2009 test instances;.
Experimental study and Optimization in turning Process of EN8 steel using RSM with Hybrid Algorithm Approach
by Thangarasu S K, Shankar Subramaniam, Navin Prasath Rajagopal
Abstract: In this study, the effects of cutting speed, cutting feed and depth of cut on surface roughness, tool wear and cutting force components in the turning were experimentally investigated for different tool conditions. Three-factor (cutting speed, cutting feed and depth of cut) and three-level fractional experiment designs completed with a statistical analysis of variance (ANOVA) were performed. Mathematical models for surface roughness and cutting force and tool wear components were developed using the response surface methodology (RSM). The work piece material selected for this work is EN8 steel and the tool inserts used are CNMG 120408 grade, TiN coated cemented carbide tool. Since the output responses for the same input setting may vary with different tool conditions hence the experiments were conducted for fresh tool and worn out tool. The three considered output responses (cutting force, tool wear and surface roughness) are to be minimized. A quadratic empirical model for each response is developed along with the combined optimization of the response using RSM. For each cutting test the cutting force, tool wear and surface roughness was measured for both fresh and worn out tool. Finally an optimum cutting speed of 90 mm/min and 270 mm/min was determined for both fresh tool and worn out tool respectively. The results concluded that PSO algorithm produces better optimisation when compared to Firefly algorithm and Cuckoo search algorithm
Keywords: Firefly algorithm; Response surface methodology; coated carbide inserts; Design of experiments; Swarm intelligent technique; Grey relational analysis.
Cuckoo search algorithm with different distribution strategy
by Hengliang Tang, Fei Xue
Abstract: Cuckoo Search (CS) is a new meta-heuristic search algorithm based on the obligate nest parasitism of cuckoos and combining the characteristic flight of some birds and fruit flies. In order to study the influence of distribution strategy on Cuckoo Search Algorithm, in the paper, introduces Cauchy distribution, Gaussian distribution, Uniform distribution and Levy distribution, analysis the performance of Cuckoo Search algorithm by the method of pair combination. In order to verify the effectiveness of the algorithm, 28 typical test functions proposed by CEC2013 were taken as examples for testing, and the experimental results showed the effectiveness of the algorithm. Simulation results show that the hybrid distribution of Levy distribution and Cauchy distribution can make the cuckoo search algorithm perform better.
Keywords: optimization algorithm; cuckoo search algorithm; distribution strategy.
Special Issue on: New Trends in Many-Objective Optimisation
Lexi-search algorithm for one to many multidimensional bi-criteria unbalanced assignment problem
by Thenepalle Jayanth Kumar, Singamsetty Purusotham
Abstract: The classical assignment problem involves one-to-one assignment between the persons and jobs. However, most of the real world scenarios, it is hard to make a balance between persons and jobs, therefore the interest on the studies of unbalanced assignment problems continuously increased. This paper deals a one-to-many multidimensional unbalanced assignment problem with two conflicting objectives, in which the first objective minimizes the total processing time and the second objective maximizes the overall productivity/profit on performing n jobs by m (m Keywords: multidimensional bi-criteria unbalanced assignment problem; Lexi-search algorithm; pattern recognition technique.