No abstract

This paper focuses on the feature gene selection for cancer classification, which employs an optimization algorithm to select a subset of the genes. We propose a binary quantum-behaved particle swarm optimization (BQPSO) for cancer feature gene selection, coupling support vector machine (SVM) for cancer classification. First, the proposed BQPSO algorithm is described, which is a discretized version of original QPSO for binary 0-1 optimization problems. Then, we present the principle and procedure for cancer feature gene selection and cancer classification based on BQPSO and SVM with leave-one-out cross validation (LOOCV). Finally, the BQPSO coupling SVM (BQPSO/SVM), binary PSO coupling SVM (BPSO/SVM), and genetic algorithm coupling SVM (GA/SVM) are tested for feature gene selection and cancer classification on five microarray data sets, namely, Leukemia, Prostate, Colon, Lung, and Lymphoma. The experimental results show that BQPSO/SVM has significant advantages in accuracy, robustness, and the number of feature genes selected compared with the other two algorithms.

No abstract

Robust calibration of an agricultural-hydrological model is critical for simulating crop yield and water quality and making reasonable agricultural management. However, calibration of the agricultural-hydrological system models is challenging because of model complexity, the existence of strong parameter correlation, and significant computational requirements. Therefore, only a limited number of simulations can be allowed in any attempt to find a near-optimal solution within an affordable time, which greatly restricts the successful application of the model. The goal of this study is to locate the optimal solution of the Root Zone Water Quality Model (RZWQM2) given a limited simulation time, so as to improve the model simulation and help make rational and effective agricultural-hydrological decisions. To this end, we propose a computationally efficient global optimization procedure using sparse-grid based surrogates. We first used advanced sparse grid (SG) interpolation to construct a surrogate system of the actual RZWQM2, and then we calibrate the surrogate model using the global optimization algorithm, Quantum-behaved Particle Swarm Optimization (QPSO). As the surrogate model is a polynomial with fast evaluation, it can be efficiently evaluated with a sufficiently large number of times during the optimization, which facilitates the global search. We calibrate seven model parameters against five years of yield, drain flow, and-loss data from a subsurface-drained cornsoybean field in Iowa. Results indicate that an accurate surrogate model can be created for the RZWQM2 with a relatively small number of SG points (i.e., RZWQM2 runs). Compared to the conventional QPSO algorithm, our surrogate-based optimization method can achieve a smaller objective function value and better calibration performance using a fewer number of expensive RZWQM2 executions, which greatly improves computational efficiency.

Since the devices in Internet of Things (IoT) are always interconnected with a stable Internet connection, they are prone to attacks. In the grey hole attack, a malicious node acts as a central controller to obtain data from all the nodes and it drops and alters the data packets as per its wish. In this way, the grey hole attack alters the core concept of the IoT, which enables different devices to communicate with each other. To prevent the grey hole attack and enable efficient communication between the IoT devices, a fuzzy concept is introduced in this article. Previous methods have not proficient in spotting uncountable kinds of grey hole attacks. The fuzzy engine identifies the suspicious activity that takes place in the network by the rules generated and identifies the malicious node and stops its function immediately. The simulation experimentation is carried out for accuracy, delay, energy consumption, packet delivery ratio and throughput, and the simulation contrasts with the proposed algorithm, analog behavioral modeling (ABM), and other previous techniques. The proposed system provides an accuracy rate of 45%, a packet delivery ratio of 78%, and reduced energy consumption of 35.6% compared to the previous ABM approach. Simulation outputs showed that the proposed fuzzy grey detection technique is a proficient scheme for detecting grey hole attacks and improving network capability.