Node localization, which is formulated as an unconstrained NP-hard optimization problem, is considered as one of the most significant issues of wireless sensor networks (WSNs). Recently, many swarm intelligent algorithms (SIAs) were applied to solve this problem. This study aimed to determine node location with high precision by SIA and presented a new localization algorithm named LMQPDV-hop. In LMQPDV-hop, an improved DV-Hop was employed as an underground mechanism to gather the estimation distance, in which the average hop distance was modified by a defined weight to reduce the distance errors among nodes. Furthermore, an efficient quantum-behaved particle swarm optimization algorithm (QPSO), named LMQPSO, was developed to find the best coordinates of unknown nodes. In LMQPSO, the memetic algorithm (MA) and Lévy flight were introduced into QPSO to enhance the global searching ability and a new fast local search rule was designed to speed up the convergence. Extensive simulations were conducted on different WSN deployment scenarios to evaluate the performance of the new algorithm and the results show that the new algorithm can effectively improve position precision.
Background: The experimental verification of a drug discovery process is expensive and time-consuming. Therefore, efficiently and effectively identifying drug–target interactions (DTIs) has been the focus of research. At present, many machine learning algorithms are used for predicting DTIs. The key idea is to train the classifier using an existing DTI to predict a new or unknown DTI. However, there are various challenges, such as class imbalance and the parameter optimization of many classifiers, that need to be solved before an optimal DTI model is developed.Methods: In this study, we propose a framework called SSELM-neg for DTI prediction, in which we use a screening approach to choose high-quality negative samples and a spherical search approach to optimize the parameters of the extreme learning machine.Results: The results demonstrated that the proposed technique outperformed other state-of-the-art methods in 10-fold cross-validation experiments in terms of the area under the receiver operating characteristic curve (0.986, 0.993, 0.988, and 0.969) and AUPR (0.982, 0.991, 0.982, and 0.946) for the enzyme dataset, G-protein coupled receptor dataset, ion channel dataset, and nuclear receptor dataset, respectively.Conclusion: The screening approach produced high-quality negative samples with the same number of positive samples, which solved the class imbalance problem. We optimized an extreme learning machine using a spherical search approach to identify DTIs. Therefore, our models performed better than other state-of-the-art methods.
21 March 2015 in Neural Computing and Applications