Showing papers on "Benchmark (computing) published in 2015"

Rethinking the Inception Architecture for Computer Vision

Abstract: Convolutional networks are at the core of most state-of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains in various benchmarks. Although increased model size and computational cost tend to translate to immediate quality gains for most tasks (as long as enough labeled data is provided for training), computational efficiency and low parameter count are still enabling factors for various use cases such as mobile vision and big-data scenarios. Here we explore ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization. We benchmark our methods on the ILSVRC 2012 classification challenge validation set demonstrate substantial gains over the state of the art: 21.2% top-1 and 5.6% top-5 error for single frame evaluation using a network with a computational cost of 5 billion multiply-adds per inference and with using less than 25 million parameters. With an ensemble of 4 models and multi-crop evaluation, we report 3.5% top-5 error on the validation set (3.6% error on the test set) and 17.3% top-1 error on the validation set.

ActivityNet: A large-scale video benchmark for human activity understanding

Abstract: In spite of many dataset efforts for human action recognition, current computer vision algorithms are still severely limited in terms of the variability and complexity of the actions that they can recognize. This is in part due to the simplicity of current benchmarks, which mostly focus on simple actions and movements occurring on manually trimmed videos. In this paper we introduce ActivityNet, a new large-scale video benchmark for human activity understanding. Our benchmark aims at covering a wide range of complex human activities that are of interest to people in their daily living. In its current version, ActivityNet provides samples from 203 activity classes with an average of 137 untrimmed videos per class and 1.41 activity instances per video, for a total of 849 video hours. We illustrate three scenarios in which ActivityNet can be used to compare algorithms for human activity understanding: untrimmed video classification, trimmed activity classification and activity detection.

Salient Object Detection: A Benchmark

Abstract: We extensively compare, qualitatively and quantitatively, 41 state-of-the-art models (29 salient object detection, 10 fixation prediction, 1 objectness, and 1 baseline) over seven challenging data sets for the purpose of benchmarking salient object detection and segmentation methods. From the results obtained so far, our evaluation shows a consistent rapid progress over the last few years in terms of both accuracy and running time. The top contenders in this benchmark significantly outperform the models identified as the best in the previous benchmark conducted three years ago. We find that the models designed specifically for salient object detection generally work better than models in closely related areas, which in turn provides a precise definition and suggests an appropriate treatment of this problem that distinguishes it from other problems. In particular, we analyze the influences of center bias and scene complexity in model performance, which, along with the hard cases for the state-of-the-art models, provide useful hints toward constructing more challenging large-scale data sets and better saliency models. Finally, we propose probable solutions for tackling several open problems, such as evaluation scores and data set bias, which also suggest future research directions in the rapidly growing field of salient object detection.

Encoding Color Information for Visual Tracking: Algorithms and Benchmark

Abstract: While color information is known to provide rich discriminative clues for visual inference, most modern visual trackers limit themselves to the grayscale realm. Despite recent efforts to integrate color in tracking, there is a lack of comprehensive understanding of the role color information can play. In this paper, we attack this problem by conducting a systematic study from both the algorithm and benchmark perspectives. On the algorithm side, we comprehensively encode 10 chromatic models into 16 carefully selected state-of-the-art visual trackers. On the benchmark side, we compile a large set of 128 color sequences with ground truth and challenge factor annotations (e.g., occlusion). A thorough evaluation is conducted by running all the color-encoded trackers, together with two recently proposed color trackers. A further validation is conducted on an RGBD tracking benchmark. The results clearly show the benefit of encoding color information for tracking. We also perform detailed analysis on several issues, including the behavior of various combinations between color model and visual tracker, the degree of difficulty of each sequence for tracking, and how different challenge factors affect the tracking performance. We expect the study to provide the guidance, motivation, and benchmark for future work on encoding color in visual tracking.

MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking

Abstract: In the recent past, the computer vision community has developed centralized benchmarks for the performance evaluation of a variety of tasks, including generic object and pedestrian detection, 3D reconstruction, optical flow, single-object short-term tracking, and stereo estimation. Despite potential pitfalls of such benchmarks, they have proved to be extremely helpful to advance the state of the art in the respective area. Interestingly, there has been rather limited work on the standardization of quantitative benchmarks for multiple target tracking. One of the few exceptions is the well-known PETS dataset, targeted primarily at surveillance applications. Despite being widely used, it is often applied inconsistently, for example involving using different subsets of the available data, different ways of training the models, or differing evaluation scripts. This paper describes our work toward a novel multiple object tracking benchmark aimed to address such issues. We discuss the challenges of creating such a framework, collecting existing and new data, gathering state-of-the-art methods to be tested on the datasets, and finally creating a unified evaluation system. With MOTChallenge we aim to pave the way toward a unified evaluation framework for a more meaningful quantification of multi-target tracking.

New ways to boost molecular dynamics simulations

Abstract: We describe a set of algorithms that allow to simulate dihydrofolate reductase (DHFR, a common benchmark) with the AMBER all-atom force field at 160 nanoseconds/day on a single Intel Core i7 5960X CPU (no graphics processing unit (GPU), 23,786 atoms, particle mesh Ewald (PME), 8.0 A cutoff, correct atom masses, reproducible trajectory, CPU with 3.6 GHz, no turbo boost, 8 AVX registers). The new features include a mixed multiple time-step algorithm (reaching 5 fs), a tuned version of LINCS to constrain bond angles, the fusion of pair list creation and force calculation, pressure coupling with a "densostat," and exploitation of new CPU instruction sets like AVX2. The impact of Intel's new transactional memory, atomic instructions, and sloppy pair lists is also analyzed. The algorithms map well to GPUs and can automatically handle most Protein Data Bank (PDB) files including ligands. An implementation is available as part of the YASARA molecular modeling and simulation program from www.YASARA.org.

Learning to rank in person re-identification with metric ensembles

Abstract: We propose an effective structured learning based approach to the problem of person re-identification which outperforms the current state-of-the-art on most benchmark data sets evaluated. Our framework is built on the basis of multiple low-level hand-crafted and high-level visual features. We then formulate two optimization algorithms, which directly optimize evaluation measures commonly used in person re-identification, also known as the Cumulative Matching Characteristic (CMC) curve. Our new approach is practical to many real-world surveillance applications as the re-identification performance can be concentrated in the range of most practical importance. The combination of these factors leads to a person re-identification system which outperforms most existing algorithms. More importantly, we advance state-of-the-art results on person re-identification by improving the rank-1 recognition rates from 40% to 50% on the iLIDS benchmark, 16% to 18% on the PRID2011 benchmark, 43% to 46% on the VIPeR benchmark, 34% to 53% on the CUHK01 benchmark and 21% to 62% on the CUHK03 benchmark.

Stochastic Fractal Search

Abstract: Evolutionary Algorithms (EAs) are well-known terms in many science fields. EAs usually interfere with science problems when common mathematical methods are unable to provide a good solution or finding the exact solution requires an unreasonable amount of time. Nowadays, many EA methods have been proposed and developed. Most of them imitate natural behavior, such as swarm animal movement. In this paper, inspired by the natural phenomenon of growth, a new metaheuristic algorithm is presented that uses a mathematic concept called the fractal. Using the diffusion property which is seen regularly in random fractals, the particles in the new algorithm explore the search space more efficiently. To verify the performance of our approach, both the constrained and unconstrained standard benchmark functions are employed. Some classic functions including unimodal and multimodal functions, as well as some modern hard functions, are employed as unconstrained benchmark functions; On the other hand, some well-known engineering design optimization problems commonly used in the literature are considered as constrained benchmark functions. Numerical results and comparisons with other state of the art stochastic algorithms are also provided. Considering both convergence and accuracy simultaneously, experimental results prove that the proposed method performs significantly better than other previous well-known metaheuristic algorithms in terms of avoiding getting stuck in local minimums, and finding the global minimum.

Evaluating Real-Time Anomaly Detection Algorithms -- The Numenta Anomaly Benchmark

Abstract: Much of the world's data is streaming, time-series data, where anomalies give significant information in critical situations, examples abound in domains such as finance, IT, security, medical, and energy. Yet detecting anomalies in streaming data is a difficult task, requiring detectors to process data in real-time, not batches, and learn while simultaneously making predictions. There are no benchmarks to adequately test and score the efficacy of real-time anomaly detectors. Here we propose the Numenta Anomaly Benchmark (NAB), which attempts to provide a controlled and repeatable environment of open-source tools to test and measure anomaly detection algorithms on streaming data. The perfect detector would detect all anomalies as soon as possible, trigger no false alarms, work with real-world time-series data across a variety of domains, and automatically adapt to changing statistics. Rewarding these characteristics is formalized in NAB, using a scoring algorithm designed for streaming data. NAB evaluates detectors on a benchmark dataset with labeled, real-world time-series data. We present these components, and give results and analyses for several open source, commercially-used algorithms. The goal for NAB is to provide a standard, open source framework with which the research community can compare and evaluate different algorithms for detecting anomalies in streaming data.

A Decomposition-Based Evolutionary Algorithm for Many Objective Optimization

Abstract: Decomposition-based evolutionary algorithms have been quite successful in solving optimization problems involving two and three objectives. Recently, there have been some attempts to exploit the strengths of decomposition-based approaches to deal with many objective optimization problems. Performance of such approaches are largely dependent on three key factors: 1) means of reference point generation; 2) schemes to simultaneously deal with convergence and diversity; and 3) methods to associate solutions to reference directions. In this paper, we introduce a decomposition-based evolutionary algorithm wherein uniformly distributed reference points are generated via systematic sampling, balance between convergence and diversity is maintained using two independent distance measures, and a simple preemptive distance comparison scheme is used for association. In order to deal with constraints, an adaptive epsilon formulation is used. The performance of the algorithm is evaluated using standard benchmark problems, i.e., DTLZ1-DTLZ4 for 3, 5, 8, 10, and 15 objectives, WFG1-WFG9, the car side impact problem, the water resource management problem, and the constrained ten-objective general aviation aircraft design problem. Results of problems involving redundant objectives and disconnected Pareto fronts are also included in this paper to illustrate the capability of the algorithm. The study clearly highlights that the proposed algorithm is better or at par with recent reference direction-based approaches for many objective optimization.

A social spider algorithm for global optimization

Abstract: Graphical abstractDisplay Omitted HighlightsWe propose a new nature-inspired social-spider-based swarm intelligence algorithm.We introduce a new social animal foraging model into meta-heuristic design.We introduce the design of information loss to handle pre-mature convergence.We perform a series of benchmark simulations to demonstrate the performance.We investigate the impact of control parameters on optimization results. The growing complexity of real-world problems has motivated computer scientists to search for efficient problem-solving methods. Metaheuristics based on evolutionary computation and swarm intelligence are outstanding examples of nature-inspired solution techniques. Inspired by the social spiders, we propose a novel social spider algorithm to solve global optimization problems. This algorithm is mainly based on the foraging strategy of social spiders, utilizing the vibrations on the spider web to determine the positions of preys. Different from the previously proposed swarm intelligence algorithms, we introduce a new social animal foraging strategy model to solve optimization problems. In addition, we perform preliminary parameter sensitivity analysis for our proposed algorithm, developing guidelines for choosing the parameter values. The social spider algorithm is evaluated by a series of widely used benchmark functions, and our proposed algorithm has superior performance compared with other state-of-the-art metaheuristics.

The ManyBugs and IntroClass Benchmarks for Automated Repair of C Programs

Abstract: The field of automated software repair lacks a set of common benchmark problems. Although benchmark sets are used widely throughout computer science, existing benchmarks are not easily adapted to the problem of automatic defect repair, which has several special requirements. Most important of these is the need for benchmark programs with reproducible, important defects and a deterministic method for assessing if those defects have been repaired. This article details the need for a new set of benchmarks, outlines requirements, and then presents two datasets, ManyBugs and IntroClass , consisting between them of 1,183 defects in 15 C programs. Each dataset is designed to support the comparative evaluation of automatic repair algorithms asking a variety of experimental questions. The datasets have empirically defined guarantees of reproducibility and benchmark quality, and each study object is categorized to facilitate qualitative evaluation and comparisons by category of bug or program. The article presents baseline experimental results on both datasets for three existing repair methods, GenProg, AE, and TrpAutoRepair, to reduce the burden on researchers who adopt these datasets for their own comparative evaluations.

Real-Time Pedestrian Detection With Deep Network Cascades

Abstract: We present a new real-time approach to object detection that exploits the efficiency of cascade classifiers with the accuracy of deep neural networks. Deep networks have been shown to excel at classification tasks, and their ability to operate on raw pixel input without the need to design special features is very appealing. However, deep nets are notoriously slow at inference time. In this paper, we propose an approach that cascades deep nets and fast features, that is both very fast and very accurate. We apply it to the challenging task of pedestrian detection. Our algorithm runs in real-time at 15 frames per second. The resulting approach achieves a 26.2% average miss rate on the Caltech Pedestrian detection benchmark, which is competitive with the very best reported results. It is the first work we are aware of that achieves very high accuracy while running in real-time.

Characterization of a Benchmark Database for Myoelectric Movement Classification

Abstract: In this paper, we characterize the Ninapro database and its use as a benchmark for hand prosthesis evaluation. The database is a publicly available resource that aims to support research on advanced myoelectric hand prostheses. The database is obtained by jointly recording surface electromyography signals from the forearm and kinematics of the hand and wrist while subjects perform a predefined set of actions and postures. Besides describing the acquisition protocol, overall features of the datasets and the processing procedures in detail, we present benchmark classification results using a variety of feature representations and classifiers. Our comparison shows that simple feature representations such as mean absolute value and waveform length can achieve similar performance to the computationally more demanding marginal discrete wavelet transform. With respect to classification methods, the nonlinear support vector machine was found to be the only method consistently achieving high performance regardless of the type of feature representation. Furthermore, statistical analysis of these results shows that classification accuracy is negatively correlated with the subject's Body Mass Index. The analysis and the results described in this paper aim to be a strong baseline for the Ninapro database. Thanks to the Ninapro database (and the characterization described in this paper), the scientific community has the opportunity to converge to a common position on hand movement recognition by surface electromyography, a field capable to strongly affect hand prosthesis capabilities.

On global optimization

Abstract: This paper presents a relatively ―unfettered‖ practical method for finding global optima to constrained nonlinear programs. The method reformulates the given program into a bi-objective mixed-integer program that is then solved for the Nash equilibrium. A numerical example is included to illustrate the efficacy of the method; the solution computed is a benchmark against which other algorithms may be assessed.

The EPFL Combinational Benchmark Suite

Abstract: In this paper, we present the EPFL combinational benchmark suite. We aim at completing existing benchmark suites by focusing only on natively combinational benchmarks. The EPFL combinational benchmark suite consists of 23 combinational circuits designed to challenge modern logic optimization tools. It is further divided into three parts. The first part includes 10 arithmetic benchmarks, e.g., square-root, hypotenuse, divisor, multiplier etc.. The second part consists of 10 random/control benchmarks, e.g., round-robin arbiter, lookahead XY router, alu control unit, memory controller etc.. The third part contains 3 very large circuits, featuring more than ten million gates each. All benchmarks have a moderate number of inputs/outputs ranging from few tens to about one thousand. The EPFL benchmark suite is available to the public and distributed in all Verilog, VHDL, BLIF and AIGER formats. In addition to providing the benchmarks, we keep track of the best optimization results, mapped into LUT-6, for size and depth metrics. Better logic implementations can be submitted online. After combinational equivalence checking tests, the best LUT-6 realizations will be included in the benchmark suite together with the author’s name and affiliation.

A comparison and evaluation of map construction algorithms using vehicle tracking data

Abstract: Map construction methods automatically produce and/or update street map datasets using vehicle tracking data. Enabled by the ubiquitous generation of geo-referenced tracking data, there has been a recent surge in map construction algorithms coming from different computer science domains. A cross-comparison of the various algorithms is still very rare, since (i) algorithms and constructed maps are generally not publicly available and (ii) there is no standard approach to assess the result quality, given the lack of benchmark data and quantitative evaluation methods. This work represents a first comprehensive attempt to benchmark such map construction algorithms. We provide an evaluation and comparison of seven algorithms using four datasets and four different evaluation measures. In addition to this comprehensive comparison, we make our datasets, source code of map construction algorithms and evaluation measures publicly available on http://mapconstruction.org. . This site has been established as a repository for map construction data and algorithms and we invite other researchers to contribute by uploading code and benchmark data supporting their contributions to map construction algorithms.

Fixed Point Quantization of Deep Convolutional Networks

Abstract: In recent years increasingly complex architectures for deep convolution networks (DCNs) have been proposed to boost the performance on image recognition tasks. However, the gains in performance have come at a cost of substantial increase in computation and model storage resources. Fixed point implementation of DCNs has the potential to alleviate some of these complexities and facilitate potential deployment on embedded hardware. In this paper, we propose a quantizer design for fixed point implementation of DCNs. We formulate and solve an optimization problem to identify optimal fixed point bit-width allocation across DCN layers. Our experiments show that in comparison to equal bit-width settings, the fixed point DCNs with optimized bit width allocation offer >20% reduction in the model size without any loss in accuracy on CIFAR-10 benchmark. We also demonstrate that fine-tuning can further enhance the accuracy of fixed point DCNs beyond that of the original floating point model. In doing so, we report a new state-of-the-art fixed point performance of 6.78% error-rate on CIFAR-10 benchmark.

UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking

Abstract: In recent years, numerous effective multi-object tracking (MOT) methods are developed because of the wide range of applications. Existing performance evaluations of MOT methods usually separate the object tracking step from the object detection step by using the same fixed object detection results for comparisons. In this work, we perform a comprehensive quantitative study on the effects of object detection accuracy to the overall MOT performance, using the new large-scale University at Albany DETection and tRACking (UA-DETRAC) benchmark dataset. The UA-DETRAC benchmark dataset consists of 100 challenging video sequences captured from real-world traffic scenes (over 140,000 frames with rich annotations, including occlusion, weather, vehicle category, truncation, and vehicle bounding boxes) for object detection, object tracking and MOT system. We evaluate complete MOT systems constructed from combinations of state-of-the-art object detection and object tracking methods. Our analysis shows the complex effects of object detection accuracy on MOT system performance. Based on these observations, we propose new evaluation tools and metrics for MOT systems that consider both object detection and object tracking for comprehensive analysis.

Two-Objective Design of Benchmark Problems of a Water Distribution System via MOEAs: Towards the Best-Known Approximation of the True Pareto Front

Abstract: Various multiobjective evolutionary algorithms (MOEAs) have been applied to solve the optimal design problems of a water distribution system (WDS). Such methods are able to find the near-optimal trade-off between cost and performance benefit in a single run. Previously published work used a number of small benchmark networks and/or a few large, real-world networks to test MOEAs on design problems of WDS. A few studies also focused on the comparison of different MOEAs given a limited computational budget. However, no consistent attempt has been made before to investigate and report the best-known approximation of the true Pareto front (PF) for a set of benchmark problems, and thus there is not a single point of reference. This paper applied 5 state-of-the-art MOEAs, with minimum time invested in parameterization (i.e., using the recommended settings), to 12 design problems collected from the literature. Three different population sizes were implemented for each MOEA with respect to the scale of eac...

SparkBench: a comprehensive benchmarking suite for in memory data analytic platform Spark

Abstract: Spark has been increasingly adopted by industries in recent years for big data analysis by providing a fault tolerant, scalable and easy-to-use in memory abstraction. Moreover, the community has been actively developing a rich ecosystem around Spark, making it even more attractive. However, there is not yet a Spark specify benchmark existing in the literature to guide the development and cluster deployment of Spark to better fit resource demands of user applications. In this paper, we present SparkBench, a Spark specific benchmarking suite, which includes a comprehensive set of applications. SparkBench covers four main categories of applications, including machine learning, graph computation, SQL query and streaming applications. We also characterize the resource consumption, data flow and timing information of each application and evaluate the performance impact of a key configuration parameter to guide the design and optimization of Spark data analytic platform.

The results of the pantograph catenary interaction benchmark

Abstract: This paper describes the results of a voluntary benchmark initiative concerning the simulation of pantograph-catenary interaction, which was proposed and coordinated by Politecnico di Milano and pa ...

SparkNet: Training Deep Networks in Spark

Abstract: Training deep networks is a time-consuming process, with networks for object recognition often requiring multiple days to train. For this reason, leveraging the resources of a cluster to speed up training is an important area of work. However, widely-popular batch-processing computational frameworks like MapReduce and Spark were not designed to support the asynchronous and communication-intensive workloads of existing distributed deep learning systems. We introduce SparkNet, a framework for training deep networks in Spark. Our implementation includes a convenient interface for reading data from Spark RDDs, a Scala interface to the Caffe deep learning framework, and a lightweight multi-dimensional tensor library. Using a simple parallelization scheme for stochastic gradient descent, SparkNet scales well with the cluster size and tolerates very high-latency communication. Furthermore, it is easy to deploy and use with no parameter tuning, and it is compatible with existing Caffe models. We quantify the dependence of the speedup obtained by SparkNet on the number of machines, the communication frequency, and the cluster's communication overhead, and we benchmark our system's performance on the ImageNet dataset.

General Program Synthesis Benchmark Suite

Abstract: Recent interest in the development and use of non-trivial benchmark problems for genetic programming research has highlighted the scarcity of general program synthesis (also called "traditional programming") benchmark problems. We present a suite of 29 general program synthesis benchmark problems systematically selected from sources of introductory computer science programming problems. This suite is suitable for experiments with any program synthesis system driven by input/output examples. We present results from illustrative experiments using our reference implementation of the problems in the PushGP genetic programming system. The results show that the problems in the suite vary in difficulty and can be useful for assessing the capabilities of a program synthesis system.

Distributed Time-Sensitive Task Selection in Mobile Crowdsensing

Abstract: With the rich set of embedded sensors installed in smartphones and the large number of mobile users, we witness the emergence of many innovative commercial mobile crowdsensing applications that combine the power of mobile technology with crowdsourcing to deliver time-sensitive and location-dependent information to their customers. Motivated by these real-world applications, we consider the task selection problem for heterogeneous users with different initial locations, movement costs, movement speeds, and reputation levels. Computing the social surplus maximization task allocation turns out to be an NP-hard problem. Hence we focus on the distributed case, and propose an asynchronous and distributed task selection (ADTS) algorithm to help the users plan their task selections on their own. We prove the convergence of the algorithm, and further characterize the computation time for users' updates in the algorithm. Simulation results suggest that the ADTS scheme achieves the highest Jain's fairness index and coverage comparing with several benchmark algorithms, while yielding similar user payoff to a greedy centralized benchmark. Finally, we illustrate how mobile users coordinate under the ADTS scheme based on some practical movement time data derived from Google Maps.

Potential and limits of numerical modelling for supporting the development of HTS devices

Abstract: In this paper, we present a general review of the status of numerical modelling applied to the design of high temperature superconductor devices. The importance of this tool is emphasized at the beginning of the paper, followed by formal definitions of the notions of models, numerical methods and numerical models. The state-of-the-art models are listed, and the main limitations of existing numerical models are reported. Those limitations are shown to concern two aspects: on the one hand, the numerical performance (i.e. speed) of the methods themselves is not good enough yet; on the other hand, the availability of model file templates, material data and benchmark problems is clearly insufficient. Paths for improving those elements are indicated in the paper. Besides the technical aspects of the research to be further pursued, for instance in adaptive numerical methods, most recommendations command for an increased collective effort for sharing files, data, codes and their documentation.

A self-optimization approach for L-SHADE incorporated with eigenvector-based crossover and successful-parent-selecting framework on CEC 2015 benchmark set

Abstract: A self-optimization approach and a new success-history based adaptive differential evolution with linear population size reduction (L-SHADE) which is incorporated with an eigenvector-based (EIG) crossover and a successful-parent-selecting (SPS) framework are proposed in this paper. The EIG crossover is a rotationally invariant operator which provides superior performance on numerical optimization problems with highly correlated variables. The SPS framework provides an alternative of the selection of parents to prevent the situation of stagnation. The proposed SPS-L-SHADE-EIG combines the L-SHADE with the EIG and SPS frameworks. To further improve the performance, the parameters of SPS-L-SHADE-EIG are self-optimized in terms of each function under IEEE Congress on Evolutionary Computation (CEC) benchmark set in 2015. The stochastic population search causes the performance of SPS-L-SHADE-EIG noisy, and therefore we deal with the noise by re-evaluating the parameters if the parameters are not updated for more than an unacceptable amount of times. The experiment evaluates the performance of the self-optimized SPS-L-SHADE-EIG in CEC 2015 real-parameter single objective optimization competition.