Qualification: 
Ph.D, M.Tech, BE

Dr. Surekha P. currently serves as an Assistant Professor (Sr. Gr.) in the department of Electrical and Electronics Engineering, School of Engineering, Amrita Vishwa Vidyapeetham, Bengaluru. She has received her B. E. Degree in Electrical and Electronics Engineering from Bharathiar University, Coimbatore in 2001, Master Degree in Control Systems from PSG College of Technology, Coimbatore in 2006, and Ph. D. in Bio-Inspired algorithms for Optimization from Anna University in 2014. Her research areas include Virtual Instrumentation, Image Processing, Robotics, Machine Learning and Computational Intelligence.

Publications

Publication Type: Journal Article

Year of Publication Title

2018

P. Surekha, Gurudath, P., Prithvi, R., and Ananth, V. G. .Ritesh, “Automatic License Plate Recognition using Image Processing and Neural Network”, ICTACT Journal on Image and Video Processing, vol. 8, no. 4, 2018.[Abstract]


In recent times, the number of vehicles on road has exponentially risen due to which traffic congestion and violations are a menace on roads. Automatic License Plate Recognition system can be used to automate the process of traffic management thereby easing out the flow of traffic and strengthening the access control systems. In this paper, we compare the efficiency achieved by morphological processing and edge processing algorithms. A detailed analysis and optimization of neural network parameters such as regularization parameter, number of hidden layer units and number of iterations is done. Here, a scheme is designed for implementation in real time and controlled using a graphical user interface suitable for the application of parking security in offices, institutions, malls, etc. The system utilizes image processing techniques and machine learning algorithms running on matlab and Raspberry Pi 2B to obtain the results with an efficiency of 97%.

More »»

2015

P. Surekha and Sumathi, S., “A Novel Approach to Solve Unit Commitment and Economic Load Dispatch Problem using IDE-OBL”, Journal of Scientific and Industrial Research, vol. 74, no. 7, pp. 395-399, 2015.[Abstract]


The non-convex and combinatorial nature of the UC-ELD problems requires the application of heuristic algorithms to generate optimal schedules. In studies reported so far, the Unit Commitment and the Economic Load Dispatch problems are solved as separate problems. In the addressed work, the commitment and de-commitment of generating units is obtained using a Genetic Algorithm (GA), and the optimal load distribution of the scheduled units is obtained using Improved Differential Evolution with Opposition Based Learning (IDE-OBL). The power demand is varied for 24 hours to determine the schedule in the IEEE 30 bus system including transmission losses, power balance and generator capacity constraints. Optimal distribution of load among generating units, fuel cost per hour, power loss, total power and computational time are computed for each of the test systems using the intelligent algorithms. From the comparative analysis, it can be concluded that GA-IDE-OBL is a better approach for solving UC-ELD problems in terms of optimal solution, robustness, and computational efficiency.

More »»

2012

P. Surekha and Sumathi, S., “An Improved Differential Evolution Algorithm for Optimal Load Dispatch in Power Systems including transmission losses”, Journal of Electrical and Electronics Engineering, vol. 11, no. 2, pp. 1379-1390, 2012.[Abstract]


This paper presents an Improved Differential Evolution (IDE) algorithm to solve Economic Load Dispatch (ELD) problem with non-smooth fuel cost curves considering transmission losses, power balance and capacity constraints. The proposed IDE varies from the Standard Differential Evolution (SDE) algorithm in terms of three basic factors. The initial population in IDE is generated through the concept of Opposition Based Learning (OBL), applies tournament based mutation and uses only one population set throughout the optimization process. The performance of the proposed algorithm is investigated and tested with two standard test systems, the IEEE 30 bus 6 unit system and the 20 unit system. The experiments showed that the searching ability and convergence rate of IDE is much better than the SDE. The results of the proposed approach were compared in terms of fuel cost, computational time, power loss and individual generator powers with existing SDE and other meta-heuristics in literature. The proposed method seems to be a promising approach for ELD problems based on the solution quality and the computational efficiency.

More »»

2012

P. Surekha and Sumathi, S., “An Integrated GA-ABC optimization technique to solve unit commitment and economic dispatch problems”, Asian Journal of Scientific Research, vol. 5, no. 3, pp. 93-107, 2012.[Abstract]


Unit Commitment (UC) and Economic Load Dispatch (ELD) problems are significant research areas to determine the economical generation schedule with all generating unit constraints, such as unit ramp rates, unit minimum and maximum generation capabilities and minimum up-time and down-time. This study proposed a technique for solving the UC and ELD problems using bio-inspired techniques like Genetic Algorithm (GA) and Artificial Bee Colony (ABC) Optimization. The experiments are performed in two phases: UC phase and ELD phase. In the UC phase, a turn-on and turn-off schedule for a given combination of generating units is performed using GA, thus satisfying a set of dynamic operational constraints. During the second ELD phase, the pre-committed schedules are optimized and the optimal load is distributed among the scheduled units using ABC algorithm. The effectiveness of the proposed technique is investigated on two test systems namely, IEEE 30 bus system and ten unit system. Experimental results prove that the proposed method is capable of yielding higher quality solution including mathematical simplicity, fast convergence, diversity maintenance, robustness and scalability for the complex UC-ELD problem.

More »»

2012

P. Surekha and Sumathi, S., “Performance comparison of optimization techniques on robust digital image watermarking against attacks”, Applied Artificial Intelligence – Taylor and Francis, vol. 26, no. 7, pp. 615-644, 2012.[Abstract]


Increasing illegal exploitation and imitation of digital images in the field of image processing has led to the urgent development of copyright protection methods. Digital watermarking has proved to be the most effectivemethod for protecting illegal authentication of data. In this article, we propose a hybrid digital-image watermarking scheme based on computational intelligence paradigms such as a genetic algorithm (GA) and particle swarm optimization (PSO). The watermark image is embedded into the host image using discrete wavelet transform (DWT). During the extraction process, GA, PSO, and the hybrid combination of GA and PSO are applied to improve the robustness and fidelity of the watermarked image by evaluating the fitness function. The perceptual transparency and the robustness of both the watermarked and the extracted images is evaluated by applying filtering attacks, additive noise, rotation, scaling, and JPEG compression attacks to the watermarked image. From the simulation results, the performance of the hybrid particle swarm optimization technique is proved best, based on the computed robustness and transparency measures, as well as the evaluated parameters of elapsed time, computation time, and fitness value. The performance of the proposed scheme was evaluated with a set of 50 textures images taken from online resources of Tampere University of Technology, Finland, and the entire algorithm for different stages was simulated using MATLAB R2008b.

More »»

2012

P. Surekha and Sumathi, S., “Solving Economic Load Dispatch problems using Differential Evolution with Opposition Based Learning”, WSEAS Transactions on Information Science and Applications, vol. 9, no. 1, pp. 1-13, 2012.[Abstract]


This paper presents a Differential Evolution algorithm combined with Opposition Based Learning (DE-OBL) to solve Economic Load Dispatch problem with non-smooth fuel cost curves considering transmission losses, power balance and capacity constraints. The proposed algorithm varies from the Standard Differential Evolution algorithm in terms of three basic factors. The initial population is generated through the concept of Opposition Based Learning, applies tournament based mutation and uses only one population set throughout the optimization process. The performance of the proposed algorithm is investigated and tested with two standard test systems, the IEEE 30 bus 6 unit system and the 20 unit system. The experiments showed that the searching ability and convergence rate of the proposed method is much better than the standard differential evolution. The results of the proposed approach were compared in terms of fuel cost, computational time, power loss and individual generator powers with existing differential evolution and other meta-heuristics in literature. The proposed method seems to be a promising approach for load dispatch problems based on the solution quality and the computational efficiency.

More »»

2011

P. Surekha and Sumathi, S., “Planning, Scheduling and Optimizing Job Shop Scheduling Problem Using Genetic Algorithm”, International Journal of Artificial Intelligent Systems and Machine Learning, vol. 3, no. 1, 2011.[Abstract]


Evolutionary algorithms are having a leading focus in solving several optimization problems. Job-shop scheduling problem (JSSP) is one among the common NP-hard combinatorial optimization problems used to allocate machines for a set of jobs over time and hence optimizing the processing time, waiting time, completion time, and makespan. In this paper an eminent approach based on the paradigm of evolutionary computation for solving job shop scheduling problem is proposed. The solution to the problem is alienated into three phases; planning, scheduling and optimization. Initially, the jobs are scheduled, in which the machines and jobs with respect to levels are planned. Scheduling is optimized using Genetic Algorithm (GA), which is a powerful search technique, built on a model of the biological evolution. Like natural evolution GA deal with a population of individuals rather than a single solution and fuzzy interface is applied for planning and scheduling of jobs. The Fisher and Thompson 10x10 instance (FT10) problem is selected as the experiment problem and the algorithm is simulated using the MATLAB R2008B software.

More »»

2011

P. Surekha and Sumathi, S., “PSO and ACO based approach for solving combinatorial Fuzzy Job Shop Scheduling Problem”, International Journal of Computer Technology and Applications, vol. 2, no. 1, pp. 112-120, 2011.[Abstract]


This paper proposes a prominent approach to solve job shop scheduling problem based on Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO). The steps to generate the solution are grouped as planning, scheduling and optimization. Initially, fuzzy logic is applied for planning and then the scheduling stage is optimized using PSO and ACO. The processing order of jobs for each machine is scheduled with an objective to find a feasible plan that minimizes the makespan, completion time and waiting time. The well known Fisher and Thompson 10x10 instance (FT10) and Adams, Balas, and Zawack 10x10 instance (ABZ10) problems are selected as the experimental benchmark problems. The results of the applied optimization techniques are compared with the computed parameters like makespan, waiting time, completion time and elapse time. The performance evaluation of optimization techniques are analysed for both benchmark problems and the PSO technique is found superior

More »»

2011

P. Surekha and Sumathi, S., “Optimization of Pre-Watermarked Digital Images using Genetic Algorithm”, International Journal of Imaging and Robotics, vol. 5, no. S.11, pp. 59-79, 2011.[Abstract]


In this paper, we propose a digital image watermarking scheme based on Genetic Algorithm (GA). The input digital host images undergo a set of pre-watermarking stages like image segmentation, feature extraction, orientation assignment, and image normalization to obtain image invariance properties when subject to attacks. Expectation Maximization (EM) algorithm is used to segment the images and the features are extracted using Difference of Gaussian (DoG) technique. The feature maps from the feature extraction methods locate the magnitude by orientation assignment making the circular regions invariant. The resultant image is normalized by scaling to acquire the scaling invariance for the circular region. The watermark image is then embedded into the host image using Discrete Wavelet Transform (DWT). During the extraction process, GA is applied to improve the robustness, and fidelity of the watermarked image by evaluating the fitness function. The perceptual transparency and the robustness of the watermarked and the extracted images are evaluated by applying filtering attacks, additive noise, rotation, scaling and JPEG compression attacks to the watermarked image. From the simulation results, the performance of the optimization technique can be understood based on the computed robustness and transparency measures along with the evaluated parameters like elapsed time, computation time and fitness value. The performance of proposed scheme was evaluated with a set of 50 textures images taken from online resources of Tampere University of Technology, Finland and the entire algorithm for different stages was simulated using MATLAB R2008b.

More »»

2011

P. Surekha and Sumathi, S., “A Self-adaptive Fuzzy C-means based Radial basis Function Network to solve Economic Load Dispatch Problems”, International Journal of Computer Applications, vol. 25, no. 4, pp. 50-59, 2011.[Abstract]


In recent decades, with a large increase in power demand, fuel cost, and limited fuel supply it has become very essential to run the power systems with minimum cost so that the committed units serve the expected load demand. The basic objective of Economic Load Dispatch (ELD) is to distribute the total generation among the generation units in operation, in order to meet the load demand at minimum operating cost while satisfying the system equality and inequality constraints. Nature inspired computing techniques like Artificial Neural Networks (ANN) are preferred for solving ELD problems because they do not impose any restrictions on the shape of the fuel cost curve and are capable of providing good solution quality, and higher precision solutions very close to the global optimum. In this paper, the application of Fuzzy c-means based Radial Basis Function Network (RBFN) to ELD is proposed in order to minimize the error function through a self adaptive process until the error is less than a given tolerance leading to a best solution. The applicability and viability for practical applications has been tested on two different power systems, viz., a IEEE 30 bus 6 unit test system and a 20 unit test system and the experiments were carried out on MATLAB R2008b software. Comparison of the results with the conventional Lambda Iteration method demonstrates the effectiveness of RBFN in solving ELD problems based on fuel cost, power loss, total generated power, algorithmic efficiency, and computational time.

More »»

2011

P. Surekha and Sumathi, S., “Solution To Multi-Depot Vehicle Routing Problem Using Genetic Algorithms”, World Applied Programming, vol. 1, no. 3, pp. 118-131, 2011.[Abstract]


The Multi-Depot Vehicle Routing Problem (MDVRP), a n extension of classical VRP, is a NP-hard problem for simultaneously determining the routes for several vehicles from multiple depots to a set of customers and then return to the same depo t. The objective of the problem is to find routes f or vehicles to service all the customers at a minimal cost in terms of number of routes and total travel distance, without violating the capacity and travel time constraints of the vehicles. The solution to the MDVRP, in this paper, is obtained through Genetic A lgorithm (GA). The customers are grouped based on distance to their nearest depots and then routed wi h Clarke and Wright saving method. Further the routes are scheduled and optimized using GA. A set of five different Cordeau’s benchmark instances (p01, p02, p03, p04, p06) from the online resource of University of Malaga, Spain were experimented using MATLAB R2008b software. The results were eval uated in terms of depot’s route length, optimal route, optimal distance, computational time, averag distance, and number of vehicles. Comparison of the experimental results with state-of-the-art tech niques shows that the performance of GA is feasible and effective for solving the multi-depot vehicle r outing problem. Key word: Multi-Depot Vehicle Routing Problem, Grouping, Rout ing, Scheduling, Genetic Algorithm.

More »»

2011

P. Surekha and Sumathi, S., “Implementation of Genetic Algorithm for a DWT based Image Watermarking Scheme”, ICTACT Journal of Soft Computing, vol. 2, no. 1, pp. 244-252, 2011.[Abstract]


This paper proposes a new optimization method for digital images in the Discrete Wavelet Transform (DWT) domain. Digital image watermarking has proved its efficiency in protecting illegal authentication of data. The amplification factor of the watermark is the significant parameter that helps in improving the perceptual transparency and robustness against attacks. The tradeoff between the transparency and robustness is considered as an optimization problem and is solved by applying Genetic Algorithm. The experimental results of this approach prove to be secure and robust to filtering attacks, additive noise, rotation, scaling, cropping and JPEG compression. The Peak Signal to Noise Ratio (PSNR), Mean Square Error (MSE), and computational time are evaluated for a set of images obtained from the Tampere University of Technology, Finland using the MATLAB R2008b software.

More »»

2011

P. Surekha and Sumathi, S., “Application of Particle Swarm Optimization for Solving Multi-Depot Vehicle Routing Problems”, International Journal of Artificial Intelligent Systems and Machine Learning, vol. 3, no. 11, 2011.[Abstract]


The Multi-Depot Vehicle Routing Problem (MDVRP), an extension of classical VRP, is a NP-hard problem for simultaneously determining the routes for several vehicles from multiple depots to a set of customers and then return to the same depot. The objective of the problem is to find routes for vehicles to service all the customers at a minimal cost in terms of number of routes and total travel distance, without violating the capacity and travel time constraints of the vehicles. The solution to the MDVRP, in this paper, is obtained through Particle Swarm Optimization (PSO). The customers are grouped based on distance to their nearest depots and then routed with Clarke and Wright saving method. Further the routes are scheduled and optimized using POS. A set of five different Cordeau’s benchmark instances (p01, p02, p03, p04, p06) from the online resource of University of Malaga, Spain were experimented using MATLAB R2008b software. The results were evaluated in terms of depot’s route length, optimal route, optimal distance, computational time, average distance, and number of vehicles. Comparison of the experimental results with state-of-the-art techniques shows that the performance of PSO is feasible and effective for solving the multi-depot vehicle routing problem.

More »»

2011

P. Surekha and Sumathi, S., “Solution to the Job Shop Scheduling Problem using Hybrid Genetic Swarm Optimization based on (λ,1) Fuzzy Processing Time”, European Journal on Scientific Research, vol. 64, no. 2, pp. 168-188, 2011.[Abstract]


Job-shop scheduling problem (JSSP) is one of the well-known hardest combinatorial optimization problems; lacking efficient exact solutions. In this paper, we propose a hybrid algorithm with Particle Swarm Optimization (PSO) and Genetic Algorithm (GA), called as Fuzzy Genetic Swarm Optimization (FGSO) for solving the scheduled JSSP problems with fuzzy processing time. The objective of JSSP is to minimize the makespan from a job sequence selected by ranking fuzzy numbers in the (λ,1) interval based on signed distance. The hybrid algorithm is modeled on the concepts of Darwin's theory based on natural selection and evolution, and on cultural and social rules derived from the swarm intelligence. The approach is tested on a set of 162 standard instances obtained from the OR literature and Taillard benchmarks. The feasibility and efficiency of the proposed method is evaluated in comparison with other state-of-the-art approaches. The computational results validate the effectiveness of the proposed algorithm.

More »»

2010

P. Surekha and Sumathi, S., “A Survey of Computational Intelligence Techniques in Industrial Applications”, International Journal of Advanced Engineering and Applications, pp. 91-96, 2010.

2010

P. Surekha and Sumathi, S., “Applications of Computational Intelligence Paradigms: A survey”, Journal of software project management and quality assurance, International Sciences Press, vol. 1, no. 2, pp. 85-97, 2010.

2010

P. Surekha and Sumathi, S., “Genetic Algorithm and Ant Colony Optimization for Optimizing Combinatorial Fuzzy Job Shop Scheduling Problems”, International Journal of Artificial Intelligent Systems and Machine Learning, vol. 2, no. 9, 2010.[Abstract]


In this paper, we present a genetic algorithm and ant colony optimization algorithm for solving the Job-shop Scheduling Problem (JSSP). The genetic algorithm generates the initial population, selects the individuals for reproduction creating new individuals. Ant Colony Optimization (ACO) is a metaheuristic inspired by the foraging behavior of ants, used to solve this combinatorial optimization problem. In JSSP ants move from one machine (nest) to another machine (food source) depending upon the job flow, thereby optimizing the sequence of jobs. The sequence of jobs is scheduled using Fuzzy logic and optimized using GA and ACO. The makespan, completion time, makespan efficiency, algorithmic efficiency and the elapsed time for the genetic algorithm and the ant colony algorithm are evaluated and compared. Computational results of these optimization algorithms are compared by analyzing the JSSP benchmark instances, FT10 and the ABZ10 problems.

More »»

2010

P. Surekha and Sumathi, S., “An Optimization Approach to Digital Image Watermarking Based On GA and PSO”, International Journal of Digital Image Processing, , vol. 2, no. 9, 2010.[Abstract]


The increasing effect of illegal exploitation and imitation of digital images in the field of image processing has led to the urgent development in the growth of copyright protection methods. Digital watermarking has proved best in protecting illegal authentication of data. In this paper, we propose a hybrid digital image watermarking scheme based on computational intelligence paradigms like Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The watermark image is embedded into the host image using Discrete Wavelet Transform (DWT). During the extraction process, GA, and PSO are applied to improve the robustness, and fidelity of the watermarked image by evaluating the fitness function. The perceptual transparency and the robustness of the watermarked and the extracted images are evaluated by applying filtering attacks, additive noise, rotation, scaling and JPEG compression attacks to the watermarked image. From the simulation results the performance of the Particle Swarm Optimization technique is proved best based on the computed robustness and transparency measures along with the evaluated parameters like elapsed time, computation time and fitness value. The performance of proposed scheme was evaluated with a set of 50 textures images taken from online resources of Tampere University of Technology, Finland and the entire algorithm for different stages was simulated using MATLAB R2008b

More »»

2010

P. Surekha and Sumathi, S., “Solving Fuzzy Based Job Shop Scheduling Problems using GA and ACO”, International Journal of Emerging Trends in Computing and Information Sciences, vol. 1, no. 2, pp. 95-102, 2010.[Abstract]


In this paper, we present a genetic algorithm and ant colony optimization algorithm for solving the Job-shop Scheduling Problem (JSSP). The genetic algorithm comprises of different stages like generating the initial population, selecting the individuals for reproduction and reproducing new individuals. Ant Colony Optimization (ACO) is a metaheuristic inspired by the foraging behavior of ants, which is also used to solve this combinatorial optimization problem. In JSSP ants move from one machine (nest) to another machine (food source) depending upon the job flow, thereby optimizing the sequence of jobs. The sequence of jobs is scheduled using Fuzzy logic and optimizes using GA and ACO. The makespan, completion time, makespan efficiency, algorithmic efficiency and the elapsed time for the genetic algorithm and the ant colony algorithm are evaluated and compared. The improvement in the performance of the algorithms based on the computed parameters is also discussed in this paper. Computational results of these optimization algorithms are compared by analyzing the JSSP benchmark instances, FT10 and the ABZ10 problems.

More »»

2010

P. Surekha and Sumathi, S., “Application of GA and PSO to the Analysis of Digital Image Watermarking Processes”, International Journal of Computer Science and Emerging Technologies, vol. 1, no. 4, 2010.[Abstract]


The increasing effect of illegal exploitation and imitation of digital images in the field of image processing has led to the urgent development in the growth of copyright protection methods. Digital watermarking has proved best in protecting illegal authentication of data. In this paper, we propose a digital image watermarking scheme based on computational intelligence paradigms like Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The input digital host images undergo a set of pre-watermarking stages like image segmentation, feature extraction, orientation assignment, and image normalization to obtain image invariance properties when subject to attacks. Expectation Maximization (EM) algorithm is used to segment the images and the features are extracted using Difference of Gaussian (DoG) technique. The feature maps from the feature extraction methods locate the magnitude by orientation assignment making the circular regions invariant. The resultant image is normalized by scaling to acquire the scaling invariance for the circular region. The watermark image is then embedded into the host image using Discrete Wavelet Transform (DWT). During the extraction process, GA, and PSO are applied to improve the robustness, and fidelity of the watermarked image by evaluating the fitness function. The perceptual transparency and the robustness of the watermarked and the extracted images are evaluated by applying filtering attacks, additive noise, rotation, scaling and JPEG compression attacks to the watermarked image. From the simulation results the performance of the Particle Swarm Optimization technique is proved best based on the computed robustness and transparency measures along with the evaluated parameters like elapsed time, computation time and fitness value. The performance of proposed scheme was evaluated with a set of 50 textures images taken from online resources of Tampere University of Technology, Finland and the entire algorithm for different stages was simulated using MATLAB R2008b.

More »»

2006

P. Surekha and Sumathi, S., “Genetic Algorithm for global path planning in a static environment implemented on a mobile robot”, Technology Journal of PSG college of Technology, Coimbatore, vol. 2, no. 3, pp. 20-32, 2006.

Publication Type: Conference Paper

Year of Publication Title

2018

P. Surekha, Rachan, O., Venu, N., and Shetty, A., “Automated Drone to Survey Orchards/Farms using Renewable Energy”, in International Conference on Innovation in Signal Processing and Communication - 2018, Chennai, India. , 2018.

2010

P. Surekha, P, Y., and Sumathi, S., “A Genetic Algorithm based Optimization Technique for Digital Image Watermark Embedding and Extraction”, in International Conference on Innovative Research in Engineering and Technology (ICIRET-2010), India, 2010.

2010

P. Surekha, P. Mohanaraajan, R. A., and Sumathi, S., “Planning, Scheduling and Optimizing Job Shop Scheduling Problem using Genetic Algorithm”, in International Conference on Innovative Research in Engineering and Technology (ICIRET-2010), , India, 2010.

2010

P. Surekha, P, Y., and Sumathi, S., “An efficient optimization technique for digital watermarking in image processing”, in IEEE Int. Conf. Intelligent Control and Information Processing (ICICIP), , Dalian, China, 2010.[Abstract]


In this paper, mathematical modeling of digital watermarking is proposed to approximate the image based on the generalized Gaussian distribution. Using maximum a posteriori probability based image segmentation and fuzzy c means image segmentation, the cover image is segmented into several homogeneous areas. In EM segmentation, every region in the image is represented by a generalized Gaussian distribution. The rotation invariant features are extracted from the segmented areas and are selected as reference points by DoG filter and principal component analysis. Rotation and scaling invariance is obtained through the process of image normalization. The watermark embedding and extraction schemes are analyzed mathematically based on the established mathematical model. The mathematical relationship between fidelity and robustness is established. A hybrid watermarking technique is proposed to improve the similarity of extracted watermarks. Furthermore, genetic algorithm (GA) is simultaneously performed to find the optimal values such as fitness value, best points and CPU time. This method has been proved its robustness to geometric attacks through experiments. The experimental results show the effectiveness and accuracy of the proposed scheme.

More »»

2010

P. Surekha, P. Mohanaraajan, R. A., and Sumathi, S., “A methodology to schedule and optimize job shop scheduling using computational intelligence paradigms”, in IEEE Int. Conf. Intelligent Control and Information Processing (ICICIP), Dalian, China, 2010.[Abstract]


Evolutionary computation is emerging as a novel engineering computational paradigm, which plays a significant role in several optimization problems. Job-shop scheduling problem (JSSP) is one among the common NP-hard combinatorial optimization problems. The JSSP is defined as allocation of machines for a set of jobs over time in order to optimize the performance measure satisfying certain constraints like processing time, waiting time, completion time, etc. In this paper an eminent approach based on the paradigms of evolutionary computation for solving job shop scheduling problem is proposed. The solution to the problem is alienated into three phases; planning, scheduling and optimization. Initially, the jobs are scheduled, in which the machines and jobs with respect to levels are planned. Scheduling is optimized using evolutionary computing algorithm such as Genetic Algorithm (GA), which is a powerful search technique, built on a model of the biological evolution. Like natural evolution GA deal with a population of individuals rather than a single solution and fuzzy interface is applied for planning and scheduling of jobs. The well known Fisher and Thompson 10×10 instance (FT10) problem is selected as the experiment problem. The discussion on the proposed techniques and paths of future research are summarized.

More »»

2010

P. Surekha, P. Mohanaraajan, R. A., and Sumathi, S., “Genetic Algorithm and Particle Swarm Optimization Approaches to Solve Combinatorial Job Shop Scheduling Problems”, in IEEE Int. Conf. Computational Intelligence and Computing Research, Tamil Nadu College of Engineering, Coimbatore, India, 2010.[Abstract]


In this paper an eminent approach based on the paradigms of evolutionary computation for solving job shop scheduling problem is proposed. The solution to the problem is alienated into three phases; planning, scheduling and optimization. Initially, fuzzy logic is applied for planning and then scheduling is optimized using evolutionary computing algorithms such as Genetic Algorithm (GA), and Particle Swarm Optimization (PSO). The well known Adams, Balas, and Zawack 10 × 10 instance (ABZ10) problem is selected as the experimental benchmark problem and simulated using MATLAB R2008b. The results of the optimization techniques are compared with the parameters like makespan, waiting time, completion time and elapse time. The performance evaluation of optimization techniques are analysed and the superior evolutionary technique for solving job shop scheduling problem is determined.

More »»

2010

P. Surekha, P. Mohanaraajan, R. A., and Sumathi, S., “Ant Colony Optimization for Solving Combinatorial Fuzzy Job Shop Scheduling Problems”, in Int. Conf. on Communication and Computational Intelligence, Erode, India, 2010.[Abstract]


In this paper, we present an ant colony optimization algorithm for solving the Job-shop Scheduling Problem (JSSP). Ant Colony Optimization (ACO) is a metaheuristic inspired by the foraging behavior of ants, which is also used to solve this combinatorial optimization problem. In JSSP ants move from one machine (nest) to another machine (food source) depending upon the job flow, thereby optimizing the sequence of jobs. The sequence of jobs is scheduled using Fuzzy logic and optimized using ACO. The makespan, completion time, makespan efficiency, algorithmic efficiency and the elapsed time for the ant colony algorithm are evaluated. Computational results of the optimization algorithm are evaluated by analyzing the two popular JSSP benchmark instances, FT10 and the ABZ10 problems and the simulation is carried out using the software, MATLAB.

More »»

2007

P. Surekha and Sumathi, S., “Vision based intelligent mobile robot for face recognition and obstacle avoidance using Neural Networks and Genetic Algorithms”, in National Conference on Microelectronics and Communication , Chennai , 2007.

2006

P. Surekha and Sumathi, S., “A Soft Computing Approach to a Surveillance System based on Audio and Video sensory agents cooperating with a Mobile Robot”, in National Conference on Advanced Computing at MIT, Chennai , 2006.

2006

P. Surekha and Sumathi, S., “Hybrid Intelligent Mobile Robot with Video and Audio sensory agents Incorporating a Web Interface”, in National Conference on Modern Trends in Electrical and Electronic Systems , Salem , 2006.

2006

P. Surekha and Sumathi, S., “A Soft Computing based Online Face Recognition system using a Robot as an Intelligent Surveillance Agent”, in National Conference on Soft Computing Techniques for Engineering Applications , Rourkela , 2006.

2006

P. Surekha and Sumathi, S., “Soft-i-Robot: An Internet-Based Intelligent Multimedia Robot Security System Using Soft Computing Paradigms”, in 3rd International Conference on Artificial Intelligence in Engineering and Technology (ICAIET 2006) , Kota Kinabalu , 2006.

2005

P. Surekha and Sumathi, S., “Image Segmentation using K-means Algorithms for Robots”, in National Conference NCIEES’05 , Coimbatore , 2005.

2005

P. Surekha and Sumathi, S., “Improvement of speed control of DC motor by Fuzzy PID tuning”, in National Conference NCIEES’05 , Coimbatore , 2005.

2004

P. Surekha and Sumathi, S., “Internet based remote control using Rabbit Microcontroller and an Embedded Ethernet board”, in National level conference PEDC’05 , Karaikudi , 2004.

Publication Type: Book

Year of Publication Title

2015

S. S., Ashok, K. L., and P. Surekha, Solar PV and Wind Energy Conversion Systems - An Introduction to Theory, Modeling with MATLAB/SIMULINK, and the Role of Soft Computing Techniques. Springer, 2015.[Abstract]


This textbook starts with a review of the principles of operation, modeling and control of common solar energy and wind-power generation systems before moving on to discuss grid compatibility, power quality issues and hybrid models of Solar PV and Wind Energy Conversion Systems (WECS). MATLAB/SIMULINK models of fuel cell technology and associated converters are discussed in detail. The impact of soft computing techniques such as neural networks, fuzzy logic and genetic algorithms in the context of solar and wind energy is explained with practical implementation using MATLAB/SIMULINK models.

This book is intended for final year undergraduate, post-graduate and research students interested in understanding the modeling and control of Solar PV and Wind Energy Conversion Systems based on MATLAB/SIMULINK.

- Each chapter includes “Learning Objectives” at the start, a “Summary” at the end and helpful Review Questions

- Includes MATLAB/SIMULINK models of different control strategies for power conditioning units in the context of Solar PV

- Presents soft computing techniques for Solar PV and WECS, as well as MATLAB/SIMULINK models, e.g. for wind turbine topologies and grid integration

- Covers hybrid solar PV and Wind Energy Conversion Systems with converters and MATLAB/SIMULINK models

- Reviews harmonic reduction in Solar PV and Wind Energy Conversion Systems in connection with power quality issues

- Covers fuel cells and converters with implementation using MATLAB/SIMULINK

More »»

2015

S. Sumathi, L. Kumar, A., and P. Surekha, Computational Intelligence Paradigms for Optimization Problems Using MATLAB/SIMULINK. CRC Press, 2015.[Abstract]


Considered one of the most innovative research directions, computational intelligence (CI) embraces techniques that use global search optimization, machine learning, approximate reasoning, and connectionist systems to develop efficient, robust, and easy-to-use solutions amidst multiple decision variables, complex constraints, and tumultuous environments. CI techniques involve a combination of learning, adaptation, and evolution used for intelligent applications.

Computational Intelligence Paradigms for Optimization Problems Using MATLAB®/ Simulink® explores the performance of CI in terms of knowledge representation, adaptability, optimality, and processing speed for different real-world optimization problems.

Focusing on the practical implementation of CI techniques, this book:

Discusses the role of CI paradigms in engineering applications such as unit commitment and economic load dispatch, harmonic reduction, load frequency control and automatic voltage regulation, job shop scheduling, multidepot vehicle routing, and digital image watermarking
Explains the impact of CI on power systems, control systems, industrial automation, and image processing through the above-mentioned applications
Shows how to apply CI algorithms to constraint-based optimization problems using MATLAB®m-files and Simulink® models
Includes experimental analyses and results of test systems
Computational Intelligence Paradigms for Optimization Problems Using MATLAB®/ Simulink® provides a valuable reference for industry professionals and advanced undergraduate, postgraduate, and research students.

More »»

2011

P. Surekha, Virtual Instrumentation using LabVIEW. India: ACME Learning, 2011.

2010

S. Sumathi and P. Surekha, Computational Intelligence Paradigms: Theory and Applications using MATLAB. CRC Press, Taylor and Francis, 2010.[Abstract]


Offering a wide range of programming examples implemented in MATLAB®, Computational Intelligence Paradigms: Theory and Applications Using MATLAB® presents theoretical concepts and a general framework for computational intelligence (CI) approaches, including artificial neural networks, fuzzy systems, evolutionary computation, genetic algorithms and programming, and swarm intelligence. It covers numerous intelligent computing methodologies and algorithms used in CI research.

The book first focuses on neural networks, including common artificial neural networks; neural networks based on data classification, data association, and data conceptualization; and real-world applications of neural networks. It then discusses fuzzy sets, fuzzy rules, applications of fuzzy systems, and different types of fused neuro-fuzzy systems, before providing MATLAB illustrations of ANFIS, classification and regression trees, fuzzy c-means clustering algorithms, fuzzy ART map, and Takagi–Sugeno inference systems. The authors also describe the history, advantages, and disadvantages of evolutionary computation and include solved MATLAB programs to illustrate the implementation of evolutionary computation in various problems. After exploring the operators and parameters of genetic algorithms, they cover the steps and MATLAB routines of genetic programming. The final chapter introduces swarm intelligence and its applications, particle swarm optimization, and ant colony optimization.

Full of worked examples and end-of-chapter questions, this comprehensive book explains how to use MATLAB to implement CI techniques for the solution of biological problems. It will help readers with their work on evolution dynamics, self-organization, natural and artificial morphogenesis, emergent collective behaviors, swarm intelligence, evolutionary strategies, genetic programming, and the evolution of social behaviors.

More »»

2010

P. Surekha, Evolutionary Algorithms using MATLAB. India: ACME Learning, 2010.

2008

S. Sumathi, Hamsapriya, T., and P. Surekha, Evolutionary Intelligence: An Introduction to theory and applications with MATLAB. Germany: Springer Verlag, 2008.[Abstract]


This book gives a good introduction to evolutionary computation for those who are first entering the field and are looking for insight into the underlying mechanisms behind them. Emphasizing the scientific and machine learning applications of genetic algorithms instead of applications to optimization and engineering, the book could serve well in an actual course on adaptive algorithms. The authors include excellent problem sets, these being divided up into "thought exercises" and "computer exercises" in genetic algorithm. Practical use of genetic algorithms demands an understanding of how to implement them, and the authors do so in the last two chapters of the book by giving the applications in various fields. This book also outlines some ideas on when genetic algorithms and genetic programming should be used, and this is useful since a newcomer to the field may be tempted to view a genetic algorithm as merely a fancy Monte Carlo simulation. The most difficult part of using a genetic algorithm is how to encode the population, and the authors discuss various ways to do this. Various "exotic" approaches to improve the performance of genetic algorithms are also discussed such as the "messy" genetic algorithms, adaptive genetic algorithm and hybrid genetic algorithm.

More »»

2007

S. Sumathi and P. Surekha, LabVIEW Based Advanced Instrumentation Systems. Germany: Springer Verlag, 2007.[Abstract]


The book is meant for wide range of readers from College, University Students wishing to learn basic as well as advanced concepts in virtual instrumentation system. It can also be meant for the programmers who may be involved in the programming based on the LabVIEW and virtual instrumentation applications. Virtual Instrumentation System, at present is a well developed field, among academicians as well as between program developers. The various approaches to data transmission, the common interface buses and standards of instrumentation are given in detail. The solutions to the problems in instrumentation are programmed using LabVIEW and the results are given. An overview of LabVIEW with examples is provided for easy reference of the students and professionals. This book also provides research projects, LabVIEW tools, and glossary of virtual instrumentation terms in appendix. The book also presents Application Case Studies on a wide range of connected fields to facilitate the reader for better understanding. This book can be used from Under Graduation to Post-Graduate Level. We hope that the reader will find this book a truly helpful guide and a valuable source of information about the advanced instrumentation principles for their numerous practical applications.

More »»