Current Issue : April - June Volume : 2015 Issue Number : 2 Articles : 5 Articles
The complexity and the dynamism of oil spillages make it difficult for planners and responders to produce robust plans towards\ntheir management. There is need for an understanding of the nature, sources, impact and responses required to prevent or control\ntheir occurrence. This paper develops an intelligent hybrid system driven by Sugeno-Type Adaptive Neuro Fuzzy Inference\nSystem (ANFIS) for the identification, extraction and classification of oil spillage risk patterns. Dataset consisting of 1008\nrecords was used for training, validation and testing of the system. Result of sensitivity analysis shows that Cause, Location\nand Type of spilled oil have cumulative significance of 85.1%. Optimal weights of Neural Network (NN) were determined via\nGenetic Algorithm with hybrid encoding scheme. The Mean Squared Error (MSE) of NN training is 0.2405. NN training,\nvalidation and testing results yielded R > 0.839 in all cases indicating a strong linear relationship between each output and\ntarget data. Rule pruning was performed with support (15%) and confidence (10%) minimum thresholds and antecedent-size of\n3. The performance of the ANFIS was evaluated with eight different types of membership functions (MFs) and two learning\nalgorithms. The model with triangular MF gave the best performance among all other given models while hybrid-learning\nalgorithm performed better than back propagation algorithm. The ANFIS model reported in the paper adopted triangular MF\nand hybrid learning algorithm for the predication and classification of oil spillage risk patterns. Average training and testing\nMSE of the model is 0.414315 and 0.221402 respectively. The knowledge mining results show that ANFIS based systems\nprovide satisfactory results in the prediction and classification of oil spillage risk patterns....
Sheila Esmeralda Gonzalez-Reyna, J Fco Martinez-Trinidad, J Ariel Carrasco-Ochoa, J Gabriel Avina-Cervantes,\nSergio Ledesma-Orozco...
We proposed a new Small-World network (called n-Star network in which average path-length L becomes absolutely small)\ninspired by ants� collective behavior. As one of the real-world applications using this network, it is shown that reorganization of\nthe world airline network is possible in the next generation. In addition, it not only has the characteristic that is more immune\nfrom random failure and resilient to targeted attacks than bimodal degree distribution network and scale-free network, but also it\ncan maintain Small-World characteristics even when probability of failure is considerably large. Furthermore, the n-Star network\ncan be extended to various types of hierarchical networks, and we performed theoretical analysis of each network structure and\nderived formulas using various network parameters such as average degree k, average path-length L, clustering coefficient C\nand newly analyzed assortativity (degree correlation) r with the number of star nodes n, their peripheral nodes N0, the total\nnumber of nodes N and the level of hierarchy l. We newly discuss the merit and demerit on the current airline network and an\nairline network based on the n-Star network, and propose a hierarchical architecture of airline network more suitable for real\nworld than both the current airline network and the basic (non-hierarchical) n-Star-based airline network....
This study exposes a critical weakness of the (0-1) knapsack dynamic programming approach, widely used for optimal allocation\nof resources. The (0-1) knapsack dynamic programming approach could waste resources on insignificant improvements and\nprevent the more efficient use of the resources to achieve maximum benefit. Despite the numerous extensive studies, this critical\nshortcoming of the classical formulation has been overlooked. The main reason is that the standard (0-1) knapsack dynamic\nprogramming approach has been devised to maximise the benefit derived from items filling a space with no intrinsic value.\nWhile this is an appropriate formulation for packing and cargo loading problems, in applications involving capital budgeting,\nthis formulation is deeply flawed. The reason is that budgets do have intrinsic value and their efficient utilisation is just as\nimportant as the maximisation of the benefit derived from the budget allocation.\nAccordingly, a new formulation of the (0-1) knapsack resource allocation model is proposed where the weighted sum of the\nbenefit and the remaining budget is maximised instead of the total benefit. The proposed optimisation model produces solutions\nsuperior to both ââ?¬â?? the standard (0-1) dynamic programming approach and the cost-benefit approach.\nOn the basis of common parallel-series systems, the paper also demonstrates that because of synergistic effects, sets including\nthe same number of identical options could remove different amount of total risk. The existence of synergistic effects does\nnot permit the application of the (0-1) dynamic programming approach. In this case, specific methods for optimal resource\nallocation should be applied. Accordingly, the paper formulates and proves a theorem stating that the maximum amount of\nremoved total risk from operations and systems with parallel-series logical arrangement is achieved by using preferentially\nthe available budget on improving the reliability of operations/components belonging to the same parallel branch. Improving\nthe reliability of randomly selected operations/components not forming a parallel branch leads to a sub-optimal risk reduction.\nThe theorem is a solid basis for achieving a significant risk reduction for systems and processes with parallel-series logical\narrangement....
The problem of knowledge acquisition in animals is considered from the point of view of cybernetics. We show that all types\nof animal behavior can be consistently explained on the basis of innate behavior programs and the creation of new behavior\nprograms is logically inconsistent. The hypothesis that all animal behavior is completely innate is proposed. As a possible\nphysical implementation of the storage of congenital programs, we considered quantum entanglement of biologically important\nmolecules. Experiments to test hypotheses are proposed....
Loading....