Current Issue : January - March Volume : 2019 Issue Number : 1 Articles : 5 Articles
As a novel swarm intelligence algorithm, artificial bee colony (ABC) algorithm inspired by individual division of\nlabor and information exchange during the process of honey collection has advantage of simple structure, less control\nparameters, and excellent performance characteristics and can be applied to neural network, parameter optimization, and so\non. In order to further improve the exploration ability of ABC, an artificial bee colony algorithm with random location\nupdating (RABC) is proposed in this paper, and the modified search equation takes a random location in swarm as\na search center, which can expand the search range of new solution. In addition, the chaos is used to initialize the swarm\npopulation, and diversity of initial population is improved. Then, the tournament selection strategy is adopted to maintain\nthe population diversity in the evolutionary process. Through the simulation experiment on a suite of unconstrained\nbenchmark functions, the results show that the proposed algorithm not only has stronger exploration ability but also has better\neffect on convergence speed and optimization precision, and it can keep good robustness and validity with the increase\nof dimension....
With the advancement of Machine Learning, since its beginning and over the last years, a special attention has been given to the\nArtificial Neural Network. As an inspiration from natural selection of animal groups and humanâ??s neural system, the Artificial\nNeural Network also known as Neural Networks has become the new computational power which is used for solving real world\nproblems. NeuralNetworks alone as a concept involve various methods for achieving their success; thus, this reviewpaper describes\nan overview of such methods called Particle Swarm Optimization, Backpropagation, and Neural Network itself, respectively. A\nbrief explanation of the concepts, history, performances, advantages, and disadvantages is given, followed by the latest researches\ndone on these methods. A description of solutions and applications on various industrial sectors such asMedicine or Information\nTechnology has been provided. The last part briefly discusses the directions, current, and future challenges of Neural Networks\ntowards achieving the highest success rate in solving real world problems....
Objectives: Observational studies suggested that patients with type 2 diabetes mellitus\n(T2DM) presented a higher risk of developing colorectal cancer (CRC). The current study aims\nto create a deep neural network (DNN) to predict the onset of CRC for patients with T2DM.\nMethods: We employed the national health insurance database of Taiwan to create predictive\nmodels for detecting an increased risk of subsequent CRC development in T2DM patients in Taiwan.\nWe identified a total of 1,349,640 patients between 2000 and 2012 with newly diagnosed T2DM.\nAll the available possible risk factors for CRC were also included in the analyses. The data were split\ninto training and test sets with 97.5% of the patients in the training set and 2.5% of the patients in\nthe test set. The deep neural network (DNN) model was optimized using Adam with Nesterovâ??s\naccelerated gradient descent. The recall, precision, F1 values, and the area under the receiver\noperating characteristic (ROC) curve were used to evaluate predictor performance. Results: The F1,\nprecision, and recall values of the DNN model across all data were 0.931, 0.982, and 0.889, respectively.\nThe area under the ROC curve of the DNN model across all data was 0.738, compared to the ideal\nvalue of 1. The metrics indicate that the DNN model appropriately predicted CRC. In contrast,\na single variable predictor using adapted the Diabetes Complication Severity Index showed poorer\nperformance compared to the DNN model. Conclusions: Our results indicated that the DNN model\nis an appropriate tool to predict CRC risk in patients with T2DM in Taiwan....
Artificial fish swarm algorithm easily converges to local optimum, especially in solving the global optimization problem of\nmultidimensional and multiextreme value functions. To overcome this drawback, a novel fish swarm algorithm (LFFSA) based on\nL´evy flight and firefly behavior is proposed. LFFSA incorporates the moving strategy of firefly algorithm into two behavior\npatterns of fish swarm, i.e., chasing behavior and preying behavior. Furthermore, L´evy flight is introduced into the searching\nstrategy. To limit the search band, nonlinear view and step size based on dynamic parameter are considered. Finally, the proposed\nalgorithm LFFSA is validated with several benchmark problems. Numerical results demonstrate that LFFSA has a better performance\nin convergence speed and optimization accuracy than the other test algorithms....
In this paper the analytical and simulation results of probability of detection\nand false alarm of a co-operative cognitive radio network are compared under\nboth awgn and Rayleigh fading environment. After getting the confidence\nlevel of above 95% from the simulation, a neural network (NN) is trained\nwith simulation data where the analytical result is given as the target of the\nNN. Finally the results are verified with the profile of MSE (mean square error)\nof three data set (train, validation and test), regression on data set, confusion\nmatrices and error histogram. Here we use Backpropagation algorithm\nand Hopfield model, all the results yield error of less than 4.5%. The concept\nof paper is applicable at fusion center (FC) to make proper judgment of\npresence of primary user (PU)....
Loading....